diff --git a/.gitattributes b/.gitattributes index c7d9f3332a950355d5a77d85000f05e6f45435ea..3fc658e0d2c8ffda2ba2a8aee195887130fb2604 100644 --- a/.gitattributes +++ b/.gitattributes @@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +*/evaluation/generation/examples*jsonl filter=lfs diff=lfs merge=lfs -text diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..216106e859fd037ec098805d33bafb633fcd725e --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff3a78c5a2a31569b5cb92537ad8e2c05b7db630862b956d977688eb30793418 +size 27478295 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..848f9f0900e28029d7fa3a02997796ae54ffede0 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bab3471ed6b2252acf5cefb05845db4d468f33a2ee2ef7fce569ecb6f3885dc +size 27478306 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0b37abe18517b558d7592478dce937257273b866 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96a2c0c2d6facee8ee787eb5a996c9430912f260f6144cdf3e6c245e98017d40 +size 27478242 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d6fea2729d3ab899527abdb303861f932ff5e869 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4569e6d36285f6c9820df600da7fb9d0aec62b4d3968b34ce52e3c481ad255e5 +size 27478242 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..eee6f58ce631e964ff70f5611a4642cc9b54c773 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b672bf570b0eed03c707240a63b409c025647619de7451d1cdfab1e277f07398 +size 27478178 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5465cfead840c04ad303d037709bb40ffee02110 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:278b795b8f6d5c58ef37cc76a1b413008eff2a927aa07ebd85eb3d4ec45255a9 +size 27478370 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..adc38dbba73563cd6a57d8cb348ff22d064eede3 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b07c287d0d4ac467b5b810a79e41ec4409d72f2c2ace763084bf7c943e47f682 +size 27478178 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..541a252715f3fa71101fefb06b4424c28fa251f5 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5365cddafcb5d0c3f5eb6ba0862cc685a7bce781a6596f0677a4117d0a8a87f7 +size 27478306 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..de6aed6cf84b542cf700852f3fb145427ec885cd --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fc27e29d9a4b9838d1ce2ded445d04c8ee0a69e1881980eafedab5ef5aa7e4d +size 27478306 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a38511409bd609c9e641c4a253f6598a0dd23fa8 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bf339c74a82f84ce76e763eeb94ccb4ad1ce36bc90c5012e673e186b05a3b44 +size 27478242 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8f50e71c9bc1dbb3b269cbf3eff36eb1f133f3a0 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bd8a4de3c06146a579e7de1d764605f5954c9e0666dd36adfabb0120cf2d2cb +size 27478306 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1f0c51696c3c4a93594f9b47b9eea7cbd4a0f705 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23e17bee47b9f63beb7778521eda84ba7e4f7ca8dfe41f3581ec132308ecf64d +size 27478231 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8ae543e3a506ab4db4249b99e6fc6f11a051e529 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71718fa07df1e081c1646378a0acd68dd5998ca261d105d285e6620f683e5876 +size 27478178 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a385ed45712587fdd5563f522bc669cb576e40b3 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41da246e9a256132653e2ad52718c6499a2ea39cc7035a006f75390ac2a5eab8 +size 27478242 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ee1488c23e5b67433e9df4865278c89afcfe2321 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f129d469069b7188ecc6a93ea27fdad3e5a002185e696ce9f4768e231a68b21 +size 27478242 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..be0d08e11bc5d6ac7341c98a1d039fcf77f240e7 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:031abfe7c4ecd85326e1f83f7eda63a012cbb1de3fcbd2f947601cb3e30ee0e4 +size 27478306 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7d513ed8cc69bc25043573219eab30b0a8dd1eac --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18f958725995fd87558a985dd62cad34081f554450fc320cf97d26fbf0f9474f +size 27478178 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c4dd4d9b7aff9c8cf802c14e7cf39900e9c3f9ed --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04a81b7f70f68dc19c108c62191bb56f15ba0821b741b85e7686d6ec3835f973 +size 27478370 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c48718c0430768828bcf98c4f2ba3491efb2987e --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:317622aa197f152665e44d0368be2b41e72da25db831b168ae3f0ed4362b4454 +size 27478178 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c341e104fc4adb22b487b18604de1ca2a132b0a6 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bae2e77542f10594db60985aea753e6e8a9ce0276250227ed5ee91e5d467af2 +size 27478370 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4a1b58bc5aa4b4d068cbc8e363d05d64c08cad90 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5481ffc980257e5e1b6b306aee484668c5c815a33902182fced9bc960d64d8c0 +size 27478242 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5d89671ef5c97d3a9a85f8f6effb186bc2b140b6 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f96bb83afc3fff9b289a20f62e813d1f54ae26838b1890e0eb4f7839567835fd +size 27478370 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..47c7f62580c03b30e8a99ca8cedc3acff59493ce --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f75aba9de4014e978d48fcc22c4e87dd7cdd451281776a83f2013edb144e8c3 +size 27478231 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..26cf6789db77ad4a0ff53d14a34ae174f869e994 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c93c8c4cbbee7727c874812d8f6db28bec1d4f1e46c001700cbe711de9356958 +size 27478242 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..37207be46b6259c8579d45cf4af957e2db3ced7b --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:983b02a6ae63fc9cf5c7890a9bbe5c9804549b3dd9f7c7852546bba1d5eb0682 +size 27478370 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d0ab924c6d6370637d8a135c81911ab78e0e0f08 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84f6963473d6288012e7af39c5526d233e5c05a5dec96b44cd1e4993cb6e1f1a +size 27478178 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..99a3c8e4a1f306e581c282788d6874c8b1844c8d --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f467db91a2fbbba20e0d9bc006ab08bf104f380e44a20b69d928b40d7371ba6 +size 27478370 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9d05f120ce5f324691d73f9838346aa8834ad21f --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4623c4ed1e39689d21fce87f563af0eb00091942e0d2e03b0a5c0b81771db501 +size 27478306 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..309312dc0da9cffa6694fc42df35318a5ff80204 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58f8edabf0f3b895ff87168025fed7473c611e409fbba8f4e3cc3e4d7e534c6f +size 27478242 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8c6d9cf43209151c9f5eef2a9153337258f87c2b --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1c762811da3e3d31ec679bb0c7b6514d8a32b543d6b3b8c6d207ab2b9ad7700 +size 27478306 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0b1fbafeba3369913b00f348a3ba019617936fa9 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85a7239fc2babfffd01a029be9d9c1c57f76fd3bd1ddc825e0f25dcd8cef17a7 +size 27478114 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1bc910ba6186be7ef505a80ae451af8f02a3446b --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae2e8f431151172af847dbc53ab9baaa8a16b8496f186eba01193586de0c4fec +size 27478306 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5803462a2e80dcb09600cd7bdf09965d64b7aed8 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7920bf5d39e8787dde250cccc07614616dc09ce885274f7376a309c66416e754 +size 27478434 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..aa42bfe84f430a5599fcb16eb80fb6a05d35aaf1 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4235e770ffaee4eb666f81af2552054c5739bd18b94e9d4635689be1c7150432 +size 27478167 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..29d36f091807e26475c8f608fea7fa68590e3659 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1144d67f8dfb73e00cd595670a03e2127ef0f1eb88ae1a3da4c0beb59d1f3ae1 +size 27478242 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ea1ed3e49dfdcb918d807bf3ea43f482a7ddb548 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5760fc8e99d59618f9ef2e00814864d0a65b05caf67339e7acd883bc9e6dfa53 +size 27478306 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..745f576ab804adec343f6e2a64983268cc5461f7 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4134249d39ffca3a96202a861cd4a522a4dcefc35a52976b3a853ca09e9080e1 +size 27478306 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..91f1dedd067d4ac5302877c77617d2b415eb81c5 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cffd936e100ed3e6b666a62592473fcd8476eb752bf492881dd2cb049f837d5a +size 27478178 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4bc3308b4a7afdf57f5e43c949b12609abd1c365 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48bf9a4f3e21cf236118257ad639d1ca151fd979baaba95d6fbecc7f5ed4325b +size 27478434 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3e67c769d69fd376900f9dbc9877d584ff37c74f --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2be37d6b30af126907d7e190f258355d93226a237e08b3a02a36cf6dcac6d7f8 +size 27478050 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3ee7a5593455926602c1f03ce18e9205dcd6164e --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99e02bfd6741b0ad5903686857efe1ab160231b6d44829058e120c3fd33f0d61 +size 27478306 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a733af74c226697bffe3d75c2f825e9bbbf288f4 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c8e1bafab7ad5bc188ff8a65eeefe940c4e7348bce9c7741c61699a08c56eda +size 27478306 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..41c99224a7bf9b07025d21390c570953b6480130 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c22985bde0ac110f2eadc7775d3b9a94412f1f201708f9118b5ff3a559709752 +size 27478306 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b9a66a127cdbb89a5311938784422bde8a16f815 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae4ae10283d00926515d796fef572ff00d87805417e95ec97da0089b1b0e95f5 +size 27478370 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e27fdcb73a58cce57505fda9f4a1085ee59cda7b --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51387e0331ff9f9755511026493d65f711a24d0a9d6fd2d9db63e81982e29909 +size 27478231 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9fa4026aba6c10726508b187f617dd67d0a4d84c --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55df81d8ee43fe7a5e43d2a8698292710b0724f1e39c5c9c48b5a578d6a1454f +size 27478242 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b912997e406af7e5aba3cb5ecb8253a994f23d64 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39298feda77f416fb61d1dc08752ea5052f172fe0111c68991d475e9cd7052fa +size 27478242 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a69758501c8e875b4c0e2d9dd12e46cbbd9c0e2d --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2543095d76fd7741265376756db53e6335ef39ca255b47e29ecee5ccbd40da1 +size 27478434 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..543d9d5d9adfcc4603059ca4e571e9c664939519 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd9f4630e6a81c8d3b09b4f266f3ccf9f9930f57240d4c397fff9cce206718f3 +size 27478178 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..abc43cbebc9c4265f508ea3da622824b3d140d15 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11b4ff0c2df6a7e52d168c95d811e3b8062bc665df7da42c0d685e0bb9ceb50e +size 27478306 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ecf4d5a6a83446d2a5dc7172b976e35b0e9743ec --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:182b2a7c63634f52134c5c31ef3377b6b3ea65e6a5dd4e9d0603a1fc6a597303 +size 27478306 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0fe5cc39d80dbdf1f242ef2f032d20649103b02a --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0da43ebc620b8df669f3d2fc4397fff2c536ea6f3e6f65449bc227b3e4adf1d +size 27478306 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..979ade244f1fe65d3e26803360b41d7c142eae02 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af74b148afacb9450add0951a98339cf2fbddc0e63c91bf9afe8d2f78a477e44 +size 27478370 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f88fb8bbd473816f20a0e7b3231533cfe7bd894c --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae8b31278d8552a8b1c9d37a1d4a011f7107eaccce947e52366eb67920382d56 +size 27478242 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1c387e067b3ac089700581026a9f66eaf2021611 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc04fa3d80de548ee2007ac884e9853bc2a7a015b3a48380371b73edcc503008 +size 27478370 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cc2a0fb35bb94b4094304728ef092321128b1770 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f10edd8c5744ec6053f3ad26b80bb5bb1a17d69151cbddae15a672a8cff7cc5e +size 27478167 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d9379c345f3ae5a4b56b4ac0360954b42139138a --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5199456b8fde5799190ae4fa3165e5ad9673aa879e440f31c32a8c25d47ebda4 +size 27478178 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5f482a90fe1c3a5864d3d0c458ca26f4fbb81a43 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21d792a053025b46bffdb73bacfa40c0712a94c0dfb363ac7081b3cd925dec35 +size 27478370 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..224747d57b129e5f42ef5ff64c3455e7fa3533bd --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30d837ecd18f212742ff16a6eec4ed22c013ee792a4858347c510a5ead6fd2e4 +size 27478178 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c4fd533de549aca99916388849b7bee26069fb69 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:290b153789d4286d13f023df9e8e92e68f88c70ac08c28d913dd95c620988970 +size 27478242 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..38b908431e9a2782eb14f7aff7182566c3b9b3a1 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8cdace3f417af39a3e1dd57efb4e0e0cfc0c722fb082657d0fb4781efac3c31 +size 27478359 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b31c46eba57c027b1d587c4bc6cd2d523d504da4 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:959ed3ee1a17b8d337c5011ab512590152bc309101b2c04b7c3eb1d505c523fe +size 27478103 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e0a85c81847a9f41aa3a758b23e93802130c5963 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:685b46cd2288c78e194c2faf1dd3b36e412c4a086fa8fb52eee27ce6d169c57d +size 27478359 diff --git a/146m14b14b/global_step21553/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt b/146m14b14b/global_step21553/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..86f41b2dccf6176db92ad962e49c85f02900e6b4 --- /dev/null +++ b/146m14b14b/global_step21553/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55824b653be365883cbe67d0e2718237ca05c2059b360ff18898ead281d09fc9 +size 27478167 diff --git a/146m14b14b/global_step21553/layer_01-model_00-model_states.pt b/146m14b14b/global_step21553/layer_01-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..358207c6483634e7894166744bc16d505e33a6a1 --- /dev/null +++ b/146m14b14b/global_step21553/layer_01-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c90d25d980b708368474fc3be8a5e473b0497a597edbc69bd7462a3431b64e5 +size 80413955 diff --git a/146m14b14b/global_step21553/layer_03-model_00-model_states.pt b/146m14b14b/global_step21553/layer_03-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4e3c87b1b1d65b84be8a65032c0ec520d062b217 --- /dev/null +++ b/146m14b14b/global_step21553/layer_03-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:628ec300f7a85d1c18ea3ea2e991fd6a35f6dd04b06cce1a931c7a058c4647ce +size 14180099 diff --git a/146m14b14b/global_step21553/layer_04-model_00-model_states.pt b/146m14b14b/global_step21553/layer_04-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8b70b59e719a759266d2941a4301a9f20c4d6d90 --- /dev/null +++ b/146m14b14b/global_step21553/layer_04-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b69e42b5f6b613d536f70344ba7a012354cab35cd175c7b85c9673c31332dc5f +size 14180099 diff --git a/146m14b14b/global_step21553/layer_05-model_00-model_states.pt b/146m14b14b/global_step21553/layer_05-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..196fe1c23f50ec3054ac82f6cf674ac10e862308 --- /dev/null +++ b/146m14b14b/global_step21553/layer_05-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6006b69df262e9ee301b18bb05d0509f455f5e12e18b6e6b2dfd7c15fbfc9133 +size 14180099 diff --git a/146m14b14b/global_step21553/layer_06-model_00-model_states.pt b/146m14b14b/global_step21553/layer_06-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3bc617cc5e2d3fe0c183d0fdc81e3ec42d4b7917 --- /dev/null +++ b/146m14b14b/global_step21553/layer_06-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5faa7a35a509f9703df4ae93477a922466ea92ea79bb37969a0e5fe5186e97bf +size 14180099 diff --git a/146m14b14b/global_step21553/layer_07-model_00-model_states.pt b/146m14b14b/global_step21553/layer_07-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a793b608186fec06e77edcae4f8c3759342974fd --- /dev/null +++ b/146m14b14b/global_step21553/layer_07-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecf46ce5a80e22f6549bb2911f376c40049f48348909566a715f5db5bdae62ff +size 14180099 diff --git a/146m14b14b/global_step21553/layer_08-model_00-model_states.pt b/146m14b14b/global_step21553/layer_08-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e0a6e5300131f59e924c5b4ecfe199b99c3bf32c --- /dev/null +++ b/146m14b14b/global_step21553/layer_08-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a11735523169a153c0c3ec7717e132c9d076c94d19f9f28855a52f71ec8db6e9 +size 14180099 diff --git a/146m14b14b/global_step21553/layer_09-model_00-model_states.pt b/146m14b14b/global_step21553/layer_09-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4d60e60e617435c72dba68a6845af202eea83827 --- /dev/null +++ b/146m14b14b/global_step21553/layer_09-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33880ca46340ef2a6dd18c04669aed973d445466aff3b95f4d2532a7182bdd73 +size 14180099 diff --git a/146m14b14b/global_step21553/layer_10-model_00-model_states.pt b/146m14b14b/global_step21553/layer_10-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4fccc8bd754038ec932cb0d52dc085260fe783ec --- /dev/null +++ b/146m14b14b/global_step21553/layer_10-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdc784d366599bc03b984abf39a24ae188177668953a4ab14ad228711279c29b +size 14180099 diff --git a/146m14b14b/global_step21553/layer_11-model_00-model_states.pt b/146m14b14b/global_step21553/layer_11-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4273bb4eb173eda08acbefbb50dd149c697e7c6a --- /dev/null +++ b/146m14b14b/global_step21553/layer_11-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e4eb047c942756e4d2b21bb20d7b9c1549cd82d383f088abe793bbeba65c34a +size 14180099 diff --git a/146m14b14b/global_step21553/layer_12-model_00-model_states.pt b/146m14b14b/global_step21553/layer_12-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..41ca58b6e6b3e8764a2f853edb33d7a2fd646e09 --- /dev/null +++ b/146m14b14b/global_step21553/layer_12-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3380b9f7ca3eb91d66361d99706e693dfb17a56c197e8f5bab6e09f379e03011 +size 14180099 diff --git a/146m14b14b/global_step21553/layer_13-model_00-model_states.pt b/146m14b14b/global_step21553/layer_13-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..561baef55323e72ed1a2a7d3536328a0ecb1f80c --- /dev/null +++ b/146m14b14b/global_step21553/layer_13-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41b0113e0941efc096de32cee996141a1d37b2bcccbf649a2bb039d33415a426 +size 14180099 diff --git a/146m14b14b/global_step21553/layer_14-model_00-model_states.pt b/146m14b14b/global_step21553/layer_14-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b7e2ffef1fd5022533531c633c0c48e8cf1b9b2f --- /dev/null +++ b/146m14b14b/global_step21553/layer_14-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e75dc9da569e15b73019784af49e0d59b03533871a5cb7857bc2960431ff2a7f +size 14180099 diff --git a/146m14b14b/global_step21553/layer_15-model_00-model_states.pt b/146m14b14b/global_step21553/layer_15-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c5ebb266617e35a0ed2d2e0787136b9908ee85a3 --- /dev/null +++ b/146m14b14b/global_step21553/layer_15-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3cf8ab2d2ef52c6ab5e0f11eb96f30fc5d2a54247b05302d51adfbbc3e4996c +size 14180099 diff --git a/146m14b14b/global_step21553/layer_16-model_00-model_states.pt b/146m14b14b/global_step21553/layer_16-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3d1be3ded254d94c5c5626149b4529d94063c4b9 --- /dev/null +++ b/146m14b14b/global_step21553/layer_16-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:920dc376e24fe0cf24164a16a08562ce8437231c6c1f31fe8f3163011d287f81 +size 14180099 diff --git a/146m14b14b/global_step21553/layer_17-model_00-model_states.pt b/146m14b14b/global_step21553/layer_17-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c26068ad750ee8f1d5debccd32e8b326f7134aa1 --- /dev/null +++ b/146m14b14b/global_step21553/layer_17-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad62b71eb796fdd6286516c7203e4ba22eddc4d2f490e4c25fa380b0e60fd081 +size 14180099 diff --git a/146m14b14b/global_step21553/layer_19-model_00-model_states.pt b/146m14b14b/global_step21553/layer_19-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..460932f80abba7970f921dffa61058c1e641a926 --- /dev/null +++ b/146m14b14b/global_step21553/layer_19-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b8ac64624f156b77f7d079787dc8a830e831c72b8685987863ce1655c169966 +size 4291 diff --git a/146m14b14b/global_step21553/mp_rank_00_model_states.pt b/146m14b14b/global_step21553/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..54b4b4c03b58b2dfc79012a00c8a72f812744e9c --- /dev/null +++ b/146m14b14b/global_step21553/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51beebf4affa8e4ff1aa257ba93b6679c39cc26e8477562540b49224ab141a76 +size 35187 diff --git a/146m14b14b/launch.sh b/146m14b14b/launch.sh new file mode 100755 index 0000000000000000000000000000000000000000..6c3445845a5dae614feb4b8a1206322cd7bd9050 --- /dev/null +++ b/146m14b14b/launch.sh @@ -0,0 +1,53 @@ +#!/bin/bash + +# Launch script using torch.distributed.run(). Used by slurm +# scripts, don't invoke directly. + +# Samuel's fix for apparent error in SLURM initialization +if [ $SLURM_LOCALID -eq 0 ]; then + rm -rf /dev/shm/* + rocm-smi || true +else + sleep 2 +fi + +export NCCL_SOCKET_IFNAME=hsn0,hsn1,hsn2,hsn3 +export OMP_NUM_THREADS=$SLURM_CPUS_PER_TASK +export FI_CXI_DEFAULT_CQ_SIZE=131072 + +# debugging (noisy) +#export NCCL_DEBUG=INFO +#export RCCL_KERNEL_COLL_TRACE_ENABLE=1 +#export NCCL_DEBUG_SUBSYS=INIT,COLL + +module --quiet purge +module load cray-python + +module load CrayEnv +module load PrgEnv-cray/8.3.3 +module load craype-accel-amd-gfx90a +module load cray-python + +module use /pfs/lustrep2/projappl/project_462000125/samantao-public/mymodules +module load suse-repo-deps/sam-default +module load rocm/sam-5.2.3.lua +module load rccl/sam-develop.lua +module load aws-ofi-rccl/sam-default.lua + +source venv/bin/activate + +MASTER_NODE=$(scontrol show hostnames "$SLURM_JOB_NODELIST" | head -n 1) +MASTER_PORT=9999 + +echo "Launching on $SLURMD_NODENAME ($SLURM_PROCID/$SLURM_JOB_NUM_NODES)," \ + "master $MASTER_NODE port $MASTER_PORT," \ + "GPUs $SLURM_GPUS_ON_NODE," \ + "CUDA: $(python -c 'import torch; print(torch.cuda.is_available())')" + +python -u -m torch.distributed.run \ + --nnodes $SLURM_JOB_NUM_NODES \ + --nproc_per_node $SLURM_GPUS_ON_NODE \ + --node_rank=$SLURM_PROCID \ + --master_addr $MASTER_NODE \ + --master_port $MASTER_PORT \ + "$@" diff --git a/146m14b14b/logs/2085658.err b/146m14b14b/logs/2085658.err new file mode 100644 index 0000000000000000000000000000000000000000..9ac74d5a0a1bf6510908d8038d6d7a416a6ac73c --- /dev/null +++ b/146m14b14b/logs/2085658.err @@ -0,0 +1,479 @@ +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module scaled_upper_triang_masked_softmax_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module scaled_upper_triang_masked_softmax_cuda... +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module scaled_masked_softmax_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module scaled_masked_softmax_cuda... +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module fused_mix_prec_layer_norm_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module fused_mix_prec_layer_norm_cuda... +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +7: Successfully preprocessed all matching files. +6: Successfully preprocessed all matching files. +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: +0: +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: +7: +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: +6: +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: +2: +2: +2: +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: +3: +3: +3: +3: +3: +3: +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: +5: +5: +5: +5: +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: +1: +1: +1: +1: +1: +1: +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: +4: +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: +4: +4: +0: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja... +0: Building extension module utils... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +7: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +0: Loading extension module utils... +2: Loading extension module utils... +3: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +1: Loading extension module utils... +3: Loading extension module utils... +4: Loading extension module utils... +1: Loading extension module utils... +5: Loading extension module utils... +3: Loading extension module utils... +2: Loading extension module utils... +4: Loading extension module utils... +1: Loading extension module utils... +3: Loading extension module utils... +5: Loading extension module utils... +4: Loading extension module utils... +2: Loading extension module utils... +1: Loading extension module utils... +5: Loading extension module utils... +2: Loading extension module utils... +3: Loading extension module utils... +4: Loading extension module utils... +5: Loading extension module utils... +1: Loading extension module utils... +2: Loading extension module utils... +4: Loading extension module utils... +3: Loading extension module utils... +2: Loading extension module utils... +1: Loading extension module utils... +4: Loading extension module utils... +5: Loading extension module utils... +3: Loading extension module utils... +1: Loading extension module utils... +4: Loading extension module utils... +2: Loading extension module utils... +3: Loading extension module utils... +5: Loading extension module utils... +1: Loading extension module utils... +2: Loading extension module utils... +4: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +0: +0: Loading extension module utils... +0: Loading extension module utils... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +0: +0: Loading extension module utils...Loading extension module utils... +0: +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: +5: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +5: +5: Loading extension module utils...Loading extension module utils... +5: +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +5: +5: Loading extension module utils... +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +5: +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +3: +3: Loading extension module utils...Loading extension module utils... +3: +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +4: +4: Loading extension module utils... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: +4: Loading extension module utils...Loading extension module utils... +4: Loading extension module utils... +4: +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/utils.py:349: UserWarning: Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings +0: warnings.warn("Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings") diff --git a/146m14b14b/logs/2085658.out b/146m14b14b/logs/2085658.out new file mode 100644 index 0000000000000000000000000000000000000000..269f6c9c548cba273866c864f26c0f7369c350bb --- /dev/null +++ b/146m14b14b/logs/2085658.out @@ -0,0 +1,9656 @@ +Model parameters: d_model 768 ffw_size 3072 kv_size 64 n_heads 12 n_layers 15 +Megatron-DeepSpeed/pretrain_gpt.py --tensor-model-parallel-size 1 --pipeline-model-parallel-size 1 --num-layers 15 --hidden-size 768 --num-attention-heads 12 --kv-channels 64 --ffn-hidden-size 3072 --seq-length 2048 --max-position-embeddings 2048 --micro-batch-size 4 --global-batch-size 256 --train-samples 5_517_578 --vocab-file gpt2/vocab.json --merge-file gpt2/merges.txt --clip-grad 1.0 --kill-switch-path kill-switch-146moscareap --bf16 --optimizer adam --adam-beta1 0.9 --adam-beta2 0.999 --adam-eps 1e-8 --lr 2e-4 --min-lr 2e-5 --lr-decay-style cosine --lr-decay-samples 5_517_578 --lr-warmup-samples 55_176 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_146moscareap --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_146moscareap --load checkpoints_146moscareap --data-path /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2085658.json --zero-stage 0 +START 2085658: Tue Nov 29 17:04:19 EET 2022 +0: +0: +0: ======================= ROCm System Management Interface ======================= +0: ================================= Concise Info ================================= +0: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +0: 0 43.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 2 42.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 4 46.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 6 44.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: ================================================================================ +0: ============================= End of ROCm SMI Log ============================== +3: +3: +3: ======================= ROCm System Management Interface ======================= +3: ================================= Concise Info ================================= +3: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +3: 0 45.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 2 44.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 4 46.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 6 44.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: ================================================================================ +3: ============================= End of ROCm SMI Log ============================== +1: +1: +1: ======================= ROCm System Management Interface ======================= +1: ================================= Concise Info ================================= +1: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +1: 0 45.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 2 40.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 4 45.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 6 46.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: ================================================================================ +1: ============================= End of ROCm SMI Log ============================== +4: +4: +4: ======================= ROCm System Management Interface ======================= +4: ================================= Concise Info ================================= +4: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +4: 0 49.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 1 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 2 41.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 4 41.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 6 46.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: ================================================================================ +4: ============================= End of ROCm SMI Log ============================== +7: +7: +7: ======================= ROCm System Management Interface ======================= +7: ================================= Concise Info ================================= +7: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +7: 0 41.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 2 43.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 4 46.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 6 40.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: ================================================================================ +7: ============================= End of ROCm SMI Log ============================== +6: +6: +6: ======================= ROCm System Management Interface ======================= +6: ================================= Concise Info ================================= +6: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +6: 0 45.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 2 41.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 4 46.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 6 40.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: ================================================================================ +6: ============================= End of ROCm SMI Log ============================== +2: +2: +2: ======================= ROCm System Management Interface ======================= +2: ================================= Concise Info ================================= +2: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +2: 0 44.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 2 42.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 4 47.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 6 42.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: ================================================================================ +2: ============================= End of ROCm SMI Log ============================== +5: +5: +5: ======================= ROCm System Management Interface ======================= +5: ================================= Concise Info ================================= +5: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +5: 0 49.0c 100.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 2 43.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 3 39.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 4 45.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 6 44.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 7 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: ================================================================================ +5: ============================= End of ROCm SMI Log ============================== +4: Launching on nid005064 (4/8), master nid005060 port 9999, GPUs 8, CUDA: True +6: Launching on nid005066 (6/8), master nid005060 port 9999, GPUs 8, CUDA: True +1: Launching on nid005061 (1/8), master nid005060 port 9999, GPUs 8, CUDA: True +5: Launching on nid005065 (5/8), master nid005060 port 9999, GPUs 8, CUDA: True +0: Launching on nid005060 (0/8), master nid005060 port 9999, GPUs 8, CUDA: True +3: Launching on nid005063 (3/8), master nid005060 port 9999, GPUs 8, CUDA: True +7: Launching on nid005067 (7/8), master nid005060 port 9999, GPUs 8, CUDA: True +2: Launching on nid005062 (2/8), master nid005060 port 9999, GPUs 8, CUDA: True +0: using world size: 64, data-parallel-size: 64, tensor-model-parallel size: 1, pipeline-model-parallel size: 1 +0: accumulate and all-reduce gradients in fp32 for bfloat16 data type. +0: using torch.bfloat16 for parameters ... +0: ------------------------ arguments ------------------------ +0: abort_on_unmet_fused_kernel_constraints ......... False +0: accumulate_allreduce_grads_in_fp32 .............. True +0: adam_beta1 ...................................... 0.9 +0: adam_beta2 ...................................... 0.999 +0: adam_eps ........................................ 1e-08 +0: adlr_autoresume ................................. False +0: adlr_autoresume_interval ........................ 1000 +0: apply_query_key_layer_scaling ................... True +0: apply_residual_connection_post_layernorm ........ False +0: attention_dropout ............................... 0.1 +0: attention_softmax_in_fp32 ....................... False +0: bert_binary_head ................................ True +0: bert_load ....................................... None +0: bf16 ............................................ True +0: bias_dropout_fusion ............................. True +0: bias_gelu_fusion ................................ True +0: biencoder_projection_dim ........................ 0 +0: biencoder_shared_query_context_model ............ False +0: block_data_path ................................. None +0: checkpoint_activations .......................... False +0: checkpoint_in_cpu ............................... False +0: checkpoint_num_layers ........................... 1 +0: clip_grad ....................................... 1.0 +0: codecarbon_dir .................................. None +0: consumed_train_samples .......................... 0 +0: consumed_train_tokens ........................... 0 +0: consumed_valid_samples .......................... 0 +0: contigious_checkpointing ........................ False +0: cpu_optimizer ................................... False +0: cpu_torch_adam .................................. False +0: curriculum_learning ............................. False +0: data_impl ....................................... mmap +0: data_parallel_size .............................. 64 +0: data_path ....................................... ['/scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document'] +0: dataloader_type ................................. single +0: DDP_impl ........................................ local +0: decoder_seq_length .............................. None +0: deepscale ....................................... False +0: deepscale_config ................................ None +0: deepspeed ....................................... True +0: deepspeed_activation_checkpointing .............. False +0: deepspeed_config ................................ ds_configs/2085658.json +0: deepspeed_mpi ................................... False +0: distribute_checkpointed_activations ............. False +0: distributed_backend ............................. nccl +0: embed_layernorm ................................. False +0: embedding_path .................................. None +0: encoder_seq_length .............................. 2048 +0: eod_mask_loss ................................... False +0: eval_interval ................................... 1000 +0: eval_iters ...................................... 1 +0: eval_only ....................................... None +0: evidence_data_path .............................. None +0: exit_duration_in_mins ........................... None +0: exit_interval ................................... None +0: ffn_hidden_size ................................. 3072 +0: finetune ........................................ False +0: fp16 ............................................ False +0: fp16_lm_cross_entropy ........................... False +0: fp32_residual_connection ........................ False +0: gigaflos_no_embeds .............................. 0 +0: global_batch_size ............................... 256 +0: glu_activation .................................. None +0: hidden_dropout .................................. 0.1 +0: hidden_size ..................................... 768 +0: hysteresis ...................................... 2 +0: ict_head_size ................................... None +0: ict_load ........................................ None +0: img_dim ......................................... 224 +0: indexer_batch_size .............................. 128 +0: indexer_log_interval ............................ 1000 +0: inference ....................................... False +0: init_method_std ................................. 0.02 +0: init_method_xavier_uniform ...................... False +0: initial_loss_scale .............................. 4294967296 +0: kill_switch_path ................................ kill-switch-146moscareap +0: kv_channels ..................................... 64 +0: layer_norm_fusion ............................... True +0: layernorm_epsilon ............................... 1e-05 +0: lazy_mpu_init ................................... None +0: load ............................................ checkpoints_146moscareap +0: local_rank ...................................... None +0: log_batch_size_to_tensorboard ................... True +0: log_interval .................................... 10 +0: log_learning_rate_to_tensorboard ................ True +0: log_level ....................................... None +0: log_level_replica ............................... None +0: log_loss_scale_to_tensorboard ................... True +0: log_num_zeros_in_grad ........................... False +0: log_params_norm ................................. False +0: log_path ........................................ None +0: log_timers_to_tensorboard ....................... True +0: log_validation_ppl_to_tensorboard ............... True +0: loss_on_targets_only ............................ False +0: loss_scale ...................................... None +0: loss_scale_window ............................... 1000 +0: lr .............................................. 0.0002 +0: lr_decay_iters .................................. None +0: lr_decay_samples ................................ 5517578 +0: lr_decay_style .................................. cosine +0: lr_decay_tokens ................................. None +0: lr_warmup_fraction .............................. None +0: lr_warmup_iters ................................. 0 +0: lr_warmup_samples ............................... 55176 +0: make_vocab_size_divisible_by .................... 128 +0: mask_prob ....................................... 0.15 +0: masked_softmax_fusion ........................... True +0: max_position_embeddings ......................... 2048 +0: mean_noise_span_length .......................... None +0: memory_centric_tiled_linear ..................... False +0: merge_file ...................................... gpt2/merges.txt +0: micro_batch_size ................................ 4 +0: min_loss_scale .................................. 1.0 +0: min_lr .......................................... 2e-05 +0: mmap_warmup ..................................... False +0: no_load_optim ................................... None +0: no_load_rng ..................................... None +0: no_save_optim ................................... None +0: no_save_rng ..................................... None +0: noise_density ................................... None +0: num_attention_heads ............................. 12 +0: num_channels .................................... 3 +0: num_classes ..................................... 1000 +0: num_layers ...................................... 15 +0: num_layers_per_virtual_pipeline_stage ........... None +0: num_workers ..................................... 2 +0: onnx_safe ....................................... None +0: openai_gelu ..................................... False +0: optimizer ....................................... adam +0: optimizer_fusion ................................ True +0: override_lr_scheduler ........................... False +0: pad_vocab_size_to ............................... None +0: params_dtype .................................... torch.bfloat16 +0: partition_activations ........................... False +0: patch_dim ....................................... 16 +0: pipeline_model_parallel_size .................... 1 +0: position_embedding_type ......................... PositionEmbeddingType.absolute +0: pp_partition_method ............................. None +0: profile_backward ................................ False +0: query_in_block_prob ............................. 0.1 +0: rampup_batch_size ............................... None +0: rank ............................................ 0 +0: remote_device ................................... none +0: reset_attention_mask ............................ False +0: reset_position_ids .............................. False +0: retriever_report_topk_accuracies ................ [] +0: retriever_score_scaling ......................... False +0: retriever_seq_length ............................ 256 +0: reweight_loss_based_on_position_frequency ....... False +0: sample_rate ..................................... 1.0 +0: save ............................................ checkpoints_146moscareap +0: save_interval ................................... 1000 +0: scatter_gather_tensors_in_pipeline .............. True +0: scattered_embeddings ............................ False +0: seed ............................................ 1234 +0: seq_length ...................................... 2048 +0: sgd_momentum .................................... 0.9 +0: short_seq_prob .................................. 0.1 +0: skip_train_iteration_range ...................... None +0: split ........................................... 949,50,1 +0: split_transformers .............................. False +0: sync_tp_duplicated_parameters ................... False +0: synchronize_each_layer .......................... False +0: tensor_model_parallel_size ...................... 1 +0: tensorboard_dir ................................. tensorboard_146moscareap +0: tensorboard_log_interval ........................ 1 +0: tensorboard_queue_size .......................... 5 +0: test_weighted_split_names ....................... None +0: test_weighted_split_paths ....................... None +0: test_weighted_split_paths_path .................. None +0: test_weighted_split_splits ...................... None +0: test_weighted_split_weights ..................... None +0: tile_factor ..................................... 1 +0: titles_data_path ................................ None +0: tokenizer_name_or_path .......................... None +0: tokenizer_type .................................. GPT2BPETokenizer +0: train_iters ..................................... None +0: train_samples ................................... 5517578 +0: train_tokens .................................... None +0: train_weighted_split_paths ...................... None +0: train_weighted_split_paths_path ................. None +0: universal_checkpoint ............................ False +0: use_bnb_optimizer ............................... False +0: use_checkpoint_lr_scheduler ..................... False +0: use_contiguous_buffers_in_ddp ................... True +0: use_cpu_initialization .......................... None +0: use_one_sent_docs ............................... False +0: use_pin_memory .................................. False +0: valid_num_workers ............................... 2 +0: valid_weighted_split_names ...................... None +0: valid_weighted_split_paths ...................... None +0: valid_weighted_split_paths_path ................. None +0: valid_weighted_split_splits ..................... None +0: valid_weighted_split_weights .................... None +0: virtual_pipeline_model_parallel_size ............ None +0: vocab_extra_ids ................................. 0 +0: vocab_file ...................................... gpt2/vocab.json +0: weight_decay .................................... 0.1 +0: world_size ...................................... 64 +0: zero_allgather_bucket_size ...................... 0.0 +0: zero_contigious_gradients ....................... False +0: zero_reduce_bucket_size ......................... 0.0 +0: zero_reduce_scatter ............................. False +0: zero_stage ...................................... 0 +0: -------------------- end of arguments --------------------- +0: setting number of micro-batches to constant 1 +0: > building GPT2BPETokenizer tokenizer ... +0: > padded vocab (size: 50257) with 47 dummy tokens (new size: 50304) +0: DeepSpeed general environment info: +0: torch install path ............... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch'] +0: torch version .................... 1.13.0+rocm5.2 +0: torch cuda version ............... None +0: torch hip version ................ 5.2.21151-afdc89f8 +0: nvcc version ..................... None +0: deepspeed install path ........... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed'] +0: deepspeed info ................... 0.7.5, unknown, unknown +0: deepspeed wheel compiled w. ...... torch 1.13, hip 5.1 +0: **** Git info for Megatron: git_hash=unknown git_branch=unknown **** +0: > initializing torch distributed ... +0: [2022-11-29 17:05:15,927] [INFO] [comm.py:633:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +7: > setting tensorboard ... +0: > initializing tensor model parallel with size 1 +0: > initializing pipeline model parallel with size 1 +0: > setting random seeds to 1234 ... +0: > initializing model parallel cuda seeds on global rank 0, model parallel rank 0, and data parallel rank 0 with model parallel seed: 3952 and data parallel seed: 1234 +0: > compiling dataset index builder ... +0: make: Entering directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' +0: make: Nothing to be done for 'default'. +0: make: Leaving directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' +0: >>> done with dataset index builder. Compilation time: 0.114 seconds +0: > compiling and loading fused kernels ... +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.cpp [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 87 +0: [1/1] c++ scaled_upper_triang_masked_softmax_hip.o scaled_upper_triang_masked_softmax_hip.cuda.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib -lamdhip64 -o scaled_upper_triang_masked_softmax_cuda.so +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.cpp [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 63 +0: [1/1] c++ scaled_masked_softmax_hip.cuda.o scaled_masked_softmax_hip.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib -lamdhip64 -o scaled_masked_softmax_cuda.so +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda_kernel.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_hip_kernel.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 67 +0: ninja: no work to do. +0: >>> done with compiling and loading fused kernels. Compilation time: 16.168 seconds +0: time to initialize megatron (seconds): 63.502 +0: [after megatron is initialized] datetime: 2022-11-29 17:05:35 +0: building GPT model ... +0: [2022-11-29 17:05:35,555] [INFO] [utils.py:827:see_memory_usage] Before Building Model +0: [2022-11-29 17:05:35,555] [INFO] [utils.py:828:see_memory_usage] MA 0.0 GB Max_MA 0.0 GB CA 0.0 GB Max_CA 0 GB +0: [2022-11-29 17:05:35,556] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 29.88 GB, percent = 5.9% +0: SEED_LAYERS=False BASE_SEED=1234 SEED_FN=None +0: Using topology: {ProcessCoord(pipe=0, data=0, model=0): 0, ProcessCoord(pipe=0, data=1, model=0): 1, ProcessCoord(pipe=0, data=2, model=0): 2, ProcessCoord(pipe=0, data=3, model=0): 3, ProcessCoord(pipe=0, data=4, model=0): 4, ProcessCoord(pipe=0, data=5, model=0): 5, ProcessCoord(pipe=0, data=6, model=0): 6, ProcessCoord(pipe=0, data=7, model=0): 7, ProcessCoord(pipe=0, data=8, model=0): 8, ProcessCoord(pipe=0, data=9, model=0): 9, ProcessCoord(pipe=0, data=10, model=0): 10, ProcessCoord(pipe=0, data=11, model=0): 11, ProcessCoord(pipe=0, data=12, model=0): 12, ProcessCoord(pipe=0, data=13, model=0): 13, ProcessCoord(pipe=0, data=14, model=0): 14, ProcessCoord(pipe=0, data=15, model=0): 15, ProcessCoord(pipe=0, data=16, model=0): 16, ProcessCoord(pipe=0, data=17, model=0): 17, ProcessCoord(pipe=0, data=18, model=0): 18, ProcessCoord(pipe=0, data=19, model=0): 19, ProcessCoord(pipe=0, data=20, model=0): 20, ProcessCoord(pipe=0, data=21, model=0): 21, ProcessCoord(pipe=0, data=22, model=0): 22, ProcessCoord(pi +0: pe=0, data=23, model=0): 23, ProcessCoord(pipe=0, data=24, model=0): 24, ProcessCoord(pipe=0, data=25, model=0): 25, ProcessCoord(pipe=0, data=26, model=0): 26, ProcessCoord(pipe=0, data=27, model=0): 27, ProcessCoord(pipe=0, data=28, model=0): 28, ProcessCoord(pipe=0, data=29, model=0): 29, ProcessCoord(pipe=0, data=30, model=0): 30, ProcessCoord(pipe=0, data=31, model=0): 31, ProcessCoord(pipe=0, data=32, model=0): 32, ProcessCoord(pipe=0, data=33, model=0): 33, ProcessCoord(pipe=0, data=34, model=0): 34, ProcessCoord(pipe=0, data=35, model=0): 35, ProcessCoord(pipe=0, data=36, model=0): 36, ProcessCoord(pipe=0, data=37, model=0): 37, ProcessCoord(pipe=0, data=38, model=0): 38, ProcessCoord(pipe=0, data=39, model=0): 39, ProcessCoord(pipe=0, data=40, model=0): 40, ProcessCoord(pipe=0, data=41, model=0): 41, ProcessCoord(pipe=0, data=42, model=0): 42, ProcessCoord(pipe=0, data=43, model=0): 43, ProcessCoord(pipe=0, data=44, model=0): 44, ProcessCoord(pipe=0, data=45, model=0): 45, ProcessCoord(pipe=0, data=4 +0: 6, model=0): 46, ProcessCoord(pipe=0, data=47, model=0): 47, ProcessCoord(pipe=0, data=48, model=0): 48, ProcessCoord(pipe=0, data=49, model=0): 49, ProcessCoord(pipe=0, data=50, model=0): 50, ProcessCoord(pipe=0, data=51, model=0): 51, ProcessCoord(pipe=0, data=52, model=0): 52, ProcessCoord(pipe=0, data=53, model=0): 53, ProcessCoord(pipe=0, data=54, model=0): 54, ProcessCoord(pipe=0, data=55, model=0): 55, ProcessCoord(pipe=0, data=56, model=0): 56, ProcessCoord(pipe=0, data=57, model=0): 57, ProcessCoord(pipe=0, data=58, model=0): 58, ProcessCoord(pipe=0, data=59, model=0): 59, ProcessCoord(pipe=0, data=60, model=0): 60, ProcessCoord(pipe=0, data=61, model=0): 61, ProcessCoord(pipe=0, data=62, model=0): 62, ProcessCoord(pipe=0, data=63, model=0): 63} +0: [2022-11-29 17:05:37,558] [INFO] [module.py:366:_partition_layers] Partitioning pipeline stages with method type:transformer +0: stage=0 layers=22 +0: 0: _to_float16 +0: 1: EmbeddingPipe +0: 2: +0: 3: ParallelTransformerLayerPipe +0: 4: ParallelTransformerLayerPipe +0: 5: ParallelTransformerLayerPipe +0: 6: ParallelTransformerLayerPipe +0: 7: ParallelTransformerLayerPipe +0: 8: ParallelTransformerLayerPipe +0: 9: ParallelTransformerLayerPipe +0: 10: ParallelTransformerLayerPipe +0: 11: ParallelTransformerLayerPipe +0: 12: ParallelTransformerLayerPipe +0: 13: ParallelTransformerLayerPipe +0: 14: ParallelTransformerLayerPipe +0: 15: ParallelTransformerLayerPipe +0: 16: ParallelTransformerLayerPipe +0: 17: ParallelTransformerLayerPipe +0: 18: undo +0: 19: MixedFusedLayerNorm +0: 20: EmbeddingPipe +0: 21: float16_to_fp32 +0: loss: CrossEntropy +0: [2022-11-29 17:05:37,700] [INFO] [utils.py:827:see_memory_usage] After Building Model +0: [2022-11-29 17:05:37,701] [INFO] [utils.py:828:see_memory_usage] MA 0.28 GB Max_MA 0.28 GB CA 0.29 GB Max_CA 0 GB +0: [2022-11-29 17:05:37,701] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 29.91 GB, percent = 5.9% +0: setting training iterations to 21553 +0: > learning rate decay style: cosine +0: DeepSpeed is enabled. +0: [2022-11-29 17:05:37,703] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed info: version=0.7.5, git-hash=unknown, git-branch=unknown +0: [2022-11-29 17:05:48,282] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False +0: [2022-11-29 17:05:48,282] [INFO] [logging.py:68:log_dist] [Rank 0] Removing param_group that has no 'params' in the client Optimizer +0: [2022-11-29 17:05:48,283] [INFO] [logging.py:68:log_dist] [Rank 0] Using client Optimizer as basic optimizer +0: [2022-11-29 17:05:48,287] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Basic Optimizer = FusedAdam +0: [2022-11-29 17:05:48,287] [INFO] [logging.py:68:log_dist] [Rank 0] Creating BF16 optimizer +0: [2022-11-29 17:05:48,333] [INFO] [utils.py:827:see_memory_usage] begin bf16_optimizer +0: [2022-11-29 17:05:48,333] [INFO] [utils.py:828:see_memory_usage] MA 0.28 GB Max_MA 0.29 GB CA 0.31 GB Max_CA 0 GB +0: [2022-11-29 17:05:48,333] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.58 GB, percent = 6.1% +0: ninja: no work to do. +0: Time to load utils op: 0.1854405403137207 seconds +0: Time to load utils op: 0.20511341094970703 seconds +0: Time to load utils op: 0.2054591178894043 seconds +0: Time to load utils op: 0.20521926879882812 seconds +0: Time to load utils op: 0.2058553695678711 seconds +0: Time to load utils op: 0.20522737503051758 seconds +0: Time to load utils op: 0.20561599731445312 seconds +0: Time to load utils op: 0.20194745063781738 seconds +6: Time to load utils op: 0.22777152061462402 seconds +6: Time to load utils op: 0.22777938842773438 seconds +6: Time to load utils op: 0.22780299186706543 secondsTime to load utils op: 0.22860932350158691 seconds +6: +6: Time to load utils op: 0.22792339324951172 seconds +6: Time to load utils op: 0.22779107093811035 seconds +6: Time to load utils op: 0.22835493087768555 seconds +6: Time to load utils op: 0.22768425941467285 seconds +7: Time to load utils op: 0.22831153869628906 seconds +7: Time to load utils op: 0.22768259048461914 seconds +7: Time to load utils op: 0.22755837440490723 seconds +7: Time to load utils op: 0.2275707721710205 seconds +7: Time to load utils op: 0.2278153896331787 seconds +7: Time to load utils op: 0.22827720642089844 seconds +7: Time to load utils op: 0.22819209098815918 secondsTime to load utils op: 0.22833919525146484 seconds +7: +5: Time to load utils op: 0.22706842422485352 secondsTime to load utils op: 0.2270674705505371 seconds +5: +5: Time to load utils op: 0.22707414627075195 seconds +5: Time to load utils op: 0.22711825370788574 secondsTime to load utils op: 0.22712087631225586 seconds +5: +5: Time to load utils op: 0.2271287441253662 seconds +5: Time to load utils op: 0.22713661193847656 secondsTime to load utils op: 0.22714710235595703 seconds +5: +3: Time to load utils op: 0.23506689071655273 seconds +1: Time to load utils op: 0.2351374626159668 secondsTime to load utils op: 0.23514080047607422 seconds +1: +3: Time to load utils op: 0.23509716987609863 seconds +1: Time to load utils op: 0.2351851463317871 seconds +1: Time to load utils op: 0.2351994514465332 seconds +1: Time to load utils op: 0.23519349098205566 seconds +4: Time to load utils op: 0.23491311073303223 secondsTime to load utils op: 0.23490214347839355 seconds +4: +4: Time to load utils op: 0.2349250316619873 seconds +3: Time to load utils op: 0.23512887954711914 secondsTime to load utils op: 0.23513293266296387 secondsTime to load utils op: 0.23510956764221191 seconds +3: +3: +1: Time to load utils op: 0.23520779609680176 seconds +4: Time to load utils op: 0.23494291305541992 secondsTime to load utils op: 0.23492646217346191 seconds +4: +4: Time to load utils op: 0.23497414588928223 seconds +4: Time to load utils op: 0.23498129844665527 seconds +4: Time to load utils op: 0.23499774932861328 seconds +3: Time to load utils op: 0.23514652252197266 seconds +3: Time to load utils op: 0.23518776893615723 seconds +3: Time to load utils op: 0.23515748977661133 seconds +1: Time to load utils op: 0.23522067070007324 seconds +1: Time to load utils op: 0.2352304458618164 seconds +2: Time to load utils op: 0.23569750785827637 seconds +2: Time to load utils op: 0.23570513725280762 seconds +2: Time to load utils op: 0.23575091361999512 seconds +2: Time to load utils op: 0.2357494831085205 seconds +2: Time to load utils op: 0.23573994636535645 seconds +2: Time to load utils op: 0.23576784133911133 seconds +2: Time to load utils op: 0.23577404022216797 seconds +2: Time to load utils op: 0.23576641082763672 seconds +0: [2022-11-29 17:05:48,583] [INFO] [utils.py:827:see_memory_usage] before initializing group 0 +0: [2022-11-29 17:05:48,584] [INFO] [utils.py:828:see_memory_usage] MA 0.28 GB Max_MA 0.28 GB CA 0.31 GB Max_CA 0 GB +0: [2022-11-29 17:05:48,584] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.58 GB, percent = 6.1% +0: Time to load utils op: 0.0006055831909179688 seconds +0: Time to load utils op: 0.0005714893341064453 seconds +0: Time to load utils op: 0.0006036758422851562 seconds +0: Time to load utils op: 0.0005228519439697266 seconds +0: Time to load utils op: 0.0005788803100585938 seconds +0: Time to load utils op: 0.0005946159362792969 seconds +0: Time to load utils op: 0.00052642822265625 seconds +7: Time to load utils op: 0.00118255615234375 seconds +7: Time to load utils op: 0.001276254653930664 seconds +7: Time to load utils op: 0.0013015270233154297 seconds +7: Time to load utils op: 0.0012102127075195312 seconds +7: Time to load utils op: 0.0013976097106933594 seconds +7: Time to load utils op: 0.0012259483337402344 seconds +7: Time to load utils op: 0.0012671947479248047 seconds +7: Time to load utils op: 0.0011906623840332031 seconds +5: Time to load utils op: 0.0010249614715576172 seconds +5: Time to load utils op: 0.0009028911590576172 seconds +5: Time to load utils op: 0.0011067390441894531 seconds +6: Time to load utils op: 0.0009636878967285156 seconds +5: Time to load utils op: 0.0012927055358886719 seconds +5: Time to load utils op: 0.0013210773468017578 seconds +5: Time to load utils op: 0.0011823177337646484 seconds +5: Time to load utils op: 0.0012404918670654297 seconds +5: Time to load utils op: 0.001371622085571289 seconds +6: Time to load utils op: 0.001302480697631836 seconds +6: Time to load utils op: 0.0013387203216552734 seconds +6: Time to load utils op: 0.0013685226440429688 seconds +6: Time to load utils op: 0.0014524459838867188 secondsTime to load utils op: 0.0014193058013916016 seconds +6: +6: Time to load utils op: 0.0013661384582519531 seconds +6: Time to load utils op: 0.0014519691467285156 seconds +2: Time to load utils op: 0.0007998943328857422 seconds +2: Time to load utils op: 0.0008978843688964844 seconds +2: Time to load utils op: 0.0012054443359375 seconds +2: Time to load utils op: 0.001203775405883789 secondsTime to load utils op: 0.0011143684387207031 seconds +2: +2: Time to load utils op: 0.0012195110321044922 seconds +2: Time to load utils op: 0.0011992454528808594 seconds +2: Time to load utils op: 0.0012950897216796875 seconds +3: Time to load utils op: 0.0010440349578857422 seconds +3: Time to load utils op: 0.0011737346649169922 seconds +3: Time to load utils op: 0.0013287067413330078 seconds +3: Time to load utils op: 0.0012156963348388672 seconds +3: Time to load utils op: 0.001285552978515625 seconds +3: Time to load utils op: 0.0012767314910888672 seconds +3: Time to load utils op: 0.0012798309326171875 seconds +3: Time to load utils op: 0.0013165473937988281 seconds +0: [2022-11-29 17:05:48,635] [INFO] [utils.py:827:see_memory_usage] after initializing group 0 +4: Time to load utils op: 0.0007605552673339844 seconds +4: Time to load utils op: 0.0008978843688964844 seconds +4: Time to load utils op: 0.0008845329284667969 seconds +4: Time to load utils op: 0.0009028911590576172 seconds +4: Time to load utils op: 0.0010044574737548828 seconds +4: Time to load utils op: 0.001007080078125 secondsTime to load utils op: 0.0009655952453613281 seconds +4: +0: [2022-11-29 17:05:48,635] [INFO] [utils.py:828:see_memory_usage] MA 0.62 GB Max_MA 0.62 GB CA 0.82 GB Max_CA 1 GB +4: Time to load utils op: 0.001071929931640625 seconds +0: [2022-11-29 17:05:48,636] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.69 GB, percent = 6.1% +1: Time to load utils op: 0.0008280277252197266 seconds +1: Time to load utils op: 0.0009031295776367188 secondsTime to load utils op: 0.0009334087371826172 seconds +1: +1: Time to load utils op: 0.0011057853698730469 secondsTime to load utils op: 0.001163482666015625 seconds +1: +1: Time to load utils op: 0.0011248588562011719 secondsTime to load utils op: 0.0011985301971435547 seconds +1: +1: Time to load utils op: 0.0011789798736572266 seconds +0: [2022-11-29 17:05:48,669] [INFO] [utils.py:827:see_memory_usage] before initializing group 1 +0: [2022-11-29 17:05:48,670] [INFO] [utils.py:828:see_memory_usage] MA 0.62 GB Max_MA 0.62 GB CA 0.82 GB Max_CA 1 GB +0: [2022-11-29 17:05:48,670] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.72 GB, percent = 6.1% +0: [2022-11-29 17:05:48,702] [INFO] [utils.py:827:see_memory_usage] after initializing group 1 +0: [2022-11-29 17:05:48,703] [INFO] [utils.py:828:see_memory_usage] MA 0.83 GB Max_MA 0.83 GB CA 1.13 GB Max_CA 1 GB +0: [2022-11-29 17:05:48,703] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.72 GB, percent = 6.1% +0: [2022-11-29 17:05:48,733] [INFO] [utils.py:827:see_memory_usage] before initializing group 2 +0: [2022-11-29 17:05:48,734] [INFO] [utils.py:828:see_memory_usage] MA 0.83 GB Max_MA 0.83 GB CA 1.13 GB Max_CA 1 GB +0: [2022-11-29 17:05:48,734] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.72 GB, percent = 6.1% +0: [2022-11-29 17:05:48,767] [INFO] [utils.py:827:see_memory_usage] after initializing group 2 +0: [2022-11-29 17:05:48,767] [INFO] [utils.py:828:see_memory_usage] MA 0.83 GB Max_MA 0.83 GB CA 1.13 GB Max_CA 1 GB +0: [2022-11-29 17:05:48,767] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.72 GB, percent = 6.1% +0: [2022-11-29 17:05:48,797] [INFO] [utils.py:827:see_memory_usage] before initialize_optimizer +0: [2022-11-29 17:05:48,798] [INFO] [utils.py:828:see_memory_usage] MA 0.83 GB Max_MA 0.83 GB CA 1.13 GB Max_CA 1 GB +0: [2022-11-29 17:05:48,798] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.72 GB, percent = 6.1% +0: [2022-11-29 17:05:48,833] [INFO] [utils.py:827:see_memory_usage] end initialize_optimizer +0: [2022-11-29 17:05:48,834] [INFO] [utils.py:828:see_memory_usage] MA 0.85 GB Max_MA 0.85 GB CA 1.13 GB Max_CA 1 GB +0: [2022-11-29 17:05:48,834] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.72 GB, percent = 6.1% +0: [2022-11-29 17:05:48,865] [INFO] [utils.py:827:see_memory_usage] end bf16_optimizer +0: [2022-11-29 17:05:48,865] [INFO] [utils.py:828:see_memory_usage] MA 0.85 GB Max_MA 0.85 GB CA 1.13 GB Max_CA 1 GB +0: [2022-11-29 17:05:48,865] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.72 GB, percent = 6.1% +0: [2022-11-29 17:05:48,866] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Final Optimizer = FusedAdam +0: [2022-11-29 17:05:48,866] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed using client LR scheduler +0: [2022-11-29 17:05:48,866] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed LR Scheduler = +0: [2022-11-29 17:05:48,866] [INFO] [logging.py:68:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0, 0.0, 0.0], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +0: [2022-11-29 17:05:48,866] [INFO] [config.py:1007:print] DeepSpeedEngine configuration: +0: [2022-11-29 17:05:48,866] [INFO] [config.py:1011:print] activation_checkpointing_config { +0: "partition_activations": false, +0: "contiguous_memory_optimization": false, +0: "cpu_checkpointing": false, +0: "number_checkpoints": null, +0: "synchronize_checkpoint_boundary": false, +0: "profile": false +0: } +0: [2022-11-29 17:05:48,866] [INFO] [config.py:1011:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True} +0: [2022-11-29 17:05:48,866] [INFO] [config.py:1011:print] amp_enabled .................. False +0: [2022-11-29 17:05:48,866] [INFO] [config.py:1011:print] amp_params ................... False +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] autotuning_config ............ { +0: "enabled": false, +0: "start_step": null, +0: "end_step": null, +0: "metric_path": null, +0: "arg_mappings": null, +0: "metric": "throughput", +0: "model_info": null, +0: "results_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_results", +0: "exps_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_exps", +0: "overwrite": true, +0: "fast": true, +0: "start_profile_step": 3, +0: "end_profile_step": 5, +0: "tuner_type": "gridsearch", +0: "tuner_early_stopping": 5, +0: "tuner_num_trials": 50, +0: "model_info_path": null, +0: "mp_size": 1, +0: "max_train_batch_size": null, +0: "min_train_batch_size": 1, +0: "max_train_micro_batch_size_per_gpu": 1.024000e+03, +0: "min_train_micro_batch_size_per_gpu": 1, +0: "num_tuning_micro_batch_sizes": 3 +0: } +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] bfloat16_enabled ............. True +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] checkpoint_parallel_write_pipeline False +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] checkpoint_tag_validation_enabled True +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] checkpoint_tag_validation_fail False +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] comms_config ................. +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] communication_data_type ...... None +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] compression_config ........... {'weight_quantization': {'shared_parameters': {'enabled': False, 'quantizer_kernel': False, 'schedule_offset': 0, 'quantize_groups': 1, 'quantize_verbose': False, 'quantization_type': 'symmetric', 'quantize_weight_in_forward': False, 'rounding': 'nearest', 'fp16_mixed_quantize': False, 'quantize_change_ratio': 0.001}, 'different_groups': {}}, 'activation_quantization': {'shared_parameters': {'enabled': False, 'quantization_type': 'symmetric', 'range_calibration': 'dynamic', 'schedule_offset': 1000}, 'different_groups': {}}, 'sparse_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'row_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'head_pruning': {'shared_parameters': {'enabled': False, 'method': 'topk', 'schedule_offset': 1000}, 'different_groups': {}}, 'channel_pruning': {'shared_pa +0: rameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'layer_reduction': {'enabled': False}} +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] curriculum_enabled ........... False +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] curriculum_params ............ False +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] dataloader_drop_last ......... False +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] disable_allgather ............ False +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] dump_state ................... False +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] dynamic_loss_scale_args ...... None +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] eigenvalue_enabled ........... False +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] eigenvalue_gas_boundary_resolution 1 +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] eigenvalue_layer_name ........ bert.encoder.layer +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] eigenvalue_layer_num ......... 0 +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] eigenvalue_max_iter .......... 100 +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] eigenvalue_stability ......... 1e-06 +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] eigenvalue_tol ............... 0.01 +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] eigenvalue_verbose ........... False +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] elasticity_enabled ........... False +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] flops_profiler_config ........ { +0: "enabled": false, +0: "profile_step": 1, +0: "module_depth": -1, +0: "top_modules": 1, +0: "detailed": true, +0: "output_file": null +0: } +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] fp16_auto_cast ............... None +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] fp16_enabled ................. False +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] fp16_master_weights_and_gradients False +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] global_rank .................. 0 +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] gradient_accumulation_steps .. 1 +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] gradient_clipping ............ 1.0 +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] gradient_predivide_factor .... 1.0 +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] initial_dynamic_scale ........ 1 +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] load_universal_checkpoint .... False +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] loss_scale ................... 1.0 +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] memory_breakdown ............. False +0: [2022-11-29 17:05:48,867] [INFO] [config.py:1011:print] monitor_config ............... +0: [2022-11-29 17:05:48,868] [INFO] [config.py:1011:print] nebula_config ................ { +0: "enabled": false, +0: "persistent_storage_path": null, +0: "persistent_time_interval": 100, +0: "num_of_version_in_retention": 2, +0: "enable_nebula_load": true, +0: "load_path": null +0: } +0: [2022-11-29 17:05:48,868] [INFO] [config.py:1011:print] optimizer_legacy_fusion ...... False +0: [2022-11-29 17:05:48,868] [INFO] [config.py:1011:print] optimizer_name ............... None +0: [2022-11-29 17:05:48,868] [INFO] [config.py:1011:print] optimizer_params ............. None +0: [2022-11-29 17:05:48,868] [INFO] [config.py:1011:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0} +0: [2022-11-29 17:05:48,868] [INFO] [config.py:1011:print] pld_enabled .................. False +0: [2022-11-29 17:05:48,868] [INFO] [config.py:1011:print] pld_params ................... False +0: [2022-11-29 17:05:48,868] [INFO] [config.py:1011:print] prescale_gradients ........... False +0: [2022-11-29 17:05:48,868] [INFO] [config.py:1011:print] scheduler_name ............... None +0: [2022-11-29 17:05:48,868] [INFO] [config.py:1011:print] scheduler_params ............. None +0: [2022-11-29 17:05:48,868] [INFO] [config.py:1011:print] sparse_attention ............. None +0: [2022-11-29 17:05:48,868] [INFO] [config.py:1011:print] sparse_gradients_enabled ..... False +0: [2022-11-29 17:05:48,868] [INFO] [config.py:1011:print] steps_per_print .............. 2000 +0: [2022-11-29 17:05:48,868] [INFO] [config.py:1011:print] train_batch_size ............. 256 +0: [2022-11-29 17:05:48,868] [INFO] [config.py:1011:print] train_micro_batch_size_per_gpu 4 +0: [2022-11-29 17:05:48,868] [INFO] [config.py:1011:print] use_node_local_storage ....... False +0: [2022-11-29 17:05:48,868] [INFO] [config.py:1011:print] wall_clock_breakdown ......... False +0: [2022-11-29 17:05:48,868] [INFO] [config.py:1011:print] world_size ................... 64 +0: [2022-11-29 17:05:48,868] [INFO] [config.py:1011:print] zero_allow_untested_optimizer False +0: [2022-11-29 17:05:48,868] [INFO] [config.py:1011:print] zero_config .................. stage=0 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=500000000 allgather_partitions=True allgather_bucket_size=500000000 overlap_comm=False load_from_fp32_weights=True elastic_checkpoint=False offload_param=None offload_optimizer=None sub_group_size=1000000000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=50000000 param_persistence_threshold=100000 model_persistence_threshold=9223372036854775807 max_live_parameters=1000000000 max_reuse_distance=1000000000 gather_16bit_weights_on_model_save=False stage3_gather_fp16_weights_on_model_save=False ignore_unused_parameters=True legacy_stage1=False round_robin_gradients=False +0: [2022-11-29 17:05:48,868] [INFO] [config.py:1011:print] zero_enabled ................. False +0: [2022-11-29 17:05:48,868] [INFO] [config.py:1011:print] zero_optimization_stage ...... 0 +0: [2022-11-29 17:05:48,868] [INFO] [config.py:996:print_user_config] json = { +0: "train_micro_batch_size_per_gpu": 4, +0: "train_batch_size": 256, +0: "gradient_clipping": 1.0, +0: "zero_optimization": { +0: "stage": 0 +0: }, +0: "bf16": { +0: "enabled": true +0: }, +0: "steps_per_print": 2.000000e+03, +0: "wall_clock_breakdown": false +0: } +0: Time to load utils op: 0.0003962516784667969 seconds +0: [2022-11-29 17:05:48,869] [INFO] [engine.py:87:__init__] CONFIG: micro_batches=1 micro_batch_size=4 +0: [2022-11-29 17:05:48,921] [INFO] [engine.py:145:__init__] RANK=0 STAGE=0 LAYERS=22 [0, 22) STAGE_PARAMS=146525952 (146.526M) TOTAL_PARAMS=146525952 (146.526M) UNIQUE_PARAMS=146525952 (146.526M) +0: [2022-11-29 17:05:48,927] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: WARNING: could not find the metadata file checkpoints_146moscareap +0: will not load any checkpoints and will start from random +6: [2022-11-29 17:05:48,927] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 17:05:48,927] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:05:48,927] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 17:05:48,927] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 17:05:48,927] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:05:48,927] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 17:05:48,927] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 17:05:48,927] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:05:48,927] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 17:05:48,927] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:05:48,927] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:05:48,927] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:05:48,927] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:05:48,927] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:05:48,928] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:05:48,929] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_146moscareap/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: time (ms) | load-checkpoint: 5.56 +0: estimated model parameters: 0.146525952 +0: estimated model parameters without embeddings: 0.106319616 +0: [after model, optimizer, and learning rate scheduler are built] datetime: 2022-11-29 17:05:49 +0: > building train, validation, and test datasets ... +0: > datasets target sizes (minimum size): +0: train: 5517578 +0: validation: 5632 +0: test: 256 +0: > building train, validation, and test datasets for GPT ... +0: > building dataset index ... +0: reading sizes... +0: reading pointers... +0: reading document index... +0: creating numpy buffer of mmap... +0: creating memory view of numpy buffer... +0: > finished creating indexed dataset in 0.024771 seconds +0: number of documents: 431992659 +0: > dataset split: +0: train: +0: document indices in [0, 409961033) total of 409961033 documents +0: validation: +0: document indices in [409961033, 431560666) total of 21599633 documents +0: test: +0: document indices in [431560666, 431992659) total of 431993 documents +0: > WARNING: could not find index map files, building the indices on rank 0 ... +0: > only one epoch required, setting separate_last_epoch to False +0: > elasped time to build and save doc-idx mapping (seconds): 29.403373 +0: using: +0: number of documents: 409961033 +0: number of epochs: 1 +0: sequence length: 2048 +0: total number of samples: 262636457 +0: > elasped time to build and save sample-idx mapping (seconds): 7.771299 +0: > building shuffle index with split [0, 262636457) and [262636457, 262636457) ... +0: > elasped time to build and save shuffle-idx mapping (seconds): 14.656659 +0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_5517578ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_5517578ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_5517578ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.911 seconds +0: total number of samples: 262636458 +0: total number of epochs: 1 +0: > WARNING: could not find index map files, building the indices on rank 0 ... +0: > only one epoch required, setting separate_last_epoch to False +0: > elasped time to build and save doc-idx mapping (seconds): 1.248159 +0: using: +0: number of documents: 21599633 +0: number of epochs: 1 +0: sequence length: 2048 +0: total number of samples: 13852049 +0: > elasped time to build and save sample-idx mapping (seconds): 0.423639 +0: > building shuffle index with split [0, 13852049) and [13852049, 13852049) ... +0: > elasped time to build and save shuffle-idx mapping (seconds): 0.513238 +0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_5632ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_5632ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_5632ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.048 seconds +0: total number of samples: 13852050 +0: total number of epochs: 1 +0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_256ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_256ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_256ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.045 seconds +0: total number of samples: 276852 +0: total number of epochs: 1 +0: > finished creating GPT datasets ... +0: [after dataloaders are built] datetime: 2022-11-29 17:07:01 +0: done with setup ... +0: training ... +0: Number of parameters: [tensor rank - pipeline rank] w/ and w/o embeddings: +7: time (ms) | model-and-optimizer-setup: 13673.35 | train/valid/test-data-iterators-setup: 71300.98 +0: [000-000] 0.1465B / 0.1063B +0: [before the start of training step] datetime: 2022-11-29 17:07:01 +0: [Rank 0] (after 10 iterations) memory (MB) | allocated: 2734.17236328125 | max allocated: 22586.583984375 | reserved: 23360.0 | max reserved: 23360.0 +7: iteration 10/ 21553 | consumed samples: 2560 | consumed tokens: 5242880 | elapsed time per iteration (s): 1.48 | learning rate: 9.279E-06 | global batch size: 256 | lm loss: 1.066109E+01 | grad norm: 5.058 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 173.131 | TFLOPs: 6.06 | +7: iteration 20/ 21553 | consumed samples: 5120 | consumed tokens: 10485760 | elapsed time per iteration (s): 0.31 | learning rate: 1.856E-05 | global batch size: 256 | lm loss: 9.809862E+00 | grad norm: 1.951 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.714 | TFLOPs: 28.63 | +7: iteration 30/ 21553 | consumed samples: 7680 | consumed tokens: 15728640 | elapsed time per iteration (s): 0.33 | learning rate: 2.784E-05 | global batch size: 256 | lm loss: 9.543860E+00 | grad norm: 1.774 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 785.308 | TFLOPs: 27.49 | +7: iteration 40/ 21553 | consumed samples: 10240 | consumed tokens: 20971520 | elapsed time per iteration (s): 0.31 | learning rate: 3.712E-05 | global batch size: 256 | lm loss: 9.172691E+00 | grad norm: 1.631 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.159 | TFLOPs: 28.71 | +7: iteration 50/ 21553 | consumed samples: 12800 | consumed tokens: 26214400 | elapsed time per iteration (s): 0.32 | learning rate: 4.640E-05 | global batch size: 256 | lm loss: 8.768566E+00 | grad norm: 1.661 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 805.737 | TFLOPs: 28.21 | +7: iteration 60/ 21553 | consumed samples: 15360 | consumed tokens: 31457280 | elapsed time per iteration (s): 0.31 | learning rate: 5.568E-05 | global batch size: 256 | lm loss: 8.361397E+00 | grad norm: 1.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.520 | TFLOPs: 28.65 | +7: iteration 70/ 21553 | consumed samples: 17920 | consumed tokens: 36700160 | elapsed time per iteration (s): 0.32 | learning rate: 6.496E-05 | global batch size: 256 | lm loss: 7.977834E+00 | grad norm: 1.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.895 | TFLOPs: 28.32 | +7: iteration 80/ 21553 | consumed samples: 20480 | consumed tokens: 41943040 | elapsed time per iteration (s): 0.32 | learning rate: 7.424E-05 | global batch size: 256 | lm loss: 7.666939E+00 | grad norm: 1.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 806.397 | TFLOPs: 28.23 | +7: iteration 90/ 21553 | consumed samples: 23040 | consumed tokens: 47185920 | elapsed time per iteration (s): 0.32 | learning rate: 8.351E-05 | global batch size: 256 | lm loss: 7.362474E+00 | grad norm: 1.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 798.858 | TFLOPs: 27.97 | +7: iteration 100/ 21553 | consumed samples: 25600 | consumed tokens: 52428800 | elapsed time per iteration (s): 0.31 | learning rate: 9.279E-05 | global batch size: 256 | lm loss: 7.197829E+00 | grad norm: 1.104 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.382 | TFLOPs: 28.79 | +7: iteration 110/ 21553 | consumed samples: 28160 | consumed tokens: 57671680 | elapsed time per iteration (s): 0.32 | learning rate: 1.021E-04 | global batch size: 256 | lm loss: 7.048285E+00 | grad norm: 1.045 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.060 | TFLOPs: 28.29 | +7: iteration 120/ 21553 | consumed samples: 30720 | consumed tokens: 62914560 | elapsed time per iteration (s): 0.33 | learning rate: 1.114E-04 | global batch size: 256 | lm loss: 6.950978E+00 | grad norm: 1.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 771.625 | TFLOPs: 27.01 | +7: iteration 130/ 21553 | consumed samples: 33280 | consumed tokens: 68157440 | elapsed time per iteration (s): 0.32 | learning rate: 1.206E-04 | global batch size: 256 | lm loss: 6.802317E+00 | grad norm: 0.934 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 809.483 | TFLOPs: 28.34 | +7: iteration 140/ 21553 | consumed samples: 35840 | consumed tokens: 73400320 | elapsed time per iteration (s): 0.33 | learning rate: 1.299E-04 | global batch size: 256 | lm loss: 6.743581E+00 | grad norm: 0.950 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 786.742 | TFLOPs: 27.54 | +7: iteration 150/ 21553 | consumed samples: 38400 | consumed tokens: 78643200 | elapsed time per iteration (s): 0.32 | learning rate: 1.392E-04 | global batch size: 256 | lm loss: 6.639964E+00 | grad norm: 0.711 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 805.890 | TFLOPs: 28.21 | +7: iteration 160/ 21553 | consumed samples: 40960 | consumed tokens: 83886080 | elapsed time per iteration (s): 0.31 | learning rate: 1.485E-04 | global batch size: 256 | lm loss: 6.580158E+00 | grad norm: 0.972 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.166 | TFLOPs: 29.03 | +7: iteration 170/ 21553 | consumed samples: 43520 | consumed tokens: 89128960 | elapsed time per iteration (s): 0.33 | learning rate: 1.577E-04 | global batch size: 256 | lm loss: 6.526424E+00 | grad norm: 1.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 773.227 | TFLOPs: 27.07 | +7: iteration 180/ 21553 | consumed samples: 46080 | consumed tokens: 94371840 | elapsed time per iteration (s): 0.31 | learning rate: 1.670E-04 | global batch size: 256 | lm loss: 6.450418E+00 | grad norm: 0.630 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.775 | TFLOPs: 29.01 | +7: iteration 190/ 21553 | consumed samples: 48640 | consumed tokens: 99614720 | elapsed time per iteration (s): 0.31 | learning rate: 1.763E-04 | global batch size: 256 | lm loss: 6.395010E+00 | grad norm: 1.030 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.574 | TFLOPs: 28.62 | +7: iteration 200/ 21553 | consumed samples: 51200 | consumed tokens: 104857600 | elapsed time per iteration (s): 0.31 | learning rate: 1.856E-04 | global batch size: 256 | lm loss: 6.372811E+00 | grad norm: 0.902 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.088 | TFLOPs: 28.78 | +7: iteration 210/ 21553 | consumed samples: 53760 | consumed tokens: 110100480 | elapsed time per iteration (s): 0.31 | learning rate: 1.949E-04 | global batch size: 256 | lm loss: 6.286521E+00 | grad norm: 0.593 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.392 | TFLOPs: 28.93 | +7: iteration 220/ 21553 | consumed samples: 56320 | consumed tokens: 115343360 | elapsed time per iteration (s): 0.32 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.254720E+00 | grad norm: 0.923 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 795.824 | TFLOPs: 27.86 | +7: iteration 230/ 21553 | consumed samples: 58880 | consumed tokens: 120586240 | elapsed time per iteration (s): 0.31 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.175033E+00 | grad norm: 0.781 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.908 | TFLOPs: 28.60 | +7: iteration 240/ 21553 | consumed samples: 61440 | consumed tokens: 125829120 | elapsed time per iteration (s): 0.35 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.109267E+00 | grad norm: 0.687 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 736.705 | TFLOPs: 25.79 | +7: iteration 250/ 21553 | consumed samples: 64000 | consumed tokens: 131072000 | elapsed time per iteration (s): 0.33 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.103474E+00 | grad norm: 0.868 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 783.422 | TFLOPs: 27.43 | +7: iteration 260/ 21553 | consumed samples: 66560 | consumed tokens: 136314880 | elapsed time per iteration (s): 0.31 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.074475E+00 | grad norm: 0.950 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.510 | TFLOPs: 29.07 | +7: iteration 270/ 21553 | consumed samples: 69120 | consumed tokens: 141557760 | elapsed time per iteration (s): 0.32 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.022895E+00 | grad norm: 0.635 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 796.084 | TFLOPs: 27.87 | +7: iteration 280/ 21553 | consumed samples: 71680 | consumed tokens: 146800640 | elapsed time per iteration (s): 0.31 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.004956E+00 | grad norm: 1.066 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.931 | TFLOPs: 28.49 | +7: iteration 290/ 21553 | consumed samples: 74240 | consumed tokens: 152043520 | elapsed time per iteration (s): 0.31 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.967760E+00 | grad norm: 0.979 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.262 | TFLOPs: 28.93 | +7: iteration 300/ 21553 | consumed samples: 76800 | consumed tokens: 157286400 | elapsed time per iteration (s): 0.32 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.911633E+00 | grad norm: 1.011 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 803.581 | TFLOPs: 28.13 | +7: iteration 310/ 21553 | consumed samples: 79360 | consumed tokens: 162529280 | elapsed time per iteration (s): 0.32 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.876690E+00 | grad norm: 0.695 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.663 | TFLOPs: 28.45 | +7: iteration 320/ 21553 | consumed samples: 81920 | consumed tokens: 167772160 | elapsed time per iteration (s): 0.32 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.842651E+00 | grad norm: 1.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.278 | TFLOPs: 28.37 | +7: iteration 330/ 21553 | consumed samples: 84480 | consumed tokens: 173015040 | elapsed time per iteration (s): 0.32 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.824531E+00 | grad norm: 0.998 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 793.148 | TFLOPs: 27.77 | +7: iteration 340/ 21553 | consumed samples: 87040 | consumed tokens: 178257920 | elapsed time per iteration (s): 0.32 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.799118E+00 | grad norm: 0.551 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 803.650 | TFLOPs: 28.13 | +7: iteration 350/ 21553 | consumed samples: 89600 | consumed tokens: 183500800 | elapsed time per iteration (s): 0.31 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.746695E+00 | grad norm: 0.719 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.949 | TFLOPs: 28.53 | +7: iteration 360/ 21553 | consumed samples: 92160 | consumed tokens: 188743680 | elapsed time per iteration (s): 0.32 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.733448E+00 | grad norm: 1.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.143 | TFLOPs: 28.40 | +7: iteration 370/ 21553 | consumed samples: 94720 | consumed tokens: 193986560 | elapsed time per iteration (s): 0.31 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.708457E+00 | grad norm: 1.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.955 | TFLOPs: 28.56 | +7: iteration 380/ 21553 | consumed samples: 97280 | consumed tokens: 199229440 | elapsed time per iteration (s): 0.33 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.634396E+00 | grad norm: 0.841 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 770.903 | TFLOPs: 26.99 | +7: iteration 390/ 21553 | consumed samples: 99840 | consumed tokens: 204472320 | elapsed time per iteration (s): 0.31 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.645324E+00 | grad norm: 0.951 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.600 | TFLOPs: 28.66 | +7: iteration 400/ 21553 | consumed samples: 102400 | consumed tokens: 209715200 | elapsed time per iteration (s): 0.31 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.593137E+00 | grad norm: 0.630 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.881 | TFLOPs: 29.16 | +7: iteration 410/ 21553 | consumed samples: 104960 | consumed tokens: 214958080 | elapsed time per iteration (s): 0.31 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.549834E+00 | grad norm: 0.899 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.461 | TFLOPs: 28.48 | +7: iteration 420/ 21553 | consumed samples: 107520 | consumed tokens: 220200960 | elapsed time per iteration (s): 0.31 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.556754E+00 | grad norm: 0.863 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.074 | TFLOPs: 28.60 | +7: iteration 430/ 21553 | consumed samples: 110080 | consumed tokens: 225443840 | elapsed time per iteration (s): 0.31 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.499828E+00 | grad norm: 0.665 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.528 | TFLOPs: 28.86 | +7: iteration 440/ 21553 | consumed samples: 112640 | consumed tokens: 230686720 | elapsed time per iteration (s): 0.32 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.474654E+00 | grad norm: 0.885 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 788.167 | TFLOPs: 27.59 | +7: iteration 450/ 21553 | consumed samples: 115200 | consumed tokens: 235929600 | elapsed time per iteration (s): 0.32 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.453230E+00 | grad norm: 0.900 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.814 | TFLOPs: 28.31 | +7: iteration 460/ 21553 | consumed samples: 117760 | consumed tokens: 241172480 | elapsed time per iteration (s): 0.31 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.452872E+00 | grad norm: 0.880 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.434 | TFLOPs: 29.00 | +7: iteration 470/ 21553 | consumed samples: 120320 | consumed tokens: 246415360 | elapsed time per iteration (s): 0.31 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.401311E+00 | grad norm: 0.995 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.771 | TFLOPs: 28.45 | +7: iteration 480/ 21553 | consumed samples: 122880 | consumed tokens: 251658240 | elapsed time per iteration (s): 0.32 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.406313E+00 | grad norm: 1.045 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 807.842 | TFLOPs: 28.28 | +7: iteration 490/ 21553 | consumed samples: 125440 | consumed tokens: 256901120 | elapsed time per iteration (s): 0.31 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.375214E+00 | grad norm: 0.955 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.604 | TFLOPs: 28.97 | +7: iteration 500/ 21553 | consumed samples: 128000 | consumed tokens: 262144000 | elapsed time per iteration (s): 0.32 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.352453E+00 | grad norm: 0.865 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 793.350 | TFLOPs: 27.77 | +7: iteration 510/ 21553 | consumed samples: 130560 | consumed tokens: 267386880 | elapsed time per iteration (s): 0.31 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.322059E+00 | grad norm: 0.826 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.843 | TFLOPs: 28.63 | +7: iteration 520/ 21553 | consumed samples: 133120 | consumed tokens: 272629760 | elapsed time per iteration (s): 0.32 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.272181E+00 | grad norm: 0.866 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 792.305 | TFLOPs: 27.74 | +7: iteration 530/ 21553 | consumed samples: 135680 | consumed tokens: 277872640 | elapsed time per iteration (s): 0.32 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.256516E+00 | grad norm: 0.795 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 800.838 | TFLOPs: 28.04 | +7: iteration 540/ 21553 | consumed samples: 138240 | consumed tokens: 283115520 | elapsed time per iteration (s): 0.32 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.255307E+00 | grad norm: 1.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.214 | TFLOPs: 28.29 | +7: iteration 550/ 21553 | consumed samples: 140800 | consumed tokens: 288358400 | elapsed time per iteration (s): 0.32 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.215833E+00 | grad norm: 1.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 805.574 | TFLOPs: 28.20 | +7: iteration 560/ 21553 | consumed samples: 143360 | consumed tokens: 293601280 | elapsed time per iteration (s): 0.31 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.183479E+00 | grad norm: 1.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.490 | TFLOPs: 28.58 | +7: iteration 570/ 21553 | consumed samples: 145920 | consumed tokens: 298844160 | elapsed time per iteration (s): 0.33 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.150847E+00 | grad norm: 1.034 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 769.558 | TFLOPs: 26.94 | +7: iteration 580/ 21553 | consumed samples: 148480 | consumed tokens: 304087040 | elapsed time per iteration (s): 0.32 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.137214E+00 | grad norm: 0.819 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 790.344 | TFLOPs: 27.67 | +7: iteration 590/ 21553 | consumed samples: 151040 | consumed tokens: 309329920 | elapsed time per iteration (s): 0.31 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.121592E+00 | grad norm: 1.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.764 | TFLOPs: 29.22 | +7: iteration 600/ 21553 | consumed samples: 153600 | consumed tokens: 314572800 | elapsed time per iteration (s): 0.31 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.077212E+00 | grad norm: 0.873 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.819 | TFLOPs: 29.12 | +7: iteration 610/ 21553 | consumed samples: 156160 | consumed tokens: 319815680 | elapsed time per iteration (s): 0.32 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.043966E+00 | grad norm: 0.909 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 800.482 | TFLOPs: 28.02 | +7: iteration 620/ 21553 | consumed samples: 158720 | consumed tokens: 325058560 | elapsed time per iteration (s): 0.31 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.027021E+00 | grad norm: 0.880 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.441 | TFLOPs: 28.72 | +7: iteration 630/ 21553 | consumed samples: 161280 | consumed tokens: 330301440 | elapsed time per iteration (s): 0.31 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.012317E+00 | grad norm: 1.041 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.722 | TFLOPs: 28.63 | +7: iteration 640/ 21553 | consumed samples: 163840 | consumed tokens: 335544320 | elapsed time per iteration (s): 0.31 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.996245E+00 | grad norm: 1.052 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.980 | TFLOPs: 29.06 | +7: iteration 650/ 21553 | consumed samples: 166400 | consumed tokens: 340787200 | elapsed time per iteration (s): 0.31 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.939416E+00 | grad norm: 1.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.256 | TFLOPs: 28.64 | +7: iteration 660/ 21553 | consumed samples: 168960 | consumed tokens: 346030080 | elapsed time per iteration (s): 0.31 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.939497E+00 | grad norm: 1.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.936 | TFLOPs: 28.56 | +7: iteration 670/ 21553 | consumed samples: 171520 | consumed tokens: 351272960 | elapsed time per iteration (s): 0.31 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.889921E+00 | grad norm: 1.040 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.452 | TFLOPs: 28.48 | +7: iteration 680/ 21553 | consumed samples: 174080 | consumed tokens: 356515840 | elapsed time per iteration (s): 0.31 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.865115E+00 | grad norm: 0.937 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.502 | TFLOPs: 28.69 | +7: iteration 690/ 21553 | consumed samples: 176640 | consumed tokens: 361758720 | elapsed time per iteration (s): 0.33 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.852061E+00 | grad norm: 1.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 783.986 | TFLOPs: 27.45 | +7: iteration 700/ 21553 | consumed samples: 179200 | consumed tokens: 367001600 | elapsed time per iteration (s): 0.31 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.828179E+00 | grad norm: 1.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.943 | TFLOPs: 29.05 | +7: iteration 710/ 21553 | consumed samples: 181760 | consumed tokens: 372244480 | elapsed time per iteration (s): 0.31 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.779774E+00 | grad norm: 0.997 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.480 | TFLOPs: 29.00 | +7: iteration 720/ 21553 | consumed samples: 184320 | consumed tokens: 377487360 | elapsed time per iteration (s): 0.31 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.771882E+00 | grad norm: 1.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.769 | TFLOPs: 29.01 | +7: iteration 730/ 21553 | consumed samples: 186880 | consumed tokens: 382730240 | elapsed time per iteration (s): 0.31 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.722205E+00 | grad norm: 0.888 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.822 | TFLOPs: 28.84 | +7: iteration 740/ 21553 | consumed samples: 189440 | consumed tokens: 387973120 | elapsed time per iteration (s): 0.31 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.691141E+00 | grad norm: 1.062 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.384 | TFLOPs: 28.51 | +7: iteration 750/ 21553 | consumed samples: 192000 | consumed tokens: 393216000 | elapsed time per iteration (s): 0.31 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.642891E+00 | grad norm: 1.073 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.648 | TFLOPs: 28.62 | +7: iteration 760/ 21553 | consumed samples: 194560 | consumed tokens: 398458880 | elapsed time per iteration (s): 0.31 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.616951E+00 | grad norm: 1.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.832 | TFLOPs: 28.56 | +7: iteration 770/ 21553 | consumed samples: 197120 | consumed tokens: 403701760 | elapsed time per iteration (s): 0.31 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.590213E+00 | grad norm: 1.052 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.131 | TFLOPs: 28.75 | +7: iteration 780/ 21553 | consumed samples: 199680 | consumed tokens: 408944640 | elapsed time per iteration (s): 0.32 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.565181E+00 | grad norm: 0.858 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 805.553 | TFLOPs: 28.20 | +7: iteration 790/ 21553 | consumed samples: 202240 | consumed tokens: 414187520 | elapsed time per iteration (s): 0.32 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.537123E+00 | grad norm: 1.033 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.237 | TFLOPs: 28.43 | +7: iteration 800/ 21553 | consumed samples: 204800 | consumed tokens: 419430400 | elapsed time per iteration (s): 0.31 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.536582E+00 | grad norm: 1.084 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.761 | TFLOPs: 28.49 | +7: iteration 810/ 21553 | consumed samples: 207360 | consumed tokens: 424673280 | elapsed time per iteration (s): 0.32 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.499851E+00 | grad norm: 1.021 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.692 | TFLOPs: 28.42 | +7: iteration 820/ 21553 | consumed samples: 209920 | consumed tokens: 429916160 | elapsed time per iteration (s): 0.31 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.440710E+00 | grad norm: 1.005 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.483 | TFLOPs: 28.83 | +7: iteration 830/ 21553 | consumed samples: 212480 | consumed tokens: 435159040 | elapsed time per iteration (s): 0.32 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.475616E+00 | grad norm: 1.007 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 798.169 | TFLOPs: 27.94 | +7: iteration 840/ 21553 | consumed samples: 215040 | consumed tokens: 440401920 | elapsed time per iteration (s): 0.32 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.452062E+00 | grad norm: 0.801 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 796.581 | TFLOPs: 27.89 | +7: iteration 850/ 21553 | consumed samples: 217600 | consumed tokens: 445644800 | elapsed time per iteration (s): 0.32 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.401528E+00 | grad norm: 0.988 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 805.230 | TFLOPs: 28.19 | +7: iteration 860/ 21553 | consumed samples: 220160 | consumed tokens: 450887680 | elapsed time per iteration (s): 0.31 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.377635E+00 | grad norm: 1.041 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.406 | TFLOPs: 28.86 | +7: iteration 870/ 21553 | consumed samples: 222720 | consumed tokens: 456130560 | elapsed time per iteration (s): 0.31 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.378871E+00 | grad norm: 0.825 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.060 | TFLOPs: 28.67 | +7: iteration 880/ 21553 | consumed samples: 225280 | consumed tokens: 461373440 | elapsed time per iteration (s): 0.32 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.339180E+00 | grad norm: 0.987 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.678 | TFLOPs: 28.38 | +7: iteration 890/ 21553 | consumed samples: 227840 | consumed tokens: 466616320 | elapsed time per iteration (s): 0.31 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.325839E+00 | grad norm: 1.059 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.566 | TFLOPs: 28.83 | +7: iteration 900/ 21553 | consumed samples: 230400 | consumed tokens: 471859200 | elapsed time per iteration (s): 0.32 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.354144E+00 | grad norm: 0.948 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 790.680 | TFLOPs: 27.68 | +7: iteration 910/ 21553 | consumed samples: 232960 | consumed tokens: 477102080 | elapsed time per iteration (s): 0.31 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.336571E+00 | grad norm: 1.030 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.479 | TFLOPs: 28.69 | +7: iteration 920/ 21553 | consumed samples: 235520 | consumed tokens: 482344960 | elapsed time per iteration (s): 0.31 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.277897E+00 | grad norm: 0.844 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.557 | TFLOPs: 29.18 | +7: iteration 930/ 21553 | consumed samples: 238080 | consumed tokens: 487587840 | elapsed time per iteration (s): 0.31 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.258017E+00 | grad norm: 0.765 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.095 | TFLOPs: 28.60 | +7: iteration 940/ 21553 | consumed samples: 240640 | consumed tokens: 492830720 | elapsed time per iteration (s): 0.32 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.227305E+00 | grad norm: 0.677 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 804.706 | TFLOPs: 28.17 | +7: iteration 950/ 21553 | consumed samples: 243200 | consumed tokens: 498073600 | elapsed time per iteration (s): 0.32 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.230376E+00 | grad norm: 0.672 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.959 | TFLOPs: 28.39 | +7: iteration 960/ 21553 | consumed samples: 245760 | consumed tokens: 503316480 | elapsed time per iteration (s): 0.32 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.231272E+00 | grad norm: 1.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 791.528 | TFLOPs: 27.71 | +7: iteration 970/ 21553 | consumed samples: 248320 | consumed tokens: 508559360 | elapsed time per iteration (s): 0.31 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.223045E+00 | grad norm: 0.669 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.399 | TFLOPs: 29.21 | +7: iteration 980/ 21553 | consumed samples: 250880 | consumed tokens: 513802240 | elapsed time per iteration (s): 0.32 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.214310E+00 | grad norm: 0.823 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 799.998 | TFLOPs: 28.01 | +7: iteration 990/ 21553 | consumed samples: 253440 | consumed tokens: 519045120 | elapsed time per iteration (s): 0.31 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.182174E+00 | grad norm: 0.938 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.662 | TFLOPs: 28.52 | +7: iteration 1000/ 21553 | consumed samples: 256000 | consumed tokens: 524288000 | elapsed time per iteration (s): 0.31 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.211174E+00 | grad norm: 0.665 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.967 | TFLOPs: 29.23 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 1000 | lm loss value: 4.014799E+00 | lm loss PPL: 5.541214E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 1000 to checkpoints_146moscareap +0: [2022-11-29 17:12:29,240] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step1000 is begin to save! +0: [2022-11-29 17:12:29,261] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:12:29,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:12:29,351] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:12:29,367] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:12:29,367] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:12:29,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:12:29,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:12:29,399] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:12:29,399] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:12:29,420] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:12:29,420] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:12:29,443] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:12:29,444] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:12:29,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:12:29,464] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:12:29,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:12:29,479] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:12:29,495] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:12:29,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:12:29,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:12:29,511] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:12:29,526] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:12:29,526] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:12:29,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:12:29,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:12:29,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:12:29,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:12:29,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:12:29,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:12:29,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:12:29,590] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:12:29,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:12:29,606] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:12:29,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:12:29,607] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_146moscareap/global_step1000/mp_rank_00_model_states.pt +0: [2022-11-29 17:12:29,608] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:12:29,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:12:29,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:12:29,672] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:12:29,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:12:29,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:12:29,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:12:29,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:12:29,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:12:29,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:12:29,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:12:29,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:12:29,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:12:29,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:12:29,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:12:29,678] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:12:29,682] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:12:29,682] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:12:29,682] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:12:29,682] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:12:29,682] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:12:29,682] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:12:29,682] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:12:29,682] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:12:29,682] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:12:29,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:12:29,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:12:29,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:12:29,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:12:29,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:12:29,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:12:29,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:12:29,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:12:29,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:12:29,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:12:29,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:12:29,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:12:29,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:12:29,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:12:29,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:12:29,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:12:29,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:12:29,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:12:29,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:12:29,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:12:29,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:12:29,684] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:12:29,684] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:12:29,684] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:12:29,685] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:12:29,685] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:12:29,685] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:12:29,685] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:12:29,685] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:12:29,685] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:12:29,685] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:12:29,685] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:12:29,685] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:12:29,685] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:12:29,685] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:12:29,685] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:12:29,685] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:12:29,685] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:12:29,685] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:12:29,685] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:12:29,685] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:12:29,685] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:12:29,685] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:12:29,685] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:12:29,685] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:12:29,687] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:12:29,687] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:12:29,687] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:12:29,687] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:12:29,687] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:12:29,687] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:12:29,687] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:12:29,687] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:12:29,687] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:12:29,687] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:12:29,687] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:12:29,687] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:12:29,687] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:12:29,687] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:12:29,688] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:12:29,688] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:12:29,688] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:12:29,688] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:12:29,688] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:12:29,688] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:12:29,688] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:12:29,688] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:12:29,688] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:12:29,688] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:12:29,688] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:12:29,688] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:12:29,688] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:12:29,688] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:12:29,689] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:12:29,689] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:12:29,689] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:12:29,689] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:12:29,689] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:12:29,689] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:12:29,689] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:12:29,689] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:12:29,689] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:12:29,689] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:12:29,689] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:12:29,689] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:12:29,689] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:12:29,689] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:12:29,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:12:29,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:12:29,690] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +6: [2022-11-29 17:12:29,690] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +3: [2022-11-29 17:12:29,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:12:29,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:12:29,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:12:29,690] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +3: [2022-11-29 17:12:29,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:12:29,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:12:29,690] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:12:29,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:12:29,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:12:29,690] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:12:29,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:12:29,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:12:29,690] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:12:29,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:12:29,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:12:29,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:12:29,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:12:29,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:12:29,693] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:12:29,693] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:12:29,693] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:12:29,693] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:12:29,693] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:12:29,693] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:12:29,693] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:12:29,693] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:12:29,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:12:29,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:12:29,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:12:29,695] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:12:29,695] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:12:29,695] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:12:29,695] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:12:29,695] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:12:29,695] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:12:29,695] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:12:29,695] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:12:29,695] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:12:29,695] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:12:29,695] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:12:29,695] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:12:29,695] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:12:29,695] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:12:29,695] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:12:29,695] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:12:29,695] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:12:29,695] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:12:29,695] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:12:29,695] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:12:29,695] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:12:29,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:12:29,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:12:29,697] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:12:29,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:12:29,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:12:29,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:12:29,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:12:29,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:12:29,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:12:29,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:12:29,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:12:29,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:12:29,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:12:29,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:12:29,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:12:29,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:12:29,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:12:29,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:12:29,699] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:12:29,699] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:12:29,699] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:12:29,699] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:12:29,699] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:12:29,699] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:12:29,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:12:29,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:12:29,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:12:29,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:12:29,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: successfully saved checkpoint at iteration 1000 to checkpoints_146moscareap +7: time (ms) | save-checkpoint: 469.62 +7: iteration 1010/ 21553 | consumed samples: 258560 | consumed tokens: 529530880 | elapsed time per iteration (s): 0.38 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.167470E+00 | grad norm: 1.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 677.959 | TFLOPs: 23.73 | +7: iteration 1020/ 21553 | consumed samples: 261120 | consumed tokens: 534773760 | elapsed time per iteration (s): 0.32 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.171522E+00 | grad norm: 0.681 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 809.749 | TFLOPs: 28.35 | +7: iteration 1030/ 21553 | consumed samples: 263680 | consumed tokens: 540016640 | elapsed time per iteration (s): 0.31 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.153846E+00 | grad norm: 0.861 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.904 | TFLOPs: 28.95 | +7: iteration 1040/ 21553 | consumed samples: 266240 | consumed tokens: 545259520 | elapsed time per iteration (s): 0.32 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.123785E+00 | grad norm: 0.966 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 806.631 | TFLOPs: 28.24 | +7: iteration 1050/ 21553 | consumed samples: 268800 | consumed tokens: 550502400 | elapsed time per iteration (s): 0.33 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.132008E+00 | grad norm: 0.978 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 782.226 | TFLOPs: 27.38 | +7: iteration 1060/ 21553 | consumed samples: 271360 | consumed tokens: 555745280 | elapsed time per iteration (s): 0.31 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.126169E+00 | grad norm: 0.755 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.120 | TFLOPs: 28.50 | +7: iteration 1070/ 21553 | consumed samples: 273920 | consumed tokens: 560988160 | elapsed time per iteration (s): 0.31 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.099335E+00 | grad norm: 0.630 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.743 | TFLOPs: 28.87 | +7: iteration 1080/ 21553 | consumed samples: 276480 | consumed tokens: 566231040 | elapsed time per iteration (s): 0.32 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.087637E+00 | grad norm: 0.707 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.682 | TFLOPs: 28.45 | +7: iteration 1090/ 21553 | consumed samples: 279040 | consumed tokens: 571473920 | elapsed time per iteration (s): 0.31 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.094578E+00 | grad norm: 0.611 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.541 | TFLOPs: 29.07 | +7: iteration 1100/ 21553 | consumed samples: 281600 | consumed tokens: 576716800 | elapsed time per iteration (s): 0.31 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.076498E+00 | grad norm: 0.698 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.669 | TFLOPs: 29.08 | +7: iteration 1110/ 21553 | consumed samples: 284160 | consumed tokens: 581959680 | elapsed time per iteration (s): 0.32 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.041076E+00 | grad norm: 0.622 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 794.046 | TFLOPs: 27.80 | +7: iteration 1120/ 21553 | consumed samples: 286720 | consumed tokens: 587202560 | elapsed time per iteration (s): 0.31 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.041511E+00 | grad norm: 0.579 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.739 | TFLOPs: 28.63 | +7: iteration 1130/ 21553 | consumed samples: 289280 | consumed tokens: 592445440 | elapsed time per iteration (s): 0.32 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.038694E+00 | grad norm: 0.695 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 796.629 | TFLOPs: 27.89 | +7: iteration 1140/ 21553 | consumed samples: 291840 | consumed tokens: 597688320 | elapsed time per iteration (s): 0.31 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.047325E+00 | grad norm: 0.629 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.954 | TFLOPs: 28.91 | +7: iteration 1150/ 21553 | consumed samples: 294400 | consumed tokens: 602931200 | elapsed time per iteration (s): 0.31 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 4.030787E+00 | grad norm: 1.014 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.365 | TFLOPs: 28.79 | +7: iteration 1160/ 21553 | consumed samples: 296960 | consumed tokens: 608174080 | elapsed time per iteration (s): 0.31 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 4.045963E+00 | grad norm: 0.594 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.074 | TFLOPs: 28.71 | +7: iteration 1170/ 21553 | consumed samples: 299520 | consumed tokens: 613416960 | elapsed time per iteration (s): 0.31 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 4.033577E+00 | grad norm: 0.790 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.140 | TFLOPs: 28.99 | +7: iteration 1180/ 21553 | consumed samples: 302080 | consumed tokens: 618659840 | elapsed time per iteration (s): 0.31 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 4.016236E+00 | grad norm: 0.725 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.402 | TFLOPs: 29.07 | +7: iteration 1190/ 21553 | consumed samples: 304640 | consumed tokens: 623902720 | elapsed time per iteration (s): 0.31 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 4.064274E+00 | grad norm: 0.642 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.751 | TFLOPs: 28.94 | +7: iteration 1200/ 21553 | consumed samples: 307200 | consumed tokens: 629145600 | elapsed time per iteration (s): 0.31 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 4.001836E+00 | grad norm: 0.613 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.025 | TFLOPs: 28.74 | +7: iteration 1210/ 21553 | consumed samples: 309760 | consumed tokens: 634388480 | elapsed time per iteration (s): 0.33 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 3.987305E+00 | grad norm: 0.736 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 774.856 | TFLOPs: 27.13 | +7: iteration 1220/ 21553 | consumed samples: 312320 | consumed tokens: 639631360 | elapsed time per iteration (s): 0.31 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 3.993578E+00 | grad norm: 0.810 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.326 | TFLOPs: 28.68 | +7: iteration 1230/ 21553 | consumed samples: 314880 | consumed tokens: 644874240 | elapsed time per iteration (s): 0.31 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 3.983152E+00 | grad norm: 0.518 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.492 | TFLOPs: 28.55 | +7: iteration 1240/ 21553 | consumed samples: 317440 | consumed tokens: 650117120 | elapsed time per iteration (s): 0.31 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 4.010371E+00 | grad norm: 0.630 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.561 | TFLOPs: 29.18 | +7: iteration 1250/ 21553 | consumed samples: 320000 | consumed tokens: 655360000 | elapsed time per iteration (s): 0.30 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 3.973061E+00 | grad norm: 0.649 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.956 | TFLOPs: 29.40 | +7: iteration 1260/ 21553 | consumed samples: 322560 | consumed tokens: 660602880 | elapsed time per iteration (s): 0.31 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 3.977309E+00 | grad norm: 0.587 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.328 | TFLOPs: 29.35 | +7: iteration 1270/ 21553 | consumed samples: 325120 | consumed tokens: 665845760 | elapsed time per iteration (s): 0.32 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 3.973532E+00 | grad norm: 0.720 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 805.770 | TFLOPs: 28.21 | +7: iteration 1280/ 21553 | consumed samples: 327680 | consumed tokens: 671088640 | elapsed time per iteration (s): 0.31 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 3.956145E+00 | grad norm: 0.661 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.352 | TFLOPs: 28.68 | +7: iteration 1290/ 21553 | consumed samples: 330240 | consumed tokens: 676331520 | elapsed time per iteration (s): 0.31 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 3.944550E+00 | grad norm: 0.614 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.811 | TFLOPs: 28.63 | +7: iteration 1300/ 21553 | consumed samples: 332800 | consumed tokens: 681574400 | elapsed time per iteration (s): 0.31 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 3.959758E+00 | grad norm: 0.609 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.847 | TFLOPs: 28.60 | +7: iteration 1310/ 21553 | consumed samples: 335360 | consumed tokens: 686817280 | elapsed time per iteration (s): 0.31 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 3.948388E+00 | grad norm: 0.851 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.935 | TFLOPs: 29.16 | +7: iteration 1320/ 21553 | consumed samples: 337920 | consumed tokens: 692060160 | elapsed time per iteration (s): 0.32 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 3.936448E+00 | grad norm: 0.594 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.059 | TFLOPs: 28.43 | +7: iteration 1330/ 21553 | consumed samples: 340480 | consumed tokens: 697303040 | elapsed time per iteration (s): 0.31 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 3.911626E+00 | grad norm: 0.618 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.405 | TFLOPs: 28.97 | +7: iteration 1340/ 21553 | consumed samples: 343040 | consumed tokens: 702545920 | elapsed time per iteration (s): 0.30 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 3.906049E+00 | grad norm: 0.583 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.482 | TFLOPs: 29.39 | +7: iteration 1350/ 21553 | consumed samples: 345600 | consumed tokens: 707788800 | elapsed time per iteration (s): 0.31 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 3.909462E+00 | grad norm: 0.802 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.993 | TFLOPs: 28.92 | +7: iteration 1360/ 21553 | consumed samples: 348160 | consumed tokens: 713031680 | elapsed time per iteration (s): 0.30 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 3.911971E+00 | grad norm: 0.600 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.397 | TFLOPs: 29.49 | +7: iteration 1370/ 21553 | consumed samples: 350720 | consumed tokens: 718274560 | elapsed time per iteration (s): 0.31 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 3.889517E+00 | grad norm: 0.646 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.717 | TFLOPs: 28.66 | +7: iteration 1380/ 21553 | consumed samples: 353280 | consumed tokens: 723517440 | elapsed time per iteration (s): 0.31 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 3.883092E+00 | grad norm: 0.567 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.829 | TFLOPs: 29.19 | +7: iteration 1390/ 21553 | consumed samples: 355840 | consumed tokens: 728760320 | elapsed time per iteration (s): 0.31 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 3.880702E+00 | grad norm: 0.702 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.680 | TFLOPs: 29.01 | +7: iteration 1400/ 21553 | consumed samples: 358400 | consumed tokens: 734003200 | elapsed time per iteration (s): 0.31 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 3.896849E+00 | grad norm: 0.680 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.597 | TFLOPs: 29.29 | +7: iteration 1410/ 21553 | consumed samples: 360960 | consumed tokens: 739246080 | elapsed time per iteration (s): 0.31 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 3.874232E+00 | grad norm: 0.588 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.507 | TFLOPs: 28.97 | +7: iteration 1420/ 21553 | consumed samples: 363520 | consumed tokens: 744488960 | elapsed time per iteration (s): 0.31 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 3.856738E+00 | grad norm: 0.676 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.473 | TFLOPs: 29.04 | +7: iteration 1430/ 21553 | consumed samples: 366080 | consumed tokens: 749731840 | elapsed time per iteration (s): 0.31 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 3.898909E+00 | grad norm: 0.771 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.249 | TFLOPs: 28.61 | +7: iteration 1440/ 21553 | consumed samples: 368640 | consumed tokens: 754974720 | elapsed time per iteration (s): 0.31 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 3.864341E+00 | grad norm: 0.628 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.704 | TFLOPs: 28.87 | +7: iteration 1450/ 21553 | consumed samples: 371200 | consumed tokens: 760217600 | elapsed time per iteration (s): 0.32 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 3.876783E+00 | grad norm: 0.605 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.917 | TFLOPs: 28.39 | +7: iteration 1460/ 21553 | consumed samples: 373760 | consumed tokens: 765460480 | elapsed time per iteration (s): 0.31 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 3.854893E+00 | grad norm: 0.658 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.186 | TFLOPs: 29.17 | +7: iteration 1470/ 21553 | consumed samples: 376320 | consumed tokens: 770703360 | elapsed time per iteration (s): 0.31 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 3.871917E+00 | grad norm: 0.614 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.174 | TFLOPs: 29.20 | +7: iteration 1480/ 21553 | consumed samples: 378880 | consumed tokens: 775946240 | elapsed time per iteration (s): 0.31 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 3.875094E+00 | grad norm: 0.684 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.469 | TFLOPs: 28.69 | +7: iteration 1490/ 21553 | consumed samples: 381440 | consumed tokens: 781189120 | elapsed time per iteration (s): 0.31 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 3.819224E+00 | grad norm: 0.487 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.786 | TFLOPs: 28.94 | +7: iteration 1500/ 21553 | consumed samples: 384000 | consumed tokens: 786432000 | elapsed time per iteration (s): 0.31 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 3.839270E+00 | grad norm: 0.654 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.540 | TFLOPs: 29.11 | +7: iteration 1510/ 21553 | consumed samples: 386560 | consumed tokens: 791674880 | elapsed time per iteration (s): 0.32 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 3.855684E+00 | grad norm: 0.589 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 805.491 | TFLOPs: 28.20 | +7: iteration 1520/ 21553 | consumed samples: 389120 | consumed tokens: 796917760 | elapsed time per iteration (s): 0.32 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 3.824246E+00 | grad norm: 0.523 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 795.440 | TFLOPs: 27.85 | +7: iteration 1530/ 21553 | consumed samples: 391680 | consumed tokens: 802160640 | elapsed time per iteration (s): 0.31 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 3.811898E+00 | grad norm: 0.634 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.905 | TFLOPs: 28.67 | +7: iteration 1540/ 21553 | consumed samples: 394240 | consumed tokens: 807403520 | elapsed time per iteration (s): 0.32 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 3.848633E+00 | grad norm: 0.625 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 803.288 | TFLOPs: 28.12 | +7: iteration 1550/ 21553 | consumed samples: 396800 | consumed tokens: 812646400 | elapsed time per iteration (s): 0.31 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 3.805587E+00 | grad norm: 0.548 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.075 | TFLOPs: 28.67 | +7: iteration 1560/ 21553 | consumed samples: 399360 | consumed tokens: 817889280 | elapsed time per iteration (s): 0.31 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 3.797489E+00 | grad norm: 0.466 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.530 | TFLOPs: 28.90 | +7: iteration 1570/ 21553 | consumed samples: 401920 | consumed tokens: 823132160 | elapsed time per iteration (s): 0.31 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 3.793907E+00 | grad norm: 0.685 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.556 | TFLOPs: 29.01 | +7: iteration 1580/ 21553 | consumed samples: 404480 | consumed tokens: 828375040 | elapsed time per iteration (s): 0.31 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 3.770703E+00 | grad norm: 0.534 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.395 | TFLOPs: 28.68 | +7: iteration 1590/ 21553 | consumed samples: 407040 | consumed tokens: 833617920 | elapsed time per iteration (s): 0.32 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 3.776468E+00 | grad norm: 0.617 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 799.731 | TFLOPs: 28.00 | +7: iteration 1600/ 21553 | consumed samples: 409600 | consumed tokens: 838860800 | elapsed time per iteration (s): 0.31 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 3.817098E+00 | grad norm: 0.747 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.952 | TFLOPs: 28.84 | +7: iteration 1610/ 21553 | consumed samples: 412160 | consumed tokens: 844103680 | elapsed time per iteration (s): 0.31 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 3.781022E+00 | grad norm: 0.620 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.331 | TFLOPs: 28.51 | +7: iteration 1620/ 21553 | consumed samples: 414720 | consumed tokens: 849346560 | elapsed time per iteration (s): 0.33 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 3.798191E+00 | grad norm: 0.796 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 782.002 | TFLOPs: 27.38 | +7: iteration 1630/ 21553 | consumed samples: 417280 | consumed tokens: 854589440 | elapsed time per iteration (s): 0.31 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 3.797713E+00 | grad norm: 0.562 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.956 | TFLOPs: 29.26 | +7: iteration 1640/ 21553 | consumed samples: 419840 | consumed tokens: 859832320 | elapsed time per iteration (s): 0.31 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 3.784192E+00 | grad norm: 0.539 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.368 | TFLOPs: 28.96 | +7: iteration 1650/ 21553 | consumed samples: 422400 | consumed tokens: 865075200 | elapsed time per iteration (s): 0.31 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 3.788105E+00 | grad norm: 0.543 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.069 | TFLOPs: 28.60 | +7: iteration 1660/ 21553 | consumed samples: 424960 | consumed tokens: 870318080 | elapsed time per iteration (s): 0.32 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 3.784713E+00 | grad norm: 0.719 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 790.149 | TFLOPs: 27.66 | +7: iteration 1670/ 21553 | consumed samples: 427520 | consumed tokens: 875560960 | elapsed time per iteration (s): 0.31 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 3.778352E+00 | grad norm: 0.547 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.061 | TFLOPs: 28.78 | +7: iteration 1680/ 21553 | consumed samples: 430080 | consumed tokens: 880803840 | elapsed time per iteration (s): 0.33 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 3.752776E+00 | grad norm: 0.579 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 783.673 | TFLOPs: 27.43 | +7: iteration 1690/ 21553 | consumed samples: 432640 | consumed tokens: 886046720 | elapsed time per iteration (s): 0.33 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 3.785247E+00 | grad norm: 0.718 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 783.383 | TFLOPs: 27.42 | +7: iteration 1700/ 21553 | consumed samples: 435200 | consumed tokens: 891289600 | elapsed time per iteration (s): 0.31 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 3.746379E+00 | grad norm: 0.485 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.882 | TFLOPs: 28.77 | +7: iteration 1710/ 21553 | consumed samples: 437760 | consumed tokens: 896532480 | elapsed time per iteration (s): 0.32 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 3.739465E+00 | grad norm: 0.706 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 809.722 | TFLOPs: 28.35 | +7: iteration 1720/ 21553 | consumed samples: 440320 | consumed tokens: 901775360 | elapsed time per iteration (s): 0.31 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 3.769103E+00 | grad norm: 0.561 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.004 | TFLOPs: 28.67 | +7: iteration 1730/ 21553 | consumed samples: 442880 | consumed tokens: 907018240 | elapsed time per iteration (s): 0.30 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 3.744893E+00 | grad norm: 0.489 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.641 | TFLOPs: 29.43 | +7: iteration 1740/ 21553 | consumed samples: 445440 | consumed tokens: 912261120 | elapsed time per iteration (s): 0.31 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 3.756224E+00 | grad norm: 0.784 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.636 | TFLOPs: 28.69 | +7: iteration 1750/ 21553 | consumed samples: 448000 | consumed tokens: 917504000 | elapsed time per iteration (s): 0.31 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 3.764635E+00 | grad norm: 0.680 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.112 | TFLOPs: 28.57 | +7: iteration 1760/ 21553 | consumed samples: 450560 | consumed tokens: 922746880 | elapsed time per iteration (s): 0.31 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 3.719016E+00 | grad norm: 0.559 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.713 | TFLOPs: 28.56 | +7: iteration 1770/ 21553 | consumed samples: 453120 | consumed tokens: 927989760 | elapsed time per iteration (s): 0.31 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 3.741069E+00 | grad norm: 0.628 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.894 | TFLOPs: 28.63 | +7: iteration 1780/ 21553 | consumed samples: 455680 | consumed tokens: 933232640 | elapsed time per iteration (s): 0.31 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 3.733029E+00 | grad norm: 0.627 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.775 | TFLOPs: 28.73 | +7: iteration 1790/ 21553 | consumed samples: 458240 | consumed tokens: 938475520 | elapsed time per iteration (s): 0.31 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 3.737641E+00 | grad norm: 0.605 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.922 | TFLOPs: 29.05 | +7: iteration 1800/ 21553 | consumed samples: 460800 | consumed tokens: 943718400 | elapsed time per iteration (s): 0.31 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 3.747245E+00 | grad norm: 0.502 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.166 | TFLOPs: 28.85 | +7: iteration 1810/ 21553 | consumed samples: 463360 | consumed tokens: 948961280 | elapsed time per iteration (s): 0.32 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 3.732231E+00 | grad norm: 0.663 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 795.276 | TFLOPs: 27.84 | +7: iteration 1820/ 21553 | consumed samples: 465920 | consumed tokens: 954204160 | elapsed time per iteration (s): 0.32 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 3.714897E+00 | grad norm: 0.548 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 803.869 | TFLOPs: 28.14 | +7: iteration 1830/ 21553 | consumed samples: 468480 | consumed tokens: 959447040 | elapsed time per iteration (s): 0.31 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 3.757443E+00 | grad norm: 0.525 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.278 | TFLOPs: 28.93 | +7: iteration 1840/ 21553 | consumed samples: 471040 | consumed tokens: 964689920 | elapsed time per iteration (s): 0.32 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 3.729536E+00 | grad norm: 0.543 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 804.655 | TFLOPs: 28.17 | +7: iteration 1850/ 21553 | consumed samples: 473600 | consumed tokens: 969932800 | elapsed time per iteration (s): 0.31 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 3.716697E+00 | grad norm: 0.549 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.008 | TFLOPs: 28.57 | +7: iteration 1860/ 21553 | consumed samples: 476160 | consumed tokens: 975175680 | elapsed time per iteration (s): 0.31 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 3.706792E+00 | grad norm: 0.446 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.827 | TFLOPs: 28.70 | +7: iteration 1870/ 21553 | consumed samples: 478720 | consumed tokens: 980418560 | elapsed time per iteration (s): 0.31 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 3.671445E+00 | grad norm: 0.655 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.234 | TFLOPs: 29.34 | +7: iteration 1880/ 21553 | consumed samples: 481280 | consumed tokens: 985661440 | elapsed time per iteration (s): 0.32 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 3.684677E+00 | grad norm: 0.529 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.319 | TFLOPs: 28.44 | +7: iteration 1890/ 21553 | consumed samples: 483840 | consumed tokens: 990904320 | elapsed time per iteration (s): 0.31 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 3.708041E+00 | grad norm: 0.618 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.160 | TFLOPs: 29.10 | +7: iteration 1900/ 21553 | consumed samples: 486400 | consumed tokens: 996147200 | elapsed time per iteration (s): 0.32 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 3.702869E+00 | grad norm: 0.621 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.082 | TFLOPs: 28.29 | +7: iteration 1910/ 21553 | consumed samples: 488960 | consumed tokens: 1001390080 | elapsed time per iteration (s): 0.31 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 3.710927E+00 | grad norm: 0.487 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.679 | TFLOPs: 28.59 | +7: iteration 1920/ 21553 | consumed samples: 491520 | consumed tokens: 1006632960 | elapsed time per iteration (s): 0.31 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 3.668325E+00 | grad norm: 0.498 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.656 | TFLOPs: 28.83 | +7: iteration 1930/ 21553 | consumed samples: 494080 | consumed tokens: 1011875840 | elapsed time per iteration (s): 0.32 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 3.679150E+00 | grad norm: 0.605 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.831 | TFLOPs: 28.38 | +7: iteration 1940/ 21553 | consumed samples: 496640 | consumed tokens: 1017118720 | elapsed time per iteration (s): 0.31 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 3.704392E+00 | grad norm: 0.640 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.040 | TFLOPs: 28.95 | +7: iteration 1950/ 21553 | consumed samples: 499200 | consumed tokens: 1022361600 | elapsed time per iteration (s): 0.31 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 3.719826E+00 | grad norm: 1.055 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.058 | TFLOPs: 28.60 | +7: iteration 1960/ 21553 | consumed samples: 501760 | consumed tokens: 1027604480 | elapsed time per iteration (s): 0.31 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 3.723594E+00 | grad norm: 0.530 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.610 | TFLOPs: 28.94 | +7: iteration 1970/ 21553 | consumed samples: 504320 | consumed tokens: 1032847360 | elapsed time per iteration (s): 0.31 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 3.711871E+00 | grad norm: 0.650 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.254 | TFLOPs: 29.06 | +7: iteration 1980/ 21553 | consumed samples: 506880 | consumed tokens: 1038090240 | elapsed time per iteration (s): 0.32 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 3.683799E+00 | grad norm: 0.465 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 797.972 | TFLOPs: 27.93 | +7: iteration 1990/ 21553 | consumed samples: 509440 | consumed tokens: 1043333120 | elapsed time per iteration (s): 0.31 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 3.670525E+00 | grad norm: 0.499 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.438 | TFLOPs: 28.69 | +0: [2022-11-29 17:17:42,811] [INFO] [logging.py:68:log_dist] [Rank 0] step=2000, skipped=0, lr=[0.00019691153209285103, 0.00019691153209285103, 0.00019691153209285103], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 2000/ 21553 | consumed samples: 512000 | consumed tokens: 1048576000 | elapsed time per iteration (s): 0.33 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 3.675546E+00 | grad norm: 0.536 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 774.647 | TFLOPs: 27.12 | +0: steps: 2000 loss: 3.6656 iter time (s): 0.318 samples/sec: 803.963 +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 2000 | lm loss value: 3.562869E+00 | lm loss PPL: 3.526424E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 2000 to checkpoints_146moscareap +0: [2022-11-29 17:17:42,941] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step2000 is begin to save! +0: [2022-11-29 17:17:42,945] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:17:43,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:17:43,071] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:17:43,093] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:17:43,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:17:43,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:17:43,115] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:17:43,137] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:17:43,137] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:17:43,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:17:43,160] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:17:43,183] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:17:43,184] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:17:43,206] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:17:43,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:17:43,225] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:17:43,225] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:17:43,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:17:43,241] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:17:43,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:17:43,256] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:17:43,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:17:43,272] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:17:43,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:17:43,287] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:17:43,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:17:43,303] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:17:43,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:17:43,318] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:17:43,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:17:43,334] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:17:43,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:17:43,349] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:17:43,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:17:43,351] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_146moscareap/global_step2000/mp_rank_00_model_states.pt +0: [2022-11-29 17:17:43,351] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:17:43,353] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:17:43,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:17:43,403] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:17:43,403] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:17:43,403] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:17:43,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:17:43,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:17:43,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:17:43,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:17:43,406] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:17:43,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:17:43,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:17:43,406] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:17:43,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:17:43,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:17:43,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:17:43,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:17:43,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:17:43,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:17:43,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:17:43,408] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:17:43,408] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +0: [2022-11-29 17:17:43,408] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:17:43,408] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:17:43,408] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:17:43,408] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:17:43,408] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:17:43,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:17:43,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:17:43,409] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:17:43,409] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:17:43,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:17:43,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:17:43,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:17:43,410] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +2: [2022-11-29 17:17:43,410] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:17:43,410] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:17:43,410] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:17:43,410] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:17:43,410] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:17:43,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:17:43,410] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:17:43,410] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:17:43,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:17:43,410] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:17:43,410] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:17:43,411] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:17:43,411] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:17:43,411] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:17:43,411] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:17:43,411] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:17:43,411] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:17:43,409] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:17:43,409] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:17:43,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:17:43,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:17:43,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:17:43,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:17:43,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:17:43,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:17:43,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:17:43,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:17:43,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:17:43,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:17:43,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:17:43,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:17:43,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:17:43,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:17:43,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:17:43,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:17:43,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:17:43,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:17:43,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:17:43,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:17:43,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:17:43,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:17:43,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:17:43,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +3: [2022-11-29 17:17:43,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:17:43,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +1: [2022-11-29 17:17:43,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:17:43,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:17:43,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:17:43,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:17:43,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:17:43,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +1: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:17:43,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +4: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:17:43,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:17:43,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +1: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:17:43,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +3: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:17:43,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:17:43,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:17:43,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:17:43,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +5: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:17:43,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:17:43,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:17:43,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:17:43,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +1: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:17:43,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +3: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:17:43,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +2: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:17:43,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +6: [2022-11-29 17:17:43,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +2: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:17:43,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:17:43,416] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:17:43,416] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:17:43,416] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:17:43,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:17:43,416] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:17:43,416] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +6: [2022-11-29 17:17:43,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:17:43,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:17:43,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:17:43,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:17:43,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:17:43,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:17:43,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:17:43,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:17:43,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:17:43,416] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:17:43,416] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:17:43,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:17:43,416] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:17:43,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:17:43,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:17:43,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:17:43,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +5: [2022-11-29 17:17:43,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:17:43,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:17:43,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:17:43,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:17:43,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:17:43,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:17:43,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:17:43,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:17:43,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:17:43,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:17:43,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:17:43,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:17:43,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:17:43,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:17:43,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:17:43,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:17:43,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:17:43,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:17:43,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:17:43,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:17:43,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:17:43,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:17:43,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:17:43,420] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:17:43,420] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:17:43,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:17:43,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:17:43,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:17:43,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:17:43,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:17:43,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:17:43,423] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:17:43,423] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:17:43,423] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:17:43,424] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:17:43,424] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: successfully saved checkpoint at iteration 2000 to checkpoints_146moscareap +7: time (ms) | save-checkpoint: 495.66 +7: iteration 2010/ 21553 | consumed samples: 514560 | consumed tokens: 1053818880 | elapsed time per iteration (s): 0.39 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 3.655590E+00 | grad norm: 0.570 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 664.240 | TFLOPs: 23.25 | +7: iteration 2020/ 21553 | consumed samples: 517120 | consumed tokens: 1059061760 | elapsed time per iteration (s): 0.31 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 3.660426E+00 | grad norm: 0.512 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.959 | TFLOPs: 28.49 | +7: iteration 2030/ 21553 | consumed samples: 519680 | consumed tokens: 1064304640 | elapsed time per iteration (s): 0.31 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 3.675495E+00 | grad norm: 0.645 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.236 | TFLOPs: 29.03 | +7: iteration 2040/ 21553 | consumed samples: 522240 | consumed tokens: 1069547520 | elapsed time per iteration (s): 0.31 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 3.647219E+00 | grad norm: 0.537 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.318 | TFLOPs: 29.07 | +7: iteration 2050/ 21553 | consumed samples: 524800 | consumed tokens: 1074790400 | elapsed time per iteration (s): 0.31 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 3.647337E+00 | grad norm: 0.472 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.915 | TFLOPs: 29.19 | +7: iteration 2060/ 21553 | consumed samples: 527360 | consumed tokens: 1080033280 | elapsed time per iteration (s): 0.31 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 3.653398E+00 | grad norm: 0.573 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.612 | TFLOPs: 28.76 | +7: iteration 2070/ 21553 | consumed samples: 529920 | consumed tokens: 1085276160 | elapsed time per iteration (s): 0.31 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 3.633658E+00 | grad norm: 0.603 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.060 | TFLOPs: 28.71 | +7: iteration 2080/ 21553 | consumed samples: 532480 | consumed tokens: 1090519040 | elapsed time per iteration (s): 0.31 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 3.639613E+00 | grad norm: 0.533 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.846 | TFLOPs: 29.30 | +7: iteration 2090/ 21553 | consumed samples: 535040 | consumed tokens: 1095761920 | elapsed time per iteration (s): 0.32 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 3.614852E+00 | grad norm: 0.588 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 802.284 | TFLOPs: 28.09 | +7: iteration 2100/ 21553 | consumed samples: 537600 | consumed tokens: 1101004800 | elapsed time per iteration (s): 0.31 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 3.644157E+00 | grad norm: 0.479 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.456 | TFLOPs: 29.00 | +7: iteration 2110/ 21553 | consumed samples: 540160 | consumed tokens: 1106247680 | elapsed time per iteration (s): 0.32 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 3.654459E+00 | grad norm: 0.559 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 805.359 | TFLOPs: 28.19 | +7: iteration 2120/ 21553 | consumed samples: 542720 | consumed tokens: 1111490560 | elapsed time per iteration (s): 0.30 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 3.631752E+00 | grad norm: 0.508 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.122 | TFLOPs: 29.45 | +7: iteration 2130/ 21553 | consumed samples: 545280 | consumed tokens: 1116733440 | elapsed time per iteration (s): 0.31 | learning rate: 1.964E-04 | global batch size: 256 | lm loss: 3.619162E+00 | grad norm: 0.435 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.750 | TFLOPs: 29.12 | +7: iteration 2140/ 21553 | consumed samples: 547840 | consumed tokens: 1121976320 | elapsed time per iteration (s): 0.31 | learning rate: 1.964E-04 | global batch size: 256 | lm loss: 3.635258E+00 | grad norm: 0.542 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.625 | TFLOPs: 28.48 | +7: iteration 2150/ 21553 | consumed samples: 550400 | consumed tokens: 1127219200 | elapsed time per iteration (s): 0.31 | learning rate: 1.964E-04 | global batch size: 256 | lm loss: 3.628497E+00 | grad norm: 0.508 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.063 | TFLOPs: 28.95 | +7: iteration 2160/ 21553 | consumed samples: 552960 | consumed tokens: 1132462080 | elapsed time per iteration (s): 0.31 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 3.652650E+00 | grad norm: 0.528 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.278 | TFLOPs: 29.35 | +7: iteration 2170/ 21553 | consumed samples: 555520 | consumed tokens: 1137704960 | elapsed time per iteration (s): 0.33 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 3.627083E+00 | grad norm: 0.501 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 774.895 | TFLOPs: 27.13 | +7: iteration 2180/ 21553 | consumed samples: 558080 | consumed tokens: 1142947840 | elapsed time per iteration (s): 0.32 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 3.628107E+00 | grad norm: 0.524 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.931 | TFLOPs: 28.39 | +7: iteration 2190/ 21553 | consumed samples: 560640 | consumed tokens: 1148190720 | elapsed time per iteration (s): 0.31 | learning rate: 1.962E-04 | global batch size: 256 | lm loss: 3.616873E+00 | grad norm: 0.483 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.455 | TFLOPs: 28.65 | +7: iteration 2200/ 21553 | consumed samples: 563200 | consumed tokens: 1153433600 | elapsed time per iteration (s): 0.31 | learning rate: 1.962E-04 | global batch size: 256 | lm loss: 3.610072E+00 | grad norm: 0.476 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.401 | TFLOPs: 29.00 | +7: iteration 2210/ 21553 | consumed samples: 565760 | consumed tokens: 1158676480 | elapsed time per iteration (s): 0.31 | learning rate: 1.961E-04 | global batch size: 256 | lm loss: 3.618685E+00 | grad norm: 0.525 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.595 | TFLOPs: 29.11 | +7: iteration 2220/ 21553 | consumed samples: 568320 | consumed tokens: 1163919360 | elapsed time per iteration (s): 0.31 | learning rate: 1.961E-04 | global batch size: 256 | lm loss: 3.620301E+00 | grad norm: 0.489 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.661 | TFLOPs: 29.04 | +7: iteration 2230/ 21553 | consumed samples: 570880 | consumed tokens: 1169162240 | elapsed time per iteration (s): 0.32 | learning rate: 1.961E-04 | global batch size: 256 | lm loss: 3.605814E+00 | grad norm: 0.500 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 809.977 | TFLOPs: 28.36 | +7: iteration 2240/ 21553 | consumed samples: 573440 | consumed tokens: 1174405120 | elapsed time per iteration (s): 0.30 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 3.622008E+00 | grad norm: 0.451 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.579 | TFLOPs: 29.43 | +7: iteration 2250/ 21553 | consumed samples: 576000 | consumed tokens: 1179648000 | elapsed time per iteration (s): 0.31 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 3.613350E+00 | grad norm: 0.460 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.093 | TFLOPs: 28.74 | +7: iteration 2260/ 21553 | consumed samples: 578560 | consumed tokens: 1184890880 | elapsed time per iteration (s): 0.31 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 3.597358E+00 | grad norm: 0.503 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.165 | TFLOPs: 28.85 | +7: iteration 2270/ 21553 | consumed samples: 581120 | consumed tokens: 1190133760 | elapsed time per iteration (s): 0.31 | learning rate: 1.959E-04 | global batch size: 256 | lm loss: 3.594812E+00 | grad norm: 0.461 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.237 | TFLOPs: 28.68 | +7: iteration 2280/ 21553 | consumed samples: 583680 | consumed tokens: 1195376640 | elapsed time per iteration (s): 0.31 | learning rate: 1.959E-04 | global batch size: 256 | lm loss: 3.605117E+00 | grad norm: 0.488 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.395 | TFLOPs: 28.93 | +7: iteration 2290/ 21553 | consumed samples: 586240 | consumed tokens: 1200619520 | elapsed time per iteration (s): 0.31 | learning rate: 1.958E-04 | global batch size: 256 | lm loss: 3.612270E+00 | grad norm: 0.653 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.886 | TFLOPs: 29.05 | +7: iteration 2300/ 21553 | consumed samples: 588800 | consumed tokens: 1205862400 | elapsed time per iteration (s): 0.32 | learning rate: 1.958E-04 | global batch size: 256 | lm loss: 3.584205E+00 | grad norm: 0.473 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.028 | TFLOPs: 28.43 | +7: iteration 2310/ 21553 | consumed samples: 591360 | consumed tokens: 1211105280 | elapsed time per iteration (s): 0.32 | learning rate: 1.958E-04 | global batch size: 256 | lm loss: 3.591594E+00 | grad norm: 0.528 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 802.189 | TFLOPs: 28.08 | +7: iteration 2320/ 21553 | consumed samples: 593920 | consumed tokens: 1216348160 | elapsed time per iteration (s): 0.32 | learning rate: 1.957E-04 | global batch size: 256 | lm loss: 3.578284E+00 | grad norm: 0.521 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.612 | TFLOPs: 28.41 | +7: iteration 2330/ 21553 | consumed samples: 596480 | consumed tokens: 1221591040 | elapsed time per iteration (s): 0.32 | learning rate: 1.957E-04 | global batch size: 256 | lm loss: 3.602683E+00 | grad norm: 0.509 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 798.953 | TFLOPs: 27.97 | +7: iteration 2340/ 21553 | consumed samples: 599040 | consumed tokens: 1226833920 | elapsed time per iteration (s): 0.31 | learning rate: 1.956E-04 | global batch size: 256 | lm loss: 3.592244E+00 | grad norm: 0.574 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.135 | TFLOPs: 29.27 | +7: iteration 2350/ 21553 | consumed samples: 601600 | consumed tokens: 1232076800 | elapsed time per iteration (s): 0.31 | learning rate: 1.956E-04 | global batch size: 256 | lm loss: 3.598687E+00 | grad norm: 0.477 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.092 | TFLOPs: 28.46 | +7: iteration 2360/ 21553 | consumed samples: 604160 | consumed tokens: 1237319680 | elapsed time per iteration (s): 0.31 | learning rate: 1.956E-04 | global batch size: 256 | lm loss: 3.567967E+00 | grad norm: 0.538 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.885 | TFLOPs: 28.70 | +7: iteration 2370/ 21553 | consumed samples: 606720 | consumed tokens: 1242562560 | elapsed time per iteration (s): 0.31 | learning rate: 1.955E-04 | global batch size: 256 | lm loss: 3.547484E+00 | grad norm: 0.511 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.461 | TFLOPs: 28.83 | +7: iteration 2380/ 21553 | consumed samples: 609280 | consumed tokens: 1247805440 | elapsed time per iteration (s): 0.31 | learning rate: 1.955E-04 | global batch size: 256 | lm loss: 3.554250E+00 | grad norm: 0.560 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.279 | TFLOPs: 29.14 | +7: iteration 2390/ 21553 | consumed samples: 611840 | consumed tokens: 1253048320 | elapsed time per iteration (s): 0.31 | learning rate: 1.954E-04 | global batch size: 256 | lm loss: 3.600047E+00 | grad norm: 0.450 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.231 | TFLOPs: 28.54 | +7: iteration 2400/ 21553 | consumed samples: 614400 | consumed tokens: 1258291200 | elapsed time per iteration (s): 0.31 | learning rate: 1.954E-04 | global batch size: 256 | lm loss: 3.555460E+00 | grad norm: 0.457 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.545 | TFLOPs: 28.94 | +7: iteration 2410/ 21553 | consumed samples: 616960 | consumed tokens: 1263534080 | elapsed time per iteration (s): 0.31 | learning rate: 1.953E-04 | global batch size: 256 | lm loss: 3.580394E+00 | grad norm: 0.536 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.573 | TFLOPs: 29.29 | +7: iteration 2420/ 21553 | consumed samples: 619520 | consumed tokens: 1268776960 | elapsed time per iteration (s): 0.31 | learning rate: 1.953E-04 | global batch size: 256 | lm loss: 3.555076E+00 | grad norm: 0.427 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.513 | TFLOPs: 28.90 | +7: iteration 2430/ 21553 | consumed samples: 622080 | consumed tokens: 1274019840 | elapsed time per iteration (s): 0.31 | learning rate: 1.953E-04 | global batch size: 256 | lm loss: 3.578085E+00 | grad norm: 0.480 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.873 | TFLOPs: 28.56 | +7: iteration 2440/ 21553 | consumed samples: 624640 | consumed tokens: 1279262720 | elapsed time per iteration (s): 0.31 | learning rate: 1.952E-04 | global batch size: 256 | lm loss: 3.566947E+00 | grad norm: 0.502 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.333 | TFLOPs: 28.68 | +7: iteration 2450/ 21553 | consumed samples: 627200 | consumed tokens: 1284505600 | elapsed time per iteration (s): 0.31 | learning rate: 1.952E-04 | global batch size: 256 | lm loss: 3.581797E+00 | grad norm: 0.601 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.061 | TFLOPs: 28.64 | +7: iteration 2460/ 21553 | consumed samples: 629760 | consumed tokens: 1289748480 | elapsed time per iteration (s): 0.31 | learning rate: 1.951E-04 | global batch size: 256 | lm loss: 3.548123E+00 | grad norm: 0.435 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.117 | TFLOPs: 28.61 | +7: iteration 2470/ 21553 | consumed samples: 632320 | consumed tokens: 1294991360 | elapsed time per iteration (s): 0.31 | learning rate: 1.951E-04 | global batch size: 256 | lm loss: 3.566425E+00 | grad norm: 0.514 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.559 | TFLOPs: 28.52 | +7: iteration 2480/ 21553 | consumed samples: 634880 | consumed tokens: 1300234240 | elapsed time per iteration (s): 0.33 | learning rate: 1.950E-04 | global batch size: 256 | lm loss: 3.572402E+00 | grad norm: 0.448 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 782.366 | TFLOPs: 27.39 | +7: iteration 2490/ 21553 | consumed samples: 637440 | consumed tokens: 1305477120 | elapsed time per iteration (s): 0.31 | learning rate: 1.950E-04 | global batch size: 256 | lm loss: 3.563131E+00 | grad norm: 0.682 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.305 | TFLOPs: 28.86 | +7: iteration 2500/ 21553 | consumed samples: 640000 | consumed tokens: 1310720000 | elapsed time per iteration (s): 0.30 | learning rate: 1.950E-04 | global batch size: 256 | lm loss: 3.584719E+00 | grad norm: 0.538 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.986 | TFLOPs: 29.51 | +7: iteration 2510/ 21553 | consumed samples: 642560 | consumed tokens: 1315962880 | elapsed time per iteration (s): 0.31 | learning rate: 1.949E-04 | global batch size: 256 | lm loss: 3.569177E+00 | grad norm: 0.457 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.236 | TFLOPs: 28.82 | +7: iteration 2520/ 21553 | consumed samples: 645120 | consumed tokens: 1321205760 | elapsed time per iteration (s): 0.31 | learning rate: 1.949E-04 | global batch size: 256 | lm loss: 3.560616E+00 | grad norm: 0.483 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.507 | TFLOPs: 29.11 | +7: iteration 2530/ 21553 | consumed samples: 647680 | consumed tokens: 1326448640 | elapsed time per iteration (s): 0.31 | learning rate: 1.948E-04 | global batch size: 256 | lm loss: 3.548184E+00 | grad norm: 0.527 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.052 | TFLOPs: 28.95 | +7: iteration 2540/ 21553 | consumed samples: 650240 | consumed tokens: 1331691520 | elapsed time per iteration (s): 0.30 | learning rate: 1.948E-04 | global batch size: 256 | lm loss: 3.545652E+00 | grad norm: 0.507 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.799 | TFLOPs: 29.43 | +7: iteration 2550/ 21553 | consumed samples: 652800 | consumed tokens: 1336934400 | elapsed time per iteration (s): 0.31 | learning rate: 1.947E-04 | global batch size: 256 | lm loss: 3.550186E+00 | grad norm: 0.541 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.398 | TFLOPs: 29.03 | +7: iteration 2560/ 21553 | consumed samples: 655360 | consumed tokens: 1342177280 | elapsed time per iteration (s): 0.31 | learning rate: 1.947E-04 | global batch size: 256 | lm loss: 3.545625E+00 | grad norm: 0.527 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.396 | TFLOPs: 29.24 | +7: iteration 2570/ 21553 | consumed samples: 657920 | consumed tokens: 1347420160 | elapsed time per iteration (s): 0.31 | learning rate: 1.946E-04 | global batch size: 256 | lm loss: 3.543803E+00 | grad norm: 0.533 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.763 | TFLOPs: 29.29 | +7: iteration 2580/ 21553 | consumed samples: 660480 | consumed tokens: 1352663040 | elapsed time per iteration (s): 0.34 | learning rate: 1.946E-04 | global batch size: 256 | lm loss: 3.548379E+00 | grad norm: 0.470 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 763.575 | TFLOPs: 26.73 | +7: iteration 2590/ 21553 | consumed samples: 663040 | consumed tokens: 1357905920 | elapsed time per iteration (s): 0.31 | learning rate: 1.946E-04 | global batch size: 256 | lm loss: 3.524303E+00 | grad norm: 0.489 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.326 | TFLOPs: 29.00 | +7: iteration 2600/ 21553 | consumed samples: 665600 | consumed tokens: 1363148800 | elapsed time per iteration (s): 0.33 | learning rate: 1.945E-04 | global batch size: 256 | lm loss: 3.523330E+00 | grad norm: 0.484 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 787.618 | TFLOPs: 27.57 | +7: iteration 2610/ 21553 | consumed samples: 668160 | consumed tokens: 1368391680 | elapsed time per iteration (s): 0.31 | learning rate: 1.945E-04 | global batch size: 256 | lm loss: 3.526301E+00 | grad norm: 0.427 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.902 | TFLOPs: 28.98 | +7: iteration 2620/ 21553 | consumed samples: 670720 | consumed tokens: 1373634560 | elapsed time per iteration (s): 0.32 | learning rate: 1.944E-04 | global batch size: 256 | lm loss: 3.523296E+00 | grad norm: 0.489 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 809.512 | TFLOPs: 28.34 | +7: iteration 2630/ 21553 | consumed samples: 673280 | consumed tokens: 1378877440 | elapsed time per iteration (s): 0.31 | learning rate: 1.944E-04 | global batch size: 256 | lm loss: 3.515672E+00 | grad norm: 0.498 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.341 | TFLOPs: 28.61 | +7: iteration 2640/ 21553 | consumed samples: 675840 | consumed tokens: 1384120320 | elapsed time per iteration (s): 0.31 | learning rate: 1.943E-04 | global batch size: 256 | lm loss: 3.545652E+00 | grad norm: 0.452 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.862 | TFLOPs: 28.67 | +7: iteration 2650/ 21553 | consumed samples: 678400 | consumed tokens: 1389363200 | elapsed time per iteration (s): 0.32 | learning rate: 1.943E-04 | global batch size: 256 | lm loss: 3.499031E+00 | grad norm: 0.413 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 798.133 | TFLOPs: 27.94 | +7: iteration 2660/ 21553 | consumed samples: 680960 | consumed tokens: 1394606080 | elapsed time per iteration (s): 0.31 | learning rate: 1.942E-04 | global batch size: 256 | lm loss: 3.574757E+00 | grad norm: 0.463 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.522 | TFLOPs: 29.18 | +7: iteration 2670/ 21553 | consumed samples: 683520 | consumed tokens: 1399848960 | elapsed time per iteration (s): 0.31 | learning rate: 1.942E-04 | global batch size: 256 | lm loss: 3.532559E+00 | grad norm: 0.448 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.422 | TFLOPs: 29.18 | +7: iteration 2680/ 21553 | consumed samples: 686080 | consumed tokens: 1405091840 | elapsed time per iteration (s): 0.31 | learning rate: 1.941E-04 | global batch size: 256 | lm loss: 3.515567E+00 | grad norm: 0.454 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.797 | TFLOPs: 29.05 | +7: iteration 2690/ 21553 | consumed samples: 688640 | consumed tokens: 1410334720 | elapsed time per iteration (s): 0.32 | learning rate: 1.941E-04 | global batch size: 256 | lm loss: 3.495128E+00 | grad norm: 0.478 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.376 | TFLOPs: 28.37 | +7: iteration 2700/ 21553 | consumed samples: 691200 | consumed tokens: 1415577600 | elapsed time per iteration (s): 0.31 | learning rate: 1.940E-04 | global batch size: 256 | lm loss: 3.517995E+00 | grad norm: 0.486 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.716 | TFLOPs: 29.05 | +7: iteration 2710/ 21553 | consumed samples: 693760 | consumed tokens: 1420820480 | elapsed time per iteration (s): 0.32 | learning rate: 1.940E-04 | global batch size: 256 | lm loss: 3.515532E+00 | grad norm: 0.438 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 796.334 | TFLOPs: 27.88 | +7: iteration 2720/ 21553 | consumed samples: 696320 | consumed tokens: 1426063360 | elapsed time per iteration (s): 0.32 | learning rate: 1.940E-04 | global batch size: 256 | lm loss: 3.506565E+00 | grad norm: 0.458 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.007 | TFLOPs: 28.39 | +7: iteration 2730/ 21553 | consumed samples: 698880 | consumed tokens: 1431306240 | elapsed time per iteration (s): 0.31 | learning rate: 1.939E-04 | global batch size: 256 | lm loss: 3.519918E+00 | grad norm: 0.499 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.711 | TFLOPs: 28.70 | +7: iteration 2740/ 21553 | consumed samples: 701440 | consumed tokens: 1436549120 | elapsed time per iteration (s): 0.31 | learning rate: 1.939E-04 | global batch size: 256 | lm loss: 3.496447E+00 | grad norm: 0.456 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.240 | TFLOPs: 28.89 | +7: iteration 2750/ 21553 | consumed samples: 704000 | consumed tokens: 1441792000 | elapsed time per iteration (s): 0.31 | learning rate: 1.938E-04 | global batch size: 256 | lm loss: 3.498393E+00 | grad norm: 0.528 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.704 | TFLOPs: 28.84 | +7: iteration 2760/ 21553 | consumed samples: 706560 | consumed tokens: 1447034880 | elapsed time per iteration (s): 0.30 | learning rate: 1.938E-04 | global batch size: 256 | lm loss: 3.537300E+00 | grad norm: 0.506 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 844.558 | TFLOPs: 29.57 | +7: iteration 2770/ 21553 | consumed samples: 709120 | consumed tokens: 1452277760 | elapsed time per iteration (s): 0.31 | learning rate: 1.937E-04 | global batch size: 256 | lm loss: 3.503557E+00 | grad norm: 0.604 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.850 | TFLOPs: 28.60 | +7: iteration 2780/ 21553 | consumed samples: 711680 | consumed tokens: 1457520640 | elapsed time per iteration (s): 0.32 | learning rate: 1.937E-04 | global batch size: 256 | lm loss: 3.493037E+00 | grad norm: 0.491 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 805.970 | TFLOPs: 28.21 | +7: iteration 2790/ 21553 | consumed samples: 714240 | consumed tokens: 1462763520 | elapsed time per iteration (s): 0.31 | learning rate: 1.936E-04 | global batch size: 256 | lm loss: 3.521471E+00 | grad norm: 0.482 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.004 | TFLOPs: 28.92 | +7: iteration 2800/ 21553 | consumed samples: 716800 | consumed tokens: 1468006400 | elapsed time per iteration (s): 0.31 | learning rate: 1.936E-04 | global batch size: 256 | lm loss: 3.472211E+00 | grad norm: 0.481 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.075 | TFLOPs: 28.53 | +7: iteration 2810/ 21553 | consumed samples: 719360 | consumed tokens: 1473249280 | elapsed time per iteration (s): 0.33 | learning rate: 1.935E-04 | global batch size: 256 | lm loss: 3.492678E+00 | grad norm: 0.447 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 782.312 | TFLOPs: 27.39 | +7: iteration 2820/ 21553 | consumed samples: 721920 | consumed tokens: 1478492160 | elapsed time per iteration (s): 0.33 | learning rate: 1.935E-04 | global batch size: 256 | lm loss: 3.498872E+00 | grad norm: 0.508 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 779.757 | TFLOPs: 27.30 | +7: iteration 2830/ 21553 | consumed samples: 724480 | consumed tokens: 1483735040 | elapsed time per iteration (s): 0.32 | learning rate: 1.934E-04 | global batch size: 256 | lm loss: 3.479000E+00 | grad norm: 0.499 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 805.766 | TFLOPs: 28.21 | +7: iteration 2840/ 21553 | consumed samples: 727040 | consumed tokens: 1488977920 | elapsed time per iteration (s): 0.32 | learning rate: 1.934E-04 | global batch size: 256 | lm loss: 3.494944E+00 | grad norm: 0.422 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 792.768 | TFLOPs: 27.75 | +7: iteration 2850/ 21553 | consumed samples: 729600 | consumed tokens: 1494220800 | elapsed time per iteration (s): 0.31 | learning rate: 1.933E-04 | global batch size: 256 | lm loss: 3.512753E+00 | grad norm: 0.537 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.925 | TFLOPs: 28.84 | +7: iteration 2860/ 21553 | consumed samples: 732160 | consumed tokens: 1499463680 | elapsed time per iteration (s): 0.31 | learning rate: 1.933E-04 | global batch size: 256 | lm loss: 3.500252E+00 | grad norm: 0.464 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.679 | TFLOPs: 28.76 | +7: iteration 2870/ 21553 | consumed samples: 734720 | consumed tokens: 1504706560 | elapsed time per iteration (s): 0.31 | learning rate: 1.932E-04 | global batch size: 256 | lm loss: 3.506714E+00 | grad norm: 0.451 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.581 | TFLOPs: 28.97 | +7: iteration 2880/ 21553 | consumed samples: 737280 | consumed tokens: 1509949440 | elapsed time per iteration (s): 0.31 | learning rate: 1.932E-04 | global batch size: 256 | lm loss: 3.473083E+00 | grad norm: 0.449 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.386 | TFLOPs: 28.86 | +7: iteration 2890/ 21553 | consumed samples: 739840 | consumed tokens: 1515192320 | elapsed time per iteration (s): 0.30 | learning rate: 1.931E-04 | global batch size: 256 | lm loss: 3.472965E+00 | grad norm: 0.484 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.012 | TFLOPs: 29.44 | +7: iteration 2900/ 21553 | consumed samples: 742400 | consumed tokens: 1520435200 | elapsed time per iteration (s): 0.32 | learning rate: 1.931E-04 | global batch size: 256 | lm loss: 3.493909E+00 | grad norm: 0.479 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.151 | TFLOPs: 28.29 | +7: iteration 2910/ 21553 | consumed samples: 744960 | consumed tokens: 1525678080 | elapsed time per iteration (s): 0.32 | learning rate: 1.930E-04 | global batch size: 256 | lm loss: 3.499267E+00 | grad norm: 0.441 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 795.847 | TFLOPs: 27.86 | +7: iteration 2920/ 21553 | consumed samples: 747520 | consumed tokens: 1530920960 | elapsed time per iteration (s): 0.31 | learning rate: 1.930E-04 | global batch size: 256 | lm loss: 3.472324E+00 | grad norm: 0.436 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.171 | TFLOPs: 28.99 | +7: iteration 2930/ 21553 | consumed samples: 750080 | consumed tokens: 1536163840 | elapsed time per iteration (s): 0.30 | learning rate: 1.929E-04 | global batch size: 256 | lm loss: 3.456403E+00 | grad norm: 0.600 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 848.532 | TFLOPs: 29.70 | +7: iteration 2940/ 21553 | consumed samples: 752640 | consumed tokens: 1541406720 | elapsed time per iteration (s): 0.31 | learning rate: 1.929E-04 | global batch size: 256 | lm loss: 3.518546E+00 | grad norm: 0.485 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.967 | TFLOPs: 29.02 | +7: iteration 2950/ 21553 | consumed samples: 755200 | consumed tokens: 1546649600 | elapsed time per iteration (s): 0.31 | learning rate: 1.928E-04 | global batch size: 256 | lm loss: 3.454708E+00 | grad norm: 0.484 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.420 | TFLOPs: 28.62 | +7: iteration 2960/ 21553 | consumed samples: 757760 | consumed tokens: 1551892480 | elapsed time per iteration (s): 0.31 | learning rate: 1.928E-04 | global batch size: 256 | lm loss: 3.456454E+00 | grad norm: 0.517 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.176 | TFLOPs: 28.64 | +7: iteration 2970/ 21553 | consumed samples: 760320 | consumed tokens: 1557135360 | elapsed time per iteration (s): 0.32 | learning rate: 1.927E-04 | global batch size: 256 | lm loss: 3.461602E+00 | grad norm: 0.432 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 795.375 | TFLOPs: 27.84 | +7: iteration 2980/ 21553 | consumed samples: 762880 | consumed tokens: 1562378240 | elapsed time per iteration (s): 0.31 | learning rate: 1.926E-04 | global batch size: 256 | lm loss: 3.512925E+00 | grad norm: 0.447 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.986 | TFLOPs: 29.02 | +7: iteration 2990/ 21553 | consumed samples: 765440 | consumed tokens: 1567621120 | elapsed time per iteration (s): 0.31 | learning rate: 1.926E-04 | global batch size: 256 | lm loss: 3.462684E+00 | grad norm: 0.558 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.348 | TFLOPs: 29.28 | +7: iteration 3000/ 21553 | consumed samples: 768000 | consumed tokens: 1572864000 | elapsed time per iteration (s): 0.46 | learning rate: 1.925E-04 | global batch size: 256 | lm loss: 3.456803E+00 | grad norm: 0.486 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 555.870 | TFLOPs: 19.46 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 3000 | lm loss value: 3.278690E+00 | lm loss PPL: 2.654097E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 3000 to checkpoints_146moscareap +0: [2022-11-29 17:22:57,574] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step3000 is begin to save! +0: [2022-11-29 17:22:57,578] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:22:57,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:22:57,664] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:22:57,679] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:22:57,680] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:22:57,695] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:22:57,695] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:22:57,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:22:57,711] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:22:57,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:22:57,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:22:57,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:22:57,741] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:22:57,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:22:57,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:22:57,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:22:57,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:22:57,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:22:57,790] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:22:57,806] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:22:57,806] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:22:57,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:22:57,821] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:22:57,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:22:57,837] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:22:57,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:22:57,852] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:22:57,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:22:57,868] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:22:57,883] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:22:57,883] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:22:57,898] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:22:57,899] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:22:57,900] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:22:57,900] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_146moscareap/global_step3000/mp_rank_00_model_states.pt +0: [2022-11-29 17:22:57,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:22:57,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:22:57,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:22:57,952] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:22:57,954] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:22:57,954] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:22:57,954] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:22:57,954] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:22:57,954] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:22:57,954] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:22:57,954] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:22:57,954] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:22:57,955] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:22:57,955] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:22:57,955] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:22:57,955] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:22:57,955] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:22:57,955] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:22:57,955] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:22:57,955] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:22:57,955] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:22:57,955] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:22:57,955] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:22:57,955] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:22:57,955] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +3: [2022-11-29 17:22:57,955] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +5: [2022-11-29 17:22:57,955] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:22:57,955] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:22:57,955] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:22:57,955] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:22:57,955] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:22:57,955] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:22:57,955] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:22:57,955] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:22:57,956] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:22:57,956] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:22:57,956] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +1: [2022-11-29 17:22:57,956] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +7: [2022-11-29 17:22:57,956] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:22:57,956] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:22:57,956] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:22:57,956] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:22:57,956] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:22:57,956] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +2: [2022-11-29 17:22:57,956] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +6: [2022-11-29 17:22:57,956] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +7: [2022-11-29 17:22:57,957] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:22:57,957] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:22:57,957] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:22:57,957] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:22:57,957] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:22:57,957] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:22:57,957] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:22:57,957] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:22:57,957] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:22:57,957] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:22:57,957] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:22:57,957] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:22:57,958] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:22:57,958] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:22:57,958] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:22:57,958] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:22:57,958] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:22:57,958] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:22:57,958] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:22:57,958] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +4: [2022-11-29 17:22:57,958] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:22:57,958] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:22:57,958] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:22:57,958] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:22:57,958] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:22:57,959] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +0: [2022-11-29 17:22:57,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:22:57,959] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:22:57,959] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:22:57,959] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:22:57,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:22:57,959] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:22:57,959] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:22:57,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:22:57,960] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:22:57,960] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:22:57,960] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:22:57,960] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:22:57,960] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:22:57,960] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:22:57,960] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:22:57,960] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +3: [2022-11-29 17:22:57,961] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +6: [2022-11-29 17:22:57,960] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:22:57,961] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:22:57,961] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +4: [2022-11-29 17:22:57,961] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +5: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:22:57,961] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +6: [2022-11-29 17:22:57,961] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +4: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:22:57,961] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:22:57,961] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +4: [2022-11-29 17:22:57,961] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +3: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:22:57,961] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +4: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:22:57,961] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +5: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:22:57,961] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:22:57,961] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:22:57,962] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:22:57,962] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:22:57,962] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:22:57,962] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:22:57,962] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:22:57,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:22:57,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:22:57,963] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:22:57,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:22:57,964] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:22:57,964] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:22:57,964] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:22:57,965] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:22:57,965] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:22:57,965] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:22:57,965] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:22:57,965] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:22:57,965] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:22:57,965] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +4: [2022-11-29 17:22:57,965] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:22:57,965] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:22:57,965] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:22:57,965] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:22:57,965] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:22:57,965] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:22:57,965] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:22:57,965] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:22:57,965] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:22:57,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:22:57,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:22:57,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:22:57,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:22:57,963] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:22:57,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:22:57,963] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:22:57,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:22:57,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:22:57,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:22:57,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:22:57,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:22:57,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:22:57,967] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:22:57,967] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:22:57,967] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:22:57,967] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:22:57,967] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:22:57,967] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:22:57,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:22:57,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:22:57,968] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:22:57,968] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:22:57,968] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:22:57,968] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:22:57,968] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:22:57,968] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:22:57,968] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:22:57,969] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:22:57,969] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:22:57,969] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:22:57,969] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:22:57,969] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:22:57,970] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:22:57,970] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:22:57,970] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:22:57,970] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:22:57,976] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:22:57,976] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: successfully saved checkpoint at iteration 3000 to checkpoints_146moscareap +7: time (ms) | save-checkpoint: 411.89 +7: iteration 3010/ 21553 | consumed samples: 770560 | consumed tokens: 1578106880 | elapsed time per iteration (s): 0.36 | learning rate: 1.925E-04 | global batch size: 256 | lm loss: 3.469042E+00 | grad norm: 0.396 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 710.635 | TFLOPs: 24.88 | +7: iteration 3020/ 21553 | consumed samples: 773120 | consumed tokens: 1583349760 | elapsed time per iteration (s): 0.30 | learning rate: 1.924E-04 | global batch size: 256 | lm loss: 3.476803E+00 | grad norm: 0.409 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.050 | TFLOPs: 29.51 | +7: iteration 3030/ 21553 | consumed samples: 775680 | consumed tokens: 1588592640 | elapsed time per iteration (s): 0.31 | learning rate: 1.924E-04 | global batch size: 256 | lm loss: 3.456575E+00 | grad norm: 0.471 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.952 | TFLOPs: 28.95 | +7: iteration 3040/ 21553 | consumed samples: 778240 | consumed tokens: 1593835520 | elapsed time per iteration (s): 0.30 | learning rate: 1.923E-04 | global batch size: 256 | lm loss: 3.480091E+00 | grad norm: 0.436 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.644 | TFLOPs: 29.53 | +7: iteration 3050/ 21553 | consumed samples: 780800 | consumed tokens: 1599078400 | elapsed time per iteration (s): 0.31 | learning rate: 1.923E-04 | global batch size: 256 | lm loss: 3.472866E+00 | grad norm: 0.478 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.983 | TFLOPs: 28.88 | +7: iteration 3060/ 21553 | consumed samples: 783360 | consumed tokens: 1604321280 | elapsed time per iteration (s): 0.31 | learning rate: 1.922E-04 | global batch size: 256 | lm loss: 3.440870E+00 | grad norm: 0.476 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.203 | TFLOPs: 28.75 | +7: iteration 3070/ 21553 | consumed samples: 785920 | consumed tokens: 1609564160 | elapsed time per iteration (s): 0.31 | learning rate: 1.922E-04 | global batch size: 256 | lm loss: 3.475681E+00 | grad norm: 0.448 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.673 | TFLOPs: 29.04 | +7: iteration 3080/ 21553 | consumed samples: 788480 | consumed tokens: 1614807040 | elapsed time per iteration (s): 0.31 | learning rate: 1.921E-04 | global batch size: 256 | lm loss: 3.477208E+00 | grad norm: 0.528 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.155 | TFLOPs: 28.99 | +7: iteration 3090/ 21553 | consumed samples: 791040 | consumed tokens: 1620049920 | elapsed time per iteration (s): 0.31 | learning rate: 1.921E-04 | global batch size: 256 | lm loss: 3.477097E+00 | grad norm: 0.485 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.767 | TFLOPs: 29.33 | +7: iteration 3100/ 21553 | consumed samples: 793600 | consumed tokens: 1625292800 | elapsed time per iteration (s): 0.31 | learning rate: 1.920E-04 | global batch size: 256 | lm loss: 3.457980E+00 | grad norm: 0.413 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.925 | TFLOPs: 29.02 | +7: iteration 3110/ 21553 | consumed samples: 796160 | consumed tokens: 1630535680 | elapsed time per iteration (s): 0.31 | learning rate: 1.920E-04 | global batch size: 256 | lm loss: 3.459182E+00 | grad norm: 0.462 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.432 | TFLOPs: 28.72 | +7: iteration 3120/ 21553 | consumed samples: 798720 | consumed tokens: 1635778560 | elapsed time per iteration (s): 0.31 | learning rate: 1.919E-04 | global batch size: 256 | lm loss: 3.471674E+00 | grad norm: 0.449 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.373 | TFLOPs: 28.96 | +7: iteration 3130/ 21553 | consumed samples: 801280 | consumed tokens: 1641021440 | elapsed time per iteration (s): 0.32 | learning rate: 1.918E-04 | global batch size: 256 | lm loss: 3.472932E+00 | grad norm: 0.438 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.972 | TFLOPs: 28.42 | +7: iteration 3140/ 21553 | consumed samples: 803840 | consumed tokens: 1646264320 | elapsed time per iteration (s): 0.34 | learning rate: 1.918E-04 | global batch size: 256 | lm loss: 3.448461E+00 | grad norm: 0.471 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 762.298 | TFLOPs: 26.69 | +7: iteration 3150/ 21553 | consumed samples: 806400 | consumed tokens: 1651507200 | elapsed time per iteration (s): 0.31 | learning rate: 1.917E-04 | global batch size: 256 | lm loss: 3.438631E+00 | grad norm: 0.433 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.328 | TFLOPs: 29.10 | +7: iteration 3160/ 21553 | consumed samples: 808960 | consumed tokens: 1656750080 | elapsed time per iteration (s): 0.31 | learning rate: 1.917E-04 | global batch size: 256 | lm loss: 3.437082E+00 | grad norm: 0.414 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.932 | TFLOPs: 29.16 | +7: iteration 3170/ 21553 | consumed samples: 811520 | consumed tokens: 1661992960 | elapsed time per iteration (s): 0.31 | learning rate: 1.916E-04 | global batch size: 256 | lm loss: 3.438639E+00 | grad norm: 0.380 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.076 | TFLOPs: 28.92 | +7: iteration 3180/ 21553 | consumed samples: 814080 | consumed tokens: 1667235840 | elapsed time per iteration (s): 0.31 | learning rate: 1.916E-04 | global batch size: 256 | lm loss: 3.452491E+00 | grad norm: 0.435 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.967 | TFLOPs: 28.98 | +7: iteration 3190/ 21553 | consumed samples: 816640 | consumed tokens: 1672478720 | elapsed time per iteration (s): 0.31 | learning rate: 1.915E-04 | global batch size: 256 | lm loss: 3.426838E+00 | grad norm: 0.437 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.069 | TFLOPs: 28.74 | +7: iteration 3200/ 21553 | consumed samples: 819200 | consumed tokens: 1677721600 | elapsed time per iteration (s): 0.31 | learning rate: 1.915E-04 | global batch size: 256 | lm loss: 3.477436E+00 | grad norm: 0.491 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.845 | TFLOPs: 29.02 | +7: iteration 3210/ 21553 | consumed samples: 821760 | consumed tokens: 1682964480 | elapsed time per iteration (s): 0.31 | learning rate: 1.914E-04 | global batch size: 256 | lm loss: 3.443152E+00 | grad norm: 0.443 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.699 | TFLOPs: 29.08 | +7: iteration 3220/ 21553 | consumed samples: 824320 | consumed tokens: 1688207360 | elapsed time per iteration (s): 0.30 | learning rate: 1.913E-04 | global batch size: 256 | lm loss: 3.446963E+00 | grad norm: 0.497 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.177 | TFLOPs: 29.59 | +7: iteration 3230/ 21553 | consumed samples: 826880 | consumed tokens: 1693450240 | elapsed time per iteration (s): 0.31 | learning rate: 1.913E-04 | global batch size: 256 | lm loss: 3.430746E+00 | grad norm: 0.446 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.307 | TFLOPs: 29.21 | +7: iteration 3240/ 21553 | consumed samples: 829440 | consumed tokens: 1698693120 | elapsed time per iteration (s): 0.31 | learning rate: 1.912E-04 | global batch size: 256 | lm loss: 3.428559E+00 | grad norm: 0.424 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.625 | TFLOPs: 29.25 | +7: iteration 3250/ 21553 | consumed samples: 832000 | consumed tokens: 1703936000 | elapsed time per iteration (s): 0.31 | learning rate: 1.912E-04 | global batch size: 256 | lm loss: 3.413074E+00 | grad norm: 0.442 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.437 | TFLOPs: 28.58 | +7: iteration 3260/ 21553 | consumed samples: 834560 | consumed tokens: 1709178880 | elapsed time per iteration (s): 0.33 | learning rate: 1.911E-04 | global batch size: 256 | lm loss: 3.412466E+00 | grad norm: 0.449 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 778.664 | TFLOPs: 27.26 | +7: iteration 3270/ 21553 | consumed samples: 837120 | consumed tokens: 1714421760 | elapsed time per iteration (s): 0.31 | learning rate: 1.911E-04 | global batch size: 256 | lm loss: 3.450068E+00 | grad norm: 0.397 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.594 | TFLOPs: 28.73 | +7: iteration 3280/ 21553 | consumed samples: 839680 | consumed tokens: 1719664640 | elapsed time per iteration (s): 0.31 | learning rate: 1.910E-04 | global batch size: 256 | lm loss: 3.429953E+00 | grad norm: 0.419 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.443 | TFLOPs: 28.65 | +7: iteration 3290/ 21553 | consumed samples: 842240 | consumed tokens: 1724907520 | elapsed time per iteration (s): 0.33 | learning rate: 1.909E-04 | global batch size: 256 | lm loss: 3.415826E+00 | grad norm: 0.501 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 784.890 | TFLOPs: 27.48 | +7: iteration 3300/ 21553 | consumed samples: 844800 | consumed tokens: 1730150400 | elapsed time per iteration (s): 0.43 | learning rate: 1.909E-04 | global batch size: 256 | lm loss: 3.434409E+00 | grad norm: 0.413 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 590.224 | TFLOPs: 20.66 | +7: iteration 3310/ 21553 | consumed samples: 847360 | consumed tokens: 1735393280 | elapsed time per iteration (s): 0.32 | learning rate: 1.908E-04 | global batch size: 256 | lm loss: 3.431649E+00 | grad norm: 0.430 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 802.381 | TFLOPs: 28.09 | +7: iteration 3320/ 21553 | consumed samples: 849920 | consumed tokens: 1740636160 | elapsed time per iteration (s): 0.31 | learning rate: 1.908E-04 | global batch size: 256 | lm loss: 3.411355E+00 | grad norm: 0.474 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.213 | TFLOPs: 28.71 | +7: iteration 3330/ 21553 | consumed samples: 852480 | consumed tokens: 1745879040 | elapsed time per iteration (s): 0.31 | learning rate: 1.907E-04 | global batch size: 256 | lm loss: 3.437975E+00 | grad norm: 0.496 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.055 | TFLOPs: 29.16 | +7: iteration 3340/ 21553 | consumed samples: 855040 | consumed tokens: 1751121920 | elapsed time per iteration (s): 0.31 | learning rate: 1.906E-04 | global batch size: 256 | lm loss: 3.442400E+00 | grad norm: 0.508 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.721 | TFLOPs: 28.70 | +7: iteration 3350/ 21553 | consumed samples: 857600 | consumed tokens: 1756364800 | elapsed time per iteration (s): 0.31 | learning rate: 1.906E-04 | global batch size: 256 | lm loss: 3.419907E+00 | grad norm: 0.458 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.876 | TFLOPs: 28.53 | +7: iteration 3360/ 21553 | consumed samples: 860160 | consumed tokens: 1761607680 | elapsed time per iteration (s): 0.31 | learning rate: 1.905E-04 | global batch size: 256 | lm loss: 3.404297E+00 | grad norm: 0.415 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.572 | TFLOPs: 28.48 | +7: iteration 3370/ 21553 | consumed samples: 862720 | consumed tokens: 1766850560 | elapsed time per iteration (s): 0.30 | learning rate: 1.905E-04 | global batch size: 256 | lm loss: 3.430499E+00 | grad norm: 0.442 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 851.577 | TFLOPs: 29.81 | +7: iteration 3380/ 21553 | consumed samples: 865280 | consumed tokens: 1772093440 | elapsed time per iteration (s): 0.30 | learning rate: 1.904E-04 | global batch size: 256 | lm loss: 3.426230E+00 | grad norm: 0.525 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.350 | TFLOPs: 29.52 | +7: iteration 3390/ 21553 | consumed samples: 867840 | consumed tokens: 1777336320 | elapsed time per iteration (s): 0.31 | learning rate: 1.903E-04 | global batch size: 256 | lm loss: 3.432922E+00 | grad norm: 0.438 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.068 | TFLOPs: 28.78 | +7: iteration 3400/ 21553 | consumed samples: 870400 | consumed tokens: 1782579200 | elapsed time per iteration (s): 0.32 | learning rate: 1.903E-04 | global batch size: 256 | lm loss: 3.390908E+00 | grad norm: 0.431 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 802.965 | TFLOPs: 28.11 | +7: iteration 3410/ 21553 | consumed samples: 872960 | consumed tokens: 1787822080 | elapsed time per iteration (s): 0.31 | learning rate: 1.902E-04 | global batch size: 256 | lm loss: 3.412766E+00 | grad norm: 0.439 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.902 | TFLOPs: 28.88 | +7: iteration 3420/ 21553 | consumed samples: 875520 | consumed tokens: 1793064960 | elapsed time per iteration (s): 0.31 | learning rate: 1.902E-04 | global batch size: 256 | lm loss: 3.382483E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.488 | TFLOPs: 28.93 | +7: iteration 3430/ 21553 | consumed samples: 878080 | consumed tokens: 1798307840 | elapsed time per iteration (s): 0.31 | learning rate: 1.901E-04 | global batch size: 256 | lm loss: 3.422618E+00 | grad norm: 0.476 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.337 | TFLOPs: 28.82 | +7: iteration 3440/ 21553 | consumed samples: 880640 | consumed tokens: 1803550720 | elapsed time per iteration (s): 0.34 | learning rate: 1.900E-04 | global batch size: 256 | lm loss: 3.422724E+00 | grad norm: 0.399 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 757.547 | TFLOPs: 26.52 | +7: iteration 3450/ 21553 | consumed samples: 883200 | consumed tokens: 1808793600 | elapsed time per iteration (s): 0.31 | learning rate: 1.900E-04 | global batch size: 256 | lm loss: 3.438011E+00 | grad norm: 0.512 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.746 | TFLOPs: 28.80 | +7: iteration 3460/ 21553 | consumed samples: 885760 | consumed tokens: 1814036480 | elapsed time per iteration (s): 0.31 | learning rate: 1.899E-04 | global batch size: 256 | lm loss: 3.408802E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.061 | TFLOPs: 29.16 | +7: iteration 3470/ 21553 | consumed samples: 888320 | consumed tokens: 1819279360 | elapsed time per iteration (s): 0.30 | learning rate: 1.899E-04 | global batch size: 256 | lm loss: 3.409819E+00 | grad norm: 0.493 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.693 | TFLOPs: 29.54 | +7: iteration 3480/ 21553 | consumed samples: 890880 | consumed tokens: 1824522240 | elapsed time per iteration (s): 0.32 | learning rate: 1.898E-04 | global batch size: 256 | lm loss: 3.419602E+00 | grad norm: 0.407 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.379 | TFLOPs: 28.30 | +7: iteration 3490/ 21553 | consumed samples: 893440 | consumed tokens: 1829765120 | elapsed time per iteration (s): 0.30 | learning rate: 1.897E-04 | global batch size: 256 | lm loss: 3.382113E+00 | grad norm: 0.402 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.066 | TFLOPs: 29.48 | +7: iteration 3500/ 21553 | consumed samples: 896000 | consumed tokens: 1835008000 | elapsed time per iteration (s): 0.32 | learning rate: 1.897E-04 | global batch size: 256 | lm loss: 3.432601E+00 | grad norm: 0.428 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 792.429 | TFLOPs: 27.74 | +7: iteration 3510/ 21553 | consumed samples: 898560 | consumed tokens: 1840250880 | elapsed time per iteration (s): 0.31 | learning rate: 1.896E-04 | global batch size: 256 | lm loss: 3.380632E+00 | grad norm: 0.424 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.086 | TFLOPs: 29.20 | +7: iteration 3520/ 21553 | consumed samples: 901120 | consumed tokens: 1845493760 | elapsed time per iteration (s): 0.31 | learning rate: 1.896E-04 | global batch size: 256 | lm loss: 3.403729E+00 | grad norm: 0.433 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.196 | TFLOPs: 28.92 | +7: iteration 3530/ 21553 | consumed samples: 903680 | consumed tokens: 1850736640 | elapsed time per iteration (s): 0.33 | learning rate: 1.895E-04 | global batch size: 256 | lm loss: 3.396992E+00 | grad norm: 0.476 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 781.433 | TFLOPs: 27.36 | +7: iteration 3540/ 21553 | consumed samples: 906240 | consumed tokens: 1855979520 | elapsed time per iteration (s): 0.32 | learning rate: 1.894E-04 | global batch size: 256 | lm loss: 3.410170E+00 | grad norm: 0.408 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 806.730 | TFLOPs: 28.24 | +7: iteration 3550/ 21553 | consumed samples: 908800 | consumed tokens: 1861222400 | elapsed time per iteration (s): 0.31 | learning rate: 1.894E-04 | global batch size: 256 | lm loss: 3.416576E+00 | grad norm: 0.419 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.210 | TFLOPs: 29.06 | +7: iteration 3560/ 21553 | consumed samples: 911360 | consumed tokens: 1866465280 | elapsed time per iteration (s): 0.31 | learning rate: 1.893E-04 | global batch size: 256 | lm loss: 3.378879E+00 | grad norm: 0.416 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.982 | TFLOPs: 28.99 | +7: iteration 3570/ 21553 | consumed samples: 913920 | consumed tokens: 1871708160 | elapsed time per iteration (s): 0.30 | learning rate: 1.892E-04 | global batch size: 256 | lm loss: 3.421217E+00 | grad norm: 0.461 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.648 | TFLOPs: 29.39 | +7: iteration 3580/ 21553 | consumed samples: 916480 | consumed tokens: 1876951040 | elapsed time per iteration (s): 0.32 | learning rate: 1.892E-04 | global batch size: 256 | lm loss: 3.394491E+00 | grad norm: 0.469 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 802.492 | TFLOPs: 28.09 | +7: iteration 3590/ 21553 | consumed samples: 919040 | consumed tokens: 1882193920 | elapsed time per iteration (s): 0.30 | learning rate: 1.891E-04 | global batch size: 256 | lm loss: 3.389695E+00 | grad norm: 0.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 848.458 | TFLOPs: 29.70 | +7: iteration 3600/ 21553 | consumed samples: 921600 | consumed tokens: 1887436800 | elapsed time per iteration (s): 0.31 | learning rate: 1.891E-04 | global batch size: 256 | lm loss: 3.402650E+00 | grad norm: 0.408 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.054 | TFLOPs: 28.64 | +7: iteration 3610/ 21553 | consumed samples: 924160 | consumed tokens: 1892679680 | elapsed time per iteration (s): 0.31 | learning rate: 1.890E-04 | global batch size: 256 | lm loss: 3.385482E+00 | grad norm: 0.430 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.534 | TFLOPs: 29.25 | +7: iteration 3620/ 21553 | consumed samples: 926720 | consumed tokens: 1897922560 | elapsed time per iteration (s): 0.31 | learning rate: 1.889E-04 | global batch size: 256 | lm loss: 3.391723E+00 | grad norm: 0.377 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.407 | TFLOPs: 29.00 | +7: iteration 3630/ 21553 | consumed samples: 929280 | consumed tokens: 1903165440 | elapsed time per iteration (s): 0.31 | learning rate: 1.889E-04 | global batch size: 256 | lm loss: 3.409732E+00 | grad norm: 0.429 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.904 | TFLOPs: 29.09 | +7: iteration 3640/ 21553 | consumed samples: 931840 | consumed tokens: 1908408320 | elapsed time per iteration (s): 0.31 | learning rate: 1.888E-04 | global batch size: 256 | lm loss: 3.376658E+00 | grad norm: 0.396 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.220 | TFLOPs: 29.34 | +7: iteration 3650/ 21553 | consumed samples: 934400 | consumed tokens: 1913651200 | elapsed time per iteration (s): 0.31 | learning rate: 1.887E-04 | global batch size: 256 | lm loss: 3.374152E+00 | grad norm: 0.409 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.133 | TFLOPs: 28.50 | +7: iteration 3660/ 21553 | consumed samples: 936960 | consumed tokens: 1918894080 | elapsed time per iteration (s): 0.31 | learning rate: 1.887E-04 | global batch size: 256 | lm loss: 3.399891E+00 | grad norm: 0.491 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.951 | TFLOPs: 29.23 | +7: iteration 3670/ 21553 | consumed samples: 939520 | consumed tokens: 1924136960 | elapsed time per iteration (s): 0.30 | learning rate: 1.886E-04 | global batch size: 256 | lm loss: 3.405409E+00 | grad norm: 0.430 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.365 | TFLOPs: 29.38 | +7: iteration 3680/ 21553 | consumed samples: 942080 | consumed tokens: 1929379840 | elapsed time per iteration (s): 0.31 | learning rate: 1.885E-04 | global batch size: 256 | lm loss: 3.367010E+00 | grad norm: 0.457 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.466 | TFLOPs: 29.18 | +7: iteration 3690/ 21553 | consumed samples: 944640 | consumed tokens: 1934622720 | elapsed time per iteration (s): 0.31 | learning rate: 1.885E-04 | global batch size: 256 | lm loss: 3.378099E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.273 | TFLOPs: 28.65 | +7: iteration 3700/ 21553 | consumed samples: 947200 | consumed tokens: 1939865600 | elapsed time per iteration (s): 0.31 | learning rate: 1.884E-04 | global batch size: 256 | lm loss: 3.393118E+00 | grad norm: 0.477 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.451 | TFLOPs: 28.69 | +7: iteration 3710/ 21553 | consumed samples: 949760 | consumed tokens: 1945108480 | elapsed time per iteration (s): 0.31 | learning rate: 1.883E-04 | global batch size: 256 | lm loss: 3.404628E+00 | grad norm: 0.475 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.085 | TFLOPs: 29.13 | +7: iteration 3720/ 21553 | consumed samples: 952320 | consumed tokens: 1950351360 | elapsed time per iteration (s): 0.31 | learning rate: 1.883E-04 | global batch size: 256 | lm loss: 3.399918E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.429 | TFLOPs: 28.62 | +7: iteration 3730/ 21553 | consumed samples: 954880 | consumed tokens: 1955594240 | elapsed time per iteration (s): 0.31 | learning rate: 1.882E-04 | global batch size: 256 | lm loss: 3.398978E+00 | grad norm: 0.449 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.841 | TFLOPs: 28.81 | +7: iteration 3740/ 21553 | consumed samples: 957440 | consumed tokens: 1960837120 | elapsed time per iteration (s): 0.32 | learning rate: 1.882E-04 | global batch size: 256 | lm loss: 3.362789E+00 | grad norm: 0.421 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 795.102 | TFLOPs: 27.83 | +7: iteration 3750/ 21553 | consumed samples: 960000 | consumed tokens: 1966080000 | elapsed time per iteration (s): 0.31 | learning rate: 1.881E-04 | global batch size: 256 | lm loss: 3.368102E+00 | grad norm: 0.442 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.012 | TFLOPs: 28.85 | +7: iteration 3760/ 21553 | consumed samples: 962560 | consumed tokens: 1971322880 | elapsed time per iteration (s): 0.31 | learning rate: 1.880E-04 | global batch size: 256 | lm loss: 3.369396E+00 | grad norm: 0.488 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.305 | TFLOPs: 29.07 | +7: iteration 3770/ 21553 | consumed samples: 965120 | consumed tokens: 1976565760 | elapsed time per iteration (s): 0.32 | learning rate: 1.880E-04 | global batch size: 256 | lm loss: 3.391605E+00 | grad norm: 0.430 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 809.764 | TFLOPs: 28.35 | +7: iteration 3780/ 21553 | consumed samples: 967680 | consumed tokens: 1981808640 | elapsed time per iteration (s): 0.31 | learning rate: 1.879E-04 | global batch size: 256 | lm loss: 3.386778E+00 | grad norm: 0.450 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.358 | TFLOPs: 28.61 | +7: iteration 3790/ 21553 | consumed samples: 970240 | consumed tokens: 1987051520 | elapsed time per iteration (s): 0.31 | learning rate: 1.878E-04 | global batch size: 256 | lm loss: 3.359232E+00 | grad norm: 0.441 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.554 | TFLOPs: 28.94 | +7: iteration 3800/ 21553 | consumed samples: 972800 | consumed tokens: 1992294400 | elapsed time per iteration (s): 0.31 | learning rate: 1.878E-04 | global batch size: 256 | lm loss: 3.390649E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.188 | TFLOPs: 29.31 | +7: iteration 3810/ 21553 | consumed samples: 975360 | consumed tokens: 1997537280 | elapsed time per iteration (s): 0.31 | learning rate: 1.877E-04 | global batch size: 256 | lm loss: 3.377865E+00 | grad norm: 0.433 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.994 | TFLOPs: 28.74 | +7: iteration 3820/ 21553 | consumed samples: 977920 | consumed tokens: 2002780160 | elapsed time per iteration (s): 0.32 | learning rate: 1.876E-04 | global batch size: 256 | lm loss: 3.375834E+00 | grad norm: 0.399 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 806.098 | TFLOPs: 28.22 | +7: iteration 3830/ 21553 | consumed samples: 980480 | consumed tokens: 2008023040 | elapsed time per iteration (s): 0.31 | learning rate: 1.876E-04 | global batch size: 256 | lm loss: 3.376830E+00 | grad norm: 0.456 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.036 | TFLOPs: 28.46 | +7: iteration 3840/ 21553 | consumed samples: 983040 | consumed tokens: 2013265920 | elapsed time per iteration (s): 0.31 | learning rate: 1.875E-04 | global batch size: 256 | lm loss: 3.377090E+00 | grad norm: 0.461 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.579 | TFLOPs: 29.11 | +7: iteration 3850/ 21553 | consumed samples: 985600 | consumed tokens: 2018508800 | elapsed time per iteration (s): 0.31 | learning rate: 1.874E-04 | global batch size: 256 | lm loss: 3.400064E+00 | grad norm: 0.458 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.943 | TFLOPs: 29.09 | +7: iteration 3860/ 21553 | consumed samples: 988160 | consumed tokens: 2023751680 | elapsed time per iteration (s): 0.31 | learning rate: 1.874E-04 | global batch size: 256 | lm loss: 3.358842E+00 | grad norm: 0.407 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.164 | TFLOPs: 29.31 | +7: iteration 3870/ 21553 | consumed samples: 990720 | consumed tokens: 2028994560 | elapsed time per iteration (s): 0.31 | learning rate: 1.873E-04 | global batch size: 256 | lm loss: 3.366697E+00 | grad norm: 0.389 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.962 | TFLOPs: 28.60 | +7: iteration 3880/ 21553 | consumed samples: 993280 | consumed tokens: 2034237440 | elapsed time per iteration (s): 0.31 | learning rate: 1.872E-04 | global batch size: 256 | lm loss: 3.351985E+00 | grad norm: 0.391 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.298 | TFLOPs: 29.21 | +7: iteration 3890/ 21553 | consumed samples: 995840 | consumed tokens: 2039480320 | elapsed time per iteration (s): 0.31 | learning rate: 1.871E-04 | global batch size: 256 | lm loss: 3.356144E+00 | grad norm: 0.501 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.186 | TFLOPs: 29.24 | +7: iteration 3900/ 21553 | consumed samples: 998400 | consumed tokens: 2044723200 | elapsed time per iteration (s): 0.31 | learning rate: 1.871E-04 | global batch size: 256 | lm loss: 3.354762E+00 | grad norm: 0.558 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.697 | TFLOPs: 29.26 | +7: iteration 3910/ 21553 | consumed samples: 1000960 | consumed tokens: 2049966080 | elapsed time per iteration (s): 0.31 | learning rate: 1.870E-04 | global batch size: 256 | lm loss: 3.344117E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.871 | TFLOPs: 29.02 | +7: iteration 3920/ 21553 | consumed samples: 1003520 | consumed tokens: 2055208960 | elapsed time per iteration (s): 0.32 | learning rate: 1.869E-04 | global batch size: 256 | lm loss: 3.348524E+00 | grad norm: 0.418 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 798.002 | TFLOPs: 27.94 | +7: iteration 3930/ 21553 | consumed samples: 1006080 | consumed tokens: 2060451840 | elapsed time per iteration (s): 0.32 | learning rate: 1.869E-04 | global batch size: 256 | lm loss: 3.355641E+00 | grad norm: 0.469 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 789.466 | TFLOPs: 27.64 | +7: iteration 3940/ 21553 | consumed samples: 1008640 | consumed tokens: 2065694720 | elapsed time per iteration (s): 0.31 | learning rate: 1.868E-04 | global batch size: 256 | lm loss: 3.360020E+00 | grad norm: 0.411 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.661 | TFLOPs: 28.62 | +7: iteration 3950/ 21553 | consumed samples: 1011200 | consumed tokens: 2070937600 | elapsed time per iteration (s): 0.31 | learning rate: 1.867E-04 | global batch size: 256 | lm loss: 3.363839E+00 | grad norm: 0.387 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.784 | TFLOPs: 28.80 | +7: iteration 3960/ 21553 | consumed samples: 1013760 | consumed tokens: 2076180480 | elapsed time per iteration (s): 0.31 | learning rate: 1.867E-04 | global batch size: 256 | lm loss: 3.334774E+00 | grad norm: 0.429 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.178 | TFLOPs: 29.06 | +7: iteration 3970/ 21553 | consumed samples: 1016320 | consumed tokens: 2081423360 | elapsed time per iteration (s): 0.32 | learning rate: 1.866E-04 | global batch size: 256 | lm loss: 3.367649E+00 | grad norm: 0.452 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 801.945 | TFLOPs: 28.07 | +7: iteration 3980/ 21553 | consumed samples: 1018880 | consumed tokens: 2086666240 | elapsed time per iteration (s): 0.31 | learning rate: 1.865E-04 | global batch size: 256 | lm loss: 3.356351E+00 | grad norm: 0.422 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.523 | TFLOPs: 28.97 | +7: iteration 3990/ 21553 | consumed samples: 1021440 | consumed tokens: 2091909120 | elapsed time per iteration (s): 0.32 | learning rate: 1.865E-04 | global batch size: 256 | lm loss: 3.357064E+00 | grad norm: 0.403 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.325 | TFLOPs: 28.40 | +0: [2022-11-29 17:28:10,594] [INFO] [logging.py:68:log_dist] [Rank 0] step=4000, skipped=0, lr=[0.00018638652011758862, 0.00018638652011758862, 0.00018638652011758862], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 4000/ 21553 | consumed samples: 1024000 | consumed tokens: 2097152000 | elapsed time per iteration (s): 0.30 | learning rate: 1.864E-04 | global batch size: 256 | lm loss: 3.351439E+00 | grad norm: 0.444 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 846.366 | TFLOPs: 29.63 | +0: steps: 4000 loss: 3.3539 iter time (s): 0.311 samples/sec: 823.687 +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 4000 | lm loss value: 3.214729E+00 | lm loss PPL: 2.489655E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 4000 to checkpoints_146moscareap +0: [2022-11-29 17:28:10,717] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step4000 is begin to save! +0: [2022-11-29 17:28:10,721] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:28:10,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:28:10,805] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:28:10,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:28:10,821] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:28:10,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:28:10,837] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:28:10,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:28:10,852] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:28:10,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:28:10,867] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:28:10,882] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:28:10,883] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:28:10,898] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:28:10,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:28:10,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:28:10,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:28:10,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:28:10,929] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:28:10,944] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:28:10,944] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:28:10,960] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:28:10,960] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:28:10,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:28:10,976] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:28:10,991] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:28:10,991] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:28:11,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:28:11,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:28:11,022] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:28:11,023] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:28:11,038] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:28:11,038] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:28:11,039] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:28:11,040] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_146moscareap/global_step4000/mp_rank_00_model_states.pt +0: [2022-11-29 17:28:11,040] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:28:11,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:28:11,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:28:11,091] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:28:11,092] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:28:11,092] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:28:11,093] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:28:11,093] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:28:11,093] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:28:11,094] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:28:11,094] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:28:11,094] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:28:11,094] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:28:11,094] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:28:11,094] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:28:11,095] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:28:11,095] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:28:11,095] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:28:11,096] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:28:11,096] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:28:11,096] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:28:11,096] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:28:11,096] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:28:11,096] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:28:11,096] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:28:11,096] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +4: [2022-11-29 17:28:11,096] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:28:11,096] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:28:11,096] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:28:11,096] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:28:11,096] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:28:11,096] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:28:11,096] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:28:11,097] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:28:11,097] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:28:11,097] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:28:11,093] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:28:11,093] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:28:11,094] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:28:11,096] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:28:11,096] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:28:11,096] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:28:11,098] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:28:11,098] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:28:11,098] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:28:11,098] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:28:11,098] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:28:11,098] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:28:11,098] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:28:11,098] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:28:11,098] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +4: [2022-11-29 17:28:11,098] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +5: [2022-11-29 17:28:11,098] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:28:11,098] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:28:11,098] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:28:11,099] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:28:11,099] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:28:11,099] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:28:11,099] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:28:11,099] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:28:11,099] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:28:11,099] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:28:11,099] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:28:11,099] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:28:11,099] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:28:11,099] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:28:11,099] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:28:11,099] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:28:11,099] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:28:11,099] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:28:11,099] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:28:11,099] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:28:11,099] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:28:11,099] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:28:11,099] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:28:11,099] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:28:11,100] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +5: [2022-11-29 17:28:11,100] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:28:11,100] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:28:11,100] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:28:11,100] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:28:11,100] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:28:11,100] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:28:11,100] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:28:11,100] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:28:11,100] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:28:11,100] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:28:11,100] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:28:11,100] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:28:11,100] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:28:11,100] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:28:11,100] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:28:11,100] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:28:11,101] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:28:11,101] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:28:11,101] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:28:11,102] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:28:11,102] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:28:11,102] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:28:11,102] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:28:11,102] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:28:11,102] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:28:11,102] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:28:11,102] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:28:11,102] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:28:11,102] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:28:11,103] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +6: [2022-11-29 17:28:11,102] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:28:11,103] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:28:11,103] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:28:11,103] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:28:11,103] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:28:11,103] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:28:11,103] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:28:11,103] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:28:11,103] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:28:11,103] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:28:11,103] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:28:11,103] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:28:11,103] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:28:11,103] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:28:11,103] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:28:11,103] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:28:11,104] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:28:11,104] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +2: [2022-11-29 17:28:11,104] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:28:11,104] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +5: [2022-11-29 17:28:11,104] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:28:11,104] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:28:11,104] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:28:11,104] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:28:11,104] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:28:11,104] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:28:11,104] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:28:11,104] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:28:11,104] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:28:11,104] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:28:11,104] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:28:11,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:28:11,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:28:11,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:28:11,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:28:11,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:28:11,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:28:11,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:28:11,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:28:11,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:28:11,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:28:11,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:28:11,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +5: [2022-11-29 17:28:11,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:28:11,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:28:11,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +4: [2022-11-29 17:28:11,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:28:11,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +3: [2022-11-29 17:28:11,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:28:11,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +5: [2022-11-29 17:28:11,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:28:11,106] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:28:11,106] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:28:11,106] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:28:11,106] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:28:11,106] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:28:11,106] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +0: [2022-11-29 17:28:11,106] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:28:11,106] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:28:11,106] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:28:11,106] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:28:11,103] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:28:11,103] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:28:11,103] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:28:11,109] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:28:11,109] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:28:11,109] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:28:11,109] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:28:11,109] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:28:11,109] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:28:11,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:28:11,110] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:28:11,110] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:28:11,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:28:11,111] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:28:11,111] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:28:11,113] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:28:11,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:28:11,114] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:28:11,113] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:28:11,113] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3: [2022-11-29 17:28:11,112] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +6: [2022-11-29 17:28:11,114] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +0: [2022-11-29 17:28:11,113] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:28:11,112] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:28:11,114] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:28:11,120] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:28:11,120] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: successfully saved checkpoint at iteration 4000 to checkpoints_146moscareap +7: time (ms) | save-checkpoint: 407.58 +7: iteration 4010/ 21553 | consumed samples: 1026560 | consumed tokens: 2102394880 | elapsed time per iteration (s): 0.37 | learning rate: 1.863E-04 | global batch size: 256 | lm loss: 3.356156E+00 | grad norm: 0.442 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 698.172 | TFLOPs: 24.44 | +7: iteration 4020/ 21553 | consumed samples: 1029120 | consumed tokens: 2107637760 | elapsed time per iteration (s): 0.31 | learning rate: 1.862E-04 | global batch size: 256 | lm loss: 3.372314E+00 | grad norm: 0.467 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.105 | TFLOPs: 28.95 | +7: iteration 4030/ 21553 | consumed samples: 1031680 | consumed tokens: 2112880640 | elapsed time per iteration (s): 0.31 | learning rate: 1.862E-04 | global batch size: 256 | lm loss: 3.359583E+00 | grad norm: 0.385 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.478 | TFLOPs: 29.35 | +7: iteration 4040/ 21553 | consumed samples: 1034240 | consumed tokens: 2118123520 | elapsed time per iteration (s): 0.30 | learning rate: 1.861E-04 | global batch size: 256 | lm loss: 3.365321E+00 | grad norm: 0.410 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.708 | TFLOPs: 29.47 | +7: iteration 4050/ 21553 | consumed samples: 1036800 | consumed tokens: 2123366400 | elapsed time per iteration (s): 0.31 | learning rate: 1.860E-04 | global batch size: 256 | lm loss: 3.354115E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.048 | TFLOPs: 28.78 | +7: iteration 4060/ 21553 | consumed samples: 1039360 | consumed tokens: 2128609280 | elapsed time per iteration (s): 0.31 | learning rate: 1.860E-04 | global batch size: 256 | lm loss: 3.355288E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.718 | TFLOPs: 28.66 | +7: iteration 4070/ 21553 | consumed samples: 1041920 | consumed tokens: 2133852160 | elapsed time per iteration (s): 0.33 | learning rate: 1.859E-04 | global batch size: 256 | lm loss: 3.333377E+00 | grad norm: 0.388 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 771.784 | TFLOPs: 27.02 | +7: iteration 4080/ 21553 | consumed samples: 1044480 | consumed tokens: 2139095040 | elapsed time per iteration (s): 0.31 | learning rate: 1.858E-04 | global batch size: 256 | lm loss: 3.356729E+00 | grad norm: 0.460 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.456 | TFLOPs: 28.83 | +7: iteration 4090/ 21553 | consumed samples: 1047040 | consumed tokens: 2144337920 | elapsed time per iteration (s): 0.31 | learning rate: 1.857E-04 | global batch size: 256 | lm loss: 3.374183E+00 | grad norm: 0.402 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.538 | TFLOPs: 29.32 | +7: iteration 4100/ 21553 | consumed samples: 1049600 | consumed tokens: 2149580800 | elapsed time per iteration (s): 0.31 | learning rate: 1.857E-04 | global batch size: 256 | lm loss: 3.345865E+00 | grad norm: 0.404 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.994 | TFLOPs: 28.95 | +7: iteration 4110/ 21553 | consumed samples: 1052160 | consumed tokens: 2154823680 | elapsed time per iteration (s): 0.30 | learning rate: 1.856E-04 | global batch size: 256 | lm loss: 3.340697E+00 | grad norm: 0.413 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.464 | TFLOPs: 29.42 | +7: iteration 4120/ 21553 | consumed samples: 1054720 | consumed tokens: 2160066560 | elapsed time per iteration (s): 0.31 | learning rate: 1.855E-04 | global batch size: 256 | lm loss: 3.324765E+00 | grad norm: 0.428 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.837 | TFLOPs: 28.60 | +7: iteration 4130/ 21553 | consumed samples: 1057280 | consumed tokens: 2165309440 | elapsed time per iteration (s): 0.31 | learning rate: 1.855E-04 | global batch size: 256 | lm loss: 3.356289E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.897 | TFLOPs: 28.74 | +7: iteration 4140/ 21553 | consumed samples: 1059840 | consumed tokens: 2170552320 | elapsed time per iteration (s): 0.31 | learning rate: 1.854E-04 | global batch size: 256 | lm loss: 3.332190E+00 | grad norm: 0.413 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.842 | TFLOPs: 28.91 | +7: iteration 4150/ 21553 | consumed samples: 1062400 | consumed tokens: 2175795200 | elapsed time per iteration (s): 0.31 | learning rate: 1.853E-04 | global batch size: 256 | lm loss: 3.346218E+00 | grad norm: 0.411 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.729 | TFLOPs: 29.36 | +7: iteration 4160/ 21553 | consumed samples: 1064960 | consumed tokens: 2181038080 | elapsed time per iteration (s): 0.31 | learning rate: 1.852E-04 | global batch size: 256 | lm loss: 3.344211E+00 | grad norm: 0.459 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.777 | TFLOPs: 29.05 | +7: iteration 4170/ 21553 | consumed samples: 1067520 | consumed tokens: 2186280960 | elapsed time per iteration (s): 0.31 | learning rate: 1.852E-04 | global batch size: 256 | lm loss: 3.326471E+00 | grad norm: 0.431 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.181 | TFLOPs: 29.06 | +7: iteration 4180/ 21553 | consumed samples: 1070080 | consumed tokens: 2191523840 | elapsed time per iteration (s): 0.30 | learning rate: 1.851E-04 | global batch size: 256 | lm loss: 3.316449E+00 | grad norm: 0.583 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.752 | TFLOPs: 29.50 | +7: iteration 4190/ 21553 | consumed samples: 1072640 | consumed tokens: 2196766720 | elapsed time per iteration (s): 0.31 | learning rate: 1.850E-04 | global batch size: 256 | lm loss: 3.334234E+00 | grad norm: 0.415 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.271 | TFLOPs: 28.93 | +7: iteration 4200/ 21553 | consumed samples: 1075200 | consumed tokens: 2202009600 | elapsed time per iteration (s): 0.31 | learning rate: 1.850E-04 | global batch size: 256 | lm loss: 3.335478E+00 | grad norm: 0.455 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.284 | TFLOPs: 28.72 | +7: iteration 4210/ 21553 | consumed samples: 1077760 | consumed tokens: 2207252480 | elapsed time per iteration (s): 0.31 | learning rate: 1.849E-04 | global batch size: 256 | lm loss: 3.352834E+00 | grad norm: 0.418 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.727 | TFLOPs: 29.01 | +7: iteration 4220/ 21553 | consumed samples: 1080320 | consumed tokens: 2212495360 | elapsed time per iteration (s): 0.33 | learning rate: 1.848E-04 | global batch size: 256 | lm loss: 3.353549E+00 | grad norm: 0.389 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 787.287 | TFLOPs: 27.56 | +7: iteration 4230/ 21553 | consumed samples: 1082880 | consumed tokens: 2217738240 | elapsed time per iteration (s): 0.30 | learning rate: 1.847E-04 | global batch size: 256 | lm loss: 3.330780E+00 | grad norm: 0.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.532 | TFLOPs: 29.46 | +7: iteration 4240/ 21553 | consumed samples: 1085440 | consumed tokens: 2222981120 | elapsed time per iteration (s): 0.31 | learning rate: 1.847E-04 | global batch size: 256 | lm loss: 3.371244E+00 | grad norm: 0.436 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.856 | TFLOPs: 28.46 | +7: iteration 4250/ 21553 | consumed samples: 1088000 | consumed tokens: 2228224000 | elapsed time per iteration (s): 0.32 | learning rate: 1.846E-04 | global batch size: 256 | lm loss: 3.297383E+00 | grad norm: 0.381 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.208 | TFLOPs: 28.43 | +7: iteration 4260/ 21553 | consumed samples: 1090560 | consumed tokens: 2233466880 | elapsed time per iteration (s): 0.30 | learning rate: 1.845E-04 | global batch size: 256 | lm loss: 3.374826E+00 | grad norm: 0.415 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.243 | TFLOPs: 29.45 | +7: iteration 4270/ 21553 | consumed samples: 1093120 | consumed tokens: 2238709760 | elapsed time per iteration (s): 0.31 | learning rate: 1.844E-04 | global batch size: 256 | lm loss: 3.342869E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.163 | TFLOPs: 28.85 | +7: iteration 4280/ 21553 | consumed samples: 1095680 | consumed tokens: 2243952640 | elapsed time per iteration (s): 0.32 | learning rate: 1.844E-04 | global batch size: 256 | lm loss: 3.344367E+00 | grad norm: 0.425 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 804.024 | TFLOPs: 28.15 | +7: iteration 4290/ 21553 | consumed samples: 1098240 | consumed tokens: 2249195520 | elapsed time per iteration (s): 0.32 | learning rate: 1.843E-04 | global batch size: 256 | lm loss: 3.341337E+00 | grad norm: 0.444 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 796.887 | TFLOPs: 27.90 | +7: iteration 4300/ 21553 | consumed samples: 1100800 | consumed tokens: 2254438400 | elapsed time per iteration (s): 0.31 | learning rate: 1.842E-04 | global batch size: 256 | lm loss: 3.291412E+00 | grad norm: 0.406 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.238 | TFLOPs: 28.78 | +7: iteration 4310/ 21553 | consumed samples: 1103360 | consumed tokens: 2259681280 | elapsed time per iteration (s): 0.31 | learning rate: 1.841E-04 | global batch size: 256 | lm loss: 3.324663E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.706 | TFLOPs: 29.15 | +7: iteration 4320/ 21553 | consumed samples: 1105920 | consumed tokens: 2264924160 | elapsed time per iteration (s): 0.31 | learning rate: 1.841E-04 | global batch size: 256 | lm loss: 3.306778E+00 | grad norm: 0.491 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.447 | TFLOPs: 28.76 | +7: iteration 4330/ 21553 | consumed samples: 1108480 | consumed tokens: 2270167040 | elapsed time per iteration (s): 0.31 | learning rate: 1.840E-04 | global batch size: 256 | lm loss: 3.323431E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.433 | TFLOPs: 29.28 | +7: iteration 4340/ 21553 | consumed samples: 1111040 | consumed tokens: 2275409920 | elapsed time per iteration (s): 0.31 | learning rate: 1.839E-04 | global batch size: 256 | lm loss: 3.361775E+00 | grad norm: 0.437 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.483 | TFLOPs: 29.14 | +7: iteration 4350/ 21553 | consumed samples: 1113600 | consumed tokens: 2280652800 | elapsed time per iteration (s): 0.30 | learning rate: 1.838E-04 | global batch size: 256 | lm loss: 3.301808E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.825 | TFLOPs: 29.47 | +7: iteration 4360/ 21553 | consumed samples: 1116160 | consumed tokens: 2285895680 | elapsed time per iteration (s): 0.31 | learning rate: 1.838E-04 | global batch size: 256 | lm loss: 3.301622E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.352 | TFLOPs: 29.10 | +7: iteration 4370/ 21553 | consumed samples: 1118720 | consumed tokens: 2291138560 | elapsed time per iteration (s): 0.31 | learning rate: 1.837E-04 | global batch size: 256 | lm loss: 3.329930E+00 | grad norm: 0.402 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.415 | TFLOPs: 29.21 | +7: iteration 4380/ 21553 | consumed samples: 1121280 | consumed tokens: 2296381440 | elapsed time per iteration (s): 0.30 | learning rate: 1.836E-04 | global batch size: 256 | lm loss: 3.323895E+00 | grad norm: 0.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.577 | TFLOPs: 29.39 | +7: iteration 4390/ 21553 | consumed samples: 1123840 | consumed tokens: 2301624320 | elapsed time per iteration (s): 0.32 | learning rate: 1.835E-04 | global batch size: 256 | lm loss: 3.312745E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 807.805 | TFLOPs: 28.28 | +7: iteration 4400/ 21553 | consumed samples: 1126400 | consumed tokens: 2306867200 | elapsed time per iteration (s): 0.31 | learning rate: 1.835E-04 | global batch size: 256 | lm loss: 3.315438E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.134 | TFLOPs: 29.06 | +7: iteration 4410/ 21553 | consumed samples: 1128960 | consumed tokens: 2312110080 | elapsed time per iteration (s): 0.35 | learning rate: 1.834E-04 | global batch size: 256 | lm loss: 3.314599E+00 | grad norm: 0.392 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 736.924 | TFLOPs: 25.80 | +7: iteration 4420/ 21553 | consumed samples: 1131520 | consumed tokens: 2317352960 | elapsed time per iteration (s): 0.32 | learning rate: 1.833E-04 | global batch size: 256 | lm loss: 3.315548E+00 | grad norm: 0.405 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.148 | TFLOPs: 28.36 | +7: iteration 4430/ 21553 | consumed samples: 1134080 | consumed tokens: 2322595840 | elapsed time per iteration (s): 0.32 | learning rate: 1.832E-04 | global batch size: 256 | lm loss: 3.318191E+00 | grad norm: 0.380 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 792.674 | TFLOPs: 27.75 | +7: iteration 4440/ 21553 | consumed samples: 1136640 | consumed tokens: 2327838720 | elapsed time per iteration (s): 0.31 | learning rate: 1.831E-04 | global batch size: 256 | lm loss: 3.298453E+00 | grad norm: 0.385 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.631 | TFLOPs: 28.90 | +7: iteration 4450/ 21553 | consumed samples: 1139200 | consumed tokens: 2333081600 | elapsed time per iteration (s): 0.32 | learning rate: 1.831E-04 | global batch size: 256 | lm loss: 3.311999E+00 | grad norm: 0.408 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.623 | TFLOPs: 28.38 | +7: iteration 4460/ 21553 | consumed samples: 1141760 | consumed tokens: 2338324480 | elapsed time per iteration (s): 0.31 | learning rate: 1.830E-04 | global batch size: 256 | lm loss: 3.315392E+00 | grad norm: 0.409 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.544 | TFLOPs: 29.08 | +7: iteration 4470/ 21553 | consumed samples: 1144320 | consumed tokens: 2343567360 | elapsed time per iteration (s): 0.30 | learning rate: 1.829E-04 | global batch size: 256 | lm loss: 3.292373E+00 | grad norm: 0.400 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 849.568 | TFLOPs: 29.74 | +7: iteration 4480/ 21553 | consumed samples: 1146880 | consumed tokens: 2348810240 | elapsed time per iteration (s): 0.31 | learning rate: 1.828E-04 | global batch size: 256 | lm loss: 3.319730E+00 | grad norm: 0.394 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.642 | TFLOPs: 29.32 | +7: iteration 4490/ 21553 | consumed samples: 1149440 | consumed tokens: 2354053120 | elapsed time per iteration (s): 0.31 | learning rate: 1.828E-04 | global batch size: 256 | lm loss: 3.318355E+00 | grad norm: 0.391 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.448 | TFLOPs: 29.00 | +7: iteration 4500/ 21553 | consumed samples: 1152000 | consumed tokens: 2359296000 | elapsed time per iteration (s): 0.31 | learning rate: 1.827E-04 | global batch size: 256 | lm loss: 3.308596E+00 | grad norm: 0.947 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.782 | TFLOPs: 28.98 | +7: iteration 4510/ 21553 | consumed samples: 1154560 | consumed tokens: 2364538880 | elapsed time per iteration (s): 0.31 | learning rate: 1.826E-04 | global batch size: 256 | lm loss: 3.365050E+00 | grad norm: 0.494 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.377 | TFLOPs: 29.21 | +7: iteration 4520/ 21553 | consumed samples: 1157120 | consumed tokens: 2369781760 | elapsed time per iteration (s): 0.31 | learning rate: 1.825E-04 | global batch size: 256 | lm loss: 3.355314E+00 | grad norm: 0.877 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.231 | TFLOPs: 28.92 | +7: iteration 4530/ 21553 | consumed samples: 1159680 | consumed tokens: 2375024640 | elapsed time per iteration (s): 0.31 | learning rate: 1.824E-04 | global batch size: 256 | lm loss: 3.347926E+00 | grad norm: 0.444 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.924 | TFLOPs: 29.09 | +7: iteration 4540/ 21553 | consumed samples: 1162240 | consumed tokens: 2380267520 | elapsed time per iteration (s): 0.31 | learning rate: 1.824E-04 | global batch size: 256 | lm loss: 3.328013E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.998 | TFLOPs: 28.67 | +7: iteration 4550/ 21553 | consumed samples: 1164800 | consumed tokens: 2385510400 | elapsed time per iteration (s): 0.31 | learning rate: 1.823E-04 | global batch size: 256 | lm loss: 3.320884E+00 | grad norm: 0.382 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.748 | TFLOPs: 28.49 | +7: iteration 4560/ 21553 | consumed samples: 1167360 | consumed tokens: 2390753280 | elapsed time per iteration (s): 0.31 | learning rate: 1.822E-04 | global batch size: 256 | lm loss: 3.302764E+00 | grad norm: 0.408 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.913 | TFLOPs: 28.60 | +7: iteration 4570/ 21553 | consumed samples: 1169920 | consumed tokens: 2395996160 | elapsed time per iteration (s): 0.32 | learning rate: 1.821E-04 | global batch size: 256 | lm loss: 3.314585E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.784 | TFLOPs: 28.42 | +7: iteration 4580/ 21553 | consumed samples: 1172480 | consumed tokens: 2401239040 | elapsed time per iteration (s): 0.31 | learning rate: 1.820E-04 | global batch size: 256 | lm loss: 3.302877E+00 | grad norm: 0.419 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.081 | TFLOPs: 29.16 | +7: iteration 4590/ 21553 | consumed samples: 1175040 | consumed tokens: 2406481920 | elapsed time per iteration (s): 0.36 | learning rate: 1.820E-04 | global batch size: 256 | lm loss: 3.320452E+00 | grad norm: 0.669 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 716.613 | TFLOPs: 25.09 | +7: iteration 4600/ 21553 | consumed samples: 1177600 | consumed tokens: 2411724800 | elapsed time per iteration (s): 0.31 | learning rate: 1.819E-04 | global batch size: 256 | lm loss: 3.329462E+00 | grad norm: 0.405 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.123 | TFLOPs: 28.99 | +7: iteration 4610/ 21553 | consumed samples: 1180160 | consumed tokens: 2416967680 | elapsed time per iteration (s): 0.32 | learning rate: 1.818E-04 | global batch size: 256 | lm loss: 3.333979E+00 | grad norm: 0.510 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.578 | TFLOPs: 28.41 | +7: iteration 4620/ 21553 | consumed samples: 1182720 | consumed tokens: 2422210560 | elapsed time per iteration (s): 0.31 | learning rate: 1.817E-04 | global batch size: 256 | lm loss: 3.325103E+00 | grad norm: 0.390 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.101 | TFLOPs: 28.53 | +7: iteration 4630/ 21553 | consumed samples: 1185280 | consumed tokens: 2427453440 | elapsed time per iteration (s): 0.30 | learning rate: 1.816E-04 | global batch size: 256 | lm loss: 3.326336E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.472 | TFLOPs: 29.60 | +7: iteration 4640/ 21553 | consumed samples: 1187840 | consumed tokens: 2432696320 | elapsed time per iteration (s): 0.31 | learning rate: 1.816E-04 | global batch size: 256 | lm loss: 3.322701E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.528 | TFLOPs: 29.11 | +7: iteration 4650/ 21553 | consumed samples: 1190400 | consumed tokens: 2437939200 | elapsed time per iteration (s): 0.31 | learning rate: 1.815E-04 | global batch size: 256 | lm loss: 3.299710E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.243 | TFLOPs: 29.03 | +7: iteration 4660/ 21553 | consumed samples: 1192960 | consumed tokens: 2443182080 | elapsed time per iteration (s): 0.32 | learning rate: 1.814E-04 | global batch size: 256 | lm loss: 3.308580E+00 | grad norm: 1.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 802.272 | TFLOPs: 28.09 | +7: iteration 4670/ 21553 | consumed samples: 1195520 | consumed tokens: 2448424960 | elapsed time per iteration (s): 0.31 | learning rate: 1.813E-04 | global batch size: 256 | lm loss: 3.313087E+00 | grad norm: 0.399 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.813 | TFLOPs: 28.49 | +7: iteration 4680/ 21553 | consumed samples: 1198080 | consumed tokens: 2453667840 | elapsed time per iteration (s): 0.31 | learning rate: 1.812E-04 | global batch size: 256 | lm loss: 3.316178E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.720 | TFLOPs: 28.52 | +7: iteration 4690/ 21553 | consumed samples: 1200640 | consumed tokens: 2458910720 | elapsed time per iteration (s): 0.31 | learning rate: 1.812E-04 | global batch size: 256 | lm loss: 3.320275E+00 | grad norm: 0.386 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.531 | TFLOPs: 28.93 | +7: iteration 4700/ 21553 | consumed samples: 1203200 | consumed tokens: 2464153600 | elapsed time per iteration (s): 0.32 | learning rate: 1.811E-04 | global batch size: 256 | lm loss: 3.301262E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.192 | TFLOPs: 28.40 | +7: iteration 4710/ 21553 | consumed samples: 1205760 | consumed tokens: 2469396480 | elapsed time per iteration (s): 0.31 | learning rate: 1.810E-04 | global batch size: 256 | lm loss: 3.308435E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.395 | TFLOPs: 28.68 | +7: iteration 4720/ 21553 | consumed samples: 1208320 | consumed tokens: 2474639360 | elapsed time per iteration (s): 0.31 | learning rate: 1.809E-04 | global batch size: 256 | lm loss: 3.302623E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.951 | TFLOPs: 28.46 | +7: iteration 4730/ 21553 | consumed samples: 1210880 | consumed tokens: 2479882240 | elapsed time per iteration (s): 0.33 | learning rate: 1.808E-04 | global batch size: 256 | lm loss: 3.326620E+00 | grad norm: 0.400 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 771.213 | TFLOPs: 27.00 | +7: iteration 4740/ 21553 | consumed samples: 1213440 | consumed tokens: 2485125120 | elapsed time per iteration (s): 0.30 | learning rate: 1.808E-04 | global batch size: 256 | lm loss: 3.297338E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 847.055 | TFLOPs: 29.65 | +7: iteration 4750/ 21553 | consumed samples: 1216000 | consumed tokens: 2490368000 | elapsed time per iteration (s): 0.31 | learning rate: 1.807E-04 | global batch size: 256 | lm loss: 3.295958E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.872 | TFLOPs: 28.70 | +7: iteration 4760/ 21553 | consumed samples: 1218560 | consumed tokens: 2495610880 | elapsed time per iteration (s): 0.31 | learning rate: 1.806E-04 | global batch size: 256 | lm loss: 3.294987E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.270 | TFLOPs: 28.96 | +7: iteration 4770/ 21553 | consumed samples: 1221120 | consumed tokens: 2500853760 | elapsed time per iteration (s): 0.31 | learning rate: 1.805E-04 | global batch size: 256 | lm loss: 3.289118E+00 | grad norm: 0.412 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.062 | TFLOPs: 28.95 | +7: iteration 4780/ 21553 | consumed samples: 1223680 | consumed tokens: 2506096640 | elapsed time per iteration (s): 0.31 | learning rate: 1.804E-04 | global batch size: 256 | lm loss: 3.306347E+00 | grad norm: 0.389 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.236 | TFLOPs: 28.85 | +7: iteration 4790/ 21553 | consumed samples: 1226240 | consumed tokens: 2511339520 | elapsed time per iteration (s): 0.31 | learning rate: 1.803E-04 | global batch size: 256 | lm loss: 3.307560E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.663 | TFLOPs: 28.87 | +7: iteration 4800/ 21553 | consumed samples: 1228800 | consumed tokens: 2516582400 | elapsed time per iteration (s): 0.31 | learning rate: 1.803E-04 | global batch size: 256 | lm loss: 3.259888E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.357 | TFLOPs: 29.31 | +7: iteration 4810/ 21553 | consumed samples: 1231360 | consumed tokens: 2521825280 | elapsed time per iteration (s): 0.32 | learning rate: 1.802E-04 | global batch size: 256 | lm loss: 3.283609E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 797.047 | TFLOPs: 27.90 | +7: iteration 4820/ 21553 | consumed samples: 1233920 | consumed tokens: 2527068160 | elapsed time per iteration (s): 0.31 | learning rate: 1.801E-04 | global batch size: 256 | lm loss: 3.310651E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.201 | TFLOPs: 29.31 | +7: iteration 4830/ 21553 | consumed samples: 1236480 | consumed tokens: 2532311040 | elapsed time per iteration (s): 0.31 | learning rate: 1.800E-04 | global batch size: 256 | lm loss: 3.274125E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.192 | TFLOPs: 29.10 | +7: iteration 4840/ 21553 | consumed samples: 1239040 | consumed tokens: 2537553920 | elapsed time per iteration (s): 0.31 | learning rate: 1.799E-04 | global batch size: 256 | lm loss: 3.334552E+00 | grad norm: 0.703 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.303 | TFLOPs: 28.68 | +7: iteration 4850/ 21553 | consumed samples: 1241600 | consumed tokens: 2542796800 | elapsed time per iteration (s): 0.31 | learning rate: 1.798E-04 | global batch size: 256 | lm loss: 3.347712E+00 | grad norm: 0.513 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.840 | TFLOPs: 29.26 | +7: iteration 4860/ 21553 | consumed samples: 1244160 | consumed tokens: 2548039680 | elapsed time per iteration (s): 0.31 | learning rate: 1.798E-04 | global batch size: 256 | lm loss: 3.299171E+00 | grad norm: 0.430 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.470 | TFLOPs: 29.04 | +7: iteration 4870/ 21553 | consumed samples: 1246720 | consumed tokens: 2553282560 | elapsed time per iteration (s): 0.31 | learning rate: 1.797E-04 | global batch size: 256 | lm loss: 3.294805E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.025 | TFLOPs: 29.16 | +7: iteration 4880/ 21553 | consumed samples: 1249280 | consumed tokens: 2558525440 | elapsed time per iteration (s): 0.31 | learning rate: 1.796E-04 | global batch size: 256 | lm loss: 3.297730E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.629 | TFLOPs: 28.90 | +7: iteration 4890/ 21553 | consumed samples: 1251840 | consumed tokens: 2563768320 | elapsed time per iteration (s): 0.33 | learning rate: 1.795E-04 | global batch size: 256 | lm loss: 3.292076E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 773.390 | TFLOPs: 27.07 | +7: iteration 4900/ 21553 | consumed samples: 1254400 | consumed tokens: 2569011200 | elapsed time per iteration (s): 0.31 | learning rate: 1.794E-04 | global batch size: 256 | lm loss: 3.282446E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.408 | TFLOPs: 28.72 | +7: iteration 4910/ 21553 | consumed samples: 1256960 | consumed tokens: 2574254080 | elapsed time per iteration (s): 0.31 | learning rate: 1.793E-04 | global batch size: 256 | lm loss: 3.279436E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.228 | TFLOPs: 28.89 | +7: iteration 4920/ 21553 | consumed samples: 1259520 | consumed tokens: 2579496960 | elapsed time per iteration (s): 0.32 | learning rate: 1.793E-04 | global batch size: 256 | lm loss: 3.303050E+00 | grad norm: 0.397 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 796.595 | TFLOPs: 27.89 | +7: iteration 4930/ 21553 | consumed samples: 1262080 | consumed tokens: 2584739840 | elapsed time per iteration (s): 0.31 | learning rate: 1.792E-04 | global batch size: 256 | lm loss: 3.264712E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.799 | TFLOPs: 28.63 | +7: iteration 4940/ 21553 | consumed samples: 1264640 | consumed tokens: 2589982720 | elapsed time per iteration (s): 0.31 | learning rate: 1.791E-04 | global batch size: 256 | lm loss: 3.308599E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.477 | TFLOPs: 29.18 | +7: iteration 4950/ 21553 | consumed samples: 1267200 | consumed tokens: 2595225600 | elapsed time per iteration (s): 0.31 | learning rate: 1.790E-04 | global batch size: 256 | lm loss: 3.278947E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.988 | TFLOPs: 29.06 | +7: iteration 4960/ 21553 | consumed samples: 1269760 | consumed tokens: 2600468480 | elapsed time per iteration (s): 0.32 | learning rate: 1.789E-04 | global batch size: 256 | lm loss: 3.304658E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 803.568 | TFLOPs: 28.13 | +7: iteration 4970/ 21553 | consumed samples: 1272320 | consumed tokens: 2605711360 | elapsed time per iteration (s): 0.32 | learning rate: 1.788E-04 | global batch size: 256 | lm loss: 3.302308E+00 | grad norm: 0.669 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.968 | TFLOPs: 28.42 | +7: iteration 4980/ 21553 | consumed samples: 1274880 | consumed tokens: 2610954240 | elapsed time per iteration (s): 0.31 | learning rate: 1.787E-04 | global batch size: 256 | lm loss: 3.274589E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.411 | TFLOPs: 29.07 | +7: iteration 4990/ 21553 | consumed samples: 1277440 | consumed tokens: 2616197120 | elapsed time per iteration (s): 0.32 | learning rate: 1.787E-04 | global batch size: 256 | lm loss: 3.291713E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.339 | TFLOPs: 28.40 | +7: iteration 5000/ 21553 | consumed samples: 1280000 | consumed tokens: 2621440000 | elapsed time per iteration (s): 0.31 | learning rate: 1.786E-04 | global batch size: 256 | lm loss: 3.274742E+00 | grad norm: 0.519 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.760 | TFLOPs: 28.77 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 5000 | lm loss value: 3.224789E+00 | lm loss PPL: 2.514827E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 5000 to checkpoints_146moscareap +0: [2022-11-29 17:33:23,363] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step5000 is begin to save! +0: [2022-11-29 17:33:23,367] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:33:23,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:33:23,452] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:33:23,468] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:33:23,468] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:33:23,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:33:23,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:33:23,500] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:33:23,500] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:33:23,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:33:23,516] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:33:23,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:33:23,531] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:33:23,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:33:23,547] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:33:23,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:33:23,563] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:33:23,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:33:23,578] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:33:23,594] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:33:23,595] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:33:23,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:33:23,611] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:33:23,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:33:23,627] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:33:23,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:33:23,644] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:33:23,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:33:23,661] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:33:23,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:33:23,677] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:33:23,692] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:33:23,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:33:23,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:33:23,695] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_146moscareap/global_step5000/mp_rank_00_model_states.pt +0: [2022-11-29 17:33:23,695] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:33:23,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:23,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:23,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:33:23,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:23,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:33:23,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:23,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:33:23,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:33:23,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:23,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:33:23,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:33:23,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:23,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:33:23,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:33:23,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:33:23,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:23,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:33:23,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:23,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:33:23,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:33:23,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:23,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:33:23,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:33:23,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:33:23,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:33:23,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:33:23,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:23,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:23,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +3: [2022-11-29 17:33:23,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:33:23,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:33:23,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:33:23,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:23,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:23,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:33:23,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:23,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:23,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:33:23,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:33:23,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:33:23,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:33:23,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:23,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:23,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:33:23,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:23,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:23,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:33:23,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:33:23,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:33:23,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:23,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:33:23,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:23,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:33:23,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:33:23,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:33:23,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:23,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:33:23,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:23,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:23,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:33:23,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:23,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:23,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:23,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:33:23,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:23,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:23,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:33:23,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:23,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:33:23,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:33:23,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:33:23,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:33:23,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:23,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:33:23,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:33:23,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:33:23,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:23,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:33:23,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:23,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:33:23,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:33:23,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:23,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:33:23,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:33:23,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:33:23,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:23,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:33:23,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:23,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +6: [2022-11-29 17:33:23,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:23,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:33:23,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:33:23,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:33:23,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:33:23,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:23,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:23,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +4: [2022-11-29 17:33:23,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:33:23,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:33:23,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:23,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:33:23,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:33:23,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:23,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:33:23,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:33:23,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:23,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:33:23,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:23,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:33:23,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:33:23,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:33:23,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:23,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:23,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:33:23,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:33:23,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:23,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +4: [2022-11-29 17:33:23,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:23,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +3: [2022-11-29 17:33:23,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:23,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:23,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:33:23,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:33:23,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:33:23,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:23,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:33:23,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:33:23,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:23,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:33:23,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:23,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:23,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:33:23,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:33:23,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:23,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:33:23,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:23,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:33:23,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:23,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:33:23,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:33:23,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:23,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:23,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:33:23,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:23,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:33:23,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:33:23,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:33:23,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:23,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:33:23,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:33:23,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:23,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:33:23,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:23,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:33:23,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:33:23,828] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:23,828] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:23,828] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:33:23,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:23,829] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:23,829] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:33:23,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:33:23,829] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:23,829] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:33:23,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:23,829] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:23,829] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:33:23,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:33:23,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:33:23,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:33:23,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:23,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:23,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:33:23,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:33:23,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:23,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:33:23,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:23,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:23,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:23,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:33:23,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:33:23,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:33:23,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:33:23,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:33:23,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:33:23,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:33:23,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:33:23,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:33:23,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:23,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:33:23,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:33:23,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:23,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:33:23,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: successfully saved checkpoint at iteration 5000 to checkpoints_146moscareap +7: time (ms) | save-checkpoint: 486.02 +7: iteration 5010/ 21553 | consumed samples: 1282560 | consumed tokens: 2626682880 | elapsed time per iteration (s): 0.37 | learning rate: 1.785E-04 | global batch size: 256 | lm loss: 3.288962E+00 | grad norm: 0.392 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 696.602 | TFLOPs: 24.39 | +7: iteration 5020/ 21553 | consumed samples: 1285120 | consumed tokens: 2631925760 | elapsed time per iteration (s): 0.31 | learning rate: 1.784E-04 | global batch size: 256 | lm loss: 3.288670E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.135 | TFLOPs: 28.54 | +7: iteration 5030/ 21553 | consumed samples: 1287680 | consumed tokens: 2637168640 | elapsed time per iteration (s): 0.31 | learning rate: 1.783E-04 | global batch size: 256 | lm loss: 3.263904E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.628 | TFLOPs: 29.15 | +7: iteration 5040/ 21553 | consumed samples: 1290240 | consumed tokens: 2642411520 | elapsed time per iteration (s): 0.32 | learning rate: 1.782E-04 | global batch size: 256 | lm loss: 3.296788E+00 | grad norm: 0.437 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 801.185 | TFLOPs: 28.05 | +7: iteration 5050/ 21553 | consumed samples: 1292800 | consumed tokens: 2647654400 | elapsed time per iteration (s): 0.31 | learning rate: 1.781E-04 | global batch size: 256 | lm loss: 3.272903E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.319 | TFLOPs: 29.00 | +7: iteration 5060/ 21553 | consumed samples: 1295360 | consumed tokens: 2652897280 | elapsed time per iteration (s): 0.31 | learning rate: 1.781E-04 | global batch size: 256 | lm loss: 3.281297E+00 | grad norm: 0.410 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.891 | TFLOPs: 29.12 | +7: iteration 5070/ 21553 | consumed samples: 1297920 | consumed tokens: 2658140160 | elapsed time per iteration (s): 0.31 | learning rate: 1.780E-04 | global batch size: 256 | lm loss: 3.280602E+00 | grad norm: 0.383 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.061 | TFLOPs: 29.37 | +7: iteration 5080/ 21553 | consumed samples: 1300480 | consumed tokens: 2663383040 | elapsed time per iteration (s): 0.31 | learning rate: 1.779E-04 | global batch size: 256 | lm loss: 3.296594E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.081 | TFLOPs: 28.99 | +7: iteration 5090/ 21553 | consumed samples: 1303040 | consumed tokens: 2668625920 | elapsed time per iteration (s): 0.31 | learning rate: 1.778E-04 | global batch size: 256 | lm loss: 3.298006E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.177 | TFLOPs: 29.31 | +7: iteration 5100/ 21553 | consumed samples: 1305600 | consumed tokens: 2673868800 | elapsed time per iteration (s): 0.31 | learning rate: 1.777E-04 | global batch size: 256 | lm loss: 3.297634E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.569 | TFLOPs: 28.69 | +7: iteration 5110/ 21553 | consumed samples: 1308160 | consumed tokens: 2679111680 | elapsed time per iteration (s): 0.31 | learning rate: 1.776E-04 | global batch size: 256 | lm loss: 3.288765E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.841 | TFLOPs: 28.95 | +7: iteration 5120/ 21553 | consumed samples: 1310720 | consumed tokens: 2684354560 | elapsed time per iteration (s): 0.32 | learning rate: 1.775E-04 | global batch size: 256 | lm loss: 3.260808E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.930 | TFLOPs: 28.39 | +7: iteration 5130/ 21553 | consumed samples: 1313280 | consumed tokens: 2689597440 | elapsed time per iteration (s): 0.31 | learning rate: 1.775E-04 | global batch size: 256 | lm loss: 3.287831E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.837 | TFLOPs: 29.05 | +7: iteration 5140/ 21553 | consumed samples: 1315840 | consumed tokens: 2694840320 | elapsed time per iteration (s): 0.31 | learning rate: 1.774E-04 | global batch size: 256 | lm loss: 3.289235E+00 | grad norm: 0.392 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.956 | TFLOPs: 28.81 | +7: iteration 5150/ 21553 | consumed samples: 1318400 | consumed tokens: 2700083200 | elapsed time per iteration (s): 0.31 | learning rate: 1.773E-04 | global batch size: 256 | lm loss: 3.283505E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.906 | TFLOPs: 28.67 | +7: iteration 5160/ 21553 | consumed samples: 1320960 | consumed tokens: 2705326080 | elapsed time per iteration (s): 0.31 | learning rate: 1.772E-04 | global batch size: 256 | lm loss: 3.276638E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.988 | TFLOPs: 29.02 | +7: iteration 5170/ 21553 | consumed samples: 1323520 | consumed tokens: 2710568960 | elapsed time per iteration (s): 0.31 | learning rate: 1.771E-04 | global batch size: 256 | lm loss: 3.286792E+00 | grad norm: 0.368 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.356 | TFLOPs: 28.68 | +7: iteration 5180/ 21553 | consumed samples: 1326080 | consumed tokens: 2715811840 | elapsed time per iteration (s): 0.31 | learning rate: 1.770E-04 | global batch size: 256 | lm loss: 3.264652E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.663 | TFLOPs: 29.11 | +7: iteration 5190/ 21553 | consumed samples: 1328640 | consumed tokens: 2721054720 | elapsed time per iteration (s): 0.32 | learning rate: 1.769E-04 | global batch size: 256 | lm loss: 3.271479E+00 | grad norm: 0.461 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 798.324 | TFLOPs: 27.95 | +7: iteration 5200/ 21553 | consumed samples: 1331200 | consumed tokens: 2726297600 | elapsed time per iteration (s): 0.31 | learning rate: 1.768E-04 | global batch size: 256 | lm loss: 3.275989E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.897 | TFLOPs: 28.46 | +7: iteration 5210/ 21553 | consumed samples: 1333760 | consumed tokens: 2731540480 | elapsed time per iteration (s): 0.33 | learning rate: 1.767E-04 | global batch size: 256 | lm loss: 3.264493E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 786.456 | TFLOPs: 27.53 | +7: iteration 5220/ 21553 | consumed samples: 1336320 | consumed tokens: 2736783360 | elapsed time per iteration (s): 0.31 | learning rate: 1.767E-04 | global batch size: 256 | lm loss: 3.264981E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.295 | TFLOPs: 29.07 | +7: iteration 5230/ 21553 | consumed samples: 1338880 | consumed tokens: 2742026240 | elapsed time per iteration (s): 0.31 | learning rate: 1.766E-04 | global batch size: 256 | lm loss: 3.231377E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.475 | TFLOPs: 29.11 | +7: iteration 5240/ 21553 | consumed samples: 1341440 | consumed tokens: 2747269120 | elapsed time per iteration (s): 0.31 | learning rate: 1.765E-04 | global batch size: 256 | lm loss: 3.246476E+00 | grad norm: 0.399 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.207 | TFLOPs: 29.20 | +7: iteration 5250/ 21553 | consumed samples: 1344000 | consumed tokens: 2752512000 | elapsed time per iteration (s): 0.31 | learning rate: 1.764E-04 | global batch size: 256 | lm loss: 3.266081E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.106 | TFLOPs: 29.16 | +7: iteration 5260/ 21553 | consumed samples: 1346560 | consumed tokens: 2757754880 | elapsed time per iteration (s): 0.31 | learning rate: 1.763E-04 | global batch size: 256 | lm loss: 3.252028E+00 | grad norm: 0.389 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.620 | TFLOPs: 29.01 | +7: iteration 5270/ 21553 | consumed samples: 1349120 | consumed tokens: 2762997760 | elapsed time per iteration (s): 0.31 | learning rate: 1.762E-04 | global batch size: 256 | lm loss: 3.254095E+00 | grad norm: 0.367 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.580 | TFLOPs: 28.73 | +7: iteration 5280/ 21553 | consumed samples: 1351680 | consumed tokens: 2768240640 | elapsed time per iteration (s): 0.30 | learning rate: 1.761E-04 | global batch size: 256 | lm loss: 3.251728E+00 | grad norm: 0.413 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.884 | TFLOPs: 29.44 | +7: iteration 5290/ 21553 | consumed samples: 1354240 | consumed tokens: 2773483520 | elapsed time per iteration (s): 0.32 | learning rate: 1.760E-04 | global batch size: 256 | lm loss: 3.273668E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 804.683 | TFLOPs: 28.17 | +7: iteration 5300/ 21553 | consumed samples: 1356800 | consumed tokens: 2778726400 | elapsed time per iteration (s): 0.31 | learning rate: 1.759E-04 | global batch size: 256 | lm loss: 3.253279E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.375 | TFLOPs: 28.82 | +7: iteration 5310/ 21553 | consumed samples: 1359360 | consumed tokens: 2783969280 | elapsed time per iteration (s): 0.31 | learning rate: 1.758E-04 | global batch size: 256 | lm loss: 3.231398E+00 | grad norm: 0.448 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.977 | TFLOPs: 28.92 | +7: iteration 5320/ 21553 | consumed samples: 1361920 | consumed tokens: 2789212160 | elapsed time per iteration (s): 0.31 | learning rate: 1.758E-04 | global batch size: 256 | lm loss: 3.286682E+00 | grad norm: 0.390 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.160 | TFLOPs: 28.96 | +7: iteration 5330/ 21553 | consumed samples: 1364480 | consumed tokens: 2794455040 | elapsed time per iteration (s): 0.31 | learning rate: 1.757E-04 | global batch size: 256 | lm loss: 3.248992E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.753 | TFLOPs: 28.87 | +7: iteration 5340/ 21553 | consumed samples: 1367040 | consumed tokens: 2799697920 | elapsed time per iteration (s): 0.31 | learning rate: 1.756E-04 | global batch size: 256 | lm loss: 3.252110E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.999 | TFLOPs: 28.64 | +7: iteration 5350/ 21553 | consumed samples: 1369600 | consumed tokens: 2804940800 | elapsed time per iteration (s): 0.31 | learning rate: 1.755E-04 | global batch size: 256 | lm loss: 3.263535E+00 | grad norm: 0.386 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.650 | TFLOPs: 28.94 | +7: iteration 5360/ 21553 | consumed samples: 1372160 | consumed tokens: 2810183680 | elapsed time per iteration (s): 0.30 | learning rate: 1.754E-04 | global batch size: 256 | lm loss: 3.234604E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.359 | TFLOPs: 29.38 | +7: iteration 5370/ 21553 | consumed samples: 1374720 | consumed tokens: 2815426560 | elapsed time per iteration (s): 0.33 | learning rate: 1.753E-04 | global batch size: 256 | lm loss: 3.246875E+00 | grad norm: 0.417 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 784.881 | TFLOPs: 27.48 | +7: iteration 5380/ 21553 | consumed samples: 1377280 | consumed tokens: 2820669440 | elapsed time per iteration (s): 0.31 | learning rate: 1.752E-04 | global batch size: 256 | lm loss: 3.276414E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.658 | TFLOPs: 29.36 | +7: iteration 5390/ 21553 | consumed samples: 1379840 | consumed tokens: 2825912320 | elapsed time per iteration (s): 0.31 | learning rate: 1.751E-04 | global batch size: 256 | lm loss: 3.250277E+00 | grad norm: 0.388 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.194 | TFLOPs: 28.92 | +7: iteration 5400/ 21553 | consumed samples: 1382400 | consumed tokens: 2831155200 | elapsed time per iteration (s): 0.30 | learning rate: 1.750E-04 | global batch size: 256 | lm loss: 3.212196E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 848.792 | TFLOPs: 29.71 | +7: iteration 5410/ 21553 | consumed samples: 1384960 | consumed tokens: 2836398080 | elapsed time per iteration (s): 0.31 | learning rate: 1.749E-04 | global batch size: 256 | lm loss: 3.250084E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.677 | TFLOPs: 28.80 | +7: iteration 5420/ 21553 | consumed samples: 1387520 | consumed tokens: 2841640960 | elapsed time per iteration (s): 0.30 | learning rate: 1.748E-04 | global batch size: 256 | lm loss: 3.281904E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.332 | TFLOPs: 29.42 | +7: iteration 5430/ 21553 | consumed samples: 1390080 | consumed tokens: 2846883840 | elapsed time per iteration (s): 0.30 | learning rate: 1.748E-04 | global batch size: 256 | lm loss: 3.258528E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.611 | TFLOPs: 29.53 | +7: iteration 5440/ 21553 | consumed samples: 1392640 | consumed tokens: 2852126720 | elapsed time per iteration (s): 0.31 | learning rate: 1.747E-04 | global batch size: 256 | lm loss: 3.264530E+00 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.911 | TFLOPs: 28.98 | +7: iteration 5450/ 21553 | consumed samples: 1395200 | consumed tokens: 2857369600 | elapsed time per iteration (s): 0.31 | learning rate: 1.746E-04 | global batch size: 256 | lm loss: 3.220209E+00 | grad norm: 0.399 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.705 | TFLOPs: 29.08 | +7: iteration 5460/ 21553 | consumed samples: 1397760 | consumed tokens: 2862612480 | elapsed time per iteration (s): 0.31 | learning rate: 1.745E-04 | global batch size: 256 | lm loss: 3.250216E+00 | grad norm: 0.389 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.262 | TFLOPs: 29.21 | +7: iteration 5470/ 21553 | consumed samples: 1400320 | consumed tokens: 2867855360 | elapsed time per iteration (s): 0.35 | learning rate: 1.744E-04 | global batch size: 256 | lm loss: 3.249505E+00 | grad norm: 0.383 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 734.715 | TFLOPs: 25.72 | +7: iteration 5480/ 21553 | consumed samples: 1402880 | consumed tokens: 2873098240 | elapsed time per iteration (s): 0.31 | learning rate: 1.743E-04 | global batch size: 256 | lm loss: 3.261930E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.521 | TFLOPs: 28.51 | +7: iteration 5490/ 21553 | consumed samples: 1405440 | consumed tokens: 2878341120 | elapsed time per iteration (s): 0.32 | learning rate: 1.742E-04 | global batch size: 256 | lm loss: 3.242454E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 804.938 | TFLOPs: 28.18 | +7: iteration 5500/ 21553 | consumed samples: 1408000 | consumed tokens: 2883584000 | elapsed time per iteration (s): 0.32 | learning rate: 1.741E-04 | global batch size: 256 | lm loss: 3.273951E+00 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 804.695 | TFLOPs: 28.17 | +7: iteration 5510/ 21553 | consumed samples: 1410560 | consumed tokens: 2888826880 | elapsed time per iteration (s): 0.31 | learning rate: 1.740E-04 | global batch size: 256 | lm loss: 3.221731E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.015 | TFLOPs: 28.99 | +7: iteration 5520/ 21553 | consumed samples: 1413120 | consumed tokens: 2894069760 | elapsed time per iteration (s): 0.33 | learning rate: 1.739E-04 | global batch size: 256 | lm loss: 3.230446E+00 | grad norm: 0.414 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 785.219 | TFLOPs: 27.49 | +7: iteration 5530/ 21553 | consumed samples: 1415680 | consumed tokens: 2899312640 | elapsed time per iteration (s): 0.31 | learning rate: 1.738E-04 | global batch size: 256 | lm loss: 3.229006E+00 | grad norm: 0.403 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.258 | TFLOPs: 29.10 | +7: iteration 5540/ 21553 | consumed samples: 1418240 | consumed tokens: 2904555520 | elapsed time per iteration (s): 0.30 | learning rate: 1.737E-04 | global batch size: 256 | lm loss: 3.248904E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 849.771 | TFLOPs: 29.75 | +7: iteration 5550/ 21553 | consumed samples: 1420800 | consumed tokens: 2909798400 | elapsed time per iteration (s): 0.31 | learning rate: 1.736E-04 | global batch size: 256 | lm loss: 3.246728E+00 | grad norm: 0.435 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.118 | TFLOPs: 29.24 | +7: iteration 5560/ 21553 | consumed samples: 1423360 | consumed tokens: 2915041280 | elapsed time per iteration (s): 0.31 | learning rate: 1.735E-04 | global batch size: 256 | lm loss: 3.227701E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.488 | TFLOPs: 28.93 | +7: iteration 5570/ 21553 | consumed samples: 1425920 | consumed tokens: 2920284160 | elapsed time per iteration (s): 0.31 | learning rate: 1.735E-04 | global batch size: 256 | lm loss: 3.232221E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.324 | TFLOPs: 29.07 | +7: iteration 5580/ 21553 | consumed samples: 1428480 | consumed tokens: 2925527040 | elapsed time per iteration (s): 0.30 | learning rate: 1.734E-04 | global batch size: 256 | lm loss: 3.245388E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.861 | TFLOPs: 29.47 | +7: iteration 5590/ 21553 | consumed samples: 1431040 | consumed tokens: 2930769920 | elapsed time per iteration (s): 0.30 | learning rate: 1.733E-04 | global batch size: 256 | lm loss: 3.206933E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.513 | TFLOPs: 29.39 | +7: iteration 5600/ 21553 | consumed samples: 1433600 | consumed tokens: 2936012800 | elapsed time per iteration (s): 0.31 | learning rate: 1.732E-04 | global batch size: 256 | lm loss: 3.241080E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.344 | TFLOPs: 29.00 | +7: iteration 5610/ 21553 | consumed samples: 1436160 | consumed tokens: 2941255680 | elapsed time per iteration (s): 0.31 | learning rate: 1.731E-04 | global batch size: 256 | lm loss: 3.226643E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.058 | TFLOPs: 29.02 | +7: iteration 5620/ 21553 | consumed samples: 1438720 | consumed tokens: 2946498560 | elapsed time per iteration (s): 0.31 | learning rate: 1.730E-04 | global batch size: 256 | lm loss: 3.239425E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.961 | TFLOPs: 29.23 | +7: iteration 5630/ 21553 | consumed samples: 1441280 | consumed tokens: 2951741440 | elapsed time per iteration (s): 0.31 | learning rate: 1.729E-04 | global batch size: 256 | lm loss: 3.226463E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.729 | TFLOPs: 29.12 | +7: iteration 5640/ 21553 | consumed samples: 1443840 | consumed tokens: 2956984320 | elapsed time per iteration (s): 0.31 | learning rate: 1.728E-04 | global batch size: 256 | lm loss: 3.237056E+00 | grad norm: 0.411 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.539 | TFLOPs: 29.21 | +7: iteration 5650/ 21553 | consumed samples: 1446400 | consumed tokens: 2962227200 | elapsed time per iteration (s): 0.31 | learning rate: 1.727E-04 | global batch size: 256 | lm loss: 3.259244E+00 | grad norm: 0.388 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.582 | TFLOPs: 29.15 | +7: iteration 5660/ 21553 | consumed samples: 1448960 | consumed tokens: 2967470080 | elapsed time per iteration (s): 0.32 | learning rate: 1.726E-04 | global batch size: 256 | lm loss: 3.255648E+00 | grad norm: 0.387 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.648 | TFLOPs: 28.38 | +7: iteration 5670/ 21553 | consumed samples: 1451520 | consumed tokens: 2972712960 | elapsed time per iteration (s): 0.30 | learning rate: 1.725E-04 | global batch size: 256 | lm loss: 3.230665E+00 | grad norm: 0.373 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.207 | TFLOPs: 29.41 | +7: iteration 5680/ 21553 | consumed samples: 1454080 | consumed tokens: 2977955840 | elapsed time per iteration (s): 0.31 | learning rate: 1.724E-04 | global batch size: 256 | lm loss: 3.239487E+00 | grad norm: 0.406 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.538 | TFLOPs: 28.76 | +7: iteration 5690/ 21553 | consumed samples: 1456640 | consumed tokens: 2983198720 | elapsed time per iteration (s): 0.31 | learning rate: 1.723E-04 | global batch size: 256 | lm loss: 3.222583E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.242 | TFLOPs: 28.78 | +7: iteration 5700/ 21553 | consumed samples: 1459200 | consumed tokens: 2988441600 | elapsed time per iteration (s): 0.32 | learning rate: 1.722E-04 | global batch size: 256 | lm loss: 3.241264E+00 | grad norm: 0.382 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 803.528 | TFLOPs: 28.13 | +7: iteration 5710/ 21553 | consumed samples: 1461760 | consumed tokens: 2993684480 | elapsed time per iteration (s): 0.31 | learning rate: 1.721E-04 | global batch size: 256 | lm loss: 3.239518E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.593 | TFLOPs: 29.15 | +7: iteration 5720/ 21553 | consumed samples: 1464320 | consumed tokens: 2998927360 | elapsed time per iteration (s): 0.30 | learning rate: 1.720E-04 | global batch size: 256 | lm loss: 3.220007E+00 | grad norm: 0.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 848.718 | TFLOPs: 29.71 | +7: iteration 5730/ 21553 | consumed samples: 1466880 | consumed tokens: 3004170240 | elapsed time per iteration (s): 0.30 | learning rate: 1.719E-04 | global batch size: 256 | lm loss: 3.206579E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.971 | TFLOPs: 29.51 | +7: iteration 5740/ 21553 | consumed samples: 1469440 | consumed tokens: 3009413120 | elapsed time per iteration (s): 0.30 | learning rate: 1.718E-04 | global batch size: 256 | lm loss: 3.237750E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.550 | TFLOPs: 29.53 | +7: iteration 5750/ 21553 | consumed samples: 1472000 | consumed tokens: 3014656000 | elapsed time per iteration (s): 0.31 | learning rate: 1.717E-04 | global batch size: 256 | lm loss: 3.224679E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.826 | TFLOPs: 28.98 | +7: iteration 5760/ 21553 | consumed samples: 1474560 | consumed tokens: 3019898880 | elapsed time per iteration (s): 0.31 | learning rate: 1.716E-04 | global batch size: 256 | lm loss: 3.204031E+00 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.651 | TFLOPs: 29.04 | +7: iteration 5770/ 21553 | consumed samples: 1477120 | consumed tokens: 3025141760 | elapsed time per iteration (s): 0.30 | learning rate: 1.715E-04 | global batch size: 256 | lm loss: 3.241042E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.979 | TFLOPs: 29.51 | +7: iteration 5780/ 21553 | consumed samples: 1479680 | consumed tokens: 3030384640 | elapsed time per iteration (s): 0.31 | learning rate: 1.714E-04 | global batch size: 256 | lm loss: 3.219922E+00 | grad norm: 0.392 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.282 | TFLOPs: 29.07 | +7: iteration 5790/ 21553 | consumed samples: 1482240 | consumed tokens: 3035627520 | elapsed time per iteration (s): 0.31 | learning rate: 1.714E-04 | global batch size: 256 | lm loss: 3.240030E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.044 | TFLOPs: 28.81 | +7: iteration 5800/ 21553 | consumed samples: 1484800 | consumed tokens: 3040870400 | elapsed time per iteration (s): 0.31 | learning rate: 1.713E-04 | global batch size: 256 | lm loss: 3.225947E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.750 | TFLOPs: 29.29 | +7: iteration 5810/ 21553 | consumed samples: 1487360 | consumed tokens: 3046113280 | elapsed time per iteration (s): 0.32 | learning rate: 1.712E-04 | global batch size: 256 | lm loss: 3.243945E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 802.989 | TFLOPs: 28.11 | +7: iteration 5820/ 21553 | consumed samples: 1489920 | consumed tokens: 3051356160 | elapsed time per iteration (s): 0.31 | learning rate: 1.711E-04 | global batch size: 256 | lm loss: 3.232056E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.792 | TFLOPs: 29.19 | +7: iteration 5830/ 21553 | consumed samples: 1492480 | consumed tokens: 3056599040 | elapsed time per iteration (s): 0.30 | learning rate: 1.710E-04 | global batch size: 256 | lm loss: 3.204475E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.900 | TFLOPs: 29.40 | +7: iteration 5840/ 21553 | consumed samples: 1495040 | consumed tokens: 3061841920 | elapsed time per iteration (s): 0.31 | learning rate: 1.709E-04 | global batch size: 256 | lm loss: 3.217787E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.941 | TFLOPs: 29.02 | +7: iteration 5850/ 21553 | consumed samples: 1497600 | consumed tokens: 3067084800 | elapsed time per iteration (s): 0.33 | learning rate: 1.708E-04 | global batch size: 256 | lm loss: 3.248265E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 784.721 | TFLOPs: 27.47 | +7: iteration 5860/ 21553 | consumed samples: 1500160 | consumed tokens: 3072327680 | elapsed time per iteration (s): 0.31 | learning rate: 1.707E-04 | global batch size: 256 | lm loss: 3.203521E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.022 | TFLOPs: 28.85 | +7: iteration 5870/ 21553 | consumed samples: 1502720 | consumed tokens: 3077570560 | elapsed time per iteration (s): 0.31 | learning rate: 1.706E-04 | global batch size: 256 | lm loss: 3.229808E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.984 | TFLOPs: 28.88 | +7: iteration 5880/ 21553 | consumed samples: 1505280 | consumed tokens: 3082813440 | elapsed time per iteration (s): 0.32 | learning rate: 1.705E-04 | global batch size: 256 | lm loss: 3.216888E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.626 | TFLOPs: 28.41 | +7: iteration 5890/ 21553 | consumed samples: 1507840 | consumed tokens: 3088056320 | elapsed time per iteration (s): 0.31 | learning rate: 1.704E-04 | global batch size: 256 | lm loss: 3.196558E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.876 | TFLOPs: 28.46 | +7: iteration 5900/ 21553 | consumed samples: 1510400 | consumed tokens: 3093299200 | elapsed time per iteration (s): 0.31 | learning rate: 1.703E-04 | global batch size: 256 | lm loss: 3.193558E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.670 | TFLOPs: 28.66 | +7: iteration 5910/ 21553 | consumed samples: 1512960 | consumed tokens: 3098542080 | elapsed time per iteration (s): 0.31 | learning rate: 1.702E-04 | global batch size: 256 | lm loss: 3.235432E+00 | grad norm: 0.373 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.378 | TFLOPs: 28.51 | +7: iteration 5920/ 21553 | consumed samples: 1515520 | consumed tokens: 3103784960 | elapsed time per iteration (s): 0.31 | learning rate: 1.701E-04 | global batch size: 256 | lm loss: 3.214619E+00 | grad norm: 0.373 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.544 | TFLOPs: 29.15 | +7: iteration 5930/ 21553 | consumed samples: 1518080 | consumed tokens: 3109027840 | elapsed time per iteration (s): 0.30 | learning rate: 1.700E-04 | global batch size: 256 | lm loss: 3.233142E+00 | grad norm: 0.559 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 848.391 | TFLOPs: 29.70 | +7: iteration 5940/ 21553 | consumed samples: 1520640 | consumed tokens: 3114270720 | elapsed time per iteration (s): 0.33 | learning rate: 1.699E-04 | global batch size: 256 | lm loss: 3.233716E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 786.792 | TFLOPs: 27.54 | +7: iteration 5950/ 21553 | consumed samples: 1523200 | consumed tokens: 3119513600 | elapsed time per iteration (s): 0.30 | learning rate: 1.698E-04 | global batch size: 256 | lm loss: 3.228408E+00 | grad norm: 0.407 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 849.788 | TFLOPs: 29.75 | +7: iteration 5960/ 21553 | consumed samples: 1525760 | consumed tokens: 3124756480 | elapsed time per iteration (s): 0.30 | learning rate: 1.697E-04 | global batch size: 256 | lm loss: 3.224272E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.804 | TFLOPs: 29.54 | +7: iteration 5970/ 21553 | consumed samples: 1528320 | consumed tokens: 3129999360 | elapsed time per iteration (s): 0.31 | learning rate: 1.696E-04 | global batch size: 256 | lm loss: 3.221080E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.366 | TFLOPs: 29.17 | +7: iteration 5980/ 21553 | consumed samples: 1530880 | consumed tokens: 3135242240 | elapsed time per iteration (s): 0.31 | learning rate: 1.695E-04 | global batch size: 256 | lm loss: 3.201709E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.621 | TFLOPs: 29.11 | +7: iteration 5990/ 21553 | consumed samples: 1533440 | consumed tokens: 3140485120 | elapsed time per iteration (s): 0.30 | learning rate: 1.694E-04 | global batch size: 256 | lm loss: 3.240320E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.433 | TFLOPs: 29.53 | +0: [2022-11-29 17:38:34,185] [INFO] [logging.py:68:log_dist] [Rank 0] step=6000, skipped=0, lr=[0.00016928570742907802, 0.00016928570742907802, 0.00016928570742907802], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 6000/ 21553 | consumed samples: 1536000 | consumed tokens: 3145728000 | elapsed time per iteration (s): 0.31 | learning rate: 1.693E-04 | global batch size: 256 | lm loss: 3.209027E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.227 | TFLOPs: 28.75 | +0: steps: 6000 loss: 3.1658 iter time (s): 0.309 samples/sec: 829.746 +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 6000 | lm loss value: 3.095521E+00 | lm loss PPL: 2.209874E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 6000 to checkpoints_146moscareap +0: [2022-11-29 17:38:34,329] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step6000 is begin to save! +0: [2022-11-29 17:38:34,333] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:38:34,416] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:38:34,417] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:38:34,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:38:34,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:38:34,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:38:34,450] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:38:34,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:38:34,465] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:38:34,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:38:34,481] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:38:34,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:38:34,497] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:38:34,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:38:34,512] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:38:34,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:38:34,528] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:38:34,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:38:34,543] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:38:34,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:38:34,559] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:38:34,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:38:34,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:38:34,589] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:38:34,590] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:38:34,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:38:34,605] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:38:34,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:38:34,620] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:38:34,636] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:38:34,636] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:38:34,651] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:38:34,651] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:38:34,652] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:38:34,653] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_146moscareap/global_step6000/mp_rank_00_model_states.pt +0: [2022-11-29 17:38:34,653] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:38:34,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:38:34,674] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:38:34,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:38:34,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:38:34,704] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:38:34,704] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:38:34,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:38:34,706] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:38:34,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +6: [2022-11-29 17:38:34,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:38:34,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:38:34,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:38:34,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:38:34,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:38:34,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:38:34,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +7: [2022-11-29 17:38:34,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:38:34,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:38:34,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +7: [2022-11-29 17:38:34,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:38:34,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:38:34,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:38:34,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:38:34,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:38:34,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:38:34,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:38:34,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:38:34,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:38:34,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:38:34,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +6: [2022-11-29 17:38:34,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:38:34,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:38:34,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:38:34,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:38:34,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:38:34,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:38:34,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:38:34,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:38:34,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:38:34,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:38:34,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:38:34,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:38:34,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:38:34,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:38:34,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:38:34,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:38:34,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:38:34,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:38:34,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:38:34,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:38:34,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:38:34,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:38:34,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:38:34,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:38:34,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3: [2022-11-29 17:38:34,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:38:34,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:38:34,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:38:34,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:38:34,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:38:34,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:38:34,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:38:34,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:38:34,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +1: [2022-11-29 17:38:34,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +7: [2022-11-29 17:38:34,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:38:34,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:38:34,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:38:34,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:38:34,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +1: [2022-11-29 17:38:34,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +7: [2022-11-29 17:38:34,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:38:34,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:38:34,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:38:34,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:38:34,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:38:34,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:38:34,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:38:34,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:38:34,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:38:34,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:38:34,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:38:34,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:38:34,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:38:34,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:38:34,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:38:34,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:38:34,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:38:34,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:38:34,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:38:34,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:38:34,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:38:34,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:38:34,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:38:34,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:38:34,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:38:34,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +4: [2022-11-29 17:38:34,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +3: [2022-11-29 17:38:34,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:38:34,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:38:34,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:38:34,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:38:34,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:38:34,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:38:34,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:38:34,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:38:34,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:38:34,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:38:34,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:38:34,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:38:34,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:38:34,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +5: [2022-11-29 17:38:34,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +4: [2022-11-29 17:38:34,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:38:34,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:38:34,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:38:34,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:38:34,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:38:34,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:38:34,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:38:34,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:38:34,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:38:34,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:38:34,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:38:34,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:38:34,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:38:34,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:38:34,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:38:34,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +3: [2022-11-29 17:38:34,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +7: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:38:34,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:38:34,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:38:34,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:38:34,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:38:34,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:38:34,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:38:34,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:38:34,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:38:34,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:38:34,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:38:34,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:38:34,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:38:34,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:38:34,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:38:34,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:38:34,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:38:34,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:38:34,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:38:34,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:38:34,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:38:34,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:38:34,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:38:34,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:38:34,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:38:34,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:38:34,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:38:34,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:38:34,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:38:34,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:38:34,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:38:34,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:38:34,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:38:34,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:38:34,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:38:34,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:38:34,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:38:34,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:38:34,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:38:34,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:38:34,727] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step6000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:38:34,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: successfully saved checkpoint at iteration 6000 to checkpoints_146moscareap +7: time (ms) | save-checkpoint: 405.48 +7: iteration 6010/ 21553 | consumed samples: 1538560 | consumed tokens: 3150970880 | elapsed time per iteration (s): 0.36 | learning rate: 1.692E-04 | global batch size: 256 | lm loss: 3.223615E+00 | grad norm: 0.392 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 720.779 | TFLOPs: 25.23 | +7: iteration 6020/ 21553 | consumed samples: 1541120 | consumed tokens: 3156213760 | elapsed time per iteration (s): 0.31 | learning rate: 1.691E-04 | global batch size: 256 | lm loss: 3.229572E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.101 | TFLOPs: 29.20 | +7: iteration 6030/ 21553 | consumed samples: 1543680 | consumed tokens: 3161456640 | elapsed time per iteration (s): 0.31 | learning rate: 1.690E-04 | global batch size: 256 | lm loss: 3.242147E+00 | grad norm: 0.409 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.813 | TFLOPs: 28.84 | +7: iteration 6040/ 21553 | consumed samples: 1546240 | consumed tokens: 3166699520 | elapsed time per iteration (s): 0.31 | learning rate: 1.689E-04 | global batch size: 256 | lm loss: 3.193808E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.520 | TFLOPs: 28.79 | +7: iteration 6050/ 21553 | consumed samples: 1548800 | consumed tokens: 3171942400 | elapsed time per iteration (s): 0.31 | learning rate: 1.688E-04 | global batch size: 256 | lm loss: 3.193464E+00 | grad norm: 0.429 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.789 | TFLOPs: 28.73 | +7: iteration 6060/ 21553 | consumed samples: 1551360 | consumed tokens: 3177185280 | elapsed time per iteration (s): 0.31 | learning rate: 1.687E-04 | global batch size: 256 | lm loss: 3.206738E+00 | grad norm: 0.368 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.030 | TFLOPs: 28.88 | +7: iteration 6070/ 21553 | consumed samples: 1553920 | consumed tokens: 3182428160 | elapsed time per iteration (s): 0.32 | learning rate: 1.686E-04 | global batch size: 256 | lm loss: 3.238066E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 799.507 | TFLOPs: 27.99 | +7: iteration 6080/ 21553 | consumed samples: 1556480 | consumed tokens: 3187671040 | elapsed time per iteration (s): 0.31 | learning rate: 1.685E-04 | global batch size: 256 | lm loss: 3.191551E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.937 | TFLOPs: 29.16 | +7: iteration 6090/ 21553 | consumed samples: 1559040 | consumed tokens: 3192913920 | elapsed time per iteration (s): 0.31 | learning rate: 1.684E-04 | global batch size: 256 | lm loss: 3.255566E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.905 | TFLOPs: 28.95 | +7: iteration 6100/ 21553 | consumed samples: 1561600 | consumed tokens: 3198156800 | elapsed time per iteration (s): 0.31 | learning rate: 1.683E-04 | global batch size: 256 | lm loss: 3.214491E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.523 | TFLOPs: 29.32 | +7: iteration 6110/ 21553 | consumed samples: 1564160 | consumed tokens: 3203399680 | elapsed time per iteration (s): 0.30 | learning rate: 1.682E-04 | global batch size: 256 | lm loss: 3.226561E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.681 | TFLOPs: 29.50 | +7: iteration 6120/ 21553 | consumed samples: 1566720 | consumed tokens: 3208642560 | elapsed time per iteration (s): 0.30 | learning rate: 1.681E-04 | global batch size: 256 | lm loss: 3.209882E+00 | grad norm: 0.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 846.444 | TFLOPs: 29.63 | +7: iteration 6130/ 21553 | consumed samples: 1569280 | consumed tokens: 3213885440 | elapsed time per iteration (s): 0.32 | learning rate: 1.680E-04 | global batch size: 256 | lm loss: 3.203744E+00 | grad norm: 0.404 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.726 | TFLOPs: 28.31 | +7: iteration 6140/ 21553 | consumed samples: 1571840 | consumed tokens: 3219128320 | elapsed time per iteration (s): 0.31 | learning rate: 1.679E-04 | global batch size: 256 | lm loss: 3.184591E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.223 | TFLOPs: 29.20 | +7: iteration 6150/ 21553 | consumed samples: 1574400 | consumed tokens: 3224371200 | elapsed time per iteration (s): 0.32 | learning rate: 1.678E-04 | global batch size: 256 | lm loss: 3.207337E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.307 | TFLOPs: 28.30 | +7: iteration 6160/ 21553 | consumed samples: 1576960 | consumed tokens: 3229614080 | elapsed time per iteration (s): 0.30 | learning rate: 1.677E-04 | global batch size: 256 | lm loss: 3.206741E+00 | grad norm: 0.377 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.536 | TFLOPs: 29.39 | +7: iteration 6170/ 21553 | consumed samples: 1579520 | consumed tokens: 3234856960 | elapsed time per iteration (s): 0.30 | learning rate: 1.676E-04 | global batch size: 256 | lm loss: 3.211990E+00 | grad norm: 0.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.939 | TFLOPs: 29.54 | +7: iteration 6180/ 21553 | consumed samples: 1582080 | consumed tokens: 3240099840 | elapsed time per iteration (s): 0.32 | learning rate: 1.675E-04 | global batch size: 256 | lm loss: 3.212678E+00 | grad norm: 0.387 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 801.001 | TFLOPs: 28.04 | +7: iteration 6190/ 21553 | consumed samples: 1584640 | consumed tokens: 3245342720 | elapsed time per iteration (s): 0.33 | learning rate: 1.674E-04 | global batch size: 256 | lm loss: 3.196765E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 782.384 | TFLOPs: 27.39 | +7: iteration 6200/ 21553 | consumed samples: 1587200 | consumed tokens: 3250585600 | elapsed time per iteration (s): 0.31 | learning rate: 1.673E-04 | global batch size: 256 | lm loss: 3.205116E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.837 | TFLOPs: 29.33 | +7: iteration 6210/ 21553 | consumed samples: 1589760 | consumed tokens: 3255828480 | elapsed time per iteration (s): 0.31 | learning rate: 1.672E-04 | global batch size: 256 | lm loss: 3.176930E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.185 | TFLOPs: 28.64 | +7: iteration 6220/ 21553 | consumed samples: 1592320 | consumed tokens: 3261071360 | elapsed time per iteration (s): 0.31 | learning rate: 1.671E-04 | global batch size: 256 | lm loss: 3.231595E+00 | grad norm: 0.935 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.449 | TFLOPs: 28.51 | +7: iteration 6230/ 21553 | consumed samples: 1594880 | consumed tokens: 3266314240 | elapsed time per iteration (s): 0.32 | learning rate: 1.670E-04 | global batch size: 256 | lm loss: 3.226583E+00 | grad norm: 0.407 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 804.661 | TFLOPs: 28.17 | +7: iteration 6240/ 21553 | consumed samples: 1597440 | consumed tokens: 3271557120 | elapsed time per iteration (s): 0.32 | learning rate: 1.669E-04 | global batch size: 256 | lm loss: 3.213863E+00 | grad norm: 0.399 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 800.252 | TFLOPs: 28.01 | +7: iteration 6250/ 21553 | consumed samples: 1600000 | consumed tokens: 3276800000 | elapsed time per iteration (s): 0.31 | learning rate: 1.668E-04 | global batch size: 256 | lm loss: 3.207579E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.105 | TFLOPs: 28.92 | +7: iteration 6260/ 21553 | consumed samples: 1602560 | consumed tokens: 3282042880 | elapsed time per iteration (s): 0.31 | learning rate: 1.667E-04 | global batch size: 256 | lm loss: 3.219876E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.269 | TFLOPs: 29.14 | +7: iteration 6270/ 21553 | consumed samples: 1605120 | consumed tokens: 3287285760 | elapsed time per iteration (s): 0.31 | learning rate: 1.665E-04 | global batch size: 256 | lm loss: 3.230619E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.547 | TFLOPs: 29.29 | +7: iteration 6280/ 21553 | consumed samples: 1607680 | consumed tokens: 3292528640 | elapsed time per iteration (s): 0.31 | learning rate: 1.664E-04 | global batch size: 256 | lm loss: 3.193984E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.379 | TFLOPs: 29.35 | +7: iteration 6290/ 21553 | consumed samples: 1610240 | consumed tokens: 3297771520 | elapsed time per iteration (s): 0.31 | learning rate: 1.663E-04 | global batch size: 256 | lm loss: 3.199455E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.554 | TFLOPs: 28.66 | +7: iteration 6300/ 21553 | consumed samples: 1612800 | consumed tokens: 3303014400 | elapsed time per iteration (s): 0.31 | learning rate: 1.662E-04 | global batch size: 256 | lm loss: 3.208609E+00 | grad norm: 0.377 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.485 | TFLOPs: 28.97 | +7: iteration 6310/ 21553 | consumed samples: 1615360 | consumed tokens: 3308257280 | elapsed time per iteration (s): 0.31 | learning rate: 1.661E-04 | global batch size: 256 | lm loss: 3.182839E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.733 | TFLOPs: 28.66 | +7: iteration 6320/ 21553 | consumed samples: 1617920 | consumed tokens: 3313500160 | elapsed time per iteration (s): 0.31 | learning rate: 1.660E-04 | global batch size: 256 | lm loss: 3.188316E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.713 | TFLOPs: 29.05 | +7: iteration 6330/ 21553 | consumed samples: 1620480 | consumed tokens: 3318743040 | elapsed time per iteration (s): 0.31 | learning rate: 1.659E-04 | global batch size: 256 | lm loss: 3.187193E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.190 | TFLOPs: 28.78 | +7: iteration 6340/ 21553 | consumed samples: 1623040 | consumed tokens: 3323985920 | elapsed time per iteration (s): 0.32 | learning rate: 1.658E-04 | global batch size: 256 | lm loss: 3.196866E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 801.432 | TFLOPs: 28.06 | +7: iteration 6350/ 21553 | consumed samples: 1625600 | consumed tokens: 3329228800 | elapsed time per iteration (s): 0.31 | learning rate: 1.657E-04 | global batch size: 256 | lm loss: 3.220970E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.418 | TFLOPs: 29.28 | +7: iteration 6360/ 21553 | consumed samples: 1628160 | consumed tokens: 3334471680 | elapsed time per iteration (s): 0.30 | learning rate: 1.656E-04 | global batch size: 256 | lm loss: 3.179549E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.359 | TFLOPs: 29.38 | +7: iteration 6370/ 21553 | consumed samples: 1630720 | consumed tokens: 3339714560 | elapsed time per iteration (s): 0.31 | learning rate: 1.655E-04 | global batch size: 256 | lm loss: 3.198226E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.525 | TFLOPs: 28.86 | +7: iteration 6380/ 21553 | consumed samples: 1633280 | consumed tokens: 3344957440 | elapsed time per iteration (s): 0.31 | learning rate: 1.654E-04 | global batch size: 256 | lm loss: 3.194406E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.958 | TFLOPs: 29.33 | +7: iteration 6390/ 21553 | consumed samples: 1635840 | consumed tokens: 3350200320 | elapsed time per iteration (s): 0.31 | learning rate: 1.653E-04 | global batch size: 256 | lm loss: 3.199244E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.655 | TFLOPs: 28.76 | +7: iteration 6400/ 21553 | consumed samples: 1638400 | consumed tokens: 3355443200 | elapsed time per iteration (s): 0.30 | learning rate: 1.652E-04 | global batch size: 256 | lm loss: 3.221173E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.702 | TFLOPs: 29.61 | +7: iteration 6410/ 21553 | consumed samples: 1640960 | consumed tokens: 3360686080 | elapsed time per iteration (s): 0.31 | learning rate: 1.651E-04 | global batch size: 256 | lm loss: 3.197077E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.501 | TFLOPs: 29.07 | +7: iteration 6420/ 21553 | consumed samples: 1643520 | consumed tokens: 3365928960 | elapsed time per iteration (s): 0.31 | learning rate: 1.650E-04 | global batch size: 256 | lm loss: 3.204741E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.781 | TFLOPs: 29.22 | +7: iteration 6430/ 21553 | consumed samples: 1646080 | consumed tokens: 3371171840 | elapsed time per iteration (s): 0.33 | learning rate: 1.649E-04 | global batch size: 256 | lm loss: 3.203930E+00 | grad norm: 0.411 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 775.228 | TFLOPs: 27.14 | +7: iteration 6440/ 21553 | consumed samples: 1648640 | consumed tokens: 3376414720 | elapsed time per iteration (s): 0.31 | learning rate: 1.648E-04 | global batch size: 256 | lm loss: 3.199592E+00 | grad norm: 0.383 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.442 | TFLOPs: 29.32 | +7: iteration 6450/ 21553 | consumed samples: 1651200 | consumed tokens: 3381657600 | elapsed time per iteration (s): 0.31 | learning rate: 1.647E-04 | global batch size: 256 | lm loss: 3.207504E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.506 | TFLOPs: 29.04 | +7: iteration 6460/ 21553 | consumed samples: 1653760 | consumed tokens: 3386900480 | elapsed time per iteration (s): 0.31 | learning rate: 1.646E-04 | global batch size: 256 | lm loss: 3.197363E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.048 | TFLOPs: 28.60 | +7: iteration 6470/ 21553 | consumed samples: 1656320 | consumed tokens: 3392143360 | elapsed time per iteration (s): 0.31 | learning rate: 1.645E-04 | global batch size: 256 | lm loss: 3.221579E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.377 | TFLOPs: 28.47 | +7: iteration 6480/ 21553 | consumed samples: 1658880 | consumed tokens: 3397386240 | elapsed time per iteration (s): 0.31 | learning rate: 1.644E-04 | global batch size: 256 | lm loss: 3.193656E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.988 | TFLOPs: 28.74 | +7: iteration 6490/ 21553 | consumed samples: 1661440 | consumed tokens: 3402629120 | elapsed time per iteration (s): 0.31 | learning rate: 1.643E-04 | global batch size: 256 | lm loss: 3.197479E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.397 | TFLOPs: 28.61 | +7: iteration 6500/ 21553 | consumed samples: 1664000 | consumed tokens: 3407872000 | elapsed time per iteration (s): 0.32 | learning rate: 1.641E-04 | global batch size: 256 | lm loss: 3.193363E+00 | grad norm: 0.390 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 807.148 | TFLOPs: 28.26 | +7: iteration 6510/ 21553 | consumed samples: 1666560 | consumed tokens: 3413114880 | elapsed time per iteration (s): 0.30 | learning rate: 1.640E-04 | global batch size: 256 | lm loss: 3.181508E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.219 | TFLOPs: 29.48 | +7: iteration 6520/ 21553 | consumed samples: 1669120 | consumed tokens: 3418357760 | elapsed time per iteration (s): 0.30 | learning rate: 1.639E-04 | global batch size: 256 | lm loss: 3.185005E+00 | grad norm: 0.367 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.828 | TFLOPs: 29.51 | +7: iteration 6530/ 21553 | consumed samples: 1671680 | consumed tokens: 3423600640 | elapsed time per iteration (s): 0.31 | learning rate: 1.638E-04 | global batch size: 256 | lm loss: 3.160998E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.442 | TFLOPs: 29.32 | +7: iteration 6540/ 21553 | consumed samples: 1674240 | consumed tokens: 3428843520 | elapsed time per iteration (s): 0.31 | learning rate: 1.637E-04 | global batch size: 256 | lm loss: 3.179117E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.668 | TFLOPs: 29.04 | +7: iteration 6550/ 21553 | consumed samples: 1676800 | consumed tokens: 3434086400 | elapsed time per iteration (s): 0.31 | learning rate: 1.636E-04 | global batch size: 256 | lm loss: 3.195086E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.962 | TFLOPs: 29.26 | +7: iteration 6560/ 21553 | consumed samples: 1679360 | consumed tokens: 3439329280 | elapsed time per iteration (s): 0.30 | learning rate: 1.635E-04 | global batch size: 256 | lm loss: 3.176852E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.580 | TFLOPs: 29.43 | +7: iteration 6570/ 21553 | consumed samples: 1681920 | consumed tokens: 3444572160 | elapsed time per iteration (s): 0.31 | learning rate: 1.634E-04 | global batch size: 256 | lm loss: 3.177767E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.642 | TFLOPs: 28.90 | +7: iteration 6580/ 21553 | consumed samples: 1684480 | consumed tokens: 3449815040 | elapsed time per iteration (s): 0.31 | learning rate: 1.633E-04 | global batch size: 256 | lm loss: 3.205607E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.593 | TFLOPs: 28.52 | +7: iteration 6590/ 21553 | consumed samples: 1687040 | consumed tokens: 3455057920 | elapsed time per iteration (s): 0.32 | learning rate: 1.632E-04 | global batch size: 256 | lm loss: 3.194770E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 807.746 | TFLOPs: 28.28 | +7: iteration 6600/ 21553 | consumed samples: 1689600 | consumed tokens: 3460300800 | elapsed time per iteration (s): 0.30 | learning rate: 1.631E-04 | global batch size: 256 | lm loss: 3.224358E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 846.062 | TFLOPs: 29.62 | +7: iteration 6610/ 21553 | consumed samples: 1692160 | consumed tokens: 3465543680 | elapsed time per iteration (s): 0.31 | learning rate: 1.630E-04 | global batch size: 256 | lm loss: 3.200631E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.256 | TFLOPs: 28.71 | +7: iteration 6620/ 21553 | consumed samples: 1694720 | consumed tokens: 3470786560 | elapsed time per iteration (s): 0.31 | learning rate: 1.629E-04 | global batch size: 256 | lm loss: 3.168320E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.929 | TFLOPs: 28.91 | +7: iteration 6630/ 21553 | consumed samples: 1697280 | consumed tokens: 3476029440 | elapsed time per iteration (s): 0.30 | learning rate: 1.628E-04 | global batch size: 256 | lm loss: 3.193445E+00 | grad norm: 0.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.456 | TFLOPs: 29.53 | +7: iteration 6640/ 21553 | consumed samples: 1699840 | consumed tokens: 3481272320 | elapsed time per iteration (s): 0.32 | learning rate: 1.627E-04 | global batch size: 256 | lm loss: 3.172618E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.630 | TFLOPs: 28.45 | +7: iteration 6650/ 21553 | consumed samples: 1702400 | consumed tokens: 3486515200 | elapsed time per iteration (s): 0.30 | learning rate: 1.625E-04 | global batch size: 256 | lm loss: 3.183676E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.094 | TFLOPs: 29.51 | +7: iteration 6660/ 21553 | consumed samples: 1704960 | consumed tokens: 3491758080 | elapsed time per iteration (s): 0.31 | learning rate: 1.624E-04 | global batch size: 256 | lm loss: 3.202449E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.131 | TFLOPs: 29.24 | +7: iteration 6670/ 21553 | consumed samples: 1707520 | consumed tokens: 3497000960 | elapsed time per iteration (s): 0.32 | learning rate: 1.623E-04 | global batch size: 256 | lm loss: 3.181457E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 795.035 | TFLOPs: 27.83 | +7: iteration 6680/ 21553 | consumed samples: 1710080 | consumed tokens: 3502243840 | elapsed time per iteration (s): 0.31 | learning rate: 1.622E-04 | global batch size: 256 | lm loss: 3.191779E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.345 | TFLOPs: 29.24 | +7: iteration 6690/ 21553 | consumed samples: 1712640 | consumed tokens: 3507486720 | elapsed time per iteration (s): 0.31 | learning rate: 1.621E-04 | global batch size: 256 | lm loss: 3.192454E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.587 | TFLOPs: 28.76 | +7: iteration 6700/ 21553 | consumed samples: 1715200 | consumed tokens: 3512729600 | elapsed time per iteration (s): 0.31 | learning rate: 1.620E-04 | global batch size: 256 | lm loss: 3.167477E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.244 | TFLOPs: 28.89 | +7: iteration 6710/ 21553 | consumed samples: 1717760 | consumed tokens: 3517972480 | elapsed time per iteration (s): 0.31 | learning rate: 1.619E-04 | global batch size: 256 | lm loss: 3.194411E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.557 | TFLOPs: 29.08 | +7: iteration 6720/ 21553 | consumed samples: 1720320 | consumed tokens: 3523215360 | elapsed time per iteration (s): 0.31 | learning rate: 1.618E-04 | global batch size: 256 | lm loss: 3.167722E+00 | grad norm: 0.392 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.165 | TFLOPs: 28.78 | +7: iteration 6730/ 21553 | consumed samples: 1722880 | consumed tokens: 3528458240 | elapsed time per iteration (s): 0.30 | learning rate: 1.617E-04 | global batch size: 256 | lm loss: 3.186503E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.985 | TFLOPs: 29.44 | +7: iteration 6740/ 21553 | consumed samples: 1725440 | consumed tokens: 3533701120 | elapsed time per iteration (s): 0.31 | learning rate: 1.616E-04 | global batch size: 256 | lm loss: 3.201159E+00 | grad norm: 0.408 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.461 | TFLOPs: 28.76 | +7: iteration 6750/ 21553 | consumed samples: 1728000 | consumed tokens: 3538944000 | elapsed time per iteration (s): 0.31 | learning rate: 1.615E-04 | global batch size: 256 | lm loss: 3.197671E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.584 | TFLOPs: 29.08 | +7: iteration 6760/ 21553 | consumed samples: 1730560 | consumed tokens: 3544186880 | elapsed time per iteration (s): 0.31 | learning rate: 1.614E-04 | global batch size: 256 | lm loss: 3.178498E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.578 | TFLOPs: 29.08 | +7: iteration 6770/ 21553 | consumed samples: 1733120 | consumed tokens: 3549429760 | elapsed time per iteration (s): 0.31 | learning rate: 1.612E-04 | global batch size: 256 | lm loss: 3.210697E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.135 | TFLOPs: 28.85 | +7: iteration 6780/ 21553 | consumed samples: 1735680 | consumed tokens: 3554672640 | elapsed time per iteration (s): 0.30 | learning rate: 1.611E-04 | global batch size: 256 | lm loss: 3.161439E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.909 | TFLOPs: 29.61 | +7: iteration 6790/ 21553 | consumed samples: 1738240 | consumed tokens: 3559915520 | elapsed time per iteration (s): 0.31 | learning rate: 1.610E-04 | global batch size: 256 | lm loss: 3.172440E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.003 | TFLOPs: 29.09 | +7: iteration 6800/ 21553 | consumed samples: 1740800 | consumed tokens: 3565158400 | elapsed time per iteration (s): 0.31 | learning rate: 1.609E-04 | global batch size: 256 | lm loss: 3.229109E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.651 | TFLOPs: 28.69 | +7: iteration 6810/ 21553 | consumed samples: 1743360 | consumed tokens: 3570401280 | elapsed time per iteration (s): 0.31 | learning rate: 1.608E-04 | global batch size: 256 | lm loss: 3.156362E+00 | grad norm: 0.385 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.270 | TFLOPs: 28.68 | +7: iteration 6820/ 21553 | consumed samples: 1745920 | consumed tokens: 3575644160 | elapsed time per iteration (s): 0.33 | learning rate: 1.607E-04 | global batch size: 256 | lm loss: 3.191393E+00 | grad norm: 0.394 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 782.787 | TFLOPs: 27.40 | +7: iteration 6830/ 21553 | consumed samples: 1748480 | consumed tokens: 3580887040 | elapsed time per iteration (s): 0.31 | learning rate: 1.606E-04 | global batch size: 256 | lm loss: 3.186072E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.263 | TFLOPs: 29.10 | +7: iteration 6840/ 21553 | consumed samples: 1751040 | consumed tokens: 3586129920 | elapsed time per iteration (s): 0.31 | learning rate: 1.605E-04 | global batch size: 256 | lm loss: 3.189287E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.654 | TFLOPs: 28.87 | +7: iteration 6850/ 21553 | consumed samples: 1753600 | consumed tokens: 3591372800 | elapsed time per iteration (s): 0.31 | learning rate: 1.604E-04 | global batch size: 256 | lm loss: 3.168889E+00 | grad norm: 0.410 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.982 | TFLOPs: 28.88 | +7: iteration 6860/ 21553 | consumed samples: 1756160 | consumed tokens: 3596615680 | elapsed time per iteration (s): 0.31 | learning rate: 1.603E-04 | global batch size: 256 | lm loss: 3.154451E+00 | grad norm: 0.408 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.982 | TFLOPs: 29.20 | +7: iteration 6870/ 21553 | consumed samples: 1758720 | consumed tokens: 3601858560 | elapsed time per iteration (s): 0.32 | learning rate: 1.601E-04 | global batch size: 256 | lm loss: 3.160772E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 805.702 | TFLOPs: 28.21 | +7: iteration 6880/ 21553 | consumed samples: 1761280 | consumed tokens: 3607101440 | elapsed time per iteration (s): 0.30 | learning rate: 1.600E-04 | global batch size: 256 | lm loss: 3.157340E+00 | grad norm: 0.368 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.375 | TFLOPs: 29.38 | +7: iteration 6890/ 21553 | consumed samples: 1763840 | consumed tokens: 3612344320 | elapsed time per iteration (s): 0.31 | learning rate: 1.599E-04 | global batch size: 256 | lm loss: 3.181865E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.050 | TFLOPs: 29.16 | +7: iteration 6900/ 21553 | consumed samples: 1766400 | consumed tokens: 3617587200 | elapsed time per iteration (s): 0.31 | learning rate: 1.598E-04 | global batch size: 256 | lm loss: 3.182917E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.212 | TFLOPs: 28.75 | +7: iteration 6910/ 21553 | consumed samples: 1768960 | consumed tokens: 3622830080 | elapsed time per iteration (s): 0.31 | learning rate: 1.597E-04 | global batch size: 256 | lm loss: 3.168088E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.275 | TFLOPs: 29.38 | +7: iteration 6920/ 21553 | consumed samples: 1771520 | consumed tokens: 3628072960 | elapsed time per iteration (s): 0.32 | learning rate: 1.596E-04 | global batch size: 256 | lm loss: 3.180331E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 791.699 | TFLOPs: 27.72 | +7: iteration 6930/ 21553 | consumed samples: 1774080 | consumed tokens: 3633315840 | elapsed time per iteration (s): 0.31 | learning rate: 1.595E-04 | global batch size: 256 | lm loss: 3.167239E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.189 | TFLOPs: 29.13 | +7: iteration 6940/ 21553 | consumed samples: 1776640 | consumed tokens: 3638558720 | elapsed time per iteration (s): 0.31 | learning rate: 1.594E-04 | global batch size: 256 | lm loss: 3.161762E+00 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.238 | TFLOPs: 29.24 | +7: iteration 6950/ 21553 | consumed samples: 1779200 | consumed tokens: 3643801600 | elapsed time per iteration (s): 0.31 | learning rate: 1.593E-04 | global batch size: 256 | lm loss: 3.180990E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.013 | TFLOPs: 29.13 | +7: iteration 6960/ 21553 | consumed samples: 1781760 | consumed tokens: 3649044480 | elapsed time per iteration (s): 0.31 | learning rate: 1.592E-04 | global batch size: 256 | lm loss: 3.151314E+00 | grad norm: 0.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.060 | TFLOPs: 29.06 | +7: iteration 6970/ 21553 | consumed samples: 1784320 | consumed tokens: 3654287360 | elapsed time per iteration (s): 0.35 | learning rate: 1.590E-04 | global batch size: 256 | lm loss: 3.167228E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 736.083 | TFLOPs: 25.77 | +7: iteration 6980/ 21553 | consumed samples: 1786880 | consumed tokens: 3659530240 | elapsed time per iteration (s): 0.30 | learning rate: 1.589E-04 | global batch size: 256 | lm loss: 3.132767E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.005 | TFLOPs: 29.48 | +7: iteration 6990/ 21553 | consumed samples: 1789440 | consumed tokens: 3664773120 | elapsed time per iteration (s): 0.32 | learning rate: 1.588E-04 | global batch size: 256 | lm loss: 3.155882E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.375 | TFLOPs: 28.40 | +7: iteration 7000/ 21553 | consumed samples: 1792000 | consumed tokens: 3670016000 | elapsed time per iteration (s): 0.31 | learning rate: 1.587E-04 | global batch size: 256 | lm loss: 3.176341E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.057 | TFLOPs: 28.95 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 7000 | lm loss value: 3.051772E+00 | lm loss PPL: 2.115279E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 7000 to checkpoints_146moscareap +0: [2022-11-29 17:43:45,436] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step7000 is begin to save! +0: [2022-11-29 17:43:45,440] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:43:45,525] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:43:45,525] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:43:45,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:43:45,541] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:43:45,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:43:45,556] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:43:45,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:43:45,571] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:43:45,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:43:45,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:43:45,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:43:45,602] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:43:45,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:43:45,617] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:43:45,632] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:43:45,632] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:43:45,647] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:43:45,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:43:45,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:43:45,663] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:43:45,678] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:43:45,678] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:43:45,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:43:45,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:43:45,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:43:45,709] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:43:45,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:43:45,724] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:43:45,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:43:45,740] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:43:45,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:43:45,755] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:43:45,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:43:45,757] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_146moscareap/global_step7000/mp_rank_00_model_states.pt +0: [2022-11-29 17:43:45,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:43:45,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:43:45,777] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:43:45,777] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:43:45,777] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:43:45,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:43:45,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:43:45,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:43:45,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 17:43:45,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:43:45,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:43:45,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 17:43:45,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:43:45,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:43:45,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 17:43:45,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:43:45,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:43:45,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:43:45,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:43:45,812] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +4: [2022-11-29 17:43:45,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:43:45,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:43:45,812] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:43:45,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:43:45,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:43:45,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:43:45,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:43:45,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:43:45,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:43:45,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:43:45,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:43:45,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:43:45,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:43:45,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:43:45,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +1: [2022-11-29 17:43:45,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:43:45,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 17:43:45,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:43:45,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 17:43:45,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:43:45,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:43:45,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 17:43:45,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:43:45,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:43:45,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 17:43:45,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:43:45,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:43:45,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:43:45,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:43:45,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:43:45,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:43:45,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:43:45,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:43:45,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:43:45,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:43:45,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:43:45,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:43:45,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:43:45,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:43:45,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:43:45,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +2: [2022-11-29 17:43:45,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +0: [2022-11-29 17:43:45,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:43:45,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 17:43:45,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:43:45,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:43:45,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +2: [2022-11-29 17:43:45,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +1: [2022-11-29 17:43:45,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:43:45,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:43:45,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:43:45,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:43:45,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 17:43:45,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:43:45,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:43:45,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:43:45,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:43:45,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:43:45,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:43:45,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:43:45,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:43:45,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:43:45,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:43:45,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:43:45,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:43:45,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +3: [2022-11-29 17:43:45,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:43:45,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +3: [2022-11-29 17:43:45,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +2: [2022-11-29 17:43:45,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:43:45,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +7: [2022-11-29 17:43:45,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:43:45,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:43:45,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:43:45,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:43:45,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +1: [2022-11-29 17:43:45,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:43:45,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 17:43:45,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:43:45,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:43:45,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:43:45,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +1: [2022-11-29 17:43:45,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:43:45,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 17:43:45,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 17:43:45,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 17:43:45,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:43:45,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:43:45,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 17:43:45,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:43:45,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:43:45,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:43:45,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +5: [2022-11-29 17:43:45,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:43:45,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 17:43:45,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:43:45,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:43:45,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 17:43:45,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:43:45,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:43:45,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:43:45,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:43:45,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:43:45,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:43:45,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:43:45,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:43:45,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +0: [2022-11-29 17:43:45,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:43:45,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +2: [2022-11-29 17:43:45,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:43:45,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3: [2022-11-29 17:43:45,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:43:45,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:43:45,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:43:45,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:43:45,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:43:45,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:43:45,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:43:45,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:43:45,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:43:45,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:43:45,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:43:45,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:43:45,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:43:45,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 17:43:45,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:43:45,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:43:45,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:43:45,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:43:45,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +7: [2022-11-29 17:43:45,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:43:45,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 17:43:45,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:43:45,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 17:43:45,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:43:45,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:43:45,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:43:45,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:43:45,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:43:45,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:43:45,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:43:45,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:43:45,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +5: [2022-11-29 17:43:45,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +2: [2022-11-29 17:43:45,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:43:45,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:43:45,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:43:45,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:43:45,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 17:43:45,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:43:45,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:43:45,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:43:45,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:43:45,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:43:45,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:43:45,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:43:45,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:43:45,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:43:45,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:43:45,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:43:45,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +4: [2022-11-29 17:43:45,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:43:45,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +5: [2022-11-29 17:43:45,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:43:45,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:43:45,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:43:45,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 17:43:45,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:43:45,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:43:45,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 17:43:45,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:43:45,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:43:45,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:43:45,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:43:45,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:43:45,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:43:45,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step7000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:43:45,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: successfully saved checkpoint at iteration 7000 to checkpoints_146moscareap +7: time (ms) | save-checkpoint: 404.20 +7: iteration 7010/ 21553 | consumed samples: 1794560 | consumed tokens: 3675258880 | elapsed time per iteration (s): 0.36 | learning rate: 1.586E-04 | global batch size: 256 | lm loss: 3.188311E+00 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 710.141 | TFLOPs: 24.86 | +7: iteration 7020/ 21553 | consumed samples: 1797120 | consumed tokens: 3680501760 | elapsed time per iteration (s): 0.31 | learning rate: 1.585E-04 | global batch size: 256 | lm loss: 3.168806E+00 | grad norm: 0.404 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.924 | TFLOPs: 28.77 | +7: iteration 7030/ 21553 | consumed samples: 1799680 | consumed tokens: 3685744640 | elapsed time per iteration (s): 0.30 | learning rate: 1.584E-04 | global batch size: 256 | lm loss: 3.171183E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.328 | TFLOPs: 29.52 | +7: iteration 7040/ 21553 | consumed samples: 1802240 | consumed tokens: 3690987520 | elapsed time per iteration (s): 0.31 | learning rate: 1.583E-04 | global batch size: 256 | lm loss: 3.174364E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.010 | TFLOPs: 28.46 | +7: iteration 7050/ 21553 | consumed samples: 1804800 | consumed tokens: 3696230400 | elapsed time per iteration (s): 0.30 | learning rate: 1.582E-04 | global batch size: 256 | lm loss: 3.182611E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.895 | TFLOPs: 29.61 | +7: iteration 7060/ 21553 | consumed samples: 1807360 | consumed tokens: 3701473280 | elapsed time per iteration (s): 0.31 | learning rate: 1.580E-04 | global batch size: 256 | lm loss: 3.187651E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.107 | TFLOPs: 28.64 | +7: iteration 7070/ 21553 | consumed samples: 1809920 | consumed tokens: 3706716160 | elapsed time per iteration (s): 0.31 | learning rate: 1.579E-04 | global batch size: 256 | lm loss: 3.149041E+00 | grad norm: 0.382 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.985 | TFLOPs: 28.60 | +7: iteration 7080/ 21553 | consumed samples: 1812480 | consumed tokens: 3711959040 | elapsed time per iteration (s): 0.31 | learning rate: 1.578E-04 | global batch size: 256 | lm loss: 3.167566E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.007 | TFLOPs: 29.02 | +7: iteration 7090/ 21553 | consumed samples: 1815040 | consumed tokens: 3717201920 | elapsed time per iteration (s): 0.31 | learning rate: 1.577E-04 | global batch size: 256 | lm loss: 3.166979E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.724 | TFLOPs: 28.77 | +7: iteration 7100/ 21553 | consumed samples: 1817600 | consumed tokens: 3722444800 | elapsed time per iteration (s): 0.31 | learning rate: 1.576E-04 | global batch size: 256 | lm loss: 3.166293E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.415 | TFLOPs: 28.48 | +7: iteration 7110/ 21553 | consumed samples: 1820160 | consumed tokens: 3727687680 | elapsed time per iteration (s): 0.31 | learning rate: 1.575E-04 | global batch size: 256 | lm loss: 3.182422E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.498 | TFLOPs: 28.86 | +7: iteration 7120/ 21553 | consumed samples: 1822720 | consumed tokens: 3732930560 | elapsed time per iteration (s): 0.32 | learning rate: 1.574E-04 | global batch size: 256 | lm loss: 3.186903E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 805.495 | TFLOPs: 28.20 | +7: iteration 7130/ 21553 | consumed samples: 1825280 | consumed tokens: 3738173440 | elapsed time per iteration (s): 0.31 | learning rate: 1.573E-04 | global batch size: 256 | lm loss: 3.187368E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.107 | TFLOPs: 28.57 | +7: iteration 7140/ 21553 | consumed samples: 1827840 | consumed tokens: 3743416320 | elapsed time per iteration (s): 0.31 | learning rate: 1.571E-04 | global batch size: 256 | lm loss: 3.170611E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.526 | TFLOPs: 29.21 | +7: iteration 7150/ 21553 | consumed samples: 1830400 | consumed tokens: 3748659200 | elapsed time per iteration (s): 0.33 | learning rate: 1.570E-04 | global batch size: 256 | lm loss: 3.177435E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 786.806 | TFLOPs: 27.54 | +7: iteration 7160/ 21553 | consumed samples: 1832960 | consumed tokens: 3753902080 | elapsed time per iteration (s): 0.31 | learning rate: 1.569E-04 | global batch size: 256 | lm loss: 3.161201E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.820 | TFLOPs: 29.19 | +7: iteration 7170/ 21553 | consumed samples: 1835520 | consumed tokens: 3759144960 | elapsed time per iteration (s): 0.31 | learning rate: 1.568E-04 | global batch size: 256 | lm loss: 3.151774E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.051 | TFLOPs: 29.27 | +7: iteration 7180/ 21553 | consumed samples: 1838080 | consumed tokens: 3764387840 | elapsed time per iteration (s): 0.30 | learning rate: 1.567E-04 | global batch size: 256 | lm loss: 3.158833E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.780 | TFLOPs: 29.43 | +7: iteration 7190/ 21553 | consumed samples: 1840640 | consumed tokens: 3769630720 | elapsed time per iteration (s): 0.31 | learning rate: 1.566E-04 | global batch size: 256 | lm loss: 3.190619E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.481 | TFLOPs: 29.25 | +7: iteration 7200/ 21553 | consumed samples: 1843200 | consumed tokens: 3774873600 | elapsed time per iteration (s): 0.30 | learning rate: 1.565E-04 | global batch size: 256 | lm loss: 3.124962E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 849.125 | TFLOPs: 29.73 | +7: iteration 7210/ 21553 | consumed samples: 1845760 | consumed tokens: 3780116480 | elapsed time per iteration (s): 0.31 | learning rate: 1.563E-04 | global batch size: 256 | lm loss: 3.189367E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.012 | TFLOPs: 29.23 | +7: iteration 7220/ 21553 | consumed samples: 1848320 | consumed tokens: 3785359360 | elapsed time per iteration (s): 0.31 | learning rate: 1.562E-04 | global batch size: 256 | lm loss: 3.166458E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.547 | TFLOPs: 29.22 | +7: iteration 7230/ 21553 | consumed samples: 1850880 | consumed tokens: 3790602240 | elapsed time per iteration (s): 0.31 | learning rate: 1.561E-04 | global batch size: 256 | lm loss: 3.160620E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.194 | TFLOPs: 29.31 | +7: iteration 7240/ 21553 | consumed samples: 1853440 | consumed tokens: 3795845120 | elapsed time per iteration (s): 0.31 | learning rate: 1.560E-04 | global batch size: 256 | lm loss: 3.144706E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.243 | TFLOPs: 29.27 | +7: iteration 7250/ 21553 | consumed samples: 1856000 | consumed tokens: 3801088000 | elapsed time per iteration (s): 0.31 | learning rate: 1.559E-04 | global batch size: 256 | lm loss: 3.174486E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.367 | TFLOPs: 28.65 | +7: iteration 7260/ 21553 | consumed samples: 1858560 | consumed tokens: 3806330880 | elapsed time per iteration (s): 0.31 | learning rate: 1.558E-04 | global batch size: 256 | lm loss: 3.156017E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.804 | TFLOPs: 28.98 | +7: iteration 7270/ 21553 | consumed samples: 1861120 | consumed tokens: 3811573760 | elapsed time per iteration (s): 0.32 | learning rate: 1.557E-04 | global batch size: 256 | lm loss: 3.177636E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.774 | TFLOPs: 28.38 | +7: iteration 7280/ 21553 | consumed samples: 1863680 | consumed tokens: 3816816640 | elapsed time per iteration (s): 0.31 | learning rate: 1.556E-04 | global batch size: 256 | lm loss: 3.140787E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.716 | TFLOPs: 29.05 | +7: iteration 7290/ 21553 | consumed samples: 1866240 | consumed tokens: 3822059520 | elapsed time per iteration (s): 0.31 | learning rate: 1.554E-04 | global batch size: 256 | lm loss: 3.157414E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.537 | TFLOPs: 28.51 | +7: iteration 7300/ 21553 | consumed samples: 1868800 | consumed tokens: 3827302400 | elapsed time per iteration (s): 0.34 | learning rate: 1.553E-04 | global batch size: 256 | lm loss: 3.175326E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 756.777 | TFLOPs: 26.49 | +7: iteration 7310/ 21553 | consumed samples: 1871360 | consumed tokens: 3832545280 | elapsed time per iteration (s): 0.31 | learning rate: 1.552E-04 | global batch size: 256 | lm loss: 3.162579E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.398 | TFLOPs: 28.68 | +7: iteration 7320/ 21553 | consumed samples: 1873920 | consumed tokens: 3837788160 | elapsed time per iteration (s): 0.30 | learning rate: 1.551E-04 | global batch size: 256 | lm loss: 3.165679E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.726 | TFLOPs: 29.54 | +7: iteration 7330/ 21553 | consumed samples: 1876480 | consumed tokens: 3843031040 | elapsed time per iteration (s): 0.31 | learning rate: 1.550E-04 | global batch size: 256 | lm loss: 3.146925E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.164 | TFLOPs: 29.38 | +7: iteration 7340/ 21553 | consumed samples: 1879040 | consumed tokens: 3848273920 | elapsed time per iteration (s): 0.31 | learning rate: 1.549E-04 | global batch size: 256 | lm loss: 3.140743E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.494 | TFLOPs: 29.35 | +7: iteration 7350/ 21553 | consumed samples: 1881600 | consumed tokens: 3853516800 | elapsed time per iteration (s): 0.31 | learning rate: 1.547E-04 | global batch size: 256 | lm loss: 3.187377E+00 | grad norm: 0.389 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.517 | TFLOPs: 28.65 | +7: iteration 7360/ 21553 | consumed samples: 1884160 | consumed tokens: 3858759680 | elapsed time per iteration (s): 0.31 | learning rate: 1.546E-04 | global batch size: 256 | lm loss: 3.179068E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.641 | TFLOPs: 28.80 | +7: iteration 7370/ 21553 | consumed samples: 1886720 | consumed tokens: 3864002560 | elapsed time per iteration (s): 0.31 | learning rate: 1.545E-04 | global batch size: 256 | lm loss: 3.147676E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.100 | TFLOPs: 29.02 | +7: iteration 7380/ 21553 | consumed samples: 1889280 | consumed tokens: 3869245440 | elapsed time per iteration (s): 0.31 | learning rate: 1.544E-04 | global batch size: 256 | lm loss: 3.150652E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.231 | TFLOPs: 29.10 | +7: iteration 7390/ 21553 | consumed samples: 1891840 | consumed tokens: 3874488320 | elapsed time per iteration (s): 0.31 | learning rate: 1.543E-04 | global batch size: 256 | lm loss: 3.135802E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.968 | TFLOPs: 29.09 | +7: iteration 7400/ 21553 | consumed samples: 1894400 | consumed tokens: 3879731200 | elapsed time per iteration (s): 0.32 | learning rate: 1.542E-04 | global batch size: 256 | lm loss: 3.150561E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 801.870 | TFLOPs: 28.07 | +7: iteration 7410/ 21553 | consumed samples: 1896960 | consumed tokens: 3884974080 | elapsed time per iteration (s): 0.31 | learning rate: 1.541E-04 | global batch size: 256 | lm loss: 3.140905E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.389 | TFLOPs: 28.79 | +7: iteration 7420/ 21553 | consumed samples: 1899520 | consumed tokens: 3890216960 | elapsed time per iteration (s): 0.31 | learning rate: 1.539E-04 | global batch size: 256 | lm loss: 3.151252E+00 | grad norm: 0.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.976 | TFLOPs: 28.74 | +7: iteration 7430/ 21553 | consumed samples: 1902080 | consumed tokens: 3895459840 | elapsed time per iteration (s): 0.31 | learning rate: 1.538E-04 | global batch size: 256 | lm loss: 3.155315E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.999 | TFLOPs: 29.09 | +7: iteration 7440/ 21553 | consumed samples: 1904640 | consumed tokens: 3900702720 | elapsed time per iteration (s): 0.31 | learning rate: 1.537E-04 | global batch size: 256 | lm loss: 3.149332E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.361 | TFLOPs: 28.82 | +7: iteration 7450/ 21553 | consumed samples: 1907200 | consumed tokens: 3905945600 | elapsed time per iteration (s): 0.31 | learning rate: 1.536E-04 | global batch size: 256 | lm loss: 3.162667E+00 | grad norm: 0.381 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.688 | TFLOPs: 29.22 | +7: iteration 7460/ 21553 | consumed samples: 1909760 | consumed tokens: 3911188480 | elapsed time per iteration (s): 0.32 | learning rate: 1.535E-04 | global batch size: 256 | lm loss: 3.170882E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 806.042 | TFLOPs: 28.22 | +7: iteration 7470/ 21553 | consumed samples: 1912320 | consumed tokens: 3916431360 | elapsed time per iteration (s): 0.31 | learning rate: 1.534E-04 | global batch size: 256 | lm loss: 3.151485E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.908 | TFLOPs: 28.60 | +7: iteration 7480/ 21553 | consumed samples: 1914880 | consumed tokens: 3921674240 | elapsed time per iteration (s): 0.31 | learning rate: 1.532E-04 | global batch size: 256 | lm loss: 3.127619E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.624 | TFLOPs: 28.76 | +7: iteration 7490/ 21553 | consumed samples: 1917440 | consumed tokens: 3926917120 | elapsed time per iteration (s): 0.31 | learning rate: 1.531E-04 | global batch size: 256 | lm loss: 3.147352E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.556 | TFLOPs: 29.36 | +7: iteration 7500/ 21553 | consumed samples: 1920000 | consumed tokens: 3932160000 | elapsed time per iteration (s): 0.31 | learning rate: 1.530E-04 | global batch size: 256 | lm loss: 3.159616E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.282 | TFLOPs: 29.07 | +7: iteration 7510/ 21553 | consumed samples: 1922560 | consumed tokens: 3937402880 | elapsed time per iteration (s): 0.31 | learning rate: 1.529E-04 | global batch size: 256 | lm loss: 3.145299E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.766 | TFLOPs: 28.98 | +7: iteration 7520/ 21553 | consumed samples: 1925120 | consumed tokens: 3942645760 | elapsed time per iteration (s): 0.31 | learning rate: 1.528E-04 | global batch size: 256 | lm loss: 3.158397E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.780 | TFLOPs: 29.08 | +7: iteration 7530/ 21553 | consumed samples: 1927680 | consumed tokens: 3947888640 | elapsed time per iteration (s): 0.31 | learning rate: 1.527E-04 | global batch size: 256 | lm loss: 3.150525E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.966 | TFLOPs: 28.56 | +7: iteration 7540/ 21553 | consumed samples: 1930240 | consumed tokens: 3953131520 | elapsed time per iteration (s): 0.31 | learning rate: 1.525E-04 | global batch size: 256 | lm loss: 3.163517E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.807 | TFLOPs: 28.70 | +7: iteration 7550/ 21553 | consumed samples: 1932800 | consumed tokens: 3958374400 | elapsed time per iteration (s): 0.32 | learning rate: 1.524E-04 | global batch size: 256 | lm loss: 3.150807E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 806.986 | TFLOPs: 28.25 | +7: iteration 7560/ 21553 | consumed samples: 1935360 | consumed tokens: 3963617280 | elapsed time per iteration (s): 0.32 | learning rate: 1.523E-04 | global batch size: 256 | lm loss: 3.140240E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 809.824 | TFLOPs: 28.35 | +7: iteration 7570/ 21553 | consumed samples: 1937920 | consumed tokens: 3968860160 | elapsed time per iteration (s): 0.31 | learning rate: 1.522E-04 | global batch size: 256 | lm loss: 3.157894E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.952 | TFLOPs: 28.70 | +7: iteration 7580/ 21553 | consumed samples: 1940480 | consumed tokens: 3974103040 | elapsed time per iteration (s): 0.33 | learning rate: 1.521E-04 | global batch size: 256 | lm loss: 3.149475E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 780.651 | TFLOPs: 27.33 | +7: iteration 7590/ 21553 | consumed samples: 1943040 | consumed tokens: 3979345920 | elapsed time per iteration (s): 0.31 | learning rate: 1.520E-04 | global batch size: 256 | lm loss: 3.134678E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.692 | TFLOPs: 29.36 | +7: iteration 7600/ 21553 | consumed samples: 1945600 | consumed tokens: 3984588800 | elapsed time per iteration (s): 0.31 | learning rate: 1.518E-04 | global batch size: 256 | lm loss: 3.124085E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.671 | TFLOPs: 28.69 | +7: iteration 7610/ 21553 | consumed samples: 1948160 | consumed tokens: 3989831680 | elapsed time per iteration (s): 0.31 | learning rate: 1.517E-04 | global batch size: 256 | lm loss: 3.159790E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.152 | TFLOPs: 29.34 | +7: iteration 7620/ 21553 | consumed samples: 1950720 | consumed tokens: 3995074560 | elapsed time per iteration (s): 0.31 | learning rate: 1.516E-04 | global batch size: 256 | lm loss: 3.142489E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.822 | TFLOPs: 28.87 | +7: iteration 7630/ 21553 | consumed samples: 1953280 | consumed tokens: 4000317440 | elapsed time per iteration (s): 0.30 | learning rate: 1.515E-04 | global batch size: 256 | lm loss: 3.152339E+00 | grad norm: 0.389 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.517 | TFLOPs: 29.39 | +7: iteration 7640/ 21553 | consumed samples: 1955840 | consumed tokens: 4005560320 | elapsed time per iteration (s): 0.30 | learning rate: 1.514E-04 | global batch size: 256 | lm loss: 3.150948E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.167 | TFLOPs: 29.41 | +7: iteration 7650/ 21553 | consumed samples: 1958400 | consumed tokens: 4010803200 | elapsed time per iteration (s): 0.30 | learning rate: 1.513E-04 | global batch size: 256 | lm loss: 3.161541E+00 | grad norm: 0.392 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 848.510 | TFLOPs: 29.70 | +7: iteration 7660/ 21553 | consumed samples: 1960960 | consumed tokens: 4016046080 | elapsed time per iteration (s): 0.31 | learning rate: 1.511E-04 | global batch size: 256 | lm loss: 3.173002E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.933 | TFLOPs: 29.05 | +7: iteration 7670/ 21553 | consumed samples: 1963520 | consumed tokens: 4021288960 | elapsed time per iteration (s): 0.31 | learning rate: 1.510E-04 | global batch size: 256 | lm loss: 3.166290E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.597 | TFLOPs: 28.83 | +7: iteration 7680/ 21553 | consumed samples: 1966080 | consumed tokens: 4026531840 | elapsed time per iteration (s): 0.31 | learning rate: 1.509E-04 | global batch size: 256 | lm loss: 3.131977E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.968 | TFLOPs: 28.67 | +7: iteration 7690/ 21553 | consumed samples: 1968640 | consumed tokens: 4031774720 | elapsed time per iteration (s): 0.31 | learning rate: 1.508E-04 | global batch size: 256 | lm loss: 3.114573E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.667 | TFLOPs: 29.29 | +7: iteration 7700/ 21553 | consumed samples: 1971200 | consumed tokens: 4037017600 | elapsed time per iteration (s): 0.31 | learning rate: 1.507E-04 | global batch size: 256 | lm loss: 3.140980E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.172 | TFLOPs: 28.89 | +7: iteration 7710/ 21553 | consumed samples: 1973760 | consumed tokens: 4042260480 | elapsed time per iteration (s): 0.31 | learning rate: 1.505E-04 | global batch size: 256 | lm loss: 3.137375E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.929 | TFLOPs: 29.26 | +7: iteration 7720/ 21553 | consumed samples: 1976320 | consumed tokens: 4047503360 | elapsed time per iteration (s): 0.31 | learning rate: 1.504E-04 | global batch size: 256 | lm loss: 3.134260E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.731 | TFLOPs: 29.36 | +7: iteration 7730/ 21553 | consumed samples: 1978880 | consumed tokens: 4052746240 | elapsed time per iteration (s): 0.31 | learning rate: 1.503E-04 | global batch size: 256 | lm loss: 3.146969E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.579 | TFLOPs: 29.36 | +7: iteration 7740/ 21553 | consumed samples: 1981440 | consumed tokens: 4057989120 | elapsed time per iteration (s): 0.31 | learning rate: 1.502E-04 | global batch size: 256 | lm loss: 3.149729E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.068 | TFLOPs: 29.27 | +7: iteration 7750/ 21553 | consumed samples: 1984000 | consumed tokens: 4063232000 | elapsed time per iteration (s): 0.31 | learning rate: 1.501E-04 | global batch size: 256 | lm loss: 3.138326E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.030 | TFLOPs: 28.50 | +7: iteration 7760/ 21553 | consumed samples: 1986560 | consumed tokens: 4068474880 | elapsed time per iteration (s): 0.30 | learning rate: 1.500E-04 | global batch size: 256 | lm loss: 3.134874E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 844.079 | TFLOPs: 29.55 | +7: iteration 7770/ 21553 | consumed samples: 1989120 | consumed tokens: 4073717760 | elapsed time per iteration (s): 0.30 | learning rate: 1.498E-04 | global batch size: 256 | lm loss: 3.108706E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.188 | TFLOPs: 29.52 | +7: iteration 7780/ 21553 | consumed samples: 1991680 | consumed tokens: 4078960640 | elapsed time per iteration (s): 0.30 | learning rate: 1.497E-04 | global batch size: 256 | lm loss: 3.127377E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.384 | TFLOPs: 29.42 | +7: iteration 7790/ 21553 | consumed samples: 1994240 | consumed tokens: 4084203520 | elapsed time per iteration (s): 0.32 | learning rate: 1.496E-04 | global batch size: 256 | lm loss: 3.129895E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 806.612 | TFLOPs: 28.24 | +7: iteration 7800/ 21553 | consumed samples: 1996800 | consumed tokens: 4089446400 | elapsed time per iteration (s): 0.32 | learning rate: 1.495E-04 | global batch size: 256 | lm loss: 3.148550E+00 | grad norm: 0.383 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 801.234 | TFLOPs: 28.05 | +7: iteration 7810/ 21553 | consumed samples: 1999360 | consumed tokens: 4094689280 | elapsed time per iteration (s): 0.31 | learning rate: 1.494E-04 | global batch size: 256 | lm loss: 3.104363E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.390 | TFLOPs: 28.58 | +7: iteration 7820/ 21553 | consumed samples: 2001920 | consumed tokens: 4099932160 | elapsed time per iteration (s): 0.31 | learning rate: 1.492E-04 | global batch size: 256 | lm loss: 3.152183E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.277 | TFLOPs: 29.00 | +7: iteration 7830/ 21553 | consumed samples: 2004480 | consumed tokens: 4105175040 | elapsed time per iteration (s): 0.31 | learning rate: 1.491E-04 | global batch size: 256 | lm loss: 3.134128E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.868 | TFLOPs: 28.91 | +7: iteration 7840/ 21553 | consumed samples: 2007040 | consumed tokens: 4110417920 | elapsed time per iteration (s): 0.31 | learning rate: 1.490E-04 | global batch size: 256 | lm loss: 3.139632E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.235 | TFLOPs: 29.27 | +7: iteration 7850/ 21553 | consumed samples: 2009600 | consumed tokens: 4115660800 | elapsed time per iteration (s): 0.30 | learning rate: 1.489E-04 | global batch size: 256 | lm loss: 3.159732E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.175 | TFLOPs: 29.41 | +7: iteration 7860/ 21553 | consumed samples: 2012160 | consumed tokens: 4120903680 | elapsed time per iteration (s): 0.31 | learning rate: 1.488E-04 | global batch size: 256 | lm loss: 3.140382E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.859 | TFLOPs: 28.88 | +7: iteration 7870/ 21553 | consumed samples: 2014720 | consumed tokens: 4126146560 | elapsed time per iteration (s): 0.31 | learning rate: 1.486E-04 | global batch size: 256 | lm loss: 3.104691E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.493 | TFLOPs: 29.18 | +7: iteration 7880/ 21553 | consumed samples: 2017280 | consumed tokens: 4131389440 | elapsed time per iteration (s): 0.31 | learning rate: 1.485E-04 | global batch size: 256 | lm loss: 3.139060E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.880 | TFLOPs: 29.09 | +7: iteration 7890/ 21553 | consumed samples: 2019840 | consumed tokens: 4136632320 | elapsed time per iteration (s): 0.31 | learning rate: 1.484E-04 | global batch size: 256 | lm loss: 3.149094E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.928 | TFLOPs: 28.67 | +7: iteration 7900/ 21553 | consumed samples: 2022400 | consumed tokens: 4141875200 | elapsed time per iteration (s): 0.36 | learning rate: 1.483E-04 | global batch size: 256 | lm loss: 3.106247E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 706.278 | TFLOPs: 24.72 | +7: iteration 7910/ 21553 | consumed samples: 2024960 | consumed tokens: 4147118080 | elapsed time per iteration (s): 0.34 | learning rate: 1.482E-04 | global batch size: 256 | lm loss: 3.165691E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 753.420 | TFLOPs: 26.38 | +7: iteration 7920/ 21553 | consumed samples: 2027520 | consumed tokens: 4152360960 | elapsed time per iteration (s): 0.30 | learning rate: 1.480E-04 | global batch size: 256 | lm loss: 3.103595E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 846.017 | TFLOPs: 29.62 | +7: iteration 7930/ 21553 | consumed samples: 2030080 | consumed tokens: 4157603840 | elapsed time per iteration (s): 0.31 | learning rate: 1.479E-04 | global batch size: 256 | lm loss: 3.124010E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.496 | TFLOPs: 29.07 | +7: iteration 7940/ 21553 | consumed samples: 2032640 | consumed tokens: 4162846720 | elapsed time per iteration (s): 0.31 | learning rate: 1.478E-04 | global batch size: 256 | lm loss: 3.130261E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.655 | TFLOPs: 29.18 | +7: iteration 7950/ 21553 | consumed samples: 2035200 | consumed tokens: 4168089600 | elapsed time per iteration (s): 0.31 | learning rate: 1.477E-04 | global batch size: 256 | lm loss: 3.138552E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.035 | TFLOPs: 28.88 | +7: iteration 7960/ 21553 | consumed samples: 2037760 | consumed tokens: 4173332480 | elapsed time per iteration (s): 0.31 | learning rate: 1.476E-04 | global batch size: 256 | lm loss: 3.137848E+00 | grad norm: 0.367 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.909 | TFLOPs: 29.02 | +7: iteration 7970/ 21553 | consumed samples: 2040320 | consumed tokens: 4178575360 | elapsed time per iteration (s): 0.31 | learning rate: 1.474E-04 | global batch size: 256 | lm loss: 3.147103E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.811 | TFLOPs: 29.26 | +7: iteration 7980/ 21553 | consumed samples: 2042880 | consumed tokens: 4183818240 | elapsed time per iteration (s): 0.31 | learning rate: 1.473E-04 | global batch size: 256 | lm loss: 3.128250E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.117 | TFLOPs: 29.06 | +7: iteration 7990/ 21553 | consumed samples: 2045440 | consumed tokens: 4189061120 | elapsed time per iteration (s): 0.31 | learning rate: 1.472E-04 | global batch size: 256 | lm loss: 3.139806E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.701 | TFLOPs: 29.12 | +0: [2022-11-29 17:48:56,571] [INFO] [logging.py:68:log_dist] [Rank 0] step=8000, skipped=0, lr=[0.00014708123251590496, 0.00014708123251590496, 0.00014708123251590496], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +0: steps: 8000 loss: 3.1268 iter time (s): 0.308 samples/sec: 830.540 +7: iteration 8000/ 21553 | consumed samples: 2048000 | consumed tokens: 4194304000 | elapsed time per iteration (s): 0.31 | learning rate: 1.471E-04 | global batch size: 256 | lm loss: 3.110561E+00 | grad norm: 0.377 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.430 | TFLOPs: 29.00 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 8000 | lm loss value: 3.152908E+00 | lm loss PPL: 2.340403E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 8000 to checkpoints_146moscareap +0: [2022-11-29 17:48:56,695] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step8000 is begin to save! +0: [2022-11-29 17:48:56,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:48:56,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:48:56,784] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:48:56,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:48:56,801] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:48:56,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:48:56,816] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:48:56,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:48:56,832] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:48:56,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:48:56,848] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:48:56,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:48:56,864] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:48:56,879] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:48:56,879] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:48:56,895] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:48:56,895] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:48:56,910] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:48:56,911] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:48:56,927] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:48:56,927] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:48:56,942] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:48:56,943] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:48:56,958] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:48:56,958] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:48:56,974] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:48:56,974] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:48:56,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:48:56,990] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:48:57,006] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:48:57,006] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:48:57,022] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:48:57,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:48:57,023] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:48:57,024] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_146moscareap/global_step8000/mp_rank_00_model_states.pt +0: [2022-11-29 17:48:57,024] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:48:57,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:48:57,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:48:57,078] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:48:57,078] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:48:57,078] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:48:57,078] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:48:57,079] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:48:57,079] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 17:48:57,079] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:48:57,079] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:48:57,079] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:48:57,080] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:48:57,080] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:48:57,080] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:48:57,080] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:48:57,080] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:48:57,080] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:48:57,080] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:48:57,080] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:48:57,080] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:48:57,080] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:48:57,080] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:48:57,080] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:48:57,080] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:48:57,080] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:48:57,080] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 17:48:57,081] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:48:57,081] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:48:57,081] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:48:57,082] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:48:57,082] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:48:57,082] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:48:57,082] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:48:57,082] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:48:57,082] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 17:48:57,082] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:48:57,082] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:48:57,083] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:48:57,083] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:48:57,083] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:48:57,083] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:48:57,083] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 17:48:57,083] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:48:57,083] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:48:57,083] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:48:57,084] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:48:57,084] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:48:57,084] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:48:57,084] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:48:57,084] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:48:57,084] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:48:57,084] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:48:57,084] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:48:57,084] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:48:57,084] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:48:57,084] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:48:57,084] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:48:57,084] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:48:57,084] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:48:57,084] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:48:57,084] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +6: [2022-11-29 17:48:57,084] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:48:57,084] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:48:57,084] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:48:57,084] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:48:57,084] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:48:57,084] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:48:57,084] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:48:57,084] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:48:57,084] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:48:57,084] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:48:57,084] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +7: [2022-11-29 17:48:57,084] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +1: [2022-11-29 17:48:57,085] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 17:48:57,085] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 17:48:57,085] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:48:57,085] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:48:57,085] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:48:57,085] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:48:57,085] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 17:48:57,085] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +4: [2022-11-29 17:48:57,085] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +6: [2022-11-29 17:48:57,085] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:48:57,085] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 17:48:57,085] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:48:57,085] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:48:57,085] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:48:57,086] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:48:57,086] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:48:57,086] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 17:48:57,086] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:48:57,086] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:48:57,086] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:48:57,087] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:48:57,087] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:48:57,087] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +7: [2022-11-29 17:48:57,087] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +1: [2022-11-29 17:48:57,087] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 17:48:57,087] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:48:57,087] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:48:57,087] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:48:57,087] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:48:57,087] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:48:57,087] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:48:57,087] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 17:48:57,087] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:48:57,087] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:48:57,088] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:48:57,088] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:48:57,088] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:48:57,088] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:48:57,088] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:48:57,088] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:48:57,088] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:48:57,089] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:48:57,089] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:48:57,089] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:48:57,089] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:48:57,089] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:48:57,089] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 17:48:57,089] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:48:57,089] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:48:57,089] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:48:57,090] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:48:57,090] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:48:57,090] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 17:48:57,090] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:48:57,090] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:48:57,090] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:48:57,090] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:48:57,090] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:48:57,090] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:48:57,091] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:48:57,091] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:48:57,091] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:48:57,091] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:48:57,091] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:48:57,091] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:48:57,092] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:48:57,082] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +0: [2022-11-29 17:48:57,091] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:48:57,082] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:48:57,092] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +5: [2022-11-29 17:48:57,085] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:48:57,092] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:48:57,092] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 17:48:57,085] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +0: [2022-11-29 17:48:57,092] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 17:48:57,085] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 17:48:57,085] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:48:57,085] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:48:57,085] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 17:48:57,086] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:48:57,086] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:48:57,086] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:48:57,092] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:48:57,092] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:48:57,092] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3: [2022-11-29 17:48:57,092] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:48:57,092] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +0: [2022-11-29 17:48:57,092] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:48:57,092] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +2: [2022-11-29 17:48:57,092] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:48:57,092] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:48:57,093] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:48:57,093] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:48:57,093] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:48:57,094] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:48:57,094] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:48:57,094] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 17:48:57,094] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:48:57,094] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +5: [2022-11-29 17:48:57,094] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:48:57,095] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +6: [2022-11-29 17:48:57,095] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 17:48:57,095] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 17:48:57,096] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:48:57,096] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:48:57,096] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:48:57,096] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:48:57,096] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 17:48:57,096] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:48:57,096] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 17:48:57,096] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:48:57,096] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 17:48:57,096] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:48:57,096] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:48:57,096] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:48:57,099] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:48:57,102] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:48:57,102] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:48:57,102] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:48:57,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step8000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:48:57,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: successfully saved checkpoint at iteration 8000 to checkpoints_146moscareap +7: time (ms) | save-checkpoint: 413.79 +7: iteration 8010/ 21553 | consumed samples: 2050560 | consumed tokens: 4199546880 | elapsed time per iteration (s): 0.36 | learning rate: 1.470E-04 | global batch size: 256 | lm loss: 3.124490E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 716.230 | TFLOPs: 25.07 | +7: iteration 8020/ 21553 | consumed samples: 2053120 | consumed tokens: 4204789760 | elapsed time per iteration (s): 0.31 | learning rate: 1.468E-04 | global batch size: 256 | lm loss: 3.122890E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.208 | TFLOPs: 28.57 | +7: iteration 8030/ 21553 | consumed samples: 2055680 | consumed tokens: 4210032640 | elapsed time per iteration (s): 0.32 | learning rate: 1.467E-04 | global batch size: 256 | lm loss: 3.117209E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.879 | TFLOPs: 28.42 | +7: iteration 8040/ 21553 | consumed samples: 2058240 | consumed tokens: 4215275520 | elapsed time per iteration (s): 0.31 | learning rate: 1.466E-04 | global batch size: 256 | lm loss: 3.132550E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.565 | TFLOPs: 29.25 | +7: iteration 8050/ 21553 | consumed samples: 2060800 | consumed tokens: 4220518400 | elapsed time per iteration (s): 0.31 | learning rate: 1.465E-04 | global batch size: 256 | lm loss: 3.134911E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.402 | TFLOPs: 28.79 | +7: iteration 8060/ 21553 | consumed samples: 2063360 | consumed tokens: 4225761280 | elapsed time per iteration (s): 0.31 | learning rate: 1.464E-04 | global batch size: 256 | lm loss: 3.130740E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.385 | TFLOPs: 28.61 | +7: iteration 8070/ 21553 | consumed samples: 2065920 | consumed tokens: 4231004160 | elapsed time per iteration (s): 0.31 | learning rate: 1.462E-04 | global batch size: 256 | lm loss: 3.165963E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.812 | TFLOPs: 29.12 | +7: iteration 8080/ 21553 | consumed samples: 2068480 | consumed tokens: 4236247040 | elapsed time per iteration (s): 0.32 | learning rate: 1.461E-04 | global batch size: 256 | lm loss: 3.114986E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 788.887 | TFLOPs: 27.62 | +7: iteration 8090/ 21553 | consumed samples: 2071040 | consumed tokens: 4241489920 | elapsed time per iteration (s): 0.31 | learning rate: 1.460E-04 | global batch size: 256 | lm loss: 3.106641E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.022 | TFLOPs: 29.06 | +7: iteration 8100/ 21553 | consumed samples: 2073600 | consumed tokens: 4246732800 | elapsed time per iteration (s): 0.31 | learning rate: 1.459E-04 | global batch size: 256 | lm loss: 3.128501E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.551 | TFLOPs: 28.80 | +7: iteration 8110/ 21553 | consumed samples: 2076160 | consumed tokens: 4251975680 | elapsed time per iteration (s): 0.31 | learning rate: 1.457E-04 | global batch size: 256 | lm loss: 3.126662E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.792 | TFLOPs: 29.26 | +7: iteration 8120/ 21553 | consumed samples: 2078720 | consumed tokens: 4257218560 | elapsed time per iteration (s): 0.30 | learning rate: 1.456E-04 | global batch size: 256 | lm loss: 3.142784E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.852 | TFLOPs: 29.51 | +7: iteration 8130/ 21553 | consumed samples: 2081280 | consumed tokens: 4262461440 | elapsed time per iteration (s): 0.31 | learning rate: 1.455E-04 | global batch size: 256 | lm loss: 3.109856E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.503 | TFLOPs: 29.00 | +7: iteration 8140/ 21553 | consumed samples: 2083840 | consumed tokens: 4267704320 | elapsed time per iteration (s): 0.31 | learning rate: 1.454E-04 | global batch size: 256 | lm loss: 3.097780E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.855 | TFLOPs: 29.16 | +7: iteration 8150/ 21553 | consumed samples: 2086400 | consumed tokens: 4272947200 | elapsed time per iteration (s): 0.30 | learning rate: 1.453E-04 | global batch size: 256 | lm loss: 3.152598E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.461 | TFLOPs: 29.42 | +7: iteration 8160/ 21553 | consumed samples: 2088960 | consumed tokens: 4278190080 | elapsed time per iteration (s): 0.31 | learning rate: 1.451E-04 | global batch size: 256 | lm loss: 3.127050E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.317 | TFLOPs: 29.00 | +7: iteration 8170/ 21553 | consumed samples: 2091520 | consumed tokens: 4283432960 | elapsed time per iteration (s): 0.31 | learning rate: 1.450E-04 | global batch size: 256 | lm loss: 3.107510E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.019 | TFLOPs: 29.13 | +7: iteration 8180/ 21553 | consumed samples: 2094080 | consumed tokens: 4288675840 | elapsed time per iteration (s): 0.31 | learning rate: 1.449E-04 | global batch size: 256 | lm loss: 3.120150E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.283 | TFLOPs: 29.10 | +7: iteration 8190/ 21553 | consumed samples: 2096640 | consumed tokens: 4293918720 | elapsed time per iteration (s): 0.32 | learning rate: 1.448E-04 | global batch size: 256 | lm loss: 3.135330E+00 | grad norm: 0.426 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 803.431 | TFLOPs: 28.13 | +7: iteration 8200/ 21553 | consumed samples: 2099200 | consumed tokens: 4299161600 | elapsed time per iteration (s): 0.31 | learning rate: 1.447E-04 | global batch size: 256 | lm loss: 3.128779E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.536 | TFLOPs: 28.69 | +7: iteration 8210/ 21553 | consumed samples: 2101760 | consumed tokens: 4304404480 | elapsed time per iteration (s): 0.32 | learning rate: 1.445E-04 | global batch size: 256 | lm loss: 3.161195E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 798.512 | TFLOPs: 27.95 | +7: iteration 8220/ 21553 | consumed samples: 2104320 | consumed tokens: 4309647360 | elapsed time per iteration (s): 0.31 | learning rate: 1.444E-04 | global batch size: 256 | lm loss: 3.128671E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.552 | TFLOPs: 29.25 | +7: iteration 8230/ 21553 | consumed samples: 2106880 | consumed tokens: 4314890240 | elapsed time per iteration (s): 0.33 | learning rate: 1.443E-04 | global batch size: 256 | lm loss: 3.140360E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 772.846 | TFLOPs: 27.06 | +7: iteration 8240/ 21553 | consumed samples: 2109440 | consumed tokens: 4320133120 | elapsed time per iteration (s): 0.31 | learning rate: 1.442E-04 | global batch size: 256 | lm loss: 3.152635E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.188 | TFLOPs: 28.92 | +7: iteration 8250/ 21553 | consumed samples: 2112000 | consumed tokens: 4325376000 | elapsed time per iteration (s): 0.31 | learning rate: 1.440E-04 | global batch size: 256 | lm loss: 3.120145E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.837 | TFLOPs: 29.02 | +7: iteration 8260/ 21553 | consumed samples: 2114560 | consumed tokens: 4330618880 | elapsed time per iteration (s): 0.30 | learning rate: 1.439E-04 | global batch size: 256 | lm loss: 3.127242E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.047 | TFLOPs: 29.41 | +7: iteration 8270/ 21553 | consumed samples: 2117120 | consumed tokens: 4335861760 | elapsed time per iteration (s): 0.32 | learning rate: 1.438E-04 | global batch size: 256 | lm loss: 3.130664E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 805.889 | TFLOPs: 28.21 | +7: iteration 8280/ 21553 | consumed samples: 2119680 | consumed tokens: 4341104640 | elapsed time per iteration (s): 0.31 | learning rate: 1.437E-04 | global batch size: 256 | lm loss: 3.155653E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.334 | TFLOPs: 29.14 | +7: iteration 8290/ 21553 | consumed samples: 2122240 | consumed tokens: 4346347520 | elapsed time per iteration (s): 0.31 | learning rate: 1.435E-04 | global batch size: 256 | lm loss: 3.146124E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.884 | TFLOPs: 29.37 | +7: iteration 8300/ 21553 | consumed samples: 2124800 | consumed tokens: 4351590400 | elapsed time per iteration (s): 0.30 | learning rate: 1.434E-04 | global batch size: 256 | lm loss: 3.098742E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 847.122 | TFLOPs: 29.66 | +7: iteration 8310/ 21553 | consumed samples: 2127360 | consumed tokens: 4356833280 | elapsed time per iteration (s): 0.30 | learning rate: 1.433E-04 | global batch size: 256 | lm loss: 3.114207E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.518 | TFLOPs: 29.42 | +7: iteration 8320/ 21553 | consumed samples: 2129920 | consumed tokens: 4362076160 | elapsed time per iteration (s): 0.31 | learning rate: 1.432E-04 | global batch size: 256 | lm loss: 3.122025E+00 | grad norm: 0.394 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.454 | TFLOPs: 29.25 | +7: iteration 8330/ 21553 | consumed samples: 2132480 | consumed tokens: 4367319040 | elapsed time per iteration (s): 0.31 | learning rate: 1.431E-04 | global batch size: 256 | lm loss: 3.114532E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.027 | TFLOPs: 28.88 | +7: iteration 8340/ 21553 | consumed samples: 2135040 | consumed tokens: 4372561920 | elapsed time per iteration (s): 0.31 | learning rate: 1.429E-04 | global batch size: 256 | lm loss: 3.122092E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.693 | TFLOPs: 29.22 | +7: iteration 8350/ 21553 | consumed samples: 2137600 | consumed tokens: 4377804800 | elapsed time per iteration (s): 0.31 | learning rate: 1.428E-04 | global batch size: 256 | lm loss: 3.119344E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.185 | TFLOPs: 28.96 | +7: iteration 8360/ 21553 | consumed samples: 2140160 | consumed tokens: 4383047680 | elapsed time per iteration (s): 0.31 | learning rate: 1.427E-04 | global batch size: 256 | lm loss: 3.138058E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.741 | TFLOPs: 29.36 | +7: iteration 8370/ 21553 | consumed samples: 2142720 | consumed tokens: 4388290560 | elapsed time per iteration (s): 0.31 | learning rate: 1.426E-04 | global batch size: 256 | lm loss: 3.122697E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.523 | TFLOPs: 28.86 | +7: iteration 8380/ 21553 | consumed samples: 2145280 | consumed tokens: 4393533440 | elapsed time per iteration (s): 0.31 | learning rate: 1.424E-04 | global batch size: 256 | lm loss: 3.110639E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.070 | TFLOPs: 29.27 | +7: iteration 8390/ 21553 | consumed samples: 2147840 | consumed tokens: 4398776320 | elapsed time per iteration (s): 0.31 | learning rate: 1.423E-04 | global batch size: 256 | lm loss: 3.137005E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.359 | TFLOPs: 29.17 | +7: iteration 8400/ 21553 | consumed samples: 2150400 | consumed tokens: 4404019200 | elapsed time per iteration (s): 0.31 | learning rate: 1.422E-04 | global batch size: 256 | lm loss: 3.097420E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.918 | TFLOPs: 28.91 | +7: iteration 8410/ 21553 | consumed samples: 2152960 | consumed tokens: 4409262080 | elapsed time per iteration (s): 0.31 | learning rate: 1.421E-04 | global batch size: 256 | lm loss: 3.113644E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.359 | TFLOPs: 29.28 | +7: iteration 8420/ 21553 | consumed samples: 2155520 | consumed tokens: 4414504960 | elapsed time per iteration (s): 0.30 | learning rate: 1.419E-04 | global batch size: 256 | lm loss: 3.120920E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.730 | TFLOPs: 29.43 | +7: iteration 8430/ 21553 | consumed samples: 2158080 | consumed tokens: 4419747840 | elapsed time per iteration (s): 0.31 | learning rate: 1.418E-04 | global batch size: 256 | lm loss: 3.107912E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.169 | TFLOPs: 29.06 | +7: iteration 8440/ 21553 | consumed samples: 2160640 | consumed tokens: 4424990720 | elapsed time per iteration (s): 0.30 | learning rate: 1.417E-04 | global batch size: 256 | lm loss: 3.111394E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 844.123 | TFLOPs: 29.55 | +7: iteration 8450/ 21553 | consumed samples: 2163200 | consumed tokens: 4430233600 | elapsed time per iteration (s): 0.31 | learning rate: 1.416E-04 | global batch size: 256 | lm loss: 3.110453E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.761 | TFLOPs: 29.08 | +7: iteration 8460/ 21553 | consumed samples: 2165760 | consumed tokens: 4435476480 | elapsed time per iteration (s): 0.31 | learning rate: 1.414E-04 | global batch size: 256 | lm loss: 3.127677E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.452 | TFLOPs: 28.58 | +7: iteration 8470/ 21553 | consumed samples: 2168320 | consumed tokens: 4440719360 | elapsed time per iteration (s): 0.31 | learning rate: 1.413E-04 | global batch size: 256 | lm loss: 3.125029E+00 | grad norm: 0.399 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.886 | TFLOPs: 29.23 | +7: iteration 8480/ 21553 | consumed samples: 2170880 | consumed tokens: 4445962240 | elapsed time per iteration (s): 0.30 | learning rate: 1.412E-04 | global batch size: 256 | lm loss: 3.111923E+00 | grad norm: 0.392 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.506 | TFLOPs: 29.53 | +7: iteration 8490/ 21553 | consumed samples: 2173440 | consumed tokens: 4451205120 | elapsed time per iteration (s): 0.31 | learning rate: 1.411E-04 | global batch size: 256 | lm loss: 3.132404E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.845 | TFLOPs: 29.23 | +7: iteration 8500/ 21553 | consumed samples: 2176000 | consumed tokens: 4456448000 | elapsed time per iteration (s): 0.30 | learning rate: 1.409E-04 | global batch size: 256 | lm loss: 3.157289E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 846.212 | TFLOPs: 29.62 | +7: iteration 8510/ 21553 | consumed samples: 2178560 | consumed tokens: 4461690880 | elapsed time per iteration (s): 0.30 | learning rate: 1.408E-04 | global batch size: 256 | lm loss: 3.124324E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.025 | TFLOPs: 29.44 | +7: iteration 8520/ 21553 | consumed samples: 2181120 | consumed tokens: 4466933760 | elapsed time per iteration (s): 0.31 | learning rate: 1.407E-04 | global batch size: 256 | lm loss: 3.118035E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.926 | TFLOPs: 29.26 | +7: iteration 8530/ 21553 | consumed samples: 2183680 | consumed tokens: 4472176640 | elapsed time per iteration (s): 0.30 | learning rate: 1.406E-04 | global batch size: 256 | lm loss: 3.132441E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.272 | TFLOPs: 29.49 | +7: iteration 8540/ 21553 | consumed samples: 2186240 | consumed tokens: 4477419520 | elapsed time per iteration (s): 0.31 | learning rate: 1.405E-04 | global batch size: 256 | lm loss: 3.114622E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.702 | TFLOPs: 28.91 | +7: iteration 8550/ 21553 | consumed samples: 2188800 | consumed tokens: 4482662400 | elapsed time per iteration (s): 0.31 | learning rate: 1.403E-04 | global batch size: 256 | lm loss: 3.123472E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.225 | TFLOPs: 28.89 | +7: iteration 8560/ 21553 | consumed samples: 2191360 | consumed tokens: 4487905280 | elapsed time per iteration (s): 0.31 | learning rate: 1.402E-04 | global batch size: 256 | lm loss: 3.095005E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.951 | TFLOPs: 28.84 | +7: iteration 8570/ 21553 | consumed samples: 2193920 | consumed tokens: 4493148160 | elapsed time per iteration (s): 0.31 | learning rate: 1.401E-04 | global batch size: 256 | lm loss: 3.127364E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.173 | TFLOPs: 28.78 | +7: iteration 8580/ 21553 | consumed samples: 2196480 | consumed tokens: 4498391040 | elapsed time per iteration (s): 0.31 | learning rate: 1.400E-04 | global batch size: 256 | lm loss: 3.089393E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.297 | TFLOPs: 29.17 | +7: iteration 8590/ 21553 | consumed samples: 2199040 | consumed tokens: 4503633920 | elapsed time per iteration (s): 0.31 | learning rate: 1.398E-04 | global batch size: 256 | lm loss: 3.126902E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.431 | TFLOPs: 29.21 | +7: iteration 8600/ 21553 | consumed samples: 2201600 | consumed tokens: 4508876800 | elapsed time per iteration (s): 0.31 | learning rate: 1.397E-04 | global batch size: 256 | lm loss: 3.093320E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.435 | TFLOPs: 29.14 | +7: iteration 8610/ 21553 | consumed samples: 2204160 | consumed tokens: 4514119680 | elapsed time per iteration (s): 0.32 | learning rate: 1.396E-04 | global batch size: 256 | lm loss: 3.106490E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.684 | TFLOPs: 28.31 | +7: iteration 8620/ 21553 | consumed samples: 2206720 | consumed tokens: 4519362560 | elapsed time per iteration (s): 0.30 | learning rate: 1.395E-04 | global batch size: 256 | lm loss: 3.089906E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.109 | TFLOPs: 29.44 | +7: iteration 8630/ 21553 | consumed samples: 2209280 | consumed tokens: 4524605440 | elapsed time per iteration (s): 0.31 | learning rate: 1.393E-04 | global batch size: 256 | lm loss: 3.148283E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.095 | TFLOPs: 28.50 | +7: iteration 8640/ 21553 | consumed samples: 2211840 | consumed tokens: 4529848320 | elapsed time per iteration (s): 0.31 | learning rate: 1.392E-04 | global batch size: 256 | lm loss: 3.156045E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.545 | TFLOPs: 29.36 | +7: iteration 8650/ 21553 | consumed samples: 2214400 | consumed tokens: 4535091200 | elapsed time per iteration (s): 0.30 | learning rate: 1.391E-04 | global batch size: 256 | lm loss: 3.101495E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.060 | TFLOPs: 29.41 | +7: iteration 8660/ 21553 | consumed samples: 2216960 | consumed tokens: 4540334080 | elapsed time per iteration (s): 0.30 | learning rate: 1.389E-04 | global batch size: 256 | lm loss: 3.101323E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.595 | TFLOPs: 29.46 | +7: iteration 8670/ 21553 | consumed samples: 2219520 | consumed tokens: 4545576960 | elapsed time per iteration (s): 0.31 | learning rate: 1.388E-04 | global batch size: 256 | lm loss: 3.118515E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.857 | TFLOPs: 29.09 | +7: iteration 8680/ 21553 | consumed samples: 2222080 | consumed tokens: 4550819840 | elapsed time per iteration (s): 0.30 | learning rate: 1.387E-04 | global batch size: 256 | lm loss: 3.089790E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.341 | TFLOPs: 29.59 | +7: iteration 8690/ 21553 | consumed samples: 2224640 | consumed tokens: 4556062720 | elapsed time per iteration (s): 0.31 | learning rate: 1.386E-04 | global batch size: 256 | lm loss: 3.083659E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.234 | TFLOPs: 29.10 | +7: iteration 8700/ 21553 | consumed samples: 2227200 | consumed tokens: 4561305600 | elapsed time per iteration (s): 0.31 | learning rate: 1.384E-04 | global batch size: 256 | lm loss: 3.129390E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.716 | TFLOPs: 29.36 | +7: iteration 8710/ 21553 | consumed samples: 2229760 | consumed tokens: 4566548480 | elapsed time per iteration (s): 0.31 | learning rate: 1.383E-04 | global batch size: 256 | lm loss: 3.124188E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.718 | TFLOPs: 29.19 | +7: iteration 8720/ 21553 | consumed samples: 2232320 | consumed tokens: 4571791360 | elapsed time per iteration (s): 0.31 | learning rate: 1.382E-04 | global batch size: 256 | lm loss: 3.099768E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.474 | TFLOPs: 28.97 | +7: iteration 8730/ 21553 | consumed samples: 2234880 | consumed tokens: 4577034240 | elapsed time per iteration (s): 0.33 | learning rate: 1.381E-04 | global batch size: 256 | lm loss: 3.118852E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 769.426 | TFLOPs: 26.94 | +7: iteration 8740/ 21553 | consumed samples: 2237440 | consumed tokens: 4582277120 | elapsed time per iteration (s): 0.31 | learning rate: 1.379E-04 | global batch size: 256 | lm loss: 3.114074E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.983 | TFLOPs: 29.13 | +7: iteration 8750/ 21553 | consumed samples: 2240000 | consumed tokens: 4587520000 | elapsed time per iteration (s): 0.30 | learning rate: 1.378E-04 | global batch size: 256 | lm loss: 3.095932E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.578 | TFLOPs: 29.50 | +7: iteration 8760/ 21553 | consumed samples: 2242560 | consumed tokens: 4592762880 | elapsed time per iteration (s): 0.32 | learning rate: 1.377E-04 | global batch size: 256 | lm loss: 3.100082E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 800.950 | TFLOPs: 28.04 | +7: iteration 8770/ 21553 | consumed samples: 2245120 | consumed tokens: 4598005760 | elapsed time per iteration (s): 0.32 | learning rate: 1.376E-04 | global batch size: 256 | lm loss: 3.109813E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 790.080 | TFLOPs: 27.66 | +7: iteration 8780/ 21553 | consumed samples: 2247680 | consumed tokens: 4603248640 | elapsed time per iteration (s): 0.31 | learning rate: 1.374E-04 | global batch size: 256 | lm loss: 3.123551E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.503 | TFLOPs: 29.18 | +7: iteration 8790/ 21553 | consumed samples: 2250240 | consumed tokens: 4608491520 | elapsed time per iteration (s): 0.31 | learning rate: 1.373E-04 | global batch size: 256 | lm loss: 3.122706E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.611 | TFLOPs: 29.36 | +7: iteration 8800/ 21553 | consumed samples: 2252800 | consumed tokens: 4613734400 | elapsed time per iteration (s): 0.31 | learning rate: 1.372E-04 | global batch size: 256 | lm loss: 3.108480E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.866 | TFLOPs: 29.19 | +7: iteration 8810/ 21553 | consumed samples: 2255360 | consumed tokens: 4618977280 | elapsed time per iteration (s): 0.30 | learning rate: 1.371E-04 | global batch size: 256 | lm loss: 3.107141E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 846.910 | TFLOPs: 29.65 | +7: iteration 8820/ 21553 | consumed samples: 2257920 | consumed tokens: 4624220160 | elapsed time per iteration (s): 0.35 | learning rate: 1.369E-04 | global batch size: 256 | lm loss: 3.098904E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 724.774 | TFLOPs: 25.37 | +7: iteration 8830/ 21553 | consumed samples: 2260480 | consumed tokens: 4629463040 | elapsed time per iteration (s): 0.31 | learning rate: 1.368E-04 | global batch size: 256 | lm loss: 3.113324E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.716 | TFLOPs: 28.59 | +7: iteration 8840/ 21553 | consumed samples: 2263040 | consumed tokens: 4634705920 | elapsed time per iteration (s): 0.33 | learning rate: 1.367E-04 | global batch size: 256 | lm loss: 3.103993E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 787.437 | TFLOPs: 27.57 | +7: iteration 8850/ 21553 | consumed samples: 2265600 | consumed tokens: 4639948800 | elapsed time per iteration (s): 0.31 | learning rate: 1.366E-04 | global batch size: 256 | lm loss: 3.129037E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.325 | TFLOPs: 28.68 | +7: iteration 8860/ 21553 | consumed samples: 2268160 | consumed tokens: 4645191680 | elapsed time per iteration (s): 0.33 | learning rate: 1.364E-04 | global batch size: 256 | lm loss: 3.103574E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 765.623 | TFLOPs: 26.80 | +7: iteration 8870/ 21553 | consumed samples: 2270720 | consumed tokens: 4650434560 | elapsed time per iteration (s): 0.30 | learning rate: 1.363E-04 | global batch size: 256 | lm loss: 3.122742E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.335 | TFLOPs: 29.42 | +7: iteration 8880/ 21553 | consumed samples: 2273280 | consumed tokens: 4655677440 | elapsed time per iteration (s): 0.31 | learning rate: 1.362E-04 | global batch size: 256 | lm loss: 3.105903E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.105 | TFLOPs: 28.95 | +7: iteration 8890/ 21553 | consumed samples: 2275840 | consumed tokens: 4660920320 | elapsed time per iteration (s): 0.31 | learning rate: 1.360E-04 | global batch size: 256 | lm loss: 3.117603E+00 | grad norm: 0.404 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.645 | TFLOPs: 29.29 | +7: iteration 8900/ 21553 | consumed samples: 2278400 | consumed tokens: 4666163200 | elapsed time per iteration (s): 0.30 | learning rate: 1.359E-04 | global batch size: 256 | lm loss: 3.106813E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.918 | TFLOPs: 29.47 | +7: iteration 8910/ 21553 | consumed samples: 2280960 | consumed tokens: 4671406080 | elapsed time per iteration (s): 0.30 | learning rate: 1.358E-04 | global batch size: 256 | lm loss: 3.127574E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.943 | TFLOPs: 29.40 | +7: iteration 8920/ 21553 | consumed samples: 2283520 | consumed tokens: 4676648960 | elapsed time per iteration (s): 0.32 | learning rate: 1.357E-04 | global batch size: 256 | lm loss: 3.105203E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 806.947 | TFLOPs: 28.25 | +7: iteration 8930/ 21553 | consumed samples: 2286080 | consumed tokens: 4681891840 | elapsed time per iteration (s): 0.30 | learning rate: 1.355E-04 | global batch size: 256 | lm loss: 3.115045E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.796 | TFLOPs: 29.54 | +7: iteration 8940/ 21553 | consumed samples: 2288640 | consumed tokens: 4687134720 | elapsed time per iteration (s): 0.31 | learning rate: 1.354E-04 | global batch size: 256 | lm loss: 3.114893E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.089 | TFLOPs: 28.67 | +7: iteration 8950/ 21553 | consumed samples: 2291200 | consumed tokens: 4692377600 | elapsed time per iteration (s): 0.31 | learning rate: 1.353E-04 | global batch size: 256 | lm loss: 3.099687E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.944 | TFLOPs: 29.16 | +7: iteration 8960/ 21553 | consumed samples: 2293760 | consumed tokens: 4697620480 | elapsed time per iteration (s): 0.30 | learning rate: 1.352E-04 | global batch size: 256 | lm loss: 3.110146E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.480 | TFLOPs: 29.46 | +7: iteration 8970/ 21553 | consumed samples: 2296320 | consumed tokens: 4702863360 | elapsed time per iteration (s): 0.31 | learning rate: 1.350E-04 | global batch size: 256 | lm loss: 3.116294E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.464 | TFLOPs: 29.25 | +7: iteration 8980/ 21553 | consumed samples: 2298880 | consumed tokens: 4708106240 | elapsed time per iteration (s): 0.31 | learning rate: 1.349E-04 | global batch size: 256 | lm loss: 3.080305E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.714 | TFLOPs: 28.94 | +7: iteration 8990/ 21553 | consumed samples: 2301440 | consumed tokens: 4713349120 | elapsed time per iteration (s): 0.30 | learning rate: 1.348E-04 | global batch size: 256 | lm loss: 3.111667E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.368 | TFLOPs: 29.59 | +7: iteration 9000/ 21553 | consumed samples: 2304000 | consumed tokens: 4718592000 | elapsed time per iteration (s): 0.31 | learning rate: 1.346E-04 | global batch size: 256 | lm loss: 3.125481E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.330 | TFLOPs: 29.28 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 9000 | lm loss value: 2.931618E+00 | lm loss PPL: 1.875796E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 9000 to checkpoints_146moscareap +0: [2022-11-29 17:54:06,986] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step9000 is begin to save! +0: [2022-11-29 17:54:06,990] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:54:07,076] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:54:07,076] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:54:07,099] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:54:07,100] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:54:07,116] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:54:07,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:54:07,133] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:54:07,133] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:54:07,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:54:07,150] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:54:07,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:54:07,166] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:54:07,183] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:54:07,183] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:54:07,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:54:07,199] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:54:07,214] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:54:07,215] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:54:07,232] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:54:07,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:54:07,248] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:54:07,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:54:07,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:54:07,264] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:54:07,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:54:07,280] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:54:07,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:54:07,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:54:07,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:54:07,313] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:54:07,329] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:54:07,329] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:54:07,331] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:54:07,332] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_146moscareap/global_step9000/mp_rank_00_model_states.pt +0: [2022-11-29 17:54:07,332] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:54:07,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:54:07,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:54:07,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:54:07,388] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:54:07,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 17:54:07,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:54:07,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:54:07,388] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +4: [2022-11-29 17:54:07,388] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +2: [2022-11-29 17:54:07,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 17:54:07,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 17:54:07,389] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:54:07,389] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:54:07,389] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 17:54:07,389] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:54:07,390] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:54:07,390] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:54:07,390] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 17:54:07,391] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:54:07,391] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:54:07,391] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 17:54:07,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:54:07,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:54:07,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +7: [2022-11-29 17:54:07,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:54:07,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +3: [2022-11-29 17:54:07,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 17:54:07,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +2: [2022-11-29 17:54:07,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 17:54:07,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 17:54:07,393] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:54:07,393] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:54:07,393] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 17:54:07,393] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:54:07,393] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:54:07,393] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 17:54:07,394] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:54:07,394] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:54:07,394] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:54:07,394] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:54:07,394] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 17:54:07,394] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 17:54:07,394] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:54:07,394] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:54:07,394] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 17:54:07,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:54:07,395] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:54:07,395] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 17:54:07,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:54:07,395] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:54:07,395] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 17:54:07,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:54:07,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:54:07,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 17:54:07,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:54:07,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:54:07,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 17:54:07,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:54:07,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:54:07,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 17:54:07,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:54:07,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:54:07,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 17:54:07,398] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:54:07,398] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:54:07,398] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:54:07,398] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:54:07,398] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 17:54:07,398] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 17:54:07,398] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:54:07,398] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:54:07,398] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 17:54:07,399] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:54:07,399] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:54:07,399] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:54:07,399] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 17:54:07,399] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:54:07,399] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 17:54:07,400] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:54:07,400] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:54:07,400] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 17:54:07,400] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:54:07,400] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:54:07,400] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 17:54:07,400] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:54:07,400] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:54:07,401] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 17:54:07,400] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:54:07,401] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +0: [2022-11-29 17:54:07,401] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:54:07,401] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +1: [2022-11-29 17:54:07,401] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 17:54:07,401] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 17:54:07,401] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:54:07,401] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:54:07,401] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 17:54:07,401] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:54:07,401] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:54:07,401] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:54:07,401] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +1: [2022-11-29 17:54:07,401] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:54:07,401] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 17:54:07,401] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 17:54:07,401] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:54:07,401] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 17:54:07,401] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:54:07,401] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:54:07,401] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 17:54:07,402] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:54:07,402] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:54:07,402] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +2: [2022-11-29 17:54:07,402] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +0: [2022-11-29 17:54:07,402] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 17:54:07,402] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 17:54:07,402] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:54:07,402] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:54:07,402] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:54:07,402] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 17:54:07,402] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:54:07,402] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 17:54:07,403] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:54:07,403] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:54:07,403] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 17:54:07,403] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:54:07,403] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:54:07,403] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:54:07,403] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:54:07,403] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 17:54:07,403] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 17:54:07,404] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:54:07,404] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:54:07,404] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 17:54:07,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:54:07,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:54:07,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:54:07,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:54:07,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 17:54:07,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 17:54:07,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:54:07,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:54:07,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 17:54:07,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:54:07,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:54:07,406] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +2: [2022-11-29 17:54:07,406] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +3: [2022-11-29 17:54:07,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 17:54:07,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 17:54:07,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:54:07,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:54:07,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 17:54:07,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:54:07,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:54:07,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 17:54:07,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:54:07,408] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:54:07,408] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 17:54:07,408] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:54:07,408] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:54:07,408] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 17:54:07,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:54:07,409] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:54:07,409] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 17:54:07,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:54:07,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:54:07,409] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:54:07,409] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 17:54:07,409] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:54:07,409] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 17:54:07,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:54:07,410] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:54:07,410] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 17:54:07,411] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:54:07,411] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:54:07,411] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 17:54:07,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:54:07,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:54:07,412] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 17:54:07,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:54:07,412] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 17:54:07,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:54:07,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:54:07,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 17:54:07,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:54:07,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:54:07,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 17:54:07,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:54:07,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:54:07,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 17:54:07,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:54:07,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:54:07,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 17:54:07,416] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:54:07,416] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step9000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:54:07,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: successfully saved checkpoint at iteration 9000 to checkpoints_146moscareap +7: time (ms) | save-checkpoint: 436.95 +7: iteration 9010/ 21553 | consumed samples: 2306560 | consumed tokens: 4723834880 | elapsed time per iteration (s): 0.38 | learning rate: 1.345E-04 | global batch size: 256 | lm loss: 3.101161E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 673.388 | TFLOPs: 23.57 | +7: iteration 9020/ 21553 | consumed samples: 2309120 | consumed tokens: 4729077760 | elapsed time per iteration (s): 0.31 | learning rate: 1.344E-04 | global batch size: 256 | lm loss: 3.093274E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.110 | TFLOPs: 28.46 | +7: iteration 9030/ 21553 | consumed samples: 2311680 | consumed tokens: 4734320640 | elapsed time per iteration (s): 0.32 | learning rate: 1.343E-04 | global batch size: 256 | lm loss: 3.096513E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 805.812 | TFLOPs: 28.21 | +7: iteration 9040/ 21553 | consumed samples: 2314240 | consumed tokens: 4739563520 | elapsed time per iteration (s): 0.31 | learning rate: 1.341E-04 | global batch size: 256 | lm loss: 3.081456E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.140 | TFLOPs: 29.34 | +7: iteration 9050/ 21553 | consumed samples: 2316800 | consumed tokens: 4744806400 | elapsed time per iteration (s): 0.32 | learning rate: 1.340E-04 | global batch size: 256 | lm loss: 3.091231E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.977 | TFLOPs: 28.39 | +7: iteration 9060/ 21553 | consumed samples: 2319360 | consumed tokens: 4750049280 | elapsed time per iteration (s): 0.31 | learning rate: 1.339E-04 | global batch size: 256 | lm loss: 3.073623E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.244 | TFLOPs: 29.38 | +7: iteration 9070/ 21553 | consumed samples: 2321920 | consumed tokens: 4755292160 | elapsed time per iteration (s): 0.31 | learning rate: 1.338E-04 | global batch size: 256 | lm loss: 3.105143E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.868 | TFLOPs: 29.12 | +7: iteration 9080/ 21553 | consumed samples: 2324480 | consumed tokens: 4760535040 | elapsed time per iteration (s): 0.31 | learning rate: 1.336E-04 | global batch size: 256 | lm loss: 3.119708E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.595 | TFLOPs: 29.18 | +7: iteration 9090/ 21553 | consumed samples: 2327040 | consumed tokens: 4765777920 | elapsed time per iteration (s): 0.32 | learning rate: 1.335E-04 | global batch size: 256 | lm loss: 3.123199E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 806.245 | TFLOPs: 28.22 | +7: iteration 9100/ 21553 | consumed samples: 2329600 | consumed tokens: 4771020800 | elapsed time per iteration (s): 0.30 | learning rate: 1.334E-04 | global batch size: 256 | lm loss: 3.082690E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.017 | TFLOPs: 29.41 | +7: iteration 9110/ 21553 | consumed samples: 2332160 | consumed tokens: 4776263680 | elapsed time per iteration (s): 0.31 | learning rate: 1.332E-04 | global batch size: 256 | lm loss: 3.091783E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.131 | TFLOPs: 29.13 | +7: iteration 9120/ 21553 | consumed samples: 2334720 | consumed tokens: 4781506560 | elapsed time per iteration (s): 0.31 | learning rate: 1.331E-04 | global batch size: 256 | lm loss: 3.085144E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.108 | TFLOPs: 28.78 | +7: iteration 9130/ 21553 | consumed samples: 2337280 | consumed tokens: 4786749440 | elapsed time per iteration (s): 0.31 | learning rate: 1.330E-04 | global batch size: 256 | lm loss: 3.096061E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.445 | TFLOPs: 28.83 | +7: iteration 9140/ 21553 | consumed samples: 2339840 | consumed tokens: 4791992320 | elapsed time per iteration (s): 0.30 | learning rate: 1.329E-04 | global batch size: 256 | lm loss: 3.095678E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.947 | TFLOPs: 29.61 | +7: iteration 9150/ 21553 | consumed samples: 2342400 | consumed tokens: 4797235200 | elapsed time per iteration (s): 0.31 | learning rate: 1.327E-04 | global batch size: 256 | lm loss: 3.065598E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.922 | TFLOPs: 28.56 | +7: iteration 9160/ 21553 | consumed samples: 2344960 | consumed tokens: 4802478080 | elapsed time per iteration (s): 0.31 | learning rate: 1.326E-04 | global batch size: 256 | lm loss: 3.099918E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.319 | TFLOPs: 29.28 | +7: iteration 9170/ 21553 | consumed samples: 2347520 | consumed tokens: 4807720960 | elapsed time per iteration (s): 0.30 | learning rate: 1.325E-04 | global batch size: 256 | lm loss: 3.094665E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.085 | TFLOPs: 29.48 | +7: iteration 9180/ 21553 | consumed samples: 2350080 | consumed tokens: 4812963840 | elapsed time per iteration (s): 0.31 | learning rate: 1.323E-04 | global batch size: 256 | lm loss: 3.088264E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.545 | TFLOPs: 29.29 | +7: iteration 9190/ 21553 | consumed samples: 2352640 | consumed tokens: 4818206720 | elapsed time per iteration (s): 0.30 | learning rate: 1.322E-04 | global batch size: 256 | lm loss: 3.086424E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 844.567 | TFLOPs: 29.57 | +7: iteration 9200/ 21553 | consumed samples: 2355200 | consumed tokens: 4823449600 | elapsed time per iteration (s): 0.31 | learning rate: 1.321E-04 | global batch size: 256 | lm loss: 3.120106E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.039 | TFLOPs: 28.99 | +7: iteration 9210/ 21553 | consumed samples: 2357760 | consumed tokens: 4828692480 | elapsed time per iteration (s): 0.31 | learning rate: 1.320E-04 | global batch size: 256 | lm loss: 3.115011E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.310 | TFLOPs: 29.35 | +7: iteration 9220/ 21553 | consumed samples: 2360320 | consumed tokens: 4833935360 | elapsed time per iteration (s): 0.31 | learning rate: 1.318E-04 | global batch size: 256 | lm loss: 3.111633E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.685 | TFLOPs: 28.76 | +7: iteration 9230/ 21553 | consumed samples: 2362880 | consumed tokens: 4839178240 | elapsed time per iteration (s): 0.31 | learning rate: 1.317E-04 | global batch size: 256 | lm loss: 3.100648E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.493 | TFLOPs: 28.69 | +7: iteration 9240/ 21553 | consumed samples: 2365440 | consumed tokens: 4844421120 | elapsed time per iteration (s): 0.31 | learning rate: 1.316E-04 | global batch size: 256 | lm loss: 3.129247E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.776 | TFLOPs: 29.33 | +7: iteration 9250/ 21553 | consumed samples: 2368000 | consumed tokens: 4849664000 | elapsed time per iteration (s): 0.31 | learning rate: 1.314E-04 | global batch size: 256 | lm loss: 3.120752E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.762 | TFLOPs: 28.80 | +7: iteration 9260/ 21553 | consumed samples: 2370560 | consumed tokens: 4854906880 | elapsed time per iteration (s): 0.31 | learning rate: 1.313E-04 | global batch size: 256 | lm loss: 3.075017E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.327 | TFLOPs: 28.82 | +7: iteration 9270/ 21553 | consumed samples: 2373120 | consumed tokens: 4860149760 | elapsed time per iteration (s): 0.30 | learning rate: 1.312E-04 | global batch size: 256 | lm loss: 3.064619E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 844.795 | TFLOPs: 29.57 | +7: iteration 9280/ 21553 | consumed samples: 2375680 | consumed tokens: 4865392640 | elapsed time per iteration (s): 0.30 | learning rate: 1.311E-04 | global batch size: 256 | lm loss: 3.108914E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.947 | TFLOPs: 29.61 | +7: iteration 9290/ 21553 | consumed samples: 2378240 | consumed tokens: 4870635520 | elapsed time per iteration (s): 0.31 | learning rate: 1.309E-04 | global batch size: 256 | lm loss: 3.088973E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.858 | TFLOPs: 28.98 | +7: iteration 9300/ 21553 | consumed samples: 2380800 | consumed tokens: 4875878400 | elapsed time per iteration (s): 0.30 | learning rate: 1.308E-04 | global batch size: 256 | lm loss: 3.078372E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.108 | TFLOPs: 29.44 | +7: iteration 9310/ 21553 | consumed samples: 2383360 | consumed tokens: 4881121280 | elapsed time per iteration (s): 0.31 | learning rate: 1.307E-04 | global batch size: 256 | lm loss: 3.097613E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.742 | TFLOPs: 28.80 | +7: iteration 9320/ 21553 | consumed samples: 2385920 | consumed tokens: 4886364160 | elapsed time per iteration (s): 0.31 | learning rate: 1.305E-04 | global batch size: 256 | lm loss: 3.071052E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.410 | TFLOPs: 29.04 | +7: iteration 9330/ 21553 | consumed samples: 2388480 | consumed tokens: 4891607040 | elapsed time per iteration (s): 0.31 | learning rate: 1.304E-04 | global batch size: 256 | lm loss: 3.077886E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.836 | TFLOPs: 29.26 | +7: iteration 9340/ 21553 | consumed samples: 2391040 | consumed tokens: 4896849920 | elapsed time per iteration (s): 0.32 | learning rate: 1.303E-04 | global batch size: 256 | lm loss: 3.089429E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 788.616 | TFLOPs: 27.61 | +7: iteration 9350/ 21553 | consumed samples: 2393600 | consumed tokens: 4902092800 | elapsed time per iteration (s): 0.31 | learning rate: 1.302E-04 | global batch size: 256 | lm loss: 3.102986E+00 | grad norm: 0.382 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.202 | TFLOPs: 28.71 | +7: iteration 9360/ 21553 | consumed samples: 2396160 | consumed tokens: 4907335680 | elapsed time per iteration (s): 0.31 | learning rate: 1.300E-04 | global batch size: 256 | lm loss: 3.087033E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.766 | TFLOPs: 28.80 | +7: iteration 9370/ 21553 | consumed samples: 2398720 | consumed tokens: 4912578560 | elapsed time per iteration (s): 0.30 | learning rate: 1.299E-04 | global batch size: 256 | lm loss: 3.085724E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 847.840 | TFLOPs: 29.68 | +7: iteration 9380/ 21553 | consumed samples: 2401280 | consumed tokens: 4917821440 | elapsed time per iteration (s): 0.31 | learning rate: 1.298E-04 | global batch size: 256 | lm loss: 3.094276E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.627 | TFLOPs: 29.22 | +7: iteration 9390/ 21553 | consumed samples: 2403840 | consumed tokens: 4923064320 | elapsed time per iteration (s): 0.31 | learning rate: 1.296E-04 | global batch size: 256 | lm loss: 3.083147E+00 | grad norm: 0.465 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.637 | TFLOPs: 28.52 | +7: iteration 9400/ 21553 | consumed samples: 2406400 | consumed tokens: 4928307200 | elapsed time per iteration (s): 0.31 | learning rate: 1.295E-04 | global batch size: 256 | lm loss: 3.090394E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.333 | TFLOPs: 29.31 | +7: iteration 9410/ 21553 | consumed samples: 2408960 | consumed tokens: 4933550080 | elapsed time per iteration (s): 0.34 | learning rate: 1.294E-04 | global batch size: 256 | lm loss: 3.104221E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 758.571 | TFLOPs: 26.56 | +7: iteration 9420/ 21553 | consumed samples: 2411520 | consumed tokens: 4938792960 | elapsed time per iteration (s): 0.33 | learning rate: 1.293E-04 | global batch size: 256 | lm loss: 3.088225E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 776.903 | TFLOPs: 27.20 | +7: iteration 9430/ 21553 | consumed samples: 2414080 | consumed tokens: 4944035840 | elapsed time per iteration (s): 0.30 | learning rate: 1.291E-04 | global batch size: 256 | lm loss: 3.112222E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.398 | TFLOPs: 29.60 | +7: iteration 9440/ 21553 | consumed samples: 2416640 | consumed tokens: 4949278720 | elapsed time per iteration (s): 0.31 | learning rate: 1.290E-04 | global batch size: 256 | lm loss: 3.118653E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.257 | TFLOPs: 29.38 | +7: iteration 9450/ 21553 | consumed samples: 2419200 | consumed tokens: 4954521600 | elapsed time per iteration (s): 0.30 | learning rate: 1.289E-04 | global batch size: 256 | lm loss: 3.064872E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.815 | TFLOPs: 29.61 | +7: iteration 9460/ 21553 | consumed samples: 2421760 | consumed tokens: 4959764480 | elapsed time per iteration (s): 0.31 | learning rate: 1.287E-04 | global batch size: 256 | lm loss: 3.085021E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.928 | TFLOPs: 29.16 | +7: iteration 9470/ 21553 | consumed samples: 2424320 | consumed tokens: 4965007360 | elapsed time per iteration (s): 0.30 | learning rate: 1.286E-04 | global batch size: 256 | lm loss: 3.113225E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.857 | TFLOPs: 29.47 | +7: iteration 9480/ 21553 | consumed samples: 2426880 | consumed tokens: 4970250240 | elapsed time per iteration (s): 0.30 | learning rate: 1.285E-04 | global batch size: 256 | lm loss: 3.072368E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.679 | TFLOPs: 29.39 | +7: iteration 9490/ 21553 | consumed samples: 2429440 | consumed tokens: 4975493120 | elapsed time per iteration (s): 0.31 | learning rate: 1.283E-04 | global batch size: 256 | lm loss: 3.056545E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.564 | TFLOPs: 28.55 | +7: iteration 9500/ 21553 | consumed samples: 2432000 | consumed tokens: 4980736000 | elapsed time per iteration (s): 0.31 | learning rate: 1.282E-04 | global batch size: 256 | lm loss: 3.095169E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.146 | TFLOPs: 28.71 | +7: iteration 9510/ 21553 | consumed samples: 2434560 | consumed tokens: 4985978880 | elapsed time per iteration (s): 0.30 | learning rate: 1.281E-04 | global batch size: 256 | lm loss: 3.096620E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.347 | TFLOPs: 29.45 | +7: iteration 9520/ 21553 | consumed samples: 2437120 | consumed tokens: 4991221760 | elapsed time per iteration (s): 0.32 | learning rate: 1.280E-04 | global batch size: 256 | lm loss: 3.111414E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 798.873 | TFLOPs: 27.97 | +7: iteration 9530/ 21553 | consumed samples: 2439680 | consumed tokens: 4996464640 | elapsed time per iteration (s): 0.31 | learning rate: 1.278E-04 | global batch size: 256 | lm loss: 3.081097E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.073 | TFLOPs: 29.16 | +7: iteration 9540/ 21553 | consumed samples: 2442240 | consumed tokens: 5001707520 | elapsed time per iteration (s): 0.33 | learning rate: 1.277E-04 | global batch size: 256 | lm loss: 3.101298E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 773.708 | TFLOPs: 27.09 | +7: iteration 9550/ 21553 | consumed samples: 2444800 | consumed tokens: 5006950400 | elapsed time per iteration (s): 0.31 | learning rate: 1.276E-04 | global batch size: 256 | lm loss: 3.092092E+00 | grad norm: 0.368 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.976 | TFLOPs: 28.95 | +7: iteration 9560/ 21553 | consumed samples: 2447360 | consumed tokens: 5012193280 | elapsed time per iteration (s): 0.30 | learning rate: 1.274E-04 | global batch size: 256 | lm loss: 3.078473E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.460 | TFLOPs: 29.39 | +7: iteration 9570/ 21553 | consumed samples: 2449920 | consumed tokens: 5017436160 | elapsed time per iteration (s): 0.33 | learning rate: 1.273E-04 | global batch size: 256 | lm loss: 3.063820E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 770.840 | TFLOPs: 26.98 | +7: iteration 9580/ 21553 | consumed samples: 2452480 | consumed tokens: 5022679040 | elapsed time per iteration (s): 0.31 | learning rate: 1.272E-04 | global batch size: 256 | lm loss: 3.088722E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.630 | TFLOPs: 28.97 | +7: iteration 9590/ 21553 | consumed samples: 2455040 | consumed tokens: 5027921920 | elapsed time per iteration (s): 0.30 | learning rate: 1.270E-04 | global batch size: 256 | lm loss: 3.098782E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.371 | TFLOPs: 29.38 | +7: iteration 9600/ 21553 | consumed samples: 2457600 | consumed tokens: 5033164800 | elapsed time per iteration (s): 0.30 | learning rate: 1.269E-04 | global batch size: 256 | lm loss: 3.081003E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.372 | TFLOPs: 29.45 | +7: iteration 9610/ 21553 | consumed samples: 2460160 | consumed tokens: 5038407680 | elapsed time per iteration (s): 0.30 | learning rate: 1.268E-04 | global batch size: 256 | lm loss: 3.048084E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.273 | TFLOPs: 29.42 | +7: iteration 9620/ 21553 | consumed samples: 2462720 | consumed tokens: 5043650560 | elapsed time per iteration (s): 0.31 | learning rate: 1.267E-04 | global batch size: 256 | lm loss: 3.096074E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.903 | TFLOPs: 29.26 | +7: iteration 9630/ 21553 | consumed samples: 2465280 | consumed tokens: 5048893440 | elapsed time per iteration (s): 0.31 | learning rate: 1.265E-04 | global batch size: 256 | lm loss: 3.085293E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.650 | TFLOPs: 29.22 | +7: iteration 9640/ 21553 | consumed samples: 2467840 | consumed tokens: 5054136320 | elapsed time per iteration (s): 0.31 | learning rate: 1.264E-04 | global batch size: 256 | lm loss: 3.084707E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.438 | TFLOPs: 29.21 | +7: iteration 9650/ 21553 | consumed samples: 2470400 | consumed tokens: 5059379200 | elapsed time per iteration (s): 0.30 | learning rate: 1.263E-04 | global batch size: 256 | lm loss: 3.083501E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.089 | TFLOPs: 29.44 | +7: iteration 9660/ 21553 | consumed samples: 2472960 | consumed tokens: 5064622080 | elapsed time per iteration (s): 0.31 | learning rate: 1.261E-04 | global batch size: 256 | lm loss: 3.075879E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.725 | TFLOPs: 29.36 | +7: iteration 9670/ 21553 | consumed samples: 2475520 | consumed tokens: 5069864960 | elapsed time per iteration (s): 0.30 | learning rate: 1.260E-04 | global batch size: 256 | lm loss: 3.081546E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.126 | TFLOPs: 29.52 | +7: iteration 9680/ 21553 | consumed samples: 2478080 | consumed tokens: 5075107840 | elapsed time per iteration (s): 0.31 | learning rate: 1.259E-04 | global batch size: 256 | lm loss: 3.044185E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.914 | TFLOPs: 28.56 | +7: iteration 9690/ 21553 | consumed samples: 2480640 | consumed tokens: 5080350720 | elapsed time per iteration (s): 0.31 | learning rate: 1.257E-04 | global batch size: 256 | lm loss: 3.092056E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.017 | TFLOPs: 29.20 | +7: iteration 9700/ 21553 | consumed samples: 2483200 | consumed tokens: 5085593600 | elapsed time per iteration (s): 0.31 | learning rate: 1.256E-04 | global batch size: 256 | lm loss: 3.066213E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.100 | TFLOPs: 28.92 | +7: iteration 9710/ 21553 | consumed samples: 2485760 | consumed tokens: 5090836480 | elapsed time per iteration (s): 0.31 | learning rate: 1.255E-04 | global batch size: 256 | lm loss: 3.100401E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.828 | TFLOPs: 29.05 | +7: iteration 9720/ 21553 | consumed samples: 2488320 | consumed tokens: 5096079360 | elapsed time per iteration (s): 0.31 | learning rate: 1.254E-04 | global batch size: 256 | lm loss: 3.066273E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.602 | TFLOPs: 29.22 | +7: iteration 9730/ 21553 | consumed samples: 2490880 | consumed tokens: 5101322240 | elapsed time per iteration (s): 0.34 | learning rate: 1.252E-04 | global batch size: 256 | lm loss: 3.084021E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 756.985 | TFLOPs: 26.50 | +7: iteration 9740/ 21553 | consumed samples: 2493440 | consumed tokens: 5106565120 | elapsed time per iteration (s): 0.31 | learning rate: 1.251E-04 | global batch size: 256 | lm loss: 3.046315E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.142 | TFLOPs: 29.27 | +7: iteration 9750/ 21553 | consumed samples: 2496000 | consumed tokens: 5111808000 | elapsed time per iteration (s): 0.31 | learning rate: 1.250E-04 | global batch size: 256 | lm loss: 3.099731E+00 | grad norm: 0.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.908 | TFLOPs: 29.05 | +7: iteration 9760/ 21553 | consumed samples: 2498560 | consumed tokens: 5117050880 | elapsed time per iteration (s): 0.31 | learning rate: 1.248E-04 | global batch size: 256 | lm loss: 3.105150E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.998 | TFLOPs: 28.92 | +7: iteration 9770/ 21553 | consumed samples: 2501120 | consumed tokens: 5122293760 | elapsed time per iteration (s): 0.31 | learning rate: 1.247E-04 | global batch size: 256 | lm loss: 3.074568E+00 | grad norm: 0.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.555 | TFLOPs: 28.94 | +7: iteration 9780/ 21553 | consumed samples: 2503680 | consumed tokens: 5127536640 | elapsed time per iteration (s): 0.31 | learning rate: 1.246E-04 | global batch size: 256 | lm loss: 3.065738E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.599 | TFLOPs: 28.90 | +7: iteration 9790/ 21553 | consumed samples: 2506240 | consumed tokens: 5132779520 | elapsed time per iteration (s): 0.30 | learning rate: 1.244E-04 | global batch size: 256 | lm loss: 3.084377E+00 | grad norm: 0.385 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.223 | TFLOPs: 29.41 | +7: iteration 9800/ 21553 | consumed samples: 2508800 | consumed tokens: 5138022400 | elapsed time per iteration (s): 0.31 | learning rate: 1.243E-04 | global batch size: 256 | lm loss: 3.095651E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.711 | TFLOPs: 28.84 | +7: iteration 9810/ 21553 | consumed samples: 2511360 | consumed tokens: 5143265280 | elapsed time per iteration (s): 0.31 | learning rate: 1.242E-04 | global batch size: 256 | lm loss: 3.063469E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.125 | TFLOPs: 29.38 | +7: iteration 9820/ 21553 | consumed samples: 2513920 | consumed tokens: 5148508160 | elapsed time per iteration (s): 0.32 | learning rate: 1.240E-04 | global batch size: 256 | lm loss: 3.062999E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.795 | TFLOPs: 28.42 | +7: iteration 9830/ 21553 | consumed samples: 2516480 | consumed tokens: 5153751040 | elapsed time per iteration (s): 0.31 | learning rate: 1.239E-04 | global batch size: 256 | lm loss: 3.068647E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.024 | TFLOPs: 29.34 | +7: iteration 9840/ 21553 | consumed samples: 2519040 | consumed tokens: 5158993920 | elapsed time per iteration (s): 0.31 | learning rate: 1.238E-04 | global batch size: 256 | lm loss: 3.097772E+00 | grad norm: 0.438 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.618 | TFLOPs: 29.04 | +7: iteration 9850/ 21553 | consumed samples: 2521600 | consumed tokens: 5164236800 | elapsed time per iteration (s): 0.31 | learning rate: 1.237E-04 | global batch size: 256 | lm loss: 3.066786E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.622 | TFLOPs: 29.29 | +7: iteration 9860/ 21553 | consumed samples: 2524160 | consumed tokens: 5169479680 | elapsed time per iteration (s): 0.30 | learning rate: 1.235E-04 | global batch size: 256 | lm loss: 3.044129E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.529 | TFLOPs: 29.53 | +7: iteration 9870/ 21553 | consumed samples: 2526720 | consumed tokens: 5174722560 | elapsed time per iteration (s): 0.30 | learning rate: 1.234E-04 | global batch size: 256 | lm loss: 3.068626E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 846.207 | TFLOPs: 29.62 | +7: iteration 9880/ 21553 | consumed samples: 2529280 | consumed tokens: 5179965440 | elapsed time per iteration (s): 0.33 | learning rate: 1.233E-04 | global batch size: 256 | lm loss: 3.087832E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 784.962 | TFLOPs: 27.48 | +7: iteration 9890/ 21553 | consumed samples: 2531840 | consumed tokens: 5185208320 | elapsed time per iteration (s): 0.33 | learning rate: 1.231E-04 | global batch size: 256 | lm loss: 3.089837E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 783.282 | TFLOPs: 27.42 | +7: iteration 9900/ 21553 | consumed samples: 2534400 | consumed tokens: 5190451200 | elapsed time per iteration (s): 0.31 | learning rate: 1.230E-04 | global batch size: 256 | lm loss: 3.095751E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.820 | TFLOPs: 29.15 | +7: iteration 9910/ 21553 | consumed samples: 2536960 | consumed tokens: 5195694080 | elapsed time per iteration (s): 0.31 | learning rate: 1.229E-04 | global batch size: 256 | lm loss: 3.101421E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.417 | TFLOPs: 29.18 | +7: iteration 9920/ 21553 | consumed samples: 2539520 | consumed tokens: 5200936960 | elapsed time per iteration (s): 0.30 | learning rate: 1.227E-04 | global batch size: 256 | lm loss: 3.070117E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.090 | TFLOPs: 29.41 | +7: iteration 9930/ 21553 | consumed samples: 2542080 | consumed tokens: 5206179840 | elapsed time per iteration (s): 0.31 | learning rate: 1.226E-04 | global batch size: 256 | lm loss: 3.078450E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.851 | TFLOPs: 28.70 | +7: iteration 9940/ 21553 | consumed samples: 2544640 | consumed tokens: 5211422720 | elapsed time per iteration (s): 0.31 | learning rate: 1.225E-04 | global batch size: 256 | lm loss: 3.085127E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.825 | TFLOPs: 28.45 | +7: iteration 9950/ 21553 | consumed samples: 2547200 | consumed tokens: 5216665600 | elapsed time per iteration (s): 0.31 | learning rate: 1.223E-04 | global batch size: 256 | lm loss: 3.091592E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.710 | TFLOPs: 29.29 | +7: iteration 9960/ 21553 | consumed samples: 2549760 | consumed tokens: 5221908480 | elapsed time per iteration (s): 0.31 | learning rate: 1.222E-04 | global batch size: 256 | lm loss: 3.082697E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.577 | TFLOPs: 29.29 | +7: iteration 9970/ 21553 | consumed samples: 2552320 | consumed tokens: 5227151360 | elapsed time per iteration (s): 0.30 | learning rate: 1.221E-04 | global batch size: 256 | lm loss: 3.070135E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 847.606 | TFLOPs: 29.67 | +7: iteration 9980/ 21553 | consumed samples: 2554880 | consumed tokens: 5232394240 | elapsed time per iteration (s): 0.31 | learning rate: 1.219E-04 | global batch size: 256 | lm loss: 3.051276E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.336 | TFLOPs: 29.14 | +7: iteration 9990/ 21553 | consumed samples: 2557440 | consumed tokens: 5237637120 | elapsed time per iteration (s): 0.30 | learning rate: 1.218E-04 | global batch size: 256 | lm loss: 3.083332E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.708 | TFLOPs: 29.47 | +0: [2022-11-29 17:59:17,204] [INFO] [logging.py:68:log_dist] [Rank 0] step=10000, skipped=0, lr=[0.00012168458711439383, 0.00012168458711439383, 0.00012168458711439383], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 10000/ 21553 | consumed samples: 2560000 | consumed tokens: 5242880000 | elapsed time per iteration (s): 0.31 | learning rate: 1.217E-04 | global batch size: 256 | lm loss: 3.088405E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.840 | TFLOPs: 29.16 | +0: steps: 10000 loss: 3.0901 iter time (s): 0.307 samples/sec: 832.971 +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 10000 | lm loss value: 2.969868E+00 | lm loss PPL: 1.948935E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 10000 to checkpoints_146moscareap +0: [2022-11-29 17:59:17,338] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step10000 is begin to save! +0: [2022-11-29 17:59:17,342] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:59:17,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:59:17,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:59:17,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:59:17,444] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:59:17,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:59:17,460] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:59:17,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:59:17,476] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:59:17,491] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:59:17,491] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:59:17,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:59:17,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:59:17,522] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:59:17,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:59:17,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:59:17,538] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:59:17,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:59:17,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:59:17,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:59:17,569] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:59:17,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:59:17,584] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:59:17,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:59:17,599] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:59:17,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:59:17,615] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:59:17,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:59:17,630] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:59:17,645] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:59:17,645] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:59:17,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:59:17,661] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:59:17,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:59:17,662] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_146moscareap/global_step10000/mp_rank_00_model_states.pt +0: [2022-11-29 17:59:17,662] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:59:17,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:59:17,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:59:17,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:59:17,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:59:17,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:59:17,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 17:59:17,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:59:17,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:59:17,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +1: [2022-11-29 17:59:17,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +6: [2022-11-29 17:59:17,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 17:59:17,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 17:59:17,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:59:17,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:59:17,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 17:59:17,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:59:17,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:59:17,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 17:59:17,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:59:17,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:59:17,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 17:59:17,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:59:17,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:59:17,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 17:59:17,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:59:17,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:59:17,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 17:59:17,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:59:17,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:59:17,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 17:59:17,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:59:17,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:59:17,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 17:59:17,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:59:17,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:59:17,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:59:17,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +2: [2022-11-29 17:59:17,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +4: [2022-11-29 17:59:17,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 17:59:17,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +2: [2022-11-29 17:59:17,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 17:59:17,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 17:59:17,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:59:17,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:59:17,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 17:59:17,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:59:17,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:59:17,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:59:17,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:59:17,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +2: [2022-11-29 17:59:17,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +3: [2022-11-29 17:59:17,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 17:59:17,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 17:59:17,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 17:59:17,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:59:17,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:59:17,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 17:59:17,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:59:17,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:59:17,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 17:59:17,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:59:17,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:59:17,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:59:17,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 17:59:17,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:59:17,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 17:59:17,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:59:17,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:59:17,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +4: [2022-11-29 17:59:17,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +1: [2022-11-29 17:59:17,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 17:59:17,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 17:59:17,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:59:17,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:59:17,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 17:59:17,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:59:17,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:59:17,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +5: [2022-11-29 17:59:17,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:59:17,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +0: [2022-11-29 17:59:17,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 17:59:17,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 17:59:17,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:59:17,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 17:59:17,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:59:17,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:59:17,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +4: [2022-11-29 17:59:17,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +2: [2022-11-29 17:59:17,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 17:59:17,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 17:59:17,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:59:17,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:59:17,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 17:59:17,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:59:17,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:59:17,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 17:59:17,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:59:17,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:59:17,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:59:17,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:59:17,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 17:59:17,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 17:59:17,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:59:17,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:59:17,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 17:59:17,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:59:17,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:59:17,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 17:59:17,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:59:17,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:59:17,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:59:17,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:59:17,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:59:17,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:59:17,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 17:59:17,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 17:59:17,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 17:59:17,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:59:17,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:59:17,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 17:59:17,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:59:17,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:59:17,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 17:59:17,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:59:17,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:59:17,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 17:59:17,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:59:17,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +5: [2022-11-29 17:59:17,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:59:17,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +6: [2022-11-29 17:59:17,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 17:59:17,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:59:17,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 17:59:17,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:59:17,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 17:59:17,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:59:17,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:59:17,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +1: [2022-11-29 17:59:17,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:59:17,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:59:17,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 17:59:17,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +1: [2022-11-29 17:59:17,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +4: [2022-11-29 17:59:17,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 17:59:17,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:59:17,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 17:59:17,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 17:59:17,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:59:17,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:59:17,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 17:59:17,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:59:17,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +4: [2022-11-29 17:59:17,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:59:17,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 17:59:17,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:59:17,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:59:17,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:59:17,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 17:59:17,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 17:59:17,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:59:17,727] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:59:17,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 17:59:17,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:59:17,727] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:59:17,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 17:59:17,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:59:17,728] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:59:17,728] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 17:59:17,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:59:17,728] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:59:17,728] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 17:59:17,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:59:17,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:59:17,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 17:59:17,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:59:17,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:59:17,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +2: [2022-11-29 17:59:17,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +7: [2022-11-29 17:59:17,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 17:59:17,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 17:59:17,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:59:17,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:59:17,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 17:59:17,731] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:59:17,731] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:59:17,731] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 17:59:17,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:59:17,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:59:17,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 17:59:17,733] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:59:17,733] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:59:17,733] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 17:59:17,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:59:17,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: successfully saved checkpoint at iteration 10000 to checkpoints_146moscareap +7: time (ms) | save-checkpoint: 406.69 +7: iteration 10010/ 21553 | consumed samples: 2562560 | consumed tokens: 5248122880 | elapsed time per iteration (s): 0.36 | learning rate: 1.216E-04 | global batch size: 256 | lm loss: 3.101935E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 716.314 | TFLOPs: 25.08 | +7: iteration 10020/ 21553 | consumed samples: 2565120 | consumed tokens: 5253365760 | elapsed time per iteration (s): 0.31 | learning rate: 1.214E-04 | global batch size: 256 | lm loss: 3.051731E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.697 | TFLOPs: 29.15 | +7: iteration 10030/ 21553 | consumed samples: 2567680 | consumed tokens: 5258608640 | elapsed time per iteration (s): 0.31 | learning rate: 1.213E-04 | global batch size: 256 | lm loss: 3.084822E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.231 | TFLOPs: 29.17 | +7: iteration 10040/ 21553 | consumed samples: 2570240 | consumed tokens: 5263851520 | elapsed time per iteration (s): 0.30 | learning rate: 1.212E-04 | global batch size: 256 | lm loss: 3.097530E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.160 | TFLOPs: 29.52 | +7: iteration 10050/ 21553 | consumed samples: 2572800 | consumed tokens: 5269094400 | elapsed time per iteration (s): 0.30 | learning rate: 1.210E-04 | global batch size: 256 | lm loss: 3.062292E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 849.751 | TFLOPs: 29.75 | +7: iteration 10060/ 21553 | consumed samples: 2575360 | consumed tokens: 5274337280 | elapsed time per iteration (s): 0.33 | learning rate: 1.209E-04 | global batch size: 256 | lm loss: 3.092615E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 773.566 | TFLOPs: 27.08 | +7: iteration 10070/ 21553 | consumed samples: 2577920 | consumed tokens: 5279580160 | elapsed time per iteration (s): 0.31 | learning rate: 1.208E-04 | global batch size: 256 | lm loss: 3.081256E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.332 | TFLOPs: 29.10 | +7: iteration 10080/ 21553 | consumed samples: 2580480 | consumed tokens: 5284823040 | elapsed time per iteration (s): 0.30 | learning rate: 1.206E-04 | global batch size: 256 | lm loss: 3.067495E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.709 | TFLOPs: 29.61 | +7: iteration 10090/ 21553 | consumed samples: 2583040 | consumed tokens: 5290065920 | elapsed time per iteration (s): 0.31 | learning rate: 1.205E-04 | global batch size: 256 | lm loss: 3.064496E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.636 | TFLOPs: 29.11 | +7: iteration 10100/ 21553 | consumed samples: 2585600 | consumed tokens: 5295308800 | elapsed time per iteration (s): 0.31 | learning rate: 1.204E-04 | global batch size: 256 | lm loss: 3.042019E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.551 | TFLOPs: 28.59 | +7: iteration 10110/ 21553 | consumed samples: 2588160 | consumed tokens: 5300551680 | elapsed time per iteration (s): 0.31 | learning rate: 1.202E-04 | global batch size: 256 | lm loss: 3.077037E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.157 | TFLOPs: 28.47 | +7: iteration 10120/ 21553 | consumed samples: 2590720 | consumed tokens: 5305794560 | elapsed time per iteration (s): 0.30 | learning rate: 1.201E-04 | global batch size: 256 | lm loss: 3.074398E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 846.040 | TFLOPs: 29.62 | +7: iteration 10130/ 21553 | consumed samples: 2593280 | consumed tokens: 5311037440 | elapsed time per iteration (s): 0.30 | learning rate: 1.200E-04 | global batch size: 256 | lm loss: 3.066319E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 844.217 | TFLOPs: 29.55 | +7: iteration 10140/ 21553 | consumed samples: 2595840 | consumed tokens: 5316280320 | elapsed time per iteration (s): 0.31 | learning rate: 1.198E-04 | global batch size: 256 | lm loss: 3.080775E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.635 | TFLOPs: 29.29 | +7: iteration 10150/ 21553 | consumed samples: 2598400 | consumed tokens: 5321523200 | elapsed time per iteration (s): 0.30 | learning rate: 1.197E-04 | global batch size: 256 | lm loss: 3.091616E+00 | grad norm: 0.394 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.320 | TFLOPs: 29.45 | +7: iteration 10160/ 21553 | consumed samples: 2600960 | consumed tokens: 5326766080 | elapsed time per iteration (s): 0.31 | learning rate: 1.196E-04 | global batch size: 256 | lm loss: 3.112759E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.409 | TFLOPs: 28.65 | +7: iteration 10170/ 21553 | consumed samples: 2603520 | consumed tokens: 5332008960 | elapsed time per iteration (s): 0.31 | learning rate: 1.194E-04 | global batch size: 256 | lm loss: 3.098215E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.609 | TFLOPs: 29.32 | +7: iteration 10180/ 21553 | consumed samples: 2606080 | consumed tokens: 5337251840 | elapsed time per iteration (s): 0.31 | learning rate: 1.193E-04 | global batch size: 256 | lm loss: 3.062722E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.745 | TFLOPs: 28.52 | +7: iteration 10190/ 21553 | consumed samples: 2608640 | consumed tokens: 5342494720 | elapsed time per iteration (s): 0.31 | learning rate: 1.192E-04 | global batch size: 256 | lm loss: 3.074955E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.254 | TFLOPs: 28.82 | +7: iteration 10200/ 21553 | consumed samples: 2611200 | consumed tokens: 5347737600 | elapsed time per iteration (s): 0.31 | learning rate: 1.191E-04 | global batch size: 256 | lm loss: 3.076324E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.672 | TFLOPs: 28.90 | +7: iteration 10210/ 21553 | consumed samples: 2613760 | consumed tokens: 5352980480 | elapsed time per iteration (s): 0.39 | learning rate: 1.189E-04 | global batch size: 256 | lm loss: 3.053612E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 656.370 | TFLOPs: 22.98 | +7: iteration 10220/ 21553 | consumed samples: 2616320 | consumed tokens: 5358223360 | elapsed time per iteration (s): 0.32 | learning rate: 1.188E-04 | global batch size: 256 | lm loss: 3.068676E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.729 | TFLOPs: 28.31 | +7: iteration 10230/ 21553 | consumed samples: 2618880 | consumed tokens: 5363466240 | elapsed time per iteration (s): 0.31 | learning rate: 1.187E-04 | global batch size: 256 | lm loss: 3.086082E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.557 | TFLOPs: 28.90 | +7: iteration 10240/ 21553 | consumed samples: 2621440 | consumed tokens: 5368709120 | elapsed time per iteration (s): 0.31 | learning rate: 1.185E-04 | global batch size: 256 | lm loss: 3.076619E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.736 | TFLOPs: 29.15 | +7: iteration 10250/ 21553 | consumed samples: 2624000 | consumed tokens: 5373952000 | elapsed time per iteration (s): 0.31 | learning rate: 1.184E-04 | global batch size: 256 | lm loss: 3.069819E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.080 | TFLOPs: 29.23 | +7: iteration 10260/ 21553 | consumed samples: 2626560 | consumed tokens: 5379194880 | elapsed time per iteration (s): 0.31 | learning rate: 1.183E-04 | global batch size: 256 | lm loss: 3.060173E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.266 | TFLOPs: 29.10 | +7: iteration 10270/ 21553 | consumed samples: 2629120 | consumed tokens: 5384437760 | elapsed time per iteration (s): 0.31 | learning rate: 1.181E-04 | global batch size: 256 | lm loss: 3.069637E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.058 | TFLOPs: 29.34 | +7: iteration 10280/ 21553 | consumed samples: 2631680 | consumed tokens: 5389680640 | elapsed time per iteration (s): 0.31 | learning rate: 1.180E-04 | global batch size: 256 | lm loss: 3.045089E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.227 | TFLOPs: 29.31 | +7: iteration 10290/ 21553 | consumed samples: 2634240 | consumed tokens: 5394923520 | elapsed time per iteration (s): 0.35 | learning rate: 1.179E-04 | global batch size: 256 | lm loss: 3.051491E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 724.094 | TFLOPs: 25.35 | +7: iteration 10300/ 21553 | consumed samples: 2636800 | consumed tokens: 5400166400 | elapsed time per iteration (s): 0.33 | learning rate: 1.177E-04 | global batch size: 256 | lm loss: 3.056728E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 777.553 | TFLOPs: 27.22 | +7: iteration 10310/ 21553 | consumed samples: 2639360 | consumed tokens: 5405409280 | elapsed time per iteration (s): 0.31 | learning rate: 1.176E-04 | global batch size: 256 | lm loss: 3.073452E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.717 | TFLOPs: 29.01 | +7: iteration 10320/ 21553 | consumed samples: 2641920 | consumed tokens: 5410652160 | elapsed time per iteration (s): 0.33 | learning rate: 1.175E-04 | global batch size: 256 | lm loss: 3.103901E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 784.048 | TFLOPs: 27.45 | +7: iteration 10330/ 21553 | consumed samples: 2644480 | consumed tokens: 5415895040 | elapsed time per iteration (s): 0.31 | learning rate: 1.173E-04 | global batch size: 256 | lm loss: 3.075531E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.532 | TFLOPs: 28.72 | +7: iteration 10340/ 21553 | consumed samples: 2647040 | consumed tokens: 5421137920 | elapsed time per iteration (s): 0.35 | learning rate: 1.172E-04 | global batch size: 256 | lm loss: 3.080236E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 733.584 | TFLOPs: 25.68 | +7: iteration 10350/ 21553 | consumed samples: 2649600 | consumed tokens: 5426380800 | elapsed time per iteration (s): 0.89 | learning rate: 1.171E-04 | global batch size: 256 | lm loss: 3.089172E+00 | grad norm: 0.407 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 286.972 | TFLOPs: 10.05 | +7: iteration 10360/ 21553 | consumed samples: 2652160 | consumed tokens: 5431623680 | elapsed time per iteration (s): 0.31 | learning rate: 1.169E-04 | global batch size: 256 | lm loss: 3.086770E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.335 | TFLOPs: 28.61 | +7: iteration 10370/ 21553 | consumed samples: 2654720 | consumed tokens: 5436866560 | elapsed time per iteration (s): 0.31 | learning rate: 1.168E-04 | global batch size: 256 | lm loss: 3.072936E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.034 | TFLOPs: 29.20 | +7: iteration 10380/ 21553 | consumed samples: 2657280 | consumed tokens: 5442109440 | elapsed time per iteration (s): 0.32 | learning rate: 1.167E-04 | global batch size: 256 | lm loss: 3.059031E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 794.407 | TFLOPs: 27.81 | +7: iteration 10390/ 21553 | consumed samples: 2659840 | consumed tokens: 5447352320 | elapsed time per iteration (s): 0.31 | learning rate: 1.165E-04 | global batch size: 256 | lm loss: 3.094077E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.509 | TFLOPs: 28.90 | +7: iteration 10400/ 21553 | consumed samples: 2662400 | consumed tokens: 5452595200 | elapsed time per iteration (s): 0.30 | learning rate: 1.164E-04 | global batch size: 256 | lm loss: 3.068248E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.595 | TFLOPs: 29.46 | +7: iteration 10410/ 21553 | consumed samples: 2664960 | consumed tokens: 5457838080 | elapsed time per iteration (s): 0.31 | learning rate: 1.163E-04 | global batch size: 256 | lm loss: 3.082508E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.172 | TFLOPs: 29.38 | +7: iteration 10420/ 21553 | consumed samples: 2667520 | consumed tokens: 5463080960 | elapsed time per iteration (s): 0.30 | learning rate: 1.161E-04 | global batch size: 256 | lm loss: 3.066338E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.184 | TFLOPs: 29.45 | +7: iteration 10430/ 21553 | consumed samples: 2670080 | consumed tokens: 5468323840 | elapsed time per iteration (s): 0.31 | learning rate: 1.160E-04 | global batch size: 256 | lm loss: 3.049464E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.347 | TFLOPs: 28.79 | +7: iteration 10440/ 21553 | consumed samples: 2672640 | consumed tokens: 5473566720 | elapsed time per iteration (s): 0.31 | learning rate: 1.159E-04 | global batch size: 256 | lm loss: 3.086033E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.427 | TFLOPs: 28.55 | +7: iteration 10450/ 21553 | consumed samples: 2675200 | consumed tokens: 5478809600 | elapsed time per iteration (s): 0.31 | learning rate: 1.158E-04 | global batch size: 256 | lm loss: 3.047740E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.376 | TFLOPs: 29.35 | +7: iteration 10460/ 21553 | consumed samples: 2677760 | consumed tokens: 5484052480 | elapsed time per iteration (s): 0.31 | learning rate: 1.156E-04 | global batch size: 256 | lm loss: 3.077335E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.211 | TFLOPs: 28.50 | +7: iteration 10470/ 21553 | consumed samples: 2680320 | consumed tokens: 5489295360 | elapsed time per iteration (s): 0.32 | learning rate: 1.155E-04 | global batch size: 256 | lm loss: 3.043403E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 802.557 | TFLOPs: 28.10 | +7: iteration 10480/ 21553 | consumed samples: 2682880 | consumed tokens: 5494538240 | elapsed time per iteration (s): 0.31 | learning rate: 1.154E-04 | global batch size: 256 | lm loss: 3.047260E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.465 | TFLOPs: 29.11 | +7: iteration 10490/ 21553 | consumed samples: 2685440 | consumed tokens: 5499781120 | elapsed time per iteration (s): 0.33 | learning rate: 1.152E-04 | global batch size: 256 | lm loss: 3.099412E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 782.743 | TFLOPs: 27.40 | +7: iteration 10500/ 21553 | consumed samples: 2688000 | consumed tokens: 5505024000 | elapsed time per iteration (s): 0.35 | learning rate: 1.151E-04 | global batch size: 256 | lm loss: 3.078673E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 726.247 | TFLOPs: 25.42 | +7: iteration 10510/ 21553 | consumed samples: 2690560 | consumed tokens: 5510266880 | elapsed time per iteration (s): 0.34 | learning rate: 1.150E-04 | global batch size: 256 | lm loss: 3.088224E+00 | grad norm: 1.465 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 751.935 | TFLOPs: 26.32 | +7: iteration 10520/ 21553 | consumed samples: 2693120 | consumed tokens: 5515509760 | elapsed time per iteration (s): 0.32 | learning rate: 1.148E-04 | global batch size: 256 | lm loss: 3.087441E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 790.028 | TFLOPs: 27.66 | +7: iteration 10530/ 21553 | consumed samples: 2695680 | consumed tokens: 5520752640 | elapsed time per iteration (s): 0.31 | learning rate: 1.147E-04 | global batch size: 256 | lm loss: 3.062491E+00 | grad norm: 0.502 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.437 | TFLOPs: 29.18 | +7: iteration 10540/ 21553 | consumed samples: 2698240 | consumed tokens: 5525995520 | elapsed time per iteration (s): 0.31 | learning rate: 1.146E-04 | global batch size: 256 | lm loss: 3.036097E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.970 | TFLOPs: 28.84 | +7: iteration 10550/ 21553 | consumed samples: 2700800 | consumed tokens: 5531238400 | elapsed time per iteration (s): 0.30 | learning rate: 1.144E-04 | global batch size: 256 | lm loss: 3.067878E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.357 | TFLOPs: 29.59 | +7: iteration 10560/ 21553 | consumed samples: 2703360 | consumed tokens: 5536481280 | elapsed time per iteration (s): 0.30 | learning rate: 1.143E-04 | global batch size: 256 | lm loss: 3.015424E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 850.307 | TFLOPs: 29.77 | +7: iteration 10570/ 21553 | consumed samples: 2705920 | consumed tokens: 5541724160 | elapsed time per iteration (s): 0.31 | learning rate: 1.142E-04 | global batch size: 256 | lm loss: 3.084960E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.636 | TFLOPs: 29.22 | +7: iteration 10580/ 21553 | consumed samples: 2708480 | consumed tokens: 5546967040 | elapsed time per iteration (s): 0.30 | learning rate: 1.140E-04 | global batch size: 256 | lm loss: 3.098063E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.483 | TFLOPs: 29.49 | +7: iteration 10590/ 21553 | consumed samples: 2711040 | consumed tokens: 5552209920 | elapsed time per iteration (s): 0.30 | learning rate: 1.139E-04 | global batch size: 256 | lm loss: 3.046699E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 847.444 | TFLOPs: 29.67 | +7: iteration 10600/ 21553 | consumed samples: 2713600 | consumed tokens: 5557452800 | elapsed time per iteration (s): 0.31 | learning rate: 1.138E-04 | global batch size: 256 | lm loss: 3.097034E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.631 | TFLOPs: 29.18 | +7: iteration 10610/ 21553 | consumed samples: 2716160 | consumed tokens: 5562695680 | elapsed time per iteration (s): 0.43 | learning rate: 1.136E-04 | global batch size: 256 | lm loss: 3.076894E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.748 | TFLOPs: 20.82 | +7: iteration 10620/ 21553 | consumed samples: 2718720 | consumed tokens: 5567938560 | elapsed time per iteration (s): 0.33 | learning rate: 1.135E-04 | global batch size: 256 | lm loss: 3.040316E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 783.405 | TFLOPs: 27.42 | +7: iteration 10630/ 21553 | consumed samples: 2721280 | consumed tokens: 5573181440 | elapsed time per iteration (s): 0.35 | learning rate: 1.134E-04 | global batch size: 256 | lm loss: 3.045639E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 725.142 | TFLOPs: 25.39 | +7: iteration 10640/ 21553 | consumed samples: 2723840 | consumed tokens: 5578424320 | elapsed time per iteration (s): 0.33 | learning rate: 1.132E-04 | global batch size: 256 | lm loss: 3.052464E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 780.842 | TFLOPs: 27.34 | +7: iteration 10650/ 21553 | consumed samples: 2726400 | consumed tokens: 5583667200 | elapsed time per iteration (s): 0.52 | learning rate: 1.131E-04 | global batch size: 256 | lm loss: 3.056431E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 493.110 | TFLOPs: 17.26 | +7: iteration 10660/ 21553 | consumed samples: 2728960 | consumed tokens: 5588910080 | elapsed time per iteration (s): 0.48 | learning rate: 1.130E-04 | global batch size: 256 | lm loss: 3.079240E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.774 | TFLOPs: 18.69 | +7: iteration 10670/ 21553 | consumed samples: 2731520 | consumed tokens: 5594152960 | elapsed time per iteration (s): 0.30 | learning rate: 1.128E-04 | global batch size: 256 | lm loss: 3.047467E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.163 | TFLOPs: 29.59 | +7: iteration 10680/ 21553 | consumed samples: 2734080 | consumed tokens: 5599395840 | elapsed time per iteration (s): 0.31 | learning rate: 1.127E-04 | global batch size: 256 | lm loss: 3.067389E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.365 | TFLOPs: 29.03 | +7: iteration 10690/ 21553 | consumed samples: 2736640 | consumed tokens: 5604638720 | elapsed time per iteration (s): 0.31 | learning rate: 1.126E-04 | global batch size: 256 | lm loss: 3.048284E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.362 | TFLOPs: 29.24 | +7: iteration 10700/ 21553 | consumed samples: 2739200 | consumed tokens: 5609881600 | elapsed time per iteration (s): 0.31 | learning rate: 1.124E-04 | global batch size: 256 | lm loss: 3.079243E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.054 | TFLOPs: 29.20 | +7: iteration 10710/ 21553 | consumed samples: 2741760 | consumed tokens: 5615124480 | elapsed time per iteration (s): 0.30 | learning rate: 1.123E-04 | global batch size: 256 | lm loss: 3.067163E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.598 | TFLOPs: 29.50 | +7: iteration 10720/ 21553 | consumed samples: 2744320 | consumed tokens: 5620367360 | elapsed time per iteration (s): 0.31 | learning rate: 1.122E-04 | global batch size: 256 | lm loss: 3.103101E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.094 | TFLOPs: 29.20 | +7: iteration 10730/ 21553 | consumed samples: 2746880 | consumed tokens: 5625610240 | elapsed time per iteration (s): 0.32 | learning rate: 1.120E-04 | global batch size: 256 | lm loss: 3.066851E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 800.365 | TFLOPs: 28.02 | +7: iteration 10740/ 21553 | consumed samples: 2749440 | consumed tokens: 5630853120 | elapsed time per iteration (s): 0.31 | learning rate: 1.119E-04 | global batch size: 256 | lm loss: 3.035206E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.095 | TFLOPs: 29.27 | +7: iteration 10750/ 21553 | consumed samples: 2752000 | consumed tokens: 5636096000 | elapsed time per iteration (s): 0.32 | learning rate: 1.118E-04 | global batch size: 256 | lm loss: 3.068476E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 806.033 | TFLOPs: 28.22 | +7: iteration 10760/ 21553 | consumed samples: 2754560 | consumed tokens: 5641338880 | elapsed time per iteration (s): 0.31 | learning rate: 1.116E-04 | global batch size: 256 | lm loss: 3.051572E+00 | grad norm: 0.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.171 | TFLOPs: 28.82 | +7: iteration 10770/ 21553 | consumed samples: 2757120 | consumed tokens: 5646581760 | elapsed time per iteration (s): 0.32 | learning rate: 1.115E-04 | global batch size: 256 | lm loss: 3.056680E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 806.380 | TFLOPs: 28.23 | +7: iteration 10780/ 21553 | consumed samples: 2759680 | consumed tokens: 5651824640 | elapsed time per iteration (s): 0.32 | learning rate: 1.114E-04 | global batch size: 256 | lm loss: 3.086518E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.193 | TFLOPs: 28.43 | +7: iteration 10790/ 21553 | consumed samples: 2762240 | consumed tokens: 5657067520 | elapsed time per iteration (s): 0.31 | learning rate: 1.112E-04 | global batch size: 256 | lm loss: 3.033735E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.114 | TFLOPs: 28.60 | +7: iteration 10800/ 21553 | consumed samples: 2764800 | consumed tokens: 5662310400 | elapsed time per iteration (s): 0.32 | learning rate: 1.111E-04 | global batch size: 256 | lm loss: 3.080284E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.713 | TFLOPs: 28.31 | +7: iteration 10810/ 21553 | consumed samples: 2767360 | consumed tokens: 5667553280 | elapsed time per iteration (s): 0.31 | learning rate: 1.110E-04 | global batch size: 256 | lm loss: 3.038464E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.874 | TFLOPs: 28.81 | +7: iteration 10820/ 21553 | consumed samples: 2769920 | consumed tokens: 5672796160 | elapsed time per iteration (s): 0.32 | learning rate: 1.109E-04 | global batch size: 256 | lm loss: 3.059774E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 809.639 | TFLOPs: 28.34 | +7: iteration 10830/ 21553 | consumed samples: 2772480 | consumed tokens: 5678039040 | elapsed time per iteration (s): 0.31 | learning rate: 1.107E-04 | global batch size: 256 | lm loss: 3.061313E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.229 | TFLOPs: 29.31 | +7: iteration 10840/ 21553 | consumed samples: 2775040 | consumed tokens: 5683281920 | elapsed time per iteration (s): 0.30 | learning rate: 1.106E-04 | global batch size: 256 | lm loss: 3.048903E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.385 | TFLOPs: 29.38 | +7: iteration 10850/ 21553 | consumed samples: 2777600 | consumed tokens: 5688524800 | elapsed time per iteration (s): 0.32 | learning rate: 1.105E-04 | global batch size: 256 | lm loss: 3.077213E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.065 | TFLOPs: 28.36 | +7: iteration 10860/ 21553 | consumed samples: 2780160 | consumed tokens: 5693767680 | elapsed time per iteration (s): 0.30 | learning rate: 1.103E-04 | global batch size: 256 | lm loss: 3.089554E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 846.858 | TFLOPs: 29.65 | +7: iteration 10870/ 21553 | consumed samples: 2782720 | consumed tokens: 5699010560 | elapsed time per iteration (s): 0.31 | learning rate: 1.102E-04 | global batch size: 256 | lm loss: 3.091503E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.348 | TFLOPs: 28.72 | +7: iteration 10880/ 21553 | consumed samples: 2785280 | consumed tokens: 5704253440 | elapsed time per iteration (s): 0.30 | learning rate: 1.101E-04 | global batch size: 256 | lm loss: 3.037291E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.002 | TFLOPs: 29.41 | +7: iteration 10890/ 21553 | consumed samples: 2787840 | consumed tokens: 5709496320 | elapsed time per iteration (s): 0.31 | learning rate: 1.099E-04 | global batch size: 256 | lm loss: 3.035063E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.913 | TFLOPs: 28.98 | +7: iteration 10900/ 21553 | consumed samples: 2790400 | consumed tokens: 5714739200 | elapsed time per iteration (s): 0.31 | learning rate: 1.098E-04 | global batch size: 256 | lm loss: 3.052606E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.340 | TFLOPs: 29.35 | +7: iteration 10910/ 21553 | consumed samples: 2792960 | consumed tokens: 5719982080 | elapsed time per iteration (s): 0.31 | learning rate: 1.097E-04 | global batch size: 256 | lm loss: 3.046585E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.763 | TFLOPs: 28.91 | +7: iteration 10920/ 21553 | consumed samples: 2795520 | consumed tokens: 5725224960 | elapsed time per iteration (s): 0.50 | learning rate: 1.095E-04 | global batch size: 256 | lm loss: 3.061488E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 508.073 | TFLOPs: 17.79 | +7: iteration 10930/ 21553 | consumed samples: 2798080 | consumed tokens: 5730467840 | elapsed time per iteration (s): 0.46 | learning rate: 1.094E-04 | global batch size: 256 | lm loss: 3.066928E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 555.976 | TFLOPs: 19.46 | +7: iteration 10940/ 21553 | consumed samples: 2800640 | consumed tokens: 5735710720 | elapsed time per iteration (s): 0.34 | learning rate: 1.093E-04 | global batch size: 256 | lm loss: 3.025098E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 744.719 | TFLOPs: 26.07 | +7: iteration 10950/ 21553 | consumed samples: 2803200 | consumed tokens: 5740953600 | elapsed time per iteration (s): 0.39 | learning rate: 1.091E-04 | global batch size: 256 | lm loss: 3.065198E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 652.084 | TFLOPs: 22.83 | +7: iteration 10960/ 21553 | consumed samples: 2805760 | consumed tokens: 5746196480 | elapsed time per iteration (s): 0.38 | learning rate: 1.090E-04 | global batch size: 256 | lm loss: 3.043441E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 678.276 | TFLOPs: 23.74 | +7: iteration 10970/ 21553 | consumed samples: 2808320 | consumed tokens: 5751439360 | elapsed time per iteration (s): 0.41 | learning rate: 1.089E-04 | global batch size: 256 | lm loss: 3.066739E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 631.033 | TFLOPs: 22.09 | +7: iteration 10980/ 21553 | consumed samples: 2810880 | consumed tokens: 5756682240 | elapsed time per iteration (s): 0.36 | learning rate: 1.087E-04 | global batch size: 256 | lm loss: 3.064581E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 702.403 | TFLOPs: 24.59 | +7: iteration 10990/ 21553 | consumed samples: 2813440 | consumed tokens: 5761925120 | elapsed time per iteration (s): 0.30 | learning rate: 1.086E-04 | global batch size: 256 | lm loss: 3.044945E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 848.324 | TFLOPs: 29.70 | +7: iteration 11000/ 21553 | consumed samples: 2816000 | consumed tokens: 5767168000 | elapsed time per iteration (s): 0.31 | learning rate: 1.085E-04 | global batch size: 256 | lm loss: 3.047306E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.482 | TFLOPs: 29.35 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 11000 | lm loss value: 2.978075E+00 | lm loss PPL: 1.964995E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 11000 to checkpoints_146moscareap +0: [2022-11-29 18:04:48,452] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step11000 is begin to save! +0: [2022-11-29 18:04:48,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:04:48,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:04:48,578] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:04:48,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:04:48,602] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:04:48,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:04:48,623] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:04:48,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:04:48,644] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:04:48,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:04:48,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:04:48,686] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:04:48,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:04:48,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:04:48,709] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:04:48,731] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:04:48,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:04:48,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:04:48,754] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:04:48,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:04:48,776] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:04:48,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:04:48,797] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/layer_13-model_00-model_states.pt... +0: [2022-11-29 18:04:48,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/layer_13-model_00-model_states.pt. +0: [2022-11-29 18:04:48,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:04:48,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:04:48,829] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/layer_15-model_00-model_states.pt... +0: [2022-11-29 18:04:48,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/layer_15-model_00-model_states.pt. +0: [2022-11-29 18:04:48,845] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/layer_16-model_00-model_states.pt... +0: [2022-11-29 18:04:48,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/layer_16-model_00-model_states.pt. +0: [2022-11-29 18:04:48,860] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/layer_17-model_00-model_states.pt... +0: [2022-11-29 18:04:48,876] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/layer_17-model_00-model_states.pt. +0: [2022-11-29 18:04:48,876] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/layer_19-model_00-model_states.pt... +0: [2022-11-29 18:04:48,877] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/layer_19-model_00-model_states.pt. +0: [2022-11-29 18:04:48,878] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_146moscareap/global_step11000/mp_rank_00_model_states.pt +0: [2022-11-29 18:04:48,878] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:04:48,880] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:04:48,899] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:04:48,899] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:04:48,899] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:04:48,899] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:04:48,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:04:48,930] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:04:48,931] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:04:48,931] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 18:04:48,932] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:04:48,932] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:04:48,932] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 18:04:48,933] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:04:48,933] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:04:48,933] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 18:04:48,933] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:04:48,934] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:04:48,934] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:04:48,934] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 18:04:48,934] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:04:48,934] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:04:48,934] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 18:04:48,935] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:04:48,935] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:04:48,935] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 18:04:48,935] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:04:48,935] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:04:48,935] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 18:04:48,935] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:04:48,935] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:04:48,935] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 18:04:48,935] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:04:48,936] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:04:48,936] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 18:04:48,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:04:48,936] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:04:48,936] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 18:04:48,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:04:48,936] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:04:48,936] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 18:04:48,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:04:48,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +1: [2022-11-29 18:04:48,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:04:48,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 18:04:48,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +4: [2022-11-29 18:04:48,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:04:48,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 18:04:48,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:04:48,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 18:04:48,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:04:48,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:04:48,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 18:04:48,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:04:48,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:04:48,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 18:04:48,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:04:48,938] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:04:48,938] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 18:04:48,938] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:04:48,938] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:04:48,938] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 18:04:48,938] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:04:48,938] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:04:48,938] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 18:04:48,939] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:04:48,939] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:04:48,939] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 18:04:48,939] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:04:48,939] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:04:48,939] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 18:04:48,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:04:48,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:04:48,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 18:04:48,939] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:04:48,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:04:48,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:04:48,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 18:04:48,939] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:04:48,939] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 18:04:48,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:04:48,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:04:48,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 18:04:48,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:04:48,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:04:48,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:04:48,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:04:48,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +6: [2022-11-29 18:04:48,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +0: [2022-11-29 18:04:48,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:04:48,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3: [2022-11-29 18:04:48,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 18:04:48,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 18:04:48,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 18:04:48,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 18:04:48,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:04:48,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:04:48,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:04:48,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:04:48,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:04:48,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:04:48,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 18:04:48,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 18:04:48,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 18:04:48,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:04:48,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:04:48,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 18:04:48,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:04:48,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:04:48,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 18:04:48,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:04:48,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:04:48,941] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +5: [2022-11-29 18:04:48,941] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +6: [2022-11-29 18:04:48,941] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 18:04:48,941] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 18:04:48,941] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:04:48,941] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:04:48,941] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +0: [2022-11-29 18:04:48,941] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +4: [2022-11-29 18:04:48,941] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 18:04:48,941] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 18:04:48,942] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:04:48,942] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:04:48,942] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +2: [2022-11-29 18:04:48,942] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +1: [2022-11-29 18:04:48,942] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 18:04:48,942] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 18:04:48,942] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:04:48,942] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:04:48,942] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:04:48,942] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:04:48,942] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:04:48,942] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 18:04:48,942] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 18:04:48,942] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:04:48,942] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 18:04:48,942] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:04:48,942] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:04:48,943] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 18:04:48,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:04:48,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:04:48,943] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +4: [2022-11-29 18:04:48,943] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +1: [2022-11-29 18:04:48,943] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 18:04:48,943] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 18:04:48,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:04:48,943] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:04:48,943] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 18:04:48,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:04:48,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:04:48,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:04:48,944] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:04:48,944] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:04:48,944] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 18:04:48,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:04:48,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:04:48,945] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +7: [2022-11-29 18:04:48,945] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +4: [2022-11-29 18:04:48,945] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 18:04:48,945] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 18:04:48,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:04:48,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:04:48,945] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:04:48,945] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:04:48,945] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 18:04:48,945] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 18:04:48,946] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:04:48,946] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:04:48,946] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 18:04:48,947] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:04:48,947] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:04:48,947] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:04:48,947] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:04:48,947] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 18:04:48,947] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 18:04:48,949] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:04:48,949] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:04:48,950] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 18:04:48,952] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:04:48,953] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:04:48,953] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 18:04:48,944] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:04:48,944] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:04:48,944] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:04:48,944] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 18:04:48,944] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 18:04:48,944] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 18:04:48,944] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:04:48,944] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:04:48,944] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 18:04:48,948] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:04:48,948] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:04:48,948] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 18:04:48,954] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:04:48,954] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:04:48,954] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 18:04:48,956] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step11000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:04:48,956] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: successfully saved checkpoint at iteration 11000 to checkpoints_146moscareap +7: time (ms) | save-checkpoint: 513.68 +7: iteration 11010/ 21553 | consumed samples: 2818560 | consumed tokens: 5772410880 | elapsed time per iteration (s): 0.37 | learning rate: 1.083E-04 | global batch size: 256 | lm loss: 3.042699E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 698.191 | TFLOPs: 24.44 | +7: iteration 11020/ 21553 | consumed samples: 2821120 | consumed tokens: 5777653760 | elapsed time per iteration (s): 0.31 | learning rate: 1.082E-04 | global batch size: 256 | lm loss: 3.036406E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.578 | TFLOPs: 28.87 | +7: iteration 11030/ 21553 | consumed samples: 2823680 | consumed tokens: 5782896640 | elapsed time per iteration (s): 0.31 | learning rate: 1.081E-04 | global batch size: 256 | lm loss: 3.062807E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.971 | TFLOPs: 28.77 | +7: iteration 11040/ 21553 | consumed samples: 2826240 | consumed tokens: 5788139520 | elapsed time per iteration (s): 0.31 | learning rate: 1.079E-04 | global batch size: 256 | lm loss: 3.074957E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.749 | TFLOPs: 28.91 | +7: iteration 11050/ 21553 | consumed samples: 2828800 | consumed tokens: 5793382400 | elapsed time per iteration (s): 0.31 | learning rate: 1.078E-04 | global batch size: 256 | lm loss: 3.047575E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.651 | TFLOPs: 29.08 | +7: iteration 11060/ 21553 | consumed samples: 2831360 | consumed tokens: 5798625280 | elapsed time per iteration (s): 0.31 | learning rate: 1.077E-04 | global batch size: 256 | lm loss: 3.069536E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.559 | TFLOPs: 29.18 | +7: iteration 11070/ 21553 | consumed samples: 2833920 | consumed tokens: 5803868160 | elapsed time per iteration (s): 0.31 | learning rate: 1.075E-04 | global batch size: 256 | lm loss: 3.067053E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.998 | TFLOPs: 29.27 | +7: iteration 11080/ 21553 | consumed samples: 2836480 | consumed tokens: 5809111040 | elapsed time per iteration (s): 0.30 | learning rate: 1.074E-04 | global batch size: 256 | lm loss: 3.018124E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 844.234 | TFLOPs: 29.55 | +7: iteration 11090/ 21553 | consumed samples: 2839040 | consumed tokens: 5814353920 | elapsed time per iteration (s): 0.31 | learning rate: 1.073E-04 | global batch size: 256 | lm loss: 3.045595E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.065 | TFLOPs: 28.95 | +7: iteration 11100/ 21553 | consumed samples: 2841600 | consumed tokens: 5819596800 | elapsed time per iteration (s): 0.31 | learning rate: 1.071E-04 | global batch size: 256 | lm loss: 3.033827E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.844 | TFLOPs: 28.49 | +7: iteration 11110/ 21553 | consumed samples: 2844160 | consumed tokens: 5824839680 | elapsed time per iteration (s): 0.31 | learning rate: 1.070E-04 | global batch size: 256 | lm loss: 3.051576E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.264 | TFLOPs: 29.07 | +7: iteration 11120/ 21553 | consumed samples: 2846720 | consumed tokens: 5830082560 | elapsed time per iteration (s): 0.32 | learning rate: 1.069E-04 | global batch size: 256 | lm loss: 3.060762E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 788.944 | TFLOPs: 27.62 | +7: iteration 11130/ 21553 | consumed samples: 2849280 | consumed tokens: 5835325440 | elapsed time per iteration (s): 0.30 | learning rate: 1.067E-04 | global batch size: 256 | lm loss: 3.070701E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.844 | TFLOPs: 29.61 | +7: iteration 11140/ 21553 | consumed samples: 2851840 | consumed tokens: 5840568320 | elapsed time per iteration (s): 0.30 | learning rate: 1.066E-04 | global batch size: 256 | lm loss: 3.046836E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 853.300 | TFLOPs: 29.87 | +7: iteration 11150/ 21553 | consumed samples: 2854400 | consumed tokens: 5845811200 | elapsed time per iteration (s): 0.30 | learning rate: 1.065E-04 | global batch size: 256 | lm loss: 3.067544E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 844.726 | TFLOPs: 29.57 | +7: iteration 11160/ 21553 | consumed samples: 2856960 | consumed tokens: 5851054080 | elapsed time per iteration (s): 0.31 | learning rate: 1.063E-04 | global batch size: 256 | lm loss: 3.038937E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.407 | TFLOPs: 29.28 | +7: iteration 11170/ 21553 | consumed samples: 2859520 | consumed tokens: 5856296960 | elapsed time per iteration (s): 0.30 | learning rate: 1.062E-04 | global batch size: 256 | lm loss: 3.045057E+00 | grad norm: 0.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 853.316 | TFLOPs: 29.87 | +7: iteration 11180/ 21553 | consumed samples: 2862080 | consumed tokens: 5861539840 | elapsed time per iteration (s): 0.31 | learning rate: 1.061E-04 | global batch size: 256 | lm loss: 3.048089E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.461 | TFLOPs: 29.28 | +7: iteration 11190/ 21553 | consumed samples: 2864640 | consumed tokens: 5866782720 | elapsed time per iteration (s): 0.31 | learning rate: 1.060E-04 | global batch size: 256 | lm loss: 3.029904E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.204 | TFLOPs: 28.99 | +7: iteration 11200/ 21553 | consumed samples: 2867200 | consumed tokens: 5872025600 | elapsed time per iteration (s): 0.36 | learning rate: 1.058E-04 | global batch size: 256 | lm loss: 3.069201E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 711.750 | TFLOPs: 24.92 | +7: iteration 11210/ 21553 | consumed samples: 2869760 | consumed tokens: 5877268480 | elapsed time per iteration (s): 0.32 | learning rate: 1.057E-04 | global batch size: 256 | lm loss: 3.054589E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.949 | TFLOPs: 28.32 | +7: iteration 11220/ 21553 | consumed samples: 2872320 | consumed tokens: 5882511360 | elapsed time per iteration (s): 0.31 | learning rate: 1.056E-04 | global batch size: 256 | lm loss: 3.035802E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.505 | TFLOPs: 28.97 | +7: iteration 11230/ 21553 | consumed samples: 2874880 | consumed tokens: 5887754240 | elapsed time per iteration (s): 0.31 | learning rate: 1.054E-04 | global batch size: 256 | lm loss: 3.059647E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.721 | TFLOPs: 29.29 | +7: iteration 11240/ 21553 | consumed samples: 2877440 | consumed tokens: 5892997120 | elapsed time per iteration (s): 0.31 | learning rate: 1.053E-04 | global batch size: 256 | lm loss: 3.056754E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.509 | TFLOPs: 29.18 | +7: iteration 11250/ 21553 | consumed samples: 2880000 | consumed tokens: 5898240000 | elapsed time per iteration (s): 0.32 | learning rate: 1.052E-04 | global batch size: 256 | lm loss: 3.029201E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 793.676 | TFLOPs: 27.78 | +7: iteration 11260/ 21553 | consumed samples: 2882560 | consumed tokens: 5903482880 | elapsed time per iteration (s): 0.41 | learning rate: 1.050E-04 | global batch size: 256 | lm loss: 3.032190E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 626.378 | TFLOPs: 21.93 | +7: iteration 11270/ 21553 | consumed samples: 2885120 | consumed tokens: 5908725760 | elapsed time per iteration (s): 0.32 | learning rate: 1.049E-04 | global batch size: 256 | lm loss: 3.051334E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 794.208 | TFLOPs: 27.80 | +7: iteration 11280/ 21553 | consumed samples: 2887680 | consumed tokens: 5913968640 | elapsed time per iteration (s): 0.34 | learning rate: 1.048E-04 | global batch size: 256 | lm loss: 3.052083E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 759.935 | TFLOPs: 26.60 | +7: iteration 11290/ 21553 | consumed samples: 2890240 | consumed tokens: 5919211520 | elapsed time per iteration (s): 0.30 | learning rate: 1.046E-04 | global batch size: 256 | lm loss: 3.044228E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 849.748 | TFLOPs: 29.75 | +7: iteration 11300/ 21553 | consumed samples: 2892800 | consumed tokens: 5924454400 | elapsed time per iteration (s): 0.30 | learning rate: 1.045E-04 | global batch size: 256 | lm loss: 3.053394E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 848.458 | TFLOPs: 29.70 | +7: iteration 11310/ 21553 | consumed samples: 2895360 | consumed tokens: 5929697280 | elapsed time per iteration (s): 0.31 | learning rate: 1.044E-04 | global batch size: 256 | lm loss: 3.060889E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.342 | TFLOPs: 29.24 | +7: iteration 11320/ 21553 | consumed samples: 2897920 | consumed tokens: 5934940160 | elapsed time per iteration (s): 0.30 | learning rate: 1.042E-04 | global batch size: 256 | lm loss: 3.038877E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.038 | TFLOPs: 29.48 | +7: iteration 11330/ 21553 | consumed samples: 2900480 | consumed tokens: 5940183040 | elapsed time per iteration (s): 0.31 | learning rate: 1.041E-04 | global batch size: 256 | lm loss: 3.041992E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.256 | TFLOPs: 29.35 | +7: iteration 11340/ 21553 | consumed samples: 2903040 | consumed tokens: 5945425920 | elapsed time per iteration (s): 0.31 | learning rate: 1.040E-04 | global batch size: 256 | lm loss: 3.076696E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.609 | TFLOPs: 28.80 | +7: iteration 11350/ 21553 | consumed samples: 2905600 | consumed tokens: 5950668800 | elapsed time per iteration (s): 0.31 | learning rate: 1.038E-04 | global batch size: 256 | lm loss: 3.051635E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.991 | TFLOPs: 29.16 | +7: iteration 11360/ 21553 | consumed samples: 2908160 | consumed tokens: 5955911680 | elapsed time per iteration (s): 0.31 | learning rate: 1.037E-04 | global batch size: 256 | lm loss: 3.070977E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.755 | TFLOPs: 29.26 | +7: iteration 11370/ 21553 | consumed samples: 2910720 | consumed tokens: 5961154560 | elapsed time per iteration (s): 0.32 | learning rate: 1.036E-04 | global batch size: 256 | lm loss: 3.057054E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 801.503 | TFLOPs: 28.06 | +7: iteration 11380/ 21553 | consumed samples: 2913280 | consumed tokens: 5966397440 | elapsed time per iteration (s): 0.31 | learning rate: 1.034E-04 | global batch size: 256 | lm loss: 3.012551E+00 | grad norm: 0.391 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.320 | TFLOPs: 29.38 | +7: iteration 11390/ 21553 | consumed samples: 2915840 | consumed tokens: 5971640320 | elapsed time per iteration (s): 0.31 | learning rate: 1.033E-04 | global batch size: 256 | lm loss: 3.040701E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.627 | TFLOPs: 28.87 | +7: iteration 11400/ 21553 | consumed samples: 2918400 | consumed tokens: 5976883200 | elapsed time per iteration (s): 0.31 | learning rate: 1.032E-04 | global batch size: 256 | lm loss: 3.050286E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.137 | TFLOPs: 29.27 | +7: iteration 11410/ 21553 | consumed samples: 2920960 | consumed tokens: 5982126080 | elapsed time per iteration (s): 0.32 | learning rate: 1.030E-04 | global batch size: 256 | lm loss: 3.042941E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 796.223 | TFLOPs: 27.87 | +7: iteration 11420/ 21553 | consumed samples: 2923520 | consumed tokens: 5987368960 | elapsed time per iteration (s): 0.31 | learning rate: 1.029E-04 | global batch size: 256 | lm loss: 3.056366E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.590 | TFLOPs: 28.97 | +7: iteration 11430/ 21553 | consumed samples: 2926080 | consumed tokens: 5992611840 | elapsed time per iteration (s): 0.30 | learning rate: 1.028E-04 | global batch size: 256 | lm loss: 3.033152E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.346 | TFLOPs: 29.59 | +7: iteration 11440/ 21553 | consumed samples: 2928640 | consumed tokens: 5997854720 | elapsed time per iteration (s): 0.32 | learning rate: 1.026E-04 | global batch size: 256 | lm loss: 3.096243E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.686 | TFLOPs: 28.41 | +7: iteration 11450/ 21553 | consumed samples: 2931200 | consumed tokens: 6003097600 | elapsed time per iteration (s): 0.31 | learning rate: 1.025E-04 | global batch size: 256 | lm loss: 3.024839E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.585 | TFLOPs: 29.15 | +7: iteration 11460/ 21553 | consumed samples: 2933760 | consumed tokens: 6008340480 | elapsed time per iteration (s): 0.31 | learning rate: 1.024E-04 | global batch size: 256 | lm loss: 3.033568E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.188 | TFLOPs: 29.27 | +7: iteration 11470/ 21553 | consumed samples: 2936320 | consumed tokens: 6013583360 | elapsed time per iteration (s): 0.31 | learning rate: 1.022E-04 | global batch size: 256 | lm loss: 3.031758E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.295 | TFLOPs: 28.93 | +7: iteration 11480/ 21553 | consumed samples: 2938880 | consumed tokens: 6018826240 | elapsed time per iteration (s): 0.30 | learning rate: 1.021E-04 | global batch size: 256 | lm loss: 3.069358E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 847.009 | TFLOPs: 29.65 | +7: iteration 11490/ 21553 | consumed samples: 2941440 | consumed tokens: 6024069120 | elapsed time per iteration (s): 0.31 | learning rate: 1.020E-04 | global batch size: 256 | lm loss: 3.069974E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.110 | TFLOPs: 29.02 | +7: iteration 11500/ 21553 | consumed samples: 2944000 | consumed tokens: 6029312000 | elapsed time per iteration (s): 0.31 | learning rate: 1.019E-04 | global batch size: 256 | lm loss: 3.022184E+00 | grad norm: 0.415 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.151 | TFLOPs: 28.75 | +7: iteration 11510/ 21553 | consumed samples: 2946560 | consumed tokens: 6034554880 | elapsed time per iteration (s): 0.31 | learning rate: 1.017E-04 | global batch size: 256 | lm loss: 3.068323E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.855 | TFLOPs: 29.16 | +7: iteration 11520/ 21553 | consumed samples: 2949120 | consumed tokens: 6039797760 | elapsed time per iteration (s): 0.31 | learning rate: 1.016E-04 | global batch size: 256 | lm loss: 3.058068E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.916 | TFLOPs: 29.26 | +7: iteration 11530/ 21553 | consumed samples: 2951680 | consumed tokens: 6045040640 | elapsed time per iteration (s): 0.30 | learning rate: 1.015E-04 | global batch size: 256 | lm loss: 3.030941E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.830 | TFLOPs: 29.40 | +7: iteration 11540/ 21553 | consumed samples: 2954240 | consumed tokens: 6050283520 | elapsed time per iteration (s): 0.32 | learning rate: 1.013E-04 | global batch size: 256 | lm loss: 3.035652E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.256 | TFLOPs: 28.43 | +7: iteration 11550/ 21553 | consumed samples: 2956800 | consumed tokens: 6055526400 | elapsed time per iteration (s): 0.31 | learning rate: 1.012E-04 | global batch size: 256 | lm loss: 3.047338E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.037 | TFLOPs: 29.34 | +7: iteration 11560/ 21553 | consumed samples: 2959360 | consumed tokens: 6060769280 | elapsed time per iteration (s): 0.30 | learning rate: 1.011E-04 | global batch size: 256 | lm loss: 3.082001E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 849.809 | TFLOPs: 29.75 | +7: iteration 11570/ 21553 | consumed samples: 2961920 | consumed tokens: 6066012160 | elapsed time per iteration (s): 0.31 | learning rate: 1.009E-04 | global batch size: 256 | lm loss: 3.055336E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.206 | TFLOPs: 29.27 | +7: iteration 11580/ 21553 | consumed samples: 2964480 | consumed tokens: 6071255040 | elapsed time per iteration (s): 0.31 | learning rate: 1.008E-04 | global batch size: 256 | lm loss: 3.066871E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.539 | TFLOPs: 29.25 | +7: iteration 11590/ 21553 | consumed samples: 2967040 | consumed tokens: 6076497920 | elapsed time per iteration (s): 0.31 | learning rate: 1.007E-04 | global batch size: 256 | lm loss: 3.038736E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.890 | TFLOPs: 29.37 | +7: iteration 11600/ 21553 | consumed samples: 2969600 | consumed tokens: 6081740800 | elapsed time per iteration (s): 0.31 | learning rate: 1.005E-04 | global batch size: 256 | lm loss: 3.015933E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.721 | TFLOPs: 29.15 | +7: iteration 11610/ 21553 | consumed samples: 2972160 | consumed tokens: 6086983680 | elapsed time per iteration (s): 0.31 | learning rate: 1.004E-04 | global batch size: 256 | lm loss: 3.054061E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.443 | TFLOPs: 29.04 | +7: iteration 11620/ 21553 | consumed samples: 2974720 | consumed tokens: 6092226560 | elapsed time per iteration (s): 0.30 | learning rate: 1.003E-04 | global batch size: 256 | lm loss: 3.066673E+00 | grad norm: 0.421 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 850.278 | TFLOPs: 29.77 | +7: iteration 11630/ 21553 | consumed samples: 2977280 | consumed tokens: 6097469440 | elapsed time per iteration (s): 0.31 | learning rate: 1.001E-04 | global batch size: 256 | lm loss: 3.036652E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.152 | TFLOPs: 29.17 | +7: iteration 11640/ 21553 | consumed samples: 2979840 | consumed tokens: 6102712320 | elapsed time per iteration (s): 0.31 | learning rate: 1.000E-04 | global batch size: 256 | lm loss: 3.025951E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.339 | TFLOPs: 29.17 | +7: iteration 11650/ 21553 | consumed samples: 2982400 | consumed tokens: 6107955200 | elapsed time per iteration (s): 0.30 | learning rate: 9.987E-05 | global batch size: 256 | lm loss: 3.033227E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.750 | TFLOPs: 29.47 | +7: iteration 11660/ 21553 | consumed samples: 2984960 | consumed tokens: 6113198080 | elapsed time per iteration (s): 0.31 | learning rate: 9.974E-05 | global batch size: 256 | lm loss: 3.053092E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.171 | TFLOPs: 28.82 | +7: iteration 11670/ 21553 | consumed samples: 2987520 | consumed tokens: 6118440960 | elapsed time per iteration (s): 0.31 | learning rate: 9.961E-05 | global batch size: 256 | lm loss: 3.023067E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.390 | TFLOPs: 28.72 | +7: iteration 11680/ 21553 | consumed samples: 2990080 | consumed tokens: 6123683840 | elapsed time per iteration (s): 0.32 | learning rate: 9.948E-05 | global batch size: 256 | lm loss: 3.041007E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 801.955 | TFLOPs: 28.07 | +7: iteration 11690/ 21553 | consumed samples: 2992640 | consumed tokens: 6128926720 | elapsed time per iteration (s): 0.31 | learning rate: 9.935E-05 | global batch size: 256 | lm loss: 3.049404E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.031 | TFLOPs: 29.02 | +7: iteration 11700/ 21553 | consumed samples: 2995200 | consumed tokens: 6134169600 | elapsed time per iteration (s): 0.31 | learning rate: 9.922E-05 | global batch size: 256 | lm loss: 3.045892E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.636 | TFLOPs: 29.18 | +7: iteration 11710/ 21553 | consumed samples: 2997760 | consumed tokens: 6139412480 | elapsed time per iteration (s): 0.31 | learning rate: 9.909E-05 | global batch size: 256 | lm loss: 3.049973E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.974 | TFLOPs: 29.20 | +7: iteration 11720/ 21553 | consumed samples: 3000320 | consumed tokens: 6144655360 | elapsed time per iteration (s): 0.31 | learning rate: 9.895E-05 | global batch size: 256 | lm loss: 3.018106E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.109 | TFLOPs: 28.78 | +7: iteration 11730/ 21553 | consumed samples: 3002880 | consumed tokens: 6149898240 | elapsed time per iteration (s): 0.30 | learning rate: 9.882E-05 | global batch size: 256 | lm loss: 3.027415E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.531 | TFLOPs: 29.60 | +7: iteration 11740/ 21553 | consumed samples: 3005440 | consumed tokens: 6155141120 | elapsed time per iteration (s): 0.31 | learning rate: 9.869E-05 | global batch size: 256 | lm loss: 3.005216E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.011 | TFLOPs: 29.34 | +7: iteration 11750/ 21553 | consumed samples: 3008000 | consumed tokens: 6160384000 | elapsed time per iteration (s): 0.32 | learning rate: 9.856E-05 | global batch size: 256 | lm loss: 3.041295E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.882 | TFLOPs: 28.32 | +7: iteration 11760/ 21553 | consumed samples: 3010560 | consumed tokens: 6165626880 | elapsed time per iteration (s): 0.31 | learning rate: 9.843E-05 | global batch size: 256 | lm loss: 3.060173E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.030 | TFLOPs: 28.64 | +7: iteration 11770/ 21553 | consumed samples: 3013120 | consumed tokens: 6170869760 | elapsed time per iteration (s): 0.32 | learning rate: 9.830E-05 | global batch size: 256 | lm loss: 3.025389E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.517 | TFLOPs: 28.41 | +7: iteration 11780/ 21553 | consumed samples: 3015680 | consumed tokens: 6176112640 | elapsed time per iteration (s): 0.31 | learning rate: 9.817E-05 | global batch size: 256 | lm loss: 3.043961E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.156 | TFLOPs: 29.13 | +7: iteration 11790/ 21553 | consumed samples: 3018240 | consumed tokens: 6181355520 | elapsed time per iteration (s): 0.31 | learning rate: 9.803E-05 | global batch size: 256 | lm loss: 3.025750E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.501 | TFLOPs: 28.97 | +7: iteration 11800/ 21553 | consumed samples: 3020800 | consumed tokens: 6186598400 | elapsed time per iteration (s): 0.32 | learning rate: 9.790E-05 | global batch size: 256 | lm loss: 3.033582E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 800.943 | TFLOPs: 28.04 | +7: iteration 11810/ 21553 | consumed samples: 3023360 | consumed tokens: 6191841280 | elapsed time per iteration (s): 0.31 | learning rate: 9.777E-05 | global batch size: 256 | lm loss: 3.052835E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.443 | TFLOPs: 29.11 | +7: iteration 11820/ 21553 | consumed samples: 3025920 | consumed tokens: 6197084160 | elapsed time per iteration (s): 0.31 | learning rate: 9.764E-05 | global batch size: 256 | lm loss: 3.040448E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.477 | TFLOPs: 29.14 | +7: iteration 11830/ 21553 | consumed samples: 3028480 | consumed tokens: 6202327040 | elapsed time per iteration (s): 0.31 | learning rate: 9.751E-05 | global batch size: 256 | lm loss: 3.054033E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.780 | TFLOPs: 28.91 | +7: iteration 11840/ 21553 | consumed samples: 3031040 | consumed tokens: 6207569920 | elapsed time per iteration (s): 0.30 | learning rate: 9.738E-05 | global batch size: 256 | lm loss: 3.038434E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 844.212 | TFLOPs: 29.55 | +7: iteration 11850/ 21553 | consumed samples: 3033600 | consumed tokens: 6212812800 | elapsed time per iteration (s): 0.30 | learning rate: 9.725E-05 | global batch size: 256 | lm loss: 3.053331E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.935 | TFLOPs: 29.44 | +7: iteration 11860/ 21553 | consumed samples: 3036160 | consumed tokens: 6218055680 | elapsed time per iteration (s): 0.31 | learning rate: 9.712E-05 | global batch size: 256 | lm loss: 3.062560E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.696 | TFLOPs: 28.84 | +7: iteration 11870/ 21553 | consumed samples: 3038720 | consumed tokens: 6223298560 | elapsed time per iteration (s): 0.31 | learning rate: 9.698E-05 | global batch size: 256 | lm loss: 3.067895E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.575 | TFLOPs: 29.15 | +7: iteration 11880/ 21553 | consumed samples: 3041280 | consumed tokens: 6228541440 | elapsed time per iteration (s): 0.31 | learning rate: 9.685E-05 | global batch size: 256 | lm loss: 2.990686E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.970 | TFLOPs: 28.84 | +7: iteration 11890/ 21553 | consumed samples: 3043840 | consumed tokens: 6233784320 | elapsed time per iteration (s): 0.32 | learning rate: 9.672E-05 | global batch size: 256 | lm loss: 3.007594E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 794.417 | TFLOPs: 27.81 | +7: iteration 11900/ 21553 | consumed samples: 3046400 | consumed tokens: 6239027200 | elapsed time per iteration (s): 0.31 | learning rate: 9.659E-05 | global batch size: 256 | lm loss: 3.031351E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.755 | TFLOPs: 29.12 | +7: iteration 11910/ 21553 | consumed samples: 3048960 | consumed tokens: 6244270080 | elapsed time per iteration (s): 0.33 | learning rate: 9.646E-05 | global batch size: 256 | lm loss: 3.024110E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 772.104 | TFLOPs: 27.03 | +7: iteration 11920/ 21553 | consumed samples: 3051520 | consumed tokens: 6249512960 | elapsed time per iteration (s): 0.32 | learning rate: 9.633E-05 | global batch size: 256 | lm loss: 3.022355E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 805.600 | TFLOPs: 28.20 | +7: iteration 11930/ 21553 | consumed samples: 3054080 | consumed tokens: 6254755840 | elapsed time per iteration (s): 0.32 | learning rate: 9.620E-05 | global batch size: 256 | lm loss: 3.037674E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 800.866 | TFLOPs: 28.04 | +7: iteration 11940/ 21553 | consumed samples: 3056640 | consumed tokens: 6259998720 | elapsed time per iteration (s): 0.32 | learning rate: 9.607E-05 | global batch size: 256 | lm loss: 3.014071E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.548 | TFLOPs: 28.45 | +7: iteration 11950/ 21553 | consumed samples: 3059200 | consumed tokens: 6265241600 | elapsed time per iteration (s): 0.30 | learning rate: 9.594E-05 | global batch size: 256 | lm loss: 3.028580E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.595 | TFLOPs: 29.43 | +7: iteration 11960/ 21553 | consumed samples: 3061760 | consumed tokens: 6270484480 | elapsed time per iteration (s): 0.31 | learning rate: 9.581E-05 | global batch size: 256 | lm loss: 3.048377E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.954 | TFLOPs: 29.30 | +7: iteration 11970/ 21553 | consumed samples: 3064320 | consumed tokens: 6275727360 | elapsed time per iteration (s): 0.31 | learning rate: 9.567E-05 | global batch size: 256 | lm loss: 3.040455E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.398 | TFLOPs: 28.82 | +7: iteration 11980/ 21553 | consumed samples: 3066880 | consumed tokens: 6280970240 | elapsed time per iteration (s): 0.31 | learning rate: 9.554E-05 | global batch size: 256 | lm loss: 3.026894E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.428 | TFLOPs: 29.35 | +7: iteration 11990/ 21553 | consumed samples: 3069440 | consumed tokens: 6286213120 | elapsed time per iteration (s): 0.31 | learning rate: 9.541E-05 | global batch size: 256 | lm loss: 3.001572E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.143 | TFLOPs: 29.10 | +0: [2022-11-29 18:09:59,913] [INFO] [logging.py:68:log_dist] [Rank 0] step=12000, skipped=0, lr=[9.528206376265585e-05, 9.528206376265585e-05, 9.528206376265585e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 12000/ 21553 | consumed samples: 3072000 | consumed tokens: 6291456000 | elapsed time per iteration (s): 0.31 | learning rate: 9.528E-05 | global batch size: 256 | lm loss: 3.008811E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.770 | TFLOPs: 28.84 | +0: steps: 12000 loss: 2.9944 iter time (s): 0.318 samples/sec: 804.813 +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 12000 | lm loss value: 2.889021E+00 | lm loss PPL: 1.797571E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 12000 to checkpoints_146moscareap +0: [2022-11-29 18:10:00,042] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step12000 is begin to save! +0: [2022-11-29 18:10:00,051] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:10:00,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:10:00,138] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:10:00,155] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:10:00,155] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:10:00,172] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:10:00,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:10:00,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:10:00,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:10:00,204] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:10:00,205] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:10:00,220] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:10:00,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:10:00,235] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:10:00,235] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:10:00,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:10:00,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:10:00,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:10:00,267] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:10:00,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:10:00,283] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:10:00,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:10:00,303] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/layer_13-model_00-model_states.pt... +0: [2022-11-29 18:10:00,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/layer_13-model_00-model_states.pt. +0: [2022-11-29 18:10:00,318] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:10:00,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:10:00,333] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/layer_15-model_00-model_states.pt... +0: [2022-11-29 18:10:00,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/layer_15-model_00-model_states.pt. +0: [2022-11-29 18:10:00,349] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/layer_16-model_00-model_states.pt... +0: [2022-11-29 18:10:00,364] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/layer_16-model_00-model_states.pt. +0: [2022-11-29 18:10:00,365] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/layer_17-model_00-model_states.pt... +0: [2022-11-29 18:10:00,380] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/layer_17-model_00-model_states.pt. +0: [2022-11-29 18:10:00,380] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/layer_19-model_00-model_states.pt... +0: [2022-11-29 18:10:00,381] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/layer_19-model_00-model_states.pt. +0: [2022-11-29 18:10:00,382] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_146moscareap/global_step12000/mp_rank_00_model_states.pt +0: [2022-11-29 18:10:00,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:10:00,385] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:10:00,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:10:00,441] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:10:00,441] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:10:00,441] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +2: [2022-11-29 18:10:00,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:10:00,444] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:10:00,444] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +5: [2022-11-29 18:10:00,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:10:00,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:10:00,444] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +2: [2022-11-29 18:10:00,444] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +5: [2022-11-29 18:10:00,444] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +2: [2022-11-29 18:10:00,444] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 18:10:00,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:10:00,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:10:00,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +2: [2022-11-29 18:10:00,444] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:10:00,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 18:10:00,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 18:10:00,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:10:00,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:10:00,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 18:10:00,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:10:00,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +1: [2022-11-29 18:10:00,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:10:00,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 18:10:00,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:10:00,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:10:00,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +1: [2022-11-29 18:10:00,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +6: [2022-11-29 18:10:00,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +4: [2022-11-29 18:10:00,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 18:10:00,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +1: [2022-11-29 18:10:00,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 18:10:00,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:10:00,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:10:00,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:10:00,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:10:00,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +1: [2022-11-29 18:10:00,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +4: [2022-11-29 18:10:00,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 18:10:00,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +1: [2022-11-29 18:10:00,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +1: [2022-11-29 18:10:00,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:10:00,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:10:00,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +5: [2022-11-29 18:10:00,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:10:00,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:10:00,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +2: [2022-11-29 18:10:00,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +5: [2022-11-29 18:10:00,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +2: [2022-11-29 18:10:00,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 18:10:00,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:10:00,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:10:00,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +2: [2022-11-29 18:10:00,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:10:00,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:10:00,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +2: [2022-11-29 18:10:00,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:10:00,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:10:00,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 18:10:00,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:10:00,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:10:00,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +5: [2022-11-29 18:10:00,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:10:00,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:10:00,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:10:00,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:10:00,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:10:00,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +5: [2022-11-29 18:10:00,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 18:10:00,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:10:00,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +6: [2022-11-29 18:10:00,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:10:00,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +5: [2022-11-29 18:10:00,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +1: [2022-11-29 18:10:00,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:10:00,450] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:10:00,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +5: [2022-11-29 18:10:00,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:10:00,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:10:00,452] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:10:00,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 18:10:00,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:10:00,452] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:10:00,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 18:10:00,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:10:00,452] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:10:00,453] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 18:10:00,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:10:00,453] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:10:00,453] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +2: [2022-11-29 18:10:00,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:10:00,454] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:10:00,454] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +1: [2022-11-29 18:10:00,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:10:00,454] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:10:00,454] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +1: [2022-11-29 18:10:00,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:10:00,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:10:00,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +1: [2022-11-29 18:10:00,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:10:00,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:10:00,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +6: [2022-11-29 18:10:00,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +1: [2022-11-29 18:10:00,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:10:00,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 18:10:00,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +1: [2022-11-29 18:10:00,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:10:00,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +7: [2022-11-29 18:10:00,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:10:00,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:10:00,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 18:10:00,441] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:10:00,441] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:10:00,441] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 18:10:00,443] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:10:00,443] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:10:00,443] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 18:10:00,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:10:00,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:10:00,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 18:10:00,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:10:00,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:10:00,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 18:10:00,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:10:00,450] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +0: [2022-11-29 18:10:00,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:10:00,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 18:10:00,450] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +5: [2022-11-29 18:10:00,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:10:00,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +5: [2022-11-29 18:10:00,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:10:00,454] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +0: [2022-11-29 18:10:00,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:10:00,454] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:10:00,454] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 18:10:00,451] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +5: [2022-11-29 18:10:00,454] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 18:10:00,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 18:10:00,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:10:00,454] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:10:00,454] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +7: [2022-11-29 18:10:00,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:10:00,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:10:00,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 18:10:00,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:10:00,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:10:00,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 18:10:00,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:10:00,459] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:10:00,459] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 18:10:00,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:10:00,459] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:10:00,459] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +7: [2022-11-29 18:10:00,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:10:00,460] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:10:00,460] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 18:10:00,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:10:00,460] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:10:00,460] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +7: [2022-11-29 18:10:00,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:10:00,460] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:10:00,460] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 18:10:00,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:10:00,461] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:10:00,461] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +7: [2022-11-29 18:10:00,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:10:00,461] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:10:00,461] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +7: [2022-11-29 18:10:00,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:10:00,461] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:10:00,461] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +7: [2022-11-29 18:10:00,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:10:00,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:10:00,462] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:10:00,462] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:10:00,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +7: [2022-11-29 18:10:00,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 18:10:00,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:10:00,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:10:00,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:10:00,462] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:10:00,462] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:10:00,462] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:10:00,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 18:10:00,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 18:10:00,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 18:10:00,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:10:00,462] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:10:00,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +7: time (ms) | save-checkpoint: 435.15 +0: [2022-11-29 18:10:00,470] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step12000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:10:00,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: successfully saved checkpoint at iteration 12000 to checkpoints_146moscareap +7: iteration 12010/ 21553 | consumed samples: 3074560 | consumed tokens: 6296698880 | elapsed time per iteration (s): 0.36 | learning rate: 9.515E-05 | global batch size: 256 | lm loss: 3.040500E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 702.193 | TFLOPs: 24.58 | +7: iteration 12020/ 21553 | consumed samples: 3077120 | consumed tokens: 6301941760 | elapsed time per iteration (s): 0.31 | learning rate: 9.502E-05 | global batch size: 256 | lm loss: 3.059344E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.657 | TFLOPs: 29.04 | +7: iteration 12030/ 21553 | consumed samples: 3079680 | consumed tokens: 6307184640 | elapsed time per iteration (s): 0.31 | learning rate: 9.489E-05 | global batch size: 256 | lm loss: 3.032331E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.110 | TFLOPs: 28.88 | +7: iteration 12040/ 21553 | consumed samples: 3082240 | consumed tokens: 6312427520 | elapsed time per iteration (s): 0.31 | learning rate: 9.476E-05 | global batch size: 256 | lm loss: 3.022880E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.949 | TFLOPs: 29.30 | +7: iteration 12050/ 21553 | consumed samples: 3084800 | consumed tokens: 6317670400 | elapsed time per iteration (s): 0.31 | learning rate: 9.463E-05 | global batch size: 256 | lm loss: 3.004765E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.312 | TFLOPs: 28.82 | +7: iteration 12060/ 21553 | consumed samples: 3087360 | consumed tokens: 6322913280 | elapsed time per iteration (s): 0.32 | learning rate: 9.450E-05 | global batch size: 256 | lm loss: 3.053661E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 803.955 | TFLOPs: 28.14 | +7: iteration 12070/ 21553 | consumed samples: 3089920 | consumed tokens: 6328156160 | elapsed time per iteration (s): 0.32 | learning rate: 9.437E-05 | global batch size: 256 | lm loss: 3.058262E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 798.401 | TFLOPs: 27.95 | +7: iteration 12080/ 21553 | consumed samples: 3092480 | consumed tokens: 6333399040 | elapsed time per iteration (s): 0.33 | learning rate: 9.424E-05 | global batch size: 256 | lm loss: 3.025723E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 776.032 | TFLOPs: 27.17 | +7: iteration 12090/ 21553 | consumed samples: 3095040 | consumed tokens: 6338641920 | elapsed time per iteration (s): 0.32 | learning rate: 9.411E-05 | global batch size: 256 | lm loss: 3.056576E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 800.903 | TFLOPs: 28.04 | +7: iteration 12100/ 21553 | consumed samples: 3097600 | consumed tokens: 6343884800 | elapsed time per iteration (s): 0.31 | learning rate: 9.398E-05 | global batch size: 256 | lm loss: 3.031945E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.217 | TFLOPs: 28.89 | +7: iteration 12110/ 21553 | consumed samples: 3100160 | consumed tokens: 6349127680 | elapsed time per iteration (s): 0.31 | learning rate: 9.385E-05 | global batch size: 256 | lm loss: 3.023671E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.165 | TFLOPs: 29.27 | +7: iteration 12120/ 21553 | consumed samples: 3102720 | consumed tokens: 6354370560 | elapsed time per iteration (s): 0.42 | learning rate: 9.372E-05 | global batch size: 256 | lm loss: 3.060669E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.492 | TFLOPs: 21.34 | +7: iteration 12130/ 21553 | consumed samples: 3105280 | consumed tokens: 6359613440 | elapsed time per iteration (s): 0.38 | learning rate: 9.359E-05 | global batch size: 256 | lm loss: 3.009803E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 674.829 | TFLOPs: 23.62 | +7: iteration 12140/ 21553 | consumed samples: 3107840 | consumed tokens: 6364856320 | elapsed time per iteration (s): 0.37 | learning rate: 9.346E-05 | global batch size: 256 | lm loss: 3.019573E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 689.836 | TFLOPs: 24.15 | +7: iteration 12150/ 21553 | consumed samples: 3110400 | consumed tokens: 6370099200 | elapsed time per iteration (s): 0.45 | learning rate: 9.332E-05 | global batch size: 256 | lm loss: 3.044581E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 571.370 | TFLOPs: 20.00 | +7: iteration 12160/ 21553 | consumed samples: 3112960 | consumed tokens: 6375342080 | elapsed time per iteration (s): 0.32 | learning rate: 9.319E-05 | global batch size: 256 | lm loss: 3.038515E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 798.344 | TFLOPs: 27.95 | +7: iteration 12170/ 21553 | consumed samples: 3115520 | consumed tokens: 6380584960 | elapsed time per iteration (s): 0.31 | learning rate: 9.306E-05 | global batch size: 256 | lm loss: 3.041611E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.478 | TFLOPs: 28.83 | +7: iteration 12180/ 21553 | consumed samples: 3118080 | consumed tokens: 6385827840 | elapsed time per iteration (s): 0.31 | learning rate: 9.293E-05 | global batch size: 256 | lm loss: 2.994592E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.762 | TFLOPs: 28.94 | +7: iteration 12190/ 21553 | consumed samples: 3120640 | consumed tokens: 6391070720 | elapsed time per iteration (s): 0.31 | learning rate: 9.280E-05 | global batch size: 256 | lm loss: 3.019757E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.824 | TFLOPs: 29.26 | +7: iteration 12200/ 21553 | consumed samples: 3123200 | consumed tokens: 6396313600 | elapsed time per iteration (s): 0.31 | learning rate: 9.267E-05 | global batch size: 256 | lm loss: 3.051655E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.694 | TFLOPs: 29.01 | +7: iteration 12210/ 21553 | consumed samples: 3125760 | consumed tokens: 6401556480 | elapsed time per iteration (s): 0.31 | learning rate: 9.254E-05 | global batch size: 256 | lm loss: 3.026161E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.758 | TFLOPs: 28.94 | +7: iteration 12220/ 21553 | consumed samples: 3128320 | consumed tokens: 6406799360 | elapsed time per iteration (s): 0.31 | learning rate: 9.241E-05 | global batch size: 256 | lm loss: 3.039485E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.335 | TFLOPs: 28.93 | +7: iteration 12230/ 21553 | consumed samples: 3130880 | consumed tokens: 6412042240 | elapsed time per iteration (s): 0.33 | learning rate: 9.228E-05 | global batch size: 256 | lm loss: 3.035902E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 786.361 | TFLOPs: 27.53 | +7: iteration 12240/ 21553 | consumed samples: 3133440 | consumed tokens: 6417285120 | elapsed time per iteration (s): 0.32 | learning rate: 9.215E-05 | global batch size: 256 | lm loss: 3.040896E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 795.061 | TFLOPs: 27.83 | +7: iteration 12250/ 21553 | consumed samples: 3136000 | consumed tokens: 6422528000 | elapsed time per iteration (s): 0.31 | learning rate: 9.202E-05 | global batch size: 256 | lm loss: 3.042946E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.603 | TFLOPs: 28.48 | +7: iteration 12260/ 21553 | consumed samples: 3138560 | consumed tokens: 6427770880 | elapsed time per iteration (s): 0.31 | learning rate: 9.189E-05 | global batch size: 256 | lm loss: 3.020057E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.214 | TFLOPs: 28.96 | +7: iteration 12270/ 21553 | consumed samples: 3141120 | consumed tokens: 6433013760 | elapsed time per iteration (s): 0.32 | learning rate: 9.177E-05 | global batch size: 256 | lm loss: 3.051182E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.568 | TFLOPs: 28.45 | +7: iteration 12280/ 21553 | consumed samples: 3143680 | consumed tokens: 6438256640 | elapsed time per iteration (s): 0.31 | learning rate: 9.164E-05 | global batch size: 256 | lm loss: 3.032243E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.447 | TFLOPs: 29.14 | +7: iteration 12290/ 21553 | consumed samples: 3146240 | consumed tokens: 6443499520 | elapsed time per iteration (s): 0.30 | learning rate: 9.151E-05 | global batch size: 256 | lm loss: 3.029428E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.619 | TFLOPs: 29.39 | +7: iteration 12300/ 21553 | consumed samples: 3148800 | consumed tokens: 6448742400 | elapsed time per iteration (s): 0.31 | learning rate: 9.138E-05 | global batch size: 256 | lm loss: 3.025447E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.197 | TFLOPs: 28.50 | +7: iteration 12310/ 21553 | consumed samples: 3151360 | consumed tokens: 6453985280 | elapsed time per iteration (s): 0.31 | learning rate: 9.125E-05 | global batch size: 256 | lm loss: 3.025416E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.318 | TFLOPs: 29.31 | +7: iteration 12320/ 21553 | consumed samples: 3153920 | consumed tokens: 6459228160 | elapsed time per iteration (s): 0.30 | learning rate: 9.112E-05 | global batch size: 256 | lm loss: 3.039717E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 846.803 | TFLOPs: 29.64 | +7: iteration 12330/ 21553 | consumed samples: 3156480 | consumed tokens: 6464471040 | elapsed time per iteration (s): 0.31 | learning rate: 9.099E-05 | global batch size: 256 | lm loss: 3.021101E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.614 | TFLOPs: 29.15 | +7: iteration 12340/ 21553 | consumed samples: 3159040 | consumed tokens: 6469713920 | elapsed time per iteration (s): 0.31 | learning rate: 9.086E-05 | global batch size: 256 | lm loss: 3.010198E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.782 | TFLOPs: 29.36 | +7: iteration 12350/ 21553 | consumed samples: 3161600 | consumed tokens: 6474956800 | elapsed time per iteration (s): 0.31 | learning rate: 9.073E-05 | global batch size: 256 | lm loss: 3.034445E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.403 | TFLOPs: 29.18 | +7: iteration 12360/ 21553 | consumed samples: 3164160 | consumed tokens: 6480199680 | elapsed time per iteration (s): 0.31 | learning rate: 9.060E-05 | global batch size: 256 | lm loss: 3.037195E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.742 | TFLOPs: 28.84 | +7: iteration 12370/ 21553 | consumed samples: 3166720 | consumed tokens: 6485442560 | elapsed time per iteration (s): 0.31 | learning rate: 9.047E-05 | global batch size: 256 | lm loss: 3.032957E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.042 | TFLOPs: 29.20 | +7: iteration 12380/ 21553 | consumed samples: 3169280 | consumed tokens: 6490685440 | elapsed time per iteration (s): 0.31 | learning rate: 9.034E-05 | global batch size: 256 | lm loss: 3.018188E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.381 | TFLOPs: 29.10 | +7: iteration 12390/ 21553 | consumed samples: 3171840 | consumed tokens: 6495928320 | elapsed time per iteration (s): 0.32 | learning rate: 9.021E-05 | global batch size: 256 | lm loss: 3.002707E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 796.803 | TFLOPs: 27.89 | +7: iteration 12400/ 21553 | consumed samples: 3174400 | consumed tokens: 6501171200 | elapsed time per iteration (s): 0.32 | learning rate: 9.008E-05 | global batch size: 256 | lm loss: 3.059467E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 796.992 | TFLOPs: 27.90 | +7: iteration 12410/ 21553 | consumed samples: 3176960 | consumed tokens: 6506414080 | elapsed time per iteration (s): 0.31 | learning rate: 8.995E-05 | global batch size: 256 | lm loss: 3.037637E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.291 | TFLOPs: 28.93 | +7: iteration 12420/ 21553 | consumed samples: 3179520 | consumed tokens: 6511656960 | elapsed time per iteration (s): 0.32 | learning rate: 8.982E-05 | global batch size: 256 | lm loss: 3.026830E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.164 | TFLOPs: 28.36 | +7: iteration 12430/ 21553 | consumed samples: 3182080 | consumed tokens: 6516899840 | elapsed time per iteration (s): 0.31 | learning rate: 8.969E-05 | global batch size: 256 | lm loss: 3.036768E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.502 | TFLOPs: 29.00 | +7: iteration 12440/ 21553 | consumed samples: 3184640 | consumed tokens: 6522142720 | elapsed time per iteration (s): 0.31 | learning rate: 8.957E-05 | global batch size: 256 | lm loss: 3.030635E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.183 | TFLOPs: 28.57 | +7: iteration 12450/ 21553 | consumed samples: 3187200 | consumed tokens: 6527385600 | elapsed time per iteration (s): 0.31 | learning rate: 8.944E-05 | global batch size: 256 | lm loss: 3.030572E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.835 | TFLOPs: 29.19 | +7: iteration 12460/ 21553 | consumed samples: 3189760 | consumed tokens: 6532628480 | elapsed time per iteration (s): 0.31 | learning rate: 8.931E-05 | global batch size: 256 | lm loss: 3.037895E+00 | grad norm: 0.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.670 | TFLOPs: 28.52 | +7: iteration 12470/ 21553 | consumed samples: 3192320 | consumed tokens: 6537871360 | elapsed time per iteration (s): 0.31 | learning rate: 8.918E-05 | global batch size: 256 | lm loss: 3.028412E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.420 | TFLOPs: 29.14 | +7: iteration 12480/ 21553 | consumed samples: 3194880 | consumed tokens: 6543114240 | elapsed time per iteration (s): 0.31 | learning rate: 8.905E-05 | global batch size: 256 | lm loss: 3.040649E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.890 | TFLOPs: 28.98 | +7: iteration 12490/ 21553 | consumed samples: 3197440 | consumed tokens: 6548357120 | elapsed time per iteration (s): 0.31 | learning rate: 8.892E-05 | global batch size: 256 | lm loss: 3.015631E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.919 | TFLOPs: 28.77 | +7: iteration 12500/ 21553 | consumed samples: 3200000 | consumed tokens: 6553600000 | elapsed time per iteration (s): 0.31 | learning rate: 8.879E-05 | global batch size: 256 | lm loss: 3.009589E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.206 | TFLOPs: 29.06 | +7: iteration 12510/ 21553 | consumed samples: 3202560 | consumed tokens: 6558842880 | elapsed time per iteration (s): 0.31 | learning rate: 8.866E-05 | global batch size: 256 | lm loss: 3.013798E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.439 | TFLOPs: 28.86 | +7: iteration 12520/ 21553 | consumed samples: 3205120 | consumed tokens: 6564085760 | elapsed time per iteration (s): 0.32 | learning rate: 8.853E-05 | global batch size: 256 | lm loss: 3.030852E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.730 | TFLOPs: 28.42 | +7: iteration 12530/ 21553 | consumed samples: 3207680 | consumed tokens: 6569328640 | elapsed time per iteration (s): 0.31 | learning rate: 8.841E-05 | global batch size: 256 | lm loss: 3.020626E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.662 | TFLOPs: 28.66 | +7: iteration 12540/ 21553 | consumed samples: 3210240 | consumed tokens: 6574571520 | elapsed time per iteration (s): 0.31 | learning rate: 8.828E-05 | global batch size: 256 | lm loss: 3.020513E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.320 | TFLOPs: 28.61 | +7: iteration 12550/ 21553 | consumed samples: 3212800 | consumed tokens: 6579814400 | elapsed time per iteration (s): 0.31 | learning rate: 8.815E-05 | global batch size: 256 | lm loss: 3.005855E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.088 | TFLOPs: 29.06 | +7: iteration 12560/ 21553 | consumed samples: 3215360 | consumed tokens: 6585057280 | elapsed time per iteration (s): 0.32 | learning rate: 8.802E-05 | global batch size: 256 | lm loss: 3.036722E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 807.488 | TFLOPs: 28.27 | +7: iteration 12570/ 21553 | consumed samples: 3217920 | consumed tokens: 6590300160 | elapsed time per iteration (s): 0.33 | learning rate: 8.789E-05 | global batch size: 256 | lm loss: 3.039915E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 771.211 | TFLOPs: 27.00 | +7: iteration 12580/ 21553 | consumed samples: 3220480 | consumed tokens: 6595543040 | elapsed time per iteration (s): 0.31 | learning rate: 8.776E-05 | global batch size: 256 | lm loss: 3.029201E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.866 | TFLOPs: 28.63 | +7: iteration 12590/ 21553 | consumed samples: 3223040 | consumed tokens: 6600785920 | elapsed time per iteration (s): 0.31 | learning rate: 8.763E-05 | global batch size: 256 | lm loss: 3.032180E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.866 | TFLOPs: 28.67 | +7: iteration 12600/ 21553 | consumed samples: 3225600 | consumed tokens: 6606028800 | elapsed time per iteration (s): 0.31 | learning rate: 8.751E-05 | global batch size: 256 | lm loss: 3.019347E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.620 | TFLOPs: 28.80 | +7: iteration 12610/ 21553 | consumed samples: 3228160 | consumed tokens: 6611271680 | elapsed time per iteration (s): 0.31 | learning rate: 8.738E-05 | global batch size: 256 | lm loss: 3.011102E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.084 | TFLOPs: 28.78 | +7: iteration 12620/ 21553 | consumed samples: 3230720 | consumed tokens: 6616514560 | elapsed time per iteration (s): 0.32 | learning rate: 8.725E-05 | global batch size: 256 | lm loss: 3.005061E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.336 | TFLOPs: 28.30 | +7: iteration 12630/ 21553 | consumed samples: 3233280 | consumed tokens: 6621757440 | elapsed time per iteration (s): 0.32 | learning rate: 8.712E-05 | global batch size: 256 | lm loss: 3.011459E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 801.563 | TFLOPs: 28.06 | +7: iteration 12640/ 21553 | consumed samples: 3235840 | consumed tokens: 6627000320 | elapsed time per iteration (s): 0.32 | learning rate: 8.699E-05 | global batch size: 256 | lm loss: 3.020265E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 804.192 | TFLOPs: 28.15 | +7: iteration 12650/ 21553 | consumed samples: 3238400 | consumed tokens: 6632243200 | elapsed time per iteration (s): 0.31 | learning rate: 8.687E-05 | global batch size: 256 | lm loss: 3.007053E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.189 | TFLOPs: 28.78 | +7: iteration 12660/ 21553 | consumed samples: 3240960 | consumed tokens: 6637486080 | elapsed time per iteration (s): 0.31 | learning rate: 8.674E-05 | global batch size: 256 | lm loss: 3.004805E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.133 | TFLOPs: 28.75 | +7: iteration 12670/ 21553 | consumed samples: 3243520 | consumed tokens: 6642728960 | elapsed time per iteration (s): 0.32 | learning rate: 8.661E-05 | global batch size: 256 | lm loss: 3.009182E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 804.842 | TFLOPs: 28.18 | +7: iteration 12680/ 21553 | consumed samples: 3246080 | consumed tokens: 6647971840 | elapsed time per iteration (s): 0.31 | learning rate: 8.648E-05 | global batch size: 256 | lm loss: 3.001719E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.680 | TFLOPs: 28.80 | +7: iteration 12690/ 21553 | consumed samples: 3248640 | consumed tokens: 6653214720 | elapsed time per iteration (s): 0.31 | learning rate: 8.635E-05 | global batch size: 256 | lm loss: 3.024589E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.049 | TFLOPs: 28.78 | +7: iteration 12700/ 21553 | consumed samples: 3251200 | consumed tokens: 6658457600 | elapsed time per iteration (s): 0.31 | learning rate: 8.623E-05 | global batch size: 256 | lm loss: 3.003441E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.846 | TFLOPs: 29.23 | +7: iteration 12710/ 21553 | consumed samples: 3253760 | consumed tokens: 6663700480 | elapsed time per iteration (s): 0.31 | learning rate: 8.610E-05 | global batch size: 256 | lm loss: 3.017408E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.540 | TFLOPs: 28.83 | +7: iteration 12720/ 21553 | consumed samples: 3256320 | consumed tokens: 6668943360 | elapsed time per iteration (s): 0.32 | learning rate: 8.597E-05 | global batch size: 256 | lm loss: 3.011105E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 809.053 | TFLOPs: 28.32 | +7: iteration 12730/ 21553 | consumed samples: 3258880 | consumed tokens: 6674186240 | elapsed time per iteration (s): 0.32 | learning rate: 8.584E-05 | global batch size: 256 | lm loss: 3.020042E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.231 | TFLOPs: 28.43 | +7: iteration 12740/ 21553 | consumed samples: 3261440 | consumed tokens: 6679429120 | elapsed time per iteration (s): 0.31 | learning rate: 8.571E-05 | global batch size: 256 | lm loss: 3.037464E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.672 | TFLOPs: 28.76 | +7: iteration 12750/ 21553 | consumed samples: 3264000 | consumed tokens: 6684672000 | elapsed time per iteration (s): 0.32 | learning rate: 8.559E-05 | global batch size: 256 | lm loss: 3.027994E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.630 | TFLOPs: 28.38 | +7: iteration 12760/ 21553 | consumed samples: 3266560 | consumed tokens: 6689914880 | elapsed time per iteration (s): 0.31 | learning rate: 8.546E-05 | global batch size: 256 | lm loss: 2.998860E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.463 | TFLOPs: 28.93 | +7: iteration 12770/ 21553 | consumed samples: 3269120 | consumed tokens: 6695157760 | elapsed time per iteration (s): 0.31 | learning rate: 8.533E-05 | global batch size: 256 | lm loss: 3.013539E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.677 | TFLOPs: 28.90 | +7: iteration 12780/ 21553 | consumed samples: 3271680 | consumed tokens: 6700400640 | elapsed time per iteration (s): 0.31 | learning rate: 8.520E-05 | global batch size: 256 | lm loss: 3.013863E+00 | grad norm: 0.382 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.258 | TFLOPs: 29.35 | +7: iteration 12790/ 21553 | consumed samples: 3274240 | consumed tokens: 6705643520 | elapsed time per iteration (s): 0.32 | learning rate: 8.508E-05 | global batch size: 256 | lm loss: 3.047073E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 809.324 | TFLOPs: 28.33 | +7: iteration 12800/ 21553 | consumed samples: 3276800 | consumed tokens: 6710886400 | elapsed time per iteration (s): 0.31 | learning rate: 8.495E-05 | global batch size: 256 | lm loss: 3.011037E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.239 | TFLOPs: 28.71 | +7: iteration 12810/ 21553 | consumed samples: 3279360 | consumed tokens: 6716129280 | elapsed time per iteration (s): 0.31 | learning rate: 8.482E-05 | global batch size: 256 | lm loss: 3.008189E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.942 | TFLOPs: 28.95 | +7: iteration 12820/ 21553 | consumed samples: 3281920 | consumed tokens: 6721372160 | elapsed time per iteration (s): 0.31 | learning rate: 8.470E-05 | global batch size: 256 | lm loss: 2.988548E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.981 | TFLOPs: 29.16 | +7: iteration 12830/ 21553 | consumed samples: 3284480 | consumed tokens: 6726615040 | elapsed time per iteration (s): 0.30 | learning rate: 8.457E-05 | global batch size: 256 | lm loss: 2.979837E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.097 | TFLOPs: 29.48 | +7: iteration 12840/ 21553 | consumed samples: 3287040 | consumed tokens: 6731857920 | elapsed time per iteration (s): 0.31 | learning rate: 8.444E-05 | global batch size: 256 | lm loss: 3.017426E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.929 | TFLOPs: 28.98 | +7: iteration 12850/ 21553 | consumed samples: 3289600 | consumed tokens: 6737100800 | elapsed time per iteration (s): 0.33 | learning rate: 8.431E-05 | global batch size: 256 | lm loss: 3.009374E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 786.144 | TFLOPs: 27.52 | +7: iteration 12860/ 21553 | consumed samples: 3292160 | consumed tokens: 6742343680 | elapsed time per iteration (s): 0.31 | learning rate: 8.419E-05 | global batch size: 256 | lm loss: 3.003822E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.339 | TFLOPs: 28.65 | +7: iteration 12870/ 21553 | consumed samples: 3294720 | consumed tokens: 6747586560 | elapsed time per iteration (s): 0.31 | learning rate: 8.406E-05 | global batch size: 256 | lm loss: 3.019866E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.572 | TFLOPs: 28.62 | +7: iteration 12880/ 21553 | consumed samples: 3297280 | consumed tokens: 6752829440 | elapsed time per iteration (s): 0.33 | learning rate: 8.393E-05 | global batch size: 256 | lm loss: 3.009271E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 771.229 | TFLOPs: 27.00 | +7: iteration 12890/ 21553 | consumed samples: 3299840 | consumed tokens: 6758072320 | elapsed time per iteration (s): 0.31 | learning rate: 8.381E-05 | global batch size: 256 | lm loss: 2.988207E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.456 | TFLOPs: 29.07 | +7: iteration 12900/ 21553 | consumed samples: 3302400 | consumed tokens: 6763315200 | elapsed time per iteration (s): 0.30 | learning rate: 8.368E-05 | global batch size: 256 | lm loss: 3.028298E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.748 | TFLOPs: 29.40 | +7: iteration 12910/ 21553 | consumed samples: 3304960 | consumed tokens: 6768558080 | elapsed time per iteration (s): 0.31 | learning rate: 8.355E-05 | global batch size: 256 | lm loss: 3.006820E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.396 | TFLOPs: 28.89 | +7: iteration 12920/ 21553 | consumed samples: 3307520 | consumed tokens: 6773800960 | elapsed time per iteration (s): 0.32 | learning rate: 8.343E-05 | global batch size: 256 | lm loss: 3.010134E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.269 | TFLOPs: 28.40 | +7: iteration 12930/ 21553 | consumed samples: 3310080 | consumed tokens: 6779043840 | elapsed time per iteration (s): 0.31 | learning rate: 8.330E-05 | global batch size: 256 | lm loss: 3.007882E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.446 | TFLOPs: 28.65 | +7: iteration 12940/ 21553 | consumed samples: 3312640 | consumed tokens: 6784286720 | elapsed time per iteration (s): 0.32 | learning rate: 8.317E-05 | global batch size: 256 | lm loss: 3.027325E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 807.469 | TFLOPs: 28.27 | +7: iteration 12950/ 21553 | consumed samples: 3315200 | consumed tokens: 6789529600 | elapsed time per iteration (s): 0.31 | learning rate: 8.305E-05 | global batch size: 256 | lm loss: 3.020550E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.340 | TFLOPs: 29.00 | +7: iteration 12960/ 21553 | consumed samples: 3317760 | consumed tokens: 6794772480 | elapsed time per iteration (s): 0.31 | learning rate: 8.292E-05 | global batch size: 256 | lm loss: 3.031963E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.447 | TFLOPs: 29.07 | +7: iteration 12970/ 21553 | consumed samples: 3320320 | consumed tokens: 6800015360 | elapsed time per iteration (s): 0.31 | learning rate: 8.279E-05 | global batch size: 256 | lm loss: 3.022638E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.475 | TFLOPs: 29.00 | +7: iteration 12980/ 21553 | consumed samples: 3322880 | consumed tokens: 6805258240 | elapsed time per iteration (s): 0.31 | learning rate: 8.267E-05 | global batch size: 256 | lm loss: 3.020835E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.922 | TFLOPs: 28.84 | +7: iteration 12990/ 21553 | consumed samples: 3325440 | consumed tokens: 6810501120 | elapsed time per iteration (s): 0.30 | learning rate: 8.254E-05 | global batch size: 256 | lm loss: 2.995591E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.188 | TFLOPs: 29.52 | +7: iteration 13000/ 21553 | consumed samples: 3328000 | consumed tokens: 6815744000 | elapsed time per iteration (s): 0.31 | learning rate: 8.242E-05 | global batch size: 256 | lm loss: 3.011425E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.032 | TFLOPs: 28.53 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 13000 | lm loss value: 2.962404E+00 | lm loss PPL: 1.934441E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 13000 to checkpoints_146moscareap +0: [2022-11-29 18:15:16,701] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step13000 is begin to save! +0: [2022-11-29 18:15:16,802] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:15:17,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:15:17,110] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:15:17,126] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:15:17,126] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:15:17,141] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:15:17,142] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:15:17,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:15:17,157] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:15:17,172] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:15:17,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:15:17,187] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:15:17,188] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:15:17,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:15:17,203] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:15:17,218] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:15:17,219] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:15:17,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:15:17,234] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:15:17,249] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:15:17,250] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:15:17,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:15:17,265] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/layer_13-model_00-model_states.pt... +0: [2022-11-29 18:15:17,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/layer_13-model_00-model_states.pt. +0: [2022-11-29 18:15:17,281] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:15:17,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:15:17,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/layer_15-model_00-model_states.pt... +0: [2022-11-29 18:15:17,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/layer_15-model_00-model_states.pt. +0: [2022-11-29 18:15:17,312] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/layer_16-model_00-model_states.pt... +0: [2022-11-29 18:15:17,327] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/layer_16-model_00-model_states.pt. +0: [2022-11-29 18:15:17,327] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/layer_17-model_00-model_states.pt... +0: [2022-11-29 18:15:17,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/layer_17-model_00-model_states.pt. +0: [2022-11-29 18:15:17,342] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/layer_19-model_00-model_states.pt... +0: [2022-11-29 18:15:17,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/layer_19-model_00-model_states.pt. +0: [2022-11-29 18:15:17,344] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_146moscareap/global_step13000/mp_rank_00_model_states.pt +0: [2022-11-29 18:15:17,344] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:15:17,385] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:15:17,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:15:17,438] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:15:17,438] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:15:17,438] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 18:15:17,439] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:15:17,439] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:15:17,439] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +3: [2022-11-29 18:15:17,439] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:15:17,439] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 18:15:17,439] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: [2022-11-29 18:15:17,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:15:17,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:15:17,440] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:15:17,440] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +3: [2022-11-29 18:15:17,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:15:17,440] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:15:17,440] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +3: [2022-11-29 18:15:17,441] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:15:17,441] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:15:17,441] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: [2022-11-29 18:15:17,441] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:15:17,441] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:15:17,441] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 18:15:17,441] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:15:17,441] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +0: [2022-11-29 18:15:17,441] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:15:17,441] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: [2022-11-29 18:15:17,441] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:15:17,441] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 18:15:17,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:15:17,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:15:17,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 18:15:17,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:15:17,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:15:17,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +3: [2022-11-29 18:15:17,443] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:15:17,443] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:15:17,443] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 18:15:17,443] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:15:17,443] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:15:17,443] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: [2022-11-29 18:15:17,443] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:15:17,444] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:15:17,444] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +3: [2022-11-29 18:15:17,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:15:17,444] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:15:17,444] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: [2022-11-29 18:15:17,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:15:17,444] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:15:17,444] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +3: [2022-11-29 18:15:17,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:15:17,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:15:17,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 18:15:17,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:15:17,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:15:17,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +3: [2022-11-29 18:15:17,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:15:17,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:15:17,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 18:15:17,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:15:17,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:15:17,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:15:17,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +3: [2022-11-29 18:15:17,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:15:17,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 18:15:17,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +2: [2022-11-29 18:15:17,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 18:15:17,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 18:15:17,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:15:17,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:15:17,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 18:15:17,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:15:17,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:15:17,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:15:17,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:15:17,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +2: [2022-11-29 18:15:17,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +4: [2022-11-29 18:15:17,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 18:15:17,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 18:15:17,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 18:15:17,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:15:17,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:15:17,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:15:17,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:15:17,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:15:17,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:15:17,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:15:17,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:15:17,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 18:15:17,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 18:15:17,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 18:15:17,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 18:15:17,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:15:17,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:15:17,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 18:15:17,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:15:17,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:15:17,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:15:17,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:15:17,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 18:15:17,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 18:15:17,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:15:17,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:15:17,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 18:15:17,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:15:17,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:15:17,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +1: [2022-11-29 18:15:17,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:15:17,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 18:15:17,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:15:17,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 18:15:17,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:15:17,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 18:15:17,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:15:17,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:15:17,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +4: [2022-11-29 18:15:17,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:15:17,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 18:15:17,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 18:15:17,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:15:17,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:15:17,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 18:15:17,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:15:17,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:15:17,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 18:15:17,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:15:17,452] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:15:17,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 18:15:17,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:15:17,452] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:15:17,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 18:15:17,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:15:17,452] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:15:17,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 18:15:17,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:15:17,454] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:15:17,454] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: [2022-11-29 18:15:17,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:15:17,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:15:17,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: [2022-11-29 18:15:17,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:15:17,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:15:17,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: [2022-11-29 18:15:17,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:15:17,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 18:15:17,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:15:17,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:15:17,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:15:17,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:15:17,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:15:17,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:15:17,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:15:17,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:15:17,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:15:17,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:15:17,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:15:17,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:15:17,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:15:17,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:15:17,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:15:17,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:15:17,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 18:15:17,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 18:15:17,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 18:15:17,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 18:15:17,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 18:15:17,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 18:15:17,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 18:15:17,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +6: [2022-11-29 18:15:17,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:15:17,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:15:17,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:15:17,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:15:17,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:15:17,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:15:17,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:15:17,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:15:17,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:15:17,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:15:17,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:15:17,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:15:17,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:15:17,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:15:17,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:15:17,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step13000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:15:17,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +6: [2022-11-29 18:15:17,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +6: [2022-11-29 18:15:17,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +6: [2022-11-29 18:15:17,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +6: [2022-11-29 18:15:17,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +6: [2022-11-29 18:15:17,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +6: [2022-11-29 18:15:17,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +6: [2022-11-29 18:15:17,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: successfully saved checkpoint at iteration 13000 to checkpoints_146moscareap +7: time (ms) | save-checkpoint: 890.66 +7: iteration 13010/ 21553 | consumed samples: 3330560 | consumed tokens: 6820986880 | elapsed time per iteration (s): 0.41 | learning rate: 8.229E-05 | global batch size: 256 | lm loss: 3.008704E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 626.749 | TFLOPs: 21.94 | +7: iteration 13020/ 21553 | consumed samples: 3333120 | consumed tokens: 6826229760 | elapsed time per iteration (s): 0.31 | learning rate: 8.216E-05 | global batch size: 256 | lm loss: 3.023075E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.935 | TFLOPs: 28.63 | +7: iteration 13030/ 21553 | consumed samples: 3335680 | consumed tokens: 6831472640 | elapsed time per iteration (s): 0.31 | learning rate: 8.204E-05 | global batch size: 256 | lm loss: 3.024826E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.044 | TFLOPs: 28.53 | +7: iteration 13040/ 21553 | consumed samples: 3338240 | consumed tokens: 6836715520 | elapsed time per iteration (s): 0.34 | learning rate: 8.191E-05 | global batch size: 256 | lm loss: 3.003235E+00 | grad norm: 0.397 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 762.675 | TFLOPs: 26.70 | +7: iteration 13050/ 21553 | consumed samples: 3340800 | consumed tokens: 6841958400 | elapsed time per iteration (s): 0.31 | learning rate: 8.179E-05 | global batch size: 256 | lm loss: 2.992185E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.661 | TFLOPs: 28.97 | +7: iteration 13060/ 21553 | consumed samples: 3343360 | consumed tokens: 6847201280 | elapsed time per iteration (s): 0.31 | learning rate: 8.166E-05 | global batch size: 256 | lm loss: 3.034209E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.671 | TFLOPs: 28.69 | +7: iteration 13070/ 21553 | consumed samples: 3345920 | consumed tokens: 6852444160 | elapsed time per iteration (s): 0.31 | learning rate: 8.153E-05 | global batch size: 256 | lm loss: 2.985222E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.396 | TFLOPs: 28.96 | +7: iteration 13080/ 21553 | consumed samples: 3348480 | consumed tokens: 6857687040 | elapsed time per iteration (s): 0.31 | learning rate: 8.141E-05 | global batch size: 256 | lm loss: 3.028238E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.721 | TFLOPs: 29.01 | +7: iteration 13090/ 21553 | consumed samples: 3351040 | consumed tokens: 6862929920 | elapsed time per iteration (s): 0.31 | learning rate: 8.128E-05 | global batch size: 256 | lm loss: 3.034699E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.474 | TFLOPs: 28.48 | +7: iteration 13100/ 21553 | consumed samples: 3353600 | consumed tokens: 6868172800 | elapsed time per iteration (s): 0.31 | learning rate: 8.116E-05 | global batch size: 256 | lm loss: 3.044116E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.762 | TFLOPs: 29.05 | +7: iteration 13110/ 21553 | consumed samples: 3356160 | consumed tokens: 6873415680 | elapsed time per iteration (s): 0.31 | learning rate: 8.103E-05 | global batch size: 256 | lm loss: 2.988535E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.503 | TFLOPs: 29.18 | +7: iteration 13120/ 21553 | consumed samples: 3358720 | consumed tokens: 6878658560 | elapsed time per iteration (s): 0.31 | learning rate: 8.091E-05 | global batch size: 256 | lm loss: 3.003027E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.619 | TFLOPs: 28.52 | +7: iteration 13130/ 21553 | consumed samples: 3361280 | consumed tokens: 6883901440 | elapsed time per iteration (s): 0.31 | learning rate: 8.078E-05 | global batch size: 256 | lm loss: 3.008380E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.839 | TFLOPs: 29.05 | +7: iteration 13140/ 21553 | consumed samples: 3363840 | consumed tokens: 6889144320 | elapsed time per iteration (s): 0.31 | learning rate: 8.066E-05 | global batch size: 256 | lm loss: 3.011117E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.085 | TFLOPs: 28.92 | +7: iteration 13150/ 21553 | consumed samples: 3366400 | consumed tokens: 6894387200 | elapsed time per iteration (s): 0.31 | learning rate: 8.053E-05 | global batch size: 256 | lm loss: 3.025544E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.133 | TFLOPs: 28.54 | +7: iteration 13160/ 21553 | consumed samples: 3368960 | consumed tokens: 6899630080 | elapsed time per iteration (s): 0.31 | learning rate: 8.041E-05 | global batch size: 256 | lm loss: 3.021735E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.095 | TFLOPs: 29.20 | +7: iteration 13170/ 21553 | consumed samples: 3371520 | consumed tokens: 6904872960 | elapsed time per iteration (s): 0.32 | learning rate: 8.028E-05 | global batch size: 256 | lm loss: 3.029069E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.870 | TFLOPs: 28.39 | +7: iteration 13180/ 21553 | consumed samples: 3374080 | consumed tokens: 6910115840 | elapsed time per iteration (s): 0.32 | learning rate: 8.016E-05 | global batch size: 256 | lm loss: 3.013885E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 804.318 | TFLOPs: 28.16 | +7: iteration 13190/ 21553 | consumed samples: 3376640 | consumed tokens: 6915358720 | elapsed time per iteration (s): 0.32 | learning rate: 8.003E-05 | global batch size: 256 | lm loss: 3.007264E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.632 | TFLOPs: 28.45 | +7: iteration 13200/ 21553 | consumed samples: 3379200 | consumed tokens: 6920601600 | elapsed time per iteration (s): 0.31 | learning rate: 7.991E-05 | global batch size: 256 | lm loss: 3.016214E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.153 | TFLOPs: 28.75 | +7: iteration 13210/ 21553 | consumed samples: 3381760 | consumed tokens: 6925844480 | elapsed time per iteration (s): 0.31 | learning rate: 7.978E-05 | global batch size: 256 | lm loss: 3.008058E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.944 | TFLOPs: 28.63 | +7: iteration 13220/ 21553 | consumed samples: 3384320 | consumed tokens: 6931087360 | elapsed time per iteration (s): 0.31 | learning rate: 7.966E-05 | global batch size: 256 | lm loss: 2.993146E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.026 | TFLOPs: 28.85 | +7: iteration 13230/ 21553 | consumed samples: 3386880 | consumed tokens: 6936330240 | elapsed time per iteration (s): 0.32 | learning rate: 7.953E-05 | global batch size: 256 | lm loss: 2.984136E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.141 | TFLOPs: 28.43 | +7: iteration 13240/ 21553 | consumed samples: 3389440 | consumed tokens: 6941573120 | elapsed time per iteration (s): 0.31 | learning rate: 7.941E-05 | global batch size: 256 | lm loss: 3.000553E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.835 | TFLOPs: 29.30 | +7: iteration 13250/ 21553 | consumed samples: 3392000 | consumed tokens: 6946816000 | elapsed time per iteration (s): 0.31 | learning rate: 7.928E-05 | global batch size: 256 | lm loss: 3.034795E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.297 | TFLOPs: 29.17 | +7: iteration 13260/ 21553 | consumed samples: 3394560 | consumed tokens: 6952058880 | elapsed time per iteration (s): 0.32 | learning rate: 7.916E-05 | global batch size: 256 | lm loss: 2.996362E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 806.680 | TFLOPs: 28.24 | +7: iteration 13270/ 21553 | consumed samples: 3397120 | consumed tokens: 6957301760 | elapsed time per iteration (s): 0.31 | learning rate: 7.903E-05 | global batch size: 256 | lm loss: 3.022998E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.361 | TFLOPs: 28.96 | +7: iteration 13280/ 21553 | consumed samples: 3399680 | consumed tokens: 6962544640 | elapsed time per iteration (s): 0.31 | learning rate: 7.891E-05 | global batch size: 256 | lm loss: 3.019759E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.559 | TFLOPs: 29.29 | +7: iteration 13290/ 21553 | consumed samples: 3402240 | consumed tokens: 6967787520 | elapsed time per iteration (s): 0.31 | learning rate: 7.878E-05 | global batch size: 256 | lm loss: 3.007799E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.845 | TFLOPs: 29.30 | +7: iteration 13300/ 21553 | consumed samples: 3404800 | consumed tokens: 6973030400 | elapsed time per iteration (s): 0.31 | learning rate: 7.866E-05 | global batch size: 256 | lm loss: 3.003292E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.391 | TFLOPs: 29.10 | +7: iteration 13310/ 21553 | consumed samples: 3407360 | consumed tokens: 6978273280 | elapsed time per iteration (s): 0.31 | learning rate: 7.854E-05 | global batch size: 256 | lm loss: 2.976094E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.550 | TFLOPs: 29.04 | +7: iteration 13320/ 21553 | consumed samples: 3409920 | consumed tokens: 6983516160 | elapsed time per iteration (s): 0.31 | learning rate: 7.841E-05 | global batch size: 256 | lm loss: 2.998832E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.907 | TFLOPs: 28.91 | +7: iteration 13330/ 21553 | consumed samples: 3412480 | consumed tokens: 6988759040 | elapsed time per iteration (s): 0.31 | learning rate: 7.829E-05 | global batch size: 256 | lm loss: 3.032313E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.700 | TFLOPs: 28.49 | +7: iteration 13340/ 21553 | consumed samples: 3415040 | consumed tokens: 6994001920 | elapsed time per iteration (s): 0.31 | learning rate: 7.816E-05 | global batch size: 256 | lm loss: 3.032935E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.015 | TFLOPs: 28.95 | +7: iteration 13350/ 21553 | consumed samples: 3417600 | consumed tokens: 6999244800 | elapsed time per iteration (s): 0.31 | learning rate: 7.804E-05 | global batch size: 256 | lm loss: 3.016091E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.944 | TFLOPs: 28.56 | +7: iteration 13360/ 21553 | consumed samples: 3420160 | consumed tokens: 7004487680 | elapsed time per iteration (s): 0.32 | learning rate: 7.792E-05 | global batch size: 256 | lm loss: 3.035736E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 797.736 | TFLOPs: 27.93 | +7: iteration 13370/ 21553 | consumed samples: 3422720 | consumed tokens: 7009730560 | elapsed time per iteration (s): 0.31 | learning rate: 7.779E-05 | global batch size: 256 | lm loss: 3.037720E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.666 | TFLOPs: 28.87 | +7: iteration 13380/ 21553 | consumed samples: 3425280 | consumed tokens: 7014973440 | elapsed time per iteration (s): 0.31 | learning rate: 7.767E-05 | global batch size: 256 | lm loss: 3.027312E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.245 | TFLOPs: 28.61 | +7: iteration 13390/ 21553 | consumed samples: 3427840 | consumed tokens: 7020216320 | elapsed time per iteration (s): 0.31 | learning rate: 7.754E-05 | global batch size: 256 | lm loss: 3.014574E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.029 | TFLOPs: 28.74 | +7: iteration 13400/ 21553 | consumed samples: 3430400 | consumed tokens: 7025459200 | elapsed time per iteration (s): 0.31 | learning rate: 7.742E-05 | global batch size: 256 | lm loss: 2.991218E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.440 | TFLOPs: 28.86 | +7: iteration 13410/ 21553 | consumed samples: 3432960 | consumed tokens: 7030702080 | elapsed time per iteration (s): 0.31 | learning rate: 7.730E-05 | global batch size: 256 | lm loss: 3.006425E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.518 | TFLOPs: 28.76 | +7: iteration 13420/ 21553 | consumed samples: 3435520 | consumed tokens: 7035944960 | elapsed time per iteration (s): 0.31 | learning rate: 7.717E-05 | global batch size: 256 | lm loss: 3.001597E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.864 | TFLOPs: 28.88 | +7: iteration 13430/ 21553 | consumed samples: 3438080 | consumed tokens: 7041187840 | elapsed time per iteration (s): 0.31 | learning rate: 7.705E-05 | global batch size: 256 | lm loss: 3.016398E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.688 | TFLOPs: 28.84 | +7: iteration 13440/ 21553 | consumed samples: 3440640 | consumed tokens: 7046430720 | elapsed time per iteration (s): 0.53 | learning rate: 7.693E-05 | global batch size: 256 | lm loss: 2.998532E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 482.718 | TFLOPs: 16.90 | +7: iteration 13450/ 21553 | consumed samples: 3443200 | consumed tokens: 7051673600 | elapsed time per iteration (s): 0.36 | learning rate: 7.680E-05 | global batch size: 256 | lm loss: 3.006501E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 701.815 | TFLOPs: 24.57 | +7: iteration 13460/ 21553 | consumed samples: 3445760 | consumed tokens: 7056916480 | elapsed time per iteration (s): 0.32 | learning rate: 7.668E-05 | global batch size: 256 | lm loss: 3.019754E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 807.993 | TFLOPs: 28.29 | +7: iteration 13470/ 21553 | consumed samples: 3448320 | consumed tokens: 7062159360 | elapsed time per iteration (s): 0.31 | learning rate: 7.656E-05 | global batch size: 256 | lm loss: 2.995329E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.820 | TFLOPs: 28.63 | +7: iteration 13480/ 21553 | consumed samples: 3450880 | consumed tokens: 7067402240 | elapsed time per iteration (s): 0.31 | learning rate: 7.644E-05 | global batch size: 256 | lm loss: 3.009017E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.479 | TFLOPs: 28.48 | +7: iteration 13490/ 21553 | consumed samples: 3453440 | consumed tokens: 7072645120 | elapsed time per iteration (s): 0.31 | learning rate: 7.631E-05 | global batch size: 256 | lm loss: 3.019187E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.925 | TFLOPs: 28.88 | +7: iteration 13500/ 21553 | consumed samples: 3456000 | consumed tokens: 7077888000 | elapsed time per iteration (s): 0.33 | learning rate: 7.619E-05 | global batch size: 256 | lm loss: 3.003338E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 776.517 | TFLOPs: 27.18 | +7: iteration 13510/ 21553 | consumed samples: 3458560 | consumed tokens: 7083130880 | elapsed time per iteration (s): 0.32 | learning rate: 7.607E-05 | global batch size: 256 | lm loss: 3.020750E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 805.273 | TFLOPs: 28.19 | +7: iteration 13520/ 21553 | consumed samples: 3461120 | consumed tokens: 7088373760 | elapsed time per iteration (s): 0.31 | learning rate: 7.594E-05 | global batch size: 256 | lm loss: 3.006097E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.825 | TFLOPs: 28.45 | +7: iteration 13530/ 21553 | consumed samples: 3463680 | consumed tokens: 7093616640 | elapsed time per iteration (s): 0.31 | learning rate: 7.582E-05 | global batch size: 256 | lm loss: 2.979517E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.882 | TFLOPs: 29.05 | +7: iteration 13540/ 21553 | consumed samples: 3466240 | consumed tokens: 7098859520 | elapsed time per iteration (s): 0.31 | learning rate: 7.570E-05 | global batch size: 256 | lm loss: 2.987568E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.123 | TFLOPs: 29.10 | +7: iteration 13550/ 21553 | consumed samples: 3468800 | consumed tokens: 7104102400 | elapsed time per iteration (s): 0.30 | learning rate: 7.558E-05 | global batch size: 256 | lm loss: 2.993028E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.561 | TFLOPs: 29.60 | +7: iteration 13560/ 21553 | consumed samples: 3471360 | consumed tokens: 7109345280 | elapsed time per iteration (s): 0.31 | learning rate: 7.545E-05 | global batch size: 256 | lm loss: 3.018436E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.855 | TFLOPs: 28.67 | +7: iteration 13570/ 21553 | consumed samples: 3473920 | consumed tokens: 7114588160 | elapsed time per iteration (s): 0.31 | learning rate: 7.533E-05 | global batch size: 256 | lm loss: 3.014972E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.735 | TFLOPs: 28.84 | +7: iteration 13580/ 21553 | consumed samples: 3476480 | consumed tokens: 7119831040 | elapsed time per iteration (s): 0.31 | learning rate: 7.521E-05 | global batch size: 256 | lm loss: 3.014515E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.275 | TFLOPs: 28.61 | +7: iteration 13590/ 21553 | consumed samples: 3479040 | consumed tokens: 7125073920 | elapsed time per iteration (s): 0.31 | learning rate: 7.509E-05 | global batch size: 256 | lm loss: 3.038348E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.349 | TFLOPs: 28.86 | +7: iteration 13600/ 21553 | consumed samples: 3481600 | consumed tokens: 7130316800 | elapsed time per iteration (s): 0.32 | learning rate: 7.497E-05 | global batch size: 256 | lm loss: 3.009688E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.920 | TFLOPs: 28.39 | +7: iteration 13610/ 21553 | consumed samples: 3484160 | consumed tokens: 7135559680 | elapsed time per iteration (s): 0.30 | learning rate: 7.484E-05 | global batch size: 256 | lm loss: 3.010369E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.002 | TFLOPs: 29.41 | +7: iteration 13620/ 21553 | consumed samples: 3486720 | consumed tokens: 7140802560 | elapsed time per iteration (s): 0.31 | learning rate: 7.472E-05 | global batch size: 256 | lm loss: 2.971878E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.757 | TFLOPs: 28.49 | +7: iteration 13630/ 21553 | consumed samples: 3489280 | consumed tokens: 7146045440 | elapsed time per iteration (s): 0.32 | learning rate: 7.460E-05 | global batch size: 256 | lm loss: 3.034702E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 799.782 | TFLOPs: 28.00 | +7: iteration 13640/ 21553 | consumed samples: 3491840 | consumed tokens: 7151288320 | elapsed time per iteration (s): 0.30 | learning rate: 7.448E-05 | global batch size: 256 | lm loss: 3.024898E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.147 | TFLOPs: 29.48 | +7: iteration 13650/ 21553 | consumed samples: 3494400 | consumed tokens: 7156531200 | elapsed time per iteration (s): 0.31 | learning rate: 7.436E-05 | global batch size: 256 | lm loss: 3.020448E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.783 | TFLOPs: 28.73 | +7: iteration 13660/ 21553 | consumed samples: 3496960 | consumed tokens: 7161774080 | elapsed time per iteration (s): 0.31 | learning rate: 7.423E-05 | global batch size: 256 | lm loss: 3.026060E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.889 | TFLOPs: 29.26 | +7: iteration 13670/ 21553 | consumed samples: 3499520 | consumed tokens: 7167016960 | elapsed time per iteration (s): 0.32 | learning rate: 7.411E-05 | global batch size: 256 | lm loss: 2.998920E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 793.670 | TFLOPs: 27.78 | +7: iteration 13680/ 21553 | consumed samples: 3502080 | consumed tokens: 7172259840 | elapsed time per iteration (s): 0.31 | learning rate: 7.399E-05 | global batch size: 256 | lm loss: 3.011267E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.299 | TFLOPs: 29.28 | +7: iteration 13690/ 21553 | consumed samples: 3504640 | consumed tokens: 7177502720 | elapsed time per iteration (s): 0.31 | learning rate: 7.387E-05 | global batch size: 256 | lm loss: 2.979966E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.871 | TFLOPs: 28.49 | +7: iteration 13700/ 21553 | consumed samples: 3507200 | consumed tokens: 7182745600 | elapsed time per iteration (s): 0.31 | learning rate: 7.375E-05 | global batch size: 256 | lm loss: 2.997007E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.242 | TFLOPs: 28.68 | +7: iteration 13710/ 21553 | consumed samples: 3509760 | consumed tokens: 7187988480 | elapsed time per iteration (s): 0.30 | learning rate: 7.363E-05 | global batch size: 256 | lm loss: 3.032613E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.692 | TFLOPs: 29.54 | +7: iteration 13720/ 21553 | consumed samples: 3512320 | consumed tokens: 7193231360 | elapsed time per iteration (s): 0.31 | learning rate: 7.351E-05 | global batch size: 256 | lm loss: 2.983518E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.518 | TFLOPs: 29.28 | +7: iteration 13730/ 21553 | consumed samples: 3514880 | consumed tokens: 7198474240 | elapsed time per iteration (s): 0.31 | learning rate: 7.339E-05 | global batch size: 256 | lm loss: 3.017857E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.846 | TFLOPs: 29.02 | +7: iteration 13740/ 21553 | consumed samples: 3517440 | consumed tokens: 7203717120 | elapsed time per iteration (s): 0.30 | learning rate: 7.326E-05 | global batch size: 256 | lm loss: 2.988370E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.794 | TFLOPs: 29.40 | +7: iteration 13750/ 21553 | consumed samples: 3520000 | consumed tokens: 7208960000 | elapsed time per iteration (s): 0.31 | learning rate: 7.314E-05 | global batch size: 256 | lm loss: 3.013315E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.921 | TFLOPs: 28.91 | +7: iteration 13760/ 21553 | consumed samples: 3522560 | consumed tokens: 7214202880 | elapsed time per iteration (s): 0.31 | learning rate: 7.302E-05 | global batch size: 256 | lm loss: 2.991409E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.522 | TFLOPs: 28.90 | +7: iteration 13770/ 21553 | consumed samples: 3525120 | consumed tokens: 7219445760 | elapsed time per iteration (s): 0.31 | learning rate: 7.290E-05 | global batch size: 256 | lm loss: 3.013976E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.071 | TFLOPs: 29.16 | +7: iteration 13780/ 21553 | consumed samples: 3527680 | consumed tokens: 7224688640 | elapsed time per iteration (s): 0.31 | learning rate: 7.278E-05 | global batch size: 256 | lm loss: 2.989808E+00 | grad norm: 0.367 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.022 | TFLOPs: 29.30 | +7: iteration 13790/ 21553 | consumed samples: 3530240 | consumed tokens: 7229931520 | elapsed time per iteration (s): 0.30 | learning rate: 7.266E-05 | global batch size: 256 | lm loss: 3.006894E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 846.190 | TFLOPs: 29.62 | +7: iteration 13800/ 21553 | consumed samples: 3532800 | consumed tokens: 7235174400 | elapsed time per iteration (s): 0.32 | learning rate: 7.254E-05 | global batch size: 256 | lm loss: 2.992574E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 802.540 | TFLOPs: 28.09 | +7: iteration 13810/ 21553 | consumed samples: 3535360 | consumed tokens: 7240417280 | elapsed time per iteration (s): 0.32 | learning rate: 7.242E-05 | global batch size: 256 | lm loss: 3.007756E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.263 | TFLOPs: 28.37 | +7: iteration 13820/ 21553 | consumed samples: 3537920 | consumed tokens: 7245660160 | elapsed time per iteration (s): 0.30 | learning rate: 7.230E-05 | global batch size: 256 | lm loss: 2.998997E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 847.320 | TFLOPs: 29.66 | +7: iteration 13830/ 21553 | consumed samples: 3540480 | consumed tokens: 7250903040 | elapsed time per iteration (s): 0.31 | learning rate: 7.218E-05 | global batch size: 256 | lm loss: 3.007331E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.605 | TFLOPs: 28.55 | +7: iteration 13840/ 21553 | consumed samples: 3543040 | consumed tokens: 7256145920 | elapsed time per iteration (s): 0.31 | learning rate: 7.206E-05 | global batch size: 256 | lm loss: 2.996061E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.816 | TFLOPs: 29.29 | +7: iteration 13850/ 21553 | consumed samples: 3545600 | consumed tokens: 7261388800 | elapsed time per iteration (s): 0.31 | learning rate: 7.194E-05 | global batch size: 256 | lm loss: 2.975836E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.764 | TFLOPs: 29.19 | +7: iteration 13860/ 21553 | consumed samples: 3548160 | consumed tokens: 7266631680 | elapsed time per iteration (s): 0.31 | learning rate: 7.182E-05 | global batch size: 256 | lm loss: 3.001694E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.703 | TFLOPs: 29.33 | +7: iteration 13870/ 21553 | consumed samples: 3550720 | consumed tokens: 7271874560 | elapsed time per iteration (s): 0.31 | learning rate: 7.170E-05 | global batch size: 256 | lm loss: 2.994279E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.910 | TFLOPs: 29.23 | +7: iteration 13880/ 21553 | consumed samples: 3553280 | consumed tokens: 7277117440 | elapsed time per iteration (s): 0.31 | learning rate: 7.158E-05 | global batch size: 256 | lm loss: 2.982671E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.049 | TFLOPs: 29.06 | +7: iteration 13890/ 21553 | consumed samples: 3555840 | consumed tokens: 7282360320 | elapsed time per iteration (s): 0.33 | learning rate: 7.146E-05 | global batch size: 256 | lm loss: 3.005026E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 781.479 | TFLOPs: 27.36 | +7: iteration 13900/ 21553 | consumed samples: 3558400 | consumed tokens: 7287603200 | elapsed time per iteration (s): 0.31 | learning rate: 7.134E-05 | global batch size: 256 | lm loss: 3.002399E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.264 | TFLOPs: 29.10 | +7: iteration 13910/ 21553 | consumed samples: 3560960 | consumed tokens: 7292846080 | elapsed time per iteration (s): 0.31 | learning rate: 7.122E-05 | global batch size: 256 | lm loss: 2.986167E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.580 | TFLOPs: 28.66 | +7: iteration 13920/ 21553 | consumed samples: 3563520 | consumed tokens: 7298088960 | elapsed time per iteration (s): 0.32 | learning rate: 7.110E-05 | global batch size: 256 | lm loss: 2.994644E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 804.683 | TFLOPs: 28.17 | +7: iteration 13930/ 21553 | consumed samples: 3566080 | consumed tokens: 7303331840 | elapsed time per iteration (s): 0.31 | learning rate: 7.098E-05 | global batch size: 256 | lm loss: 2.991572E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.546 | TFLOPs: 28.62 | +7: iteration 13940/ 21553 | consumed samples: 3568640 | consumed tokens: 7308574720 | elapsed time per iteration (s): 0.31 | learning rate: 7.086E-05 | global batch size: 256 | lm loss: 2.990836E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.713 | TFLOPs: 28.45 | +7: iteration 13950/ 21553 | consumed samples: 3571200 | consumed tokens: 7313817600 | elapsed time per iteration (s): 0.31 | learning rate: 7.074E-05 | global batch size: 256 | lm loss: 3.028601E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.960 | TFLOPs: 28.88 | +7: iteration 13960/ 21553 | consumed samples: 3573760 | consumed tokens: 7319060480 | elapsed time per iteration (s): 0.31 | learning rate: 7.062E-05 | global batch size: 256 | lm loss: 2.980444E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.400 | TFLOPs: 28.68 | +7: iteration 13970/ 21553 | consumed samples: 3576320 | consumed tokens: 7324303360 | elapsed time per iteration (s): 0.31 | learning rate: 7.050E-05 | global batch size: 256 | lm loss: 3.015377E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.153 | TFLOPs: 29.10 | +7: iteration 13980/ 21553 | consumed samples: 3578880 | consumed tokens: 7329546240 | elapsed time per iteration (s): 0.30 | learning rate: 7.038E-05 | global batch size: 256 | lm loss: 3.016470E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.792 | TFLOPs: 29.61 | +7: iteration 13990/ 21553 | consumed samples: 3581440 | consumed tokens: 7334789120 | elapsed time per iteration (s): 0.32 | learning rate: 7.027E-05 | global batch size: 256 | lm loss: 2.994829E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 809.144 | TFLOPs: 28.33 | +0: [2022-11-29 18:20:31,647] [INFO] [logging.py:68:log_dist] [Rank 0] step=14000, skipped=0, lr=[7.014654688611906e-05, 7.014654688611906e-05, 7.014654688611906e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 14000/ 21553 | consumed samples: 3584000 | consumed tokens: 7340032000 | elapsed time per iteration (s): 0.30 | learning rate: 7.015E-05 | global batch size: 256 | lm loss: 2.971956E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.287 | TFLOPs: 29.42 | +0: steps: 14000 loss: 3.0100 iter time (s): 0.312 samples/sec: 821.298 +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 14000 | lm loss value: 2.998721E+00 | lm loss PPL: 2.005986E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 14000 to checkpoints_146moscareap +0: [2022-11-29 18:20:31,831] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step14000 is begin to save! +0: [2022-11-29 18:20:31,857] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:20:31,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:20:31,944] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:20:31,960] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:20:31,960] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:20:31,976] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:20:31,976] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:20:31,991] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:20:31,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:20:32,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:20:32,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:20:32,023] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:20:32,023] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:20:32,038] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:20:32,038] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:20:32,054] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:20:32,054] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:20:32,069] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:20:32,069] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:20:32,085] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:20:32,085] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:20:32,100] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:20:32,101] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/layer_13-model_00-model_states.pt... +0: [2022-11-29 18:20:32,116] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/layer_13-model_00-model_states.pt. +0: [2022-11-29 18:20:32,116] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:20:32,131] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:20:32,132] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/layer_15-model_00-model_states.pt... +0: [2022-11-29 18:20:32,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/layer_15-model_00-model_states.pt. +0: [2022-11-29 18:20:32,147] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/layer_16-model_00-model_states.pt... +0: [2022-11-29 18:20:32,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/layer_16-model_00-model_states.pt. +0: [2022-11-29 18:20:32,163] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/layer_17-model_00-model_states.pt... +0: [2022-11-29 18:20:32,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/layer_17-model_00-model_states.pt. +0: [2022-11-29 18:20:32,178] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/layer_19-model_00-model_states.pt... +0: [2022-11-29 18:20:32,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/layer_19-model_00-model_states.pt. +0: [2022-11-29 18:20:32,180] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_146moscareap/global_step14000/mp_rank_00_model_states.pt +0: [2022-11-29 18:20:32,180] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:20:32,182] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:20:32,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:20:32,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:20:32,232] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:20:32,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:20:32,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +7: [2022-11-29 18:20:32,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:20:32,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:20:32,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +7: [2022-11-29 18:20:32,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:20:32,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:20:32,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +7: [2022-11-29 18:20:32,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:20:32,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:20:32,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +7: [2022-11-29 18:20:32,236] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:20:32,236] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:20:32,236] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:20:32,236] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +7: [2022-11-29 18:20:32,236] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:20:32,236] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:20:32,236] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:20:32,236] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +7: [2022-11-29 18:20:32,236] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:20:32,236] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:20:32,236] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +7: [2022-11-29 18:20:32,236] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 18:20:32,237] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:20:32,237] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:20:32,237] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 18:20:32,237] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:20:32,237] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:20:32,237] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:20:32,237] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:20:32,237] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 18:20:32,237] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +7: [2022-11-29 18:20:32,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:20:32,241] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:20:32,241] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +6: [2022-11-29 18:20:32,242] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:20:32,243] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:20:32,243] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +6: [2022-11-29 18:20:32,243] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:20:32,243] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:20:32,243] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +6: [2022-11-29 18:20:32,243] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:20:32,243] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:20:32,243] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +6: [2022-11-29 18:20:32,243] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:20:32,243] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:20:32,243] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 18:20:32,244] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:20:32,244] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:20:32,245] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 18:20:32,245] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:20:32,245] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:20:32,245] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 18:20:32,245] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:20:32,245] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:20:32,245] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +6: [2022-11-29 18:20:32,249] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:20:32,249] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:20:32,249] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +6: [2022-11-29 18:20:32,249] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:20:32,249] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:20:32,249] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +6: [2022-11-29 18:20:32,249] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:20:32,249] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:20:32,249] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +6: [2022-11-29 18:20:32,249] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:20:32,250] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:20:32,250] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 18:20:32,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:20:32,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +4: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +4: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +4: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +4: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +4: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +4: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +4: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +4: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +5: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +3: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +5: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +5: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:20:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +3: [2022-11-29 18:20:32,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +5: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +5: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 18:20:32,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +1: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +5: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +5: [2022-11-29 18:20:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 18:20:32,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:20:32,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:20:32,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:20:32,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:20:32,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:20:32,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +1: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 18:20:32,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:20:32,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:20:32,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:20:32,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +3: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 18:20:32,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:20:32,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:20:32,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:20:32,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step14000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 18:20:32,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: successfully saved checkpoint at iteration 14000 to checkpoints_146moscareap +7: time (ms) | save-checkpoint: 870.03 +7: iteration 14010/ 21553 | consumed samples: 3586560 | consumed tokens: 7345274880 | elapsed time per iteration (s): 0.41 | learning rate: 7.003E-05 | global batch size: 256 | lm loss: 3.022050E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 627.430 | TFLOPs: 21.96 | +7: iteration 14020/ 21553 | consumed samples: 3589120 | consumed tokens: 7350517760 | elapsed time per iteration (s): 0.31 | learning rate: 6.991E-05 | global batch size: 256 | lm loss: 2.968876E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.367 | TFLOPs: 28.72 | +7: iteration 14030/ 21553 | consumed samples: 3591680 | consumed tokens: 7355760640 | elapsed time per iteration (s): 0.31 | learning rate: 6.979E-05 | global batch size: 256 | lm loss: 2.990575E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.783 | TFLOPs: 29.19 | +7: iteration 14040/ 21553 | consumed samples: 3594240 | consumed tokens: 7361003520 | elapsed time per iteration (s): 0.31 | learning rate: 6.967E-05 | global batch size: 256 | lm loss: 2.980007E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.882 | TFLOPs: 28.84 | +7: iteration 14050/ 21553 | consumed samples: 3596800 | consumed tokens: 7366246400 | elapsed time per iteration (s): 0.31 | learning rate: 6.955E-05 | global batch size: 256 | lm loss: 2.997806E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.592 | TFLOPs: 28.76 | +7: iteration 14060/ 21553 | consumed samples: 3599360 | consumed tokens: 7371489280 | elapsed time per iteration (s): 0.31 | learning rate: 6.944E-05 | global batch size: 256 | lm loss: 3.003987E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.491 | TFLOPs: 28.65 | +7: iteration 14070/ 21553 | consumed samples: 3601920 | consumed tokens: 7376732160 | elapsed time per iteration (s): 0.30 | learning rate: 6.932E-05 | global batch size: 256 | lm loss: 2.986656E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 847.682 | TFLOPs: 29.68 | +7: iteration 14080/ 21553 | consumed samples: 3604480 | consumed tokens: 7381975040 | elapsed time per iteration (s): 0.33 | learning rate: 6.920E-05 | global batch size: 256 | lm loss: 3.007317E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 778.541 | TFLOPs: 27.25 | +7: iteration 14090/ 21553 | consumed samples: 3607040 | consumed tokens: 7387217920 | elapsed time per iteration (s): 0.31 | learning rate: 6.908E-05 | global batch size: 256 | lm loss: 3.007385E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.975 | TFLOPs: 28.81 | +7: iteration 14100/ 21553 | consumed samples: 3609600 | consumed tokens: 7392460800 | elapsed time per iteration (s): 0.31 | learning rate: 6.896E-05 | global batch size: 256 | lm loss: 2.979904E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.160 | TFLOPs: 28.47 | +7: iteration 14110/ 21553 | consumed samples: 3612160 | consumed tokens: 7397703680 | elapsed time per iteration (s): 0.35 | learning rate: 6.884E-05 | global batch size: 256 | lm loss: 3.000867E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 729.490 | TFLOPs: 25.54 | +7: iteration 14120/ 21553 | consumed samples: 3614720 | consumed tokens: 7402946560 | elapsed time per iteration (s): 0.32 | learning rate: 6.873E-05 | global batch size: 256 | lm loss: 3.009812E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 809.230 | TFLOPs: 28.33 | +7: iteration 14130/ 21553 | consumed samples: 3617280 | consumed tokens: 7408189440 | elapsed time per iteration (s): 0.40 | learning rate: 6.861E-05 | global batch size: 256 | lm loss: 3.006301E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 634.232 | TFLOPs: 22.20 | +7: iteration 14140/ 21553 | consumed samples: 3619840 | consumed tokens: 7413432320 | elapsed time per iteration (s): 0.32 | learning rate: 6.849E-05 | global batch size: 256 | lm loss: 2.964132E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 794.989 | TFLOPs: 27.83 | +7: iteration 14150/ 21553 | consumed samples: 3622400 | consumed tokens: 7418675200 | elapsed time per iteration (s): 0.31 | learning rate: 6.837E-05 | global batch size: 256 | lm loss: 2.967934E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.778 | TFLOPs: 28.49 | +7: iteration 14160/ 21553 | consumed samples: 3624960 | consumed tokens: 7423918080 | elapsed time per iteration (s): 0.31 | learning rate: 6.826E-05 | global batch size: 256 | lm loss: 3.014783E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.455 | TFLOPs: 28.55 | +7: iteration 14170/ 21553 | consumed samples: 3627520 | consumed tokens: 7429160960 | elapsed time per iteration (s): 0.31 | learning rate: 6.814E-05 | global batch size: 256 | lm loss: 2.982357E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.616 | TFLOPs: 29.04 | +7: iteration 14180/ 21553 | consumed samples: 3630080 | consumed tokens: 7434403840 | elapsed time per iteration (s): 0.31 | learning rate: 6.802E-05 | global batch size: 256 | lm loss: 3.003259E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.102 | TFLOPs: 29.20 | +7: iteration 14190/ 21553 | consumed samples: 3632640 | consumed tokens: 7439646720 | elapsed time per iteration (s): 0.30 | learning rate: 6.791E-05 | global batch size: 256 | lm loss: 3.001535E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.797 | TFLOPs: 29.43 | +7: iteration 14200/ 21553 | consumed samples: 3635200 | consumed tokens: 7444889600 | elapsed time per iteration (s): 0.31 | learning rate: 6.779E-05 | global batch size: 256 | lm loss: 3.007949E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.633 | TFLOPs: 28.83 | +7: iteration 14210/ 21553 | consumed samples: 3637760 | consumed tokens: 7450132480 | elapsed time per iteration (s): 0.30 | learning rate: 6.767E-05 | global batch size: 256 | lm loss: 2.979024E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 846.731 | TFLOPs: 29.64 | +7: iteration 14220/ 21553 | consumed samples: 3640320 | consumed tokens: 7455375360 | elapsed time per iteration (s): 0.41 | learning rate: 6.755E-05 | global batch size: 256 | lm loss: 2.980665E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 628.331 | TFLOPs: 22.00 | +7: iteration 14230/ 21553 | consumed samples: 3642880 | consumed tokens: 7460618240 | elapsed time per iteration (s): 0.31 | learning rate: 6.744E-05 | global batch size: 256 | lm loss: 3.004998E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.188 | TFLOPs: 29.38 | +7: iteration 14240/ 21553 | consumed samples: 3645440 | consumed tokens: 7465861120 | elapsed time per iteration (s): 0.31 | learning rate: 6.732E-05 | global batch size: 256 | lm loss: 2.984379E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.418 | TFLOPs: 28.58 | +7: iteration 14250/ 21553 | consumed samples: 3648000 | consumed tokens: 7471104000 | elapsed time per iteration (s): 0.30 | learning rate: 6.720E-05 | global batch size: 256 | lm loss: 2.991627E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.351 | TFLOPs: 29.38 | +7: iteration 14260/ 21553 | consumed samples: 3650560 | consumed tokens: 7476346880 | elapsed time per iteration (s): 0.31 | learning rate: 6.709E-05 | global batch size: 256 | lm loss: 2.991449E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.923 | TFLOPs: 28.77 | +7: iteration 14270/ 21553 | consumed samples: 3653120 | consumed tokens: 7481589760 | elapsed time per iteration (s): 0.77 | learning rate: 6.697E-05 | global batch size: 256 | lm loss: 2.999998E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.554 | TFLOPs: 11.57 | +7: iteration 14280/ 21553 | consumed samples: 3655680 | consumed tokens: 7486832640 | elapsed time per iteration (s): 0.38 | learning rate: 6.685E-05 | global batch size: 256 | lm loss: 3.010887E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 668.890 | TFLOPs: 23.42 | +7: iteration 14290/ 21553 | consumed samples: 3658240 | consumed tokens: 7492075520 | elapsed time per iteration (s): 0.32 | learning rate: 6.674E-05 | global batch size: 256 | lm loss: 2.999083E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 792.066 | TFLOPs: 27.73 | +7: iteration 14300/ 21553 | consumed samples: 3660800 | consumed tokens: 7497318400 | elapsed time per iteration (s): 0.31 | learning rate: 6.662E-05 | global batch size: 256 | lm loss: 2.997160E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.693 | TFLOPs: 28.94 | +7: iteration 14310/ 21553 | consumed samples: 3663360 | consumed tokens: 7502561280 | elapsed time per iteration (s): 0.32 | learning rate: 6.651E-05 | global batch size: 256 | lm loss: 2.954988E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.380 | TFLOPs: 28.30 | +7: iteration 14320/ 21553 | consumed samples: 3665920 | consumed tokens: 7507804160 | elapsed time per iteration (s): 0.31 | learning rate: 6.639E-05 | global batch size: 256 | lm loss: 3.001358E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.406 | TFLOPs: 28.97 | +7: iteration 14330/ 21553 | consumed samples: 3668480 | consumed tokens: 7513047040 | elapsed time per iteration (s): 0.31 | learning rate: 6.627E-05 | global batch size: 256 | lm loss: 2.992942E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.246 | TFLOPs: 29.06 | +7: iteration 14340/ 21553 | consumed samples: 3671040 | consumed tokens: 7518289920 | elapsed time per iteration (s): 0.31 | learning rate: 6.616E-05 | global batch size: 256 | lm loss: 2.991887E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.193 | TFLOPs: 28.68 | +7: iteration 14350/ 21553 | consumed samples: 3673600 | consumed tokens: 7523532800 | elapsed time per iteration (s): 0.31 | learning rate: 6.604E-05 | global batch size: 256 | lm loss: 3.013472E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.168 | TFLOPs: 28.71 | +7: iteration 14360/ 21553 | consumed samples: 3676160 | consumed tokens: 7528775680 | elapsed time per iteration (s): 0.31 | learning rate: 6.593E-05 | global batch size: 256 | lm loss: 2.999213E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.615 | TFLOPs: 28.76 | +7: iteration 14370/ 21553 | consumed samples: 3678720 | consumed tokens: 7534018560 | elapsed time per iteration (s): 0.32 | learning rate: 6.581E-05 | global batch size: 256 | lm loss: 2.984146E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 796.497 | TFLOPs: 27.88 | +7: iteration 14380/ 21553 | consumed samples: 3681280 | consumed tokens: 7539261440 | elapsed time per iteration (s): 0.32 | learning rate: 6.570E-05 | global batch size: 256 | lm loss: 2.985140E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.047 | TFLOPs: 28.43 | +7: iteration 14390/ 21553 | consumed samples: 3683840 | consumed tokens: 7544504320 | elapsed time per iteration (s): 0.31 | learning rate: 6.558E-05 | global batch size: 256 | lm loss: 3.003012E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.639 | TFLOPs: 28.73 | +7: iteration 14400/ 21553 | consumed samples: 3686400 | consumed tokens: 7549747200 | elapsed time per iteration (s): 0.32 | learning rate: 6.547E-05 | global batch size: 256 | lm loss: 3.007957E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 789.916 | TFLOPs: 27.65 | +7: iteration 14410/ 21553 | consumed samples: 3688960 | consumed tokens: 7554990080 | elapsed time per iteration (s): 0.32 | learning rate: 6.535E-05 | global batch size: 256 | lm loss: 3.009773E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 809.885 | TFLOPs: 28.35 | +7: iteration 14420/ 21553 | consumed samples: 3691520 | consumed tokens: 7560232960 | elapsed time per iteration (s): 0.32 | learning rate: 6.524E-05 | global batch size: 256 | lm loss: 2.966387E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 795.566 | TFLOPs: 27.85 | +7: iteration 14430/ 21553 | consumed samples: 3694080 | consumed tokens: 7565475840 | elapsed time per iteration (s): 0.32 | learning rate: 6.512E-05 | global batch size: 256 | lm loss: 2.993391E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 802.774 | TFLOPs: 28.10 | +7: iteration 14440/ 21553 | consumed samples: 3696640 | consumed tokens: 7570718720 | elapsed time per iteration (s): 0.31 | learning rate: 6.501E-05 | global batch size: 256 | lm loss: 2.986397E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.537 | TFLOPs: 28.86 | +7: iteration 14450/ 21553 | consumed samples: 3699200 | consumed tokens: 7575961600 | elapsed time per iteration (s): 0.32 | learning rate: 6.489E-05 | global batch size: 256 | lm loss: 3.003704E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.901 | TFLOPs: 28.39 | +7: iteration 14460/ 21553 | consumed samples: 3701760 | consumed tokens: 7581204480 | elapsed time per iteration (s): 0.31 | learning rate: 6.478E-05 | global batch size: 256 | lm loss: 3.002273E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.483 | TFLOPs: 28.83 | +7: iteration 14470/ 21553 | consumed samples: 3704320 | consumed tokens: 7586447360 | elapsed time per iteration (s): 0.31 | learning rate: 6.466E-05 | global batch size: 256 | lm loss: 3.006079E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.193 | TFLOPs: 28.61 | +7: iteration 14480/ 21553 | consumed samples: 3706880 | consumed tokens: 7591690240 | elapsed time per iteration (s): 0.31 | learning rate: 6.455E-05 | global batch size: 256 | lm loss: 2.988760E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.739 | TFLOPs: 29.12 | +7: iteration 14490/ 21553 | consumed samples: 3709440 | consumed tokens: 7596933120 | elapsed time per iteration (s): 0.31 | learning rate: 6.443E-05 | global batch size: 256 | lm loss: 3.000348E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.436 | TFLOPs: 29.32 | +7: iteration 14500/ 21553 | consumed samples: 3712000 | consumed tokens: 7602176000 | elapsed time per iteration (s): 0.30 | learning rate: 6.432E-05 | global batch size: 256 | lm loss: 2.988171E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.942 | TFLOPs: 29.61 | +7: iteration 14510/ 21553 | consumed samples: 3714560 | consumed tokens: 7607418880 | elapsed time per iteration (s): 0.31 | learning rate: 6.421E-05 | global batch size: 256 | lm loss: 2.985170E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.758 | TFLOPs: 28.80 | +7: iteration 14520/ 21553 | consumed samples: 3717120 | consumed tokens: 7612661760 | elapsed time per iteration (s): 0.31 | learning rate: 6.409E-05 | global batch size: 256 | lm loss: 2.978689E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.829 | TFLOPs: 28.84 | +7: iteration 14530/ 21553 | consumed samples: 3719680 | consumed tokens: 7617904640 | elapsed time per iteration (s): 0.31 | learning rate: 6.398E-05 | global batch size: 256 | lm loss: 2.982154E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.098 | TFLOPs: 29.20 | +7: iteration 14540/ 21553 | consumed samples: 3722240 | consumed tokens: 7623147520 | elapsed time per iteration (s): 0.32 | learning rate: 6.386E-05 | global batch size: 256 | lm loss: 2.965978E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 807.086 | TFLOPs: 28.25 | +7: iteration 14550/ 21553 | consumed samples: 3724800 | consumed tokens: 7628390400 | elapsed time per iteration (s): 0.32 | learning rate: 6.375E-05 | global batch size: 256 | lm loss: 2.987494E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 789.101 | TFLOPs: 27.62 | +7: iteration 14560/ 21553 | consumed samples: 3727360 | consumed tokens: 7633633280 | elapsed time per iteration (s): 0.32 | learning rate: 6.364E-05 | global batch size: 256 | lm loss: 2.958522E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.196 | TFLOPs: 28.40 | +7: iteration 14570/ 21553 | consumed samples: 3729920 | consumed tokens: 7638876160 | elapsed time per iteration (s): 0.33 | learning rate: 6.352E-05 | global batch size: 256 | lm loss: 2.966559E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 779.936 | TFLOPs: 27.30 | +7: iteration 14580/ 21553 | consumed samples: 3732480 | consumed tokens: 7644119040 | elapsed time per iteration (s): 0.42 | learning rate: 6.341E-05 | global batch size: 256 | lm loss: 2.975346E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 614.278 | TFLOPs: 21.50 | +7: iteration 14590/ 21553 | consumed samples: 3735040 | consumed tokens: 7649361920 | elapsed time per iteration (s): 0.31 | learning rate: 6.330E-05 | global batch size: 256 | lm loss: 2.988463E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.781 | TFLOPs: 28.80 | +7: iteration 14600/ 21553 | consumed samples: 3737600 | consumed tokens: 7654604800 | elapsed time per iteration (s): 0.31 | learning rate: 6.318E-05 | global batch size: 256 | lm loss: 2.993065E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.028 | TFLOPs: 28.81 | +7: iteration 14610/ 21553 | consumed samples: 3740160 | consumed tokens: 7659847680 | elapsed time per iteration (s): 0.32 | learning rate: 6.307E-05 | global batch size: 256 | lm loss: 2.977775E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 807.267 | TFLOPs: 28.26 | +7: iteration 14620/ 21553 | consumed samples: 3742720 | consumed tokens: 7665090560 | elapsed time per iteration (s): 0.30 | learning rate: 6.296E-05 | global batch size: 256 | lm loss: 3.014529E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.804 | TFLOPs: 29.50 | +7: iteration 14630/ 21553 | consumed samples: 3745280 | consumed tokens: 7670333440 | elapsed time per iteration (s): 0.31 | learning rate: 6.284E-05 | global batch size: 256 | lm loss: 2.967964E+00 | grad norm: 0.394 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.514 | TFLOPs: 28.58 | +7: iteration 14640/ 21553 | consumed samples: 3747840 | consumed tokens: 7675576320 | elapsed time per iteration (s): 0.30 | learning rate: 6.273E-05 | global batch size: 256 | lm loss: 3.019874E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.647 | TFLOPs: 29.39 | +7: iteration 14650/ 21553 | consumed samples: 3750400 | consumed tokens: 7680819200 | elapsed time per iteration (s): 0.31 | learning rate: 6.262E-05 | global batch size: 256 | lm loss: 2.980767E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.439 | TFLOPs: 29.00 | +7: iteration 14660/ 21553 | consumed samples: 3752960 | consumed tokens: 7686062080 | elapsed time per iteration (s): 0.31 | learning rate: 6.251E-05 | global batch size: 256 | lm loss: 2.994870E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.642 | TFLOPs: 29.36 | +7: iteration 14670/ 21553 | consumed samples: 3755520 | consumed tokens: 7691304960 | elapsed time per iteration (s): 0.31 | learning rate: 6.239E-05 | global batch size: 256 | lm loss: 2.989693E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.133 | TFLOPs: 29.06 | +7: iteration 14680/ 21553 | consumed samples: 3758080 | consumed tokens: 7696547840 | elapsed time per iteration (s): 0.32 | learning rate: 6.228E-05 | global batch size: 256 | lm loss: 2.965657E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 805.846 | TFLOPs: 28.21 | +7: iteration 14690/ 21553 | consumed samples: 3760640 | consumed tokens: 7701790720 | elapsed time per iteration (s): 0.31 | learning rate: 6.217E-05 | global batch size: 256 | lm loss: 2.997095E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.111 | TFLOPs: 29.13 | +7: iteration 14700/ 21553 | consumed samples: 3763200 | consumed tokens: 7707033600 | elapsed time per iteration (s): 0.31 | learning rate: 6.206E-05 | global batch size: 256 | lm loss: 2.973527E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.113 | TFLOPs: 28.50 | +7: iteration 14710/ 21553 | consumed samples: 3765760 | consumed tokens: 7712276480 | elapsed time per iteration (s): 0.32 | learning rate: 6.194E-05 | global batch size: 256 | lm loss: 2.985083E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.242 | TFLOPs: 28.29 | +7: iteration 14720/ 21553 | consumed samples: 3768320 | consumed tokens: 7717519360 | elapsed time per iteration (s): 0.31 | learning rate: 6.183E-05 | global batch size: 256 | lm loss: 2.977808E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.226 | TFLOPs: 28.85 | +7: iteration 14730/ 21553 | consumed samples: 3770880 | consumed tokens: 7722762240 | elapsed time per iteration (s): 0.32 | learning rate: 6.172E-05 | global batch size: 256 | lm loss: 2.980989E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 806.869 | TFLOPs: 28.25 | +7: iteration 14740/ 21553 | consumed samples: 3773440 | consumed tokens: 7728005120 | elapsed time per iteration (s): 0.30 | learning rate: 6.161E-05 | global batch size: 256 | lm loss: 3.012315E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.636 | TFLOPs: 29.43 | +7: iteration 14750/ 21553 | consumed samples: 3776000 | consumed tokens: 7733248000 | elapsed time per iteration (s): 0.31 | learning rate: 6.150E-05 | global batch size: 256 | lm loss: 2.996952E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.443 | TFLOPs: 28.65 | +7: iteration 14760/ 21553 | consumed samples: 3778560 | consumed tokens: 7738490880 | elapsed time per iteration (s): 0.31 | learning rate: 6.139E-05 | global batch size: 256 | lm loss: 2.974580E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.360 | TFLOPs: 29.10 | +7: iteration 14770/ 21553 | consumed samples: 3781120 | consumed tokens: 7743733760 | elapsed time per iteration (s): 0.31 | learning rate: 6.127E-05 | global batch size: 256 | lm loss: 2.978391E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.238 | TFLOPs: 28.71 | +7: iteration 14780/ 21553 | consumed samples: 3783680 | consumed tokens: 7748976640 | elapsed time per iteration (s): 0.31 | learning rate: 6.116E-05 | global batch size: 256 | lm loss: 2.978997E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.233 | TFLOPs: 28.47 | +7: iteration 14790/ 21553 | consumed samples: 3786240 | consumed tokens: 7754219520 | elapsed time per iteration (s): 0.30 | learning rate: 6.105E-05 | global batch size: 256 | lm loss: 2.994216E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.024 | TFLOPs: 29.44 | +7: iteration 14800/ 21553 | consumed samples: 3788800 | consumed tokens: 7759462400 | elapsed time per iteration (s): 0.31 | learning rate: 6.094E-05 | global batch size: 256 | lm loss: 3.019913E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.529 | TFLOPs: 28.97 | +7: iteration 14810/ 21553 | consumed samples: 3791360 | consumed tokens: 7764705280 | elapsed time per iteration (s): 0.31 | learning rate: 6.083E-05 | global batch size: 256 | lm loss: 2.973674E+00 | grad norm: 0.383 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.914 | TFLOPs: 28.88 | +7: iteration 14820/ 21553 | consumed samples: 3793920 | consumed tokens: 7769948160 | elapsed time per iteration (s): 0.31 | learning rate: 6.072E-05 | global batch size: 256 | lm loss: 2.973661E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.983 | TFLOPs: 29.30 | +7: iteration 14830/ 21553 | consumed samples: 3796480 | consumed tokens: 7775191040 | elapsed time per iteration (s): 0.32 | learning rate: 6.061E-05 | global batch size: 256 | lm loss: 2.982122E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.685 | TFLOPs: 28.38 | +7: iteration 14840/ 21553 | consumed samples: 3799040 | consumed tokens: 7780433920 | elapsed time per iteration (s): 0.31 | learning rate: 6.050E-05 | global batch size: 256 | lm loss: 2.977005E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.846 | TFLOPs: 29.30 | +7: iteration 14850/ 21553 | consumed samples: 3801600 | consumed tokens: 7785676800 | elapsed time per iteration (s): 0.31 | learning rate: 6.039E-05 | global batch size: 256 | lm loss: 3.015816E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.212 | TFLOPs: 28.54 | +7: iteration 14860/ 21553 | consumed samples: 3804160 | consumed tokens: 7790919680 | elapsed time per iteration (s): 0.31 | learning rate: 6.028E-05 | global batch size: 256 | lm loss: 3.005006E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.928 | TFLOPs: 28.53 | +7: iteration 14870/ 21553 | consumed samples: 3806720 | consumed tokens: 7796162560 | elapsed time per iteration (s): 0.35 | learning rate: 6.016E-05 | global batch size: 256 | lm loss: 2.965705E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 731.734 | TFLOPs: 25.62 | +7: iteration 14880/ 21553 | consumed samples: 3809280 | consumed tokens: 7801405440 | elapsed time per iteration (s): 0.32 | learning rate: 6.005E-05 | global batch size: 256 | lm loss: 2.983557E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 809.284 | TFLOPs: 28.33 | +7: iteration 14890/ 21553 | consumed samples: 3811840 | consumed tokens: 7806648320 | elapsed time per iteration (s): 0.31 | learning rate: 5.994E-05 | global batch size: 256 | lm loss: 2.957530E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.772 | TFLOPs: 29.12 | +7: iteration 14900/ 21553 | consumed samples: 3814400 | consumed tokens: 7811891200 | elapsed time per iteration (s): 0.31 | learning rate: 5.983E-05 | global batch size: 256 | lm loss: 3.004790E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.883 | TFLOPs: 29.05 | +7: iteration 14910/ 21553 | consumed samples: 3816960 | consumed tokens: 7817134080 | elapsed time per iteration (s): 0.31 | learning rate: 5.972E-05 | global batch size: 256 | lm loss: 2.993200E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.115 | TFLOPs: 29.03 | +7: iteration 14920/ 21553 | consumed samples: 3819520 | consumed tokens: 7822376960 | elapsed time per iteration (s): 0.32 | learning rate: 5.961E-05 | global batch size: 256 | lm loss: 2.958630E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.534 | TFLOPs: 28.37 | +7: iteration 14930/ 21553 | consumed samples: 3822080 | consumed tokens: 7827619840 | elapsed time per iteration (s): 0.31 | learning rate: 5.950E-05 | global batch size: 256 | lm loss: 2.979424E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.300 | TFLOPs: 29.21 | +7: iteration 14940/ 21553 | consumed samples: 3824640 | consumed tokens: 7832862720 | elapsed time per iteration (s): 0.32 | learning rate: 5.940E-05 | global batch size: 256 | lm loss: 2.981254E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 803.296 | TFLOPs: 28.12 | +7: iteration 14950/ 21553 | consumed samples: 3827200 | consumed tokens: 7838105600 | elapsed time per iteration (s): 0.31 | learning rate: 5.929E-05 | global batch size: 256 | lm loss: 3.003519E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.699 | TFLOPs: 28.87 | +7: iteration 14960/ 21553 | consumed samples: 3829760 | consumed tokens: 7843348480 | elapsed time per iteration (s): 0.31 | learning rate: 5.918E-05 | global batch size: 256 | lm loss: 2.978958E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.125 | TFLOPs: 29.20 | +7: iteration 14970/ 21553 | consumed samples: 3832320 | consumed tokens: 7848591360 | elapsed time per iteration (s): 0.33 | learning rate: 5.907E-05 | global batch size: 256 | lm loss: 2.987357E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 781.102 | TFLOPs: 27.34 | +7: iteration 14980/ 21553 | consumed samples: 3834880 | consumed tokens: 7853834240 | elapsed time per iteration (s): 0.31 | learning rate: 5.896E-05 | global batch size: 256 | lm loss: 2.961468E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.112 | TFLOPs: 28.74 | +7: iteration 14990/ 21553 | consumed samples: 3837440 | consumed tokens: 7859077120 | elapsed time per iteration (s): 0.31 | learning rate: 5.885E-05 | global batch size: 256 | lm loss: 3.006536E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.305 | TFLOPs: 28.82 | +7: iteration 15000/ 21553 | consumed samples: 3840000 | consumed tokens: 7864320000 | elapsed time per iteration (s): 0.31 | learning rate: 5.874E-05 | global batch size: 256 | lm loss: 2.984748E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.390 | TFLOPs: 29.28 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 15000 | lm loss value: 2.923536E+00 | lm loss PPL: 1.860697E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 15000 to checkpoints_146moscareap +0: [2022-11-29 18:25:53,881] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step15000 is begin to save! +0: [2022-11-29 18:25:53,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:25:53,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:25:53,977] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:25:53,995] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:25:53,995] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:25:54,013] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:25:54,013] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:25:54,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:25:54,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:25:54,048] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:25:54,048] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:25:54,065] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:25:54,065] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:25:54,082] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:25:54,082] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:25:54,099] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:25:54,099] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:25:54,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:25:54,115] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:25:54,131] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:25:54,131] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:25:54,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:25:54,147] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/layer_13-model_00-model_states.pt... +0: [2022-11-29 18:25:54,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/layer_13-model_00-model_states.pt. +0: [2022-11-29 18:25:54,163] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:25:54,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:25:54,179] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/layer_15-model_00-model_states.pt... +0: [2022-11-29 18:25:54,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/layer_15-model_00-model_states.pt. +0: [2022-11-29 18:25:54,195] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/layer_16-model_00-model_states.pt... +0: [2022-11-29 18:25:54,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/layer_16-model_00-model_states.pt. +0: [2022-11-29 18:25:54,213] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/layer_17-model_00-model_states.pt... +0: [2022-11-29 18:25:54,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/layer_17-model_00-model_states.pt. +0: [2022-11-29 18:25:54,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/layer_19-model_00-model_states.pt... +0: [2022-11-29 18:25:54,232] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/layer_19-model_00-model_states.pt. +0: [2022-11-29 18:25:54,232] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_146moscareap/global_step15000/mp_rank_00_model_states.pt +0: [2022-11-29 18:25:54,233] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:25:54,236] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:25:54,257] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:25:54,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:25:54,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:25:54,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +5: [2022-11-29 18:25:54,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:25:54,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:25:54,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +1: [2022-11-29 18:25:54,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:25:54,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:25:54,291] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:25:54,291] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +7: [2022-11-29 18:25:54,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:25:54,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:25:54,291] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:25:54,291] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:25:54,292] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +7: [2022-11-29 18:25:54,292] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +0: [2022-11-29 18:25:54,292] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:25:54,292] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:25:54,292] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +6: [2022-11-29 18:25:54,292] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:25:54,292] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:25:54,292] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +2: [2022-11-29 18:25:54,292] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:25:54,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:25:54,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +5: [2022-11-29 18:25:54,294] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:25:54,294] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:25:54,294] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +1: [2022-11-29 18:25:54,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:25:54,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:25:54,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +2: [2022-11-29 18:25:54,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:25:54,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:25:54,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +1: [2022-11-29 18:25:54,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:25:54,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +3: [2022-11-29 18:25:54,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:25:54,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +1: [2022-11-29 18:25:54,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +3: [2022-11-29 18:25:54,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +6: [2022-11-29 18:25:54,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:25:54,298] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:25:54,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +7: [2022-11-29 18:25:54,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:25:54,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:25:54,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +2: [2022-11-29 18:25:54,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:25:54,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:25:54,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +1: [2022-11-29 18:25:54,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:25:54,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:25:54,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +3: [2022-11-29 18:25:54,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:25:54,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:25:54,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:25:54,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +7: [2022-11-29 18:25:54,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:25:54,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +3: [2022-11-29 18:25:54,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:25:54,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:25:54,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +2: [2022-11-29 18:25:54,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:25:54,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:25:54,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +0: [2022-11-29 18:25:54,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:25:54,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:25:54,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +1: [2022-11-29 18:25:54,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:25:54,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:25:54,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +5: [2022-11-29 18:25:54,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:25:54,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:25:54,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +0: [2022-11-29 18:25:54,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:25:54,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:25:54,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +3: [2022-11-29 18:25:54,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:25:54,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:25:54,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +2: [2022-11-29 18:25:54,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:25:54,305] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:25:54,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +6: [2022-11-29 18:25:54,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:25:54,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +0: [2022-11-29 18:25:54,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:25:54,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +3: [2022-11-29 18:25:54,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:25:54,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3: [2022-11-29 18:25:54,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +0: [2022-11-29 18:25:54,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +3: [2022-11-29 18:25:54,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +1: [2022-11-29 18:25:54,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:25:54,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:25:54,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +5: [2022-11-29 18:25:54,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:25:54,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:25:54,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +5: [2022-11-29 18:25:54,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:25:54,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:25:54,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +7: [2022-11-29 18:25:54,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:25:54,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +7: [2022-11-29 18:25:54,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:25:54,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +0: [2022-11-29 18:25:54,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +0: [2022-11-29 18:25:54,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:25:54,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:25:54,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +7: [2022-11-29 18:25:54,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:25:54,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:25:54,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +6: [2022-11-29 18:25:54,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:25:54,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:25:54,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +7: [2022-11-29 18:25:54,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:25:54,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:25:54,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +4: [2022-11-29 18:25:54,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:25:54,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:25:54,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:25:54,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:25:54,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:25:54,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +6: [2022-11-29 18:25:54,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:25:54,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +4: [2022-11-29 18:25:54,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +2: [2022-11-29 18:25:54,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:25:54,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:25:54,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +3: [2022-11-29 18:25:54,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:25:54,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:25:54,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +4: [2022-11-29 18:25:54,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:25:54,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:25:54,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +6: [2022-11-29 18:25:54,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:25:54,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:25:54,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +4: [2022-11-29 18:25:54,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:25:54,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:25:54,312] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:25:54,312] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:25:54,312] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +4: [2022-11-29 18:25:54,312] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +5: [2022-11-29 18:25:54,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:25:54,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:25:54,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +0: [2022-11-29 18:25:54,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:25:54,316] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:25:54,316] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +4: [2022-11-29 18:25:54,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:25:54,318] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:25:54,318] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +3: [2022-11-29 18:25:54,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:25:54,322] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:25:54,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +1: [2022-11-29 18:25:54,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:25:54,323] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:25:54,323] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +6: [2022-11-29 18:25:54,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:25:54,323] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:25:54,323] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +4: [2022-11-29 18:25:54,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:25:54,323] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:25:54,323] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +0: [2022-11-29 18:25:54,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:25:54,323] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:25:54,323] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +5: [2022-11-29 18:25:54,324] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:25:54,324] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:25:54,325] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +6: [2022-11-29 18:25:54,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:25:54,325] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:25:54,325] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +7: [2022-11-29 18:25:54,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:25:54,328] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:25:54,328] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +4: [2022-11-29 18:25:54,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:25:54,328] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +3: [2022-11-29 18:25:54,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:25:54,329] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +3: [2022-11-29 18:25:54,329] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:25:54,329] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +1: [2022-11-29 18:25:54,332] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:25:54,332] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:25:54,332] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +2: [2022-11-29 18:25:54,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:25:54,339] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:25:54,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +5: [2022-11-29 18:25:54,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:25:54,346] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step15000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:25:54,346] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +0: successfully saved checkpoint at iteration 15000 to checkpoints_146moscareap +7: time (ms) | save-checkpoint: 471.22 +7: iteration 15010/ 21553 | consumed samples: 3842560 | consumed tokens: 7869562880 | elapsed time per iteration (s): 0.38 | learning rate: 5.863E-05 | global batch size: 256 | lm loss: 2.970377E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 681.133 | TFLOPs: 23.84 | +7: iteration 15020/ 21553 | consumed samples: 3845120 | consumed tokens: 7874805760 | elapsed time per iteration (s): 0.31 | learning rate: 5.852E-05 | global batch size: 256 | lm loss: 2.966776E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.046 | TFLOPs: 28.50 | +7: iteration 15030/ 21553 | consumed samples: 3847680 | consumed tokens: 7880048640 | elapsed time per iteration (s): 0.31 | learning rate: 5.841E-05 | global batch size: 256 | lm loss: 3.024497E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.321 | TFLOPs: 29.00 | +7: iteration 15040/ 21553 | consumed samples: 3850240 | consumed tokens: 7885291520 | elapsed time per iteration (s): 0.31 | learning rate: 5.830E-05 | global batch size: 256 | lm loss: 2.985422E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.813 | TFLOPs: 28.63 | +7: iteration 15050/ 21553 | consumed samples: 3852800 | consumed tokens: 7890534400 | elapsed time per iteration (s): 0.31 | learning rate: 5.820E-05 | global batch size: 256 | lm loss: 2.994701E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.223 | TFLOPs: 28.92 | +7: iteration 15060/ 21553 | consumed samples: 3855360 | consumed tokens: 7895777280 | elapsed time per iteration (s): 0.31 | learning rate: 5.809E-05 | global batch size: 256 | lm loss: 3.008389E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.321 | TFLOPs: 28.58 | +7: iteration 15070/ 21553 | consumed samples: 3857920 | consumed tokens: 7901020160 | elapsed time per iteration (s): 0.32 | learning rate: 5.798E-05 | global batch size: 256 | lm loss: 2.993576E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 790.653 | TFLOPs: 27.68 | +7: iteration 15080/ 21553 | consumed samples: 3860480 | consumed tokens: 7906263040 | elapsed time per iteration (s): 0.31 | learning rate: 5.787E-05 | global batch size: 256 | lm loss: 2.974149E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.798 | TFLOPs: 28.91 | +7: iteration 15090/ 21553 | consumed samples: 3863040 | consumed tokens: 7911505920 | elapsed time per iteration (s): 0.30 | learning rate: 5.776E-05 | global batch size: 256 | lm loss: 2.974206E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 844.337 | TFLOPs: 29.56 | +7: iteration 15100/ 21553 | consumed samples: 3865600 | consumed tokens: 7916748800 | elapsed time per iteration (s): 0.31 | learning rate: 5.766E-05 | global batch size: 256 | lm loss: 2.971738E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.094 | TFLOPs: 29.30 | +7: iteration 15110/ 21553 | consumed samples: 3868160 | consumed tokens: 7921991680 | elapsed time per iteration (s): 0.31 | learning rate: 5.755E-05 | global batch size: 256 | lm loss: 2.999520E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.619 | TFLOPs: 28.90 | +7: iteration 15120/ 21553 | consumed samples: 3870720 | consumed tokens: 7927234560 | elapsed time per iteration (s): 0.31 | learning rate: 5.744E-05 | global batch size: 256 | lm loss: 2.991072E+00 | grad norm: 0.399 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.604 | TFLOPs: 29.25 | +7: iteration 15130/ 21553 | consumed samples: 3873280 | consumed tokens: 7932477440 | elapsed time per iteration (s): 0.31 | learning rate: 5.733E-05 | global batch size: 256 | lm loss: 3.042438E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.993 | TFLOPs: 29.37 | +7: iteration 15140/ 21553 | consumed samples: 3875840 | consumed tokens: 7937720320 | elapsed time per iteration (s): 0.31 | learning rate: 5.723E-05 | global batch size: 256 | lm loss: 2.959741E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.368 | TFLOPs: 28.93 | +7: iteration 15150/ 21553 | consumed samples: 3878400 | consumed tokens: 7942963200 | elapsed time per iteration (s): 0.31 | learning rate: 5.712E-05 | global batch size: 256 | lm loss: 2.991278E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.922 | TFLOPs: 28.88 | +7: iteration 15160/ 21553 | consumed samples: 3880960 | consumed tokens: 7948206080 | elapsed time per iteration (s): 0.31 | learning rate: 5.701E-05 | global batch size: 256 | lm loss: 2.967437E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.001 | TFLOPs: 29.16 | +7: iteration 15170/ 21553 | consumed samples: 3883520 | consumed tokens: 7953448960 | elapsed time per iteration (s): 0.31 | learning rate: 5.690E-05 | global batch size: 256 | lm loss: 2.953775E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.845 | TFLOPs: 28.56 | +7: iteration 15180/ 21553 | consumed samples: 3886080 | consumed tokens: 7958691840 | elapsed time per iteration (s): 0.31 | learning rate: 5.680E-05 | global batch size: 256 | lm loss: 2.988412E+00 | grad norm: 0.389 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.251 | TFLOPs: 28.85 | +7: iteration 15190/ 21553 | consumed samples: 3888640 | consumed tokens: 7963934720 | elapsed time per iteration (s): 0.31 | learning rate: 5.669E-05 | global batch size: 256 | lm loss: 2.995893E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.137 | TFLOPs: 28.85 | +7: iteration 15200/ 21553 | consumed samples: 3891200 | consumed tokens: 7969177600 | elapsed time per iteration (s): 0.31 | learning rate: 5.658E-05 | global batch size: 256 | lm loss: 2.983950E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.762 | TFLOPs: 28.94 | +7: iteration 15210/ 21553 | consumed samples: 3893760 | consumed tokens: 7974420480 | elapsed time per iteration (s): 0.31 | learning rate: 5.648E-05 | global batch size: 256 | lm loss: 2.965488E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.218 | TFLOPs: 29.03 | +7: iteration 15220/ 21553 | consumed samples: 3896320 | consumed tokens: 7979663360 | elapsed time per iteration (s): 0.33 | learning rate: 5.637E-05 | global batch size: 256 | lm loss: 2.971768E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 775.882 | TFLOPs: 27.16 | +7: iteration 15230/ 21553 | consumed samples: 3898880 | consumed tokens: 7984906240 | elapsed time per iteration (s): 0.31 | learning rate: 5.626E-05 | global batch size: 256 | lm loss: 2.968096E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.421 | TFLOPs: 29.14 | +7: iteration 15240/ 21553 | consumed samples: 3901440 | consumed tokens: 7990149120 | elapsed time per iteration (s): 0.31 | learning rate: 5.616E-05 | global batch size: 256 | lm loss: 2.985922E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.418 | TFLOPs: 29.35 | +7: iteration 15250/ 21553 | consumed samples: 3904000 | consumed tokens: 7995392000 | elapsed time per iteration (s): 0.32 | learning rate: 5.605E-05 | global batch size: 256 | lm loss: 2.991728E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 796.878 | TFLOPs: 27.90 | +7: iteration 15260/ 21553 | consumed samples: 3906560 | consumed tokens: 8000634880 | elapsed time per iteration (s): 0.31 | learning rate: 5.595E-05 | global batch size: 256 | lm loss: 2.969063E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.095 | TFLOPs: 29.34 | +7: iteration 15270/ 21553 | consumed samples: 3909120 | consumed tokens: 8005877760 | elapsed time per iteration (s): 0.32 | learning rate: 5.584E-05 | global batch size: 256 | lm loss: 2.999024E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 794.872 | TFLOPs: 27.83 | +7: iteration 15280/ 21553 | consumed samples: 3911680 | consumed tokens: 8011120640 | elapsed time per iteration (s): 0.31 | learning rate: 5.573E-05 | global batch size: 256 | lm loss: 2.973134E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.298 | TFLOPs: 29.03 | +7: iteration 15290/ 21553 | consumed samples: 3914240 | consumed tokens: 8016363520 | elapsed time per iteration (s): 0.32 | learning rate: 5.563E-05 | global batch size: 256 | lm loss: 2.984463E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 809.183 | TFLOPs: 28.33 | +7: iteration 15300/ 21553 | consumed samples: 3916800 | consumed tokens: 8021606400 | elapsed time per iteration (s): 0.32 | learning rate: 5.552E-05 | global batch size: 256 | lm loss: 2.999252E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.083 | TFLOPs: 28.29 | +7: iteration 15310/ 21553 | consumed samples: 3919360 | consumed tokens: 8026849280 | elapsed time per iteration (s): 0.31 | learning rate: 5.542E-05 | global batch size: 256 | lm loss: 2.979976E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.018 | TFLOPs: 28.92 | +7: iteration 15320/ 21553 | consumed samples: 3921920 | consumed tokens: 8032092160 | elapsed time per iteration (s): 0.31 | learning rate: 5.531E-05 | global batch size: 256 | lm loss: 2.992485E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.868 | TFLOPs: 28.49 | +7: iteration 15330/ 21553 | consumed samples: 3924480 | consumed tokens: 8037335040 | elapsed time per iteration (s): 0.31 | learning rate: 5.521E-05 | global batch size: 256 | lm loss: 2.970019E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.793 | TFLOPs: 28.98 | +7: iteration 15340/ 21553 | consumed samples: 3927040 | consumed tokens: 8042577920 | elapsed time per iteration (s): 0.31 | learning rate: 5.510E-05 | global batch size: 256 | lm loss: 2.989047E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.992 | TFLOPs: 28.81 | +7: iteration 15350/ 21553 | consumed samples: 3929600 | consumed tokens: 8047820800 | elapsed time per iteration (s): 0.31 | learning rate: 5.500E-05 | global batch size: 256 | lm loss: 3.003306E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.542 | TFLOPs: 29.21 | +7: iteration 15360/ 21553 | consumed samples: 3932160 | consumed tokens: 8053063680 | elapsed time per iteration (s): 0.31 | learning rate: 5.489E-05 | global batch size: 256 | lm loss: 2.963458E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.724 | TFLOPs: 29.26 | +7: iteration 15370/ 21553 | consumed samples: 3934720 | consumed tokens: 8058306560 | elapsed time per iteration (s): 0.31 | learning rate: 5.479E-05 | global batch size: 256 | lm loss: 2.990385E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.385 | TFLOPs: 29.24 | +7: iteration 15380/ 21553 | consumed samples: 3937280 | consumed tokens: 8063549440 | elapsed time per iteration (s): 0.31 | learning rate: 5.468E-05 | global batch size: 256 | lm loss: 2.961257E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.994 | TFLOPs: 29.09 | +7: iteration 15390/ 21553 | consumed samples: 3939840 | consumed tokens: 8068792320 | elapsed time per iteration (s): 0.31 | learning rate: 5.458E-05 | global batch size: 256 | lm loss: 3.022902E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.067 | TFLOPs: 29.02 | +7: iteration 15400/ 21553 | consumed samples: 3942400 | consumed tokens: 8074035200 | elapsed time per iteration (s): 0.32 | learning rate: 5.447E-05 | global batch size: 256 | lm loss: 2.996364E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 794.693 | TFLOPs: 27.82 | +7: iteration 15410/ 21553 | consumed samples: 3944960 | consumed tokens: 8079278080 | elapsed time per iteration (s): 0.31 | learning rate: 5.437E-05 | global batch size: 256 | lm loss: 2.984889E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.785 | TFLOPs: 29.29 | +7: iteration 15420/ 21553 | consumed samples: 3947520 | consumed tokens: 8084520960 | elapsed time per iteration (s): 0.32 | learning rate: 5.427E-05 | global batch size: 256 | lm loss: 2.982560E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 803.002 | TFLOPs: 28.11 | +7: iteration 15430/ 21553 | consumed samples: 3950080 | consumed tokens: 8089763840 | elapsed time per iteration (s): 0.31 | learning rate: 5.416E-05 | global batch size: 256 | lm loss: 2.973157E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.147 | TFLOPs: 29.03 | +7: iteration 15440/ 21553 | consumed samples: 3952640 | consumed tokens: 8095006720 | elapsed time per iteration (s): 0.31 | learning rate: 5.406E-05 | global batch size: 256 | lm loss: 2.992405E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.259 | TFLOPs: 29.03 | +7: iteration 15450/ 21553 | consumed samples: 3955200 | consumed tokens: 8100249600 | elapsed time per iteration (s): 0.31 | learning rate: 5.395E-05 | global batch size: 256 | lm loss: 2.973133E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.471 | TFLOPs: 29.07 | +7: iteration 15460/ 21553 | consumed samples: 3957760 | consumed tokens: 8105492480 | elapsed time per iteration (s): 0.31 | learning rate: 5.385E-05 | global batch size: 256 | lm loss: 2.986510E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.441 | TFLOPs: 28.79 | +7: iteration 15470/ 21553 | consumed samples: 3960320 | consumed tokens: 8110735360 | elapsed time per iteration (s): 0.31 | learning rate: 5.375E-05 | global batch size: 256 | lm loss: 2.957860E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.650 | TFLOPs: 28.90 | +7: iteration 15480/ 21553 | consumed samples: 3962880 | consumed tokens: 8115978240 | elapsed time per iteration (s): 0.32 | learning rate: 5.364E-05 | global batch size: 256 | lm loss: 2.967616E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.690 | TFLOPs: 28.45 | +7: iteration 15490/ 21553 | consumed samples: 3965440 | consumed tokens: 8121221120 | elapsed time per iteration (s): 0.31 | learning rate: 5.354E-05 | global batch size: 256 | lm loss: 2.982662E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.163 | TFLOPs: 28.92 | +7: iteration 15500/ 21553 | consumed samples: 3968000 | consumed tokens: 8126464000 | elapsed time per iteration (s): 0.31 | learning rate: 5.344E-05 | global batch size: 256 | lm loss: 2.980338E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.669 | TFLOPs: 28.94 | +7: iteration 15510/ 21553 | consumed samples: 3970560 | consumed tokens: 8131706880 | elapsed time per iteration (s): 0.32 | learning rate: 5.333E-05 | global batch size: 256 | lm loss: 2.998348E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 805.705 | TFLOPs: 28.21 | +7: iteration 15520/ 21553 | consumed samples: 3973120 | consumed tokens: 8136949760 | elapsed time per iteration (s): 0.31 | learning rate: 5.323E-05 | global batch size: 256 | lm loss: 2.969151E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.445 | TFLOPs: 29.18 | +7: iteration 15530/ 21553 | consumed samples: 3975680 | consumed tokens: 8142192640 | elapsed time per iteration (s): 0.30 | learning rate: 5.313E-05 | global batch size: 256 | lm loss: 2.982989E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.473 | TFLOPs: 29.42 | +7: iteration 15540/ 21553 | consumed samples: 3978240 | consumed tokens: 8147435520 | elapsed time per iteration (s): 0.31 | learning rate: 5.303E-05 | global batch size: 256 | lm loss: 2.985373E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.150 | TFLOPs: 28.78 | +7: iteration 15550/ 21553 | consumed samples: 3980800 | consumed tokens: 8152678400 | elapsed time per iteration (s): 0.31 | learning rate: 5.292E-05 | global batch size: 256 | lm loss: 2.986036E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.850 | TFLOPs: 29.30 | +7: iteration 15560/ 21553 | consumed samples: 3983360 | consumed tokens: 8157921280 | elapsed time per iteration (s): 0.31 | learning rate: 5.282E-05 | global batch size: 256 | lm loss: 3.006619E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.923 | TFLOPs: 28.77 | +7: iteration 15570/ 21553 | consumed samples: 3985920 | consumed tokens: 8163164160 | elapsed time per iteration (s): 0.33 | learning rate: 5.272E-05 | global batch size: 256 | lm loss: 2.973253E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 776.843 | TFLOPs: 27.20 | +7: iteration 15580/ 21553 | consumed samples: 3988480 | consumed tokens: 8168407040 | elapsed time per iteration (s): 0.33 | learning rate: 5.262E-05 | global batch size: 256 | lm loss: 2.971566E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 777.977 | TFLOPs: 27.23 | +7: iteration 15590/ 21553 | consumed samples: 3991040 | consumed tokens: 8173649920 | elapsed time per iteration (s): 0.31 | learning rate: 5.251E-05 | global batch size: 256 | lm loss: 3.027309E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.716 | TFLOPs: 28.87 | +7: iteration 15600/ 21553 | consumed samples: 3993600 | consumed tokens: 8178892800 | elapsed time per iteration (s): 0.31 | learning rate: 5.241E-05 | global batch size: 256 | lm loss: 2.957220E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.754 | TFLOPs: 28.80 | +7: iteration 15610/ 21553 | consumed samples: 3996160 | consumed tokens: 8184135680 | elapsed time per iteration (s): 0.31 | learning rate: 5.231E-05 | global batch size: 256 | lm loss: 2.965801E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.101 | TFLOPs: 28.85 | +7: iteration 15620/ 21553 | consumed samples: 3998720 | consumed tokens: 8189378560 | elapsed time per iteration (s): 0.32 | learning rate: 5.221E-05 | global batch size: 256 | lm loss: 2.991184E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.968 | TFLOPs: 28.39 | +7: iteration 15630/ 21553 | consumed samples: 4001280 | consumed tokens: 8194621440 | elapsed time per iteration (s): 0.30 | learning rate: 5.211E-05 | global batch size: 256 | lm loss: 2.984525E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.432 | TFLOPs: 29.53 | +7: iteration 15640/ 21553 | consumed samples: 4003840 | consumed tokens: 8199864320 | elapsed time per iteration (s): 0.31 | learning rate: 5.201E-05 | global batch size: 256 | lm loss: 2.980164E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.981 | TFLOPs: 29.16 | +7: iteration 15650/ 21553 | consumed samples: 4006400 | consumed tokens: 8205107200 | elapsed time per iteration (s): 0.31 | learning rate: 5.191E-05 | global batch size: 256 | lm loss: 2.971955E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.496 | TFLOPs: 29.32 | +7: iteration 15660/ 21553 | consumed samples: 4008960 | consumed tokens: 8210350080 | elapsed time per iteration (s): 0.31 | learning rate: 5.180E-05 | global batch size: 256 | lm loss: 2.973338E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.406 | TFLOPs: 29.35 | +7: iteration 15670/ 21553 | consumed samples: 4011520 | consumed tokens: 8215592960 | elapsed time per iteration (s): 0.31 | learning rate: 5.170E-05 | global batch size: 256 | lm loss: 2.980069E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.277 | TFLOPs: 28.61 | +7: iteration 15680/ 21553 | consumed samples: 4014080 | consumed tokens: 8220835840 | elapsed time per iteration (s): 0.30 | learning rate: 5.160E-05 | global batch size: 256 | lm loss: 2.975131E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.180 | TFLOPs: 29.45 | +7: iteration 15690/ 21553 | consumed samples: 4016640 | consumed tokens: 8226078720 | elapsed time per iteration (s): 0.31 | learning rate: 5.150E-05 | global batch size: 256 | lm loss: 2.981048E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.372 | TFLOPs: 29.28 | +7: iteration 15700/ 21553 | consumed samples: 4019200 | consumed tokens: 8231321600 | elapsed time per iteration (s): 0.31 | learning rate: 5.140E-05 | global batch size: 256 | lm loss: 2.980330E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.777 | TFLOPs: 28.91 | +7: iteration 15710/ 21553 | consumed samples: 4021760 | consumed tokens: 8236564480 | elapsed time per iteration (s): 0.31 | learning rate: 5.130E-05 | global batch size: 256 | lm loss: 2.982991E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.312 | TFLOPs: 28.79 | +7: iteration 15720/ 21553 | consumed samples: 4024320 | consumed tokens: 8241807360 | elapsed time per iteration (s): 0.31 | learning rate: 5.120E-05 | global batch size: 256 | lm loss: 2.974771E+00 | grad norm: 0.381 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.436 | TFLOPs: 29.35 | +7: iteration 15730/ 21553 | consumed samples: 4026880 | consumed tokens: 8247050240 | elapsed time per iteration (s): 0.31 | learning rate: 5.110E-05 | global batch size: 256 | lm loss: 2.994353E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.684 | TFLOPs: 28.69 | +7: iteration 15740/ 21553 | consumed samples: 4029440 | consumed tokens: 8252293120 | elapsed time per iteration (s): 0.32 | learning rate: 5.100E-05 | global batch size: 256 | lm loss: 3.016994E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 799.241 | TFLOPs: 27.98 | +7: iteration 15750/ 21553 | consumed samples: 4032000 | consumed tokens: 8257536000 | elapsed time per iteration (s): 0.31 | learning rate: 5.090E-05 | global batch size: 256 | lm loss: 2.998488E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.057 | TFLOPs: 29.09 | +7: iteration 15760/ 21553 | consumed samples: 4034560 | consumed tokens: 8262778880 | elapsed time per iteration (s): 0.31 | learning rate: 5.080E-05 | global batch size: 256 | lm loss: 2.991047E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.972 | TFLOPs: 29.09 | +7: iteration 15770/ 21553 | consumed samples: 4037120 | consumed tokens: 8268021760 | elapsed time per iteration (s): 0.31 | learning rate: 5.070E-05 | global batch size: 256 | lm loss: 2.969078E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.702 | TFLOPs: 29.26 | +7: iteration 15780/ 21553 | consumed samples: 4039680 | consumed tokens: 8273264640 | elapsed time per iteration (s): 0.31 | learning rate: 5.060E-05 | global batch size: 256 | lm loss: 2.967528E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.208 | TFLOPs: 29.17 | +7: iteration 15790/ 21553 | consumed samples: 4042240 | consumed tokens: 8278507520 | elapsed time per iteration (s): 0.31 | learning rate: 5.050E-05 | global batch size: 256 | lm loss: 2.964017E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.264 | TFLOPs: 29.10 | +7: iteration 15800/ 21553 | consumed samples: 4044800 | consumed tokens: 8283750400 | elapsed time per iteration (s): 0.31 | learning rate: 5.040E-05 | global batch size: 256 | lm loss: 2.975281E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.072 | TFLOPs: 29.02 | +7: iteration 15810/ 21553 | consumed samples: 4047360 | consumed tokens: 8288993280 | elapsed time per iteration (s): 0.31 | learning rate: 5.030E-05 | global batch size: 256 | lm loss: 2.959710E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.892 | TFLOPs: 29.09 | +7: iteration 15820/ 21553 | consumed samples: 4049920 | consumed tokens: 8294236160 | elapsed time per iteration (s): 0.31 | learning rate: 5.020E-05 | global batch size: 256 | lm loss: 2.973975E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.311 | TFLOPs: 28.51 | +7: iteration 15830/ 21553 | consumed samples: 4052480 | consumed tokens: 8299479040 | elapsed time per iteration (s): 0.31 | learning rate: 5.010E-05 | global batch size: 256 | lm loss: 2.991375E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.936 | TFLOPs: 29.09 | +7: iteration 15840/ 21553 | consumed samples: 4055040 | consumed tokens: 8304721920 | elapsed time per iteration (s): 0.31 | learning rate: 5.001E-05 | global batch size: 256 | lm loss: 2.983224E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.847 | TFLOPs: 29.12 | +7: iteration 15850/ 21553 | consumed samples: 4057600 | consumed tokens: 8309964800 | elapsed time per iteration (s): 0.31 | learning rate: 4.991E-05 | global batch size: 256 | lm loss: 2.978677E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.067 | TFLOPs: 28.78 | +7: iteration 15860/ 21553 | consumed samples: 4060160 | consumed tokens: 8315207680 | elapsed time per iteration (s): 0.31 | learning rate: 4.981E-05 | global batch size: 256 | lm loss: 2.983926E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.487 | TFLOPs: 28.86 | +7: iteration 15870/ 21553 | consumed samples: 4062720 | consumed tokens: 8320450560 | elapsed time per iteration (s): 0.31 | learning rate: 4.971E-05 | global batch size: 256 | lm loss: 2.966937E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.389 | TFLOPs: 28.93 | +7: iteration 15880/ 21553 | consumed samples: 4065280 | consumed tokens: 8325693440 | elapsed time per iteration (s): 0.31 | learning rate: 4.961E-05 | global batch size: 256 | lm loss: 3.009224E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.083 | TFLOPs: 29.16 | +7: iteration 15890/ 21553 | consumed samples: 4067840 | consumed tokens: 8330936320 | elapsed time per iteration (s): 0.31 | learning rate: 4.951E-05 | global batch size: 256 | lm loss: 2.996914E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.321 | TFLOPs: 28.89 | +7: iteration 15900/ 21553 | consumed samples: 4070400 | consumed tokens: 8336179200 | elapsed time per iteration (s): 0.32 | learning rate: 4.942E-05 | global batch size: 256 | lm loss: 2.978345E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 805.625 | TFLOPs: 28.20 | +7: iteration 15910/ 21553 | consumed samples: 4072960 | consumed tokens: 8341422080 | elapsed time per iteration (s): 0.31 | learning rate: 4.932E-05 | global batch size: 256 | lm loss: 2.991869E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.213 | TFLOPs: 28.85 | +7: iteration 15920/ 21553 | consumed samples: 4075520 | consumed tokens: 8346664960 | elapsed time per iteration (s): 0.31 | learning rate: 4.922E-05 | global batch size: 256 | lm loss: 2.992873E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.911 | TFLOPs: 28.46 | +7: iteration 15930/ 21553 | consumed samples: 4078080 | consumed tokens: 8351907840 | elapsed time per iteration (s): 0.30 | learning rate: 4.912E-05 | global batch size: 256 | lm loss: 2.958338E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.590 | TFLOPs: 29.53 | +7: iteration 15940/ 21553 | consumed samples: 4080640 | consumed tokens: 8357150720 | elapsed time per iteration (s): 0.31 | learning rate: 4.902E-05 | global batch size: 256 | lm loss: 3.014719E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.811 | TFLOPs: 29.22 | +7: iteration 15950/ 21553 | consumed samples: 4083200 | consumed tokens: 8362393600 | elapsed time per iteration (s): 0.31 | learning rate: 4.893E-05 | global batch size: 256 | lm loss: 2.965657E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.595 | TFLOPs: 29.32 | +7: iteration 15960/ 21553 | consumed samples: 4085760 | consumed tokens: 8367636480 | elapsed time per iteration (s): 0.31 | learning rate: 4.883E-05 | global batch size: 256 | lm loss: 2.992655E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.843 | TFLOPs: 29.30 | +7: iteration 15970/ 21553 | consumed samples: 4088320 | consumed tokens: 8372879360 | elapsed time per iteration (s): 0.30 | learning rate: 4.873E-05 | global batch size: 256 | lm loss: 2.982212E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.194 | TFLOPs: 29.41 | +7: iteration 15980/ 21553 | consumed samples: 4090880 | consumed tokens: 8378122240 | elapsed time per iteration (s): 0.30 | learning rate: 4.864E-05 | global batch size: 256 | lm loss: 2.942903E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 844.428 | TFLOPs: 29.56 | +7: iteration 15990/ 21553 | consumed samples: 4093440 | consumed tokens: 8383365120 | elapsed time per iteration (s): 0.31 | learning rate: 4.854E-05 | global batch size: 256 | lm loss: 2.943768E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.951 | TFLOPs: 29.09 | +0: [2022-11-29 18:31:04,942] [INFO] [logging.py:68:log_dist] [Rank 0] step=16000, skipped=0, lr=[4.8441849544340955e-05, 4.8441849544340955e-05, 4.8441849544340955e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +0: steps: 16000 loss: 2.9684 iter time (s): 0.314 samples/sec: 814.227 +7: iteration 16000/ 21553 | consumed samples: 4096000 | consumed tokens: 8388608000 | elapsed time per iteration (s): 0.31 | learning rate: 4.844E-05 | global batch size: 256 | lm loss: 3.004676E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.083 | TFLOPs: 28.88 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 16000 | lm loss value: 2.888182E+00 | lm loss PPL: 1.796062E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 16000 to checkpoints_146moscareap +0: [2022-11-29 18:31:05,068] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step16000 is begin to save! +0: [2022-11-29 18:31:05,073] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:31:05,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:31:05,162] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:31:05,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:31:05,178] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:31:05,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:31:05,193] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:31:05,208] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:31:05,209] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:31:05,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:31:05,225] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:31:05,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:31:05,240] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:31:05,255] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:31:05,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:31:05,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:31:05,271] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:31:05,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:31:05,287] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:31:05,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:31:05,302] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:31:05,317] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:31:05,318] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/layer_13-model_00-model_states.pt... +0: [2022-11-29 18:31:05,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/layer_13-model_00-model_states.pt. +0: [2022-11-29 18:31:05,333] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:31:05,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:31:05,349] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/layer_15-model_00-model_states.pt... +0: [2022-11-29 18:31:05,364] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/layer_15-model_00-model_states.pt. +0: [2022-11-29 18:31:05,364] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/layer_16-model_00-model_states.pt... +0: [2022-11-29 18:31:05,380] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/layer_16-model_00-model_states.pt. +0: [2022-11-29 18:31:05,380] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/layer_17-model_00-model_states.pt... +0: [2022-11-29 18:31:05,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/layer_17-model_00-model_states.pt. +0: [2022-11-29 18:31:05,395] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/layer_19-model_00-model_states.pt... +0: [2022-11-29 18:31:05,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/layer_19-model_00-model_states.pt. +0: [2022-11-29 18:31:05,397] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_146moscareap/global_step16000/mp_rank_00_model_states.pt +0: [2022-11-29 18:31:05,397] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:31:05,400] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:31:05,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:31:05,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:31:05,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:31:05,453] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:31:05,453] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +0: [2022-11-29 18:31:05,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:31:05,454] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:31:05,454] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +0: [2022-11-29 18:31:05,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:31:05,454] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:31:05,454] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +0: [2022-11-29 18:31:05,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:31:05,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:31:05,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +5: [2022-11-29 18:31:05,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:31:05,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:31:05,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:31:05,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:31:05,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:31:05,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +1: [2022-11-29 18:31:05,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +2: [2022-11-29 18:31:05,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:31:05,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:31:05,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +1: [2022-11-29 18:31:05,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:31:05,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:31:05,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +2: [2022-11-29 18:31:05,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:31:05,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:31:05,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +2: [2022-11-29 18:31:05,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:31:05,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:31:05,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:31:05,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:31:05,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:31:05,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +4: [2022-11-29 18:31:05,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +2: [2022-11-29 18:31:05,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +4: [2022-11-29 18:31:05,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +4: [2022-11-29 18:31:05,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:31:05,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:31:05,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +6: [2022-11-29 18:31:05,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:31:05,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:31:05,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +3: [2022-11-29 18:31:05,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:31:05,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:31:05,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:31:05,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:31:05,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +3: [2022-11-29 18:31:05,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +6: [2022-11-29 18:31:05,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +3: [2022-11-29 18:31:05,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +6: [2022-11-29 18:31:05,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +3: [2022-11-29 18:31:05,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:31:05,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +1: [2022-11-29 18:31:05,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:31:05,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +1: [2022-11-29 18:31:05,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:31:05,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +0: [2022-11-29 18:31:05,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:31:05,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:31:05,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +1: [2022-11-29 18:31:05,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:31:05,460] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:31:05,460] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +0: [2022-11-29 18:31:05,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:31:05,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:31:05,460] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +4: [2022-11-29 18:31:05,460] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +0: [2022-11-29 18:31:05,460] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +4: [2022-11-29 18:31:05,460] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +2: [2022-11-29 18:31:05,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:31:05,460] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:31:05,460] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +0: [2022-11-29 18:31:05,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:31:05,460] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:31:05,461] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +3: [2022-11-29 18:31:05,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:31:05,461] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:31:05,461] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +4: [2022-11-29 18:31:05,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:31:05,461] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:31:05,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:31:05,461] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +4: [2022-11-29 18:31:05,461] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:31:05,461] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +6: [2022-11-29 18:31:05,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:31:05,461] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +1: [2022-11-29 18:31:05,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:31:05,461] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +1: [2022-11-29 18:31:05,461] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +5: [2022-11-29 18:31:05,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +1: [2022-11-29 18:31:05,461] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +5: [2022-11-29 18:31:05,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +5: [2022-11-29 18:31:05,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:31:05,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:31:05,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +5: [2022-11-29 18:31:05,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:31:05,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +2: [2022-11-29 18:31:05,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:31:05,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +5: [2022-11-29 18:31:05,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:31:05,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +2: [2022-11-29 18:31:05,461] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +1: [2022-11-29 18:31:05,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:31:05,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +6: [2022-11-29 18:31:05,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:31:05,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:31:05,461] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +6: [2022-11-29 18:31:05,462] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +5: [2022-11-29 18:31:05,459] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +2: [2022-11-29 18:31:05,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +1: [2022-11-29 18:31:05,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +6: [2022-11-29 18:31:05,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +5: [2022-11-29 18:31:05,459] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +4: [2022-11-29 18:31:05,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:31:05,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:31:05,461] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:31:05,461] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +5: [2022-11-29 18:31:05,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:31:05,462] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +5: [2022-11-29 18:31:05,461] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:31:05,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +6: [2022-11-29 18:31:05,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:31:05,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +6: [2022-11-29 18:31:05,462] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:31:05,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +1: [2022-11-29 18:31:05,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:31:05,462] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:31:05,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +3: [2022-11-29 18:31:05,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:31:05,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:31:05,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:31:05,462] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:31:05,462] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +5: [2022-11-29 18:31:05,462] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +3: [2022-11-29 18:31:05,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +3: [2022-11-29 18:31:05,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +5: [2022-11-29 18:31:05,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +0: [2022-11-29 18:31:05,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:31:05,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:31:05,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +3: [2022-11-29 18:31:05,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:31:05,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +4: [2022-11-29 18:31:05,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:31:05,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:31:05,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:31:05,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:31:05,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +4: [2022-11-29 18:31:05,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +6: [2022-11-29 18:31:05,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +3: [2022-11-29 18:31:05,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +4: [2022-11-29 18:31:05,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +6: [2022-11-29 18:31:05,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:31:05,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +6: [2022-11-29 18:31:05,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +3: [2022-11-29 18:31:05,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +4: [2022-11-29 18:31:05,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:31:05,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:31:05,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +7: [2022-11-29 18:31:05,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:31:05,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:31:05,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +7: [2022-11-29 18:31:05,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:31:05,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:31:05,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +7: [2022-11-29 18:31:05,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:31:05,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:31:05,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +7: [2022-11-29 18:31:05,464] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:31:05,464] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:31:05,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +6: [2022-11-29 18:31:05,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:31:05,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:31:05,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +2: [2022-11-29 18:31:05,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +6: [2022-11-29 18:31:05,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +2: [2022-11-29 18:31:05,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +7: [2022-11-29 18:31:05,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:31:05,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:31:05,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +7: [2022-11-29 18:31:05,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:31:05,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:31:05,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:31:05,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:31:05,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:31:05,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:31:05,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +7: [2022-11-29 18:31:05,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +7: [2022-11-29 18:31:05,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +0: [2022-11-29 18:31:05,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step16000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:31:05,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +0: successfully saved checkpoint at iteration 16000 to checkpoints_146moscareap +7: time (ms) | save-checkpoint: 416.04 +7: iteration 16010/ 21553 | consumed samples: 4098560 | consumed tokens: 8393850880 | elapsed time per iteration (s): 0.36 | learning rate: 4.835E-05 | global batch size: 256 | lm loss: 2.991094E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 709.342 | TFLOPs: 24.83 | +7: iteration 16020/ 21553 | consumed samples: 4101120 | consumed tokens: 8399093760 | elapsed time per iteration (s): 0.31 | learning rate: 4.825E-05 | global batch size: 256 | lm loss: 2.960332E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.755 | TFLOPs: 28.98 | +7: iteration 16030/ 21553 | consumed samples: 4103680 | consumed tokens: 8404336640 | elapsed time per iteration (s): 0.31 | learning rate: 4.815E-05 | global batch size: 256 | lm loss: 2.960904E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.313 | TFLOPs: 28.96 | +7: iteration 16040/ 21553 | consumed samples: 4106240 | consumed tokens: 8409579520 | elapsed time per iteration (s): 0.31 | learning rate: 4.806E-05 | global batch size: 256 | lm loss: 2.953518E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.506 | TFLOPs: 29.21 | +7: iteration 16050/ 21553 | consumed samples: 4108800 | consumed tokens: 8414822400 | elapsed time per iteration (s): 0.31 | learning rate: 4.796E-05 | global batch size: 256 | lm loss: 2.964510E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.856 | TFLOPs: 28.95 | +7: iteration 16060/ 21553 | consumed samples: 4111360 | consumed tokens: 8420065280 | elapsed time per iteration (s): 0.31 | learning rate: 4.786E-05 | global batch size: 256 | lm loss: 2.959855E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.822 | TFLOPs: 28.84 | +7: iteration 16070/ 21553 | consumed samples: 4113920 | consumed tokens: 8425308160 | elapsed time per iteration (s): 0.31 | learning rate: 4.777E-05 | global batch size: 256 | lm loss: 2.990106E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.124 | TFLOPs: 28.89 | +7: iteration 16080/ 21553 | consumed samples: 4116480 | consumed tokens: 8430551040 | elapsed time per iteration (s): 0.31 | learning rate: 4.767E-05 | global batch size: 256 | lm loss: 2.989678E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.204 | TFLOPs: 28.96 | +7: iteration 16090/ 21553 | consumed samples: 4119040 | consumed tokens: 8435793920 | elapsed time per iteration (s): 0.31 | learning rate: 4.758E-05 | global batch size: 256 | lm loss: 2.950781E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.903 | TFLOPs: 29.16 | +7: iteration 16100/ 21553 | consumed samples: 4121600 | consumed tokens: 8441036800 | elapsed time per iteration (s): 0.31 | learning rate: 4.748E-05 | global batch size: 256 | lm loss: 2.957168E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.304 | TFLOPs: 28.82 | +7: iteration 16110/ 21553 | consumed samples: 4124160 | consumed tokens: 8446279680 | elapsed time per iteration (s): 0.31 | learning rate: 4.739E-05 | global batch size: 256 | lm loss: 2.961375E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.518 | TFLOPs: 28.69 | +7: iteration 16120/ 21553 | consumed samples: 4126720 | consumed tokens: 8451522560 | elapsed time per iteration (s): 0.31 | learning rate: 4.729E-05 | global batch size: 256 | lm loss: 2.996698E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.436 | TFLOPs: 28.93 | +7: iteration 16130/ 21553 | consumed samples: 4129280 | consumed tokens: 8456765440 | elapsed time per iteration (s): 0.31 | learning rate: 4.720E-05 | global batch size: 256 | lm loss: 2.969635E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.834 | TFLOPs: 29.26 | +7: iteration 16140/ 21553 | consumed samples: 4131840 | consumed tokens: 8462008320 | elapsed time per iteration (s): 0.31 | learning rate: 4.710E-05 | global batch size: 256 | lm loss: 2.976209E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.009 | TFLOPs: 28.85 | +7: iteration 16150/ 21553 | consumed samples: 4134400 | consumed tokens: 8467251200 | elapsed time per iteration (s): 0.31 | learning rate: 4.701E-05 | global batch size: 256 | lm loss: 2.958060E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.690 | TFLOPs: 28.94 | +7: iteration 16160/ 21553 | consumed samples: 4136960 | consumed tokens: 8472494080 | elapsed time per iteration (s): 0.32 | learning rate: 4.691E-05 | global batch size: 256 | lm loss: 2.958263E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 795.078 | TFLOPs: 27.83 | +7: iteration 16170/ 21553 | consumed samples: 4139520 | consumed tokens: 8477736960 | elapsed time per iteration (s): 0.31 | learning rate: 4.682E-05 | global batch size: 256 | lm loss: 2.967300E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.026 | TFLOPs: 28.71 | +7: iteration 16180/ 21553 | consumed samples: 4142080 | consumed tokens: 8482979840 | elapsed time per iteration (s): 0.33 | learning rate: 4.672E-05 | global batch size: 256 | lm loss: 2.949414E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 769.341 | TFLOPs: 26.93 | +7: iteration 16190/ 21553 | consumed samples: 4144640 | consumed tokens: 8488222720 | elapsed time per iteration (s): 0.31 | learning rate: 4.663E-05 | global batch size: 256 | lm loss: 2.938600E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.691 | TFLOPs: 28.84 | +7: iteration 16200/ 21553 | consumed samples: 4147200 | consumed tokens: 8493465600 | elapsed time per iteration (s): 0.31 | learning rate: 4.654E-05 | global batch size: 256 | lm loss: 2.981229E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.847 | TFLOPs: 28.70 | +7: iteration 16210/ 21553 | consumed samples: 4149760 | consumed tokens: 8498708480 | elapsed time per iteration (s): 0.31 | learning rate: 4.644E-05 | global batch size: 256 | lm loss: 3.001735E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.034 | TFLOPs: 28.99 | +7: iteration 16220/ 21553 | consumed samples: 4152320 | consumed tokens: 8503951360 | elapsed time per iteration (s): 0.32 | learning rate: 4.635E-05 | global batch size: 256 | lm loss: 2.994932E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 787.943 | TFLOPs: 27.58 | +7: iteration 16230/ 21553 | consumed samples: 4154880 | consumed tokens: 8509194240 | elapsed time per iteration (s): 0.31 | learning rate: 4.625E-05 | global batch size: 256 | lm loss: 2.979129E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.835 | TFLOPs: 28.74 | +7: iteration 16240/ 21553 | consumed samples: 4157440 | consumed tokens: 8514437120 | elapsed time per iteration (s): 0.31 | learning rate: 4.616E-05 | global batch size: 256 | lm loss: 2.979344E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.217 | TFLOPs: 29.24 | +7: iteration 16250/ 21553 | consumed samples: 4160000 | consumed tokens: 8519680000 | elapsed time per iteration (s): 0.31 | learning rate: 4.607E-05 | global batch size: 256 | lm loss: 2.967824E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.897 | TFLOPs: 29.09 | +7: iteration 16260/ 21553 | consumed samples: 4162560 | consumed tokens: 8524922880 | elapsed time per iteration (s): 0.30 | learning rate: 4.597E-05 | global batch size: 256 | lm loss: 2.982722E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.968 | TFLOPs: 29.61 | +7: iteration 16270/ 21553 | consumed samples: 4165120 | consumed tokens: 8530165760 | elapsed time per iteration (s): 0.31 | learning rate: 4.588E-05 | global batch size: 256 | lm loss: 2.961861E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.641 | TFLOPs: 28.73 | +7: iteration 16280/ 21553 | consumed samples: 4167680 | consumed tokens: 8535408640 | elapsed time per iteration (s): 0.31 | learning rate: 4.579E-05 | global batch size: 256 | lm loss: 2.962395E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.846 | TFLOPs: 28.91 | +7: iteration 16290/ 21553 | consumed samples: 4170240 | consumed tokens: 8540651520 | elapsed time per iteration (s): 0.30 | learning rate: 4.570E-05 | global batch size: 256 | lm loss: 2.986057E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.883 | TFLOPs: 29.61 | +7: iteration 16300/ 21553 | consumed samples: 4172800 | consumed tokens: 8545894400 | elapsed time per iteration (s): 0.30 | learning rate: 4.560E-05 | global batch size: 256 | lm loss: 2.984417E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.421 | TFLOPs: 29.42 | +7: iteration 16310/ 21553 | consumed samples: 4175360 | consumed tokens: 8551137280 | elapsed time per iteration (s): 0.31 | learning rate: 4.551E-05 | global batch size: 256 | lm loss: 2.950886E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.905 | TFLOPs: 29.16 | +7: iteration 16320/ 21553 | consumed samples: 4177920 | consumed tokens: 8556380160 | elapsed time per iteration (s): 0.31 | learning rate: 4.542E-05 | global batch size: 256 | lm loss: 2.969156E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.489 | TFLOPs: 28.55 | +7: iteration 16330/ 21553 | consumed samples: 4180480 | consumed tokens: 8561623040 | elapsed time per iteration (s): 0.31 | learning rate: 4.533E-05 | global batch size: 256 | lm loss: 2.943512E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.220 | TFLOPs: 28.99 | +7: iteration 16340/ 21553 | consumed samples: 4183040 | consumed tokens: 8566865920 | elapsed time per iteration (s): 0.31 | learning rate: 4.523E-05 | global batch size: 256 | lm loss: 2.970178E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.073 | TFLOPs: 28.81 | +7: iteration 16350/ 21553 | consumed samples: 4185600 | consumed tokens: 8572108800 | elapsed time per iteration (s): 0.32 | learning rate: 4.514E-05 | global batch size: 256 | lm loss: 2.994336E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.010 | TFLOPs: 28.39 | +7: iteration 16360/ 21553 | consumed samples: 4188160 | consumed tokens: 8577351680 | elapsed time per iteration (s): 0.31 | learning rate: 4.505E-05 | global batch size: 256 | lm loss: 2.982001E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.309 | TFLOPs: 29.21 | +7: iteration 16370/ 21553 | consumed samples: 4190720 | consumed tokens: 8582594560 | elapsed time per iteration (s): 0.33 | learning rate: 4.496E-05 | global batch size: 256 | lm loss: 2.998814E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 778.246 | TFLOPs: 27.24 | +7: iteration 16380/ 21553 | consumed samples: 4193280 | consumed tokens: 8587837440 | elapsed time per iteration (s): 0.32 | learning rate: 4.487E-05 | global batch size: 256 | lm loss: 2.968900E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 791.330 | TFLOPs: 27.70 | +7: iteration 16390/ 21553 | consumed samples: 4195840 | consumed tokens: 8593080320 | elapsed time per iteration (s): 0.31 | learning rate: 4.478E-05 | global batch size: 256 | lm loss: 2.976219E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.862 | TFLOPs: 29.33 | +7: iteration 16400/ 21553 | consumed samples: 4198400 | consumed tokens: 8598323200 | elapsed time per iteration (s): 0.31 | learning rate: 4.468E-05 | global batch size: 256 | lm loss: 2.938837E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.262 | TFLOPs: 28.61 | +7: iteration 16410/ 21553 | consumed samples: 4200960 | consumed tokens: 8603566080 | elapsed time per iteration (s): 0.31 | learning rate: 4.459E-05 | global batch size: 256 | lm loss: 2.998323E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.871 | TFLOPs: 28.81 | +7: iteration 16420/ 21553 | consumed samples: 4203520 | consumed tokens: 8608808960 | elapsed time per iteration (s): 0.31 | learning rate: 4.450E-05 | global batch size: 256 | lm loss: 2.975903E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.510 | TFLOPs: 28.72 | +7: iteration 16430/ 21553 | consumed samples: 4206080 | consumed tokens: 8614051840 | elapsed time per iteration (s): 0.31 | learning rate: 4.441E-05 | global batch size: 256 | lm loss: 2.954773E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.075 | TFLOPs: 28.88 | +7: iteration 16440/ 21553 | consumed samples: 4208640 | consumed tokens: 8619294720 | elapsed time per iteration (s): 0.31 | learning rate: 4.432E-05 | global batch size: 256 | lm loss: 2.948766E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.164 | TFLOPs: 28.82 | +7: iteration 16450/ 21553 | consumed samples: 4211200 | consumed tokens: 8624537600 | elapsed time per iteration (s): 0.32 | learning rate: 4.423E-05 | global batch size: 256 | lm loss: 2.952425E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 807.873 | TFLOPs: 28.28 | +7: iteration 16460/ 21553 | consumed samples: 4213760 | consumed tokens: 8629780480 | elapsed time per iteration (s): 0.31 | learning rate: 4.414E-05 | global batch size: 256 | lm loss: 2.968303E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.903 | TFLOPs: 28.95 | +7: iteration 16470/ 21553 | consumed samples: 4216320 | consumed tokens: 8635023360 | elapsed time per iteration (s): 0.31 | learning rate: 4.405E-05 | global batch size: 256 | lm loss: 2.989225E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.154 | TFLOPs: 28.85 | +7: iteration 16480/ 21553 | consumed samples: 4218880 | consumed tokens: 8640266240 | elapsed time per iteration (s): 0.31 | learning rate: 4.396E-05 | global batch size: 256 | lm loss: 2.970274E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.360 | TFLOPs: 28.61 | +7: iteration 16490/ 21553 | consumed samples: 4221440 | consumed tokens: 8645509120 | elapsed time per iteration (s): 0.31 | learning rate: 4.387E-05 | global batch size: 256 | lm loss: 2.968129E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.639 | TFLOPs: 28.73 | +7: iteration 16500/ 21553 | consumed samples: 4224000 | consumed tokens: 8650752000 | elapsed time per iteration (s): 0.31 | learning rate: 4.378E-05 | global batch size: 256 | lm loss: 2.965632E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.519 | TFLOPs: 29.32 | +7: iteration 16510/ 21553 | consumed samples: 4226560 | consumed tokens: 8655994880 | elapsed time per iteration (s): 0.31 | learning rate: 4.369E-05 | global batch size: 256 | lm loss: 2.950434E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.729 | TFLOPs: 28.87 | +7: iteration 16520/ 21553 | consumed samples: 4229120 | consumed tokens: 8661237760 | elapsed time per iteration (s): 0.31 | learning rate: 4.360E-05 | global batch size: 256 | lm loss: 2.974767E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.399 | TFLOPs: 28.72 | +7: iteration 16530/ 21553 | consumed samples: 4231680 | consumed tokens: 8666480640 | elapsed time per iteration (s): 0.31 | learning rate: 4.351E-05 | global batch size: 256 | lm loss: 2.975504E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.102 | TFLOPs: 29.23 | +7: iteration 16540/ 21553 | consumed samples: 4234240 | consumed tokens: 8671723520 | elapsed time per iteration (s): 0.31 | learning rate: 4.342E-05 | global batch size: 256 | lm loss: 2.945563E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.524 | TFLOPs: 28.97 | +7: iteration 16550/ 21553 | consumed samples: 4236800 | consumed tokens: 8676966400 | elapsed time per iteration (s): 0.31 | learning rate: 4.333E-05 | global batch size: 256 | lm loss: 2.974348E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.387 | TFLOPs: 28.72 | +7: iteration 16560/ 21553 | consumed samples: 4239360 | consumed tokens: 8682209280 | elapsed time per iteration (s): 0.31 | learning rate: 4.324E-05 | global batch size: 256 | lm loss: 2.999898E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.200 | TFLOPs: 28.64 | +7: iteration 16570/ 21553 | consumed samples: 4241920 | consumed tokens: 8687452160 | elapsed time per iteration (s): 0.31 | learning rate: 4.315E-05 | global batch size: 256 | lm loss: 2.968539E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.734 | TFLOPs: 29.15 | +7: iteration 16580/ 21553 | consumed samples: 4244480 | consumed tokens: 8692695040 | elapsed time per iteration (s): 0.32 | learning rate: 4.307E-05 | global batch size: 256 | lm loss: 2.959314E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 804.629 | TFLOPs: 28.17 | +7: iteration 16590/ 21553 | consumed samples: 4247040 | consumed tokens: 8697937920 | elapsed time per iteration (s): 0.31 | learning rate: 4.298E-05 | global batch size: 256 | lm loss: 2.962218E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.629 | TFLOPs: 29.08 | +7: iteration 16600/ 21553 | consumed samples: 4249600 | consumed tokens: 8703180800 | elapsed time per iteration (s): 0.31 | learning rate: 4.289E-05 | global batch size: 256 | lm loss: 2.965730E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.351 | TFLOPs: 29.07 | +7: iteration 16610/ 21553 | consumed samples: 4252160 | consumed tokens: 8708423680 | elapsed time per iteration (s): 0.31 | learning rate: 4.280E-05 | global batch size: 256 | lm loss: 2.947025E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.414 | TFLOPs: 28.90 | +7: iteration 16620/ 21553 | consumed samples: 4254720 | consumed tokens: 8713666560 | elapsed time per iteration (s): 0.31 | learning rate: 4.271E-05 | global batch size: 256 | lm loss: 3.002544E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.986 | TFLOPs: 29.27 | +7: iteration 16630/ 21553 | consumed samples: 4257280 | consumed tokens: 8718909440 | elapsed time per iteration (s): 0.31 | learning rate: 4.263E-05 | global batch size: 256 | lm loss: 2.993179E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.941 | TFLOPs: 29.26 | +7: iteration 16640/ 21553 | consumed samples: 4259840 | consumed tokens: 8724152320 | elapsed time per iteration (s): 0.31 | learning rate: 4.254E-05 | global batch size: 256 | lm loss: 2.946023E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.663 | TFLOPs: 29.01 | +7: iteration 16650/ 21553 | consumed samples: 4262400 | consumed tokens: 8729395200 | elapsed time per iteration (s): 0.31 | learning rate: 4.245E-05 | global batch size: 256 | lm loss: 2.968079E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.367 | TFLOPs: 29.35 | +7: iteration 16660/ 21553 | consumed samples: 4264960 | consumed tokens: 8734638080 | elapsed time per iteration (s): 0.31 | learning rate: 4.236E-05 | global batch size: 256 | lm loss: 2.963610E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.679 | TFLOPs: 28.90 | +7: iteration 16670/ 21553 | consumed samples: 4267520 | consumed tokens: 8739880960 | elapsed time per iteration (s): 0.33 | learning rate: 4.227E-05 | global batch size: 256 | lm loss: 2.948724E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 777.837 | TFLOPs: 27.23 | +7: iteration 16680/ 21553 | consumed samples: 4270080 | consumed tokens: 8745123840 | elapsed time per iteration (s): 0.31 | learning rate: 4.219E-05 | global batch size: 256 | lm loss: 2.965586E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.918 | TFLOPs: 29.23 | +7: iteration 16690/ 21553 | consumed samples: 4272640 | consumed tokens: 8750366720 | elapsed time per iteration (s): 0.31 | learning rate: 4.210E-05 | global batch size: 256 | lm loss: 2.975655E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.418 | TFLOPs: 29.14 | +7: iteration 16700/ 21553 | consumed samples: 4275200 | consumed tokens: 8755609600 | elapsed time per iteration (s): 0.33 | learning rate: 4.201E-05 | global batch size: 256 | lm loss: 2.960120E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 780.774 | TFLOPs: 27.33 | +7: iteration 16710/ 21553 | consumed samples: 4277760 | consumed tokens: 8760852480 | elapsed time per iteration (s): 0.31 | learning rate: 4.193E-05 | global batch size: 256 | lm loss: 2.970806E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.109 | TFLOPs: 29.30 | +7: iteration 16720/ 21553 | consumed samples: 4280320 | consumed tokens: 8766095360 | elapsed time per iteration (s): 0.31 | learning rate: 4.184E-05 | global batch size: 256 | lm loss: 2.957563E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.468 | TFLOPs: 29.11 | +7: iteration 16730/ 21553 | consumed samples: 4282880 | consumed tokens: 8771338240 | elapsed time per iteration (s): 0.31 | learning rate: 4.175E-05 | global batch size: 256 | lm loss: 2.992184E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.593 | TFLOPs: 28.59 | +7: iteration 16740/ 21553 | consumed samples: 4285440 | consumed tokens: 8776581120 | elapsed time per iteration (s): 0.31 | learning rate: 4.167E-05 | global batch size: 256 | lm loss: 2.953491E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.884 | TFLOPs: 28.81 | +7: iteration 16750/ 21553 | consumed samples: 4288000 | consumed tokens: 8781824000 | elapsed time per iteration (s): 0.31 | learning rate: 4.158E-05 | global batch size: 256 | lm loss: 2.988221E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.802 | TFLOPs: 28.56 | +7: iteration 16760/ 21553 | consumed samples: 4290560 | consumed tokens: 8787066880 | elapsed time per iteration (s): 0.31 | learning rate: 4.150E-05 | global batch size: 256 | lm loss: 2.994885E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.392 | TFLOPs: 28.61 | +7: iteration 16770/ 21553 | consumed samples: 4293120 | consumed tokens: 8792309760 | elapsed time per iteration (s): 0.31 | learning rate: 4.141E-05 | global batch size: 256 | lm loss: 2.949909E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.219 | TFLOPs: 29.31 | +7: iteration 16780/ 21553 | consumed samples: 4295680 | consumed tokens: 8797552640 | elapsed time per iteration (s): 0.32 | learning rate: 4.132E-05 | global batch size: 256 | lm loss: 3.009492E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.646 | TFLOPs: 28.45 | +7: iteration 16790/ 21553 | consumed samples: 4298240 | consumed tokens: 8802795520 | elapsed time per iteration (s): 0.31 | learning rate: 4.124E-05 | global batch size: 256 | lm loss: 2.985992E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.158 | TFLOPs: 29.10 | +7: iteration 16800/ 21553 | consumed samples: 4300800 | consumed tokens: 8808038400 | elapsed time per iteration (s): 0.31 | learning rate: 4.115E-05 | global batch size: 256 | lm loss: 2.972214E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.741 | TFLOPs: 29.01 | +7: iteration 16810/ 21553 | consumed samples: 4303360 | consumed tokens: 8813281280 | elapsed time per iteration (s): 0.31 | learning rate: 4.107E-05 | global batch size: 256 | lm loss: 2.978556E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.834 | TFLOPs: 29.05 | +7: iteration 16820/ 21553 | consumed samples: 4305920 | consumed tokens: 8818524160 | elapsed time per iteration (s): 0.31 | learning rate: 4.098E-05 | global batch size: 256 | lm loss: 2.989198E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.815 | TFLOPs: 28.80 | +7: iteration 16830/ 21553 | consumed samples: 4308480 | consumed tokens: 8823767040 | elapsed time per iteration (s): 0.32 | learning rate: 4.090E-05 | global batch size: 256 | lm loss: 2.953688E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.723 | TFLOPs: 28.31 | +7: iteration 16840/ 21553 | consumed samples: 4311040 | consumed tokens: 8829009920 | elapsed time per iteration (s): 0.31 | learning rate: 4.081E-05 | global batch size: 256 | lm loss: 2.961486E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.818 | TFLOPs: 29.22 | +7: iteration 16850/ 21553 | consumed samples: 4313600 | consumed tokens: 8834252800 | elapsed time per iteration (s): 0.31 | learning rate: 4.073E-05 | global batch size: 256 | lm loss: 2.964079E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.794 | TFLOPs: 29.05 | +7: iteration 16860/ 21553 | consumed samples: 4316160 | consumed tokens: 8839495680 | elapsed time per iteration (s): 0.31 | learning rate: 4.064E-05 | global batch size: 256 | lm loss: 2.993197E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.487 | TFLOPs: 29.14 | +7: iteration 16870/ 21553 | consumed samples: 4318720 | consumed tokens: 8844738560 | elapsed time per iteration (s): 0.32 | learning rate: 4.056E-05 | global batch size: 256 | lm loss: 2.962444E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 789.431 | TFLOPs: 27.64 | +7: iteration 16880/ 21553 | consumed samples: 4321280 | consumed tokens: 8849981440 | elapsed time per iteration (s): 0.31 | learning rate: 4.047E-05 | global batch size: 256 | lm loss: 2.956591E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.604 | TFLOPs: 29.29 | +7: iteration 16890/ 21553 | consumed samples: 4323840 | consumed tokens: 8855224320 | elapsed time per iteration (s): 0.30 | learning rate: 4.039E-05 | global batch size: 256 | lm loss: 2.981799E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.123 | TFLOPs: 29.45 | +7: iteration 16900/ 21553 | consumed samples: 4326400 | consumed tokens: 8860467200 | elapsed time per iteration (s): 0.31 | learning rate: 4.031E-05 | global batch size: 256 | lm loss: 2.956125E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.958 | TFLOPs: 28.95 | +7: iteration 16910/ 21553 | consumed samples: 4328960 | consumed tokens: 8865710080 | elapsed time per iteration (s): 0.31 | learning rate: 4.022E-05 | global batch size: 256 | lm loss: 2.936181E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.549 | TFLOPs: 28.97 | +7: iteration 16920/ 21553 | consumed samples: 4331520 | consumed tokens: 8870952960 | elapsed time per iteration (s): 0.31 | learning rate: 4.014E-05 | global batch size: 256 | lm loss: 2.970008E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.768 | TFLOPs: 29.22 | +7: iteration 16930/ 21553 | consumed samples: 4334080 | consumed tokens: 8876195840 | elapsed time per iteration (s): 0.31 | learning rate: 4.006E-05 | global batch size: 256 | lm loss: 2.997113E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.145 | TFLOPs: 29.03 | +7: iteration 16940/ 21553 | consumed samples: 4336640 | consumed tokens: 8881438720 | elapsed time per iteration (s): 0.31 | learning rate: 3.997E-05 | global batch size: 256 | lm loss: 2.956202E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.971 | TFLOPs: 29.37 | +7: iteration 16950/ 21553 | consumed samples: 4339200 | consumed tokens: 8886681600 | elapsed time per iteration (s): 0.31 | learning rate: 3.989E-05 | global batch size: 256 | lm loss: 2.996244E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.066 | TFLOPs: 28.67 | +7: iteration 16960/ 21553 | consumed samples: 4341760 | consumed tokens: 8891924480 | elapsed time per iteration (s): 0.31 | learning rate: 3.981E-05 | global batch size: 256 | lm loss: 2.953942E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.929 | TFLOPs: 28.88 | +7: iteration 16970/ 21553 | consumed samples: 4344320 | consumed tokens: 8897167360 | elapsed time per iteration (s): 0.31 | learning rate: 3.972E-05 | global batch size: 256 | lm loss: 2.955452E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.360 | TFLOPs: 28.96 | +7: iteration 16980/ 21553 | consumed samples: 4346880 | consumed tokens: 8902410240 | elapsed time per iteration (s): 0.31 | learning rate: 3.964E-05 | global batch size: 256 | lm loss: 2.966671E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.015 | TFLOPs: 29.37 | +7: iteration 16990/ 21553 | consumed samples: 4349440 | consumed tokens: 8907653120 | elapsed time per iteration (s): 0.30 | learning rate: 3.956E-05 | global batch size: 256 | lm loss: 2.924035E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 844.586 | TFLOPs: 29.57 | +7: iteration 17000/ 21553 | consumed samples: 4352000 | consumed tokens: 8912896000 | elapsed time per iteration (s): 0.31 | learning rate: 3.948E-05 | global batch size: 256 | lm loss: 2.979325E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.769 | TFLOPs: 28.84 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 17000 | lm loss value: 2.879547E+00 | lm loss PPL: 1.780620E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 17000 to checkpoints_146moscareap +0: [2022-11-29 18:36:16,404] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step17000 is begin to save! +0: [2022-11-29 18:36:16,409] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:36:16,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:36:16,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:36:16,524] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:36:16,524] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:36:16,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:36:16,541] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:36:16,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:36:16,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:36:16,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:36:16,573] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:36:16,589] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:36:16,589] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:36:16,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:36:16,605] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:36:16,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:36:16,621] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:36:16,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:36:16,637] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:36:16,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:36:16,653] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:36:16,669] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:36:16,669] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/layer_13-model_00-model_states.pt... +0: [2022-11-29 18:36:16,685] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/layer_13-model_00-model_states.pt. +0: [2022-11-29 18:36:16,685] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:36:16,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:36:16,701] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/layer_15-model_00-model_states.pt... +0: [2022-11-29 18:36:16,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/layer_15-model_00-model_states.pt. +0: [2022-11-29 18:36:16,718] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/layer_16-model_00-model_states.pt... +0: [2022-11-29 18:36:16,733] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/layer_16-model_00-model_states.pt. +0: [2022-11-29 18:36:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/layer_17-model_00-model_states.pt... +0: [2022-11-29 18:36:16,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/layer_17-model_00-model_states.pt. +0: [2022-11-29 18:36:16,750] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/layer_19-model_00-model_states.pt... +0: [2022-11-29 18:36:16,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/layer_19-model_00-model_states.pt. +0: [2022-11-29 18:36:16,752] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_146moscareap/global_step17000/mp_rank_00_model_states.pt +0: [2022-11-29 18:36:16,752] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:36:16,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:36:16,773] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:36:16,773] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:36:16,773] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:36:16,773] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:36:16,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:36:16,773] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:36:16,773] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:36:16,806] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:36:16,806] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:36:16,806] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +7: [2022-11-29 18:36:16,806] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:36:16,806] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:36:16,806] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +1: [2022-11-29 18:36:16,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:36:16,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:36:16,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +2: [2022-11-29 18:36:16,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:36:16,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:36:16,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +7: [2022-11-29 18:36:16,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:36:16,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:36:16,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:36:16,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:36:16,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +7: [2022-11-29 18:36:16,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +5: [2022-11-29 18:36:16,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +5: [2022-11-29 18:36:16,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +2: [2022-11-29 18:36:16,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:36:16,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +2: [2022-11-29 18:36:16,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:36:16,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +5: [2022-11-29 18:36:16,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:36:16,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:36:16,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +2: [2022-11-29 18:36:16,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:36:16,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:36:16,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +5: [2022-11-29 18:36:16,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:36:16,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:36:16,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +1: [2022-11-29 18:36:16,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:36:16,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +5: [2022-11-29 18:36:16,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +1: [2022-11-29 18:36:16,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:36:16,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:36:16,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +7: [2022-11-29 18:36:16,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +1: [2022-11-29 18:36:16,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +7: [2022-11-29 18:36:16,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +4: [2022-11-29 18:36:16,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:36:16,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:36:16,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +4: [2022-11-29 18:36:16,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:36:16,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:36:16,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +6: [2022-11-29 18:36:16,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:36:16,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:36:16,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:36:16,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:36:16,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:36:16,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +6: [2022-11-29 18:36:16,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +0: [2022-11-29 18:36:16,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:36:16,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:36:16,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +1: [2022-11-29 18:36:16,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:36:16,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:36:16,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +2: [2022-11-29 18:36:16,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +1: [2022-11-29 18:36:16,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +2: [2022-11-29 18:36:16,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +0: [2022-11-29 18:36:16,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:36:16,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:36:16,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +0: [2022-11-29 18:36:16,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:36:16,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:36:16,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:36:16,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +7: [2022-11-29 18:36:16,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:36:16,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +2: [2022-11-29 18:36:16,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:36:16,812] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:36:16,812] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +0: [2022-11-29 18:36:16,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:36:16,812] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:36:16,812] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +6: [2022-11-29 18:36:16,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:36:16,812] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:36:16,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:36:16,812] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +6: [2022-11-29 18:36:16,812] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:36:16,812] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +6: [2022-11-29 18:36:16,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:36:16,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:36:16,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +1: [2022-11-29 18:36:16,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:36:16,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:36:16,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +2: [2022-11-29 18:36:16,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:36:16,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:36:16,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +7: [2022-11-29 18:36:16,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:36:16,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:36:16,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:36:16,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:36:16,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +7: [2022-11-29 18:36:16,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:36:16,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +6: [2022-11-29 18:36:16,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +7: [2022-11-29 18:36:16,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:36:16,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +7: [2022-11-29 18:36:16,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +7: [2022-11-29 18:36:16,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +7: [2022-11-29 18:36:16,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:36:16,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:36:16,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +6: [2022-11-29 18:36:16,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:36:16,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:36:16,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +5: [2022-11-29 18:36:16,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:36:16,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:36:16,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:36:16,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:36:16,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +5: [2022-11-29 18:36:16,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +5: [2022-11-29 18:36:16,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:36:16,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +0: [2022-11-29 18:36:16,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:36:16,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +0: [2022-11-29 18:36:16,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:36:16,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +0: [2022-11-29 18:36:16,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:36:16,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:36:16,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +2: [2022-11-29 18:36:16,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:36:16,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:36:16,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +1: [2022-11-29 18:36:16,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:36:16,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:36:16,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +4: [2022-11-29 18:36:16,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:36:16,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:36:16,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +6: [2022-11-29 18:36:16,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:36:16,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:36:16,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +0: [2022-11-29 18:36:16,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:36:16,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:36:16,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:36:16,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +1: [2022-11-29 18:36:16,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +4: [2022-11-29 18:36:16,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +0: [2022-11-29 18:36:16,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +4: [2022-11-29 18:36:16,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +1: [2022-11-29 18:36:16,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +4: [2022-11-29 18:36:16,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:36:16,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:36:16,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +1: [2022-11-29 18:36:16,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:36:16,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +4: [2022-11-29 18:36:16,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:36:16,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:36:16,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:36:16,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:36:16,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +1: [2022-11-29 18:36:16,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +4: [2022-11-29 18:36:16,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:36:16,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +4: [2022-11-29 18:36:16,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +4: [2022-11-29 18:36:16,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +5: [2022-11-29 18:36:16,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:36:16,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:36:16,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +3: [2022-11-29 18:36:16,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:36:16,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:36:16,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +3: [2022-11-29 18:36:16,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:36:16,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:36:16,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +3: [2022-11-29 18:36:16,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:36:16,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:36:16,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +3: [2022-11-29 18:36:16,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:36:16,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:36:16,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +3: [2022-11-29 18:36:16,828] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:36:16,828] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:36:16,828] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +3: [2022-11-29 18:36:16,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:36:16,829] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:36:16,829] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +3: [2022-11-29 18:36:16,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:36:16,829] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:36:16,829] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +3: [2022-11-29 18:36:16,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:36:16,832] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:36:16,833] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +0: [2022-11-29 18:36:16,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step17000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:36:16,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +0: successfully saved checkpoint at iteration 17000 to checkpoints_146moscareap +7: time (ms) | save-checkpoint: 442.61 +7: iteration 17010/ 21553 | consumed samples: 4354560 | consumed tokens: 8918138880 | elapsed time per iteration (s): 0.36 | learning rate: 3.939E-05 | global batch size: 256 | lm loss: 2.961952E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 706.051 | TFLOPs: 24.72 | +7: iteration 17020/ 21553 | consumed samples: 4357120 | consumed tokens: 8923381760 | elapsed time per iteration (s): 0.33 | learning rate: 3.931E-05 | global batch size: 256 | lm loss: 2.977371E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 775.952 | TFLOPs: 27.16 | +7: iteration 17030/ 21553 | consumed samples: 4359680 | consumed tokens: 8928624640 | elapsed time per iteration (s): 0.31 | learning rate: 3.923E-05 | global batch size: 256 | lm loss: 2.932738E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.792 | TFLOPs: 28.59 | +7: iteration 17040/ 21553 | consumed samples: 4362240 | consumed tokens: 8933867520 | elapsed time per iteration (s): 0.31 | learning rate: 3.915E-05 | global batch size: 256 | lm loss: 2.964189E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.816 | TFLOPs: 28.98 | +7: iteration 17050/ 21553 | consumed samples: 4364800 | consumed tokens: 8939110400 | elapsed time per iteration (s): 0.31 | learning rate: 3.907E-05 | global batch size: 256 | lm loss: 2.956125E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.458 | TFLOPs: 28.97 | +7: iteration 17060/ 21553 | consumed samples: 4367360 | consumed tokens: 8944353280 | elapsed time per iteration (s): 0.31 | learning rate: 3.898E-05 | global batch size: 256 | lm loss: 2.980567E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.837 | TFLOPs: 29.02 | +7: iteration 17070/ 21553 | consumed samples: 4369920 | consumed tokens: 8949596160 | elapsed time per iteration (s): 0.31 | learning rate: 3.890E-05 | global batch size: 256 | lm loss: 2.965784E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.415 | TFLOPs: 29.18 | +7: iteration 17080/ 21553 | consumed samples: 4372480 | consumed tokens: 8954839040 | elapsed time per iteration (s): 0.31 | learning rate: 3.882E-05 | global batch size: 256 | lm loss: 2.984298E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.716 | TFLOPs: 28.91 | +7: iteration 17090/ 21553 | consumed samples: 4375040 | consumed tokens: 8960081920 | elapsed time per iteration (s): 0.31 | learning rate: 3.874E-05 | global batch size: 256 | lm loss: 2.971173E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.461 | TFLOPs: 28.69 | +7: iteration 17100/ 21553 | consumed samples: 4377600 | consumed tokens: 8965324800 | elapsed time per iteration (s): 0.32 | learning rate: 3.866E-05 | global batch size: 256 | lm loss: 2.993222E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 809.801 | TFLOPs: 28.35 | +7: iteration 17110/ 21553 | consumed samples: 4380160 | consumed tokens: 8970567680 | elapsed time per iteration (s): 0.31 | learning rate: 3.858E-05 | global batch size: 256 | lm loss: 2.940144E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.966 | TFLOPs: 29.19 | +7: iteration 17120/ 21553 | consumed samples: 4382720 | consumed tokens: 8975810560 | elapsed time per iteration (s): 0.31 | learning rate: 3.850E-05 | global batch size: 256 | lm loss: 2.970940E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.055 | TFLOPs: 28.85 | +7: iteration 17130/ 21553 | consumed samples: 4385280 | consumed tokens: 8981053440 | elapsed time per iteration (s): 0.31 | learning rate: 3.842E-05 | global batch size: 256 | lm loss: 2.992346E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.873 | TFLOPs: 29.02 | +7: iteration 17140/ 21553 | consumed samples: 4387840 | consumed tokens: 8986296320 | elapsed time per iteration (s): 0.31 | learning rate: 3.834E-05 | global batch size: 256 | lm loss: 2.983832E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.023 | TFLOPs: 28.88 | +7: iteration 17150/ 21553 | consumed samples: 4390400 | consumed tokens: 8991539200 | elapsed time per iteration (s): 0.32 | learning rate: 3.826E-05 | global batch size: 256 | lm loss: 2.961102E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.864 | TFLOPs: 28.39 | +7: iteration 17160/ 21553 | consumed samples: 4392960 | consumed tokens: 8996782080 | elapsed time per iteration (s): 0.31 | learning rate: 3.818E-05 | global batch size: 256 | lm loss: 2.958002E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.832 | TFLOPs: 28.63 | +7: iteration 17170/ 21553 | consumed samples: 4395520 | consumed tokens: 9002024960 | elapsed time per iteration (s): 0.30 | learning rate: 3.810E-05 | global batch size: 256 | lm loss: 2.954753E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 846.386 | TFLOPs: 29.63 | +7: iteration 17180/ 21553 | consumed samples: 4398080 | consumed tokens: 9007267840 | elapsed time per iteration (s): 0.31 | learning rate: 3.802E-05 | global batch size: 256 | lm loss: 2.977147E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.172 | TFLOPs: 29.03 | +7: iteration 17190/ 21553 | consumed samples: 4400640 | consumed tokens: 9012510720 | elapsed time per iteration (s): 0.30 | learning rate: 3.794E-05 | global batch size: 256 | lm loss: 2.955858E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.811 | TFLOPs: 29.40 | +7: iteration 17200/ 21553 | consumed samples: 4403200 | consumed tokens: 9017753600 | elapsed time per iteration (s): 0.31 | learning rate: 3.786E-05 | global batch size: 256 | lm loss: 2.949971E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.109 | TFLOPs: 29.20 | +7: iteration 17210/ 21553 | consumed samples: 4405760 | consumed tokens: 9022996480 | elapsed time per iteration (s): 0.31 | learning rate: 3.778E-05 | global batch size: 256 | lm loss: 2.976286E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.564 | TFLOPs: 29.11 | +7: iteration 17220/ 21553 | consumed samples: 4408320 | consumed tokens: 9028239360 | elapsed time per iteration (s): 0.32 | learning rate: 3.770E-05 | global batch size: 256 | lm loss: 2.970787E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.170 | TFLOPs: 28.40 | +7: iteration 17230/ 21553 | consumed samples: 4410880 | consumed tokens: 9033482240 | elapsed time per iteration (s): 0.32 | learning rate: 3.762E-05 | global batch size: 256 | lm loss: 2.989794E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 803.486 | TFLOPs: 28.13 | +7: iteration 17240/ 21553 | consumed samples: 4413440 | consumed tokens: 9038725120 | elapsed time per iteration (s): 0.31 | learning rate: 3.754E-05 | global batch size: 256 | lm loss: 2.968856E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.724 | TFLOPs: 29.29 | +7: iteration 17250/ 21553 | consumed samples: 4416000 | consumed tokens: 9043968000 | elapsed time per iteration (s): 0.31 | learning rate: 3.747E-05 | global batch size: 256 | lm loss: 2.955657E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.742 | TFLOPs: 28.77 | +7: iteration 17260/ 21553 | consumed samples: 4418560 | consumed tokens: 9049210880 | elapsed time per iteration (s): 0.31 | learning rate: 3.739E-05 | global batch size: 256 | lm loss: 2.980139E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.631 | TFLOPs: 29.29 | +7: iteration 17270/ 21553 | consumed samples: 4421120 | consumed tokens: 9054453760 | elapsed time per iteration (s): 0.31 | learning rate: 3.731E-05 | global batch size: 256 | lm loss: 2.963537E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.541 | TFLOPs: 29.28 | +7: iteration 17280/ 21553 | consumed samples: 4423680 | consumed tokens: 9059696640 | elapsed time per iteration (s): 0.30 | learning rate: 3.723E-05 | global batch size: 256 | lm loss: 2.948755E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.405 | TFLOPs: 29.39 | +7: iteration 17290/ 21553 | consumed samples: 4426240 | consumed tokens: 9064939520 | elapsed time per iteration (s): 0.31 | learning rate: 3.715E-05 | global batch size: 256 | lm loss: 2.960438E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.328 | TFLOPs: 29.21 | +7: iteration 17300/ 21553 | consumed samples: 4428800 | consumed tokens: 9070182400 | elapsed time per iteration (s): 0.31 | learning rate: 3.708E-05 | global batch size: 256 | lm loss: 2.960439E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.406 | TFLOPs: 28.83 | +7: iteration 17310/ 21553 | consumed samples: 4431360 | consumed tokens: 9075425280 | elapsed time per iteration (s): 0.31 | learning rate: 3.700E-05 | global batch size: 256 | lm loss: 2.962347E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.975 | TFLOPs: 28.85 | +7: iteration 17320/ 21553 | consumed samples: 4433920 | consumed tokens: 9080668160 | elapsed time per iteration (s): 0.31 | learning rate: 3.692E-05 | global batch size: 256 | lm loss: 2.958284E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.622 | TFLOPs: 29.15 | +7: iteration 17330/ 21553 | consumed samples: 4436480 | consumed tokens: 9085911040 | elapsed time per iteration (s): 0.31 | learning rate: 3.684E-05 | global batch size: 256 | lm loss: 2.954331E+00 | grad norm: 0.373 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.031 | TFLOPs: 29.20 | +7: iteration 17340/ 21553 | consumed samples: 4439040 | consumed tokens: 9091153920 | elapsed time per iteration (s): 0.33 | learning rate: 3.677E-05 | global batch size: 256 | lm loss: 2.931294E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 777.954 | TFLOPs: 27.23 | +7: iteration 17350/ 21553 | consumed samples: 4441600 | consumed tokens: 9096396800 | elapsed time per iteration (s): 0.32 | learning rate: 3.669E-05 | global batch size: 256 | lm loss: 2.962912E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 803.582 | TFLOPs: 28.13 | +7: iteration 17360/ 21553 | consumed samples: 4444160 | consumed tokens: 9101639680 | elapsed time per iteration (s): 0.30 | learning rate: 3.661E-05 | global batch size: 256 | lm loss: 2.982761E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.391 | TFLOPs: 29.59 | +7: iteration 17370/ 21553 | consumed samples: 4446720 | consumed tokens: 9106882560 | elapsed time per iteration (s): 0.31 | learning rate: 3.654E-05 | global batch size: 256 | lm loss: 2.973754E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.524 | TFLOPs: 29.00 | +7: iteration 17380/ 21553 | consumed samples: 4449280 | consumed tokens: 9112125440 | elapsed time per iteration (s): 0.31 | learning rate: 3.646E-05 | global batch size: 256 | lm loss: 2.972499E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.044 | TFLOPs: 28.85 | +7: iteration 17390/ 21553 | consumed samples: 4451840 | consumed tokens: 9117368320 | elapsed time per iteration (s): 0.31 | learning rate: 3.638E-05 | global batch size: 256 | lm loss: 2.962784E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.772 | TFLOPs: 29.08 | +7: iteration 17400/ 21553 | consumed samples: 4454400 | consumed tokens: 9122611200 | elapsed time per iteration (s): 0.30 | learning rate: 3.631E-05 | global batch size: 256 | lm loss: 2.962318E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 847.757 | TFLOPs: 29.68 | +7: iteration 17410/ 21553 | consumed samples: 4456960 | consumed tokens: 9127854080 | elapsed time per iteration (s): 0.31 | learning rate: 3.623E-05 | global batch size: 256 | lm loss: 2.940026E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.615 | TFLOPs: 28.94 | +7: iteration 17420/ 21553 | consumed samples: 4459520 | consumed tokens: 9133096960 | elapsed time per iteration (s): 0.31 | learning rate: 3.616E-05 | global batch size: 256 | lm loss: 2.980917E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.734 | TFLOPs: 28.56 | +7: iteration 17430/ 21553 | consumed samples: 4462080 | consumed tokens: 9138339840 | elapsed time per iteration (s): 0.31 | learning rate: 3.608E-05 | global batch size: 256 | lm loss: 2.946602E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.473 | TFLOPs: 28.83 | +7: iteration 17440/ 21553 | consumed samples: 4464640 | consumed tokens: 9143582720 | elapsed time per iteration (s): 0.31 | learning rate: 3.600E-05 | global batch size: 256 | lm loss: 2.994626E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.257 | TFLOPs: 29.28 | +7: iteration 17450/ 21553 | consumed samples: 4467200 | consumed tokens: 9148825600 | elapsed time per iteration (s): 0.31 | learning rate: 3.593E-05 | global batch size: 256 | lm loss: 2.945967E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.381 | TFLOPs: 28.47 | +7: iteration 17460/ 21553 | consumed samples: 4469760 | consumed tokens: 9154068480 | elapsed time per iteration (s): 0.30 | learning rate: 3.585E-05 | global batch size: 256 | lm loss: 2.978754E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.907 | TFLOPs: 29.44 | +7: iteration 17470/ 21553 | consumed samples: 4472320 | consumed tokens: 9159311360 | elapsed time per iteration (s): 0.31 | learning rate: 3.578E-05 | global batch size: 256 | lm loss: 2.929362E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.718 | TFLOPs: 29.22 | +7: iteration 17480/ 21553 | consumed samples: 4474880 | consumed tokens: 9164554240 | elapsed time per iteration (s): 0.31 | learning rate: 3.570E-05 | global batch size: 256 | lm loss: 2.991827E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.003 | TFLOPs: 29.06 | +7: iteration 17490/ 21553 | consumed samples: 4477440 | consumed tokens: 9169797120 | elapsed time per iteration (s): 0.32 | learning rate: 3.563E-05 | global batch size: 256 | lm loss: 2.959240E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.768 | TFLOPs: 28.31 | +7: iteration 17500/ 21553 | consumed samples: 4480000 | consumed tokens: 9175040000 | elapsed time per iteration (s): 0.30 | learning rate: 3.555E-05 | global batch size: 256 | lm loss: 2.969601E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.985 | TFLOPs: 29.48 | +7: iteration 17510/ 21553 | consumed samples: 4482560 | consumed tokens: 9180282880 | elapsed time per iteration (s): 0.31 | learning rate: 3.548E-05 | global batch size: 256 | lm loss: 2.946519E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.619 | TFLOPs: 29.01 | +7: iteration 17520/ 21553 | consumed samples: 4485120 | consumed tokens: 9185525760 | elapsed time per iteration (s): 0.31 | learning rate: 3.541E-05 | global batch size: 256 | lm loss: 2.930580E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.035 | TFLOPs: 29.16 | +7: iteration 17530/ 21553 | consumed samples: 4487680 | consumed tokens: 9190768640 | elapsed time per iteration (s): 0.31 | learning rate: 3.533E-05 | global batch size: 256 | lm loss: 2.959623E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.514 | TFLOPs: 28.76 | +7: iteration 17540/ 21553 | consumed samples: 4490240 | consumed tokens: 9196011520 | elapsed time per iteration (s): 0.31 | learning rate: 3.526E-05 | global batch size: 256 | lm loss: 2.993450E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.315 | TFLOPs: 29.38 | +7: iteration 17550/ 21553 | consumed samples: 4492800 | consumed tokens: 9201254400 | elapsed time per iteration (s): 0.31 | learning rate: 3.518E-05 | global batch size: 256 | lm loss: 2.964506E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.091 | TFLOPs: 29.34 | +7: iteration 17560/ 21553 | consumed samples: 4495360 | consumed tokens: 9206497280 | elapsed time per iteration (s): 0.31 | learning rate: 3.511E-05 | global batch size: 256 | lm loss: 2.934958E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.584 | TFLOPs: 28.76 | +7: iteration 17570/ 21553 | consumed samples: 4497920 | consumed tokens: 9211740160 | elapsed time per iteration (s): 0.31 | learning rate: 3.504E-05 | global batch size: 256 | lm loss: 2.973628E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.325 | TFLOPs: 29.24 | +7: iteration 17580/ 21553 | consumed samples: 4500480 | consumed tokens: 9216983040 | elapsed time per iteration (s): 0.30 | learning rate: 3.496E-05 | global batch size: 256 | lm loss: 2.940446E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.827 | TFLOPs: 29.61 | +7: iteration 17590/ 21553 | consumed samples: 4503040 | consumed tokens: 9222225920 | elapsed time per iteration (s): 0.31 | learning rate: 3.489E-05 | global batch size: 256 | lm loss: 2.953769E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.237 | TFLOPs: 28.99 | +7: iteration 17600/ 21553 | consumed samples: 4505600 | consumed tokens: 9227468800 | elapsed time per iteration (s): 0.31 | learning rate: 3.482E-05 | global batch size: 256 | lm loss: 2.968386E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.770 | TFLOPs: 28.87 | +7: iteration 17610/ 21553 | consumed samples: 4508160 | consumed tokens: 9232711680 | elapsed time per iteration (s): 0.30 | learning rate: 3.475E-05 | global batch size: 256 | lm loss: 2.952487E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.867 | TFLOPs: 29.40 | +7: iteration 17620/ 21553 | consumed samples: 4510720 | consumed tokens: 9237954560 | elapsed time per iteration (s): 0.31 | learning rate: 3.467E-05 | global batch size: 256 | lm loss: 2.964771E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.276 | TFLOPs: 28.72 | +7: iteration 17630/ 21553 | consumed samples: 4513280 | consumed tokens: 9243197440 | elapsed time per iteration (s): 0.31 | learning rate: 3.460E-05 | global batch size: 256 | lm loss: 2.939657E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.077 | TFLOPs: 29.20 | +7: iteration 17640/ 21553 | consumed samples: 4515840 | consumed tokens: 9248440320 | elapsed time per iteration (s): 0.31 | learning rate: 3.453E-05 | global batch size: 256 | lm loss: 2.952220E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.007 | TFLOPs: 28.64 | +7: iteration 17650/ 21553 | consumed samples: 4518400 | consumed tokens: 9253683200 | elapsed time per iteration (s): 0.32 | learning rate: 3.446E-05 | global batch size: 256 | lm loss: 2.935992E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 790.462 | TFLOPs: 27.67 | +7: iteration 17660/ 21553 | consumed samples: 4520960 | consumed tokens: 9258926080 | elapsed time per iteration (s): 0.31 | learning rate: 3.438E-05 | global batch size: 256 | lm loss: 2.975636E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.873 | TFLOPs: 29.19 | +7: iteration 17670/ 21553 | consumed samples: 4523520 | consumed tokens: 9264168960 | elapsed time per iteration (s): 0.33 | learning rate: 3.431E-05 | global batch size: 256 | lm loss: 2.975767E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 780.455 | TFLOPs: 27.32 | +7: iteration 17680/ 21553 | consumed samples: 4526080 | consumed tokens: 9269411840 | elapsed time per iteration (s): 0.31 | learning rate: 3.424E-05 | global batch size: 256 | lm loss: 2.982485E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.856 | TFLOPs: 28.98 | +7: iteration 17690/ 21553 | consumed samples: 4528640 | consumed tokens: 9274654720 | elapsed time per iteration (s): 0.31 | learning rate: 3.417E-05 | global batch size: 256 | lm loss: 2.958417E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.148 | TFLOPs: 29.24 | +7: iteration 17700/ 21553 | consumed samples: 4531200 | consumed tokens: 9279897600 | elapsed time per iteration (s): 0.31 | learning rate: 3.410E-05 | global batch size: 256 | lm loss: 2.956221E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.992 | TFLOPs: 28.92 | +7: iteration 17710/ 21553 | consumed samples: 4533760 | consumed tokens: 9285140480 | elapsed time per iteration (s): 0.31 | learning rate: 3.403E-05 | global batch size: 256 | lm loss: 2.950592E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.008 | TFLOPs: 29.34 | +7: iteration 17720/ 21553 | consumed samples: 4536320 | consumed tokens: 9290383360 | elapsed time per iteration (s): 0.31 | learning rate: 3.396E-05 | global batch size: 256 | lm loss: 2.953228E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.235 | TFLOPs: 28.78 | +7: iteration 17730/ 21553 | consumed samples: 4538880 | consumed tokens: 9295626240 | elapsed time per iteration (s): 0.31 | learning rate: 3.388E-05 | global batch size: 256 | lm loss: 2.948323E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.883 | TFLOPs: 28.77 | +7: iteration 17740/ 21553 | consumed samples: 4541440 | consumed tokens: 9300869120 | elapsed time per iteration (s): 0.31 | learning rate: 3.381E-05 | global batch size: 256 | lm loss: 2.954336E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.532 | TFLOPs: 28.97 | +7: iteration 17750/ 21553 | consumed samples: 4544000 | consumed tokens: 9306112000 | elapsed time per iteration (s): 0.31 | learning rate: 3.374E-05 | global batch size: 256 | lm loss: 2.973636E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.316 | TFLOPs: 29.38 | +7: iteration 17760/ 21553 | consumed samples: 4546560 | consumed tokens: 9311354880 | elapsed time per iteration (s): 0.31 | learning rate: 3.367E-05 | global batch size: 256 | lm loss: 2.969100E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.706 | TFLOPs: 29.19 | +7: iteration 17770/ 21553 | consumed samples: 4549120 | consumed tokens: 9316597760 | elapsed time per iteration (s): 0.31 | learning rate: 3.360E-05 | global batch size: 256 | lm loss: 2.971032E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.285 | TFLOPs: 29.24 | +7: iteration 17780/ 21553 | consumed samples: 4551680 | consumed tokens: 9321840640 | elapsed time per iteration (s): 0.31 | learning rate: 3.353E-05 | global batch size: 256 | lm loss: 2.948909E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.902 | TFLOPs: 28.98 | +7: iteration 17790/ 21553 | consumed samples: 4554240 | consumed tokens: 9327083520 | elapsed time per iteration (s): 0.31 | learning rate: 3.346E-05 | global batch size: 256 | lm loss: 2.965229E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.617 | TFLOPs: 28.52 | +7: iteration 17800/ 21553 | consumed samples: 4556800 | consumed tokens: 9332326400 | elapsed time per iteration (s): 0.30 | learning rate: 3.339E-05 | global batch size: 256 | lm loss: 2.983241E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.284 | TFLOPs: 29.42 | +7: iteration 17810/ 21553 | consumed samples: 4559360 | consumed tokens: 9337569280 | elapsed time per iteration (s): 0.31 | learning rate: 3.332E-05 | global batch size: 256 | lm loss: 2.999448E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.192 | TFLOPs: 28.89 | +7: iteration 17820/ 21553 | consumed samples: 4561920 | consumed tokens: 9342812160 | elapsed time per iteration (s): 0.30 | learning rate: 3.326E-05 | global batch size: 256 | lm loss: 2.936773E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.120 | TFLOPs: 29.52 | +7: iteration 17830/ 21553 | consumed samples: 4564480 | consumed tokens: 9348055040 | elapsed time per iteration (s): 0.32 | learning rate: 3.319E-05 | global batch size: 256 | lm loss: 2.978305E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 788.502 | TFLOPs: 27.60 | +7: iteration 17840/ 21553 | consumed samples: 4567040 | consumed tokens: 9353297920 | elapsed time per iteration (s): 0.33 | learning rate: 3.312E-05 | global batch size: 256 | lm loss: 2.965014E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 779.440 | TFLOPs: 27.29 | +7: iteration 17850/ 21553 | consumed samples: 4569600 | consumed tokens: 9358540800 | elapsed time per iteration (s): 0.31 | learning rate: 3.305E-05 | global batch size: 256 | lm loss: 2.953182E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.396 | TFLOPs: 29.00 | +7: iteration 17860/ 21553 | consumed samples: 4572160 | consumed tokens: 9363783680 | elapsed time per iteration (s): 0.32 | learning rate: 3.298E-05 | global batch size: 256 | lm loss: 2.960302E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.354 | TFLOPs: 28.30 | +7: iteration 17870/ 21553 | consumed samples: 4574720 | consumed tokens: 9369026560 | elapsed time per iteration (s): 0.31 | learning rate: 3.291E-05 | global batch size: 256 | lm loss: 2.964002E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.783 | TFLOPs: 29.19 | +7: iteration 17880/ 21553 | consumed samples: 4577280 | consumed tokens: 9374269440 | elapsed time per iteration (s): 0.31 | learning rate: 3.284E-05 | global batch size: 256 | lm loss: 2.956119E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.255 | TFLOPs: 29.38 | +7: iteration 17890/ 21553 | consumed samples: 4579840 | consumed tokens: 9379512320 | elapsed time per iteration (s): 0.31 | learning rate: 3.277E-05 | global batch size: 256 | lm loss: 2.973766E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.834 | TFLOPs: 29.33 | +7: iteration 17900/ 21553 | consumed samples: 4582400 | consumed tokens: 9384755200 | elapsed time per iteration (s): 0.31 | learning rate: 3.271E-05 | global batch size: 256 | lm loss: 2.980167E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.048 | TFLOPs: 29.23 | +7: iteration 17910/ 21553 | consumed samples: 4584960 | consumed tokens: 9389998080 | elapsed time per iteration (s): 0.30 | learning rate: 3.264E-05 | global batch size: 256 | lm loss: 2.942649E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.782 | TFLOPs: 29.50 | +7: iteration 17920/ 21553 | consumed samples: 4587520 | consumed tokens: 9395240960 | elapsed time per iteration (s): 0.31 | learning rate: 3.257E-05 | global batch size: 256 | lm loss: 2.958900E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.614 | TFLOPs: 29.18 | +7: iteration 17930/ 21553 | consumed samples: 4590080 | consumed tokens: 9400483840 | elapsed time per iteration (s): 0.31 | learning rate: 3.250E-05 | global batch size: 256 | lm loss: 2.952410E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.142 | TFLOPs: 28.61 | +7: iteration 17940/ 21553 | consumed samples: 4592640 | consumed tokens: 9405726720 | elapsed time per iteration (s): 0.31 | learning rate: 3.244E-05 | global batch size: 256 | lm loss: 2.962977E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.203 | TFLOPs: 28.99 | +7: iteration 17950/ 21553 | consumed samples: 4595200 | consumed tokens: 9410969600 | elapsed time per iteration (s): 0.31 | learning rate: 3.237E-05 | global batch size: 256 | lm loss: 2.977375E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.326 | TFLOPs: 28.89 | +7: iteration 17960/ 21553 | consumed samples: 4597760 | consumed tokens: 9416212480 | elapsed time per iteration (s): 0.31 | learning rate: 3.230E-05 | global batch size: 256 | lm loss: 2.967260E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.742 | TFLOPs: 28.91 | +7: iteration 17970/ 21553 | consumed samples: 4600320 | consumed tokens: 9421455360 | elapsed time per iteration (s): 0.31 | learning rate: 3.224E-05 | global batch size: 256 | lm loss: 2.947240E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.633 | TFLOPs: 28.76 | +7: iteration 17980/ 21553 | consumed samples: 4602880 | consumed tokens: 9426698240 | elapsed time per iteration (s): 0.31 | learning rate: 3.217E-05 | global batch size: 256 | lm loss: 2.977266E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.836 | TFLOPs: 28.70 | +7: iteration 17990/ 21553 | consumed samples: 4605440 | consumed tokens: 9431941120 | elapsed time per iteration (s): 0.30 | learning rate: 3.210E-05 | global batch size: 256 | lm loss: 2.952966E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.421 | TFLOPs: 29.49 | +0: [2022-11-29 18:41:26,805] [INFO] [logging.py:68:log_dist] [Rank 0] step=18000, skipped=0, lr=[3.2036439682204886e-05, 3.2036439682204886e-05, 3.2036439682204886e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 18000/ 21553 | consumed samples: 4608000 | consumed tokens: 9437184000 | elapsed time per iteration (s): 0.31 | learning rate: 3.204E-05 | global batch size: 256 | lm loss: 2.982598E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.627 | TFLOPs: 29.18 | +0: steps: 18000 loss: 3.0329 iter time (s): 0.309 samples/sec: 828.676 +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 18000 | lm loss value: 2.799227E+00 | lm loss PPL: 1.643194E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 18000 to checkpoints_146moscareap +0: [2022-11-29 18:41:26,929] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step18000 is begin to save! +0: [2022-11-29 18:41:26,933] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:41:27,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:41:27,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:41:27,047] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:41:27,047] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:41:27,065] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:41:27,065] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:41:27,081] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:41:27,081] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:41:27,097] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:41:27,098] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:41:27,114] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:41:27,114] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:41:27,130] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:41:27,130] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:41:27,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:41:27,147] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:41:27,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:41:27,163] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:41:27,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:41:27,180] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:41:27,196] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:41:27,196] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/layer_13-model_00-model_states.pt... +0: [2022-11-29 18:41:27,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/layer_13-model_00-model_states.pt. +0: [2022-11-29 18:41:27,213] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:41:27,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:41:27,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/layer_15-model_00-model_states.pt... +0: [2022-11-29 18:41:27,245] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/layer_15-model_00-model_states.pt. +0: [2022-11-29 18:41:27,246] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/layer_16-model_00-model_states.pt... +0: [2022-11-29 18:41:27,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/layer_16-model_00-model_states.pt. +0: [2022-11-29 18:41:27,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/layer_17-model_00-model_states.pt... +0: [2022-11-29 18:41:27,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/layer_17-model_00-model_states.pt. +0: [2022-11-29 18:41:27,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/layer_19-model_00-model_states.pt... +0: [2022-11-29 18:41:27,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/layer_19-model_00-model_states.pt. +0: [2022-11-29 18:41:27,280] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_146moscareap/global_step18000/mp_rank_00_model_states.pt +0: [2022-11-29 18:41:27,280] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:41:27,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:41:27,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:41:27,332] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:41:27,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:41:27,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +6: [2022-11-29 18:41:27,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:41:27,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:41:27,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +2: [2022-11-29 18:41:27,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:41:27,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:41:27,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +3: [2022-11-29 18:41:27,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:41:27,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:41:27,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +5: [2022-11-29 18:41:27,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:41:27,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:41:27,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +0: [2022-11-29 18:41:27,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +5: [2022-11-29 18:41:27,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +0: [2022-11-29 18:41:27,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +6: [2022-11-29 18:41:27,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:41:27,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:41:27,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +5: [2022-11-29 18:41:27,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:41:27,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:41:27,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +0: [2022-11-29 18:41:27,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:41:27,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:41:27,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:41:27,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:41:27,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +5: [2022-11-29 18:41:27,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:41:27,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +2: [2022-11-29 18:41:27,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:41:27,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:41:27,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +6: [2022-11-29 18:41:27,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +2: [2022-11-29 18:41:27,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +6: [2022-11-29 18:41:27,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +1: [2022-11-29 18:41:27,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:41:27,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:41:27,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +7: [2022-11-29 18:41:27,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:41:27,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:41:27,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +7: [2022-11-29 18:41:27,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:41:27,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:41:27,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +0: [2022-11-29 18:41:27,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:41:27,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3: [2022-11-29 18:41:27,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:41:27,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +0: [2022-11-29 18:41:27,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +3: [2022-11-29 18:41:27,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +3: [2022-11-29 18:41:27,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:41:27,339] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:41:27,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +6: [2022-11-29 18:41:27,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:41:27,339] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:41:27,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +3: [2022-11-29 18:41:27,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:41:27,339] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:41:27,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +1: [2022-11-29 18:41:27,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:41:27,339] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:41:27,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +5: [2022-11-29 18:41:27,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:41:27,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +2: [2022-11-29 18:41:27,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:41:27,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +5: [2022-11-29 18:41:27,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +2: [2022-11-29 18:41:27,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +3: [2022-11-29 18:41:27,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:41:27,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:41:27,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:41:27,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:41:27,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:41:27,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +2: [2022-11-29 18:41:27,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +6: [2022-11-29 18:41:27,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:41:27,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:41:27,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:41:27,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:41:27,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +6: [2022-11-29 18:41:27,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +3: [2022-11-29 18:41:27,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:41:27,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +4: [2022-11-29 18:41:27,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:41:27,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:41:27,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +4: [2022-11-29 18:41:27,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:41:27,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:41:27,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:41:27,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:41:27,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +1: [2022-11-29 18:41:27,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:41:27,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +3: [2022-11-29 18:41:27,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:41:27,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +3: [2022-11-29 18:41:27,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +1: [2022-11-29 18:41:27,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +3: [2022-11-29 18:41:27,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +7: [2022-11-29 18:41:27,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:41:27,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:41:27,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +4: [2022-11-29 18:41:27,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:41:27,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:41:27,342] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:41:27,342] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:41:27,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +4: [2022-11-29 18:41:27,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +3: [2022-11-29 18:41:27,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:41:27,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:41:27,342] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +2: [2022-11-29 18:41:27,342] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +3: [2022-11-29 18:41:27,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +2: [2022-11-29 18:41:27,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +4: [2022-11-29 18:41:27,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:41:27,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:41:27,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +5: [2022-11-29 18:41:27,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:41:27,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:41:27,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +3: [2022-11-29 18:41:27,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:41:27,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:41:27,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +1: [2022-11-29 18:41:27,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +3: [2022-11-29 18:41:27,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +1: [2022-11-29 18:41:27,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +6: [2022-11-29 18:41:27,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:41:27,345] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:41:27,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +4: [2022-11-29 18:41:27,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:41:27,345] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:41:27,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +2: [2022-11-29 18:41:27,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:41:27,345] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:41:27,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +0: [2022-11-29 18:41:27,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:41:27,345] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:41:27,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +0: [2022-11-29 18:41:27,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:41:27,345] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:41:27,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +5: [2022-11-29 18:41:27,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:41:27,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:41:27,346] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:41:27,346] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +4: [2022-11-29 18:41:27,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:41:27,347] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:41:27,347] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +5: [2022-11-29 18:41:27,346] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:41:27,346] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +0: [2022-11-29 18:41:27,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:41:27,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:41:27,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +0: [2022-11-29 18:41:27,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:41:27,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:41:27,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +6: [2022-11-29 18:41:27,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:41:27,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:41:27,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +2: [2022-11-29 18:41:27,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:41:27,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:41:27,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +1: [2022-11-29 18:41:27,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:41:27,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:41:27,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:41:27,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:41:27,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:41:27,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:41:27,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:41:27,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:41:27,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +1: [2022-11-29 18:41:27,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +1: [2022-11-29 18:41:27,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +1: [2022-11-29 18:41:27,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +7: [2022-11-29 18:41:27,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:41:27,347] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:41:27,347] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +7: [2022-11-29 18:41:27,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:41:27,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:41:27,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:41:27,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +7: [2022-11-29 18:41:27,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:41:27,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +7: [2022-11-29 18:41:27,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:41:27,352] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:41:27,352] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +7: [2022-11-29 18:41:27,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:41:27,352] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:41:27,352] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +0: [2022-11-29 18:41:27,374] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step18000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:41:27,374] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +0: successfully saved checkpoint at iteration 18000 to checkpoints_146moscareap +7: time (ms) | save-checkpoint: 449.60 +7: iteration 18010/ 21553 | consumed samples: 4610560 | consumed tokens: 9442426880 | elapsed time per iteration (s): 0.37 | learning rate: 3.197E-05 | global batch size: 256 | lm loss: 2.960490E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 700.739 | TFLOPs: 24.53 | +7: iteration 18020/ 21553 | consumed samples: 4613120 | consumed tokens: 9447669760 | elapsed time per iteration (s): 0.30 | learning rate: 3.190E-05 | global batch size: 256 | lm loss: 2.984208E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 844.666 | TFLOPs: 29.57 | +7: iteration 18030/ 21553 | consumed samples: 4615680 | consumed tokens: 9452912640 | elapsed time per iteration (s): 0.31 | learning rate: 3.184E-05 | global batch size: 256 | lm loss: 2.942823E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.236 | TFLOPs: 29.17 | +7: iteration 18040/ 21553 | consumed samples: 4618240 | consumed tokens: 9458155520 | elapsed time per iteration (s): 0.31 | learning rate: 3.177E-05 | global batch size: 256 | lm loss: 2.929715E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.611 | TFLOPs: 29.11 | +7: iteration 18050/ 21553 | consumed samples: 4620800 | consumed tokens: 9463398400 | elapsed time per iteration (s): 0.31 | learning rate: 3.171E-05 | global batch size: 256 | lm loss: 2.948136E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.927 | TFLOPs: 28.98 | +7: iteration 18060/ 21553 | consumed samples: 4623360 | consumed tokens: 9468641280 | elapsed time per iteration (s): 0.30 | learning rate: 3.164E-05 | global batch size: 256 | lm loss: 2.967511E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.077 | TFLOPs: 29.48 | +7: iteration 18070/ 21553 | consumed samples: 4625920 | consumed tokens: 9473884160 | elapsed time per iteration (s): 0.32 | learning rate: 3.158E-05 | global batch size: 256 | lm loss: 2.943221E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.294 | TFLOPs: 28.44 | +7: iteration 18080/ 21553 | consumed samples: 4628480 | consumed tokens: 9479127040 | elapsed time per iteration (s): 0.31 | learning rate: 3.151E-05 | global batch size: 256 | lm loss: 2.941460E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.924 | TFLOPs: 29.33 | +7: iteration 18090/ 21553 | consumed samples: 4631040 | consumed tokens: 9484369920 | elapsed time per iteration (s): 0.31 | learning rate: 3.145E-05 | global batch size: 256 | lm loss: 2.971399E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.313 | TFLOPs: 29.10 | +7: iteration 18100/ 21553 | consumed samples: 4633600 | consumed tokens: 9489612800 | elapsed time per iteration (s): 0.32 | learning rate: 3.138E-05 | global batch size: 256 | lm loss: 2.918613E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.069 | TFLOPs: 28.29 | +7: iteration 18110/ 21553 | consumed samples: 4636160 | consumed tokens: 9494855680 | elapsed time per iteration (s): 0.31 | learning rate: 3.132E-05 | global batch size: 256 | lm loss: 2.953259E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.098 | TFLOPs: 29.20 | +7: iteration 18120/ 21553 | consumed samples: 4638720 | consumed tokens: 9500098560 | elapsed time per iteration (s): 0.31 | learning rate: 3.125E-05 | global batch size: 256 | lm loss: 2.953252E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.108 | TFLOPs: 29.27 | +7: iteration 18130/ 21553 | consumed samples: 4641280 | consumed tokens: 9505341440 | elapsed time per iteration (s): 0.30 | learning rate: 3.119E-05 | global batch size: 256 | lm loss: 2.978024E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.549 | TFLOPs: 29.43 | +7: iteration 18140/ 21553 | consumed samples: 4643840 | consumed tokens: 9510584320 | elapsed time per iteration (s): 0.31 | learning rate: 3.113E-05 | global batch size: 256 | lm loss: 2.933273E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.588 | TFLOPs: 28.76 | +7: iteration 18150/ 21553 | consumed samples: 4646400 | consumed tokens: 9515827200 | elapsed time per iteration (s): 0.31 | learning rate: 3.106E-05 | global batch size: 256 | lm loss: 2.940590E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.400 | TFLOPs: 28.68 | +7: iteration 18160/ 21553 | consumed samples: 4648960 | consumed tokens: 9521070080 | elapsed time per iteration (s): 0.31 | learning rate: 3.100E-05 | global batch size: 256 | lm loss: 2.951271E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.696 | TFLOPs: 29.01 | +7: iteration 18170/ 21553 | consumed samples: 4651520 | consumed tokens: 9526312960 | elapsed time per iteration (s): 0.32 | learning rate: 3.094E-05 | global batch size: 256 | lm loss: 2.961935E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 809.872 | TFLOPs: 28.35 | +7: iteration 18180/ 21553 | consumed samples: 4654080 | consumed tokens: 9531555840 | elapsed time per iteration (s): 0.31 | learning rate: 3.087E-05 | global batch size: 256 | lm loss: 2.960924E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.735 | TFLOPs: 29.26 | +7: iteration 18190/ 21553 | consumed samples: 4656640 | consumed tokens: 9536798720 | elapsed time per iteration (s): 0.31 | learning rate: 3.081E-05 | global batch size: 256 | lm loss: 2.962894E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.357 | TFLOPs: 28.79 | +7: iteration 18200/ 21553 | consumed samples: 4659200 | consumed tokens: 9542041600 | elapsed time per iteration (s): 0.31 | learning rate: 3.075E-05 | global batch size: 256 | lm loss: 2.951007E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.468 | TFLOPs: 28.65 | +7: iteration 18210/ 21553 | consumed samples: 4661760 | consumed tokens: 9547284480 | elapsed time per iteration (s): 0.31 | learning rate: 3.068E-05 | global batch size: 256 | lm loss: 2.970685E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.942 | TFLOPs: 29.05 | +7: iteration 18220/ 21553 | consumed samples: 4664320 | consumed tokens: 9552527360 | elapsed time per iteration (s): 0.31 | learning rate: 3.062E-05 | global batch size: 256 | lm loss: 2.965736E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.173 | TFLOPs: 28.78 | +7: iteration 18230/ 21553 | consumed samples: 4666880 | consumed tokens: 9557770240 | elapsed time per iteration (s): 0.31 | learning rate: 3.056E-05 | global batch size: 256 | lm loss: 2.961535E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.599 | TFLOPs: 29.25 | +7: iteration 18240/ 21553 | consumed samples: 4669440 | consumed tokens: 9563013120 | elapsed time per iteration (s): 0.31 | learning rate: 3.050E-05 | global batch size: 256 | lm loss: 2.967370E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.370 | TFLOPs: 28.89 | +7: iteration 18250/ 21553 | consumed samples: 4672000 | consumed tokens: 9568256000 | elapsed time per iteration (s): 0.31 | learning rate: 3.043E-05 | global batch size: 256 | lm loss: 2.946155E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.832 | TFLOPs: 29.33 | +7: iteration 18260/ 21553 | consumed samples: 4674560 | consumed tokens: 9573498880 | elapsed time per iteration (s): 0.30 | learning rate: 3.037E-05 | global batch size: 256 | lm loss: 2.986864E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.008 | TFLOPs: 29.58 | +7: iteration 18270/ 21553 | consumed samples: 4677120 | consumed tokens: 9578741760 | elapsed time per iteration (s): 0.32 | learning rate: 3.031E-05 | global batch size: 256 | lm loss: 2.968813E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.438 | TFLOPs: 28.41 | +7: iteration 18280/ 21553 | consumed samples: 4679680 | consumed tokens: 9583984640 | elapsed time per iteration (s): 0.31 | learning rate: 3.025E-05 | global batch size: 256 | lm loss: 2.967983E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.284 | TFLOPs: 29.00 | +7: iteration 18290/ 21553 | consumed samples: 4682240 | consumed tokens: 9589227520 | elapsed time per iteration (s): 0.31 | learning rate: 3.019E-05 | global batch size: 256 | lm loss: 2.969991E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.536 | TFLOPs: 29.25 | +7: iteration 18300/ 21553 | consumed samples: 4684800 | consumed tokens: 9594470400 | elapsed time per iteration (s): 0.32 | learning rate: 3.013E-05 | global batch size: 256 | lm loss: 2.962277E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 804.859 | TFLOPs: 28.18 | +7: iteration 18310/ 21553 | consumed samples: 4687360 | consumed tokens: 9599713280 | elapsed time per iteration (s): 0.31 | learning rate: 3.007E-05 | global batch size: 256 | lm loss: 2.935603E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.860 | TFLOPs: 29.05 | +7: iteration 18320/ 21553 | consumed samples: 4689920 | consumed tokens: 9604956160 | elapsed time per iteration (s): 0.32 | learning rate: 3.001E-05 | global batch size: 256 | lm loss: 2.959085E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 801.444 | TFLOPs: 28.06 | +7: iteration 18330/ 21553 | consumed samples: 4692480 | consumed tokens: 9610199040 | elapsed time per iteration (s): 0.31 | learning rate: 2.994E-05 | global batch size: 256 | lm loss: 2.944897E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.969 | TFLOPs: 28.53 | +7: iteration 18340/ 21553 | consumed samples: 4695040 | consumed tokens: 9615441920 | elapsed time per iteration (s): 0.32 | learning rate: 2.988E-05 | global batch size: 256 | lm loss: 2.941537E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.057 | TFLOPs: 28.43 | +7: iteration 18350/ 21553 | consumed samples: 4697600 | consumed tokens: 9620684800 | elapsed time per iteration (s): 0.31 | learning rate: 2.982E-05 | global batch size: 256 | lm loss: 2.958370E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.468 | TFLOPs: 29.32 | +7: iteration 18360/ 21553 | consumed samples: 4700160 | consumed tokens: 9625927680 | elapsed time per iteration (s): 0.31 | learning rate: 2.976E-05 | global batch size: 256 | lm loss: 2.978032E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.774 | TFLOPs: 29.12 | +7: iteration 18370/ 21553 | consumed samples: 4702720 | consumed tokens: 9631170560 | elapsed time per iteration (s): 0.31 | learning rate: 2.970E-05 | global batch size: 256 | lm loss: 2.958478E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.191 | TFLOPs: 28.96 | +7: iteration 18380/ 21553 | consumed samples: 4705280 | consumed tokens: 9636413440 | elapsed time per iteration (s): 0.31 | learning rate: 2.964E-05 | global batch size: 256 | lm loss: 2.948850E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.828 | TFLOPs: 29.33 | +7: iteration 18390/ 21553 | consumed samples: 4707840 | consumed tokens: 9641656320 | elapsed time per iteration (s): 0.31 | learning rate: 2.958E-05 | global batch size: 256 | lm loss: 2.936566E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.721 | TFLOPs: 28.77 | +7: iteration 18400/ 21553 | consumed samples: 4710400 | consumed tokens: 9646899200 | elapsed time per iteration (s): 0.31 | learning rate: 2.953E-05 | global batch size: 256 | lm loss: 2.936161E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.250 | TFLOPs: 29.03 | +7: iteration 18410/ 21553 | consumed samples: 4712960 | consumed tokens: 9652142080 | elapsed time per iteration (s): 0.31 | learning rate: 2.947E-05 | global batch size: 256 | lm loss: 2.978265E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.608 | TFLOPs: 29.08 | +7: iteration 18420/ 21553 | consumed samples: 4715520 | consumed tokens: 9657384960 | elapsed time per iteration (s): 0.30 | learning rate: 2.941E-05 | global batch size: 256 | lm loss: 2.949468E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.647 | TFLOPs: 29.39 | +7: iteration 18430/ 21553 | consumed samples: 4718080 | consumed tokens: 9662627840 | elapsed time per iteration (s): 0.30 | learning rate: 2.935E-05 | global batch size: 256 | lm loss: 2.961346E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.565 | TFLOPs: 29.39 | +7: iteration 18440/ 21553 | consumed samples: 4720640 | consumed tokens: 9667870720 | elapsed time per iteration (s): 0.31 | learning rate: 2.929E-05 | global batch size: 256 | lm loss: 2.968101E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.684 | TFLOPs: 29.25 | +7: iteration 18450/ 21553 | consumed samples: 4723200 | consumed tokens: 9673113600 | elapsed time per iteration (s): 0.31 | learning rate: 2.923E-05 | global batch size: 256 | lm loss: 2.954339E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.205 | TFLOPs: 28.61 | +7: iteration 18460/ 21553 | consumed samples: 4725760 | consumed tokens: 9678356480 | elapsed time per iteration (s): 0.31 | learning rate: 2.917E-05 | global batch size: 256 | lm loss: 2.955539E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.262 | TFLOPs: 28.89 | +7: iteration 18470/ 21553 | consumed samples: 4728320 | consumed tokens: 9683599360 | elapsed time per iteration (s): 0.32 | learning rate: 2.911E-05 | global batch size: 256 | lm loss: 2.924507E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 806.306 | TFLOPs: 28.23 | +7: iteration 18480/ 21553 | consumed samples: 4730880 | consumed tokens: 9688842240 | elapsed time per iteration (s): 0.32 | learning rate: 2.906E-05 | global batch size: 256 | lm loss: 2.948721E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 790.064 | TFLOPs: 27.66 | +7: iteration 18490/ 21553 | consumed samples: 4733440 | consumed tokens: 9694085120 | elapsed time per iteration (s): 0.31 | learning rate: 2.900E-05 | global batch size: 256 | lm loss: 2.962306E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.964 | TFLOPs: 29.02 | +7: iteration 18500/ 21553 | consumed samples: 4736000 | consumed tokens: 9699328000 | elapsed time per iteration (s): 0.31 | learning rate: 2.894E-05 | global batch size: 256 | lm loss: 2.970951E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.451 | TFLOPs: 29.14 | +7: iteration 18510/ 21553 | consumed samples: 4738560 | consumed tokens: 9704570880 | elapsed time per iteration (s): 0.31 | learning rate: 2.888E-05 | global batch size: 256 | lm loss: 2.961175E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.002 | TFLOPs: 29.34 | +7: iteration 18520/ 21553 | consumed samples: 4741120 | consumed tokens: 9709813760 | elapsed time per iteration (s): 0.30 | learning rate: 2.883E-05 | global batch size: 256 | lm loss: 2.957193E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 844.391 | TFLOPs: 29.56 | +7: iteration 18530/ 21553 | consumed samples: 4743680 | consumed tokens: 9715056640 | elapsed time per iteration (s): 0.32 | learning rate: 2.877E-05 | global batch size: 256 | lm loss: 2.967897E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.562 | TFLOPs: 28.31 | +7: iteration 18540/ 21553 | consumed samples: 4746240 | consumed tokens: 9720299520 | elapsed time per iteration (s): 0.32 | learning rate: 2.871E-05 | global batch size: 256 | lm loss: 2.975806E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.537 | TFLOPs: 28.30 | +7: iteration 18550/ 21553 | consumed samples: 4748800 | consumed tokens: 9725542400 | elapsed time per iteration (s): 0.31 | learning rate: 2.865E-05 | global batch size: 256 | lm loss: 2.931728E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.652 | TFLOPs: 29.18 | +7: iteration 18560/ 21553 | consumed samples: 4751360 | consumed tokens: 9730785280 | elapsed time per iteration (s): 0.31 | learning rate: 2.860E-05 | global batch size: 256 | lm loss: 2.962384E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.619 | TFLOPs: 29.25 | +7: iteration 18570/ 21553 | consumed samples: 4753920 | consumed tokens: 9736028160 | elapsed time per iteration (s): 0.31 | learning rate: 2.854E-05 | global batch size: 256 | lm loss: 2.956150E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.845 | TFLOPs: 29.26 | +7: iteration 18580/ 21553 | consumed samples: 4756480 | consumed tokens: 9741271040 | elapsed time per iteration (s): 0.31 | learning rate: 2.849E-05 | global batch size: 256 | lm loss: 2.951876E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.440 | TFLOPs: 28.76 | +7: iteration 18590/ 21553 | consumed samples: 4759040 | consumed tokens: 9746513920 | elapsed time per iteration (s): 0.30 | learning rate: 2.843E-05 | global batch size: 256 | lm loss: 2.930751E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 844.186 | TFLOPs: 29.55 | +7: iteration 18600/ 21553 | consumed samples: 4761600 | consumed tokens: 9751756800 | elapsed time per iteration (s): 0.31 | learning rate: 2.837E-05 | global batch size: 256 | lm loss: 2.961595E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.984 | TFLOPs: 28.64 | +7: iteration 18610/ 21553 | consumed samples: 4764160 | consumed tokens: 9756999680 | elapsed time per iteration (s): 0.31 | learning rate: 2.832E-05 | global batch size: 256 | lm loss: 2.986005E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.359 | TFLOPs: 29.10 | +7: iteration 18620/ 21553 | consumed samples: 4766720 | consumed tokens: 9762242560 | elapsed time per iteration (s): 0.31 | learning rate: 2.826E-05 | global batch size: 256 | lm loss: 2.930490E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.186 | TFLOPs: 28.85 | +7: iteration 18630/ 21553 | consumed samples: 4769280 | consumed tokens: 9767485440 | elapsed time per iteration (s): 0.31 | learning rate: 2.821E-05 | global batch size: 256 | lm loss: 2.984965E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.036 | TFLOPs: 29.16 | +7: iteration 18640/ 21553 | consumed samples: 4771840 | consumed tokens: 9772728320 | elapsed time per iteration (s): 0.32 | learning rate: 2.815E-05 | global batch size: 256 | lm loss: 2.979626E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 802.731 | TFLOPs: 28.10 | +7: iteration 18650/ 21553 | consumed samples: 4774400 | consumed tokens: 9777971200 | elapsed time per iteration (s): 0.31 | learning rate: 2.810E-05 | global batch size: 256 | lm loss: 2.940811E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.043 | TFLOPs: 28.99 | +7: iteration 18660/ 21553 | consumed samples: 4776960 | consumed tokens: 9783214080 | elapsed time per iteration (s): 0.31 | learning rate: 2.804E-05 | global batch size: 256 | lm loss: 2.971936E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.220 | TFLOPs: 28.82 | +7: iteration 18670/ 21553 | consumed samples: 4779520 | consumed tokens: 9788456960 | elapsed time per iteration (s): 0.31 | learning rate: 2.799E-05 | global batch size: 256 | lm loss: 2.942049E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.216 | TFLOPs: 28.71 | +7: iteration 18680/ 21553 | consumed samples: 4782080 | consumed tokens: 9793699840 | elapsed time per iteration (s): 0.31 | learning rate: 2.793E-05 | global batch size: 256 | lm loss: 2.922819E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.036 | TFLOPs: 29.27 | +7: iteration 18690/ 21553 | consumed samples: 4784640 | consumed tokens: 9798942720 | elapsed time per iteration (s): 0.31 | learning rate: 2.788E-05 | global batch size: 256 | lm loss: 2.940678E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.207 | TFLOPs: 29.24 | +7: iteration 18700/ 21553 | consumed samples: 4787200 | consumed tokens: 9804185600 | elapsed time per iteration (s): 0.31 | learning rate: 2.782E-05 | global batch size: 256 | lm loss: 2.946491E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.997 | TFLOPs: 29.09 | +7: iteration 18710/ 21553 | consumed samples: 4789760 | consumed tokens: 9809428480 | elapsed time per iteration (s): 0.30 | learning rate: 2.777E-05 | global batch size: 256 | lm loss: 2.951133E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 844.267 | TFLOPs: 29.56 | +7: iteration 18720/ 21553 | consumed samples: 4792320 | consumed tokens: 9814671360 | elapsed time per iteration (s): 0.31 | learning rate: 2.772E-05 | global batch size: 256 | lm loss: 2.942008E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.464 | TFLOPs: 29.28 | +7: iteration 18730/ 21553 | consumed samples: 4794880 | consumed tokens: 9819914240 | elapsed time per iteration (s): 0.31 | learning rate: 2.766E-05 | global batch size: 256 | lm loss: 2.937740E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.354 | TFLOPs: 28.51 | +7: iteration 18740/ 21553 | consumed samples: 4797440 | consumed tokens: 9825157120 | elapsed time per iteration (s): 0.31 | learning rate: 2.761E-05 | global batch size: 256 | lm loss: 2.939099E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.426 | TFLOPs: 29.18 | +7: iteration 18750/ 21553 | consumed samples: 4800000 | consumed tokens: 9830400000 | elapsed time per iteration (s): 0.31 | learning rate: 2.756E-05 | global batch size: 256 | lm loss: 2.958028E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.233 | TFLOPs: 29.10 | +7: iteration 18760/ 21553 | consumed samples: 4802560 | consumed tokens: 9835642880 | elapsed time per iteration (s): 0.31 | learning rate: 2.750E-05 | global batch size: 256 | lm loss: 2.927198E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.933 | TFLOPs: 28.95 | +7: iteration 18770/ 21553 | consumed samples: 4805120 | consumed tokens: 9840885760 | elapsed time per iteration (s): 0.31 | learning rate: 2.745E-05 | global batch size: 256 | lm loss: 2.957333E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.014 | TFLOPs: 28.92 | +7: iteration 18780/ 21553 | consumed samples: 4807680 | consumed tokens: 9846128640 | elapsed time per iteration (s): 0.31 | learning rate: 2.740E-05 | global batch size: 256 | lm loss: 2.943513E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.472 | TFLOPs: 29.11 | +7: iteration 18790/ 21553 | consumed samples: 4810240 | consumed tokens: 9851371520 | elapsed time per iteration (s): 0.31 | learning rate: 2.735E-05 | global batch size: 256 | lm loss: 2.948679E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.051 | TFLOPs: 29.09 | +7: iteration 18800/ 21553 | consumed samples: 4812800 | consumed tokens: 9856614400 | elapsed time per iteration (s): 0.31 | learning rate: 2.729E-05 | global batch size: 256 | lm loss: 2.957705E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.342 | TFLOPs: 29.14 | +7: iteration 18810/ 21553 | consumed samples: 4815360 | consumed tokens: 9861857280 | elapsed time per iteration (s): 0.33 | learning rate: 2.724E-05 | global batch size: 256 | lm loss: 2.959110E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 778.973 | TFLOPs: 27.27 | +7: iteration 18820/ 21553 | consumed samples: 4817920 | consumed tokens: 9867100160 | elapsed time per iteration (s): 0.32 | learning rate: 2.719E-05 | global batch size: 256 | lm loss: 2.964805E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.173 | TFLOPs: 28.43 | +7: iteration 18830/ 21553 | consumed samples: 4820480 | consumed tokens: 9872343040 | elapsed time per iteration (s): 0.31 | learning rate: 2.714E-05 | global batch size: 256 | lm loss: 2.944445E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.425 | TFLOPs: 28.58 | +7: iteration 18840/ 21553 | consumed samples: 4823040 | consumed tokens: 9877585920 | elapsed time per iteration (s): 0.31 | learning rate: 2.709E-05 | global batch size: 256 | lm loss: 2.914423E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.600 | TFLOPs: 28.83 | +7: iteration 18850/ 21553 | consumed samples: 4825600 | consumed tokens: 9882828800 | elapsed time per iteration (s): 0.31 | learning rate: 2.703E-05 | global batch size: 256 | lm loss: 2.938250E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.463 | TFLOPs: 28.69 | +7: iteration 18860/ 21553 | consumed samples: 4828160 | consumed tokens: 9888071680 | elapsed time per iteration (s): 0.31 | learning rate: 2.698E-05 | global batch size: 256 | lm loss: 2.947646E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.862 | TFLOPs: 29.05 | +7: iteration 18870/ 21553 | consumed samples: 4830720 | consumed tokens: 9893314560 | elapsed time per iteration (s): 0.31 | learning rate: 2.693E-05 | global batch size: 256 | lm loss: 2.963792E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.546 | TFLOPs: 29.01 | +7: iteration 18880/ 21553 | consumed samples: 4833280 | consumed tokens: 9898557440 | elapsed time per iteration (s): 0.31 | learning rate: 2.688E-05 | global batch size: 256 | lm loss: 2.936095E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.197 | TFLOPs: 28.64 | +7: iteration 18890/ 21553 | consumed samples: 4835840 | consumed tokens: 9903800320 | elapsed time per iteration (s): 0.30 | learning rate: 2.683E-05 | global batch size: 256 | lm loss: 2.962398E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.012 | TFLOPs: 29.44 | +7: iteration 18900/ 21553 | consumed samples: 4838400 | consumed tokens: 9909043200 | elapsed time per iteration (s): 0.31 | learning rate: 2.678E-05 | global batch size: 256 | lm loss: 2.947957E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.264 | TFLOPs: 29.21 | +7: iteration 18910/ 21553 | consumed samples: 4840960 | consumed tokens: 9914286080 | elapsed time per iteration (s): 0.31 | learning rate: 2.673E-05 | global batch size: 256 | lm loss: 2.940218E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.211 | TFLOPs: 28.99 | +7: iteration 18920/ 21553 | consumed samples: 4843520 | consumed tokens: 9919528960 | elapsed time per iteration (s): 0.31 | learning rate: 2.668E-05 | global batch size: 256 | lm loss: 2.949860E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.525 | TFLOPs: 29.28 | +7: iteration 18930/ 21553 | consumed samples: 4846080 | consumed tokens: 9924771840 | elapsed time per iteration (s): 0.31 | learning rate: 2.663E-05 | global batch size: 256 | lm loss: 2.958850E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.316 | TFLOPs: 28.86 | +7: iteration 18940/ 21553 | consumed samples: 4848640 | consumed tokens: 9930014720 | elapsed time per iteration (s): 0.31 | learning rate: 2.658E-05 | global batch size: 256 | lm loss: 2.970624E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.375 | TFLOPs: 29.24 | +7: iteration 18950/ 21553 | consumed samples: 4851200 | consumed tokens: 9935257600 | elapsed time per iteration (s): 0.33 | learning rate: 2.653E-05 | global batch size: 256 | lm loss: 2.964270E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 773.455 | TFLOPs: 27.08 | +7: iteration 18960/ 21553 | consumed samples: 4853760 | consumed tokens: 9940500480 | elapsed time per iteration (s): 0.31 | learning rate: 2.648E-05 | global batch size: 256 | lm loss: 2.939311E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.896 | TFLOPs: 28.53 | +7: iteration 18970/ 21553 | consumed samples: 4856320 | consumed tokens: 9945743360 | elapsed time per iteration (s): 0.31 | learning rate: 2.643E-05 | global batch size: 256 | lm loss: 2.997460E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.161 | TFLOPs: 28.82 | +7: iteration 18980/ 21553 | consumed samples: 4858880 | consumed tokens: 9950986240 | elapsed time per iteration (s): 0.31 | learning rate: 2.638E-05 | global batch size: 256 | lm loss: 2.973968E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.943 | TFLOPs: 29.23 | +7: iteration 18990/ 21553 | consumed samples: 4861440 | consumed tokens: 9956229120 | elapsed time per iteration (s): 0.31 | learning rate: 2.633E-05 | global batch size: 256 | lm loss: 2.977981E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.824 | TFLOPs: 29.05 | +7: iteration 19000/ 21553 | consumed samples: 4864000 | consumed tokens: 9961472000 | elapsed time per iteration (s): 0.31 | learning rate: 2.628E-05 | global batch size: 256 | lm loss: 2.946991E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.566 | TFLOPs: 29.08 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 19000 | lm loss value: 2.929189E+00 | lm loss PPL: 1.871245E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 19000 to checkpoints_146moscareap +0: [2022-11-29 18:46:37,405] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step19000 is begin to save! +0: [2022-11-29 18:46:37,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:46:37,504] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:46:37,505] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:46:37,522] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:46:37,522] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:46:37,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:46:37,538] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:46:37,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:46:37,555] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:46:37,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:46:37,572] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:46:37,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:46:37,588] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:46:37,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:46:37,604] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:46:37,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:46:37,621] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:46:37,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:46:37,638] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:46:37,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:46:37,654] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:46:37,670] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:46:37,671] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/layer_13-model_00-model_states.pt... +0: [2022-11-29 18:46:37,687] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/layer_13-model_00-model_states.pt. +0: [2022-11-29 18:46:37,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:46:37,703] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:46:37,704] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/layer_15-model_00-model_states.pt... +0: [2022-11-29 18:46:37,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/layer_15-model_00-model_states.pt. +0: [2022-11-29 18:46:37,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/layer_16-model_00-model_states.pt... +0: [2022-11-29 18:46:37,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/layer_16-model_00-model_states.pt. +0: [2022-11-29 18:46:37,736] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/layer_17-model_00-model_states.pt... +0: [2022-11-29 18:46:37,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/layer_17-model_00-model_states.pt. +0: [2022-11-29 18:46:37,753] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/layer_19-model_00-model_states.pt... +0: [2022-11-29 18:46:37,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/layer_19-model_00-model_states.pt. +0: [2022-11-29 18:46:37,755] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_146moscareap/global_step19000/mp_rank_00_model_states.pt +0: [2022-11-29 18:46:37,755] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:46:37,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:46:37,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:46:37,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:46:37,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:46:37,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +3: [2022-11-29 18:46:37,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:46:37,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:46:37,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +3: [2022-11-29 18:46:37,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:46:37,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:46:37,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +0: [2022-11-29 18:46:37,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:46:37,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:46:37,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +2: [2022-11-29 18:46:37,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:46:37,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +3: [2022-11-29 18:46:37,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +2: [2022-11-29 18:46:37,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +3: [2022-11-29 18:46:37,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:46:37,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:46:37,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +2: [2022-11-29 18:46:37,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:46:37,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:46:37,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +3: [2022-11-29 18:46:37,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:46:37,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:46:37,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +2: [2022-11-29 18:46:37,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:46:37,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:46:37,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +0: [2022-11-29 18:46:37,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:46:37,812] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:46:37,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:46:37,812] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +0: [2022-11-29 18:46:37,812] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:46:37,812] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +2: [2022-11-29 18:46:37,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:46:37,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:46:37,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +2: [2022-11-29 18:46:37,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:46:37,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:46:37,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +3: [2022-11-29 18:46:37,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +2: [2022-11-29 18:46:37,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +3: [2022-11-29 18:46:37,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +3: [2022-11-29 18:46:37,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:46:37,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:46:37,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +2: [2022-11-29 18:46:37,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:46:37,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:46:37,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +0: [2022-11-29 18:46:37,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:46:37,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:46:37,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +3: [2022-11-29 18:46:37,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:46:37,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:46:37,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +5: [2022-11-29 18:46:37,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:46:37,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:46:37,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +6: [2022-11-29 18:46:37,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:46:37,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:46:37,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +4: [2022-11-29 18:46:37,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:46:37,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:46:37,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +4: [2022-11-29 18:46:37,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:46:37,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:46:37,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:46:37,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:46:37,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:46:37,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +6: [2022-11-29 18:46:37,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:46:37,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:46:37,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +6: [2022-11-29 18:46:37,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +5: [2022-11-29 18:46:37,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:46:37,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:46:37,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +5: [2022-11-29 18:46:37,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:46:37,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +4: [2022-11-29 18:46:37,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +5: [2022-11-29 18:46:37,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +4: [2022-11-29 18:46:37,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +4: [2022-11-29 18:46:37,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:46:37,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:46:37,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +5: [2022-11-29 18:46:37,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:46:37,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +0: [2022-11-29 18:46:37,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:46:37,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +0: [2022-11-29 18:46:37,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:46:37,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +4: [2022-11-29 18:46:37,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:46:37,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:46:37,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:46:37,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:46:37,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:46:37,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:46:37,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +4: [2022-11-29 18:46:37,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +0: [2022-11-29 18:46:37,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +0: [2022-11-29 18:46:37,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +0: [2022-11-29 18:46:37,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +4: [2022-11-29 18:46:37,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +6: [2022-11-29 18:46:37,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:46:37,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:46:37,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +6: [2022-11-29 18:46:37,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:46:37,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:46:37,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +2: [2022-11-29 18:46:37,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:46:37,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:46:37,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +4: [2022-11-29 18:46:37,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:46:37,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:46:37,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:46:37,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:46:37,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:46:37,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:46:37,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +6: [2022-11-29 18:46:37,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +4: [2022-11-29 18:46:37,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +4: [2022-11-29 18:46:37,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +6: [2022-11-29 18:46:37,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +4: [2022-11-29 18:46:37,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +4: [2022-11-29 18:46:37,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:46:37,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +6: [2022-11-29 18:46:37,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:46:37,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +6: [2022-11-29 18:46:37,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:46:37,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +7: [2022-11-29 18:46:37,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:46:37,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:46:37,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:46:37,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:46:37,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:46:37,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +7: [2022-11-29 18:46:37,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:46:37,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:46:37,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +7: [2022-11-29 18:46:37,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +7: [2022-11-29 18:46:37,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:46:37,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +7: [2022-11-29 18:46:37,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:46:37,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:46:37,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:46:37,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:46:37,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:46:37,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:46:37,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:46:37,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +7: [2022-11-29 18:46:37,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +7: [2022-11-29 18:46:37,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +7: [2022-11-29 18:46:37,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:46:37,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +1: [2022-11-29 18:46:37,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:46:37,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:46:37,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +5: [2022-11-29 18:46:37,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:46:37,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:46:37,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:46:37,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:46:37,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +5: [2022-11-29 18:46:37,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +1: [2022-11-29 18:46:37,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:46:37,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:46:37,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:46:37,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:46:37,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:46:37,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:46:37,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +5: [2022-11-29 18:46:37,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:46:37,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +1: [2022-11-29 18:46:37,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +5: [2022-11-29 18:46:37,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:46:37,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:46:37,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:46:37,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +5: [2022-11-29 18:46:37,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +1: [2022-11-29 18:46:37,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:46:37,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:46:37,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:46:37,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:46:37,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:46:37,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +1: [2022-11-29 18:46:37,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:46:37,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +1: [2022-11-29 18:46:37,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:46:37,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:46:37,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +1: [2022-11-29 18:46:37,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +0: [2022-11-29 18:46:37,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step19000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:46:37,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +0: successfully saved checkpoint at iteration 19000 to checkpoints_146moscareap +7: time (ms) | save-checkpoint: 444.10 +7: iteration 19010/ 21553 | consumed samples: 4866560 | consumed tokens: 9966714880 | elapsed time per iteration (s): 0.36 | learning rate: 2.624E-05 | global batch size: 256 | lm loss: 2.933759E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 714.869 | TFLOPs: 25.03 | +7: iteration 19020/ 21553 | consumed samples: 4869120 | consumed tokens: 9971957760 | elapsed time per iteration (s): 0.31 | learning rate: 2.619E-05 | global batch size: 256 | lm loss: 2.955640E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.108 | TFLOPs: 29.37 | +7: iteration 19030/ 21553 | consumed samples: 4871680 | consumed tokens: 9977200640 | elapsed time per iteration (s): 0.31 | learning rate: 2.614E-05 | global batch size: 256 | lm loss: 2.964226E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 814.438 | TFLOPs: 28.51 | +7: iteration 19040/ 21553 | consumed samples: 4874240 | consumed tokens: 9982443520 | elapsed time per iteration (s): 0.31 | learning rate: 2.609E-05 | global batch size: 256 | lm loss: 2.935629E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.736 | TFLOPs: 29.36 | +7: iteration 19050/ 21553 | consumed samples: 4876800 | consumed tokens: 9987686400 | elapsed time per iteration (s): 0.30 | learning rate: 2.604E-05 | global batch size: 256 | lm loss: 2.930621E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.298 | TFLOPs: 29.59 | +7: iteration 19060/ 21553 | consumed samples: 4879360 | consumed tokens: 9992929280 | elapsed time per iteration (s): 0.31 | learning rate: 2.600E-05 | global batch size: 256 | lm loss: 2.950077E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.808 | TFLOPs: 28.94 | +7: iteration 19070/ 21553 | consumed samples: 4881920 | consumed tokens: 9998172160 | elapsed time per iteration (s): 0.31 | learning rate: 2.595E-05 | global batch size: 256 | lm loss: 2.975562E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.095 | TFLOPs: 28.71 | +7: iteration 19080/ 21553 | consumed samples: 4884480 | consumed tokens: 10003415040 | elapsed time per iteration (s): 0.31 | learning rate: 2.590E-05 | global batch size: 256 | lm loss: 2.959605E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.298 | TFLOPs: 28.86 | +7: iteration 19090/ 21553 | consumed samples: 4887040 | consumed tokens: 10008657920 | elapsed time per iteration (s): 0.30 | learning rate: 2.585E-05 | global batch size: 256 | lm loss: 2.958516E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 844.517 | TFLOPs: 29.56 | +7: iteration 19100/ 21553 | consumed samples: 4889600 | consumed tokens: 10013900800 | elapsed time per iteration (s): 0.31 | learning rate: 2.581E-05 | global batch size: 256 | lm loss: 2.953547E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.205 | TFLOPs: 28.47 | +7: iteration 19110/ 21553 | consumed samples: 4892160 | consumed tokens: 10019143680 | elapsed time per iteration (s): 0.31 | learning rate: 2.576E-05 | global batch size: 256 | lm loss: 2.976519E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.402 | TFLOPs: 29.04 | +7: iteration 19120/ 21553 | consumed samples: 4894720 | consumed tokens: 10024386560 | elapsed time per iteration (s): 0.32 | learning rate: 2.571E-05 | global batch size: 256 | lm loss: 2.946388E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 804.613 | TFLOPs: 28.17 | +7: iteration 19130/ 21553 | consumed samples: 4897280 | consumed tokens: 10029629440 | elapsed time per iteration (s): 0.31 | learning rate: 2.567E-05 | global batch size: 256 | lm loss: 2.955418E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.339 | TFLOPs: 28.58 | +7: iteration 19140/ 21553 | consumed samples: 4899840 | consumed tokens: 10034872320 | elapsed time per iteration (s): 0.31 | learning rate: 2.562E-05 | global batch size: 256 | lm loss: 2.978316E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.471 | TFLOPs: 29.32 | +7: iteration 19150/ 21553 | consumed samples: 4902400 | consumed tokens: 10040115200 | elapsed time per iteration (s): 0.30 | learning rate: 2.557E-05 | global batch size: 256 | lm loss: 2.923952E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 847.833 | TFLOPs: 29.68 | +7: iteration 19160/ 21553 | consumed samples: 4904960 | consumed tokens: 10045358080 | elapsed time per iteration (s): 0.31 | learning rate: 2.553E-05 | global batch size: 256 | lm loss: 2.944746E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.048 | TFLOPs: 29.13 | +7: iteration 19170/ 21553 | consumed samples: 4907520 | consumed tokens: 10050600960 | elapsed time per iteration (s): 0.31 | learning rate: 2.548E-05 | global batch size: 256 | lm loss: 2.944592E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.355 | TFLOPs: 28.68 | +7: iteration 19180/ 21553 | consumed samples: 4910080 | consumed tokens: 10055843840 | elapsed time per iteration (s): 0.31 | learning rate: 2.544E-05 | global batch size: 256 | lm loss: 2.976893E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.126 | TFLOPs: 28.99 | +7: iteration 19190/ 21553 | consumed samples: 4912640 | consumed tokens: 10061086720 | elapsed time per iteration (s): 0.31 | learning rate: 2.539E-05 | global batch size: 256 | lm loss: 2.946095E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.568 | TFLOPs: 29.11 | +7: iteration 19200/ 21553 | consumed samples: 4915200 | consumed tokens: 10066329600 | elapsed time per iteration (s): 0.30 | learning rate: 2.535E-05 | global batch size: 256 | lm loss: 2.964862E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 844.599 | TFLOPs: 29.57 | +7: iteration 19210/ 21553 | consumed samples: 4917760 | consumed tokens: 10071572480 | elapsed time per iteration (s): 0.30 | learning rate: 2.530E-05 | global batch size: 256 | lm loss: 2.955547E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.130 | TFLOPs: 29.59 | +7: iteration 19220/ 21553 | consumed samples: 4920320 | consumed tokens: 10076815360 | elapsed time per iteration (s): 0.30 | learning rate: 2.526E-05 | global batch size: 256 | lm loss: 2.960815E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 847.293 | TFLOPs: 29.66 | +7: iteration 19230/ 21553 | consumed samples: 4922880 | consumed tokens: 10082058240 | elapsed time per iteration (s): 0.30 | learning rate: 2.521E-05 | global batch size: 256 | lm loss: 2.924614E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.334 | TFLOPs: 29.59 | +7: iteration 19240/ 21553 | consumed samples: 4925440 | consumed tokens: 10087301120 | elapsed time per iteration (s): 0.31 | learning rate: 2.517E-05 | global batch size: 256 | lm loss: 2.946351E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.143 | TFLOPs: 29.13 | +7: iteration 19250/ 21553 | consumed samples: 4928000 | consumed tokens: 10092544000 | elapsed time per iteration (s): 0.31 | learning rate: 2.512E-05 | global batch size: 256 | lm loss: 2.946926E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.628 | TFLOPs: 28.90 | +7: iteration 19260/ 21553 | consumed samples: 4930560 | consumed tokens: 10097786880 | elapsed time per iteration (s): 0.30 | learning rate: 2.508E-05 | global batch size: 256 | lm loss: 2.944497E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 847.520 | TFLOPs: 29.67 | +7: iteration 19270/ 21553 | consumed samples: 4933120 | consumed tokens: 10103029760 | elapsed time per iteration (s): 0.31 | learning rate: 2.504E-05 | global batch size: 256 | lm loss: 2.950224E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.153 | TFLOPs: 29.10 | +7: iteration 19280/ 21553 | consumed samples: 4935680 | consumed tokens: 10108272640 | elapsed time per iteration (s): 0.31 | learning rate: 2.499E-05 | global batch size: 256 | lm loss: 2.964277E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.144 | TFLOPs: 28.85 | +7: iteration 19290/ 21553 | consumed samples: 4938240 | consumed tokens: 10113515520 | elapsed time per iteration (s): 0.32 | learning rate: 2.495E-05 | global batch size: 256 | lm loss: 2.959531E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 789.176 | TFLOPs: 27.63 | +7: iteration 19300/ 21553 | consumed samples: 4940800 | consumed tokens: 10118758400 | elapsed time per iteration (s): 0.31 | learning rate: 2.491E-05 | global batch size: 256 | lm loss: 2.947057E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.544 | TFLOPs: 29.25 | +7: iteration 19310/ 21553 | consumed samples: 4943360 | consumed tokens: 10124001280 | elapsed time per iteration (s): 0.31 | learning rate: 2.486E-05 | global batch size: 256 | lm loss: 2.922150E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.634 | TFLOPs: 29.04 | +7: iteration 19320/ 21553 | consumed samples: 4945920 | consumed tokens: 10129244160 | elapsed time per iteration (s): 0.31 | learning rate: 2.482E-05 | global batch size: 256 | lm loss: 2.961032E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.556 | TFLOPs: 29.04 | +7: iteration 19330/ 21553 | consumed samples: 4948480 | consumed tokens: 10134487040 | elapsed time per iteration (s): 0.31 | learning rate: 2.478E-05 | global batch size: 256 | lm loss: 2.951029E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.771 | TFLOPs: 29.22 | +7: iteration 19340/ 21553 | consumed samples: 4951040 | consumed tokens: 10139729920 | elapsed time per iteration (s): 0.30 | learning rate: 2.474E-05 | global batch size: 256 | lm loss: 2.955070E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 848.577 | TFLOPs: 29.71 | +7: iteration 19350/ 21553 | consumed samples: 4953600 | consumed tokens: 10144972800 | elapsed time per iteration (s): 0.30 | learning rate: 2.469E-05 | global batch size: 256 | lm loss: 2.955597E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.470 | TFLOPs: 29.42 | +7: iteration 19360/ 21553 | consumed samples: 4956160 | consumed tokens: 10150215680 | elapsed time per iteration (s): 0.30 | learning rate: 2.465E-05 | global batch size: 256 | lm loss: 2.955637E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.499 | TFLOPs: 29.46 | +7: iteration 19370/ 21553 | consumed samples: 4958720 | consumed tokens: 10155458560 | elapsed time per iteration (s): 0.31 | learning rate: 2.461E-05 | global batch size: 256 | lm loss: 2.934313E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.511 | TFLOPs: 28.93 | +7: iteration 19380/ 21553 | consumed samples: 4961280 | consumed tokens: 10160701440 | elapsed time per iteration (s): 0.31 | learning rate: 2.457E-05 | global batch size: 256 | lm loss: 2.978202E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.904 | TFLOPs: 29.26 | +7: iteration 19390/ 21553 | consumed samples: 4963840 | consumed tokens: 10165944320 | elapsed time per iteration (s): 0.31 | learning rate: 2.453E-05 | global batch size: 256 | lm loss: 2.954178E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.891 | TFLOPs: 28.67 | +7: iteration 19400/ 21553 | consumed samples: 4966400 | consumed tokens: 10171187200 | elapsed time per iteration (s): 0.31 | learning rate: 2.448E-05 | global batch size: 256 | lm loss: 2.945183E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.906 | TFLOPs: 29.33 | +7: iteration 19410/ 21553 | consumed samples: 4968960 | consumed tokens: 10176430080 | elapsed time per iteration (s): 0.31 | learning rate: 2.444E-05 | global batch size: 256 | lm loss: 2.952820E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.939 | TFLOPs: 28.74 | +7: iteration 19420/ 21553 | consumed samples: 4971520 | consumed tokens: 10181672960 | elapsed time per iteration (s): 0.31 | learning rate: 2.440E-05 | global batch size: 256 | lm loss: 2.970119E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.424 | TFLOPs: 28.97 | +7: iteration 19430/ 21553 | consumed samples: 4974080 | consumed tokens: 10186915840 | elapsed time per iteration (s): 0.30 | learning rate: 2.436E-05 | global batch size: 256 | lm loss: 2.948340E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.504 | TFLOPs: 29.53 | +7: iteration 19440/ 21553 | consumed samples: 4976640 | consumed tokens: 10192158720 | elapsed time per iteration (s): 0.31 | learning rate: 2.432E-05 | global batch size: 256 | lm loss: 2.924898E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.716 | TFLOPs: 29.22 | +7: iteration 19450/ 21553 | consumed samples: 4979200 | consumed tokens: 10197401600 | elapsed time per iteration (s): 0.31 | learning rate: 2.428E-05 | global batch size: 256 | lm loss: 2.928917E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.446 | TFLOPs: 28.65 | +7: iteration 19460/ 21553 | consumed samples: 4981760 | consumed tokens: 10202644480 | elapsed time per iteration (s): 0.31 | learning rate: 2.424E-05 | global batch size: 256 | lm loss: 2.928970E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 813.924 | TFLOPs: 28.49 | +7: iteration 19470/ 21553 | consumed samples: 4984320 | consumed tokens: 10207887360 | elapsed time per iteration (s): 0.31 | learning rate: 2.420E-05 | global batch size: 256 | lm loss: 2.942280E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.955 | TFLOPs: 28.77 | +7: iteration 19480/ 21553 | consumed samples: 4986880 | consumed tokens: 10213130240 | elapsed time per iteration (s): 0.31 | learning rate: 2.416E-05 | global batch size: 256 | lm loss: 2.947348E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.370 | TFLOPs: 29.07 | +7: iteration 19490/ 21553 | consumed samples: 4989440 | consumed tokens: 10218373120 | elapsed time per iteration (s): 0.30 | learning rate: 2.412E-05 | global batch size: 256 | lm loss: 2.932096E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.159 | TFLOPs: 29.52 | +7: iteration 19500/ 21553 | consumed samples: 4992000 | consumed tokens: 10223616000 | elapsed time per iteration (s): 0.30 | learning rate: 2.408E-05 | global batch size: 256 | lm loss: 2.928556E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.745 | TFLOPs: 29.54 | +7: iteration 19510/ 21553 | consumed samples: 4994560 | consumed tokens: 10228858880 | elapsed time per iteration (s): 0.30 | learning rate: 2.404E-05 | global batch size: 256 | lm loss: 2.929047E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.646 | TFLOPs: 29.53 | +7: iteration 19520/ 21553 | consumed samples: 4997120 | consumed tokens: 10234101760 | elapsed time per iteration (s): 0.31 | learning rate: 2.400E-05 | global batch size: 256 | lm loss: 2.966823E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.107 | TFLOPs: 28.99 | +7: iteration 19530/ 21553 | consumed samples: 4999680 | consumed tokens: 10239344640 | elapsed time per iteration (s): 0.30 | learning rate: 2.396E-05 | global batch size: 256 | lm loss: 2.949743E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 846.199 | TFLOPs: 29.62 | +7: iteration 19540/ 21553 | consumed samples: 5002240 | consumed tokens: 10244587520 | elapsed time per iteration (s): 0.31 | learning rate: 2.392E-05 | global batch size: 256 | lm loss: 2.935262E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 817.665 | TFLOPs: 28.62 | +7: iteration 19550/ 21553 | consumed samples: 5004800 | consumed tokens: 10249830400 | elapsed time per iteration (s): 0.31 | learning rate: 2.389E-05 | global batch size: 256 | lm loss: 2.966323E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.238 | TFLOPs: 29.24 | +7: iteration 19560/ 21553 | consumed samples: 5007360 | consumed tokens: 10255073280 | elapsed time per iteration (s): 0.31 | learning rate: 2.385E-05 | global batch size: 256 | lm loss: 2.963702E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.043 | TFLOPs: 29.06 | +7: iteration 19570/ 21553 | consumed samples: 5009920 | consumed tokens: 10260316160 | elapsed time per iteration (s): 0.30 | learning rate: 2.381E-05 | global batch size: 256 | lm loss: 2.915695E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.374 | TFLOPs: 29.45 | +7: iteration 19580/ 21553 | consumed samples: 5012480 | consumed tokens: 10265559040 | elapsed time per iteration (s): 0.31 | learning rate: 2.377E-05 | global batch size: 256 | lm loss: 2.950319E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.683 | TFLOPs: 29.29 | +7: iteration 19590/ 21553 | consumed samples: 5015040 | consumed tokens: 10270801920 | elapsed time per iteration (s): 0.31 | learning rate: 2.373E-05 | global batch size: 256 | lm loss: 2.941210E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.354 | TFLOPs: 28.65 | +7: iteration 19600/ 21553 | consumed samples: 5017600 | consumed tokens: 10276044800 | elapsed time per iteration (s): 0.31 | learning rate: 2.370E-05 | global batch size: 256 | lm loss: 2.950290E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.287 | TFLOPs: 29.38 | +7: iteration 19610/ 21553 | consumed samples: 5020160 | consumed tokens: 10281287680 | elapsed time per iteration (s): 0.32 | learning rate: 2.366E-05 | global batch size: 256 | lm loss: 2.956772E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 791.576 | TFLOPs: 27.71 | +7: iteration 19620/ 21553 | consumed samples: 5022720 | consumed tokens: 10286530560 | elapsed time per iteration (s): 0.31 | learning rate: 2.362E-05 | global batch size: 256 | lm loss: 2.950986E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.068 | TFLOPs: 28.85 | +7: iteration 19630/ 21553 | consumed samples: 5025280 | consumed tokens: 10291773440 | elapsed time per iteration (s): 0.31 | learning rate: 2.358E-05 | global batch size: 256 | lm loss: 2.980904E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.690 | TFLOPs: 29.12 | +7: iteration 19640/ 21553 | consumed samples: 5027840 | consumed tokens: 10297016320 | elapsed time per iteration (s): 0.30 | learning rate: 2.355E-05 | global batch size: 256 | lm loss: 2.946919E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.657 | TFLOPs: 29.43 | +7: iteration 19650/ 21553 | consumed samples: 5030400 | consumed tokens: 10302259200 | elapsed time per iteration (s): 0.31 | learning rate: 2.351E-05 | global batch size: 256 | lm loss: 2.956842E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.936 | TFLOPs: 28.81 | +7: iteration 19660/ 21553 | consumed samples: 5032960 | consumed tokens: 10307502080 | elapsed time per iteration (s): 0.30 | learning rate: 2.347E-05 | global batch size: 256 | lm loss: 2.946052E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.280 | TFLOPs: 29.42 | +7: iteration 19670/ 21553 | consumed samples: 5035520 | consumed tokens: 10312744960 | elapsed time per iteration (s): 0.31 | learning rate: 2.344E-05 | global batch size: 256 | lm loss: 2.933194E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.029 | TFLOPs: 29.09 | +7: iteration 19680/ 21553 | consumed samples: 5038080 | consumed tokens: 10317987840 | elapsed time per iteration (s): 0.31 | learning rate: 2.340E-05 | global batch size: 256 | lm loss: 2.981053E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.347 | TFLOPs: 28.65 | +7: iteration 19690/ 21553 | consumed samples: 5040640 | consumed tokens: 10323230720 | elapsed time per iteration (s): 0.30 | learning rate: 2.336E-05 | global batch size: 256 | lm loss: 2.946484E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.673 | TFLOPs: 29.39 | +7: iteration 19700/ 21553 | consumed samples: 5043200 | consumed tokens: 10328473600 | elapsed time per iteration (s): 0.31 | learning rate: 2.333E-05 | global batch size: 256 | lm loss: 2.948185E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.689 | TFLOPs: 28.70 | +7: iteration 19710/ 21553 | consumed samples: 5045760 | consumed tokens: 10333716480 | elapsed time per iteration (s): 0.30 | learning rate: 2.329E-05 | global batch size: 256 | lm loss: 2.938941E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.042 | TFLOPs: 29.44 | +7: iteration 19720/ 21553 | consumed samples: 5048320 | consumed tokens: 10338959360 | elapsed time per iteration (s): 0.30 | learning rate: 2.326E-05 | global batch size: 256 | lm loss: 2.942640E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.891 | TFLOPs: 29.47 | +7: iteration 19730/ 21553 | consumed samples: 5050880 | consumed tokens: 10344202240 | elapsed time per iteration (s): 0.31 | learning rate: 2.322E-05 | global batch size: 256 | lm loss: 2.955320E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.012 | TFLOPs: 29.06 | +7: iteration 19740/ 21553 | consumed samples: 5053440 | consumed tokens: 10349445120 | elapsed time per iteration (s): 0.31 | learning rate: 2.319E-05 | global batch size: 256 | lm loss: 2.952339E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.744 | TFLOPs: 29.12 | +7: iteration 19750/ 21553 | consumed samples: 5056000 | consumed tokens: 10354688000 | elapsed time per iteration (s): 0.30 | learning rate: 2.315E-05 | global batch size: 256 | lm loss: 2.957336E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.959 | TFLOPs: 29.61 | +7: iteration 19760/ 21553 | consumed samples: 5058560 | consumed tokens: 10359930880 | elapsed time per iteration (s): 0.32 | learning rate: 2.312E-05 | global batch size: 256 | lm loss: 2.971502E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 807.705 | TFLOPs: 28.28 | +7: iteration 19770/ 21553 | consumed samples: 5061120 | consumed tokens: 10365173760 | elapsed time per iteration (s): 0.31 | learning rate: 2.308E-05 | global batch size: 256 | lm loss: 2.951498E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.393 | TFLOPs: 28.54 | +7: iteration 19780/ 21553 | consumed samples: 5063680 | consumed tokens: 10370416640 | elapsed time per iteration (s): 0.33 | learning rate: 2.305E-05 | global batch size: 256 | lm loss: 2.972974E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 786.061 | TFLOPs: 27.52 | +7: iteration 19790/ 21553 | consumed samples: 5066240 | consumed tokens: 10375659520 | elapsed time per iteration (s): 0.31 | learning rate: 2.302E-05 | global batch size: 256 | lm loss: 2.978277E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.276 | TFLOPs: 29.35 | +7: iteration 19800/ 21553 | consumed samples: 5068800 | consumed tokens: 10380902400 | elapsed time per iteration (s): 0.31 | learning rate: 2.298E-05 | global batch size: 256 | lm loss: 2.947406E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.354 | TFLOPs: 29.21 | +7: iteration 19810/ 21553 | consumed samples: 5071360 | consumed tokens: 10386145280 | elapsed time per iteration (s): 0.31 | learning rate: 2.295E-05 | global batch size: 256 | lm loss: 2.952905E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.690 | TFLOPs: 29.22 | +7: iteration 19820/ 21553 | consumed samples: 5073920 | consumed tokens: 10391388160 | elapsed time per iteration (s): 0.30 | learning rate: 2.291E-05 | global batch size: 256 | lm loss: 2.924504E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.873 | TFLOPs: 29.54 | +7: iteration 19830/ 21553 | consumed samples: 5076480 | consumed tokens: 10396631040 | elapsed time per iteration (s): 0.31 | learning rate: 2.288E-05 | global batch size: 256 | lm loss: 2.956547E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.226 | TFLOPs: 29.10 | +7: iteration 19840/ 21553 | consumed samples: 5079040 | consumed tokens: 10401873920 | elapsed time per iteration (s): 0.31 | learning rate: 2.285E-05 | global batch size: 256 | lm loss: 2.948135E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.570 | TFLOPs: 28.83 | +7: iteration 19850/ 21553 | consumed samples: 5081600 | consumed tokens: 10407116800 | elapsed time per iteration (s): 0.31 | learning rate: 2.281E-05 | global batch size: 256 | lm loss: 2.937880E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.880 | TFLOPs: 29.16 | +7: iteration 19860/ 21553 | consumed samples: 5084160 | consumed tokens: 10412359680 | elapsed time per iteration (s): 0.31 | learning rate: 2.278E-05 | global batch size: 256 | lm loss: 2.965538E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.373 | TFLOPs: 29.00 | +7: iteration 19870/ 21553 | consumed samples: 5086720 | consumed tokens: 10417602560 | elapsed time per iteration (s): 0.31 | learning rate: 2.275E-05 | global batch size: 256 | lm loss: 2.930407E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.431 | TFLOPs: 29.21 | +7: iteration 19880/ 21553 | consumed samples: 5089280 | consumed tokens: 10422845440 | elapsed time per iteration (s): 0.31 | learning rate: 2.272E-05 | global batch size: 256 | lm loss: 2.969674E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.844 | TFLOPs: 29.16 | +7: iteration 19890/ 21553 | consumed samples: 5091840 | consumed tokens: 10428088320 | elapsed time per iteration (s): 0.31 | learning rate: 2.268E-05 | global batch size: 256 | lm loss: 2.926923E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.084 | TFLOPs: 28.99 | +7: iteration 19900/ 21553 | consumed samples: 5094400 | consumed tokens: 10433331200 | elapsed time per iteration (s): 0.31 | learning rate: 2.265E-05 | global batch size: 256 | lm loss: 2.918610E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.755 | TFLOPs: 28.98 | +7: iteration 19910/ 21553 | consumed samples: 5096960 | consumed tokens: 10438574080 | elapsed time per iteration (s): 0.31 | learning rate: 2.262E-05 | global batch size: 256 | lm loss: 2.936235E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.882 | TFLOPs: 29.37 | +7: iteration 19920/ 21553 | consumed samples: 5099520 | consumed tokens: 10443816960 | elapsed time per iteration (s): 0.30 | learning rate: 2.259E-05 | global batch size: 256 | lm loss: 2.951553E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.731 | TFLOPs: 29.40 | +7: iteration 19930/ 21553 | consumed samples: 5102080 | consumed tokens: 10449059840 | elapsed time per iteration (s): 0.30 | learning rate: 2.256E-05 | global batch size: 256 | lm loss: 2.950035E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.016 | TFLOPs: 29.41 | +7: iteration 19940/ 21553 | consumed samples: 5104640 | consumed tokens: 10454302720 | elapsed time per iteration (s): 0.32 | learning rate: 2.253E-05 | global batch size: 256 | lm loss: 2.933904E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.411 | TFLOPs: 28.41 | +7: iteration 19950/ 21553 | consumed samples: 5107200 | consumed tokens: 10459545600 | elapsed time per iteration (s): 0.30 | learning rate: 2.250E-05 | global batch size: 256 | lm loss: 2.937102E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.765 | TFLOPs: 29.40 | +7: iteration 19960/ 21553 | consumed samples: 5109760 | consumed tokens: 10464788480 | elapsed time per iteration (s): 0.31 | learning rate: 2.246E-05 | global batch size: 256 | lm loss: 2.958655E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.991 | TFLOPs: 29.23 | +7: iteration 19970/ 21553 | consumed samples: 5112320 | consumed tokens: 10470031360 | elapsed time per iteration (s): 0.31 | learning rate: 2.243E-05 | global batch size: 256 | lm loss: 2.938092E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.711 | TFLOPs: 29.33 | +7: iteration 19980/ 21553 | consumed samples: 5114880 | consumed tokens: 10475274240 | elapsed time per iteration (s): 0.30 | learning rate: 2.240E-05 | global batch size: 256 | lm loss: 2.922082E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 850.112 | TFLOPs: 29.76 | +7: iteration 19990/ 21553 | consumed samples: 5117440 | consumed tokens: 10480517120 | elapsed time per iteration (s): 0.31 | learning rate: 2.237E-05 | global batch size: 256 | lm loss: 2.932270E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.908 | TFLOPs: 28.98 | +0: [2022-11-29 18:51:45,881] [INFO] [logging.py:68:log_dist] [Rank 0] step=20000, skipped=0, lr=[2.234259142486404e-05, 2.234259142486404e-05, 2.234259142486404e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 20000/ 21553 | consumed samples: 5120000 | consumed tokens: 10485760000 | elapsed time per iteration (s): 0.30 | learning rate: 2.234E-05 | global batch size: 256 | lm loss: 2.967794E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 849.891 | TFLOPs: 29.75 | +0: steps: 20000 loss: 2.9494 iter time (s): 0.308 samples/sec: 832.515 +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 20000 | lm loss value: 2.870371E+00 | lm loss PPL: 1.764356E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 20000 to checkpoints_146moscareap +0: [2022-11-29 18:51:46,013] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step20000 is begin to save! +0: [2022-11-29 18:51:46,017] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:51:46,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:51:46,157] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:51:46,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:51:46,180] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:51:46,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:51:46,203] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:51:46,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:51:46,225] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:51:46,246] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:51:46,246] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:51:46,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:51:46,264] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:51:46,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:51:46,280] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:51:46,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:51:46,295] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:51:46,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:51:46,311] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:51:46,327] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:51:46,327] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:51:46,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:51:46,343] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/layer_13-model_00-model_states.pt... +0: [2022-11-29 18:51:46,359] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/layer_13-model_00-model_states.pt. +0: [2022-11-29 18:51:46,359] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:51:46,375] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:51:46,375] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/layer_15-model_00-model_states.pt... +0: [2022-11-29 18:51:46,390] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/layer_15-model_00-model_states.pt. +0: [2022-11-29 18:51:46,391] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/layer_16-model_00-model_states.pt... +0: [2022-11-29 18:51:46,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/layer_16-model_00-model_states.pt. +0: [2022-11-29 18:51:46,407] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/layer_17-model_00-model_states.pt... +0: [2022-11-29 18:51:46,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/layer_17-model_00-model_states.pt. +0: [2022-11-29 18:51:46,423] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/layer_19-model_00-model_states.pt... +0: [2022-11-29 18:51:46,424] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/layer_19-model_00-model_states.pt. +0: [2022-11-29 18:51:46,424] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_146moscareap/global_step20000/mp_rank_00_model_states.pt +0: [2022-11-29 18:51:46,425] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:51:46,427] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:51:46,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:51:46,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:51:46,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:51:46,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +5: [2022-11-29 18:51:46,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:51:46,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:51:46,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:51:46,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +5: [2022-11-29 18:51:46,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +7: [2022-11-29 18:51:46,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +5: [2022-11-29 18:51:46,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +7: [2022-11-29 18:51:46,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:51:46,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:51:46,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:51:46,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:51:46,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +7: [2022-11-29 18:51:46,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +3: [2022-11-29 18:51:46,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:51:46,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:51:46,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +7: [2022-11-29 18:51:46,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:51:46,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:51:46,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:51:46,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:51:46,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +3: [2022-11-29 18:51:46,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:51:46,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:51:46,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:51:46,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +2: [2022-11-29 18:51:46,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +2: [2022-11-29 18:51:46,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +3: [2022-11-29 18:51:46,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +3: [2022-11-29 18:51:46,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +5: [2022-11-29 18:51:46,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:51:46,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:51:46,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +2: [2022-11-29 18:51:46,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:51:46,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:51:46,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +5: [2022-11-29 18:51:46,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:51:46,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +2: [2022-11-29 18:51:46,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +5: [2022-11-29 18:51:46,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:51:46,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:51:46,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +2: [2022-11-29 18:51:46,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:51:46,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:51:46,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +3: [2022-11-29 18:51:46,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:51:46,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:51:46,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +2: [2022-11-29 18:51:46,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:51:46,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:51:46,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +1: [2022-11-29 18:51:46,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:51:46,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:51:46,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:51:46,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3: [2022-11-29 18:51:46,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:51:46,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +0: [2022-11-29 18:51:46,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +1: [2022-11-29 18:51:46,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:51:46,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +3: [2022-11-29 18:51:46,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +1: [2022-11-29 18:51:46,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +1: [2022-11-29 18:51:46,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:51:46,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +1: [2022-11-29 18:51:46,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:51:46,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +0: [2022-11-29 18:51:46,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:51:46,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:51:46,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +7: [2022-11-29 18:51:46,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:51:46,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +7: [2022-11-29 18:51:46,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:51:46,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:51:46,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +0: [2022-11-29 18:51:46,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:51:46,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:51:46,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +0: [2022-11-29 18:51:46,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +5: [2022-11-29 18:51:46,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +0: [2022-11-29 18:51:46,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +6: [2022-11-29 18:51:46,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:51:46,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:51:46,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +7: [2022-11-29 18:51:46,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:51:46,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:51:46,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +7: [2022-11-29 18:51:46,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:51:46,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +6: [2022-11-29 18:51:46,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +4: [2022-11-29 18:51:46,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:51:46,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:51:46,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +2: [2022-11-29 18:51:46,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:51:46,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:51:46,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +4: [2022-11-29 18:51:46,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:51:46,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:51:46,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:51:46,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:51:46,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:51:46,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +4: [2022-11-29 18:51:46,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +6: [2022-11-29 18:51:46,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +4: [2022-11-29 18:51:46,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +3: [2022-11-29 18:51:46,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +4: [2022-11-29 18:51:46,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +6: [2022-11-29 18:51:46,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +4: [2022-11-29 18:51:46,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:51:46,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:51:46,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:51:46,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +4: [2022-11-29 18:51:46,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +7: [2022-11-29 18:51:46,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +4: [2022-11-29 18:51:46,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +0: [2022-11-29 18:51:46,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +6: [2022-11-29 18:51:46,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:51:46,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +6: [2022-11-29 18:51:46,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:51:46,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +6: [2022-11-29 18:51:46,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:51:46,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:51:46,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +1: [2022-11-29 18:51:46,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:51:46,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +0: [2022-11-29 18:51:46,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:51:46,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +0: [2022-11-29 18:51:46,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +1: [2022-11-29 18:51:46,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:51:46,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +1: [2022-11-29 18:51:46,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:51:46,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +1: [2022-11-29 18:51:46,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:51:46,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:51:46,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +1: [2022-11-29 18:51:46,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:51:46,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:51:46,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +6: [2022-11-29 18:51:46,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:51:46,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +4: [2022-11-29 18:51:46,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:51:46,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +4: [2022-11-29 18:51:46,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:51:46,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +3: [2022-11-29 18:51:46,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:51:46,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:51:46,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +2: [2022-11-29 18:51:46,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:51:46,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:51:46,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +4: [2022-11-29 18:51:46,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:51:46,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:51:46,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +0: [2022-11-29 18:51:46,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:51:46,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:51:46,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +4: [2022-11-29 18:51:46,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:51:46,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:51:46,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +2: [2022-11-29 18:51:46,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:51:46,491] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:51:46,491] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:51:46,491] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +0: [2022-11-29 18:51:46,491] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3: [2022-11-29 18:51:46,491] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +2: [2022-11-29 18:51:46,491] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +0: [2022-11-29 18:51:46,491] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +3: [2022-11-29 18:51:46,491] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +4: [2022-11-29 18:51:46,491] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:51:46,491] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:51:46,491] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +7: [2022-11-29 18:51:46,491] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:51:46,491] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:51:46,491] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +1: [2022-11-29 18:51:46,493] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:51:46,493] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:51:46,493] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +6: [2022-11-29 18:51:46,493] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:51:46,493] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:51:46,494] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +6: [2022-11-29 18:51:46,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:51:46,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:51:46,494] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +5: [2022-11-29 18:51:46,494] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +6: [2022-11-29 18:51:46,494] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +5: [2022-11-29 18:51:46,494] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +5: [2022-11-29 18:51:46,495] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:51:46,495] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:51:46,495] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +0: [2022-11-29 18:51:46,513] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step20000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:51:46,513] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +0: successfully saved checkpoint at iteration 20000 to checkpoints_146moscareap +7: time (ms) | save-checkpoint: 505.28 +7: iteration 20010/ 21553 | consumed samples: 5122560 | consumed tokens: 10491002880 | elapsed time per iteration (s): 0.37 | learning rate: 2.231E-05 | global batch size: 256 | lm loss: 2.960618E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 690.435 | TFLOPs: 24.17 | +7: iteration 20020/ 21553 | consumed samples: 5125120 | consumed tokens: 10496245760 | elapsed time per iteration (s): 0.31 | learning rate: 2.228E-05 | global batch size: 256 | lm loss: 2.934708E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.823 | TFLOPs: 29.05 | +7: iteration 20030/ 21553 | consumed samples: 5127680 | consumed tokens: 10501488640 | elapsed time per iteration (s): 0.31 | learning rate: 2.225E-05 | global batch size: 256 | lm loss: 2.969653E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.531 | TFLOPs: 29.04 | +7: iteration 20040/ 21553 | consumed samples: 5130240 | consumed tokens: 10506731520 | elapsed time per iteration (s): 0.31 | learning rate: 2.222E-05 | global batch size: 256 | lm loss: 2.953973E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.109 | TFLOPs: 28.81 | +7: iteration 20050/ 21553 | consumed samples: 5132800 | consumed tokens: 10511974400 | elapsed time per iteration (s): 0.31 | learning rate: 2.219E-05 | global batch size: 256 | lm loss: 2.948051E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.380 | TFLOPs: 29.03 | +7: iteration 20060/ 21553 | consumed samples: 5135360 | consumed tokens: 10517217280 | elapsed time per iteration (s): 0.30 | learning rate: 2.217E-05 | global batch size: 256 | lm loss: 2.957098E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 847.975 | TFLOPs: 29.69 | +7: iteration 20070/ 21553 | consumed samples: 5137920 | consumed tokens: 10522460160 | elapsed time per iteration (s): 0.32 | learning rate: 2.214E-05 | global batch size: 256 | lm loss: 2.957331E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 805.933 | TFLOPs: 28.21 | +7: iteration 20080/ 21553 | consumed samples: 5140480 | consumed tokens: 10527703040 | elapsed time per iteration (s): 0.31 | learning rate: 2.211E-05 | global batch size: 256 | lm loss: 2.925057E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.138 | TFLOPs: 28.96 | +7: iteration 20090/ 21553 | consumed samples: 5143040 | consumed tokens: 10532945920 | elapsed time per iteration (s): 0.30 | learning rate: 2.208E-05 | global batch size: 256 | lm loss: 2.933658E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.660 | TFLOPs: 29.43 | +7: iteration 20100/ 21553 | consumed samples: 5145600 | consumed tokens: 10538188800 | elapsed time per iteration (s): 0.32 | learning rate: 2.205E-05 | global batch size: 256 | lm loss: 2.913223E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 791.289 | TFLOPs: 27.70 | +7: iteration 20110/ 21553 | consumed samples: 5148160 | consumed tokens: 10543431680 | elapsed time per iteration (s): 0.30 | learning rate: 2.202E-05 | global batch size: 256 | lm loss: 2.940491E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.349 | TFLOPs: 29.52 | +7: iteration 20120/ 21553 | consumed samples: 5150720 | consumed tokens: 10548674560 | elapsed time per iteration (s): 0.30 | learning rate: 2.200E-05 | global batch size: 256 | lm loss: 2.949621E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 850.807 | TFLOPs: 29.78 | +7: iteration 20130/ 21553 | consumed samples: 5153280 | consumed tokens: 10553917440 | elapsed time per iteration (s): 0.32 | learning rate: 2.197E-05 | global batch size: 256 | lm loss: 2.949147E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 803.967 | TFLOPs: 28.14 | +7: iteration 20140/ 21553 | consumed samples: 5155840 | consumed tokens: 10559160320 | elapsed time per iteration (s): 0.31 | learning rate: 2.194E-05 | global batch size: 256 | lm loss: 2.938764E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.597 | TFLOPs: 28.87 | +7: iteration 20150/ 21553 | consumed samples: 5158400 | consumed tokens: 10564403200 | elapsed time per iteration (s): 0.31 | learning rate: 2.191E-05 | global batch size: 256 | lm loss: 2.977012E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.637 | TFLOPs: 29.04 | +7: iteration 20160/ 21553 | consumed samples: 5160960 | consumed tokens: 10569646080 | elapsed time per iteration (s): 0.31 | learning rate: 2.189E-05 | global batch size: 256 | lm loss: 2.922094E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.387 | TFLOPs: 29.21 | +7: iteration 20170/ 21553 | consumed samples: 5163520 | consumed tokens: 10574888960 | elapsed time per iteration (s): 0.31 | learning rate: 2.186E-05 | global batch size: 256 | lm loss: 2.941003E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.817 | TFLOPs: 29.12 | +7: iteration 20180/ 21553 | consumed samples: 5166080 | consumed tokens: 10580131840 | elapsed time per iteration (s): 0.30 | learning rate: 2.183E-05 | global batch size: 256 | lm loss: 2.950815E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.069 | TFLOPs: 29.44 | +7: iteration 20190/ 21553 | consumed samples: 5168640 | consumed tokens: 10585374720 | elapsed time per iteration (s): 0.31 | learning rate: 2.181E-05 | global batch size: 256 | lm loss: 2.960149E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.363 | TFLOPs: 29.31 | +7: iteration 20200/ 21553 | consumed samples: 5171200 | consumed tokens: 10590617600 | elapsed time per iteration (s): 0.31 | learning rate: 2.178E-05 | global batch size: 256 | lm loss: 2.940799E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.889 | TFLOPs: 29.30 | +7: iteration 20210/ 21553 | consumed samples: 5173760 | consumed tokens: 10595860480 | elapsed time per iteration (s): 0.31 | learning rate: 2.175E-05 | global batch size: 256 | lm loss: 2.924348E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.394 | TFLOPs: 29.31 | +7: iteration 20220/ 21553 | consumed samples: 5176320 | consumed tokens: 10601103360 | elapsed time per iteration (s): 0.31 | learning rate: 2.173E-05 | global batch size: 256 | lm loss: 2.958759E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.797 | TFLOPs: 29.01 | +7: iteration 20230/ 21553 | consumed samples: 5178880 | consumed tokens: 10606346240 | elapsed time per iteration (s): 0.31 | learning rate: 2.170E-05 | global batch size: 256 | lm loss: 2.946567E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.247 | TFLOPs: 29.03 | +7: iteration 20240/ 21553 | consumed samples: 5181440 | consumed tokens: 10611589120 | elapsed time per iteration (s): 0.30 | learning rate: 2.168E-05 | global batch size: 256 | lm loss: 2.928706E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 847.856 | TFLOPs: 29.68 | +7: iteration 20250/ 21553 | consumed samples: 5184000 | consumed tokens: 10616832000 | elapsed time per iteration (s): 0.31 | learning rate: 2.165E-05 | global batch size: 256 | lm loss: 2.949948E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.377 | TFLOPs: 29.31 | +7: iteration 20260/ 21553 | consumed samples: 5186560 | consumed tokens: 10622074880 | elapsed time per iteration (s): 0.31 | learning rate: 2.163E-05 | global batch size: 256 | lm loss: 2.981004E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.554 | TFLOPs: 28.83 | +7: iteration 20270/ 21553 | consumed samples: 5189120 | consumed tokens: 10627317760 | elapsed time per iteration (s): 0.32 | learning rate: 2.160E-05 | global batch size: 256 | lm loss: 2.956259E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 795.635 | TFLOPs: 27.85 | +7: iteration 20280/ 21553 | consumed samples: 5191680 | consumed tokens: 10632560640 | elapsed time per iteration (s): 0.31 | learning rate: 2.158E-05 | global batch size: 256 | lm loss: 2.941969E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.001 | TFLOPs: 28.95 | +7: iteration 20290/ 21553 | consumed samples: 5194240 | consumed tokens: 10637803520 | elapsed time per iteration (s): 0.31 | learning rate: 2.155E-05 | global batch size: 256 | lm loss: 2.937849E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.706 | TFLOPs: 29.33 | +7: iteration 20300/ 21553 | consumed samples: 5196800 | consumed tokens: 10643046400 | elapsed time per iteration (s): 0.31 | learning rate: 2.153E-05 | global batch size: 256 | lm loss: 2.926977E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.540 | TFLOPs: 28.83 | +7: iteration 20310/ 21553 | consumed samples: 5199360 | consumed tokens: 10648289280 | elapsed time per iteration (s): 0.32 | learning rate: 2.150E-05 | global batch size: 256 | lm loss: 2.927634E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 806.874 | TFLOPs: 28.25 | +7: iteration 20320/ 21553 | consumed samples: 5201920 | consumed tokens: 10653532160 | elapsed time per iteration (s): 0.31 | learning rate: 2.148E-05 | global batch size: 256 | lm loss: 2.954128E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.177 | TFLOPs: 29.17 | +7: iteration 20330/ 21553 | consumed samples: 5204480 | consumed tokens: 10658775040 | elapsed time per iteration (s): 0.30 | learning rate: 2.146E-05 | global batch size: 256 | lm loss: 2.967989E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.671 | TFLOPs: 29.39 | +7: iteration 20340/ 21553 | consumed samples: 5207040 | consumed tokens: 10664017920 | elapsed time per iteration (s): 0.31 | learning rate: 2.143E-05 | global batch size: 256 | lm loss: 2.967484E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.723 | TFLOPs: 29.08 | +7: iteration 20350/ 21553 | consumed samples: 5209600 | consumed tokens: 10669260800 | elapsed time per iteration (s): 0.31 | learning rate: 2.141E-05 | global batch size: 256 | lm loss: 2.943003E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.244 | TFLOPs: 29.20 | +7: iteration 20360/ 21553 | consumed samples: 5212160 | consumed tokens: 10674503680 | elapsed time per iteration (s): 0.31 | learning rate: 2.138E-05 | global batch size: 256 | lm loss: 2.923549E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 838.772 | TFLOPs: 29.36 | +7: iteration 20370/ 21553 | consumed samples: 5214720 | consumed tokens: 10679746560 | elapsed time per iteration (s): 0.30 | learning rate: 2.136E-05 | global batch size: 256 | lm loss: 2.969324E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.564 | TFLOPs: 29.46 | +7: iteration 20380/ 21553 | consumed samples: 5217280 | consumed tokens: 10684989440 | elapsed time per iteration (s): 0.30 | learning rate: 2.134E-05 | global batch size: 256 | lm loss: 2.953599E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.512 | TFLOPs: 29.42 | +7: iteration 20390/ 21553 | consumed samples: 5219840 | consumed tokens: 10690232320 | elapsed time per iteration (s): 0.30 | learning rate: 2.132E-05 | global batch size: 256 | lm loss: 2.951082E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 847.123 | TFLOPs: 29.66 | +7: iteration 20400/ 21553 | consumed samples: 5222400 | consumed tokens: 10695475200 | elapsed time per iteration (s): 0.31 | learning rate: 2.129E-05 | global batch size: 256 | lm loss: 2.951824E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.847 | TFLOPs: 29.23 | +7: iteration 20410/ 21553 | consumed samples: 5224960 | consumed tokens: 10700718080 | elapsed time per iteration (s): 0.33 | learning rate: 2.127E-05 | global batch size: 256 | lm loss: 2.913027E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 784.973 | TFLOPs: 27.48 | +7: iteration 20420/ 21553 | consumed samples: 5227520 | consumed tokens: 10705960960 | elapsed time per iteration (s): 0.32 | learning rate: 2.125E-05 | global batch size: 256 | lm loss: 2.920920E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 798.336 | TFLOPs: 27.95 | +7: iteration 20430/ 21553 | consumed samples: 5230080 | consumed tokens: 10711203840 | elapsed time per iteration (s): 0.30 | learning rate: 2.123E-05 | global batch size: 256 | lm loss: 2.934995E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.408 | TFLOPs: 29.60 | +7: iteration 20440/ 21553 | consumed samples: 5232640 | consumed tokens: 10716446720 | elapsed time per iteration (s): 0.31 | learning rate: 2.121E-05 | global batch size: 256 | lm loss: 2.971733E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 820.421 | TFLOPs: 28.72 | +7: iteration 20450/ 21553 | consumed samples: 5235200 | consumed tokens: 10721689600 | elapsed time per iteration (s): 0.32 | learning rate: 2.118E-05 | global batch size: 256 | lm loss: 2.945068E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.485 | TFLOPs: 28.37 | +7: iteration 20460/ 21553 | consumed samples: 5237760 | consumed tokens: 10726932480 | elapsed time per iteration (s): 0.31 | learning rate: 2.116E-05 | global batch size: 256 | lm loss: 2.929959E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.321 | TFLOPs: 29.21 | +7: iteration 20470/ 21553 | consumed samples: 5240320 | consumed tokens: 10732175360 | elapsed time per iteration (s): 0.30 | learning rate: 2.114E-05 | global batch size: 256 | lm loss: 2.943689E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.967 | TFLOPs: 29.44 | +7: iteration 20480/ 21553 | consumed samples: 5242880 | consumed tokens: 10737418240 | elapsed time per iteration (s): 0.30 | learning rate: 2.112E-05 | global batch size: 256 | lm loss: 2.933174E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.731 | TFLOPs: 29.43 | +7: iteration 20490/ 21553 | consumed samples: 5245440 | consumed tokens: 10742661120 | elapsed time per iteration (s): 0.31 | learning rate: 2.110E-05 | global batch size: 256 | lm loss: 2.933496E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.822 | TFLOPs: 28.77 | +7: iteration 20500/ 21553 | consumed samples: 5248000 | consumed tokens: 10747904000 | elapsed time per iteration (s): 0.30 | learning rate: 2.108E-05 | global batch size: 256 | lm loss: 2.931048E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.785 | TFLOPs: 29.61 | +7: iteration 20510/ 21553 | consumed samples: 5250560 | consumed tokens: 10753146880 | elapsed time per iteration (s): 0.31 | learning rate: 2.106E-05 | global batch size: 256 | lm loss: 2.959357E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.190 | TFLOPs: 29.31 | +7: iteration 20520/ 21553 | consumed samples: 5253120 | consumed tokens: 10758389760 | elapsed time per iteration (s): 0.31 | learning rate: 2.104E-05 | global batch size: 256 | lm loss: 2.943335E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.281 | TFLOPs: 29.14 | +7: iteration 20530/ 21553 | consumed samples: 5255680 | consumed tokens: 10763632640 | elapsed time per iteration (s): 0.31 | learning rate: 2.102E-05 | global batch size: 256 | lm loss: 2.941528E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.371 | TFLOPs: 28.68 | +7: iteration 20540/ 21553 | consumed samples: 5258240 | consumed tokens: 10768875520 | elapsed time per iteration (s): 0.30 | learning rate: 2.100E-05 | global batch size: 256 | lm loss: 2.943367E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 847.185 | TFLOPs: 29.66 | +7: iteration 20550/ 21553 | consumed samples: 5260800 | consumed tokens: 10774118400 | elapsed time per iteration (s): 0.30 | learning rate: 2.098E-05 | global batch size: 256 | lm loss: 2.940948E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.739 | TFLOPs: 29.40 | +7: iteration 20560/ 21553 | consumed samples: 5263360 | consumed tokens: 10779361280 | elapsed time per iteration (s): 0.30 | learning rate: 2.096E-05 | global batch size: 256 | lm loss: 2.929575E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.229 | TFLOPs: 29.52 | +7: iteration 20570/ 21553 | consumed samples: 5265920 | consumed tokens: 10784604160 | elapsed time per iteration (s): 0.30 | learning rate: 2.094E-05 | global batch size: 256 | lm loss: 2.960044E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 848.691 | TFLOPs: 29.71 | +7: iteration 20580/ 21553 | consumed samples: 5268480 | consumed tokens: 10789847040 | elapsed time per iteration (s): 0.31 | learning rate: 2.092E-05 | global batch size: 256 | lm loss: 2.915532E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.828 | TFLOPs: 29.19 | +7: iteration 20590/ 21553 | consumed samples: 5271040 | consumed tokens: 10795089920 | elapsed time per iteration (s): 0.32 | learning rate: 2.090E-05 | global batch size: 256 | lm loss: 2.938541E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 789.981 | TFLOPs: 27.66 | +7: iteration 20600/ 21553 | consumed samples: 5273600 | consumed tokens: 10800332800 | elapsed time per iteration (s): 0.31 | learning rate: 2.088E-05 | global batch size: 256 | lm loss: 2.938610E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.109 | TFLOPs: 29.20 | +7: iteration 20610/ 21553 | consumed samples: 5276160 | consumed tokens: 10805575680 | elapsed time per iteration (s): 0.32 | learning rate: 2.087E-05 | global batch size: 256 | lm loss: 2.948036E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 804.640 | TFLOPs: 28.17 | +7: iteration 20620/ 21553 | consumed samples: 5278720 | consumed tokens: 10810818560 | elapsed time per iteration (s): 0.31 | learning rate: 2.085E-05 | global batch size: 256 | lm loss: 2.970867E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.626 | TFLOPs: 29.15 | +7: iteration 20630/ 21553 | consumed samples: 5281280 | consumed tokens: 10816061440 | elapsed time per iteration (s): 0.31 | learning rate: 2.083E-05 | global batch size: 256 | lm loss: 2.905845E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.477 | TFLOPs: 28.86 | +7: iteration 20640/ 21553 | consumed samples: 5283840 | consumed tokens: 10821304320 | elapsed time per iteration (s): 0.30 | learning rate: 2.081E-05 | global batch size: 256 | lm loss: 2.952885E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 849.895 | TFLOPs: 29.75 | +7: iteration 20650/ 21553 | consumed samples: 5286400 | consumed tokens: 10826547200 | elapsed time per iteration (s): 0.31 | learning rate: 2.079E-05 | global batch size: 256 | lm loss: 2.921594E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.527 | TFLOPs: 29.28 | +7: iteration 20660/ 21553 | consumed samples: 5288960 | consumed tokens: 10831790080 | elapsed time per iteration (s): 0.31 | learning rate: 2.078E-05 | global batch size: 256 | lm loss: 2.947258E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.232 | TFLOPs: 29.27 | +7: iteration 20670/ 21553 | consumed samples: 5291520 | consumed tokens: 10837032960 | elapsed time per iteration (s): 0.30 | learning rate: 2.076E-05 | global batch size: 256 | lm loss: 2.934397E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.423 | TFLOPs: 29.53 | +7: iteration 20680/ 21553 | consumed samples: 5294080 | consumed tokens: 10842275840 | elapsed time per iteration (s): 0.31 | learning rate: 2.074E-05 | global batch size: 256 | lm loss: 2.939480E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.127 | TFLOPs: 29.27 | +7: iteration 20690/ 21553 | consumed samples: 5296640 | consumed tokens: 10847518720 | elapsed time per iteration (s): 0.31 | learning rate: 2.073E-05 | global batch size: 256 | lm loss: 2.934541E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.494 | TFLOPs: 29.25 | +7: iteration 20700/ 21553 | consumed samples: 5299200 | consumed tokens: 10852761600 | elapsed time per iteration (s): 0.30 | learning rate: 2.071E-05 | global batch size: 256 | lm loss: 2.965219E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.461 | TFLOPs: 29.39 | +7: iteration 20710/ 21553 | consumed samples: 5301760 | consumed tokens: 10858004480 | elapsed time per iteration (s): 0.31 | learning rate: 2.069E-05 | global batch size: 256 | lm loss: 2.922604E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.363 | TFLOPs: 29.10 | +7: iteration 20720/ 21553 | consumed samples: 5304320 | consumed tokens: 10863247360 | elapsed time per iteration (s): 0.31 | learning rate: 2.068E-05 | global batch size: 256 | lm loss: 2.905270E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.216 | TFLOPs: 28.64 | +7: iteration 20730/ 21553 | consumed samples: 5306880 | consumed tokens: 10868490240 | elapsed time per iteration (s): 0.31 | learning rate: 2.066E-05 | global batch size: 256 | lm loss: 2.968678E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.476 | TFLOPs: 29.18 | +7: iteration 20740/ 21553 | consumed samples: 5309440 | consumed tokens: 10873733120 | elapsed time per iteration (s): 0.31 | learning rate: 2.064E-05 | global batch size: 256 | lm loss: 2.920128E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.322 | TFLOPs: 29.00 | +7: iteration 20750/ 21553 | consumed samples: 5312000 | consumed tokens: 10878976000 | elapsed time per iteration (s): 0.30 | learning rate: 2.063E-05 | global batch size: 256 | lm loss: 2.979213E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 846.504 | TFLOPs: 29.63 | +7: iteration 20760/ 21553 | consumed samples: 5314560 | consumed tokens: 10884218880 | elapsed time per iteration (s): 0.33 | learning rate: 2.061E-05 | global batch size: 256 | lm loss: 2.927966E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 775.118 | TFLOPs: 27.13 | +7: iteration 20770/ 21553 | consumed samples: 5317120 | consumed tokens: 10889461760 | elapsed time per iteration (s): 0.31 | learning rate: 2.060E-05 | global batch size: 256 | lm loss: 2.907539E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.594 | TFLOPs: 28.94 | +7: iteration 20780/ 21553 | consumed samples: 5319680 | consumed tokens: 10894704640 | elapsed time per iteration (s): 0.31 | learning rate: 2.058E-05 | global batch size: 256 | lm loss: 2.944110E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.200 | TFLOPs: 28.96 | +7: iteration 20790/ 21553 | consumed samples: 5322240 | consumed tokens: 10899947520 | elapsed time per iteration (s): 0.31 | learning rate: 2.057E-05 | global batch size: 256 | lm loss: 2.958076E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.462 | TFLOPs: 29.07 | +7: iteration 20800/ 21553 | consumed samples: 5324800 | consumed tokens: 10905190400 | elapsed time per iteration (s): 0.31 | learning rate: 2.055E-05 | global batch size: 256 | lm loss: 2.964515E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.271 | TFLOPs: 29.14 | +7: iteration 20810/ 21553 | consumed samples: 5327360 | consumed tokens: 10910433280 | elapsed time per iteration (s): 0.31 | learning rate: 2.054E-05 | global batch size: 256 | lm loss: 2.919849E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.290 | TFLOPs: 29.21 | +7: iteration 20820/ 21553 | consumed samples: 5329920 | consumed tokens: 10915676160 | elapsed time per iteration (s): 0.31 | learning rate: 2.052E-05 | global batch size: 256 | lm loss: 2.941580E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.113 | TFLOPs: 28.85 | +7: iteration 20830/ 21553 | consumed samples: 5332480 | consumed tokens: 10920919040 | elapsed time per iteration (s): 0.30 | learning rate: 2.051E-05 | global batch size: 256 | lm loss: 2.950965E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.376 | TFLOPs: 29.42 | +7: iteration 20840/ 21553 | consumed samples: 5335040 | consumed tokens: 10926161920 | elapsed time per iteration (s): 0.30 | learning rate: 2.050E-05 | global batch size: 256 | lm loss: 2.940370E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 849.497 | TFLOPs: 29.74 | +7: iteration 20850/ 21553 | consumed samples: 5337600 | consumed tokens: 10931404800 | elapsed time per iteration (s): 0.31 | learning rate: 2.048E-05 | global batch size: 256 | lm loss: 2.909317E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.089 | TFLOPs: 29.20 | +7: iteration 20860/ 21553 | consumed samples: 5340160 | consumed tokens: 10936647680 | elapsed time per iteration (s): 0.31 | learning rate: 2.047E-05 | global batch size: 256 | lm loss: 2.942740E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.561 | TFLOPs: 29.11 | +7: iteration 20870/ 21553 | consumed samples: 5342720 | consumed tokens: 10941890560 | elapsed time per iteration (s): 0.31 | learning rate: 2.045E-05 | global batch size: 256 | lm loss: 2.950298E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.363 | TFLOPs: 29.03 | +7: iteration 20880/ 21553 | consumed samples: 5345280 | consumed tokens: 10947133440 | elapsed time per iteration (s): 0.31 | learning rate: 2.044E-05 | global batch size: 256 | lm loss: 2.954826E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.117 | TFLOPs: 28.68 | +7: iteration 20890/ 21553 | consumed samples: 5347840 | consumed tokens: 10952376320 | elapsed time per iteration (s): 0.31 | learning rate: 2.043E-05 | global batch size: 256 | lm loss: 2.921581E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.747 | TFLOPs: 29.19 | +7: iteration 20900/ 21553 | consumed samples: 5350400 | consumed tokens: 10957619200 | elapsed time per iteration (s): 0.32 | learning rate: 2.042E-05 | global batch size: 256 | lm loss: 2.954579E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 799.925 | TFLOPs: 28.00 | +7: iteration 20910/ 21553 | consumed samples: 5352960 | consumed tokens: 10962862080 | elapsed time per iteration (s): 0.32 | learning rate: 2.040E-05 | global batch size: 256 | lm loss: 2.950457E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 805.384 | TFLOPs: 28.19 | +7: iteration 20920/ 21553 | consumed samples: 5355520 | consumed tokens: 10968104960 | elapsed time per iteration (s): 0.31 | learning rate: 2.039E-05 | global batch size: 256 | lm loss: 2.952130E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 824.301 | TFLOPs: 28.86 | +7: iteration 20930/ 21553 | consumed samples: 5358080 | consumed tokens: 10973347840 | elapsed time per iteration (s): 0.30 | learning rate: 2.038E-05 | global batch size: 256 | lm loss: 2.952803E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 849.814 | TFLOPs: 29.75 | +7: iteration 20940/ 21553 | consumed samples: 5360640 | consumed tokens: 10978590720 | elapsed time per iteration (s): 0.31 | learning rate: 2.037E-05 | global batch size: 256 | lm loss: 2.952740E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.550 | TFLOPs: 28.55 | +7: iteration 20950/ 21553 | consumed samples: 5363200 | consumed tokens: 10983833600 | elapsed time per iteration (s): 0.31 | learning rate: 2.035E-05 | global batch size: 256 | lm loss: 2.919299E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.228 | TFLOPs: 28.89 | +7: iteration 20960/ 21553 | consumed samples: 5365760 | consumed tokens: 10989076480 | elapsed time per iteration (s): 0.31 | learning rate: 2.034E-05 | global batch size: 256 | lm loss: 2.957513E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.545 | TFLOPs: 29.25 | +7: iteration 20970/ 21553 | consumed samples: 5368320 | consumed tokens: 10994319360 | elapsed time per iteration (s): 0.31 | learning rate: 2.033E-05 | global batch size: 256 | lm loss: 2.992130E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.846 | TFLOPs: 29.09 | +7: iteration 20980/ 21553 | consumed samples: 5370880 | consumed tokens: 10999562240 | elapsed time per iteration (s): 0.32 | learning rate: 2.032E-05 | global batch size: 256 | lm loss: 2.926044E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 809.066 | TFLOPs: 28.32 | +7: iteration 20990/ 21553 | consumed samples: 5373440 | consumed tokens: 11004805120 | elapsed time per iteration (s): 0.30 | learning rate: 2.031E-05 | global batch size: 256 | lm loss: 2.941653E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.889 | TFLOPs: 29.40 | +7: iteration 21000/ 21553 | consumed samples: 5376000 | consumed tokens: 11010048000 | elapsed time per iteration (s): 0.31 | learning rate: 2.030E-05 | global batch size: 256 | lm loss: 2.937964E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.991 | TFLOPs: 29.20 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 21000 | lm loss value: 2.941766E+00 | lm loss PPL: 1.894928E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 21000 to checkpoints_146moscareap +0: [2022-11-29 18:56:55,401] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step21000 is begin to save! +0: [2022-11-29 18:56:55,407] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:56:55,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:56:55,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:56:55,520] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:56:55,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:56:55,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:56:55,536] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:56:55,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:56:55,551] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:56:55,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:56:55,567] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:56:55,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:56:55,582] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:56:55,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:56:55,598] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:56:55,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:56:55,613] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:56:55,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:56:55,628] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:56:55,643] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:56:55,644] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:56:55,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:56:55,660] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/layer_13-model_00-model_states.pt... +0: [2022-11-29 18:56:55,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/layer_13-model_00-model_states.pt. +0: [2022-11-29 18:56:55,675] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:56:55,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:56:55,691] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/layer_15-model_00-model_states.pt... +0: [2022-11-29 18:56:55,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/layer_15-model_00-model_states.pt. +0: [2022-11-29 18:56:55,707] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/layer_16-model_00-model_states.pt... +0: [2022-11-29 18:56:55,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/layer_16-model_00-model_states.pt. +0: [2022-11-29 18:56:55,722] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/layer_17-model_00-model_states.pt... +0: [2022-11-29 18:56:55,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/layer_17-model_00-model_states.pt. +0: [2022-11-29 18:56:55,738] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/layer_19-model_00-model_states.pt... +0: [2022-11-29 18:56:55,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/layer_19-model_00-model_states.pt. +0: [2022-11-29 18:56:55,739] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_146moscareap/global_step21000/mp_rank_00_model_states.pt +0: [2022-11-29 18:56:55,739] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:56:55,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:56:55,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:56:55,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:56:55,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +5: [2022-11-29 18:56:55,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:56:55,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +5: [2022-11-29 18:56:55,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:56:55,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +1: [2022-11-29 18:56:55,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:56:55,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:56:55,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +2: [2022-11-29 18:56:55,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:56:55,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:56:55,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +1: [2022-11-29 18:56:55,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:56:55,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:56:55,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +2: [2022-11-29 18:56:55,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:56:55,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:56:55,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +5: [2022-11-29 18:56:55,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:56:55,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:56:55,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +1: [2022-11-29 18:56:55,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:56:55,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:56:55,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +6: [2022-11-29 18:56:55,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:56:55,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:56:55,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:56:55,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:56:55,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +6: [2022-11-29 18:56:55,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +3: [2022-11-29 18:56:55,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:56:55,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:56:55,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:56:55,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +3: [2022-11-29 18:56:55,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:56:55,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +5: [2022-11-29 18:56:55,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:56:55,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:56:55,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +7: [2022-11-29 18:56:55,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:56:55,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:56:55,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +7: [2022-11-29 18:56:55,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:56:55,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:56:55,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +2: [2022-11-29 18:56:55,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:56:55,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +4: [2022-11-29 18:56:55,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:56:55,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:56:55,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +7: [2022-11-29 18:56:55,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:56:55,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:56:55,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +3: [2022-11-29 18:56:55,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +7: [2022-11-29 18:56:55,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +4: [2022-11-29 18:56:55,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +2: [2022-11-29 18:56:55,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +3: [2022-11-29 18:56:55,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +7: [2022-11-29 18:56:55,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +2: [2022-11-29 18:56:55,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +6: [2022-11-29 18:56:55,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:56:55,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +5: [2022-11-29 18:56:55,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:56:55,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +0: [2022-11-29 18:56:55,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:56:55,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:56:55,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +7: [2022-11-29 18:56:55,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:56:55,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:56:55,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +2: [2022-11-29 18:56:55,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:56:55,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:56:55,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +1: [2022-11-29 18:56:55,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:56:55,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +4: [2022-11-29 18:56:55,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:56:55,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +4: [2022-11-29 18:56:55,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +0: [2022-11-29 18:56:55,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:56:55,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +0: [2022-11-29 18:56:55,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:56:55,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +2: [2022-11-29 18:56:55,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:56:55,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:56:55,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +3: [2022-11-29 18:56:55,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:56:55,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:56:55,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +4: [2022-11-29 18:56:55,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:56:55,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:56:55,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +4: [2022-11-29 18:56:55,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:56:55,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:56:55,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +6: [2022-11-29 18:56:55,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:56:55,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:56:55,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +5: [2022-11-29 18:56:55,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:56:55,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:56:55,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +0: [2022-11-29 18:56:55,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:56:55,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:56:55,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:56:55,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:56:55,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +6: [2022-11-29 18:56:55,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +0: [2022-11-29 18:56:55,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +6: [2022-11-29 18:56:55,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +7: [2022-11-29 18:56:55,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +0: [2022-11-29 18:56:55,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +0: [2022-11-29 18:56:55,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +7: [2022-11-29 18:56:55,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +5: [2022-11-29 18:56:55,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:56:55,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:56:55,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:56:55,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:56:55,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +1: [2022-11-29 18:56:55,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:56:55,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +0: [2022-11-29 18:56:55,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +1: [2022-11-29 18:56:55,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +1: [2022-11-29 18:56:55,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +6: [2022-11-29 18:56:55,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:56:55,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +7: [2022-11-29 18:56:55,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:56:55,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +7: [2022-11-29 18:56:55,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +4: [2022-11-29 18:56:55,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:56:55,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +3: [2022-11-29 18:56:55,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:56:55,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:56:55,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +3: [2022-11-29 18:56:55,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:56:55,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +7: [2022-11-29 18:56:55,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:56:55,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:56:55,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +3: [2022-11-29 18:56:55,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:56:55,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:56:55,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:56:55,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:56:55,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +3: [2022-11-29 18:56:55,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +1: [2022-11-29 18:56:55,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:56:55,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:56:55,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +4: [2022-11-29 18:56:55,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:56:55,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:56:55,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +6: [2022-11-29 18:56:55,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:56:55,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:56:55,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +4: [2022-11-29 18:56:55,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:56:55,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:56:55,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +0: [2022-11-29 18:56:55,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:56:55,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:56:55,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:56:55,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +0: [2022-11-29 18:56:55,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:56:55,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +2: [2022-11-29 18:56:55,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:56:55,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:56:55,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:56:55,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:56:55,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +2: [2022-11-29 18:56:55,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +4: [2022-11-29 18:56:55,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:56:55,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:56:55,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +4: [2022-11-29 18:56:55,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +7: [2022-11-29 18:56:55,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +4: [2022-11-29 18:56:55,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +5: [2022-11-29 18:56:55,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:56:55,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +5: [2022-11-29 18:56:55,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:56:55,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:56:55,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:56:55,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +5: [2022-11-29 18:56:55,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:56:55,804] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:56:55,804] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +1: [2022-11-29 18:56:55,804] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:56:55,804] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +0: [2022-11-29 18:56:55,805] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:56:55,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:56:55,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +6: [2022-11-29 18:56:55,806] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:56:55,806] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:56:55,806] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +0: [2022-11-29 18:56:55,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:56:55,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +0: successfully saved checkpoint at iteration 21000 to checkpoints_146moscareap +7: time (ms) | save-checkpoint: 480.39 +7: iteration 21010/ 21553 | consumed samples: 5378560 | consumed tokens: 11015290880 | elapsed time per iteration (s): 0.36 | learning rate: 2.029E-05 | global batch size: 256 | lm loss: 2.917549E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 708.059 | TFLOPs: 24.79 | +7: iteration 21020/ 21553 | consumed samples: 5381120 | consumed tokens: 11020533760 | elapsed time per iteration (s): 0.31 | learning rate: 2.028E-05 | global batch size: 256 | lm loss: 2.940940E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.936 | TFLOPs: 29.12 | +7: iteration 21030/ 21553 | consumed samples: 5383680 | consumed tokens: 11025776640 | elapsed time per iteration (s): 0.31 | learning rate: 2.027E-05 | global batch size: 256 | lm loss: 2.950849E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.845 | TFLOPs: 28.81 | +7: iteration 21040/ 21553 | consumed samples: 5386240 | consumed tokens: 11031019520 | elapsed time per iteration (s): 0.33 | learning rate: 2.026E-05 | global batch size: 256 | lm loss: 2.941676E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 781.777 | TFLOPs: 27.37 | +7: iteration 21050/ 21553 | consumed samples: 5388800 | consumed tokens: 11036262400 | elapsed time per iteration (s): 0.32 | learning rate: 2.025E-05 | global batch size: 256 | lm loss: 2.966746E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 810.338 | TFLOPs: 28.37 | +7: iteration 21060/ 21553 | consumed samples: 5391360 | consumed tokens: 11041505280 | elapsed time per iteration (s): 0.30 | learning rate: 2.024E-05 | global batch size: 256 | lm loss: 2.968646E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.573 | TFLOPs: 29.53 | +7: iteration 21070/ 21553 | consumed samples: 5393920 | consumed tokens: 11046748160 | elapsed time per iteration (s): 0.32 | learning rate: 2.023E-05 | global batch size: 256 | lm loss: 2.933592E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 794.883 | TFLOPs: 27.83 | +7: iteration 21080/ 21553 | consumed samples: 5396480 | consumed tokens: 11051991040 | elapsed time per iteration (s): 0.31 | learning rate: 2.022E-05 | global batch size: 256 | lm loss: 2.966691E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.904 | TFLOPs: 28.84 | +7: iteration 21090/ 21553 | consumed samples: 5399040 | consumed tokens: 11057233920 | elapsed time per iteration (s): 0.31 | learning rate: 2.021E-05 | global batch size: 256 | lm loss: 2.963936E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.889 | TFLOPs: 29.16 | +7: iteration 21100/ 21553 | consumed samples: 5401600 | consumed tokens: 11062476800 | elapsed time per iteration (s): 0.31 | learning rate: 2.020E-05 | global batch size: 256 | lm loss: 2.942320E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.166 | TFLOPs: 28.99 | +7: iteration 21110/ 21553 | consumed samples: 5404160 | consumed tokens: 11067719680 | elapsed time per iteration (s): 0.31 | learning rate: 2.019E-05 | global batch size: 256 | lm loss: 2.954644E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.218 | TFLOPs: 28.89 | +7: iteration 21120/ 21553 | consumed samples: 5406720 | consumed tokens: 11072962560 | elapsed time per iteration (s): 0.31 | learning rate: 2.018E-05 | global batch size: 256 | lm loss: 2.941638E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.409 | TFLOPs: 28.93 | +7: iteration 21130/ 21553 | consumed samples: 5409280 | consumed tokens: 11078205440 | elapsed time per iteration (s): 0.31 | learning rate: 2.017E-05 | global batch size: 256 | lm loss: 2.930762E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.457 | TFLOPs: 29.07 | +7: iteration 21140/ 21553 | consumed samples: 5411840 | consumed tokens: 11083448320 | elapsed time per iteration (s): 0.31 | learning rate: 2.017E-05 | global batch size: 256 | lm loss: 2.960563E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.861 | TFLOPs: 28.91 | +7: iteration 21150/ 21553 | consumed samples: 5414400 | consumed tokens: 11088691200 | elapsed time per iteration (s): 0.31 | learning rate: 2.016E-05 | global batch size: 256 | lm loss: 2.933740E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 829.278 | TFLOPs: 29.03 | +7: iteration 21160/ 21553 | consumed samples: 5416960 | consumed tokens: 11093934080 | elapsed time per iteration (s): 0.32 | learning rate: 2.015E-05 | global batch size: 256 | lm loss: 2.931449E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 808.598 | TFLOPs: 28.31 | +7: iteration 21170/ 21553 | consumed samples: 5419520 | consumed tokens: 11099176960 | elapsed time per iteration (s): 0.31 | learning rate: 2.014E-05 | global batch size: 256 | lm loss: 2.962052E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.888 | TFLOPs: 28.95 | +7: iteration 21180/ 21553 | consumed samples: 5422080 | consumed tokens: 11104419840 | elapsed time per iteration (s): 0.30 | learning rate: 2.014E-05 | global batch size: 256 | lm loss: 2.935782E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.888 | TFLOPs: 29.47 | +7: iteration 21190/ 21553 | consumed samples: 5424640 | consumed tokens: 11109662720 | elapsed time per iteration (s): 0.32 | learning rate: 2.013E-05 | global batch size: 256 | lm loss: 2.926315E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 795.177 | TFLOPs: 27.84 | +7: iteration 21200/ 21553 | consumed samples: 5427200 | consumed tokens: 11114905600 | elapsed time per iteration (s): 0.31 | learning rate: 2.012E-05 | global batch size: 256 | lm loss: 2.953256E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 819.191 | TFLOPs: 28.68 | +7: iteration 21210/ 21553 | consumed samples: 5429760 | consumed tokens: 11120148480 | elapsed time per iteration (s): 0.31 | learning rate: 2.011E-05 | global batch size: 256 | lm loss: 2.919324E+00 | grad norm: 0.529 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.820 | TFLOPs: 29.22 | +7: iteration 21220/ 21553 | consumed samples: 5432320 | consumed tokens: 11125391360 | elapsed time per iteration (s): 0.31 | learning rate: 2.011E-05 | global batch size: 256 | lm loss: 2.954950E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.899 | TFLOPs: 29.02 | +7: iteration 21230/ 21553 | consumed samples: 5434880 | consumed tokens: 11130634240 | elapsed time per iteration (s): 0.31 | learning rate: 2.010E-05 | global batch size: 256 | lm loss: 2.941633E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.284 | TFLOPs: 28.79 | +7: iteration 21240/ 21553 | consumed samples: 5437440 | consumed tokens: 11135877120 | elapsed time per iteration (s): 0.30 | learning rate: 2.010E-05 | global batch size: 256 | lm loss: 2.944387E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.652 | TFLOPs: 29.39 | +7: iteration 21250/ 21553 | consumed samples: 5440000 | consumed tokens: 11141120000 | elapsed time per iteration (s): 0.31 | learning rate: 2.009E-05 | global batch size: 256 | lm loss: 2.949744E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.343 | TFLOPs: 29.21 | +7: iteration 21260/ 21553 | consumed samples: 5442560 | consumed tokens: 11146362880 | elapsed time per iteration (s): 0.31 | learning rate: 2.008E-05 | global batch size: 256 | lm loss: 2.928722E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.479 | TFLOPs: 28.55 | +7: iteration 21270/ 21553 | consumed samples: 5445120 | consumed tokens: 11151605760 | elapsed time per iteration (s): 0.31 | learning rate: 2.008E-05 | global batch size: 256 | lm loss: 2.938019E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.619 | TFLOPs: 29.11 | +7: iteration 21280/ 21553 | consumed samples: 5447680 | consumed tokens: 11156848640 | elapsed time per iteration (s): 0.32 | learning rate: 2.007E-05 | global batch size: 256 | lm loss: 2.932121E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 806.141 | TFLOPs: 28.22 | +7: iteration 21290/ 21553 | consumed samples: 5450240 | consumed tokens: 11162091520 | elapsed time per iteration (s): 0.30 | learning rate: 2.007E-05 | global batch size: 256 | lm loss: 2.949174E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 847.139 | TFLOPs: 29.66 | +7: iteration 21300/ 21553 | consumed samples: 5452800 | consumed tokens: 11167334400 | elapsed time per iteration (s): 0.31 | learning rate: 2.006E-05 | global batch size: 256 | lm loss: 2.908609E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.059 | TFLOPs: 29.30 | +7: iteration 21310/ 21553 | consumed samples: 5455360 | consumed tokens: 11172577280 | elapsed time per iteration (s): 0.31 | learning rate: 2.006E-05 | global batch size: 256 | lm loss: 2.938960E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 826.670 | TFLOPs: 28.94 | +7: iteration 21320/ 21553 | consumed samples: 5457920 | consumed tokens: 11177820160 | elapsed time per iteration (s): 0.32 | learning rate: 2.005E-05 | global batch size: 256 | lm loss: 2.930080E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.268 | TFLOPs: 28.40 | +7: iteration 21330/ 21553 | consumed samples: 5460480 | consumed tokens: 11183063040 | elapsed time per iteration (s): 0.30 | learning rate: 2.005E-05 | global batch size: 256 | lm loss: 2.956924E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 849.635 | TFLOPs: 29.74 | +7: iteration 21340/ 21553 | consumed samples: 5463040 | consumed tokens: 11188305920 | elapsed time per iteration (s): 0.30 | learning rate: 2.004E-05 | global batch size: 256 | lm loss: 2.915141E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.129 | TFLOPs: 29.41 | +7: iteration 21350/ 21553 | consumed samples: 5465600 | consumed tokens: 11193548800 | elapsed time per iteration (s): 0.31 | learning rate: 2.004E-05 | global batch size: 256 | lm loss: 2.939607E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.459 | TFLOPs: 29.14 | +7: iteration 21360/ 21553 | consumed samples: 5468160 | consumed tokens: 11198791680 | elapsed time per iteration (s): 0.30 | learning rate: 2.004E-05 | global batch size: 256 | lm loss: 2.929324E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.713 | TFLOPs: 29.54 | +7: iteration 21370/ 21553 | consumed samples: 5470720 | consumed tokens: 11204034560 | elapsed time per iteration (s): 0.31 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 2.944499E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 821.533 | TFLOPs: 28.76 | +7: iteration 21380/ 21553 | consumed samples: 5473280 | consumed tokens: 11209277440 | elapsed time per iteration (s): 0.31 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 2.945690E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 833.182 | TFLOPs: 29.17 | +7: iteration 21390/ 21553 | consumed samples: 5475840 | consumed tokens: 11214520320 | elapsed time per iteration (s): 0.32 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 2.930763E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 803.906 | TFLOPs: 28.14 | +7: iteration 21400/ 21553 | consumed samples: 5478400 | consumed tokens: 11219763200 | elapsed time per iteration (s): 0.31 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 2.971010E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 830.325 | TFLOPs: 29.07 | +7: iteration 21410/ 21553 | consumed samples: 5480960 | consumed tokens: 11225006080 | elapsed time per iteration (s): 0.31 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 2.934699E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.916 | TFLOPs: 29.16 | +7: iteration 21420/ 21553 | consumed samples: 5483520 | consumed tokens: 11230248960 | elapsed time per iteration (s): 0.30 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 2.967743E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 843.475 | TFLOPs: 29.53 | +7: iteration 21430/ 21553 | consumed samples: 5486080 | consumed tokens: 11235491840 | elapsed time per iteration (s): 0.31 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.960382E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.477 | TFLOPs: 29.11 | +7: iteration 21440/ 21553 | consumed samples: 5488640 | consumed tokens: 11240734720 | elapsed time per iteration (s): 0.30 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.952553E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 845.508 | TFLOPs: 29.60 | +7: iteration 21450/ 21553 | consumed samples: 5491200 | consumed tokens: 11245977600 | elapsed time per iteration (s): 0.30 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.929347E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.939 | TFLOPs: 29.40 | +7: iteration 21460/ 21553 | consumed samples: 5493760 | consumed tokens: 11251220480 | elapsed time per iteration (s): 0.31 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.913113E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 825.878 | TFLOPs: 28.91 | +7: iteration 21470/ 21553 | consumed samples: 5496320 | consumed tokens: 11256463360 | elapsed time per iteration (s): 0.30 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.937231E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 840.601 | TFLOPs: 29.43 | +7: iteration 21480/ 21553 | consumed samples: 5498880 | consumed tokens: 11261706240 | elapsed time per iteration (s): 0.31 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.946931E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.035 | TFLOPs: 29.13 | +7: iteration 21490/ 21553 | consumed samples: 5501440 | consumed tokens: 11266949120 | elapsed time per iteration (s): 0.31 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.949174E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.041 | TFLOPs: 29.20 | +7: iteration 21500/ 21553 | consumed samples: 5504000 | consumed tokens: 11272192000 | elapsed time per iteration (s): 0.30 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.934248E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 844.009 | TFLOPs: 29.55 | +7: iteration 21510/ 21553 | consumed samples: 5506560 | consumed tokens: 11277434880 | elapsed time per iteration (s): 0.31 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.964304E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 815.966 | TFLOPs: 28.56 | +7: iteration 21520/ 21553 | consumed samples: 5509120 | consumed tokens: 11282677760 | elapsed time per iteration (s): 0.31 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.959314E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.261 | TFLOPs: 28.82 | +7: iteration 21530/ 21553 | consumed samples: 5511680 | consumed tokens: 11287920640 | elapsed time per iteration (s): 0.31 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.947265E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 832.363 | TFLOPs: 29.14 | +7: iteration 21540/ 21553 | consumed samples: 5514240 | consumed tokens: 11293163520 | elapsed time per iteration (s): 0.31 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.936246E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.769 | TFLOPs: 29.22 | +7: iteration 21550/ 21553 | consumed samples: 5516800 | consumed tokens: 11298406400 | elapsed time per iteration (s): 0.31 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.936220E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 827.420 | TFLOPs: 28.97 | +0: [after training is done] datetime: 2022-11-29 18:59:46 +0: saving checkpoint at iteration 21553 to checkpoints_146moscareap +7: ------------------------------------------------------------------------------------------------------------ +7: valid loss at the end of training for val data | lm loss value: 2.839046E+00 | lm loss PPL: 1.709944E+01 | +7: ------------------------------------------------------------------------------------------------------------ +0: [2022-11-29 18:59:46,988] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step21553 is begin to save! +0: [2022-11-29 18:59:46,991] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:59:47,089] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:59:47,089] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:59:47,107] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:59:47,107] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:59:47,122] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:59:47,123] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:59:47,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:59:47,138] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:59:47,153] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:59:47,154] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:59:47,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:59:47,170] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:59:47,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:59:47,186] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:59:47,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:59:47,202] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:59:47,218] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:59:47,218] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:59:47,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:59:47,234] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:59:47,250] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:59:47,250] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/layer_13-model_00-model_states.pt... +0: [2022-11-29 18:59:47,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/layer_13-model_00-model_states.pt. +0: [2022-11-29 18:59:47,267] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:59:47,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:59:47,283] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/layer_15-model_00-model_states.pt... +0: [2022-11-29 18:59:47,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/layer_15-model_00-model_states.pt. +0: [2022-11-29 18:59:47,299] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/layer_16-model_00-model_states.pt... +0: [2022-11-29 18:59:47,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/layer_16-model_00-model_states.pt. +0: [2022-11-29 18:59:47,315] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/layer_17-model_00-model_states.pt... +0: [2022-11-29 18:59:47,331] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/layer_17-model_00-model_states.pt. +0: [2022-11-29 18:59:47,331] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/layer_19-model_00-model_states.pt... +0: [2022-11-29 18:59:47,332] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/layer_19-model_00-model_states.pt. +0: [2022-11-29 18:59:47,333] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_146moscareap/global_step21553/mp_rank_00_model_states.pt +0: [2022-11-29 18:59:47,333] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/mp_rank_00_model_states.pt... +0: [2022-11-29 18:59:47,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/mp_rank_00_model_states.pt. +0: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:59:47,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:59:47,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:59:47,425] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +6: [2022-11-29 18:59:47,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:59:47,425] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +6: [2022-11-29 18:59:47,425] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:59:47,425] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +3: [2022-11-29 18:59:47,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:59:47,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:59:47,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +5: [2022-11-29 18:59:47,427] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:59:47,427] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:59:47,427] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +2: [2022-11-29 18:59:47,427] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:59:47,427] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:59:47,427] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +5: [2022-11-29 18:59:47,427] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:59:47,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:59:47,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +1: [2022-11-29 18:59:47,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:59:47,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:59:47,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:59:47,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +2: [2022-11-29 18:59:47,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:59:47,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +7: [2022-11-29 18:59:47,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:59:47,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:59:47,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +2: [2022-11-29 18:59:47,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:59:47,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:59:47,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:59:47,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +2: [2022-11-29 18:59:47,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +7: [2022-11-29 18:59:47,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:59:47,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +7: [2022-11-29 18:59:47,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:59:47,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +7: [2022-11-29 18:59:47,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:59:47,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:59:47,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +5: [2022-11-29 18:59:47,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +7: [2022-11-29 18:59:47,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +5: [2022-11-29 18:59:47,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +4: [2022-11-29 18:59:47,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:59:47,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:59:47,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +6: [2022-11-29 18:59:47,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:59:47,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:59:47,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +1: [2022-11-29 18:59:47,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +6: [2022-11-29 18:59:47,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +1: [2022-11-29 18:59:47,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +3: [2022-11-29 18:59:47,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:59:47,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:59:47,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:59:47,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +4: [2022-11-29 18:59:47,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:59:47,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +3: [2022-11-29 18:59:47,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:59:47,430] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +5: [2022-11-29 18:59:47,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:59:47,430] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +5: [2022-11-29 18:59:47,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:59:47,430] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +1: [2022-11-29 18:59:47,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:59:47,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:59:47,430] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +4: [2022-11-29 18:59:47,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:59:47,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +3: [2022-11-29 18:59:47,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:59:47,430] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +3: [2022-11-29 18:59:47,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:59:47,430] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +1: [2022-11-29 18:59:47,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:59:47,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +5: [2022-11-29 18:59:47,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:59:47,430] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +5: [2022-11-29 18:59:47,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +2: [2022-11-29 18:59:47,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:59:47,430] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +2: [2022-11-29 18:59:47,431] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:59:47,431] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +7: [2022-11-29 18:59:47,431] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:59:47,431] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:59:47,431] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +4: [2022-11-29 18:59:47,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:59:47,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:59:47,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:59:47,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +5: [2022-11-29 18:59:47,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:59:47,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +1: [2022-11-29 18:59:47,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:59:47,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:59:47,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +7: [2022-11-29 18:59:47,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:59:47,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:59:47,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +2: [2022-11-29 18:59:47,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:59:47,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:59:47,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +3: [2022-11-29 18:59:47,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:59:47,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:59:47,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:59:47,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:59:47,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +3: [2022-11-29 18:59:47,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +6: [2022-11-29 18:59:47,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:59:47,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:59:47,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:59:47,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +6: [2022-11-29 18:59:47,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:59:47,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +4: [2022-11-29 18:59:47,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:59:47,434] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:59:47,434] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +2: [2022-11-29 18:59:47,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:59:47,434] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:59:47,434] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +6: [2022-11-29 18:59:47,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:59:47,434] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:59:47,434] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +6: [2022-11-29 18:59:47,435] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:59:47,435] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:59:47,435] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +1: [2022-11-29 18:59:47,435] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:59:47,435] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:59:47,435] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +1: [2022-11-29 18:59:47,435] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:59:47,435] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +5: [2022-11-29 18:59:47,435] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:59:47,435] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +5: [2022-11-29 18:59:47,435] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:59:47,436] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +7: [2022-11-29 18:59:47,436] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:59:47,436] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:59:47,436] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +7: [2022-11-29 18:59:47,436] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:59:47,436] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:59:47,436] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:59:47,436] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:59:47,436] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +0: [2022-11-29 18:59:47,436] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:59:47,436] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:59:47,436] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +7: [2022-11-29 18:59:47,436] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:59:47,436] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +0: [2022-11-29 18:59:47,436] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:59:47,436] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +0: [2022-11-29 18:59:47,436] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +0: [2022-11-29 18:59:47,436] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +3: [2022-11-29 18:59:47,436] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:59:47,436] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:59:47,436] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +3: [2022-11-29 18:59:47,436] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:59:47,436] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:59:47,436] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +3: [2022-11-29 18:59:47,436] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +5: [2022-11-29 18:59:47,436] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:59:47,436] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:59:47,436] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +1: [2022-11-29 18:59:47,437] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:59:47,438] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:59:47,438] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +0: [2022-11-29 18:59:47,438] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:59:47,438] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:59:47,438] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:59:47,438] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:59:47,438] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:59:47,439] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:59:47,439] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:59:47,439] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:59:47,439] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:59:47,439] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +0: [2022-11-29 18:59:47,439] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +0: [2022-11-29 18:59:47,439] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +0: [2022-11-29 18:59:47,439] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +4: [2022-11-29 18:59:47,439] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:59:47,439] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:59:47,439] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +4: [2022-11-29 18:59:47,439] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:59:47,439] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:59:47,439] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:59:47,439] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:59:47,439] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +4: [2022-11-29 18:59:47,439] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +6: [2022-11-29 18:59:47,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:59:47,451] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:59:47,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +6: [2022-11-29 18:59:47,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:59:47,452] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:59:47,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +0: [2022-11-29 18:59:47,459] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_146moscareap/global_step21553/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:59:47,459] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21553 is ready now! +0: successfully saved checkpoint at iteration 21553 to checkpoints_146moscareap +7: ------------------------------------------------------------------------------------------------------------ +7: test loss at the end of training for test data | lm loss value: 2.841546E+00 | lm loss PPL: 1.714224E+01 | +7: ------------------------------------------------------------------------------------------------------------ +END 2085658: Tue Nov 29 18:59:58 EET 2022 diff --git a/146m14b14b/sbatch_146m_oscar.sh b/146m14b14b/sbatch_146m_oscar.sh new file mode 100644 index 0000000000000000000000000000000000000000..b5aa1d6f1abaafc7ff9c96b656ef99f699969d34 --- /dev/null +++ b/146m14b14b/sbatch_146m_oscar.sh @@ -0,0 +1,160 @@ +#!/bin/bash +#SBATCH --nodes=8 +#SBATCH --ntasks-per-node=1 +#SBATCH --cpus-per-task=32 +#SBATCH --mem=256G +#SBATCH -p eap +#SBATCH -t 48:00:00 +#SBATCH --gpus-per-node=mi250:8 +#SBATCH --exclusive=user +#SBATCH --hint=nomultithread +#SBATCH --account=project_462000119 +#SBATCH -o logs/%j.out +#SBATCH -e logs/%j.err + +VARIANT=146moscareap + +# if run without sbatch, invoke here +if [ -z $SLURM_JOB_ID ]; then + mkdir -p logs + sbatch "$0" + exit +fi + +set -euo pipefail + +# symlink logs/latest.out and logs/latest.err +ln -f -s $SLURM_JOB_ID.out logs/latest.out +ln -f -s $SLURM_JOB_ID.err logs/latest.err + +KILL_SWITCH_PATH=kill-switch-$VARIANT +CHECKPOINT_PATH=checkpoints_$VARIANT +TENSORBOARD_PATH=tensorboard_$VARIANT +# Start from scratch +rm -rf "$CHECKPOINT_PATH" "$TENSORBOARD_PATH" + +# Data +VOCAB_FILE="gpt2/vocab.json" +MERGE_FILE="gpt2/merges.txt" +DATA_PATH="/scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document" + +PP_SIZE=1 +TP_SIZE=1 + +MICRO_BATCH_SIZE=4 +GRADIENT_ACCUMULATION_STEPS=1 +WORLD_SIZE=$((SLURM_GPUS_ON_NODE*SLURM_JOB_NUM_NODES)) +GLOBAL_BATCH_SIZE=$((MICRO_BATCH_SIZE*WORLD_SIZE*GRADIENT_ACCUMULATION_STEPS)) + +# Model parameters +source model_params.sh +MODEL_PARAM=("${PARAM_140M[@]}") +NHIDDEN=${MODEL_PARAM[0]} +FFN_HIDDEN_SIZE=${MODEL_PARAM[1]} +KV_SIZE=${MODEL_PARAM[2]} +NHEADS=${MODEL_PARAM[3]} +NLAYERS=${MODEL_PARAM[4]} +SEQ_LEN=2048 + +echo "Model parameters: d_model $NHIDDEN ffw_size $FFN_HIDDEN_SIZE kv_size $KV_SIZE n_heads $NHEADS n_layers $NLAYERS" + +SAVE_INTERVAL=1000 + +# Tokens: 11300000000 +# -> Samples: 5517578 +TRAIN_SAMPLES=5_517_578 + +OPTIMIZER_ARGS=" \ + --optimizer adam \ + --adam-beta1 0.9 \ + --adam-beta2 0.999 \ + --adam-eps 1e-8 \ + --lr 2e-4 \ + --min-lr 2e-5 \ + --lr-decay-style cosine \ + --lr-decay-samples $TRAIN_SAMPLES \ + --lr-warmup-samples 55_176 \ + --clip-grad 1.0 \ + --weight-decay 1e-1 \ + " + +GPT_ARGS=" \ + --num-layers $NLAYERS \ + --hidden-size $NHIDDEN \ + --num-attention-heads $NHEADS \ + --kv-channels $KV_SIZE \ + --ffn-hidden-size $FFN_HIDDEN_SIZE \ + --seq-length $SEQ_LEN \ + --max-position-embeddings $SEQ_LEN \ + --micro-batch-size $MICRO_BATCH_SIZE \ + --global-batch-size $GLOBAL_BATCH_SIZE \ + --train-samples $TRAIN_SAMPLES \ + --vocab-file $VOCAB_FILE \ + --merge-file $MERGE_FILE \ + --clip-grad 1.0 \ + --kill-switch-path $KILL_SWITCH_PATH \ + --bf16 \ + $OPTIMIZER_ARGS \ + " + +OUTPUT_ARGS=" \ + --log-interval 10 \ + --save-interval $SAVE_INTERVAL \ + --eval-interval 1000 \ + --eval-iters 1 \ + --tensorboard-dir $TENSORBOARD_PATH \ + --tensorboard-queue-size 5 \ + --log-timers-to-tensorboard \ + --log-batch-size-to-tensorboard \ + --log-validation-ppl-to-tensorboard \ + " + +ZERO_STAGE=0 + +mkdir -p ds_configs +DS_CONFIG_PATH="ds_configs/$SLURM_JOB_ID.json" + +cat < $DS_CONFIG_PATH +{ + "train_micro_batch_size_per_gpu": $MICRO_BATCH_SIZE, + "train_batch_size": $GLOBAL_BATCH_SIZE, + "gradient_clipping": 1.0, + "zero_optimization": { + "stage": $ZERO_STAGE + }, + "bf16": { + "enabled": true + }, + "steps_per_print": 2000, + "wall_clock_breakdown": false +} +EOF + +DEEPSPEED_ARGS=" \ + --deepspeed \ + --deepspeed_config $DS_CONFIG_PATH \ + --zero-stage $ZERO_STAGE \ + " + +CMD=" \ + Megatron-DeepSpeed/pretrain_gpt.py \ + --tensor-model-parallel-size $TP_SIZE \ + --pipeline-model-parallel-size $PP_SIZE \ + $GPT_ARGS \ + $OUTPUT_ARGS \ + --save $CHECKPOINT_PATH \ + --load $CHECKPOINT_PATH \ + --data-path $DATA_PATH \ + --data-impl mmap \ + --split 949,50,1 \ + $DEEPSPEED_ARGS \ + " + +echo $CMD + +echo "START $SLURM_JOBID: $(date)" + +# bash launch_srun.sh $CMD +srun --label launch.sh $CMD + +echo "END $SLURM_JOBID: $(date)" diff --git a/146m14b14b/tensorboard/events.out.tfevents.1669733427.nid006772.22469.0 b/146m14b14b/tensorboard/events.out.tfevents.1669733427.nid006772.22469.0 new file mode 100644 index 0000000000000000000000000000000000000000..bc8d2f3e305b01753f5b91956d6d3027f2d18bea --- /dev/null +++ b/146m14b14b/tensorboard/events.out.tfevents.1669733427.nid006772.22469.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6b8dd036c4e6877684fb8b3bb9ed67d2a0d422aa10e075e64ac4d8b2c0d8adc +size 40 diff --git a/146m14b14b/tensorboard_146moscareap/events.out.tfevents.1669734316.nid005067.119617.0 b/146m14b14b/tensorboard_146moscareap/events.out.tfevents.1669734316.nid005067.119617.0 new file mode 100644 index 0000000000000000000000000000000000000000..e046f3a4b414f5ce206c518956233558e766e016 --- /dev/null +++ b/146m14b14b/tensorboard_146moscareap/events.out.tfevents.1669734316.nid005067.119617.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9acc7a846a7ea82d4677e6a9579cfcfcb194566f0c533194334c1be935b98b2d +size 38441355 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..afe57c3c04c4da5520ab47ae6e993751dd9a2495 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:394488d6e14f8f7385e03c0012e40a9e708a78a6edfb5bada587d9db60afd712 +size 205568023 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..356694e37b5d63f054844f59813aff3b7afea367 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f391b5b27ad1384e7471108b34f7c5301ad920b772b5cfc730723ad3c59120e +size 205568162 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..300d6879dd9cd75eb51969b501a0c85b974923b4 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3e0924abc436332126fa7bc272be4ad842ca984fb6c245e81ebb8c064115fd5 +size 205568226 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..eee81bbc18c921da994a8984c257db5c21cd3a8e --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de7c0d03fcb3feb836bb61104494ea8f5056c842ca040adfe3216008f22b6637 +size 205568226 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..181e3f6ef4c266895782eae47e4c77715c3b154f --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd4239652034d17821f68d85e2db04f49ab11fef591c2858151d006ead5a7da5 +size 205568162 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fd3be5d75d0f6139adb48b9d50dcbd8578c9d3ec --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8f5c96ee284776705948cdadd6e1e965b7703f32823369b6acdc8e652a2cc31 +size 205568162 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..80077ee669db8f9835561f3730a734d09232aa93 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:179cce12cf6dc10b49782538fd7614e8022c459760c232ca376c21ee60ab59c0 +size 205568162 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1db251cb48f021f00865fa9036645bad48fc6a26 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83e8b32817671a8ad12f02c7babd81286aa3e87c425872c50c73d333207ec8dc +size 205567970 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..16efd995837565f8f923b8888c55fd3270708851 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1393710c5f599b627f864c14428371bffda0fc3475d6a12b996b93efc30581e +size 205568226 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..443a00f8ba49602c72b5ad8b261e9ae3ba6678bc --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35ec1d51729264e87838e116f7e3d568d7954154c0cd8b7e4b3dc13c91de07fd +size 205568226 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b36510641875113175741196b0f3f5ec186e64e3 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bb17a6ab0eb4d92201992078d5e76fd436bbdf958526a488b46b927df2eccdd +size 205568226 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..416430017e49e3f09bf3945e1e69fb01501eac2b --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5658015939c74c9e97c16901d14237ce63a6666b2447d504b991ab21b7273172 +size 205568151 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4499362c387b34b805c01df115fed04066564688 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb662eeca3f5f40b405aee667441be0ac90813394e2e8eaf5d637fccd1cd2cc7 +size 205568226 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..584e4414aa763d758c0c1f8a85c8498ffbc4e5aa --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ba8e160d0948aad8380a51b57b4cc266ea27f2721a5c65e96110dc1a5121891 +size 205568034 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..53726e3de3ee6a8b9065b6fa0ceae62cf807957a --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a6904c524448ecacd7ee671dd429ea04d98bcc224f7854820a85a83ae1ecdb9 +size 205568162 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4224e81bd15d67996de5f617bd1d1f2119d8a449 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80f3f9c1c232d1267e8ce74997ba693b2d0cff17a3017fcfd90e3564cf0ecc6b +size 205568098 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1559de869de8d5f7843dfbffdba68d8b594f1baf --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdde2119e6916e7bacf6fabac5bc8be506a92ad4d3913212c911d6dda47942a1 +size 205568226 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f224615fccf7475ec16c181eced5a998c7f8d595 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:503ea4c6fe3a413357c2d6931ad656c969f12275cd20286f33ed2391daef4c3b +size 205568226 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..055269e21c2508f100e58f81615257f18f57cf3e --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a59974d88ef692a6d7e24c4cb59d2a0814e83bf2127da904472e30d185c593ee +size 205568034 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7ab183f7fa323d29ad9ff02bc7a16c5e134afb52 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7bc21147838ddd04e4b560b81beb278890133019f659b8f4e2cd6c1ed9211aa +size 205568162 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9a156aa9938db2fb04741c2e1a3e87bd2c44606d --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da8e6ddb86743e36fc0132485d2ae8768ad14c2bfc06f0522bd6fdbb0c2bcd7d +size 205568226 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8acce13add0b9ee99d6bd8895e14a8d0c82cb9c5 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10798c3ea64f1cb1851f07524f943db3fae460c11a7bd186ee4a1d5e834c5e07 +size 205568098 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..96572844111369da055a37f192cf848a6a888fa3 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7258d68f8c1e0a610cf147d24b1a7c61c95e1d312d166d1c005d4960c0e218e2 +size 205568151 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..99c853deb7b26dfe001e9b971dc5861a468f1b83 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e4ee687087914927a3d834de8e3c54049d9e157423bde4d179b735f4c280206 +size 205568226 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3d8b4ed495e1679c01b44e2e313519a93e012b6d --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29b5738b7c31600d3bd6705461d067d0c41bbd2d631ca198c2414fc38bb300e1 +size 205568162 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..154f057ae71cccb04ce2516300640a63a08f68db --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d67c52558858741c7202fc4bf63adba5639c1bdf63f82721bba2099ebd5d1fa +size 205568226 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..34e795689de9b7e2f758d5d7ebd3edade6b68f20 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd3afb9dc465b44ee07bc4acef807d94f125e78c762febf3af43e60c7e19c28f +size 205568034 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dcfbd2e170b12280f6cad6f7dae1f8759db9597c --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:413595620a6ee63f0234d3212f3a30179032218bdadf2f2347bc2ba3a1e80cc4 +size 205568162 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..de8dda075e85d5a6ad7508382ddc9003da7a1b60 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0a636d0dc328ca2de221df16139b86dfe5170d41f47b7f3904b4b9ba4838618 +size 205568290 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a94dd237d64750884faeba48eb9798d472977174 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57274cfc5e6cb6d56012c5e1332f84309b8594c0b8660f7059f6da3e938903ce +size 205568226 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f4c295ee52cb0fb3b4340ddb038c0398186dd81f --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8c97a08629fc813d0c03fc9e3c60f9a50b97a00f2a4df1c1b05e609085e4b08 +size 205568098 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c02df8d4058bb5f50077ab8b4fc75f7106ee2db3 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5e909e1561a8edd0b484205bca6b591e6eff3ecce8023f3f0fc50f7fa110454 +size 205568162 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b506c2b228eb6414521aad16ceff8a8048d444a1 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:003458877d0ac8924fb442ed80dc4c66ffccfacee15be35a8e1e4754e7edb570 +size 205568098 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..db22ad983d250e195ad436b3e9bcb6b698a4f216 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88494491aab78bb971c06849596c68583218686e5d2a13b4ffdbbf958632053f +size 205568215 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c17cd5a325e9eb72ae2697ef82c1679f5c5ccabc --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43ba3fd405d70f84de0e59b9abe7e938b33f32e10353fafb6754a3875d111151 +size 205568162 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..99d075364493639ebd221458dd0872e02ec46ab9 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3929936cd0541c579e1b696f4fb4fb2eccd41b260fddf11b1b4df8f3ed70b941 +size 205568354 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..58a9f045d0fbc511e9769ff8165297b05e5c085a --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b99a16ba4a7eb8f9aa42e3569f5e77fa8fceaaa281e032da2c868a80ce358506 +size 205568162 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..be4725f8cdc672bf5d8cc011de48af53b91ec935 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9e6c8040c4ced7dff3fb97183300aa1cb090afdc9873905784c16502139acf7 +size 205568034 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..98b3653316d6bb6875befcbbb9a1780025439f95 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a47051182d27c2b5b7d3d1e75b667af35014a78b70e2cd26fcbd1746456b9a13 +size 205568226 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..074bbddc41a30a0da07458bf9d1769eb46173e42 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47d06118b8a3de79c28bc9592608b248f50eac5a318938de092d329384a80435 +size 205568226 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2bf97feebe3869e3963795a3ba527a8825580f39 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:632c62f30c49032a16916efadc2bec99a2fadbe90fe89ba36c08b5ca18c54cef +size 205568162 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f257ad1e7af0756cb5dd6a03422c1b2957390757 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0a2e4ffde0975905e0b88796daf82239630720f5f02f6f4d93c1e58f4a56ba7 +size 205568162 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7d99163fbd6755b7bca44c21d94c69bf61d93077 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e62ccebba6e3c61e96761e63e60b69ebb2b2d2176896adeacfaa0e4acc4d898 +size 205568034 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..db8b4ff2369ce2deefd70f8b6f8bcd5225a1cd1c --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1df156ead88a5ca2b0283ea5ab86b880094cd7b0a7bd01945a559652f03c3c0 +size 205568290 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a86ea434da7d0345d286a1f73d5597cb41a58dfa --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1937a19af5684961fd43e83b52128a7c6186e8f0099c84715d95a7f6d442d88f +size 205568023 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..185232bd0f6059a85c33fbfaa67d0d87e92281ef --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58dec9072ff7a2c20cfff8bf373483cc50ffaf3794ef910f4bdc2ab1ce08860f +size 205568162 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..db9acb63ec62c85ca1f465645d941255d65cdd3d --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1757bc23f6db59cdb326b1cb6c77fd070d84b8f55cc91ad66ad70063d386d5d +size 205568226 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..88d1a1af66b0b1443d9d0f0257ef4a62704ad76a --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2c93cf7dce49cd34453b14a9062a5295f276fb0e844e44f710b5c7cd7d62185 +size 205568290 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8f0c4bfad9c0ea1bab0ab81fa54985821a4b5336 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8042d47013a66b53e3dd839bcbbc6018e140fbd0470f74a1759abedb39ba1adf +size 205568034 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..70b0d8d92402c9efc2422c341f2dce2c069f3918 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19d3a417a64155b4173489c40849b152372a8b2a87ba6186a8bf9742b0e6d083 +size 205568226 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a912029f545d67c52169b951182a11b027bf8e4 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a80576bc150591a02a6241318e2d2c8c16b1584b26faa48b941e7426d9068f1 +size 205568162 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9b9afe235aa46c41fd81aa629060c67c8ad1e17a --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e64e06fbc1d7632d25a477114b1a0764bceb27e95acd16e67fa1bcdea29b6b3e +size 205568162 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..84c35c22940c81f9204bc1b7da2b1b18b522065d --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46981443463b4d4314c1716f115fedac575f134d61c395142cfe06c8c321a127 +size 205568290 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f6857d6a0200c526a0c5526bfc2340aefb349440 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d9414fdbda47ff7a4fbdb3490a9ea64bd6edab60208d62120372bc73fd0c7c9 +size 205568098 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..34c05f352608e05ae769021fa05b961f84af064d --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e94bfe0554d904a8272370ee3069423ee71363edcb2d062cd19cc86c73511cdd +size 205568226 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..afedfb7dacb2ecd17d44c2137abcef43e609df2e --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64d8f69d01f18f606abd010405ca59c358e9f93be5f25989baa3d9992c52541b +size 205568023 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c764b1d3b8fdddc504bb762ce97061dea10da0af --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a8f47cee78b1b35b4d76b9ac6763ffe408ba789badd155ff68b09889dc966a5 +size 205568162 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..af39619d7260d208f07970ac2a06c9efb010a543 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9fab2217c9acfb6304f9a4a7e7fd6cbd02751cb6a5b591e7e78108014f9b5f8 +size 205568098 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cd23907e0ac85bf634a357c03ef48b3ad44cb2ed --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:256f14381510a3b806b9ff941d21f986971024d2e5788d7da6459f80d01ffcd7 +size 205568290 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cdac27e94b7db1c82ea8239362ba79d5bb780a4e --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:839704406714141243813f10218daf504f97e4bbe4fdb1401be6bab286cc41f4 +size 205568034 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..22553cb7911b22d21ba7b13bb6088593573d7f52 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a5fd9365433c17fb1eba6fe5c4c4c6fbcd6341f33437cab48aeb552844a29f4 +size 205568151 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..eb6a68231be43131076513613ba708d22d37eba9 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e64357f803f29d0399f945562bb2f016d59113f0e939aba7e7f1f5f01d22a16b +size 205568151 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fddf6831c37ec13b4bb99243deed5caeacdd7620 --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:198ab942e7cea2e97cc817e72c37bd707dea5100a512d430be9625ec48e85c6a +size 205568151 diff --git a/1b11b51b5/global_step2891/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt b/1b11b51b5/global_step2891/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..642f2010e0545a23d60f6a992d24baec7a84c3af --- /dev/null +++ b/1b11b51b5/global_step2891/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cdd80488ce3a63533f74c14b979c871afa1d64e8376e349de598316332c4e5f +size 205568151 diff --git a/1b11b51b5/global_step2891/layer_01-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_01-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7517d2338afa2b46980c66f4a4e839976521d127 --- /dev/null +++ b/1b11b51b5/global_step2891/layer_01-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0727f32a423b7c8e7aff3d6a421cc31458df04c7af48784e7034a07aaa27c2d2 +size 187630851 diff --git a/1b11b51b5/global_step2891/layer_03-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_03-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4c7977a4bf0c1a6ed8dac7f5988f78f0d9484cf9 --- /dev/null +++ b/1b11b51b5/global_step2891/layer_03-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da6a1feccebbedbc2542118d9a6526ef3b5c828d9c60b76ecdafd00cabe4bf36 +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_04-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_04-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f6023d7a82315cfb7f68227d03e88875a7e91727 --- /dev/null +++ b/1b11b51b5/global_step2891/layer_04-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64afaa66c5343d2c86db409bd49969c6028e71a4470fca286ae629c96cbb3210 +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_05-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_05-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..488e35d798ae36244c5381faa02c507a923f1a6a --- /dev/null +++ b/1b11b51b5/global_step2891/layer_05-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61594639ac0cf14e81e982c68ecf1a590a7eac5c0bb032be6b2a1b01ba98620e +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_06-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_06-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5128772a1a738aee594f21c63fb102b3009e6217 --- /dev/null +++ b/1b11b51b5/global_step2891/layer_06-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:762ccabb20a1e860c03c2d6846f4342b9fa48f7d298e5d9ed9c4f029e8ed92a8 +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_07-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_07-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..badc4a2c619b1cc603f4e9471733d25f11a33e5e --- /dev/null +++ b/1b11b51b5/global_step2891/layer_07-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7c29943003d28c94a06e473f46f5cd12f0000566cb2ffbaae9ccdd5505d4cac +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_08-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_08-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..78534799d4f795af9c3360e830d30bb91d7ec4df --- /dev/null +++ b/1b11b51b5/global_step2891/layer_08-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67fdc03dd54177f944cef9939ecfa14f1200ed6ee0890265ff29e0f1188b5671 +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_09-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_09-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4c16476cdd634949dbd2db50a917e6bc5853f8b9 --- /dev/null +++ b/1b11b51b5/global_step2891/layer_09-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c81fb0f151c09764b1b563b4de8dc9bd9706935a30acf9cbdcd3738074cf81e +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_10-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_10-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..36b0ca882ad4403653b61239325dd18b69402aa0 --- /dev/null +++ b/1b11b51b5/global_step2891/layer_10-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e26bd11bdc0285d9cc92fbf23a710f40cc271eb6cb19c5767bc097b985cf539b +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_11-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_11-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..04cad5ba95ac7419267aa4154713d6b0b2ea6135 --- /dev/null +++ b/1b11b51b5/global_step2891/layer_11-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e4a79223c23b7250b6fcf7908ee9808e0cdc426f98397d1ee16181a7b43da77 +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_12-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_12-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..79d53481d09e9af489b9d2aa8a043c3c63a9db29 --- /dev/null +++ b/1b11b51b5/global_step2891/layer_12-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78781bf7d1466f40fd253be3338d4e136664bf96eeb409f3efeb775356b4c615 +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_13-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_13-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d518652dc586944448ef571a55672b593c99a42f --- /dev/null +++ b/1b11b51b5/global_step2891/layer_13-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7ed436c578d75015fa2b7c77897a77cd4b9c9c7ed1f5e74a96834aa8dc77c63 +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_14-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_14-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e9598112d541386603bb14bce9a32cc330550d59 --- /dev/null +++ b/1b11b51b5/global_step2891/layer_14-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35578e3350ef43bffe9d38bf25fc19e591b8aaee4bfaa90af094d5b9032e65d4 +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_15-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_15-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1c63227889af5f3fe4f2a3c62f8a44abcc066d77 --- /dev/null +++ b/1b11b51b5/global_step2891/layer_15-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b0a3b0a67c80c5a92eae94e95e058c032974baf23c0ced482ccdd76cbf61e1c +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_16-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_16-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..562ed282190c11ab58e92934392e13b169bf32c0 --- /dev/null +++ b/1b11b51b5/global_step2891/layer_16-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70680811cabc0a090a290312913ce72722769bc3770d90107efa430e5f93494e +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_17-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_17-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b871120c0f016b60f8c8cf7b82f0e941db06ce68 --- /dev/null +++ b/1b11b51b5/global_step2891/layer_17-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c53be967a4fabb0747ae08851437a1fcd65b315a020a15359e3591b1930e66b +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_18-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_18-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..524171a7528d8c4968d1767cc832550009e43f03 --- /dev/null +++ b/1b11b51b5/global_step2891/layer_18-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d27556e802a0e63cfd8e6739306648625832810a0fd7dad9277f1865db96256 +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_19-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_19-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bfc1845a5ac4c006202f2c70d207042b42d16574 --- /dev/null +++ b/1b11b51b5/global_step2891/layer_19-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b0b61eecadce0494770d03445c8ee4090d386b7c3a957e4c4aee9227c8aeb15 +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_20-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_20-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f40a40315bcfa15da368e61b5f1862ea8c41f49a --- /dev/null +++ b/1b11b51b5/global_step2891/layer_20-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5022598f45f235e3db4bd4edb2d6410f9494e2bca58671f5ffc4491adf60562 +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_21-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_21-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..61e711e1a7f12e087b93f1138f26bd0d29a15a5a --- /dev/null +++ b/1b11b51b5/global_step2891/layer_21-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df40ea07a5b86db88d6a34b60633ed3833c848110ba5c7d07bcc2e7f319de903 +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_22-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_22-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3c7049a0db623f3b8a4bda66630323a8c7882360 --- /dev/null +++ b/1b11b51b5/global_step2891/layer_22-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acb90314634e3c74350a70b2749cf677f6003af5d44e48a33d88b6d99a0af13d +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_23-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_23-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2824b69041d32136d20858be1a2f2c065c0d22e3 --- /dev/null +++ b/1b11b51b5/global_step2891/layer_23-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce15d68c591a7f113430e6f1bede94f275429dfdf29b6f393f2e85fd756620a5 +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_24-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_24-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e4d7f678e92b4725d2e525fca0ab8b5d06a30421 --- /dev/null +++ b/1b11b51b5/global_step2891/layer_24-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e49f74ee82a213b8a749964d3d1d115c3ba05b211c7d6b6870d13d0b5887634c +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_25-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_25-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f5ad785881282a55d56b90482f4552882df66c36 --- /dev/null +++ b/1b11b51b5/global_step2891/layer_25-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb4caae317c456429651003bfcd654d1d14adbb7db1ad87546a727105000c0aa +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_26-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_26-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..721b0a479d33ee5c4857f783c9911292c8ca4b54 --- /dev/null +++ b/1b11b51b5/global_step2891/layer_26-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1799f9751f62a538e5a6032f83cf0f09d836bd8a4105a049f00728c1abe58ad +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_27-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_27-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a455e6360192d9cff601304b7ed19a49d01c09b5 --- /dev/null +++ b/1b11b51b5/global_step2891/layer_27-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac114c548f160f88a2a2a8ec731b55455a205adb043e9324a779c213d7cc5bd6 +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_28-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_28-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c281aaff530c464038dd205b38b5b4a34aa3a44e --- /dev/null +++ b/1b11b51b5/global_step2891/layer_28-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38f03e7117d0b45b08cc80415d59ca6129dc646efcec062138fecc58f55d7032 +size 77121283 diff --git a/1b11b51b5/global_step2891/layer_30-model_00-model_states.pt b/1b11b51b5/global_step2891/layer_30-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..84b4ca22658e6cfb46aa1daa66af1f01c766a0df --- /dev/null +++ b/1b11b51b5/global_step2891/layer_30-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea8ec59c4a610d683c32525f4b268a7d4e32d515eabff8188c9867012dc9efcb +size 8387 diff --git a/1b11b51b5/global_step2891/mp_rank_00_model_states.pt b/1b11b51b5/global_step2891/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8efa600b3ea927c6e4d65a32dc31d1beb99f3b2d --- /dev/null +++ b/1b11b51b5/global_step2891/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:512bfe46ff351d5ad0d3cf59d40f6ab915b89e9f306aa08897602ab017a621cc +size 43507 diff --git a/1b11b51b5/launch.sh b/1b11b51b5/launch.sh new file mode 100755 index 0000000000000000000000000000000000000000..6c3445845a5dae614feb4b8a1206322cd7bd9050 --- /dev/null +++ b/1b11b51b5/launch.sh @@ -0,0 +1,53 @@ +#!/bin/bash + +# Launch script using torch.distributed.run(). Used by slurm +# scripts, don't invoke directly. + +# Samuel's fix for apparent error in SLURM initialization +if [ $SLURM_LOCALID -eq 0 ]; then + rm -rf /dev/shm/* + rocm-smi || true +else + sleep 2 +fi + +export NCCL_SOCKET_IFNAME=hsn0,hsn1,hsn2,hsn3 +export OMP_NUM_THREADS=$SLURM_CPUS_PER_TASK +export FI_CXI_DEFAULT_CQ_SIZE=131072 + +# debugging (noisy) +#export NCCL_DEBUG=INFO +#export RCCL_KERNEL_COLL_TRACE_ENABLE=1 +#export NCCL_DEBUG_SUBSYS=INIT,COLL + +module --quiet purge +module load cray-python + +module load CrayEnv +module load PrgEnv-cray/8.3.3 +module load craype-accel-amd-gfx90a +module load cray-python + +module use /pfs/lustrep2/projappl/project_462000125/samantao-public/mymodules +module load suse-repo-deps/sam-default +module load rocm/sam-5.2.3.lua +module load rccl/sam-develop.lua +module load aws-ofi-rccl/sam-default.lua + +source venv/bin/activate + +MASTER_NODE=$(scontrol show hostnames "$SLURM_JOB_NODELIST" | head -n 1) +MASTER_PORT=9999 + +echo "Launching on $SLURMD_NODENAME ($SLURM_PROCID/$SLURM_JOB_NUM_NODES)," \ + "master $MASTER_NODE port $MASTER_PORT," \ + "GPUs $SLURM_GPUS_ON_NODE," \ + "CUDA: $(python -c 'import torch; print(torch.cuda.is_available())')" + +python -u -m torch.distributed.run \ + --nnodes $SLURM_JOB_NUM_NODES \ + --nproc_per_node $SLURM_GPUS_ON_NODE \ + --node_rank=$SLURM_PROCID \ + --master_addr $MASTER_NODE \ + --master_port $MASTER_PORT \ + "$@" diff --git a/1b11b51b5/logs/2085640.err b/1b11b51b5/logs/2085640.err new file mode 100644 index 0000000000000000000000000000000000000000..543f47ad23550c81bd6dd097904d1eabd56b2907 --- /dev/null +++ b/1b11b51b5/logs/2085640.err @@ -0,0 +1,482 @@ +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module scaled_upper_triang_masked_softmax_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module scaled_upper_triang_masked_softmax_cuda... +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module scaled_masked_softmax_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module scaled_masked_softmax_cuda... +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module fused_mix_prec_layer_norm_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module fused_mix_prec_layer_norm_cuda... +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +2: Successfully preprocessed all matching files. +2: Successfully preprocessed all matching files. +2: Successfully preprocessed all matching files. +4: Successfully preprocessed all matching files. +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: +1: +1: +1: +1: +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja... +2: Building extension module utils... +2: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: +4: +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: +3: +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: +3: +3: +3: +2: Loading extension module utils... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: +5: +5: +5: +5: +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: +6: +6: +6: +6: +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: +7: +7: +7: +7: +7: +7: +3: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja... +3: Building extension module utils... +3: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +3: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +3: Loading extension module utils... +3: Loading extension module utils... +3: Loading extension module utils... +3: Loading extension module utils... +3: Loading extension module utils... +3: Loading extension module utils... +3: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +7: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +7: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +6: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: No modifications detected for re-loaded extension module utils, skipping build step... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +2: +2: Loading extension module utils...Loading extension module utils... +0: Loading extension module utils... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +2: +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: No modifications detected for re-loaded extension module utils, skipping build step... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: +2: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: +6: +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +4: +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +6: +6: Loading extension module utils...Loading extension module utils... +6: +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: +1: +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: +1: +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +5: +5: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +5: +5: Loading extension module utils...Loading extension module utils... +5: +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +1: +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +3: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +3: +3: +3: Loading extension module utils...Loading extension module utils... +3: +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +7: +7: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +7: +7: +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/utils.py:349: UserWarning: Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings +0: warnings.warn("Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings") diff --git a/1b11b51b5/logs/2085640.out b/1b11b51b5/logs/2085640.out new file mode 100644 index 0000000000000000000000000000000000000000..c896aa2f766842fecceebd12ae61be59fb7ea75a --- /dev/null +++ b/1b11b51b5/logs/2085640.out @@ -0,0 +1,2150 @@ +Model parameters: d_model 1792 ffw_size 7168 kv_size 128 n_heads 14 n_layers 26 +Megatron-DeepSpeed/pretrain_gpt.py --tensor-model-parallel-size 1 --pipeline-model-parallel-size 1 --num-layers 26 --hidden-size 1792 --num-attention-heads 14 --kv-channels 128 --ffn-hidden-size 7168 --seq-length 2048 --max-position-embeddings 2048 --micro-batch-size 4 --global-batch-size 256 --train-samples 740_269 --vocab-file gpt2/vocab.json --merge-file gpt2/merges.txt --loss-scale 12 --clip-grad 1.0 --kill-switch-path kill-switch-1b1oscar --bf16 --optimizer adam --adam-beta1 0.9 --adam-beta2 0.999 --adam-eps 1e-8 --lr 2e-4 --min-lr 2e-5 --lr-decay-style cosine --lr-decay-samples 740_269 --lr-warmup-samples 7403 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_1b1oscar --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_1b1oscar --load checkpoints_1b1oscar --data-path /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2085640.json --zero-stage 0 +START 2085640: Tue Nov 29 17:48:36 EET 2022 +0: +0: +0: ======================= ROCm System Management Interface ======================= +0: ================================= Concise Info ================================= +0: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +0: 0 42.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 2 40.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 3 37.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 4 41.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 6 43.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: ================================================================================ +0: ============================= End of ROCm SMI Log ============================== +5: +5: +5: ======================= ROCm System Management Interface ======================= +5: ================================= Concise Info ================================= +5: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +5: 0 47.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 2 42.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 4 41.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 6 39.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: ================================================================================ +5: ============================= End of ROCm SMI Log ============================== +4: +4: +4: ======================= ROCm System Management Interface ======================= +4: ================================= Concise Info ================================= +4: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +4: 0 42.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 2 41.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 4 42.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 6 36.0c 98.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: ================================================================================ +4: ============================= End of ROCm SMI Log ============================== +3: +3: +3: ======================= ROCm System Management Interface ======================= +3: ================================= Concise Info ================================= +3: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +3: 0 41.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 2 36.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 3 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 4 40.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 6 42.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: ================================================================================ +3: ============================= End of ROCm SMI Log ============================== +1: +1: +1: ======================= ROCm System Management Interface ======================= +1: ================================= Concise Info ================================= +1: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +1: 0 49.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 2 41.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 4 42.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 6 42.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: ================================================================================ +1: ============================= End of ROCm SMI Log ============================== +2: +2: +2: ======================= ROCm System Management Interface ======================= +2: ================================= Concise Info ================================= +2: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +2: 0 43.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 2 43.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 4 43.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 6 44.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: ================================================================================ +2: ============================= End of ROCm SMI Log ============================== +7: +7: +7: ======================= ROCm System Management Interface ======================= +7: ================================= Concise Info ================================= +7: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +7: 0 43.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 1 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 2 42.0c 99.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 4 45.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 6 41.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: ================================================================================ +7: ============================= End of ROCm SMI Log ============================== +6: +6: +6: ======================= ROCm System Management Interface ======================= +6: ================================= Concise Info ================================= +6: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +6: 0 40.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 2 39.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 4 39.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 6 41.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: ================================================================================ +6: ============================= End of ROCm SMI Log ============================== +4: Launching on nid005020 (4/8), master nid005016 port 9999, GPUs 8, CUDA: True +6: Launching on nid005022 (6/8), master nid005016 port 9999, GPUs 8, CUDA: True +7: Launching on nid005023 (7/8), master nid005016 port 9999, GPUs 8, CUDA: True +3: Launching on nid005019 (3/8), master nid005016 port 9999, GPUs 8, CUDA: True +0: Launching on nid005016 (0/8), master nid005016 port 9999, GPUs 8, CUDA: True +2: Launching on nid005018 (2/8), master nid005016 port 9999, GPUs 8, CUDA: True +5: Launching on nid005021 (5/8), master nid005016 port 9999, GPUs 8, CUDA: True +1: Launching on nid005017 (1/8), master nid005016 port 9999, GPUs 8, CUDA: True +0: using world size: 64, data-parallel-size: 64, tensor-model-parallel size: 1, pipeline-model-parallel size: 1 +0: accumulate and all-reduce gradients in fp32 for bfloat16 data type. +0: using torch.bfloat16 for parameters ... +0: ------------------------ arguments ------------------------ +0: abort_on_unmet_fused_kernel_constraints ......... False +0: accumulate_allreduce_grads_in_fp32 .............. True +0: adam_beta1 ...................................... 0.9 +0: adam_beta2 ...................................... 0.999 +0: adam_eps ........................................ 1e-08 +0: adlr_autoresume ................................. False +0: adlr_autoresume_interval ........................ 1000 +0: apply_query_key_layer_scaling ................... True +0: apply_residual_connection_post_layernorm ........ False +0: attention_dropout ............................... 0.1 +0: attention_softmax_in_fp32 ....................... False +0: bert_binary_head ................................ True +0: bert_load ....................................... None +0: bf16 ............................................ True +0: bias_dropout_fusion ............................. True +0: bias_gelu_fusion ................................ True +0: biencoder_projection_dim ........................ 0 +0: biencoder_shared_query_context_model ............ False +0: block_data_path ................................. None +0: checkpoint_activations .......................... False +0: checkpoint_in_cpu ............................... False +0: checkpoint_num_layers ........................... 1 +0: clip_grad ....................................... 1.0 +0: codecarbon_dir .................................. None +0: consumed_train_samples .......................... 0 +0: consumed_train_tokens ........................... 0 +0: consumed_valid_samples .......................... 0 +0: contigious_checkpointing ........................ False +0: cpu_optimizer ................................... False +0: cpu_torch_adam .................................. False +0: curriculum_learning ............................. False +0: data_impl ....................................... mmap +0: data_parallel_size .............................. 64 +0: data_path ....................................... ['/scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document'] +0: dataloader_type ................................. single +0: DDP_impl ........................................ local +0: decoder_seq_length .............................. None +0: deepscale ....................................... False +0: deepscale_config ................................ None +0: deepspeed ....................................... True +0: deepspeed_activation_checkpointing .............. False +0: deepspeed_config ................................ ds_configs/2085640.json +0: deepspeed_mpi ................................... False +0: distribute_checkpointed_activations ............. False +0: distributed_backend ............................. nccl +0: embed_layernorm ................................. False +0: embedding_path .................................. None +0: encoder_seq_length .............................. 2048 +0: eod_mask_loss ................................... False +0: eval_interval ................................... 1000 +0: eval_iters ...................................... 1 +0: eval_only ....................................... None +0: evidence_data_path .............................. None +0: exit_duration_in_mins ........................... None +0: exit_interval ................................... None +0: ffn_hidden_size ................................. 7168 +0: finetune ........................................ False +0: fp16 ............................................ False +0: fp16_lm_cross_entropy ........................... False +0: fp32_residual_connection ........................ False +0: gigaflos_no_embeds .............................. 0 +0: global_batch_size ............................... 256 +0: glu_activation .................................. None +0: hidden_dropout .................................. 0.1 +0: hidden_size ..................................... 1792 +0: hysteresis ...................................... 2 +0: ict_head_size ................................... None +0: ict_load ........................................ None +0: img_dim ......................................... 224 +0: indexer_batch_size .............................. 128 +0: indexer_log_interval ............................ 1000 +0: inference ....................................... False +0: init_method_std ................................. 0.02 +0: init_method_xavier_uniform ...................... False +0: initial_loss_scale .............................. 4294967296 +0: kill_switch_path ................................ kill-switch-1b1oscar +0: kv_channels ..................................... 128 +0: layer_norm_fusion ............................... True +0: layernorm_epsilon ............................... 1e-05 +0: lazy_mpu_init ................................... None +0: load ............................................ checkpoints_1b1oscar +0: local_rank ...................................... None +0: log_batch_size_to_tensorboard ................... True +0: log_interval .................................... 10 +0: log_learning_rate_to_tensorboard ................ True +0: log_level ....................................... None +0: log_level_replica ............................... None +0: log_loss_scale_to_tensorboard ................... True +0: log_num_zeros_in_grad ........................... False +0: log_params_norm ................................. False +0: log_path ........................................ None +0: log_timers_to_tensorboard ....................... True +0: log_validation_ppl_to_tensorboard ............... True +0: loss_on_targets_only ............................ False +0: loss_scale ...................................... 12.0 +0: loss_scale_window ............................... 1000 +0: lr .............................................. 0.0002 +0: lr_decay_iters .................................. None +0: lr_decay_samples ................................ 740269 +0: lr_decay_style .................................. cosine +0: lr_decay_tokens ................................. None +0: lr_warmup_fraction .............................. None +0: lr_warmup_iters ................................. 0 +0: lr_warmup_samples ............................... 7403 +0: make_vocab_size_divisible_by .................... 128 +0: mask_prob ....................................... 0.15 +0: masked_softmax_fusion ........................... True +0: max_position_embeddings ......................... 2048 +0: mean_noise_span_length .......................... None +0: memory_centric_tiled_linear ..................... False +0: merge_file ...................................... gpt2/merges.txt +0: micro_batch_size ................................ 4 +0: min_loss_scale .................................. 1.0 +0: min_lr .......................................... 2e-05 +0: mmap_warmup ..................................... False +0: no_load_optim ................................... None +0: no_load_rng ..................................... None +0: no_save_optim ................................... None +0: no_save_rng ..................................... None +0: noise_density ................................... None +0: num_attention_heads ............................. 14 +0: num_channels .................................... 3 +0: num_classes ..................................... 1000 +0: num_layers ...................................... 26 +0: num_layers_per_virtual_pipeline_stage ........... None +0: num_workers ..................................... 2 +0: onnx_safe ....................................... None +0: openai_gelu ..................................... False +0: optimizer ....................................... adam +0: optimizer_fusion ................................ True +0: override_lr_scheduler ........................... False +0: pad_vocab_size_to ............................... None +0: params_dtype .................................... torch.bfloat16 +0: partition_activations ........................... False +0: patch_dim ....................................... 16 +0: pipeline_model_parallel_size .................... 1 +0: position_embedding_type ......................... PositionEmbeddingType.absolute +0: pp_partition_method ............................. None +0: profile_backward ................................ False +0: query_in_block_prob ............................. 0.1 +0: rampup_batch_size ............................... None +0: rank ............................................ 0 +0: remote_device ................................... none +0: reset_attention_mask ............................ False +0: reset_position_ids .............................. False +0: retriever_report_topk_accuracies ................ [] +0: retriever_score_scaling ......................... False +0: retriever_seq_length ............................ 256 +0: reweight_loss_based_on_position_frequency ....... False +0: sample_rate ..................................... 1.0 +0: save ............................................ checkpoints_1b1oscar +0: save_interval ................................... 1000 +0: scatter_gather_tensors_in_pipeline .............. True +0: scattered_embeddings ............................ False +0: seed ............................................ 1234 +0: seq_length ...................................... 2048 +0: sgd_momentum .................................... 0.9 +0: short_seq_prob .................................. 0.1 +0: skip_train_iteration_range ...................... None +0: split ........................................... 949,50,1 +0: split_transformers .............................. False +0: sync_tp_duplicated_parameters ................... False +0: synchronize_each_layer .......................... False +0: tensor_model_parallel_size ...................... 1 +0: tensorboard_dir ................................. tensorboard_1b1oscar +0: tensorboard_log_interval ........................ 1 +0: tensorboard_queue_size .......................... 5 +0: test_weighted_split_names ....................... None +0: test_weighted_split_paths ....................... None +0: test_weighted_split_paths_path .................. None +0: test_weighted_split_splits ...................... None +0: test_weighted_split_weights ..................... None +0: tile_factor ..................................... 1 +0: titles_data_path ................................ None +0: tokenizer_name_or_path .......................... None +0: tokenizer_type .................................. GPT2BPETokenizer +0: train_iters ..................................... None +0: train_samples ................................... 740269 +0: train_tokens .................................... None +0: train_weighted_split_paths ...................... None +0: train_weighted_split_paths_path ................. None +0: universal_checkpoint ............................ False +0: use_bnb_optimizer ............................... False +0: use_checkpoint_lr_scheduler ..................... False +0: use_contiguous_buffers_in_ddp ................... True +0: use_cpu_initialization .......................... None +0: use_one_sent_docs ............................... False +0: use_pin_memory .................................. False +0: valid_num_workers ............................... 2 +0: valid_weighted_split_names ...................... None +0: valid_weighted_split_paths ...................... None +0: valid_weighted_split_paths_path ................. None +0: valid_weighted_split_splits ..................... None +0: valid_weighted_split_weights .................... None +0: virtual_pipeline_model_parallel_size ............ None +0: vocab_extra_ids ................................. 0 +0: vocab_file ...................................... gpt2/vocab.json +0: weight_decay .................................... 0.1 +0: world_size ...................................... 64 +0: zero_allgather_bucket_size ...................... 0.0 +0: zero_contigious_gradients ....................... False +0: zero_reduce_bucket_size ......................... 0.0 +0: zero_reduce_scatter ............................. False +0: zero_stage ...................................... 0 +0: -------------------- end of arguments --------------------- +0: setting number of micro-batches to constant 1 +0: > building GPT2BPETokenizer tokenizer ... +0: > padded vocab (size: 50257) with 47 dummy tokens (new size: 50304) +0: DeepSpeed general environment info: +0: torch install path ............... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch'] +0: torch version .................... 1.13.0+rocm5.2 +0: torch cuda version ............... None +0: torch hip version ................ 5.2.21151-afdc89f8 +0: nvcc version ..................... None +0: deepspeed install path ........... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed'] +0: deepspeed info ................... 0.7.5, unknown, unknown +0: deepspeed wheel compiled w. ...... torch 1.13, hip 5.1 +0: **** Git info for Megatron: git_hash=unknown git_branch=unknown **** +0: > initializing torch distributed ... +0: [2022-11-29 17:50:11,092] [INFO] [comm.py:633:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +7: > setting tensorboard ... +0: > initializing tensor model parallel with size 1 +0: > initializing pipeline model parallel with size 1 +0: > setting random seeds to 1234 ... +0: > initializing model parallel cuda seeds on global rank 0, model parallel rank 0, and data parallel rank 0 with model parallel seed: 3952 and data parallel seed: 1234 +0: > compiling dataset index builder ... +0: make: Entering directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' +0: make: Nothing to be done for 'default'. +0: make: Leaving directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' +0: >>> done with dataset index builder. Compilation time: 0.091 seconds +0: > compiling and loading fused kernels ... +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.cpp [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 87 +0: ninja: no work to do. +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.cpp [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 63 +0: ninja: no work to do. +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda_kernel.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_hip_kernel.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 67 +0: ninja: no work to do. +0: >>> done with compiling and loading fused kernels. Compilation time: 21.171 seconds +0: time to initialize megatron (seconds): 77.428 +0: [after megatron is initialized] datetime: 2022-11-29 17:50:37 +0: building GPT model ... +0: [2022-11-29 17:50:37,483] [INFO] [utils.py:827:see_memory_usage] Before Building Model +0: [2022-11-29 17:50:37,484] [INFO] [utils.py:828:see_memory_usage] MA 0.0 GB Max_MA 0.0 GB CA 0.0 GB Max_CA 0 GB +0: [2022-11-29 17:50:37,484] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 29.14 GB, percent = 5.8% +0: SEED_LAYERS=False BASE_SEED=1234 SEED_FN=None +0: Using topology: {ProcessCoord(pipe=0, data=0, model=0): 0, ProcessCoord(pipe=0, data=1, model=0): 1, ProcessCoord(pipe=0, data=2, model=0): 2, ProcessCoord(pipe=0, data=3, model=0): 3, ProcessCoord(pipe=0, data=4, model=0): 4, ProcessCoord(pipe=0, data=5, model=0): 5, ProcessCoord(pipe=0, data=6, model=0): 6, ProcessCoord(pipe=0, data=7, model=0): 7, ProcessCoord(pipe=0, data=8, model=0): 8, ProcessCoord(pipe=0, data=9, model=0): 9, ProcessCoord(pipe=0, data=10, model=0): 10, ProcessCoord(pipe=0, data=11, model=0): 11, ProcessCoord(pipe=0, data=12, model=0): 12, ProcessCoord(pipe=0, data=13, model=0): 13, ProcessCoord(pipe=0, data=14, model=0): 14, ProcessCoord(pipe=0, data=15, model=0): 15, ProcessCoord(pipe=0, data=16, model=0): 16, ProcessCoord(pipe=0, data=17, model=0): 17, ProcessCoord(pipe=0, data=18, model=0): 18, ProcessCoord(pipe=0, data=19, model=0): 19, ProcessCoord(pipe=0, data=20, model=0): 20, ProcessCoord(pipe=0, data=21, model=0): 21, ProcessCoord(pipe=0, data=22, model=0): 22, ProcessCoord(pi +0: pe=0, data=23, model=0): 23, ProcessCoord(pipe=0, data=24, model=0): 24, ProcessCoord(pipe=0, data=25, model=0): 25, ProcessCoord(pipe=0, data=26, model=0): 26, ProcessCoord(pipe=0, data=27, model=0): 27, ProcessCoord(pipe=0, data=28, model=0): 28, ProcessCoord(pipe=0, data=29, model=0): 29, ProcessCoord(pipe=0, data=30, model=0): 30, ProcessCoord(pipe=0, data=31, model=0): 31, ProcessCoord(pipe=0, data=32, model=0): 32, ProcessCoord(pipe=0, data=33, model=0): 33, ProcessCoord(pipe=0, data=34, model=0): 34, ProcessCoord(pipe=0, data=35, model=0): 35, ProcessCoord(pipe=0, data=36, model=0): 36, ProcessCoord(pipe=0, data=37, model=0): 37, ProcessCoord(pipe=0, data=38, model=0): 38, ProcessCoord(pipe=0, data=39, model=0): 39, ProcessCoord(pipe=0, data=40, model=0): 40, ProcessCoord(pipe=0, data=41, model=0): 41, ProcessCoord(pipe=0, data=42, model=0): 42, ProcessCoord(pipe=0, data=43, model=0): 43, ProcessCoord(pipe=0, data=44, model=0): 44, ProcessCoord(pipe=0, data=45, model=0): 45, ProcessCoord(pipe=0, data=4 +0: 6, model=0): 46, ProcessCoord(pipe=0, data=47, model=0): 47, ProcessCoord(pipe=0, data=48, model=0): 48, ProcessCoord(pipe=0, data=49, model=0): 49, ProcessCoord(pipe=0, data=50, model=0): 50, ProcessCoord(pipe=0, data=51, model=0): 51, ProcessCoord(pipe=0, data=52, model=0): 52, ProcessCoord(pipe=0, data=53, model=0): 53, ProcessCoord(pipe=0, data=54, model=0): 54, ProcessCoord(pipe=0, data=55, model=0): 55, ProcessCoord(pipe=0, data=56, model=0): 56, ProcessCoord(pipe=0, data=57, model=0): 57, ProcessCoord(pipe=0, data=58, model=0): 58, ProcessCoord(pipe=0, data=59, model=0): 59, ProcessCoord(pipe=0, data=60, model=0): 60, ProcessCoord(pipe=0, data=61, model=0): 61, ProcessCoord(pipe=0, data=62, model=0): 62, ProcessCoord(pipe=0, data=63, model=0): 63} +0: [2022-11-29 17:50:39,575] [INFO] [module.py:366:_partition_layers] Partitioning pipeline stages with method type:transformer +0: stage=0 layers=33 +0: 0: _to_float16 +0: 1: EmbeddingPipe +0: 2: +0: 3: ParallelTransformerLayerPipe +0: 4: ParallelTransformerLayerPipe +0: 5: ParallelTransformerLayerPipe +0: 6: ParallelTransformerLayerPipe +0: 7: ParallelTransformerLayerPipe +0: 8: ParallelTransformerLayerPipe +0: 9: ParallelTransformerLayerPipe +0: 10: ParallelTransformerLayerPipe +0: 11: ParallelTransformerLayerPipe +0: 12: ParallelTransformerLayerPipe +0: 13: ParallelTransformerLayerPipe +0: 14: ParallelTransformerLayerPipe +0: 15: ParallelTransformerLayerPipe +0: 16: ParallelTransformerLayerPipe +0: 17: ParallelTransformerLayerPipe +0: 18: ParallelTransformerLayerPipe +0: 19: ParallelTransformerLayerPipe +0: 20: ParallelTransformerLayerPipe +0: 21: ParallelTransformerLayerPipe +0: 22: ParallelTransformerLayerPipe +0: 23: ParallelTransformerLayerPipe +0: 24: ParallelTransformerLayerPipe +0: 25: ParallelTransformerLayerPipe +0: 26: ParallelTransformerLayerPipe +0: 27: ParallelTransformerLayerPipe +0: 28: ParallelTransformerLayerPipe +0: 29: undo +0: 30: MixedFusedLayerNorm +0: 31: EmbeddingPipe +0: 32: float16_to_fp32 +0: loss: CrossEntropy +0: [2022-11-29 17:50:40,132] [INFO] [utils.py:827:see_memory_usage] After Building Model +0: [2022-11-29 17:50:40,132] [INFO] [utils.py:828:see_memory_usage] MA 2.05 GB Max_MA 2.05 GB CA 2.19 GB Max_CA 2 GB +0: [2022-11-29 17:50:40,132] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 29.19 GB, percent = 5.8% +0: setting training iterations to 2891 +0: > learning rate decay style: cosine +0: DeepSpeed is enabled. +0: [2022-11-29 17:50:40,134] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed info: version=0.7.5, git-hash=unknown, git-branch=unknown +0: [2022-11-29 17:50:53,232] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False +0: [2022-11-29 17:50:53,232] [INFO] [logging.py:68:log_dist] [Rank 0] Removing param_group that has no 'params' in the client Optimizer +0: [2022-11-29 17:50:53,232] [INFO] [logging.py:68:log_dist] [Rank 0] Using client Optimizer as basic optimizer +0: [2022-11-29 17:50:53,244] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Basic Optimizer = FusedAdam +0: [2022-11-29 17:50:53,244] [INFO] [logging.py:68:log_dist] [Rank 0] Creating BF16 optimizer +0: [2022-11-29 17:50:53,287] [INFO] [utils.py:827:see_memory_usage] begin bf16_optimizer +0: [2022-11-29 17:50:53,288] [INFO] [utils.py:828:see_memory_usage] MA 2.04 GB Max_MA 2.06 GB CA 2.19 GB Max_CA 2 GB +0: [2022-11-29 17:50:53,288] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 29.88 GB, percent = 5.9% +2: ninja: no work to do. +2: Time to load utils op: 0.23566126823425293 seconds +3: ninja: no work to do. +3: Time to load utils op: 0.17323756217956543 seconds +0: Time to load utils op: 0.33142590522766113 seconds +0: Time to load utils op: 0.3027992248535156 seconds +0: Time to load utils op: 0.30228495597839355 seconds +0: Time to load utils op: 0.3031189441680908 seconds +0: Time to load utils op: 0.30384206771850586 seconds +0: Time to load utils op: 0.3040444850921631 seconds +0: Time to load utils op: 0.3023831844329834 seconds +0: Time to load utils op: 0.30482029914855957 seconds +2: Time to load utils op: 0.304034948348999 seconds +2: Time to load utils op: 0.3036925792694092 secondsTime to load utils op: 0.3044910430908203 seconds +2: +2: Time to load utils op: 0.3046729564666748 seconds +2: Time to load utils op: 0.20252513885498047 seconds +2: Time to load utils op: 0.20206379890441895 seconds +2: Time to load utils op: 0.20276308059692383 seconds +3: Time to load utils op: 0.20595955848693848 seconds +3: Time to load utils op: 0.20621442794799805 seconds +3: Time to load utils op: 0.20627641677856445 seconds +3: Time to load utils op: 0.20633983612060547 seconds +3: Time to load utils op: 0.2063581943511963 seconds +3: Time to load utils op: 0.20648479461669922 seconds +3: Time to load utils op: 0.20666980743408203 seconds +4: Time to load utils op: 0.22125029563903809 secondsTime to load utils op: 0.22104287147521973 seconds +4: +4: Time to load utils op: 0.2197115421295166 seconds +4: Time to load utils op: 0.22103190422058105 secondsTime to load utils op: 0.22060585021972656 secondsTime to load utils op: 0.2202603816986084 seconds +4: Time to load utils op: 0.2210216522216797 seconds +4: +4: +4: Time to load utils op: 0.2212374210357666 seconds +1: Time to load utils op: 0.324230432510376 seconds +1: Time to load utils op: 0.3242325782775879 secondsTime to load utils op: 0.3242371082305908 seconds +1: +1: Time to load utils op: 0.32424139976501465 seconds +1: Time to load utils op: 0.3241105079650879 seconds +1: Time to load utils op: 0.32425761222839355 seconds +1: Time to load utils op: 0.32433271408081055 seconds +1: Time to load utils op: 0.32428956031799316 seconds +0: [2022-11-29 17:50:53,626] [INFO] [utils.py:827:see_memory_usage] before initializing group 0 +0: [2022-11-29 17:50:53,626] [INFO] [utils.py:828:see_memory_usage] MA 2.04 GB Max_MA 2.04 GB CA 2.19 GB Max_CA 2 GB +0: [2022-11-29 17:50:53,626] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 29.88 GB, percent = 5.9% +5: Time to load utils op: 0.21216583251953125 seconds +5: Time to load utils op: 0.21256661415100098 seconds +5: Time to load utils op: 0.2125706672668457 secondsTime to load utils op: 0.2125694751739502 seconds +5: +5: Time to load utils op: 0.21259331703186035 secondsTime to load utils op: 0.21260380744934082 seconds +5: Time to load utils op: 0.21259689331054688 seconds +5: +5: Time to load utils op: 0.21260643005371094 seconds +6: Time to load utils op: 0.21385622024536133 seconds +6: Time to load utils op: 0.21386194229125977 seconds +6: Time to load utils op: 0.213881254196167 seconds +6: Time to load utils op: 0.21387791633605957 seconds +6: Time to load utils op: 0.21389269828796387 secondsTime to load utils op: 0.21390056610107422 secondsTime to load utils op: 0.21390032768249512 seconds +6: +6: +6: Time to load utils op: 0.21390700340270996 seconds +7: Time to load utils op: 0.21324944496154785 seconds +7: Time to load utils op: 0.2132704257965088 secondsTime to load utils op: 0.21326994895935059 seconds +7: +7: Time to load utils op: 0.21330785751342773 secondsTime to load utils op: 0.21331262588500977 seconds +7: +7: Time to load utils op: 0.21332073211669922 secondsTime to load utils op: 0.2133185863494873 seconds +7: +7: Time to load utils op: 0.21333527565002441 seconds +0: [2022-11-29 17:50:53,967] [INFO] [utils.py:827:see_memory_usage] after initializing group 0 +0: [2022-11-29 17:50:53,967] [INFO] [utils.py:828:see_memory_usage] MA 4.24 GB Max_MA 4.24 GB CA 5.44 GB Max_CA 5 GB +0: [2022-11-29 17:50:53,967] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 29.89 GB, percent = 5.9% +2: Time to load utils op: 0.0005064010620117188 seconds +2: Time to load utils op: 0.0004057884216308594 seconds +2: Time to load utils op: 0.0003991127014160156 seconds +0: Time to load utils op: 0.0005359649658203125 seconds +0: Time to load utils op: 0.00045180320739746094 seconds +0: Time to load utils op: 0.00042748451232910156 seconds +2: Time to load utils op: 0.0005943775177001953 seconds +0: Time to load utils op: 0.0004229545593261719 seconds +2: Time to load utils op: 0.0006234645843505859 seconds +0: Time to load utils op: 0.00042247772216796875 seconds +2: Time to load utils op: 0.0006449222564697266 seconds +0: Time to load utils op: 0.0006496906280517578 seconds +0: Time to load utils op: 0.0006239414215087891 seconds +2: Time to load utils op: 0.0006906986236572266 seconds +2: Time to load utils op: 0.000476837158203125 seconds +4: Time to load utils op: 0.0007371902465820312 seconds +6: Time to load utils op: 0.0013804435729980469 seconds +4: Time to load utils op: 0.0009975433349609375 secondsTime to load utils op: 0.001041412353515625 seconds +4: +4: Time to load utils op: 0.0011353492736816406 seconds +4: Time to load utils op: 0.0011258125305175781 seconds +4: Time to load utils op: 0.0011293888092041016 seconds +4: Time to load utils op: 0.0011546611785888672 seconds +4: Time to load utils op: 0.0011615753173828125 seconds +6: Time to load utils op: 0.001924753189086914 seconds +5: Time to load utils op: 0.0009436607360839844 seconds +6: Time to load utils op: 0.0020017623901367188 seconds +6: Time to load utils op: 0.0019345283508300781 seconds +6: Time to load utils op: 0.0019729137420654297 secondsTime to load utils op: 0.001962900161743164 seconds +6: +6: Time to load utils op: 0.001992464065551758 seconds +6: Time to load utils op: 0.0020034313201904297 seconds +5: Time to load utils op: 0.001226186752319336 seconds +5: Time to load utils op: 0.0015766620635986328 seconds +1: Time to load utils op: 0.0007855892181396484 seconds +5: Time to load utils op: 0.0016503334045410156 seconds +5: Time to load utils op: 0.001684427261352539 seconds +5: Time to load utils op: 0.00164794921875 secondsTime to load utils op: 0.0016486644744873047 seconds +5: +5: Time to load utils op: 0.0016918182373046875 seconds +1: Time to load utils op: 0.0013966560363769531 seconds +1: Time to load utils op: 0.0019440650939941406 seconds +1: Time to load utils op: 0.0019609928131103516 seconds +1: Time to load utils op: 0.0019588470458984375 seconds +1: Time to load utils op: 0.0019412040710449219 seconds +1: Time to load utils op: 0.0019609928131103516 seconds +1: Time to load utils op: 0.0020444393157958984 seconds +0: [2022-11-29 17:50:53,999] [INFO] [utils.py:827:see_memory_usage] before initializing group 1 +0: [2022-11-29 17:50:54,000] [INFO] [utils.py:828:see_memory_usage] MA 4.24 GB Max_MA 4.24 GB CA 5.44 GB Max_CA 5 GB +0: [2022-11-29 17:50:54,000] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 29.9 GB, percent = 5.9% +3: Time to load utils op: 0.0009582042694091797 seconds +3: Time to load utils op: 0.0009634494781494141 seconds +3: Time to load utils op: 0.0013456344604492188 seconds +3: Time to load utils op: 0.0013494491577148438 seconds +3: Time to load utils op: 0.0012884140014648438 secondsTime to load utils op: 0.0014028549194335938 seconds +3: +3: Time to load utils op: 0.0010943412780761719 seconds +3: Time to load utils op: 0.0013670921325683594 seconds +7: Time to load utils op: 0.0012385845184326172 seconds +7: Time to load utils op: 0.002031087875366211 seconds +7: Time to load utils op: 0.0020279884338378906 seconds +7: Time to load utils op: 0.0020189285278320312 secondsTime to load utils op: 0.0020744800567626953 seconds +7: +7: Time to load utils op: 0.00201416015625 seconds +7: Time to load utils op: 0.002043008804321289 seconds +7: Time to load utils op: 0.002056121826171875 seconds +0: [2022-11-29 17:50:54,048] [INFO] [utils.py:827:see_memory_usage] after initializing group 1 +0: [2022-11-29 17:50:54,049] [INFO] [utils.py:828:see_memory_usage] MA 6.19 GB Max_MA 6.19 GB CA 8.31 GB Max_CA 8 GB +0: [2022-11-29 17:50:54,049] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.03 GB, percent = 6.0% +0: [2022-11-29 17:50:54,081] [INFO] [utils.py:827:see_memory_usage] before initializing group 2 +0: [2022-11-29 17:50:54,081] [INFO] [utils.py:828:see_memory_usage] MA 6.19 GB Max_MA 6.19 GB CA 8.31 GB Max_CA 8 GB +0: [2022-11-29 17:50:54,082] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.03 GB, percent = 6.0% +0: [2022-11-29 17:50:54,116] [INFO] [utils.py:827:see_memory_usage] after initializing group 2 +0: [2022-11-29 17:50:54,116] [INFO] [utils.py:828:see_memory_usage] MA 6.19 GB Max_MA 6.19 GB CA 8.31 GB Max_CA 8 GB +0: [2022-11-29 17:50:54,116] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.03 GB, percent = 6.0% +0: [2022-11-29 17:50:54,147] [INFO] [utils.py:827:see_memory_usage] before initialize_optimizer +0: [2022-11-29 17:50:54,147] [INFO] [utils.py:828:see_memory_usage] MA 6.19 GB Max_MA 6.19 GB CA 8.31 GB Max_CA 8 GB +0: [2022-11-29 17:50:54,148] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.03 GB, percent = 6.0% +0: [2022-11-29 17:50:54,184] [INFO] [utils.py:827:see_memory_usage] end initialize_optimizer +0: [2022-11-29 17:50:54,185] [INFO] [utils.py:828:see_memory_usage] MA 6.32 GB Max_MA 6.32 GB CA 8.34 GB Max_CA 8 GB +0: [2022-11-29 17:50:54,185] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.03 GB, percent = 6.0% +0: [2022-11-29 17:50:54,217] [INFO] [utils.py:827:see_memory_usage] end bf16_optimizer +0: [2022-11-29 17:50:54,217] [INFO] [utils.py:828:see_memory_usage] MA 6.32 GB Max_MA 6.32 GB CA 8.34 GB Max_CA 8 GB +0: [2022-11-29 17:50:54,217] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.03 GB, percent = 6.0% +0: [2022-11-29 17:50:54,217] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Final Optimizer = FusedAdam +0: [2022-11-29 17:50:54,217] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed using client LR scheduler +0: [2022-11-29 17:50:54,218] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed LR Scheduler = +0: [2022-11-29 17:50:54,218] [INFO] [logging.py:68:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0, 0.0, 0.0], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +0: [2022-11-29 17:50:54,218] [INFO] [config.py:1007:print] DeepSpeedEngine configuration: +0: [2022-11-29 17:50:54,218] [INFO] [config.py:1011:print] activation_checkpointing_config { +0: "partition_activations": false, +0: "contiguous_memory_optimization": false, +0: "cpu_checkpointing": false, +0: "number_checkpoints": null, +0: "synchronize_checkpoint_boundary": false, +0: "profile": false +0: } +0: [2022-11-29 17:50:54,218] [INFO] [config.py:1011:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True} +0: [2022-11-29 17:50:54,218] [INFO] [config.py:1011:print] amp_enabled .................. False +0: [2022-11-29 17:50:54,218] [INFO] [config.py:1011:print] amp_params ................... False +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] autotuning_config ............ { +0: "enabled": false, +0: "start_step": null, +0: "end_step": null, +0: "metric_path": null, +0: "arg_mappings": null, +0: "metric": "throughput", +0: "model_info": null, +0: "results_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_results", +0: "exps_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_exps", +0: "overwrite": true, +0: "fast": true, +0: "start_profile_step": 3, +0: "end_profile_step": 5, +0: "tuner_type": "gridsearch", +0: "tuner_early_stopping": 5, +0: "tuner_num_trials": 50, +0: "model_info_path": null, +0: "mp_size": 1, +0: "max_train_batch_size": null, +0: "min_train_batch_size": 1, +0: "max_train_micro_batch_size_per_gpu": 1.024000e+03, +0: "min_train_micro_batch_size_per_gpu": 1, +0: "num_tuning_micro_batch_sizes": 3 +0: } +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] bfloat16_enabled ............. True +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] checkpoint_parallel_write_pipeline False +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] checkpoint_tag_validation_enabled True +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] checkpoint_tag_validation_fail False +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] comms_config ................. +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] communication_data_type ...... None +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] compression_config ........... {'weight_quantization': {'shared_parameters': {'enabled': False, 'quantizer_kernel': False, 'schedule_offset': 0, 'quantize_groups': 1, 'quantize_verbose': False, 'quantization_type': 'symmetric', 'quantize_weight_in_forward': False, 'rounding': 'nearest', 'fp16_mixed_quantize': False, 'quantize_change_ratio': 0.001}, 'different_groups': {}}, 'activation_quantization': {'shared_parameters': {'enabled': False, 'quantization_type': 'symmetric', 'range_calibration': 'dynamic', 'schedule_offset': 1000}, 'different_groups': {}}, 'sparse_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'row_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'head_pruning': {'shared_parameters': {'enabled': False, 'method': 'topk', 'schedule_offset': 1000}, 'different_groups': {}}, 'channel_pruning': {'shared_pa +0: rameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'layer_reduction': {'enabled': False}} +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] curriculum_enabled ........... False +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] curriculum_params ............ False +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] dataloader_drop_last ......... False +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] disable_allgather ............ False +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] dump_state ................... False +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] dynamic_loss_scale_args ...... None +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] eigenvalue_enabled ........... False +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] eigenvalue_gas_boundary_resolution 1 +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] eigenvalue_layer_name ........ bert.encoder.layer +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] eigenvalue_layer_num ......... 0 +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] eigenvalue_max_iter .......... 100 +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] eigenvalue_stability ......... 1e-06 +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] eigenvalue_tol ............... 0.01 +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] eigenvalue_verbose ........... False +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] elasticity_enabled ........... False +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] flops_profiler_config ........ { +0: "enabled": false, +0: "profile_step": 1, +0: "module_depth": -1, +0: "top_modules": 1, +0: "detailed": true, +0: "output_file": null +0: } +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] fp16_auto_cast ............... None +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] fp16_enabled ................. False +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] fp16_master_weights_and_gradients False +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] global_rank .................. 0 +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] gradient_accumulation_steps .. 1 +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] gradient_clipping ............ 1.0 +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] gradient_predivide_factor .... 1.0 +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] initial_dynamic_scale ........ 1 +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] load_universal_checkpoint .... False +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] loss_scale ................... 1.0 +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] memory_breakdown ............. False +0: [2022-11-29 17:50:54,219] [INFO] [config.py:1011:print] monitor_config ............... +0: [2022-11-29 17:50:54,220] [INFO] [config.py:1011:print] nebula_config ................ { +0: "enabled": false, +0: "persistent_storage_path": null, +0: "persistent_time_interval": 100, +0: "num_of_version_in_retention": 2, +0: "enable_nebula_load": true, +0: "load_path": null +0: } +0: [2022-11-29 17:50:54,220] [INFO] [config.py:1011:print] optimizer_legacy_fusion ...... False +0: [2022-11-29 17:50:54,220] [INFO] [config.py:1011:print] optimizer_name ............... None +0: [2022-11-29 17:50:54,220] [INFO] [config.py:1011:print] optimizer_params ............. None +0: [2022-11-29 17:50:54,220] [INFO] [config.py:1011:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0} +0: [2022-11-29 17:50:54,220] [INFO] [config.py:1011:print] pld_enabled .................. False +0: [2022-11-29 17:50:54,220] [INFO] [config.py:1011:print] pld_params ................... False +0: [2022-11-29 17:50:54,220] [INFO] [config.py:1011:print] prescale_gradients ........... False +0: [2022-11-29 17:50:54,220] [INFO] [config.py:1011:print] scheduler_name ............... None +0: [2022-11-29 17:50:54,220] [INFO] [config.py:1011:print] scheduler_params ............. None +0: [2022-11-29 17:50:54,220] [INFO] [config.py:1011:print] sparse_attention ............. None +0: [2022-11-29 17:50:54,220] [INFO] [config.py:1011:print] sparse_gradients_enabled ..... False +0: [2022-11-29 17:50:54,220] [INFO] [config.py:1011:print] steps_per_print .............. 2000 +0: [2022-11-29 17:50:54,220] [INFO] [config.py:1011:print] train_batch_size ............. 256 +0: [2022-11-29 17:50:54,220] [INFO] [config.py:1011:print] train_micro_batch_size_per_gpu 4 +0: [2022-11-29 17:50:54,220] [INFO] [config.py:1011:print] use_node_local_storage ....... False +0: [2022-11-29 17:50:54,220] [INFO] [config.py:1011:print] wall_clock_breakdown ......... False +0: [2022-11-29 17:50:54,220] [INFO] [config.py:1011:print] world_size ................... 64 +0: [2022-11-29 17:50:54,220] [INFO] [config.py:1011:print] zero_allow_untested_optimizer False +0: [2022-11-29 17:50:54,220] [INFO] [config.py:1011:print] zero_config .................. stage=0 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=500000000 allgather_partitions=True allgather_bucket_size=500000000 overlap_comm=False load_from_fp32_weights=True elastic_checkpoint=False offload_param=None offload_optimizer=None sub_group_size=1000000000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=50000000 param_persistence_threshold=100000 model_persistence_threshold=9223372036854775807 max_live_parameters=1000000000 max_reuse_distance=1000000000 gather_16bit_weights_on_model_save=False stage3_gather_fp16_weights_on_model_save=False ignore_unused_parameters=True legacy_stage1=False round_robin_gradients=False +0: [2022-11-29 17:50:54,220] [INFO] [config.py:1011:print] zero_enabled ................. False +0: [2022-11-29 17:50:54,220] [INFO] [config.py:1011:print] zero_optimization_stage ...... 0 +0: [2022-11-29 17:50:54,220] [INFO] [config.py:996:print_user_config] json = { +0: "train_micro_batch_size_per_gpu": 4, +0: "train_batch_size": 256, +0: "gradient_clipping": 1.0, +0: "zero_optimization": { +0: "stage": 0 +0: }, +0: "bf16": { +0: "enabled": true +0: }, +0: "steps_per_print": 2.000000e+03, +0: "wall_clock_breakdown": false +0: } +0: Time to load utils op: 0.00041604042053222656 seconds +0: [2022-11-29 17:50:54,221] [INFO] [engine.py:87:__init__] CONFIG: micro_batches=1 micro_batch_size=4 +0: [2022-11-29 17:50:54,245] [INFO] [engine.py:145:__init__] RANK=0 STAGE=0 LAYERS=33 [0, 33) STAGE_PARAMS=1096338432 (1096.338M) TOTAL_PARAMS=1096338432 (1096.338M) UNIQUE_PARAMS=1096338432 (1096.338M) +0: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: WARNING: could not find the metadata file checkpoints_1b1oscar +0: will not load any checkpoints and will start from random +6: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:50:54,251] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:50:54,252] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:50:54,252] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_1b1oscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: time (ms) | load-checkpoint: 7.04 +0: estimated model parameters: 1.096338432 +0: estimated model parameters without embeddings: 1.002523648 +0: [after model, optimizer, and learning rate scheduler are built] datetime: 2022-11-29 17:50:55 +0: > building train, validation, and test datasets ... +0: > datasets target sizes (minimum size): +0: train: 740269 +0: validation: 768 +0: test: 256 +0: > building train, validation, and test datasets for GPT ... +0: > building dataset index ... +0: reading sizes... +0: reading pointers... +0: reading document index... +0: creating numpy buffer of mmap... +0: creating memory view of numpy buffer... +0: > finished creating indexed dataset in 0.025524 seconds +0: number of documents: 431992659 +0: > dataset split: +0: train: +0: document indices in [0, 409961033) total of 409961033 documents +0: validation: +0: document indices in [409961033, 431560666) total of 21599633 documents +0: test: +0: document indices in [431560666, 431992659) total of 431993 documents +0: > WARNING: could not find index map files, building the indices on rank 0 ... +0: > only one epoch required, setting separate_last_epoch to False +0: > elasped time to build and save doc-idx mapping (seconds): 30.706916 +0: using: +0: number of documents: 409961033 +0: number of epochs: 1 +0: sequence length: 2048 +0: total number of samples: 262636457 +0: > elasped time to build and save sample-idx mapping (seconds): 7.716910 +0: > building shuffle index with split [0, 262636457) and [262636457, 262636457) ... +0: > elasped time to build and save shuffle-idx mapping (seconds): 15.653235 +0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_740269ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_740269ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_740269ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.140 seconds +0: total number of samples: 262636458 +0: total number of epochs: 1 +0: > WARNING: could not find index map files, building the indices on rank 0 ... +0: > only one epoch required, setting separate_last_epoch to False +0: > elasped time to build and save doc-idx mapping (seconds): 1.270410 +0: using: +0: number of documents: 21599633 +0: number of epochs: 1 +0: sequence length: 2048 +0: total number of samples: 13852049 +0: > elasped time to build and save sample-idx mapping (seconds): 0.415536 +0: > building shuffle index with split [0, 13852049) and [13852049, 13852049) ... +0: > elasped time to build and save shuffle-idx mapping (seconds): 0.490091 +0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_768ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_768ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_768ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.034 seconds +0: total number of samples: 13852050 +0: total number of epochs: 1 +0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_256ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_256ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_256ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.052 seconds +0: total number of samples: 276852 +0: total number of epochs: 1 +0: > finished creating GPT datasets ... +0: [after dataloaders are built] datetime: 2022-11-29 17:52:22 +0: done with setup ... +0: training ... +0: Number of parameters: [tensor rank - pipeline rank] w/ and w/o embeddings: +7: time (ms) | model-and-optimizer-setup: 17490.59 | train/valid/test-data-iterators-setup: 87650.14 +0: [000-000] 1.0963B / 1.0025B +0: [before the start of training step] datetime: 2022-11-29 17:52:23 +0: [Rank 0] (after 10 iterations) memory (MB) | allocated: 10138.55712890625 | max allocated: 54070.994140625 | reserved: 55702.0 | max reserved: 55702.0 +7: iteration 10/ 2891 | consumed samples: 2560 | consumed tokens: 5242880 | elapsed time per iteration (s): 3.63 | learning rate: 6.916E-05 | global batch size: 256 | lm loss: 1.004691E+01 | grad norm: 3.924 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 70.600 | TFLOPs: 17.08 | +7: iteration 20/ 2891 | consumed samples: 5120 | consumed tokens: 10485760 | elapsed time per iteration (s): 1.29 | learning rate: 1.383E-04 | global batch size: 256 | lm loss: 8.535011E+00 | grad norm: 1.547 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.490 | TFLOPs: 48.03 | +7: iteration 30/ 2891 | consumed samples: 7680 | consumed tokens: 15728640 | elapsed time per iteration (s): 1.30 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 7.889861E+00 | grad norm: 1.003 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 197.089 | TFLOPs: 47.69 | +7: iteration 40/ 2891 | consumed samples: 10240 | consumed tokens: 20971520 | elapsed time per iteration (s): 1.26 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 7.719034E+00 | grad norm: 0.750 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.856 | TFLOPs: 49.09 | +7: iteration 50/ 2891 | consumed samples: 12800 | consumed tokens: 26214400 | elapsed time per iteration (s): 1.28 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 7.486797E+00 | grad norm: 1.875 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.565 | TFLOPs: 48.29 | +7: iteration 60/ 2891 | consumed samples: 15360 | consumed tokens: 31457280 | elapsed time per iteration (s): 1.27 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 7.247771E+00 | grad norm: 1.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.289 | TFLOPs: 48.71 | +7: iteration 70/ 2891 | consumed samples: 17920 | consumed tokens: 36700160 | elapsed time per iteration (s): 1.27 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 7.072065E+00 | grad norm: 0.787 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.287 | TFLOPs: 48.95 | +7: iteration 80/ 2891 | consumed samples: 20480 | consumed tokens: 41943040 | elapsed time per iteration (s): 1.29 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 6.970959E+00 | grad norm: 0.608 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.443 | TFLOPs: 48.02 | +7: iteration 90/ 2891 | consumed samples: 23040 | consumed tokens: 47185920 | elapsed time per iteration (s): 1.29 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 6.801189E+00 | grad norm: 0.621 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.436 | TFLOPs: 48.02 | +7: iteration 100/ 2891 | consumed samples: 25600 | consumed tokens: 52428800 | elapsed time per iteration (s): 1.28 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 6.721026E+00 | grad norm: 0.568 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.761 | TFLOPs: 48.58 | +7: iteration 110/ 2891 | consumed samples: 28160 | consumed tokens: 57671680 | elapsed time per iteration (s): 1.27 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 6.648073E+00 | grad norm: 0.931 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.686 | TFLOPs: 48.81 | +7: iteration 120/ 2891 | consumed samples: 30720 | consumed tokens: 62914560 | elapsed time per iteration (s): 1.28 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 6.601103E+00 | grad norm: 0.663 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.196 | TFLOPs: 48.45 | +7: iteration 130/ 2891 | consumed samples: 33280 | consumed tokens: 68157440 | elapsed time per iteration (s): 1.28 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 6.506982E+00 | grad norm: 1.053 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.931 | TFLOPs: 48.38 | +7: iteration 140/ 2891 | consumed samples: 35840 | consumed tokens: 73400320 | elapsed time per iteration (s): 1.27 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 6.472588E+00 | grad norm: 0.751 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.956 | TFLOPs: 48.63 | +7: iteration 150/ 2891 | consumed samples: 38400 | consumed tokens: 78643200 | elapsed time per iteration (s): 1.29 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 6.405199E+00 | grad norm: 0.740 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.396 | TFLOPs: 48.01 | +7: iteration 160/ 2891 | consumed samples: 40960 | consumed tokens: 83886080 | elapsed time per iteration (s): 1.28 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 6.387122E+00 | grad norm: 0.658 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.733 | TFLOPs: 48.33 | +7: iteration 170/ 2891 | consumed samples: 43520 | consumed tokens: 89128960 | elapsed time per iteration (s): 1.27 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 6.346349E+00 | grad norm: 0.666 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.682 | TFLOPs: 48.80 | +7: iteration 180/ 2891 | consumed samples: 46080 | consumed tokens: 94371840 | elapsed time per iteration (s): 1.27 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 6.302601E+00 | grad norm: 1.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.972 | TFLOPs: 48.63 | +7: iteration 190/ 2891 | consumed samples: 48640 | consumed tokens: 99614720 | elapsed time per iteration (s): 1.27 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 6.280320E+00 | grad norm: 0.520 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.269 | TFLOPs: 48.71 | +7: iteration 200/ 2891 | consumed samples: 51200 | consumed tokens: 104857600 | elapsed time per iteration (s): 1.26 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 6.255330E+00 | grad norm: 0.813 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.686 | TFLOPs: 49.05 | +7: iteration 210/ 2891 | consumed samples: 53760 | consumed tokens: 110100480 | elapsed time per iteration (s): 1.26 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 6.184408E+00 | grad norm: 0.531 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.545 | TFLOPs: 49.01 | +7: iteration 220/ 2891 | consumed samples: 56320 | consumed tokens: 115343360 | elapsed time per iteration (s): 1.27 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 6.182448E+00 | grad norm: 0.750 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.483 | TFLOPs: 48.76 | +7: iteration 230/ 2891 | consumed samples: 58880 | consumed tokens: 120586240 | elapsed time per iteration (s): 1.30 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 6.089656E+00 | grad norm: 0.490 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 197.162 | TFLOPs: 47.71 | +7: iteration 240/ 2891 | consumed samples: 61440 | consumed tokens: 125829120 | elapsed time per iteration (s): 1.29 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 6.059994E+00 | grad norm: 0.728 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.183 | TFLOPs: 47.96 | +7: iteration 250/ 2891 | consumed samples: 64000 | consumed tokens: 131072000 | elapsed time per iteration (s): 1.29 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 6.052314E+00 | grad norm: 0.447 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.947 | TFLOPs: 48.14 | +7: iteration 260/ 2891 | consumed samples: 66560 | consumed tokens: 136314880 | elapsed time per iteration (s): 1.28 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 6.016652E+00 | grad norm: 0.867 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.301 | TFLOPs: 48.47 | +7: iteration 270/ 2891 | consumed samples: 69120 | consumed tokens: 141557760 | elapsed time per iteration (s): 1.28 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 5.984499E+00 | grad norm: 0.427 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.669 | TFLOPs: 48.32 | +7: iteration 280/ 2891 | consumed samples: 71680 | consumed tokens: 146800640 | elapsed time per iteration (s): 1.30 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 5.945768E+00 | grad norm: 0.547 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 196.959 | TFLOPs: 47.66 | +7: iteration 290/ 2891 | consumed samples: 74240 | consumed tokens: 152043520 | elapsed time per iteration (s): 1.27 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 5.918950E+00 | grad norm: 0.623 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.468 | TFLOPs: 48.75 | +7: iteration 300/ 2891 | consumed samples: 76800 | consumed tokens: 157286400 | elapsed time per iteration (s): 1.29 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 5.851524E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.607 | TFLOPs: 48.06 | +7: iteration 310/ 2891 | consumed samples: 79360 | consumed tokens: 162529280 | elapsed time per iteration (s): 1.30 | learning rate: 1.958E-04 | global batch size: 256 | lm loss: 5.849449E+00 | grad norm: 0.728 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 197.232 | TFLOPs: 47.73 | +7: iteration 320/ 2891 | consumed samples: 81920 | consumed tokens: 167772160 | elapsed time per iteration (s): 1.28 | learning rate: 1.954E-04 | global batch size: 256 | lm loss: 5.822430E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.730 | TFLOPs: 48.33 | +7: iteration 330/ 2891 | consumed samples: 84480 | consumed tokens: 173015040 | elapsed time per iteration (s): 1.28 | learning rate: 1.951E-04 | global batch size: 256 | lm loss: 5.772898E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.186 | TFLOPs: 48.44 | +7: iteration 340/ 2891 | consumed samples: 87040 | consumed tokens: 178257920 | elapsed time per iteration (s): 1.27 | learning rate: 1.948E-04 | global batch size: 256 | lm loss: 5.747245E+00 | grad norm: 0.774 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.560 | TFLOPs: 48.78 | +7: iteration 350/ 2891 | consumed samples: 89600 | consumed tokens: 183500800 | elapsed time per iteration (s): 1.29 | learning rate: 1.945E-04 | global batch size: 256 | lm loss: 5.703384E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.154 | TFLOPs: 47.95 | +7: iteration 360/ 2891 | consumed samples: 92160 | consumed tokens: 188743680 | elapsed time per iteration (s): 1.27 | learning rate: 1.941E-04 | global batch size: 256 | lm loss: 5.666056E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.833 | TFLOPs: 48.60 | +7: iteration 370/ 2891 | consumed samples: 94720 | consumed tokens: 193986560 | elapsed time per iteration (s): 1.28 | learning rate: 1.938E-04 | global batch size: 256 | lm loss: 5.644558E+00 | grad norm: 0.499 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.497 | TFLOPs: 48.52 | +7: iteration 380/ 2891 | consumed samples: 97280 | consumed tokens: 199229440 | elapsed time per iteration (s): 1.28 | learning rate: 1.934E-04 | global batch size: 256 | lm loss: 5.657554E+00 | grad norm: 0.964 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.193 | TFLOPs: 48.44 | +7: iteration 390/ 2891 | consumed samples: 99840 | consumed tokens: 204472320 | elapsed time per iteration (s): 1.27 | learning rate: 1.930E-04 | global batch size: 256 | lm loss: 5.669816E+00 | grad norm: 0.386 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.133 | TFLOPs: 48.91 | +7: iteration 400/ 2891 | consumed samples: 102400 | consumed tokens: 209715200 | elapsed time per iteration (s): 1.42 | learning rate: 1.926E-04 | global batch size: 256 | lm loss: 5.564518E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 180.908 | TFLOPs: 43.78 | +7: iteration 410/ 2891 | consumed samples: 104960 | consumed tokens: 214958080 | elapsed time per iteration (s): 1.27 | learning rate: 1.922E-04 | global batch size: 256 | lm loss: 5.515744E+00 | grad norm: 0.437 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.293 | TFLOPs: 48.95 | +7: iteration 420/ 2891 | consumed samples: 107520 | consumed tokens: 220200960 | elapsed time per iteration (s): 1.29 | learning rate: 1.918E-04 | global batch size: 256 | lm loss: 5.492318E+00 | grad norm: 0.625 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.660 | TFLOPs: 48.07 | +7: iteration 430/ 2891 | consumed samples: 110080 | consumed tokens: 225443840 | elapsed time per iteration (s): 1.28 | learning rate: 1.914E-04 | global batch size: 256 | lm loss: 5.468146E+00 | grad norm: 0.585 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.491 | TFLOPs: 48.27 | +7: iteration 440/ 2891 | consumed samples: 112640 | consumed tokens: 230686720 | elapsed time per iteration (s): 1.27 | learning rate: 1.910E-04 | global batch size: 256 | lm loss: 5.424212E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.751 | TFLOPs: 48.82 | +7: iteration 450/ 2891 | consumed samples: 115200 | consumed tokens: 235929600 | elapsed time per iteration (s): 1.27 | learning rate: 1.906E-04 | global batch size: 256 | lm loss: 5.390857E+00 | grad norm: 0.693 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.618 | TFLOPs: 48.79 | +7: iteration 460/ 2891 | consumed samples: 117760 | consumed tokens: 241172480 | elapsed time per iteration (s): 1.28 | learning rate: 1.901E-04 | global batch size: 256 | lm loss: 5.402158E+00 | grad norm: 0.520 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.613 | TFLOPs: 48.55 | +7: iteration 470/ 2891 | consumed samples: 120320 | consumed tokens: 246415360 | elapsed time per iteration (s): 1.27 | learning rate: 1.897E-04 | global batch size: 256 | lm loss: 5.347914E+00 | grad norm: 0.519 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.077 | TFLOPs: 48.90 | +7: iteration 480/ 2891 | consumed samples: 122880 | consumed tokens: 251658240 | elapsed time per iteration (s): 1.27 | learning rate: 1.892E-04 | global batch size: 256 | lm loss: 5.333340E+00 | grad norm: 0.484 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.166 | TFLOPs: 48.68 | +7: iteration 490/ 2891 | consumed samples: 125440 | consumed tokens: 256901120 | elapsed time per iteration (s): 1.27 | learning rate: 1.887E-04 | global batch size: 256 | lm loss: 5.303981E+00 | grad norm: 0.527 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.337 | TFLOPs: 48.96 | +7: iteration 500/ 2891 | consumed samples: 128000 | consumed tokens: 262144000 | elapsed time per iteration (s): 1.27 | learning rate: 1.882E-04 | global batch size: 256 | lm loss: 5.271611E+00 | grad norm: 0.720 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.182 | TFLOPs: 48.93 | +7: iteration 510/ 2891 | consumed samples: 130560 | consumed tokens: 267386880 | elapsed time per iteration (s): 1.31 | learning rate: 1.877E-04 | global batch size: 256 | lm loss: 5.297839E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 195.783 | TFLOPs: 47.38 | +7: iteration 520/ 2891 | consumed samples: 133120 | consumed tokens: 272629760 | elapsed time per iteration (s): 1.27 | learning rate: 1.872E-04 | global batch size: 256 | lm loss: 5.216937E+00 | grad norm: 0.452 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.048 | TFLOPs: 48.65 | +7: iteration 530/ 2891 | consumed samples: 135680 | consumed tokens: 277872640 | elapsed time per iteration (s): 1.27 | learning rate: 1.867E-04 | global batch size: 256 | lm loss: 5.188192E+00 | grad norm: 0.632 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.990 | TFLOPs: 48.88 | +7: iteration 540/ 2891 | consumed samples: 138240 | consumed tokens: 283115520 | elapsed time per iteration (s): 1.32 | learning rate: 1.862E-04 | global batch size: 256 | lm loss: 5.187362E+00 | grad norm: 0.437 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 194.294 | TFLOPs: 47.02 | +7: iteration 550/ 2891 | consumed samples: 140800 | consumed tokens: 288358400 | elapsed time per iteration (s): 1.31 | learning rate: 1.857E-04 | global batch size: 256 | lm loss: 5.129262E+00 | grad norm: 0.618 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 194.957 | TFLOPs: 47.18 | +7: iteration 560/ 2891 | consumed samples: 143360 | consumed tokens: 293601280 | elapsed time per iteration (s): 1.26 | learning rate: 1.851E-04 | global batch size: 256 | lm loss: 5.110377E+00 | grad norm: 0.485 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.604 | TFLOPs: 49.03 | +7: iteration 570/ 2891 | consumed samples: 145920 | consumed tokens: 298844160 | elapsed time per iteration (s): 1.29 | learning rate: 1.846E-04 | global batch size: 256 | lm loss: 5.050526E+00 | grad norm: 0.438 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.576 | TFLOPs: 48.05 | +7: iteration 580/ 2891 | consumed samples: 148480 | consumed tokens: 304087040 | elapsed time per iteration (s): 1.30 | learning rate: 1.840E-04 | global batch size: 256 | lm loss: 5.020714E+00 | grad norm: 0.458 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 197.002 | TFLOPs: 47.67 | +7: iteration 590/ 2891 | consumed samples: 151040 | consumed tokens: 309329920 | elapsed time per iteration (s): 1.27 | learning rate: 1.835E-04 | global batch size: 256 | lm loss: 5.024595E+00 | grad norm: 0.458 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.828 | TFLOPs: 48.84 | +7: iteration 600/ 2891 | consumed samples: 153600 | consumed tokens: 314572800 | elapsed time per iteration (s): 1.27 | learning rate: 1.829E-04 | global batch size: 256 | lm loss: 4.962969E+00 | grad norm: 0.521 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.731 | TFLOPs: 48.82 | +7: iteration 610/ 2891 | consumed samples: 156160 | consumed tokens: 319815680 | elapsed time per iteration (s): 1.28 | learning rate: 1.823E-04 | global batch size: 256 | lm loss: 4.929038E+00 | grad norm: 0.489 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.929 | TFLOPs: 48.38 | +7: iteration 620/ 2891 | consumed samples: 158720 | consumed tokens: 325058560 | elapsed time per iteration (s): 1.28 | learning rate: 1.817E-04 | global batch size: 256 | lm loss: 4.886727E+00 | grad norm: 0.586 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.627 | TFLOPs: 48.31 | +7: iteration 630/ 2891 | consumed samples: 161280 | consumed tokens: 330301440 | elapsed time per iteration (s): 1.30 | learning rate: 1.811E-04 | global batch size: 256 | lm loss: 4.875563E+00 | grad norm: 0.511 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 196.587 | TFLOPs: 47.57 | +7: iteration 640/ 2891 | consumed samples: 163840 | consumed tokens: 335544320 | elapsed time per iteration (s): 1.29 | learning rate: 1.805E-04 | global batch size: 256 | lm loss: 4.857310E+00 | grad norm: 0.662 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 197.718 | TFLOPs: 47.85 | +7: iteration 650/ 2891 | consumed samples: 166400 | consumed tokens: 340787200 | elapsed time per iteration (s): 1.29 | learning rate: 1.799E-04 | global batch size: 256 | lm loss: 4.812180E+00 | grad norm: 0.507 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.081 | TFLOPs: 48.18 | +7: iteration 660/ 2891 | consumed samples: 168960 | consumed tokens: 346030080 | elapsed time per iteration (s): 1.27 | learning rate: 1.793E-04 | global batch size: 256 | lm loss: 4.802442E+00 | grad norm: 0.428 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.347 | TFLOPs: 48.97 | +7: iteration 670/ 2891 | consumed samples: 171520 | consumed tokens: 351272960 | elapsed time per iteration (s): 1.31 | learning rate: 1.786E-04 | global batch size: 256 | lm loss: 4.730896E+00 | grad norm: 0.447 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 195.044 | TFLOPs: 47.20 | +7: iteration 680/ 2891 | consumed samples: 174080 | consumed tokens: 356515840 | elapsed time per iteration (s): 1.28 | learning rate: 1.780E-04 | global batch size: 256 | lm loss: 4.710181E+00 | grad norm: 0.680 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.806 | TFLOPs: 48.35 | +7: iteration 690/ 2891 | consumed samples: 176640 | consumed tokens: 361758720 | elapsed time per iteration (s): 1.28 | learning rate: 1.773E-04 | global batch size: 256 | lm loss: 4.698782E+00 | grad norm: 0.512 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.252 | TFLOPs: 48.46 | +7: iteration 700/ 2891 | consumed samples: 179200 | consumed tokens: 367001600 | elapsed time per iteration (s): 1.27 | learning rate: 1.767E-04 | global batch size: 256 | lm loss: 4.669154E+00 | grad norm: 0.423 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.351 | TFLOPs: 48.72 | +7: iteration 710/ 2891 | consumed samples: 181760 | consumed tokens: 372244480 | elapsed time per iteration (s): 1.27 | learning rate: 1.760E-04 | global batch size: 256 | lm loss: 4.596683E+00 | grad norm: 0.560 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.040 | TFLOPs: 48.65 | +7: iteration 720/ 2891 | consumed samples: 184320 | consumed tokens: 377487360 | elapsed time per iteration (s): 1.28 | learning rate: 1.753E-04 | global batch size: 256 | lm loss: 4.621252E+00 | grad norm: 0.496 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.597 | TFLOPs: 48.30 | +7: iteration 730/ 2891 | consumed samples: 186880 | consumed tokens: 382730240 | elapsed time per iteration (s): 1.27 | learning rate: 1.747E-04 | global batch size: 256 | lm loss: 4.562813E+00 | grad norm: 0.658 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.875 | TFLOPs: 48.85 | +7: iteration 740/ 2891 | consumed samples: 189440 | consumed tokens: 387973120 | elapsed time per iteration (s): 1.27 | learning rate: 1.740E-04 | global batch size: 256 | lm loss: 4.529232E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.787 | TFLOPs: 48.83 | +7: iteration 750/ 2891 | consumed samples: 192000 | consumed tokens: 393216000 | elapsed time per iteration (s): 1.27 | learning rate: 1.733E-04 | global batch size: 256 | lm loss: 4.463338E+00 | grad norm: 0.456 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.857 | TFLOPs: 48.85 | +7: iteration 760/ 2891 | consumed samples: 194560 | consumed tokens: 398458880 | elapsed time per iteration (s): 1.28 | learning rate: 1.726E-04 | global batch size: 256 | lm loss: 4.450971E+00 | grad norm: 0.753 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.411 | TFLOPs: 48.50 | +7: iteration 770/ 2891 | consumed samples: 197120 | consumed tokens: 403701760 | elapsed time per iteration (s): 1.27 | learning rate: 1.718E-04 | global batch size: 256 | lm loss: 4.549761E+00 | grad norm: 0.685 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.535 | TFLOPs: 48.77 | +7: iteration 780/ 2891 | consumed samples: 199680 | consumed tokens: 408944640 | elapsed time per iteration (s): 1.26 | learning rate: 1.711E-04 | global batch size: 256 | lm loss: 4.497304E+00 | grad norm: 0.433 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.414 | TFLOPs: 48.98 | +7: iteration 790/ 2891 | consumed samples: 202240 | consumed tokens: 414187520 | elapsed time per iteration (s): 1.27 | learning rate: 1.704E-04 | global batch size: 256 | lm loss: 4.435748E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.974 | TFLOPs: 48.88 | +7: iteration 800/ 2891 | consumed samples: 204800 | consumed tokens: 419430400 | elapsed time per iteration (s): 1.30 | learning rate: 1.697E-04 | global batch size: 256 | lm loss: 4.400716E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 197.262 | TFLOPs: 47.74 | +7: iteration 810/ 2891 | consumed samples: 207360 | consumed tokens: 424673280 | elapsed time per iteration (s): 1.30 | learning rate: 1.689E-04 | global batch size: 256 | lm loss: 4.347423E+00 | grad norm: 0.383 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 197.081 | TFLOPs: 47.69 | +7: iteration 820/ 2891 | consumed samples: 209920 | consumed tokens: 429916160 | elapsed time per iteration (s): 1.27 | learning rate: 1.682E-04 | global batch size: 256 | lm loss: 4.281096E+00 | grad norm: 0.467 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.212 | TFLOPs: 48.69 | +7: iteration 830/ 2891 | consumed samples: 212480 | consumed tokens: 435159040 | elapsed time per iteration (s): 1.27 | learning rate: 1.674E-04 | global batch size: 256 | lm loss: 4.317418E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.520 | TFLOPs: 48.77 | +7: iteration 840/ 2891 | consumed samples: 215040 | consumed tokens: 440401920 | elapsed time per iteration (s): 1.28 | learning rate: 1.666E-04 | global batch size: 256 | lm loss: 4.302997E+00 | grad norm: 0.456 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.254 | TFLOPs: 48.46 | +7: iteration 850/ 2891 | consumed samples: 217600 | consumed tokens: 445644800 | elapsed time per iteration (s): 1.27 | learning rate: 1.659E-04 | global batch size: 256 | lm loss: 4.240327E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.720 | TFLOPs: 48.81 | +7: iteration 860/ 2891 | consumed samples: 220160 | consumed tokens: 450887680 | elapsed time per iteration (s): 1.27 | learning rate: 1.651E-04 | global batch size: 256 | lm loss: 4.223909E+00 | grad norm: 0.405 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.486 | TFLOPs: 48.76 | +7: iteration 870/ 2891 | consumed samples: 222720 | consumed tokens: 456130560 | elapsed time per iteration (s): 1.28 | learning rate: 1.643E-04 | global batch size: 256 | lm loss: 4.213624E+00 | grad norm: 0.445 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.123 | TFLOPs: 48.43 | +7: iteration 880/ 2891 | consumed samples: 225280 | consumed tokens: 461373440 | elapsed time per iteration (s): 1.28 | learning rate: 1.635E-04 | global batch size: 256 | lm loss: 4.172175E+00 | grad norm: 0.568 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.310 | TFLOPs: 48.23 | +7: iteration 890/ 2891 | consumed samples: 227840 | consumed tokens: 466616320 | elapsed time per iteration (s): 1.30 | learning rate: 1.627E-04 | global batch size: 256 | lm loss: 4.170717E+00 | grad norm: 0.399 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 196.491 | TFLOPs: 47.55 | +7: iteration 900/ 2891 | consumed samples: 230400 | consumed tokens: 471859200 | elapsed time per iteration (s): 1.28 | learning rate: 1.619E-04 | global batch size: 256 | lm loss: 4.200544E+00 | grad norm: 0.405 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.452 | TFLOPs: 48.27 | +7: iteration 910/ 2891 | consumed samples: 232960 | consumed tokens: 477102080 | elapsed time per iteration (s): 1.28 | learning rate: 1.611E-04 | global batch size: 256 | lm loss: 4.168121E+00 | grad norm: 0.405 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.133 | TFLOPs: 48.43 | +7: iteration 920/ 2891 | consumed samples: 235520 | consumed tokens: 482344960 | elapsed time per iteration (s): 1.28 | learning rate: 1.603E-04 | global batch size: 256 | lm loss: 4.109627E+00 | grad norm: 0.443 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.008 | TFLOPs: 48.40 | +7: iteration 930/ 2891 | consumed samples: 238080 | consumed tokens: 487587840 | elapsed time per iteration (s): 1.27 | learning rate: 1.595E-04 | global batch size: 256 | lm loss: 4.100901E+00 | grad norm: 0.518 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.217 | TFLOPs: 48.93 | +7: iteration 940/ 2891 | consumed samples: 240640 | consumed tokens: 492830720 | elapsed time per iteration (s): 1.26 | learning rate: 1.586E-04 | global batch size: 256 | lm loss: 4.072250E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.567 | TFLOPs: 49.02 | +7: iteration 950/ 2891 | consumed samples: 243200 | consumed tokens: 498073600 | elapsed time per iteration (s): 1.27 | learning rate: 1.578E-04 | global batch size: 256 | lm loss: 4.063911E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.738 | TFLOPs: 48.82 | +7: iteration 960/ 2891 | consumed samples: 245760 | consumed tokens: 503316480 | elapsed time per iteration (s): 1.29 | learning rate: 1.570E-04 | global batch size: 256 | lm loss: 4.049501E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.392 | TFLOPs: 48.01 | +7: iteration 970/ 2891 | consumed samples: 248320 | consumed tokens: 508559360 | elapsed time per iteration (s): 1.30 | learning rate: 1.561E-04 | global batch size: 256 | lm loss: 4.044304E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 197.643 | TFLOPs: 47.83 | +7: iteration 980/ 2891 | consumed samples: 250880 | consumed tokens: 513802240 | elapsed time per iteration (s): 1.26 | learning rate: 1.553E-04 | global batch size: 256 | lm loss: 4.052804E+00 | grad norm: 0.406 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.686 | TFLOPs: 49.05 | +7: iteration 990/ 2891 | consumed samples: 253440 | consumed tokens: 519045120 | elapsed time per iteration (s): 1.29 | learning rate: 1.544E-04 | global batch size: 256 | lm loss: 4.015865E+00 | grad norm: 0.558 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.096 | TFLOPs: 47.94 | +7: iteration 1000/ 2891 | consumed samples: 256000 | consumed tokens: 524288000 | elapsed time per iteration (s): 1.28 | learning rate: 1.536E-04 | global batch size: 256 | lm loss: 4.052459E+00 | grad norm: 0.405 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.570 | TFLOPs: 48.29 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 1000 | lm loss value: 3.881743E+00 | lm loss PPL: 4.850871E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 1000 to checkpoints_1b1oscar +0: [2022-11-29 18:14:07,843] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step1000 is begin to save! +0: [2022-11-29 18:14:07,977] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:14:08,237] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:14:08,238] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:14:08,319] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:14:08,320] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:14:08,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:14:08,396] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:14:08,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:14:08,472] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:14:08,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:14:08,547] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:14:08,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:14:08,623] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:14:08,697] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:14:08,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:14:08,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:14:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:14:08,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:14:08,848] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:14:08,926] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:14:08,926] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:14:09,002] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:14:09,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_13-model_00-model_states.pt... +0: [2022-11-29 18:14:09,114] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_13-model_00-model_states.pt. +0: [2022-11-29 18:14:09,115] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:14:09,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:14:09,190] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_15-model_00-model_states.pt... +0: [2022-11-29 18:14:09,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_15-model_00-model_states.pt. +0: [2022-11-29 18:14:09,266] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_16-model_00-model_states.pt... +0: [2022-11-29 18:14:09,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_16-model_00-model_states.pt. +0: [2022-11-29 18:14:09,342] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_17-model_00-model_states.pt... +0: [2022-11-29 18:14:09,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_17-model_00-model_states.pt. +0: [2022-11-29 18:14:09,418] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_18-model_00-model_states.pt... +0: [2022-11-29 18:14:09,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_18-model_00-model_states.pt. +0: [2022-11-29 18:14:09,490] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_19-model_00-model_states.pt... +0: [2022-11-29 18:14:09,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_19-model_00-model_states.pt. +0: [2022-11-29 18:14:09,565] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_20-model_00-model_states.pt... +0: [2022-11-29 18:14:09,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_20-model_00-model_states.pt. +0: [2022-11-29 18:14:09,642] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_21-model_00-model_states.pt... +0: [2022-11-29 18:14:09,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_21-model_00-model_states.pt. +0: [2022-11-29 18:14:09,717] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_22-model_00-model_states.pt... +0: [2022-11-29 18:14:09,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_22-model_00-model_states.pt. +0: [2022-11-29 18:14:09,793] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_23-model_00-model_states.pt... +0: [2022-11-29 18:14:09,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_23-model_00-model_states.pt. +0: [2022-11-29 18:14:09,867] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_24-model_00-model_states.pt... +0: [2022-11-29 18:14:09,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_24-model_00-model_states.pt. +0: [2022-11-29 18:14:09,945] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_25-model_00-model_states.pt... +0: [2022-11-29 18:14:10,021] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_25-model_00-model_states.pt. +0: [2022-11-29 18:14:10,021] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_26-model_00-model_states.pt... +0: [2022-11-29 18:14:10,094] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_26-model_00-model_states.pt. +0: [2022-11-29 18:14:10,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_27-model_00-model_states.pt... +0: [2022-11-29 18:14:10,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_27-model_00-model_states.pt. +0: [2022-11-29 18:14:10,169] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_28-model_00-model_states.pt... +0: [2022-11-29 18:14:10,245] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_28-model_00-model_states.pt. +0: [2022-11-29 18:14:10,245] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/layer_30-model_00-model_states.pt... +0: [2022-11-29 18:14:10,247] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/layer_30-model_00-model_states.pt. +0: [2022-11-29 18:14:10,248] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_1b1oscar/global_step1000/mp_rank_00_model_states.pt +0: [2022-11-29 18:14:10,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:14:10,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:14:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:14:10,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:14:10,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:14:10,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:14:10,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 18:14:10,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:14:10,550] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:14:10,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 18:14:10,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:14:10,551] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:14:10,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 18:14:10,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:14:10,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:14:10,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 18:14:10,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:14:10,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:14:10,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 18:14:10,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:14:10,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:14:10,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 18:14:10,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:14:10,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:14:10,587] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 18:14:10,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:14:10,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:14:10,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 18:14:10,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:14:10,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:14:10,607] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:14:10,607] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 18:14:10,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:14:10,615] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:14:10,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 18:14:10,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:14:10,616] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:14:10,616] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 18:14:10,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:14:10,616] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:14:10,616] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 18:14:10,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:14:10,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:14:10,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:14:10,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:14:10,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:14:10,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:14:10,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 18:14:10,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 18:14:10,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 18:14:10,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:14:10,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 18:14:10,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:14:10,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:14:10,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 18:14:10,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:14:10,599] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:14:10,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 18:14:10,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:14:10,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:14:10,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:14:10,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:14:10,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:14:10,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:14:10,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 18:14:10,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 18:14:10,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 18:14:10,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:14:10,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:14:10,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 18:14:10,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:14:10,637] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:14:10,637] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 18:14:10,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:14:10,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:14:10,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 18:14:10,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:14:10,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:14:10,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 18:14:10,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:14:10,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:14:10,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 18:14:10,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:14:10,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:14:10,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 18:14:10,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:14:10,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:14:10,644] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:14:10,644] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:14:10,644] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 18:14:10,645] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 18:14:10,645] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:14:10,645] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:14:10,645] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 18:14:10,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:14:10,665] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:14:10,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 18:14:10,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:14:10,666] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:14:10,666] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 18:14:10,666] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:14:10,666] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:14:10,666] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 18:14:10,689] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:14:10,689] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:14:10,689] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 18:14:10,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:14:10,690] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:14:10,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 18:14:10,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:14:10,691] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:14:10,691] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 18:14:10,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:14:10,691] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:14:10,691] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 18:14:10,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:14:10,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:14:10,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 18:14:10,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:14:10,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:14:10,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 18:14:10,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:14:10,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:14:10,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 18:14:10,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:14:10,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:14:10,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 18:14:10,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:14:10,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:14:10,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 18:14:10,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:14:10,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:14:10,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 18:14:10,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:14:10,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:14:10,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:14:10,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:14:10,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:14:10,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:14:10,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 18:14:10,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 18:14:10,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 18:14:10,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:14:10,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:14:10,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:14:10,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:14:10,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:14:10,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:14:10,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 18:14:10,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:14:10,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 18:14:10,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 18:14:10,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:14:10,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:14:10,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:14:10,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:14:10,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:14:10,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 18:14:10,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 18:14:10,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 18:14:10,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:14:10,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:14:10,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 18:14:10,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:14:10,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 18:14:10,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:14:10,920] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:14:10,920] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 18:14:10,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:14:10,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:14:10,920] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:14:10,920] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:14:10,920] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 18:14:10,920] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 18:14:10,927] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:14:10,927] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:14:10,927] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 18:14:10,928] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:14:10,928] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:14:10,928] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:14:10,928] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:14:10,928] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:14:10,928] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:14:10,928] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:14:10,928] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:14:10,928] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 18:14:10,928] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 18:14:10,928] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 18:14:10,928] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 18:14:10,956] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:14:10,957] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:14:10,957] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 18:14:10,964] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:14:10,964] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:14:10,964] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: successfully saved checkpoint at iteration 1000 to checkpoints_1b1oscar +7: time (ms) | save-checkpoint: 3129.32 +7: iteration 1010/ 2891 | consumed samples: 258560 | consumed tokens: 529530880 | elapsed time per iteration (s): 1.64 | learning rate: 1.527E-04 | global batch size: 256 | lm loss: 3.996400E+00 | grad norm: 0.481 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 156.540 | TFLOPs: 37.88 | +7: iteration 1020/ 2891 | consumed samples: 261120 | consumed tokens: 534773760 | elapsed time per iteration (s): 1.26 | learning rate: 1.518E-04 | global batch size: 256 | lm loss: 4.009910E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.599 | TFLOPs: 49.03 | +7: iteration 1030/ 2891 | consumed samples: 263680 | consumed tokens: 540016640 | elapsed time per iteration (s): 1.27 | learning rate: 1.509E-04 | global batch size: 256 | lm loss: 3.982069E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.359 | TFLOPs: 48.73 | +7: iteration 1040/ 2891 | consumed samples: 266240 | consumed tokens: 545259520 | elapsed time per iteration (s): 1.28 | learning rate: 1.501E-04 | global batch size: 256 | lm loss: 3.940005E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.621 | TFLOPs: 48.55 | +7: iteration 1050/ 2891 | consumed samples: 268800 | consumed tokens: 550502400 | elapsed time per iteration (s): 1.27 | learning rate: 1.492E-04 | global batch size: 256 | lm loss: 3.942002E+00 | grad norm: 0.403 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.508 | TFLOPs: 48.76 | +7: iteration 1060/ 2891 | consumed samples: 271360 | consumed tokens: 555745280 | elapsed time per iteration (s): 1.26 | learning rate: 1.483E-04 | global batch size: 256 | lm loss: 3.936320E+00 | grad norm: 0.419 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.655 | TFLOPs: 49.04 | +7: iteration 1070/ 2891 | consumed samples: 273920 | consumed tokens: 560988160 | elapsed time per iteration (s): 1.26 | learning rate: 1.474E-04 | global batch size: 256 | lm loss: 3.919482E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.552 | TFLOPs: 49.02 | +7: iteration 1080/ 2891 | consumed samples: 276480 | consumed tokens: 566231040 | elapsed time per iteration (s): 1.27 | learning rate: 1.465E-04 | global batch size: 256 | lm loss: 3.901269E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.907 | TFLOPs: 48.86 | +7: iteration 1090/ 2891 | consumed samples: 279040 | consumed tokens: 571473920 | elapsed time per iteration (s): 1.27 | learning rate: 1.456E-04 | global batch size: 256 | lm loss: 3.906593E+00 | grad norm: 0.522 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.336 | TFLOPs: 48.72 | +7: iteration 1100/ 2891 | consumed samples: 281600 | consumed tokens: 576716800 | elapsed time per iteration (s): 1.27 | learning rate: 1.447E-04 | global batch size: 256 | lm loss: 3.888079E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.856 | TFLOPs: 48.85 | +7: iteration 1110/ 2891 | consumed samples: 284160 | consumed tokens: 581959680 | elapsed time per iteration (s): 1.27 | learning rate: 1.438E-04 | global batch size: 256 | lm loss: 3.837761E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.764 | TFLOPs: 48.82 | +7: iteration 1120/ 2891 | consumed samples: 286720 | consumed tokens: 587202560 | elapsed time per iteration (s): 1.26 | learning rate: 1.428E-04 | global batch size: 256 | lm loss: 3.852570E+00 | grad norm: 0.424 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.667 | TFLOPs: 49.04 | +7: iteration 1130/ 2891 | consumed samples: 289280 | consumed tokens: 592445440 | elapsed time per iteration (s): 1.27 | learning rate: 1.419E-04 | global batch size: 256 | lm loss: 3.841681E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.243 | TFLOPs: 48.94 | +7: iteration 1140/ 2891 | consumed samples: 291840 | consumed tokens: 597688320 | elapsed time per iteration (s): 1.28 | learning rate: 1.410E-04 | global batch size: 256 | lm loss: 3.849986E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.721 | TFLOPs: 48.33 | +7: iteration 1150/ 2891 | consumed samples: 294400 | consumed tokens: 602931200 | elapsed time per iteration (s): 1.27 | learning rate: 1.401E-04 | global batch size: 256 | lm loss: 3.826727E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.036 | TFLOPs: 48.65 | +7: iteration 1160/ 2891 | consumed samples: 296960 | consumed tokens: 608174080 | elapsed time per iteration (s): 1.27 | learning rate: 1.391E-04 | global batch size: 256 | lm loss: 3.842875E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.792 | TFLOPs: 48.83 | +7: iteration 1170/ 2891 | consumed samples: 299520 | consumed tokens: 613416960 | elapsed time per iteration (s): 1.29 | learning rate: 1.382E-04 | global batch size: 256 | lm loss: 3.828712E+00 | grad norm: 0.397 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.131 | TFLOPs: 47.95 | +7: iteration 1180/ 2891 | consumed samples: 302080 | consumed tokens: 618659840 | elapsed time per iteration (s): 1.26 | learning rate: 1.372E-04 | global batch size: 256 | lm loss: 3.866740E+00 | grad norm: 1.616 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.516 | TFLOPs: 49.01 | +7: iteration 1190/ 2891 | consumed samples: 304640 | consumed tokens: 623902720 | elapsed time per iteration (s): 1.33 | learning rate: 1.363E-04 | global batch size: 256 | lm loss: 3.962951E+00 | grad norm: 0.722 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 191.885 | TFLOPs: 46.43 | +7: iteration 1200/ 2891 | consumed samples: 307200 | consumed tokens: 629145600 | elapsed time per iteration (s): 1.28 | learning rate: 1.354E-04 | global batch size: 256 | lm loss: 3.884757E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.930 | TFLOPs: 48.38 | +7: iteration 1210/ 2891 | consumed samples: 309760 | consumed tokens: 634388480 | elapsed time per iteration (s): 1.28 | learning rate: 1.344E-04 | global batch size: 256 | lm loss: 3.831664E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.369 | TFLOPs: 48.25 | +7: iteration 1220/ 2891 | consumed samples: 312320 | consumed tokens: 639631360 | elapsed time per iteration (s): 1.29 | learning rate: 1.335E-04 | global batch size: 256 | lm loss: 3.811860E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.972 | TFLOPs: 48.15 | +7: iteration 1230/ 2891 | consumed samples: 314880 | consumed tokens: 644874240 | elapsed time per iteration (s): 1.27 | learning rate: 1.325E-04 | global batch size: 256 | lm loss: 3.793566E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.663 | TFLOPs: 48.80 | +7: iteration 1240/ 2891 | consumed samples: 317440 | consumed tokens: 650117120 | elapsed time per iteration (s): 1.28 | learning rate: 1.315E-04 | global batch size: 256 | lm loss: 3.810783E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.884 | TFLOPs: 48.37 | +7: iteration 1250/ 2891 | consumed samples: 320000 | consumed tokens: 655360000 | elapsed time per iteration (s): 1.27 | learning rate: 1.306E-04 | global batch size: 256 | lm loss: 3.774150E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.684 | TFLOPs: 48.81 | +7: iteration 1260/ 2891 | consumed samples: 322560 | consumed tokens: 660602880 | elapsed time per iteration (s): 1.27 | learning rate: 1.296E-04 | global batch size: 256 | lm loss: 3.774349E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.735 | TFLOPs: 48.82 | +7: iteration 1270/ 2891 | consumed samples: 325120 | consumed tokens: 665845760 | elapsed time per iteration (s): 1.27 | learning rate: 1.287E-04 | global batch size: 256 | lm loss: 3.763657E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.916 | TFLOPs: 48.62 | +7: iteration 1280/ 2891 | consumed samples: 327680 | consumed tokens: 671088640 | elapsed time per iteration (s): 1.27 | learning rate: 1.277E-04 | global batch size: 256 | lm loss: 3.749620E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.071 | TFLOPs: 48.90 | +7: iteration 1290/ 2891 | consumed samples: 330240 | consumed tokens: 676331520 | elapsed time per iteration (s): 1.27 | learning rate: 1.267E-04 | global batch size: 256 | lm loss: 3.735962E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.882 | TFLOPs: 48.61 | +7: iteration 1300/ 2891 | consumed samples: 332800 | consumed tokens: 681574400 | elapsed time per iteration (s): 1.27 | learning rate: 1.258E-04 | global batch size: 256 | lm loss: 3.754087E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.037 | TFLOPs: 48.89 | +7: iteration 1310/ 2891 | consumed samples: 335360 | consumed tokens: 686817280 | elapsed time per iteration (s): 1.28 | learning rate: 1.248E-04 | global batch size: 256 | lm loss: 3.736427E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.686 | TFLOPs: 48.56 | +7: iteration 1320/ 2891 | consumed samples: 337920 | consumed tokens: 692060160 | elapsed time per iteration (s): 1.28 | learning rate: 1.238E-04 | global batch size: 256 | lm loss: 3.726226E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.494 | TFLOPs: 48.52 | +7: iteration 1330/ 2891 | consumed samples: 340480 | consumed tokens: 697303040 | elapsed time per iteration (s): 1.30 | learning rate: 1.228E-04 | global batch size: 256 | lm loss: 3.697341E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 197.198 | TFLOPs: 47.72 | +7: iteration 1340/ 2891 | consumed samples: 343040 | consumed tokens: 702545920 | elapsed time per iteration (s): 1.30 | learning rate: 1.218E-04 | global batch size: 256 | lm loss: 3.695453E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 196.504 | TFLOPs: 47.55 | +7: iteration 1350/ 2891 | consumed samples: 345600 | consumed tokens: 707788800 | elapsed time per iteration (s): 1.27 | learning rate: 1.209E-04 | global batch size: 256 | lm loss: 3.699658E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.928 | TFLOPs: 48.86 | +7: iteration 1360/ 2891 | consumed samples: 348160 | consumed tokens: 713031680 | elapsed time per iteration (s): 1.27 | learning rate: 1.199E-04 | global batch size: 256 | lm loss: 3.695967E+00 | grad norm: 0.437 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.434 | TFLOPs: 48.74 | +7: iteration 1370/ 2891 | consumed samples: 350720 | consumed tokens: 718274560 | elapsed time per iteration (s): 1.27 | learning rate: 1.189E-04 | global batch size: 256 | lm loss: 3.675379E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.339 | TFLOPs: 48.96 | +7: iteration 1380/ 2891 | consumed samples: 353280 | consumed tokens: 723517440 | elapsed time per iteration (s): 1.28 | learning rate: 1.179E-04 | global batch size: 256 | lm loss: 3.667464E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.286 | TFLOPs: 48.47 | +7: iteration 1390/ 2891 | consumed samples: 355840 | consumed tokens: 728760320 | elapsed time per iteration (s): 1.27 | learning rate: 1.169E-04 | global batch size: 256 | lm loss: 3.661503E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.447 | TFLOPs: 48.75 | +7: iteration 1400/ 2891 | consumed samples: 358400 | consumed tokens: 734003200 | elapsed time per iteration (s): 1.27 | learning rate: 1.160E-04 | global batch size: 256 | lm loss: 3.677907E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.015 | TFLOPs: 48.89 | +7: iteration 1410/ 2891 | consumed samples: 360960 | consumed tokens: 739246080 | elapsed time per iteration (s): 1.27 | learning rate: 1.150E-04 | global batch size: 256 | lm loss: 3.661739E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.174 | TFLOPs: 48.68 | +7: iteration 1420/ 2891 | consumed samples: 363520 | consumed tokens: 744488960 | elapsed time per iteration (s): 1.27 | learning rate: 1.140E-04 | global batch size: 256 | lm loss: 3.643872E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.043 | TFLOPs: 48.89 | +7: iteration 1430/ 2891 | consumed samples: 366080 | consumed tokens: 749731840 | elapsed time per iteration (s): 1.27 | learning rate: 1.130E-04 | global batch size: 256 | lm loss: 3.680123E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.754 | TFLOPs: 48.82 | +7: iteration 1440/ 2891 | consumed samples: 368640 | consumed tokens: 754974720 | elapsed time per iteration (s): 1.27 | learning rate: 1.120E-04 | global batch size: 256 | lm loss: 3.638352E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.471 | TFLOPs: 48.75 | +7: iteration 1450/ 2891 | consumed samples: 371200 | consumed tokens: 760217600 | elapsed time per iteration (s): 1.27 | learning rate: 1.110E-04 | global batch size: 256 | lm loss: 3.658081E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.263 | TFLOPs: 48.70 | +7: iteration 1460/ 2891 | consumed samples: 373760 | consumed tokens: 765460480 | elapsed time per iteration (s): 1.27 | learning rate: 1.100E-04 | global batch size: 256 | lm loss: 3.639560E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.982 | TFLOPs: 48.88 | +7: iteration 1470/ 2891 | consumed samples: 376320 | consumed tokens: 770703360 | elapsed time per iteration (s): 1.26 | learning rate: 1.090E-04 | global batch size: 256 | lm loss: 3.652111E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.642 | TFLOPs: 49.04 | +7: iteration 1480/ 2891 | consumed samples: 378880 | consumed tokens: 775946240 | elapsed time per iteration (s): 1.27 | learning rate: 1.081E-04 | global batch size: 256 | lm loss: 3.657534E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.979 | TFLOPs: 48.88 | +7: iteration 1490/ 2891 | consumed samples: 381440 | consumed tokens: 781189120 | elapsed time per iteration (s): 1.26 | learning rate: 1.071E-04 | global batch size: 256 | lm loss: 3.601139E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.408 | TFLOPs: 48.98 | +7: iteration 1500/ 2891 | consumed samples: 384000 | consumed tokens: 786432000 | elapsed time per iteration (s): 1.27 | learning rate: 1.061E-04 | global batch size: 256 | lm loss: 3.618388E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.004 | TFLOPs: 48.88 | +7: iteration 1510/ 2891 | consumed samples: 386560 | consumed tokens: 791674880 | elapsed time per iteration (s): 1.26 | learning rate: 1.051E-04 | global batch size: 256 | lm loss: 3.635867E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.663 | TFLOPs: 49.04 | +7: iteration 1520/ 2891 | consumed samples: 389120 | consumed tokens: 796917760 | elapsed time per iteration (s): 1.27 | learning rate: 1.041E-04 | global batch size: 256 | lm loss: 3.604443E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.362 | TFLOPs: 48.97 | +7: iteration 1530/ 2891 | consumed samples: 391680 | consumed tokens: 802160640 | elapsed time per iteration (s): 1.26 | learning rate: 1.031E-04 | global batch size: 256 | lm loss: 3.589257E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.565 | TFLOPs: 49.02 | +7: iteration 1540/ 2891 | consumed samples: 394240 | consumed tokens: 807403520 | elapsed time per iteration (s): 1.27 | learning rate: 1.021E-04 | global batch size: 256 | lm loss: 3.625220E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.572 | TFLOPs: 48.78 | +7: iteration 1550/ 2891 | consumed samples: 396800 | consumed tokens: 812646400 | elapsed time per iteration (s): 1.26 | learning rate: 1.012E-04 | global batch size: 256 | lm loss: 3.578123E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.650 | TFLOPs: 49.04 | +7: iteration 1560/ 2891 | consumed samples: 399360 | consumed tokens: 817889280 | elapsed time per iteration (s): 1.27 | learning rate: 1.002E-04 | global batch size: 256 | lm loss: 3.570392E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.324 | TFLOPs: 48.96 | +7: iteration 1570/ 2891 | consumed samples: 401920 | consumed tokens: 823132160 | elapsed time per iteration (s): 1.27 | learning rate: 9.919E-05 | global batch size: 256 | lm loss: 3.570094E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.603 | TFLOPs: 48.79 | +7: iteration 1580/ 2891 | consumed samples: 404480 | consumed tokens: 828375040 | elapsed time per iteration (s): 1.27 | learning rate: 9.821E-05 | global batch size: 256 | lm loss: 3.544429E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.902 | TFLOPs: 48.86 | +7: iteration 1590/ 2891 | consumed samples: 407040 | consumed tokens: 833617920 | elapsed time per iteration (s): 1.27 | learning rate: 9.723E-05 | global batch size: 256 | lm loss: 3.551081E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.404 | TFLOPs: 48.74 | +7: iteration 1600/ 2891 | consumed samples: 409600 | consumed tokens: 838860800 | elapsed time per iteration (s): 1.27 | learning rate: 9.626E-05 | global batch size: 256 | lm loss: 3.587671E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.038 | TFLOPs: 48.89 | +7: iteration 1610/ 2891 | consumed samples: 412160 | consumed tokens: 844103680 | elapsed time per iteration (s): 1.28 | learning rate: 9.528E-05 | global batch size: 256 | lm loss: 3.555887E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.590 | TFLOPs: 48.54 | +7: iteration 1620/ 2891 | consumed samples: 414720 | consumed tokens: 849346560 | elapsed time per iteration (s): 1.26 | learning rate: 9.431E-05 | global batch size: 256 | lm loss: 3.570174E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.540 | TFLOPs: 49.01 | +7: iteration 1630/ 2891 | consumed samples: 417280 | consumed tokens: 854589440 | elapsed time per iteration (s): 1.26 | learning rate: 9.334E-05 | global batch size: 256 | lm loss: 3.569979E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.403 | TFLOPs: 48.98 | +7: iteration 1640/ 2891 | consumed samples: 419840 | consumed tokens: 859832320 | elapsed time per iteration (s): 1.26 | learning rate: 9.237E-05 | global batch size: 256 | lm loss: 3.556800E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.757 | TFLOPs: 49.07 | +7: iteration 1650/ 2891 | consumed samples: 422400 | consumed tokens: 865075200 | elapsed time per iteration (s): 1.27 | learning rate: 9.140E-05 | global batch size: 256 | lm loss: 3.566114E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.329 | TFLOPs: 48.72 | +7: iteration 1660/ 2891 | consumed samples: 424960 | consumed tokens: 870318080 | elapsed time per iteration (s): 1.27 | learning rate: 9.043E-05 | global batch size: 256 | lm loss: 3.557945E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.940 | TFLOPs: 48.63 | +7: iteration 1670/ 2891 | consumed samples: 427520 | consumed tokens: 875560960 | elapsed time per iteration (s): 1.26 | learning rate: 8.947E-05 | global batch size: 256 | lm loss: 3.550856E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.665 | TFLOPs: 49.04 | +7: iteration 1680/ 2891 | consumed samples: 430080 | consumed tokens: 880803840 | elapsed time per iteration (s): 1.27 | learning rate: 8.851E-05 | global batch size: 256 | lm loss: 3.521834E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.601 | TFLOPs: 48.79 | +7: iteration 1690/ 2891 | consumed samples: 432640 | consumed tokens: 886046720 | elapsed time per iteration (s): 1.27 | learning rate: 8.755E-05 | global batch size: 256 | lm loss: 3.559994E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.066 | TFLOPs: 48.90 | +7: iteration 1700/ 2891 | consumed samples: 435200 | consumed tokens: 891289600 | elapsed time per iteration (s): 1.27 | learning rate: 8.660E-05 | global batch size: 256 | lm loss: 3.521171E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.545 | TFLOPs: 48.77 | +7: iteration 1710/ 2891 | consumed samples: 437760 | consumed tokens: 896532480 | elapsed time per iteration (s): 1.26 | learning rate: 8.565E-05 | global batch size: 256 | lm loss: 3.513585E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.689 | TFLOPs: 49.05 | +7: iteration 1720/ 2891 | consumed samples: 440320 | consumed tokens: 901775360 | elapsed time per iteration (s): 1.28 | learning rate: 8.470E-05 | global batch size: 256 | lm loss: 3.536938E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.841 | TFLOPs: 48.36 | +7: iteration 1730/ 2891 | consumed samples: 442880 | consumed tokens: 907018240 | elapsed time per iteration (s): 1.27 | learning rate: 8.375E-05 | global batch size: 256 | lm loss: 3.513513E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.051 | TFLOPs: 48.89 | +7: iteration 1740/ 2891 | consumed samples: 445440 | consumed tokens: 912261120 | elapsed time per iteration (s): 1.27 | learning rate: 8.281E-05 | global batch size: 256 | lm loss: 3.525639E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.909 | TFLOPs: 48.86 | +7: iteration 1750/ 2891 | consumed samples: 448000 | consumed tokens: 917504000 | elapsed time per iteration (s): 1.26 | learning rate: 8.187E-05 | global batch size: 256 | lm loss: 3.530594E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.688 | TFLOPs: 49.05 | +7: iteration 1760/ 2891 | consumed samples: 450560 | consumed tokens: 922746880 | elapsed time per iteration (s): 1.27 | learning rate: 8.093E-05 | global batch size: 256 | lm loss: 3.487004E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.088 | TFLOPs: 48.90 | +7: iteration 1770/ 2891 | consumed samples: 453120 | consumed tokens: 927989760 | elapsed time per iteration (s): 1.27 | learning rate: 8.000E-05 | global batch size: 256 | lm loss: 3.507674E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.355 | TFLOPs: 48.97 | +7: iteration 1780/ 2891 | consumed samples: 455680 | consumed tokens: 933232640 | elapsed time per iteration (s): 1.28 | learning rate: 7.907E-05 | global batch size: 256 | lm loss: 3.508082E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.349 | TFLOPs: 48.24 | +7: iteration 1790/ 2891 | consumed samples: 458240 | consumed tokens: 938475520 | elapsed time per iteration (s): 1.26 | learning rate: 7.814E-05 | global batch size: 256 | lm loss: 3.507079E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.628 | TFLOPs: 49.03 | +7: iteration 1800/ 2891 | consumed samples: 460800 | consumed tokens: 943718400 | elapsed time per iteration (s): 1.28 | learning rate: 7.722E-05 | global batch size: 256 | lm loss: 3.517303E+00 | grad norm: 0.560 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.505 | TFLOPs: 48.52 | +7: iteration 1810/ 2891 | consumed samples: 463360 | consumed tokens: 948961280 | elapsed time per iteration (s): 1.26 | learning rate: 7.630E-05 | global batch size: 256 | lm loss: 3.495737E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.627 | TFLOPs: 49.03 | +7: iteration 1820/ 2891 | consumed samples: 465920 | consumed tokens: 954204160 | elapsed time per iteration (s): 1.26 | learning rate: 7.539E-05 | global batch size: 256 | lm loss: 3.479797E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.540 | TFLOPs: 49.01 | +7: iteration 1830/ 2891 | consumed samples: 468480 | consumed tokens: 959447040 | elapsed time per iteration (s): 1.26 | learning rate: 7.448E-05 | global batch size: 256 | lm loss: 3.524964E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.529 | TFLOPs: 49.01 | +7: iteration 1840/ 2891 | consumed samples: 471040 | consumed tokens: 964689920 | elapsed time per iteration (s): 1.29 | learning rate: 7.357E-05 | global batch size: 256 | lm loss: 3.498029E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 197.864 | TFLOPs: 47.88 | +7: iteration 1850/ 2891 | consumed samples: 473600 | consumed tokens: 969932800 | elapsed time per iteration (s): 1.26 | learning rate: 7.267E-05 | global batch size: 256 | lm loss: 3.489665E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.495 | TFLOPs: 49.00 | +7: iteration 1860/ 2891 | consumed samples: 476160 | consumed tokens: 975175680 | elapsed time per iteration (s): 1.26 | learning rate: 7.178E-05 | global batch size: 256 | lm loss: 3.487114E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.560 | TFLOPs: 49.02 | +7: iteration 1870/ 2891 | consumed samples: 478720 | consumed tokens: 980418560 | elapsed time per iteration (s): 1.27 | learning rate: 7.088E-05 | global batch size: 256 | lm loss: 3.447561E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.912 | TFLOPs: 48.62 | +7: iteration 1880/ 2891 | consumed samples: 481280 | consumed tokens: 985661440 | elapsed time per iteration (s): 1.26 | learning rate: 7.000E-05 | global batch size: 256 | lm loss: 3.454849E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.615 | TFLOPs: 49.03 | +7: iteration 1890/ 2891 | consumed samples: 483840 | consumed tokens: 990904320 | elapsed time per iteration (s): 1.26 | learning rate: 6.912E-05 | global batch size: 256 | lm loss: 3.477499E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.576 | TFLOPs: 49.02 | +7: iteration 1900/ 2891 | consumed samples: 486400 | consumed tokens: 996147200 | elapsed time per iteration (s): 1.26 | learning rate: 6.824E-05 | global batch size: 256 | lm loss: 3.466372E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.601 | TFLOPs: 49.03 | +7: iteration 1910/ 2891 | consumed samples: 488960 | consumed tokens: 1001390080 | elapsed time per iteration (s): 1.26 | learning rate: 6.737E-05 | global batch size: 256 | lm loss: 3.483150E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.612 | TFLOPs: 49.03 | +7: iteration 1920/ 2891 | consumed samples: 491520 | consumed tokens: 1006632960 | elapsed time per iteration (s): 1.26 | learning rate: 6.650E-05 | global batch size: 256 | lm loss: 3.441427E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.549 | TFLOPs: 49.01 | +7: iteration 1930/ 2891 | consumed samples: 494080 | consumed tokens: 1011875840 | elapsed time per iteration (s): 1.26 | learning rate: 6.564E-05 | global batch size: 256 | lm loss: 3.454887E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.612 | TFLOPs: 49.03 | +7: iteration 1940/ 2891 | consumed samples: 496640 | consumed tokens: 1017118720 | elapsed time per iteration (s): 1.26 | learning rate: 6.478E-05 | global batch size: 256 | lm loss: 3.479169E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.663 | TFLOPs: 49.04 | +7: iteration 1950/ 2891 | consumed samples: 499200 | consumed tokens: 1022361600 | elapsed time per iteration (s): 1.26 | learning rate: 6.393E-05 | global batch size: 256 | lm loss: 3.480439E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.621 | TFLOPs: 49.03 | +7: iteration 1960/ 2891 | consumed samples: 501760 | consumed tokens: 1027604480 | elapsed time per iteration (s): 1.28 | learning rate: 6.308E-05 | global batch size: 256 | lm loss: 3.474596E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.492 | TFLOPs: 48.52 | +7: iteration 1970/ 2891 | consumed samples: 504320 | consumed tokens: 1032847360 | elapsed time per iteration (s): 1.26 | learning rate: 6.224E-05 | global batch size: 256 | lm loss: 3.474303E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.641 | TFLOPs: 49.04 | +7: iteration 1980/ 2891 | consumed samples: 506880 | consumed tokens: 1038090240 | elapsed time per iteration (s): 1.27 | learning rate: 6.141E-05 | global batch size: 256 | lm loss: 3.454424E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.404 | TFLOPs: 48.74 | +7: iteration 1990/ 2891 | consumed samples: 509440 | consumed tokens: 1043333120 | elapsed time per iteration (s): 1.26 | learning rate: 6.058E-05 | global batch size: 256 | lm loss: 3.442164E+00 | grad norm: 0.387 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.639 | TFLOPs: 49.04 | +0: [2022-11-29 18:35:21,641] [INFO] [logging.py:68:log_dist] [Rank 0] step=2000, skipped=0, lr=[5.9757828883278194e-05, 5.9757828883278194e-05, 5.9757828883278194e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 2000/ 2891 | consumed samples: 512000 | consumed tokens: 1048576000 | elapsed time per iteration (s): 1.26 | learning rate: 5.976E-05 | global batch size: 256 | lm loss: 3.447073E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.649 | TFLOPs: 49.04 | +0: steps: 2000 loss: 3.4402 iter time (s): 1.285 samples/sec: 199.288 +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 2000 | lm loss value: 3.345912E+00 | lm loss PPL: 2.838647E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 2000 to checkpoints_1b1oscar +0: [2022-11-29 18:35:22,064] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step2000 is begin to save! +0: [2022-11-29 18:35:22,067] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:35:22,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:35:22,265] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:35:22,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:35:22,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:35:22,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:35:22,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:35:22,502] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:35:22,502] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:35:22,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:35:22,577] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:35:22,650] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:35:22,650] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:35:22,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:35:22,721] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:35:22,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:35:22,797] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:35:22,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:35:22,872] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:35:22,947] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:35:22,948] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:35:23,022] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:35:23,023] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_13-model_00-model_states.pt... +0: [2022-11-29 18:35:23,099] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_13-model_00-model_states.pt. +0: [2022-11-29 18:35:23,099] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:35:23,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:35:23,224] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_15-model_00-model_states.pt... +0: [2022-11-29 18:35:23,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_15-model_00-model_states.pt. +0: [2022-11-29 18:35:23,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_16-model_00-model_states.pt... +0: [2022-11-29 18:35:23,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_16-model_00-model_states.pt. +0: [2022-11-29 18:35:23,376] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_17-model_00-model_states.pt... +0: [2022-11-29 18:35:23,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_17-model_00-model_states.pt. +0: [2022-11-29 18:35:23,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_18-model_00-model_states.pt... +0: [2022-11-29 18:35:23,525] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_18-model_00-model_states.pt. +0: [2022-11-29 18:35:23,526] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_19-model_00-model_states.pt... +0: [2022-11-29 18:35:23,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_19-model_00-model_states.pt. +0: [2022-11-29 18:35:23,599] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_20-model_00-model_states.pt... +0: [2022-11-29 18:35:23,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_20-model_00-model_states.pt. +0: [2022-11-29 18:35:23,677] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_21-model_00-model_states.pt... +0: [2022-11-29 18:35:23,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_21-model_00-model_states.pt. +0: [2022-11-29 18:35:23,753] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_22-model_00-model_states.pt... +0: [2022-11-29 18:35:23,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_22-model_00-model_states.pt. +0: [2022-11-29 18:35:23,826] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_23-model_00-model_states.pt... +0: [2022-11-29 18:35:23,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_23-model_00-model_states.pt. +0: [2022-11-29 18:35:23,903] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_24-model_00-model_states.pt... +0: [2022-11-29 18:35:23,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_24-model_00-model_states.pt. +0: [2022-11-29 18:35:23,978] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_25-model_00-model_states.pt... +0: [2022-11-29 18:35:24,050] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_25-model_00-model_states.pt. +0: [2022-11-29 18:35:24,050] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_26-model_00-model_states.pt... +0: [2022-11-29 18:35:24,124] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_26-model_00-model_states.pt. +0: [2022-11-29 18:35:24,124] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_27-model_00-model_states.pt... +0: [2022-11-29 18:35:24,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_27-model_00-model_states.pt. +0: [2022-11-29 18:35:24,199] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_28-model_00-model_states.pt... +0: [2022-11-29 18:35:24,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_28-model_00-model_states.pt. +0: [2022-11-29 18:35:24,274] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/layer_30-model_00-model_states.pt... +0: [2022-11-29 18:35:24,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/layer_30-model_00-model_states.pt. +0: [2022-11-29 18:35:24,278] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_1b1oscar/global_step2000/mp_rank_00_model_states.pt +0: [2022-11-29 18:35:24,279] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:35:24,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:35:24,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:35:24,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:35:24,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:35:24,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:35:24,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 18:35:24,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:35:24,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:35:24,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 18:35:24,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:35:24,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:35:24,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 18:35:24,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:35:24,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:35:24,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 18:35:24,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:35:24,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:35:24,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 18:35:24,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:35:24,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:35:24,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 18:35:24,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:35:24,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:35:24,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 18:35:24,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:35:24,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:35:24,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 18:35:24,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:35:24,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:35:24,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 18:35:24,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:35:24,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:35:24,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 18:35:24,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:35:24,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:35:24,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 18:35:24,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:35:24,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:35:24,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 18:35:24,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:35:24,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:35:24,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 18:35:24,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:35:24,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:35:24,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 18:35:24,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:35:24,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:35:24,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 18:35:24,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:35:24,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:35:24,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 18:35:24,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:35:24,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:35:24,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 18:35:24,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:35:24,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:35:24,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 18:35:24,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:35:24,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:35:24,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 18:35:24,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:35:24,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:35:24,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:35:24,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 18:35:24,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:35:24,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:35:24,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 18:35:24,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:35:24,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:35:24,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 18:35:24,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:35:24,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:35:24,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:35:24,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 18:35:24,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:35:24,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:35:24,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 18:35:24,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:35:24,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:35:24,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 18:35:24,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:35:24,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:35:24,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 18:35:24,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:35:24,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:35:24,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 18:35:24,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:35:24,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:35:24,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 18:35:24,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:35:24,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:35:24,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 18:35:24,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:35:24,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:35:24,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:35:24,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 18:35:24,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:35:24,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 18:35:24,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +2: [2022-11-29 18:35:24,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +3: [2022-11-29 18:35:24,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 18:35:24,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 18:35:24,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:35:24,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:35:24,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +2: [2022-11-29 18:35:24,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +3: [2022-11-29 18:35:24,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 18:35:24,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 18:35:24,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:35:24,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:35:24,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 18:35:24,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:35:24,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:35:24,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 18:35:24,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:35:24,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:35:24,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:35:24,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:35:24,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 18:35:24,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 18:35:24,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:35:24,578] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:35:24,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 18:35:24,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:35:24,578] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:35:24,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 18:35:24,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:35:24,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:35:24,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:35:24,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 18:35:24,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +6: [2022-11-29 18:35:24,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:35:24,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 18:35:24,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:35:24,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 18:35:24,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:35:24,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:35:24,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 18:35:24,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:35:24,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:35:24,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 18:35:24,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:35:24,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:35:24,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 18:35:24,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:35:24,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:35:24,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 18:35:24,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:35:24,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:35:24,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 18:35:24,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:35:24,588] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:35:24,588] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 18:35:24,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:35:24,588] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:35:24,588] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 18:35:24,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:35:24,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:35:24,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 18:35:24,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:35:24,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:35:24,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 18:35:24,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:35:24,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:35:24,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:35:24,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 18:35:24,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:35:24,605] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:35:24,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 18:35:24,606] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:35:24,606] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:35:24,606] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:35:24,606] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:35:24,606] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:35:24,606] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:35:24,606] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 18:35:24,606] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 18:35:24,606] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 18:35:24,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:35:24,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 18:35:24,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:35:24,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:35:24,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 18:35:24,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:35:24,609] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:35:24,609] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 18:35:24,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:35:24,611] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:35:24,611] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 18:35:24,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:35:24,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:35:24,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 18:35:24,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:35:24,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: successfully saved checkpoint at iteration 2000 to checkpoints_1b1oscar +7: time (ms) | save-checkpoint: 2769.97 +7: iteration 2010/ 2891 | consumed samples: 514560 | consumed tokens: 1053818880 | elapsed time per iteration (s): 1.60 | learning rate: 5.894E-05 | global batch size: 256 | lm loss: 3.431136E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 159.674 | TFLOPs: 38.64 | +7: iteration 2020/ 2891 | consumed samples: 517120 | consumed tokens: 1059061760 | elapsed time per iteration (s): 1.28 | learning rate: 5.813E-05 | global batch size: 256 | lm loss: 3.434014E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.733 | TFLOPs: 48.58 | +7: iteration 2030/ 2891 | consumed samples: 519680 | consumed tokens: 1064304640 | elapsed time per iteration (s): 1.27 | learning rate: 5.733E-05 | global batch size: 256 | lm loss: 3.448711E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.867 | TFLOPs: 48.85 | +7: iteration 2040/ 2891 | consumed samples: 522240 | consumed tokens: 1069547520 | elapsed time per iteration (s): 1.26 | learning rate: 5.653E-05 | global batch size: 256 | lm loss: 3.415279E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.592 | TFLOPs: 49.03 | +7: iteration 2050/ 2891 | consumed samples: 524800 | consumed tokens: 1074790400 | elapsed time per iteration (s): 1.26 | learning rate: 5.574E-05 | global batch size: 256 | lm loss: 3.419112E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.570 | TFLOPs: 49.02 | +7: iteration 2060/ 2891 | consumed samples: 527360 | consumed tokens: 1080033280 | elapsed time per iteration (s): 1.27 | learning rate: 5.495E-05 | global batch size: 256 | lm loss: 3.421627E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.406 | TFLOPs: 48.74 | +7: iteration 2070/ 2891 | consumed samples: 529920 | consumed tokens: 1085276160 | elapsed time per iteration (s): 1.27 | learning rate: 5.418E-05 | global batch size: 256 | lm loss: 3.406310E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.987 | TFLOPs: 48.88 | +7: iteration 2080/ 2891 | consumed samples: 532480 | consumed tokens: 1090519040 | elapsed time per iteration (s): 1.26 | learning rate: 5.340E-05 | global batch size: 256 | lm loss: 3.414038E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.486 | TFLOPs: 49.00 | +7: iteration 2090/ 2891 | consumed samples: 535040 | consumed tokens: 1095761920 | elapsed time per iteration (s): 1.27 | learning rate: 5.264E-05 | global batch size: 256 | lm loss: 3.394331E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.650 | TFLOPs: 48.80 | +7: iteration 2100/ 2891 | consumed samples: 537600 | consumed tokens: 1101004800 | elapsed time per iteration (s): 1.26 | learning rate: 5.188E-05 | global batch size: 256 | lm loss: 3.416785E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.593 | TFLOPs: 49.03 | +7: iteration 2110/ 2891 | consumed samples: 540160 | consumed tokens: 1106247680 | elapsed time per iteration (s): 1.26 | learning rate: 5.113E-05 | global batch size: 256 | lm loss: 3.430867E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.427 | TFLOPs: 48.99 | +7: iteration 2120/ 2891 | consumed samples: 542720 | consumed tokens: 1111490560 | elapsed time per iteration (s): 1.26 | learning rate: 5.039E-05 | global batch size: 256 | lm loss: 3.407412E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.602 | TFLOPs: 49.03 | +7: iteration 2130/ 2891 | consumed samples: 545280 | consumed tokens: 1116733440 | elapsed time per iteration (s): 1.26 | learning rate: 4.965E-05 | global batch size: 256 | lm loss: 3.400624E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.498 | TFLOPs: 49.00 | +7: iteration 2140/ 2891 | consumed samples: 547840 | consumed tokens: 1121976320 | elapsed time per iteration (s): 1.26 | learning rate: 4.892E-05 | global batch size: 256 | lm loss: 3.414149E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.562 | TFLOPs: 49.02 | +7: iteration 2150/ 2891 | consumed samples: 550400 | consumed tokens: 1127219200 | elapsed time per iteration (s): 1.26 | learning rate: 4.820E-05 | global batch size: 256 | lm loss: 3.407611E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.557 | TFLOPs: 49.02 | +7: iteration 2160/ 2891 | consumed samples: 552960 | consumed tokens: 1132462080 | elapsed time per iteration (s): 1.26 | learning rate: 4.749E-05 | global batch size: 256 | lm loss: 3.430661E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.517 | TFLOPs: 49.01 | +7: iteration 2170/ 2891 | consumed samples: 555520 | consumed tokens: 1137704960 | elapsed time per iteration (s): 1.26 | learning rate: 4.678E-05 | global batch size: 256 | lm loss: 3.402907E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.535 | TFLOPs: 49.01 | +7: iteration 2180/ 2891 | consumed samples: 558080 | consumed tokens: 1142947840 | elapsed time per iteration (s): 1.26 | learning rate: 4.608E-05 | global batch size: 256 | lm loss: 3.398573E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.468 | TFLOPs: 49.00 | +7: iteration 2190/ 2891 | consumed samples: 560640 | consumed tokens: 1148190720 | elapsed time per iteration (s): 1.27 | learning rate: 4.539E-05 | global batch size: 256 | lm loss: 3.400523E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.272 | TFLOPs: 48.71 | +7: iteration 2200/ 2891 | consumed samples: 563200 | consumed tokens: 1153433600 | elapsed time per iteration (s): 1.26 | learning rate: 4.471E-05 | global batch size: 256 | lm loss: 3.393715E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.607 | TFLOPs: 49.03 | +7: iteration 2210/ 2891 | consumed samples: 565760 | consumed tokens: 1158676480 | elapsed time per iteration (s): 1.26 | learning rate: 4.403E-05 | global batch size: 256 | lm loss: 3.393682E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.543 | TFLOPs: 49.01 | +7: iteration 2220/ 2891 | consumed samples: 568320 | consumed tokens: 1163919360 | elapsed time per iteration (s): 1.26 | learning rate: 4.336E-05 | global batch size: 256 | lm loss: 3.397488E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.628 | TFLOPs: 49.03 | +7: iteration 2230/ 2891 | consumed samples: 570880 | consumed tokens: 1169162240 | elapsed time per iteration (s): 1.26 | learning rate: 4.270E-05 | global batch size: 256 | lm loss: 3.383004E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.534 | TFLOPs: 49.01 | +7: iteration 2240/ 2891 | consumed samples: 573440 | consumed tokens: 1174405120 | elapsed time per iteration (s): 1.26 | learning rate: 4.205E-05 | global batch size: 256 | lm loss: 3.405868E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.559 | TFLOPs: 49.02 | +7: iteration 2250/ 2891 | consumed samples: 576000 | consumed tokens: 1179648000 | elapsed time per iteration (s): 1.26 | learning rate: 4.141E-05 | global batch size: 256 | lm loss: 3.392905E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.391 | TFLOPs: 48.98 | +7: iteration 2260/ 2891 | consumed samples: 578560 | consumed tokens: 1184890880 | elapsed time per iteration (s): 1.26 | learning rate: 4.077E-05 | global batch size: 256 | lm loss: 3.378339E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.661 | TFLOPs: 49.04 | +7: iteration 2270/ 2891 | consumed samples: 581120 | consumed tokens: 1190133760 | elapsed time per iteration (s): 1.26 | learning rate: 4.014E-05 | global batch size: 256 | lm loss: 3.384299E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.470 | TFLOPs: 49.00 | +7: iteration 2280/ 2891 | consumed samples: 583680 | consumed tokens: 1195376640 | elapsed time per iteration (s): 1.26 | learning rate: 3.953E-05 | global batch size: 256 | lm loss: 3.391397E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.548 | TFLOPs: 49.01 | +7: iteration 2290/ 2891 | consumed samples: 586240 | consumed tokens: 1200619520 | elapsed time per iteration (s): 1.26 | learning rate: 3.892E-05 | global batch size: 256 | lm loss: 3.399052E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.479 | TFLOPs: 49.00 | +7: iteration 2300/ 2891 | consumed samples: 588800 | consumed tokens: 1205862400 | elapsed time per iteration (s): 1.26 | learning rate: 3.831E-05 | global batch size: 256 | lm loss: 3.367217E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.587 | TFLOPs: 49.02 | +7: iteration 2310/ 2891 | consumed samples: 591360 | consumed tokens: 1211105280 | elapsed time per iteration (s): 1.28 | learning rate: 3.772E-05 | global batch size: 256 | lm loss: 3.377293E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.047 | TFLOPs: 48.41 | +7: iteration 2320/ 2891 | consumed samples: 593920 | consumed tokens: 1216348160 | elapsed time per iteration (s): 1.26 | learning rate: 3.714E-05 | global batch size: 256 | lm loss: 3.359563E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.614 | TFLOPs: 49.03 | +7: iteration 2330/ 2891 | consumed samples: 596480 | consumed tokens: 1221591040 | elapsed time per iteration (s): 1.26 | learning rate: 3.656E-05 | global batch size: 256 | lm loss: 3.386751E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.408 | TFLOPs: 48.98 | +7: iteration 2340/ 2891 | consumed samples: 599040 | consumed tokens: 1226833920 | elapsed time per iteration (s): 1.26 | learning rate: 3.600E-05 | global batch size: 256 | lm loss: 3.375873E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.440 | TFLOPs: 48.99 | +7: iteration 2350/ 2891 | consumed samples: 601600 | consumed tokens: 1232076800 | elapsed time per iteration (s): 1.29 | learning rate: 3.544E-05 | global batch size: 256 | lm loss: 3.389051E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.399 | TFLOPs: 48.01 | +7: iteration 2360/ 2891 | consumed samples: 604160 | consumed tokens: 1237319680 | elapsed time per iteration (s): 1.26 | learning rate: 3.489E-05 | global batch size: 256 | lm loss: 3.352780E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.488 | TFLOPs: 49.00 | +7: iteration 2370/ 2891 | consumed samples: 606720 | consumed tokens: 1242562560 | elapsed time per iteration (s): 1.26 | learning rate: 3.435E-05 | global batch size: 256 | lm loss: 3.333027E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.533 | TFLOPs: 49.01 | +7: iteration 2380/ 2891 | consumed samples: 609280 | consumed tokens: 1247805440 | elapsed time per iteration (s): 1.26 | learning rate: 3.382E-05 | global batch size: 256 | lm loss: 3.339282E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.640 | TFLOPs: 49.04 | +7: iteration 2390/ 2891 | consumed samples: 611840 | consumed tokens: 1253048320 | elapsed time per iteration (s): 1.27 | learning rate: 3.330E-05 | global batch size: 256 | lm loss: 3.383463E+00 | grad norm: 0.478 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.827 | TFLOPs: 48.84 | +7: iteration 2400/ 2891 | consumed samples: 614400 | consumed tokens: 1258291200 | elapsed time per iteration (s): 1.26 | learning rate: 3.279E-05 | global batch size: 256 | lm loss: 3.343145E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.548 | TFLOPs: 49.01 | +7: iteration 2410/ 2891 | consumed samples: 616960 | consumed tokens: 1263534080 | elapsed time per iteration (s): 1.26 | learning rate: 3.228E-05 | global batch size: 256 | lm loss: 3.370723E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.593 | TFLOPs: 49.03 | +7: iteration 2420/ 2891 | consumed samples: 619520 | consumed tokens: 1268776960 | elapsed time per iteration (s): 1.26 | learning rate: 3.179E-05 | global batch size: 256 | lm loss: 3.345803E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.705 | TFLOPs: 49.05 | +7: iteration 2430/ 2891 | consumed samples: 622080 | consumed tokens: 1274019840 | elapsed time per iteration (s): 1.26 | learning rate: 3.131E-05 | global batch size: 256 | lm loss: 3.370715E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.531 | TFLOPs: 49.01 | +7: iteration 2440/ 2891 | consumed samples: 624640 | consumed tokens: 1279262720 | elapsed time per iteration (s): 1.28 | learning rate: 3.083E-05 | global batch size: 256 | lm loss: 3.354684E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.854 | TFLOPs: 48.36 | +7: iteration 2450/ 2891 | consumed samples: 627200 | consumed tokens: 1284505600 | elapsed time per iteration (s): 1.26 | learning rate: 3.037E-05 | global batch size: 256 | lm loss: 3.366651E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.526 | TFLOPs: 49.01 | +7: iteration 2460/ 2891 | consumed samples: 629760 | consumed tokens: 1289748480 | elapsed time per iteration (s): 1.26 | learning rate: 2.991E-05 | global batch size: 256 | lm loss: 3.340447E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.638 | TFLOPs: 49.04 | +7: iteration 2470/ 2891 | consumed samples: 632320 | consumed tokens: 1294991360 | elapsed time per iteration (s): 1.26 | learning rate: 2.947E-05 | global batch size: 256 | lm loss: 3.362162E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.650 | TFLOPs: 49.04 | +7: iteration 2480/ 2891 | consumed samples: 634880 | consumed tokens: 1300234240 | elapsed time per iteration (s): 1.26 | learning rate: 2.903E-05 | global batch size: 256 | lm loss: 3.364618E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.584 | TFLOPs: 49.02 | +7: iteration 2490/ 2891 | consumed samples: 637440 | consumed tokens: 1305477120 | elapsed time per iteration (s): 1.26 | learning rate: 2.860E-05 | global batch size: 256 | lm loss: 3.355886E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.572 | TFLOPs: 49.02 | +7: iteration 2500/ 2891 | consumed samples: 640000 | consumed tokens: 1310720000 | elapsed time per iteration (s): 1.26 | learning rate: 2.819E-05 | global batch size: 256 | lm loss: 3.377243E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.575 | TFLOPs: 49.02 | +7: iteration 2510/ 2891 | consumed samples: 642560 | consumed tokens: 1315962880 | elapsed time per iteration (s): 1.26 | learning rate: 2.778E-05 | global batch size: 256 | lm loss: 3.365576E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.574 | TFLOPs: 49.02 | +7: iteration 2520/ 2891 | consumed samples: 645120 | consumed tokens: 1321205760 | elapsed time per iteration (s): 1.26 | learning rate: 2.738E-05 | global batch size: 256 | lm loss: 3.353968E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.480 | TFLOPs: 49.00 | +7: iteration 2530/ 2891 | consumed samples: 647680 | consumed tokens: 1326448640 | elapsed time per iteration (s): 1.26 | learning rate: 2.700E-05 | global batch size: 256 | lm loss: 3.347538E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.701 | TFLOPs: 49.05 | +7: iteration 2540/ 2891 | consumed samples: 650240 | consumed tokens: 1331691520 | elapsed time per iteration (s): 1.26 | learning rate: 2.662E-05 | global batch size: 256 | lm loss: 3.346878E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.566 | TFLOPs: 49.02 | +7: iteration 2550/ 2891 | consumed samples: 652800 | consumed tokens: 1336934400 | elapsed time per iteration (s): 1.28 | learning rate: 2.625E-05 | global batch size: 256 | lm loss: 3.349545E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.673 | TFLOPs: 48.32 | +7: iteration 2560/ 2891 | consumed samples: 655360 | consumed tokens: 1342177280 | elapsed time per iteration (s): 1.26 | learning rate: 2.590E-05 | global batch size: 256 | lm loss: 3.347480E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.527 | TFLOPs: 49.01 | +7: iteration 2570/ 2891 | consumed samples: 657920 | consumed tokens: 1347420160 | elapsed time per iteration (s): 1.26 | learning rate: 2.555E-05 | global batch size: 256 | lm loss: 3.346072E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.548 | TFLOPs: 49.01 | +7: iteration 2580/ 2891 | consumed samples: 660480 | consumed tokens: 1352663040 | elapsed time per iteration (s): 1.26 | learning rate: 2.521E-05 | global batch size: 256 | lm loss: 3.348163E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.578 | TFLOPs: 49.02 | +7: iteration 2590/ 2891 | consumed samples: 663040 | consumed tokens: 1357905920 | elapsed time per iteration (s): 1.27 | learning rate: 2.489E-05 | global batch size: 256 | lm loss: 3.326427E+00 | grad norm: 0.377 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.151 | TFLOPs: 48.92 | +7: iteration 2600/ 2891 | consumed samples: 665600 | consumed tokens: 1363148800 | elapsed time per iteration (s): 1.26 | learning rate: 2.457E-05 | global batch size: 256 | lm loss: 3.324560E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.527 | TFLOPs: 49.01 | +7: iteration 2610/ 2891 | consumed samples: 668160 | consumed tokens: 1368391680 | elapsed time per iteration (s): 1.26 | learning rate: 2.427E-05 | global batch size: 256 | lm loss: 3.325753E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.409 | TFLOPs: 48.98 | +7: iteration 2620/ 2891 | consumed samples: 670720 | consumed tokens: 1373634560 | elapsed time per iteration (s): 1.26 | learning rate: 2.397E-05 | global batch size: 256 | lm loss: 3.330455E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.545 | TFLOPs: 49.01 | +7: iteration 2630/ 2891 | consumed samples: 673280 | consumed tokens: 1378877440 | elapsed time per iteration (s): 1.26 | learning rate: 2.369E-05 | global batch size: 256 | lm loss: 3.319068E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.504 | TFLOPs: 49.00 | +7: iteration 2640/ 2891 | consumed samples: 675840 | consumed tokens: 1384120320 | elapsed time per iteration (s): 1.26 | learning rate: 2.341E-05 | global batch size: 256 | lm loss: 3.348583E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.509 | TFLOPs: 49.01 | +7: iteration 2650/ 2891 | consumed samples: 678400 | consumed tokens: 1389363200 | elapsed time per iteration (s): 1.26 | learning rate: 2.315E-05 | global batch size: 256 | lm loss: 3.305918E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.398 | TFLOPs: 48.98 | +7: iteration 2660/ 2891 | consumed samples: 680960 | consumed tokens: 1394606080 | elapsed time per iteration (s): 1.26 | learning rate: 2.289E-05 | global batch size: 256 | lm loss: 3.380468E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.414 | TFLOPs: 48.98 | +7: iteration 2670/ 2891 | consumed samples: 683520 | consumed tokens: 1399848960 | elapsed time per iteration (s): 1.27 | learning rate: 2.265E-05 | global batch size: 256 | lm loss: 3.335890E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.903 | TFLOPs: 48.62 | +7: iteration 2680/ 2891 | consumed samples: 686080 | consumed tokens: 1405091840 | elapsed time per iteration (s): 1.27 | learning rate: 2.242E-05 | global batch size: 256 | lm loss: 3.317033E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.068 | TFLOPs: 48.90 | +7: iteration 2690/ 2891 | consumed samples: 688640 | consumed tokens: 1410334720 | elapsed time per iteration (s): 1.26 | learning rate: 2.220E-05 | global batch size: 256 | lm loss: 3.305687E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.442 | TFLOPs: 48.99 | +7: iteration 2700/ 2891 | consumed samples: 691200 | consumed tokens: 1415577600 | elapsed time per iteration (s): 1.26 | learning rate: 2.198E-05 | global batch size: 256 | lm loss: 3.325862E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.437 | TFLOPs: 48.99 | +7: iteration 2710/ 2891 | consumed samples: 693760 | consumed tokens: 1420820480 | elapsed time per iteration (s): 1.26 | learning rate: 2.178E-05 | global batch size: 256 | lm loss: 3.326694E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.475 | TFLOPs: 49.00 | +7: iteration 2720/ 2891 | consumed samples: 696320 | consumed tokens: 1426063360 | elapsed time per iteration (s): 1.26 | learning rate: 2.159E-05 | global batch size: 256 | lm loss: 3.313206E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.428 | TFLOPs: 48.99 | +7: iteration 2730/ 2891 | consumed samples: 698880 | consumed tokens: 1431306240 | elapsed time per iteration (s): 1.26 | learning rate: 2.141E-05 | global batch size: 256 | lm loss: 3.327401E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.428 | TFLOPs: 48.99 | +7: iteration 2740/ 2891 | consumed samples: 701440 | consumed tokens: 1436549120 | elapsed time per iteration (s): 1.26 | learning rate: 2.124E-05 | global batch size: 256 | lm loss: 3.306187E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.445 | TFLOPs: 48.99 | +7: iteration 2750/ 2891 | consumed samples: 704000 | consumed tokens: 1441792000 | elapsed time per iteration (s): 1.27 | learning rate: 2.109E-05 | global batch size: 256 | lm loss: 3.313600E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.227 | TFLOPs: 48.94 | +7: iteration 2760/ 2891 | consumed samples: 706560 | consumed tokens: 1447034880 | elapsed time per iteration (s): 1.26 | learning rate: 2.094E-05 | global batch size: 256 | lm loss: 3.341908E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.436 | TFLOPs: 48.99 | +7: iteration 2770/ 2891 | consumed samples: 709120 | consumed tokens: 1452277760 | elapsed time per iteration (s): 1.27 | learning rate: 2.080E-05 | global batch size: 256 | lm loss: 3.312650E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.126 | TFLOPs: 48.91 | +7: iteration 2780/ 2891 | consumed samples: 711680 | consumed tokens: 1457520640 | elapsed time per iteration (s): 1.27 | learning rate: 2.068E-05 | global batch size: 256 | lm loss: 3.307022E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.348 | TFLOPs: 48.97 | +7: iteration 2790/ 2891 | consumed samples: 714240 | consumed tokens: 1462763520 | elapsed time per iteration (s): 1.27 | learning rate: 2.056E-05 | global batch size: 256 | lm loss: 3.332689E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.304 | TFLOPs: 48.96 | +7: iteration 2800/ 2891 | consumed samples: 716800 | consumed tokens: 1468006400 | elapsed time per iteration (s): 1.27 | learning rate: 2.046E-05 | global batch size: 256 | lm loss: 3.286166E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.351 | TFLOPs: 48.97 | +7: iteration 2810/ 2891 | consumed samples: 719360 | consumed tokens: 1473249280 | elapsed time per iteration (s): 1.27 | learning rate: 2.036E-05 | global batch size: 256 | lm loss: 3.310330E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.255 | TFLOPs: 48.70 | +7: iteration 2820/ 2891 | consumed samples: 721920 | consumed tokens: 1478492160 | elapsed time per iteration (s): 1.27 | learning rate: 2.028E-05 | global batch size: 256 | lm loss: 3.319715E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.249 | TFLOPs: 48.94 | +7: iteration 2830/ 2891 | consumed samples: 724480 | consumed tokens: 1483735040 | elapsed time per iteration (s): 1.27 | learning rate: 2.021E-05 | global batch size: 256 | lm loss: 3.300797E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.346 | TFLOPs: 48.97 | +7: iteration 2840/ 2891 | consumed samples: 727040 | consumed tokens: 1488977920 | elapsed time per iteration (s): 1.27 | learning rate: 2.014E-05 | global batch size: 256 | lm loss: 3.316748E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.357 | TFLOPs: 48.97 | +7: iteration 2850/ 2891 | consumed samples: 729600 | consumed tokens: 1494220800 | elapsed time per iteration (s): 1.27 | learning rate: 2.009E-05 | global batch size: 256 | lm loss: 3.333828E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.007 | TFLOPs: 48.88 | +7: iteration 2860/ 2891 | consumed samples: 732160 | consumed tokens: 1499463680 | elapsed time per iteration (s): 1.26 | learning rate: 2.005E-05 | global batch size: 256 | lm loss: 3.319077E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.382 | TFLOPs: 48.97 | +7: iteration 2870/ 2891 | consumed samples: 734720 | consumed tokens: 1504706560 | elapsed time per iteration (s): 1.29 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 3.328903E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.256 | TFLOPs: 47.98 | +7: iteration 2880/ 2891 | consumed samples: 737280 | consumed tokens: 1509949440 | elapsed time per iteration (s): 1.27 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 3.298471E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.879 | TFLOPs: 48.85 | +7: iteration 2890/ 2891 | consumed samples: 739840 | consumed tokens: 1515192320 | elapsed time per iteration (s): 1.27 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 3.297031E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.822 | TFLOPs: 48.60 | +0: [after training is done] datetime: 2022-11-29 18:54:13 +0: saving checkpoint at iteration 2891 to checkpoints_1b1oscar +7: ------------------------------------------------------------------------------------------------------------ +7: valid loss at the end of training for val data | lm loss value: 3.137404E+00 | lm loss PPL: 2.304397E+01 | +7: ------------------------------------------------------------------------------------------------------------ +0: [2022-11-29 18:54:13,711] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step2891 is begin to save! +0: [2022-11-29 18:54:13,714] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:54:13,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:54:13,916] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:54:13,995] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:54:13,995] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:54:14,069] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:54:14,069] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:54:14,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:54:14,143] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:54:14,218] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:54:14,218] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:54:14,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:54:14,294] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:54:14,370] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:54:14,370] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:54:14,443] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:54:14,443] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:54:14,518] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:54:14,518] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:54:14,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:54:14,591] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:54:14,668] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:54:14,669] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_13-model_00-model_states.pt... +0: [2022-11-29 18:54:14,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_13-model_00-model_states.pt. +0: [2022-11-29 18:54:14,745] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:54:14,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:54:14,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_15-model_00-model_states.pt... +0: [2022-11-29 18:54:14,895] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_15-model_00-model_states.pt. +0: [2022-11-29 18:54:14,896] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_16-model_00-model_states.pt... +0: [2022-11-29 18:54:14,968] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_16-model_00-model_states.pt. +0: [2022-11-29 18:54:14,969] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_17-model_00-model_states.pt... +0: [2022-11-29 18:54:15,045] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_17-model_00-model_states.pt. +0: [2022-11-29 18:54:15,046] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_18-model_00-model_states.pt... +0: [2022-11-29 18:54:15,122] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_18-model_00-model_states.pt. +0: [2022-11-29 18:54:15,123] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_19-model_00-model_states.pt... +0: [2022-11-29 18:54:15,197] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_19-model_00-model_states.pt. +0: [2022-11-29 18:54:15,197] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_20-model_00-model_states.pt... +0: [2022-11-29 18:54:15,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_20-model_00-model_states.pt. +0: [2022-11-29 18:54:15,274] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_21-model_00-model_states.pt... +0: [2022-11-29 18:54:15,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_21-model_00-model_states.pt. +0: [2022-11-29 18:54:15,346] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_22-model_00-model_states.pt... +0: [2022-11-29 18:54:15,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_22-model_00-model_states.pt. +0: [2022-11-29 18:54:15,423] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_23-model_00-model_states.pt... +0: [2022-11-29 18:54:15,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_23-model_00-model_states.pt. +0: [2022-11-29 18:54:15,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_24-model_00-model_states.pt... +0: [2022-11-29 18:54:15,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_24-model_00-model_states.pt. +0: [2022-11-29 18:54:15,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_25-model_00-model_states.pt... +0: [2022-11-29 18:54:15,643] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_25-model_00-model_states.pt. +0: [2022-11-29 18:54:15,643] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_26-model_00-model_states.pt... +0: [2022-11-29 18:54:15,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_26-model_00-model_states.pt. +0: [2022-11-29 18:54:15,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_27-model_00-model_states.pt... +0: [2022-11-29 18:54:15,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_27-model_00-model_states.pt. +0: [2022-11-29 18:54:15,795] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_28-model_00-model_states.pt... +0: [2022-11-29 18:54:15,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_28-model_00-model_states.pt. +0: [2022-11-29 18:54:15,867] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/layer_30-model_00-model_states.pt... +0: [2022-11-29 18:54:15,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/layer_30-model_00-model_states.pt. +0: [2022-11-29 18:54:15,872] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_1b1oscar/global_step2891/mp_rank_00_model_states.pt +0: [2022-11-29 18:54:15,872] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/mp_rank_00_model_states.pt... +0: [2022-11-29 18:54:15,874] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/mp_rank_00_model_states.pt. +0: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:54:15,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:54:16,139] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:54:16,139] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:54:16,139] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +4: [2022-11-29 18:54:16,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:54:16,140] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:54:16,140] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +6: [2022-11-29 18:54:16,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:54:16,142] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:54:16,142] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +1: [2022-11-29 18:54:16,144] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:54:16,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:54:16,145] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:54:16,145] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +6: [2022-11-29 18:54:16,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:54:16,145] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +6: [2022-11-29 18:54:16,145] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +4: [2022-11-29 18:54:16,145] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +6: [2022-11-29 18:54:16,145] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +7: [2022-11-29 18:54:16,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:54:16,151] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:54:16,151] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +3: [2022-11-29 18:54:16,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:54:16,151] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:54:16,151] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +6: [2022-11-29 18:54:16,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:54:16,151] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:54:16,151] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +1: [2022-11-29 18:54:16,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:54:16,156] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:54:16,156] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +1: [2022-11-29 18:54:16,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:54:16,156] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:54:16,156] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +5: [2022-11-29 18:54:16,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:54:16,157] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:54:16,157] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +7: [2022-11-29 18:54:16,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:54:16,157] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:54:16,157] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +0: [2022-11-29 18:54:16,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:54:16,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:54:16,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +2: [2022-11-29 18:54:16,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:54:16,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:54:16,160] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:54:16,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +5: [2022-11-29 18:54:16,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:54:16,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:54:16,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +0: [2022-11-29 18:54:16,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:54:16,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:54:16,162] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:54:16,162] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +4: [2022-11-29 18:54:16,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:54:16,163] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:54:16,163] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +1: [2022-11-29 18:54:16,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:54:16,163] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:54:16,163] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +7: [2022-11-29 18:54:16,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:54:16,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:54:16,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +0: [2022-11-29 18:54:16,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:54:16,165] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:54:16,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +4: [2022-11-29 18:54:16,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:54:16,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:54:16,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:54:16,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:54:16,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +4: [2022-11-29 18:54:16,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +5: [2022-11-29 18:54:16,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:54:16,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +3: [2022-11-29 18:54:16,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:54:16,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +7: [2022-11-29 18:54:16,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:54:16,171] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:54:16,171] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +1: [2022-11-29 18:54:16,175] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:54:16,175] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:54:16,175] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:54:16,175] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:54:16,175] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +1: [2022-11-29 18:54:16,175] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +4: [2022-11-29 18:54:16,175] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:54:16,175] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:54:16,175] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +1: [2022-11-29 18:54:16,176] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:54:16,176] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:54:16,176] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +0: [2022-11-29 18:54:16,176] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:54:16,176] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:54:16,176] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +3: [2022-11-29 18:54:16,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +2: [2022-11-29 18:54:16,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +3: [2022-11-29 18:54:16,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +2: [2022-11-29 18:54:16,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +2: [2022-11-29 18:54:16,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:54:16,165] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:54:16,165] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +2: [2022-11-29 18:54:16,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:54:16,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:54:16,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +2: [2022-11-29 18:54:16,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:54:16,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:54:16,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:54:16,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +2: [2022-11-29 18:54:16,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:54:16,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +2: [2022-11-29 18:54:16,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:54:16,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:54:16,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +7: [2022-11-29 18:54:16,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:54:16,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:54:16,179] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:54:16,179] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +4: [2022-11-29 18:54:16,179] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:54:16,179] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +6: [2022-11-29 18:54:16,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:54:16,179] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:54:16,179] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +0: [2022-11-29 18:54:16,182] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:54:16,182] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:54:16,182] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +0: [2022-11-29 18:54:16,182] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:54:16,182] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:54:16,182] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:54:16,182] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:54:16,182] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +3: [2022-11-29 18:54:16,182] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:54:16,182] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +3: [2022-11-29 18:54:16,182] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:54:16,182] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +7: [2022-11-29 18:54:16,183] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:54:16,183] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:54:16,183] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:54:16,183] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +7: [2022-11-29 18:54:16,183] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:54:16,183] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:54:16,183] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +3: [2022-11-29 18:54:16,183] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +7: [2022-11-29 18:54:16,183] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +3: [2022-11-29 18:54:16,183] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:54:16,183] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:54:16,183] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +7: [2022-11-29 18:54:16,183] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:54:16,183] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:54:16,183] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +6: [2022-11-29 18:54:16,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:54:16,185] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:54:16,185] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +2: [2022-11-29 18:54:16,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:54:16,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:54:16,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:54:16,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:54:16,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +5: [2022-11-29 18:54:16,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:54:16,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:54:16,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +5: [2022-11-29 18:54:16,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:54:16,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:54:16,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +5: [2022-11-29 18:54:16,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:54:16,196] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:54:16,196] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +6: [2022-11-29 18:54:16,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:54:16,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:54:16,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +6: [2022-11-29 18:54:16,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:54:16,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:54:16,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +3: [2022-11-29 18:54:16,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:54:16,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +3: [2022-11-29 18:54:16,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:54:16,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:54:16,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +3: [2022-11-29 18:54:16,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:54:16,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:54:16,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +0: [2022-11-29 18:54:16,202] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:54:16,202] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +5: [2022-11-29 18:54:16,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:54:16,212] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:54:16,212] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +5: [2022-11-29 18:54:16,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:54:16,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:54:16,213] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +2: [2022-11-29 18:54:16,186] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:54:16,186] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_1b1oscar/global_step2891/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:54:16,186] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +2: [2022-11-29 18:54:16,186] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +5: [2022-11-29 18:54:16,213] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2891 is ready now! +0: successfully saved checkpoint at iteration 2891 to checkpoints_1b1oscar +7: ------------------------------------------------------------------------------------------------------------ +7: test loss at the end of training for test data | lm loss value: 3.239900E+00 | lm loss PPL: 2.553117E+01 | +7: ------------------------------------------------------------------------------------------------------------ +END 2085640: Tue Nov 29 18:54:26 EET 2022 diff --git a/1b11b51b5/sbatch_1b1_oscar.sh b/1b11b51b5/sbatch_1b1_oscar.sh new file mode 100755 index 0000000000000000000000000000000000000000..7f18883bd3e953de9d8918a98bdb2c25742c8a77 --- /dev/null +++ b/1b11b51b5/sbatch_1b1_oscar.sh @@ -0,0 +1,162 @@ +#!/bin/bash +#SBATCH --exclude=nid007571,nid007112,nid006774,nid007502,nid007506,nid007507,nid005145,nid006692,nid007218,nid007123,nid006124,nid006123,nid007496,nid007237,nid006852,nid007206,nid006947,nid007212,nid006977,nid007222,nid005444,nid007219,nid007493,nid007221,nid005300,nid005619,nid006118,nid005203,nid006113,nid006481,nid007077,nid005208,nid005207,nid005879,nid005901 +#SBATCH --nodes=8 +#SBATCH --ntasks-per-node=1 +#SBATCH --cpus-per-task=32 +#SBATCH --mem=256G +#SBATCH -p pilot +#SBATCH -t 12:00:00 +#SBATCH --gpus-per-node=mi250:8 +#SBATCH --exclusive=user +#SBATCH --hint=nomultithread +#SBATCH --account=project_462000119 +#SBATCH -o logs/%j.out +#SBATCH -e logs/%j.err + +VARIANT=1b1oscar + +# if run without sbatch, invoke here +if [ -z $SLURM_JOB_ID ]; then + mkdir -p logs + sbatch "$0" + exit +fi + +set -euo pipefail + +# symlink logs/latest.out and logs/latest.err +ln -f -s $SLURM_JOB_ID.out logs/latest.out +ln -f -s $SLURM_JOB_ID.err logs/latest.err + +KILL_SWITCH_PATH=kill-switch-$VARIANT +CHECKPOINT_PATH=checkpoints_$VARIANT +TENSORBOARD_PATH=tensorboard_$VARIANT +# Start from scratch +rm -rf "$CHECKPOINT_PATH" "$TENSORBOARD_PATH" + +# Data +VOCAB_FILE="gpt2/vocab.json" +MERGE_FILE="gpt2/merges.txt" +DATA_PATH="/scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document" + +PP_SIZE=1 +TP_SIZE=1 + +MICRO_BATCH_SIZE=4 +GRADIENT_ACCUMULATION_STEPS=1 +WORLD_SIZE=$((SLURM_GPUS_ON_NODE*SLURM_JOB_NUM_NODES)) +GLOBAL_BATCH_SIZE=$((MICRO_BATCH_SIZE*WORLD_SIZE*GRADIENT_ACCUMULATION_STEPS)) + +# Model parameters +source model_params.sh +MODEL_PARAM=("${PARAM_1143M[@]}") +NHIDDEN=${MODEL_PARAM[0]} +FFN_HIDDEN_SIZE=${MODEL_PARAM[1]} +KV_SIZE=${MODEL_PARAM[2]} +NHEADS=${MODEL_PARAM[3]} +NLAYERS=${MODEL_PARAM[4]} +SEQ_LEN=2048 + +echo "Model parameters: d_model $NHIDDEN ffw_size $FFN_HIDDEN_SIZE kv_size $KV_SIZE n_heads $NHEADS n_layers $NLAYERS" + +SAVE_INTERVAL=1000 + +# Tokens: 1516071000 +# -> Samples: 740269 +TRAIN_SAMPLES=740_269 + +OPTIMIZER_ARGS=" \ + --optimizer adam \ + --adam-beta1 0.9 \ + --adam-beta2 0.999 \ + --adam-eps 1e-8 \ + --lr 2e-4 \ + --min-lr 2e-5 \ + --lr-decay-style cosine \ + --lr-decay-samples $TRAIN_SAMPLES \ + --lr-warmup-samples 7403 \ + --clip-grad 1.0 \ + --weight-decay 1e-1 \ + " + +GPT_ARGS=" \ + --num-layers $NLAYERS \ + --hidden-size $NHIDDEN \ + --num-attention-heads $NHEADS \ + --kv-channels $KV_SIZE \ + --ffn-hidden-size $FFN_HIDDEN_SIZE \ + --seq-length $SEQ_LEN \ + --max-position-embeddings $SEQ_LEN \ + --micro-batch-size $MICRO_BATCH_SIZE \ + --global-batch-size $GLOBAL_BATCH_SIZE \ + --train-samples $TRAIN_SAMPLES \ + --vocab-file $VOCAB_FILE \ + --merge-file $MERGE_FILE \ + --loss-scale 12 \ + --clip-grad 1.0 \ + --kill-switch-path $KILL_SWITCH_PATH \ + --bf16 \ + $OPTIMIZER_ARGS \ + " + +OUTPUT_ARGS=" \ + --log-interval 10 \ + --save-interval $SAVE_INTERVAL \ + --eval-interval 1000 \ + --eval-iters 1 \ + --tensorboard-dir $TENSORBOARD_PATH \ + --tensorboard-queue-size 5 \ + --log-timers-to-tensorboard \ + --log-batch-size-to-tensorboard \ + --log-validation-ppl-to-tensorboard \ + " + +ZERO_STAGE=0 + +mkdir -p ds_configs +DS_CONFIG_PATH="ds_configs/$SLURM_JOB_ID.json" + +cat < $DS_CONFIG_PATH +{ + "train_micro_batch_size_per_gpu": $MICRO_BATCH_SIZE, + "train_batch_size": $GLOBAL_BATCH_SIZE, + "gradient_clipping": 1.0, + "zero_optimization": { + "stage": $ZERO_STAGE + }, + "bf16": { + "enabled": true + }, + "steps_per_print": 2000, + "wall_clock_breakdown": false +} +EOF + +DEEPSPEED_ARGS=" \ + --deepspeed \ + --deepspeed_config $DS_CONFIG_PATH \ + --zero-stage $ZERO_STAGE \ + " + +CMD=" \ + Megatron-DeepSpeed/pretrain_gpt.py \ + --tensor-model-parallel-size $TP_SIZE \ + --pipeline-model-parallel-size $PP_SIZE \ + $GPT_ARGS \ + $OUTPUT_ARGS \ + --save $CHECKPOINT_PATH \ + --load $CHECKPOINT_PATH \ + --data-path $DATA_PATH \ + --data-impl mmap \ + --split 949,50,1 \ + $DEEPSPEED_ARGS \ + " + +echo $CMD + +echo "START $SLURM_JOBID: $(date)" + +# bash launch_srun.sh $CMD +srun --label launch.sh $CMD + +echo "END $SLURM_JOBID: $(date)" diff --git a/1b11b51b5/tensorboard/events.out.tfevents.1669737013.nid005023.22403.0 b/1b11b51b5/tensorboard/events.out.tfevents.1669737013.nid005023.22403.0 new file mode 100644 index 0000000000000000000000000000000000000000..f05366318a650fcf4552b8b90ab88e5b99a36f66 --- /dev/null +++ b/1b11b51b5/tensorboard/events.out.tfevents.1669737013.nid005023.22403.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2a172549d7f830a847ed84def0d84ae7b80e599d90bf2d9d4c8ebf1a4428b79 +size 5154238 diff --git a/1b121b21b/evaluation/lm1-1b1-21b-oscar-results_lm-eval_global_step39672_2022-12-02-14-19-24.csv b/1b121b21b/evaluation/lm1-1b1-21b-oscar-results_lm-eval_global_step39672_2022-12-02-14-19-24.csv new file mode 100644 index 0000000000000000000000000000000000000000..c05c6f7c72db8ac58a86d433934134a4332dfbdc --- /dev/null +++ b/1b121b21b/evaluation/lm1-1b1-21b-oscar-results_lm-eval_global_step39672_2022-12-02-14-19-24.csv @@ -0,0 +1,120 @@ +task,metric,value,err,version +copa,acc,0.7,0.046056618647183814,0 +hendrycksTest-abstract_algebra,acc,0.22,0.0416333199893227,0 +hendrycksTest-abstract_algebra,acc_norm,0.22,0.0416333199893227,0 +hendrycksTest-anatomy,acc,0.17037037037037037,0.03247781185995593,0 +hendrycksTest-anatomy,acc_norm,0.17777777777777778,0.0330278985990172,0 +hendrycksTest-astronomy,acc,0.21052631578947367,0.03317672787533156,0 +hendrycksTest-astronomy,acc_norm,0.3026315789473684,0.037385206761196686,0 +hendrycksTest-business_ethics,acc,0.32,0.046882617226215034,0 +hendrycksTest-business_ethics,acc_norm,0.31,0.04648231987117316,0 +hendrycksTest-clinical_knowledge,acc,0.24528301886792453,0.026480357179895674,0 +hendrycksTest-clinical_knowledge,acc_norm,0.3132075471698113,0.028544793319055326,0 +hendrycksTest-college_biology,acc,0.2361111111111111,0.03551446610810826,0 +hendrycksTest-college_biology,acc_norm,0.2013888888888889,0.033536474697138406,0 +hendrycksTest-college_chemistry,acc,0.27,0.044619604333847394,0 +hendrycksTest-college_chemistry,acc_norm,0.32,0.046882617226215034,0 +hendrycksTest-college_computer_science,acc,0.29,0.04560480215720684,0 +hendrycksTest-college_computer_science,acc_norm,0.3,0.046056618647183814,0 +hendrycksTest-college_mathematics,acc,0.23,0.04229525846816505,0 +hendrycksTest-college_mathematics,acc_norm,0.29,0.04560480215720684,0 +hendrycksTest-college_medicine,acc,0.24855491329479767,0.03295304696818318,0 +hendrycksTest-college_medicine,acc_norm,0.2543352601156069,0.0332055644308557,0 +hendrycksTest-college_physics,acc,0.2549019607843137,0.043364327079931785,0 +hendrycksTest-college_physics,acc_norm,0.24509803921568626,0.04280105837364395,0 +hendrycksTest-computer_security,acc,0.2,0.04020151261036844,0 +hendrycksTest-computer_security,acc_norm,0.29,0.04560480215720684,0 +hendrycksTest-conceptual_physics,acc,0.28936170212765955,0.02964400657700962,0 +hendrycksTest-conceptual_physics,acc_norm,0.225531914893617,0.027321078417387536,0 +hendrycksTest-econometrics,acc,0.32456140350877194,0.04404556157374768,0 +hendrycksTest-econometrics,acc_norm,0.2631578947368421,0.04142439719489362,0 +hendrycksTest-electrical_engineering,acc,0.27586206896551724,0.03724563619774632,0 +hendrycksTest-electrical_engineering,acc_norm,0.2896551724137931,0.03780019230438014,0 +hendrycksTest-elementary_mathematics,acc,0.20105820105820105,0.02064181078237016,0 +hendrycksTest-elementary_mathematics,acc_norm,0.2275132275132275,0.021591269407823778,0 +hendrycksTest-formal_logic,acc,0.29365079365079366,0.04073524322147127,0 +hendrycksTest-formal_logic,acc_norm,0.23809523809523808,0.03809523809523811,0 +hendrycksTest-global_facts,acc,0.24,0.042923469599092816,0 +hendrycksTest-global_facts,acc_norm,0.26,0.044084400227680794,0 +hendrycksTest-high_school_biology,acc,0.2129032258064516,0.02328766512726854,0 +hendrycksTest-high_school_biology,acc_norm,0.26129032258064516,0.024993053397764812,0 +hendrycksTest-high_school_chemistry,acc,0.1921182266009852,0.027719315709614775,0 +hendrycksTest-high_school_chemistry,acc_norm,0.23645320197044334,0.029896114291733552,0 +hendrycksTest-high_school_computer_science,acc,0.25,0.04351941398892446,0 +hendrycksTest-high_school_computer_science,acc_norm,0.29,0.04560480215720684,0 +hendrycksTest-high_school_european_history,acc,0.24848484848484848,0.03374402644139404,0 +hendrycksTest-high_school_european_history,acc_norm,0.2909090909090909,0.03546563019624336,0 +hendrycksTest-high_school_geography,acc,0.23737373737373738,0.030313710538198906,0 +hendrycksTest-high_school_geography,acc_norm,0.3181818181818182,0.033184773338453315,0 +hendrycksTest-high_school_government_and_politics,acc,0.26424870466321243,0.03182155050916648,0 +hendrycksTest-high_school_government_and_politics,acc_norm,0.27979274611398963,0.03239637046735702,0 +hendrycksTest-high_school_macroeconomics,acc,0.2512820512820513,0.021992016662370543,0 +hendrycksTest-high_school_macroeconomics,acc_norm,0.2641025641025641,0.022352193737453268,0 +hendrycksTest-high_school_mathematics,acc,0.2037037037037037,0.02455617221914128,0 +hendrycksTest-high_school_mathematics,acc_norm,0.26296296296296295,0.026842057873833713,0 +hendrycksTest-high_school_microeconomics,acc,0.25630252100840334,0.02835962087053395,0 +hendrycksTest-high_school_microeconomics,acc_norm,0.31512605042016806,0.030176808288974337,0 +hendrycksTest-high_school_physics,acc,0.1986754966887417,0.03257847384436776,0 +hendrycksTest-high_school_physics,acc_norm,0.23178807947019867,0.03445406271987054,0 +hendrycksTest-high_school_psychology,acc,0.20917431192660552,0.017437937173343233,0 +hendrycksTest-high_school_psychology,acc_norm,0.22568807339449543,0.017923087667803057,0 +hendrycksTest-high_school_statistics,acc,0.20833333333333334,0.027696910713093936,0 +hendrycksTest-high_school_statistics,acc_norm,0.30092592592592593,0.031280390843298804,0 +hendrycksTest-high_school_us_history,acc,0.27450980392156865,0.031321798030832904,0 +hendrycksTest-high_school_us_history,acc_norm,0.28431372549019607,0.03166009679399812,0 +hendrycksTest-high_school_world_history,acc,0.22784810126582278,0.027303484599069422,0 +hendrycksTest-high_school_world_history,acc_norm,0.28270042194092826,0.02931281415395593,0 +hendrycksTest-human_aging,acc,0.29596412556053814,0.030636591348699796,0 +hendrycksTest-human_aging,acc_norm,0.26905829596412556,0.029763779406874972,0 +hendrycksTest-human_sexuality,acc,0.32061068702290074,0.04093329229834278,0 +hendrycksTest-human_sexuality,acc_norm,0.31297709923664124,0.04066962905677697,0 +hendrycksTest-international_law,acc,0.2231404958677686,0.03800754475228733,0 +hendrycksTest-international_law,acc_norm,0.4049586776859504,0.04481137755942469,0 +hendrycksTest-jurisprudence,acc,0.24074074074074073,0.0413311944024384,0 +hendrycksTest-jurisprudence,acc_norm,0.37962962962962965,0.04691521224077742,0 +hendrycksTest-logical_fallacies,acc,0.1656441717791411,0.029208296231259104,0 +hendrycksTest-logical_fallacies,acc_norm,0.27607361963190186,0.0351238528370505,0 +hendrycksTest-machine_learning,acc,0.3125,0.043994650575715215,0 +hendrycksTest-machine_learning,acc_norm,0.25892857142857145,0.04157751539865629,0 +hendrycksTest-management,acc,0.2524271844660194,0.04301250399690878,0 +hendrycksTest-management,acc_norm,0.2912621359223301,0.044986763205729224,0 +hendrycksTest-marketing,acc,0.29914529914529914,0.02999695185834948,0 +hendrycksTest-marketing,acc_norm,0.32051282051282054,0.030572811310299604,0 +hendrycksTest-medical_genetics,acc,0.28,0.045126085985421255,0 +hendrycksTest-medical_genetics,acc_norm,0.38,0.04878317312145632,0 +hendrycksTest-miscellaneous,acc,0.2567049808429119,0.015620480263064535,0 +hendrycksTest-miscellaneous,acc_norm,0.24904214559386972,0.015464676163395962,0 +hendrycksTest-moral_disputes,acc,0.28901734104046245,0.02440517393578324,0 +hendrycksTest-moral_disputes,acc_norm,0.30057803468208094,0.0246853168672578,0 +hendrycksTest-moral_scenarios,acc,0.2346368715083799,0.014173044098303658,0 +hendrycksTest-moral_scenarios,acc_norm,0.27262569832402234,0.01489339173524959,0 +hendrycksTest-nutrition,acc,0.25163398692810457,0.024848018263875202,0 +hendrycksTest-nutrition,acc_norm,0.3366013071895425,0.027057974624494385,0 +hendrycksTest-philosophy,acc,0.1832797427652733,0.021974198848265812,0 +hendrycksTest-philosophy,acc_norm,0.2990353697749196,0.02600330111788513,0 +hendrycksTest-prehistory,acc,0.2654320987654321,0.02456922360046085,0 +hendrycksTest-prehistory,acc_norm,0.22839506172839505,0.023358211840626267,0 +hendrycksTest-professional_accounting,acc,0.2127659574468085,0.024414612974307706,0 +hendrycksTest-professional_accounting,acc_norm,0.2695035460992908,0.026469036818590638,0 +hendrycksTest-professional_law,acc,0.2522816166883963,0.011092789056875238,0 +hendrycksTest-professional_law,acc_norm,0.30182529335071706,0.011724350518105893,0 +hendrycksTest-professional_medicine,acc,0.21323529411764705,0.024880971512294257,0 +hendrycksTest-professional_medicine,acc_norm,0.2426470588235294,0.026040662474201275,0 +hendrycksTest-professional_psychology,acc,0.2565359477124183,0.01766784161237899,0 +hendrycksTest-professional_psychology,acc_norm,0.2565359477124183,0.017667841612378977,0 +hendrycksTest-public_relations,acc,0.2818181818181818,0.04309118709946458,0 +hendrycksTest-public_relations,acc_norm,0.2,0.03831305140884603,0 +hendrycksTest-security_studies,acc,0.2938775510204082,0.02916273841024977,0 +hendrycksTest-security_studies,acc_norm,0.2653061224489796,0.028263889943784603,0 +hendrycksTest-sociology,acc,0.2537313432835821,0.03076944496729602,0 +hendrycksTest-sociology,acc_norm,0.2537313432835821,0.03076944496729602,0 +hendrycksTest-us_foreign_policy,acc,0.3,0.046056618647183814,0 +hendrycksTest-us_foreign_policy,acc_norm,0.35,0.0479372485441102,0 +hendrycksTest-virology,acc,0.28313253012048195,0.03507295431370518,0 +hendrycksTest-virology,acc_norm,0.2469879518072289,0.03357351982064536,0 +hendrycksTest-world_religions,acc,0.3216374269005848,0.03582529442573122,0 +hendrycksTest-world_religions,acc_norm,0.32748538011695905,0.035993357714560276,0 +piqa,acc,0.6675734494015234,0.01099114155744559,0 +piqa,acc_norm,0.6697497279651795,0.010972947133006297,0 +rte,acc,0.5631768953068592,0.029855247390314938,0 +winogrande,acc,0.5011838989739542,0.014052446290529009,0 diff --git a/1b121b21b/evaluation/lm1-1b1-21b-oscar-results_lm-eval_global_step39672_2022-12-02-14-19-24.json b/1b121b21b/evaluation/lm1-1b1-21b-oscar-results_lm-eval_global_step39672_2022-12-02-14-19-24.json new file mode 100644 index 0000000000000000000000000000000000000000..4fb3776e863ccad74201a52a0b8fa2c9e12b083f --- /dev/null +++ b/1b121b21b/evaluation/lm1-1b1-21b-oscar-results_lm-eval_global_step39672_2022-12-02-14-19-24.json @@ -0,0 +1,427 @@ +{ + "results": { + "copa": { + "acc": 0.7, + "acc_stderr": 0.046056618647183814 + }, + "piqa": { + "acc": 0.6675734494015234, + "acc_stderr": 0.01099114155744559, + "acc_norm": 0.6697497279651795, + "acc_norm_stderr": 0.010972947133006297 + }, + "rte": { + "acc": 0.5631768953068592, + "acc_stderr": 0.029855247390314938 + }, + "winogrande": { + "acc": 0.5011838989739542, + "acc_stderr": 0.014052446290529009 + }, + "hendrycksTest-abstract_algebra": { + "acc": 0.22, + "acc_stderr": 0.0416333199893227, + "acc_norm": 0.22, + "acc_norm_stderr": 0.0416333199893227 + }, + "hendrycksTest-anatomy": { + "acc": 0.17037037037037037, + "acc_stderr": 0.03247781185995593, + "acc_norm": 0.17777777777777778, + "acc_norm_stderr": 0.0330278985990172 + }, + "hendrycksTest-astronomy": { + "acc": 0.21052631578947367, + "acc_stderr": 0.03317672787533156, + "acc_norm": 0.3026315789473684, + "acc_norm_stderr": 0.037385206761196686 + }, + "hendrycksTest-business_ethics": { + "acc": 0.32, + "acc_stderr": 0.046882617226215034, + "acc_norm": 0.31, + "acc_norm_stderr": 0.04648231987117316 + }, + "hendrycksTest-clinical_knowledge": { + "acc": 0.24528301886792453, + "acc_stderr": 0.026480357179895674, + "acc_norm": 0.3132075471698113, + "acc_norm_stderr": 0.028544793319055326 + }, + "hendrycksTest-college_biology": { + "acc": 0.2361111111111111, + "acc_stderr": 0.03551446610810826, + "acc_norm": 0.2013888888888889, + "acc_norm_stderr": 0.033536474697138406 + }, + "hendrycksTest-college_chemistry": { + "acc": 0.27, + "acc_stderr": 0.044619604333847394, + "acc_norm": 0.32, + "acc_norm_stderr": 0.046882617226215034 + }, + "hendrycksTest-college_computer_science": { + "acc": 0.29, + "acc_stderr": 0.04560480215720684, + "acc_norm": 0.3, + "acc_norm_stderr": 0.046056618647183814 + }, + "hendrycksTest-college_mathematics": { + "acc": 0.23, + "acc_stderr": 0.04229525846816505, + "acc_norm": 0.29, + "acc_norm_stderr": 0.04560480215720684 + }, + "hendrycksTest-college_medicine": { + "acc": 0.24855491329479767, + "acc_stderr": 0.03295304696818318, + "acc_norm": 0.2543352601156069, + "acc_norm_stderr": 0.0332055644308557 + }, + "hendrycksTest-college_physics": { + "acc": 0.2549019607843137, + "acc_stderr": 0.043364327079931785, + "acc_norm": 0.24509803921568626, + "acc_norm_stderr": 0.04280105837364395 + }, + "hendrycksTest-computer_security": { + "acc": 0.2, + "acc_stderr": 0.04020151261036844, + "acc_norm": 0.29, + "acc_norm_stderr": 0.04560480215720684 + }, + "hendrycksTest-conceptual_physics": { + "acc": 0.28936170212765955, + "acc_stderr": 0.02964400657700962, + "acc_norm": 0.225531914893617, + "acc_norm_stderr": 0.027321078417387536 + }, + "hendrycksTest-econometrics": { + "acc": 0.32456140350877194, + "acc_stderr": 0.04404556157374768, + "acc_norm": 0.2631578947368421, + "acc_norm_stderr": 0.04142439719489362 + }, + "hendrycksTest-electrical_engineering": { + "acc": 0.27586206896551724, + "acc_stderr": 0.03724563619774632, + "acc_norm": 0.2896551724137931, + "acc_norm_stderr": 0.03780019230438014 + }, + "hendrycksTest-elementary_mathematics": { + "acc": 0.20105820105820105, + "acc_stderr": 0.02064181078237016, + "acc_norm": 0.2275132275132275, + "acc_norm_stderr": 0.021591269407823778 + }, + "hendrycksTest-formal_logic": { + "acc": 0.29365079365079366, + "acc_stderr": 0.04073524322147127, + "acc_norm": 0.23809523809523808, + "acc_norm_stderr": 0.03809523809523811 + }, + "hendrycksTest-global_facts": { + "acc": 0.24, + "acc_stderr": 0.042923469599092816, + "acc_norm": 0.26, + "acc_norm_stderr": 0.044084400227680794 + }, + "hendrycksTest-high_school_biology": { + "acc": 0.2129032258064516, + "acc_stderr": 0.02328766512726854, + "acc_norm": 0.26129032258064516, + "acc_norm_stderr": 0.024993053397764812 + }, + "hendrycksTest-high_school_chemistry": { + "acc": 0.1921182266009852, + "acc_stderr": 0.027719315709614775, + "acc_norm": 0.23645320197044334, + "acc_norm_stderr": 0.029896114291733552 + }, + "hendrycksTest-high_school_computer_science": { + "acc": 0.25, + "acc_stderr": 0.04351941398892446, + "acc_norm": 0.29, + "acc_norm_stderr": 0.04560480215720684 + }, + "hendrycksTest-high_school_european_history": { + "acc": 0.24848484848484848, + "acc_stderr": 0.03374402644139404, + "acc_norm": 0.2909090909090909, + "acc_norm_stderr": 0.03546563019624336 + }, + "hendrycksTest-high_school_geography": { + "acc": 0.23737373737373738, + "acc_stderr": 0.030313710538198906, + "acc_norm": 0.3181818181818182, + "acc_norm_stderr": 0.033184773338453315 + }, + "hendrycksTest-high_school_government_and_politics": { + "acc": 0.26424870466321243, + "acc_stderr": 0.03182155050916648, + "acc_norm": 0.27979274611398963, + "acc_norm_stderr": 0.03239637046735702 + }, + "hendrycksTest-high_school_macroeconomics": { + "acc": 0.2512820512820513, + "acc_stderr": 0.021992016662370543, + "acc_norm": 0.2641025641025641, + "acc_norm_stderr": 0.022352193737453268 + }, + "hendrycksTest-high_school_mathematics": { + "acc": 0.2037037037037037, + "acc_stderr": 0.02455617221914128, + "acc_norm": 0.26296296296296295, + "acc_norm_stderr": 0.026842057873833713 + }, + "hendrycksTest-high_school_microeconomics": { + "acc": 0.25630252100840334, + "acc_stderr": 0.02835962087053395, + "acc_norm": 0.31512605042016806, + "acc_norm_stderr": 0.030176808288974337 + }, + "hendrycksTest-high_school_physics": { + "acc": 0.1986754966887417, + "acc_stderr": 0.03257847384436776, + "acc_norm": 0.23178807947019867, + "acc_norm_stderr": 0.03445406271987054 + }, + "hendrycksTest-high_school_psychology": { + "acc": 0.20917431192660552, + "acc_stderr": 0.017437937173343233, + "acc_norm": 0.22568807339449543, + "acc_norm_stderr": 0.017923087667803057 + }, + "hendrycksTest-high_school_statistics": { + "acc": 0.20833333333333334, + "acc_stderr": 0.027696910713093936, + "acc_norm": 0.30092592592592593, + "acc_norm_stderr": 0.031280390843298804 + }, + "hendrycksTest-high_school_us_history": { + "acc": 0.27450980392156865, + "acc_stderr": 0.031321798030832904, + "acc_norm": 0.28431372549019607, + "acc_norm_stderr": 0.03166009679399812 + }, + "hendrycksTest-high_school_world_history": { + "acc": 0.22784810126582278, + "acc_stderr": 0.027303484599069422, + "acc_norm": 0.28270042194092826, + "acc_norm_stderr": 0.02931281415395593 + }, + "hendrycksTest-human_aging": { + "acc": 0.29596412556053814, + "acc_stderr": 0.030636591348699796, + "acc_norm": 0.26905829596412556, + "acc_norm_stderr": 0.029763779406874972 + }, + "hendrycksTest-human_sexuality": { + "acc": 0.32061068702290074, + "acc_stderr": 0.04093329229834278, + "acc_norm": 0.31297709923664124, + "acc_norm_stderr": 0.04066962905677697 + }, + "hendrycksTest-international_law": { + "acc": 0.2231404958677686, + "acc_stderr": 0.03800754475228733, + "acc_norm": 0.4049586776859504, + "acc_norm_stderr": 0.04481137755942469 + }, + "hendrycksTest-jurisprudence": { + "acc": 0.24074074074074073, + "acc_stderr": 0.0413311944024384, + "acc_norm": 0.37962962962962965, + "acc_norm_stderr": 0.04691521224077742 + }, + "hendrycksTest-logical_fallacies": { + "acc": 0.1656441717791411, + "acc_stderr": 0.029208296231259104, + "acc_norm": 0.27607361963190186, + "acc_norm_stderr": 0.0351238528370505 + }, + "hendrycksTest-machine_learning": { + "acc": 0.3125, + "acc_stderr": 0.043994650575715215, + "acc_norm": 0.25892857142857145, + "acc_norm_stderr": 0.04157751539865629 + }, + "hendrycksTest-management": { + "acc": 0.2524271844660194, + "acc_stderr": 0.04301250399690878, + "acc_norm": 0.2912621359223301, + "acc_norm_stderr": 0.044986763205729224 + }, + "hendrycksTest-marketing": { + "acc": 0.29914529914529914, + "acc_stderr": 0.02999695185834948, + "acc_norm": 0.32051282051282054, + "acc_norm_stderr": 0.030572811310299604 + }, + "hendrycksTest-medical_genetics": { + "acc": 0.28, + "acc_stderr": 0.045126085985421255, + "acc_norm": 0.38, + "acc_norm_stderr": 0.04878317312145632 + }, + "hendrycksTest-miscellaneous": { + "acc": 0.2567049808429119, + "acc_stderr": 0.015620480263064535, + "acc_norm": 0.24904214559386972, + "acc_norm_stderr": 0.015464676163395962 + }, + "hendrycksTest-moral_disputes": { + "acc": 0.28901734104046245, + "acc_stderr": 0.02440517393578324, + "acc_norm": 0.30057803468208094, + "acc_norm_stderr": 0.0246853168672578 + }, + "hendrycksTest-moral_scenarios": { + "acc": 0.2346368715083799, + "acc_stderr": 0.014173044098303658, + "acc_norm": 0.27262569832402234, + "acc_norm_stderr": 0.01489339173524959 + }, + "hendrycksTest-nutrition": { + "acc": 0.25163398692810457, + "acc_stderr": 0.024848018263875202, + "acc_norm": 0.3366013071895425, + "acc_norm_stderr": 0.027057974624494385 + }, + "hendrycksTest-philosophy": { + "acc": 0.1832797427652733, + "acc_stderr": 0.021974198848265812, + "acc_norm": 0.2990353697749196, + "acc_norm_stderr": 0.02600330111788513 + }, + "hendrycksTest-prehistory": { + "acc": 0.2654320987654321, + "acc_stderr": 0.02456922360046085, + "acc_norm": 0.22839506172839505, + "acc_norm_stderr": 0.023358211840626267 + }, + "hendrycksTest-professional_accounting": { + "acc": 0.2127659574468085, + "acc_stderr": 0.024414612974307706, + "acc_norm": 0.2695035460992908, + "acc_norm_stderr": 0.026469036818590638 + }, + "hendrycksTest-professional_law": { + "acc": 0.2522816166883963, + "acc_stderr": 0.011092789056875238, + "acc_norm": 0.30182529335071706, + "acc_norm_stderr": 0.011724350518105893 + }, + "hendrycksTest-professional_medicine": { + "acc": 0.21323529411764705, + "acc_stderr": 0.024880971512294257, + "acc_norm": 0.2426470588235294, + "acc_norm_stderr": 0.026040662474201275 + }, + "hendrycksTest-professional_psychology": { + "acc": 0.2565359477124183, + "acc_stderr": 0.01766784161237899, + "acc_norm": 0.2565359477124183, + "acc_norm_stderr": 0.017667841612378977 + }, + "hendrycksTest-public_relations": { + "acc": 0.2818181818181818, + "acc_stderr": 0.04309118709946458, + "acc_norm": 0.2, + "acc_norm_stderr": 0.03831305140884603 + }, + "hendrycksTest-security_studies": { + "acc": 0.2938775510204082, + "acc_stderr": 0.02916273841024977, + "acc_norm": 0.2653061224489796, + "acc_norm_stderr": 0.028263889943784603 + }, + "hendrycksTest-sociology": { + "acc": 0.2537313432835821, + "acc_stderr": 0.03076944496729602, + "acc_norm": 0.2537313432835821, + "acc_norm_stderr": 0.03076944496729602 + }, + "hendrycksTest-us_foreign_policy": { + "acc": 0.3, + "acc_stderr": 0.046056618647183814, + "acc_norm": 0.35, + "acc_norm_stderr": 0.0479372485441102 + }, + "hendrycksTest-virology": { + "acc": 0.28313253012048195, + "acc_stderr": 0.03507295431370518, + "acc_norm": 0.2469879518072289, + "acc_norm_stderr": 0.03357351982064536 + }, + "hendrycksTest-world_religions": { + "acc": 0.3216374269005848, + "acc_stderr": 0.03582529442573122, + "acc_norm": 0.32748538011695905, + "acc_norm_stderr": 0.035993357714560276 + } + }, + "versions": { + "copa": 0, + "piqa": 0, + "rte": 0, + "winogrande": 0, + "hendrycksTest-abstract_algebra": 0, + "hendrycksTest-anatomy": 0, + "hendrycksTest-astronomy": 0, + "hendrycksTest-business_ethics": 0, + "hendrycksTest-clinical_knowledge": 0, + "hendrycksTest-college_biology": 0, + "hendrycksTest-college_chemistry": 0, + "hendrycksTest-college_computer_science": 0, + "hendrycksTest-college_mathematics": 0, + "hendrycksTest-college_medicine": 0, + "hendrycksTest-college_physics": 0, + "hendrycksTest-computer_security": 0, + "hendrycksTest-conceptual_physics": 0, + "hendrycksTest-econometrics": 0, + "hendrycksTest-electrical_engineering": 0, + "hendrycksTest-elementary_mathematics": 0, + "hendrycksTest-formal_logic": 0, + "hendrycksTest-global_facts": 0, + "hendrycksTest-high_school_biology": 0, + "hendrycksTest-high_school_chemistry": 0, + "hendrycksTest-high_school_computer_science": 0, + "hendrycksTest-high_school_european_history": 0, + "hendrycksTest-high_school_geography": 0, + "hendrycksTest-high_school_government_and_politics": 0, + "hendrycksTest-high_school_macroeconomics": 0, + "hendrycksTest-high_school_mathematics": 0, + "hendrycksTest-high_school_microeconomics": 0, + "hendrycksTest-high_school_physics": 0, + "hendrycksTest-high_school_psychology": 0, + "hendrycksTest-high_school_statistics": 0, + "hendrycksTest-high_school_us_history": 0, + "hendrycksTest-high_school_world_history": 0, + "hendrycksTest-human_aging": 0, + "hendrycksTest-human_sexuality": 0, + "hendrycksTest-international_law": 0, + "hendrycksTest-jurisprudence": 0, + "hendrycksTest-logical_fallacies": 0, + "hendrycksTest-machine_learning": 0, + "hendrycksTest-management": 0, + "hendrycksTest-marketing": 0, + "hendrycksTest-medical_genetics": 0, + "hendrycksTest-miscellaneous": 0, + "hendrycksTest-moral_disputes": 0, + "hendrycksTest-moral_scenarios": 0, + "hendrycksTest-nutrition": 0, + "hendrycksTest-philosophy": 0, + "hendrycksTest-prehistory": 0, + "hendrycksTest-professional_accounting": 0, + "hendrycksTest-professional_law": 0, + "hendrycksTest-professional_medicine": 0, + "hendrycksTest-professional_psychology": 0, + "hendrycksTest-public_relations": 0, + "hendrycksTest-security_studies": 0, + "hendrycksTest-sociology": 0, + "hendrycksTest-us_foreign_policy": 0, + "hendrycksTest-virology": 0, + "hendrycksTest-world_religions": 0 + } +} \ No newline at end of file diff --git a/1b121b21b/evaluation/lm1-1b1-21b-oscar-results_lm-eval_global_step39672_2022-12-03-10-25-38.csv b/1b121b21b/evaluation/lm1-1b1-21b-oscar-results_lm-eval_global_step39672_2022-12-03-10-25-38.csv new file mode 100644 index 0000000000000000000000000000000000000000..413d22f5ad14c5a5ce4c1f7b821bcdaf7c79486a --- /dev/null +++ b/1b121b21b/evaluation/lm1-1b1-21b-oscar-results_lm-eval_global_step39672_2022-12-03-10-25-38.csv @@ -0,0 +1,10 @@ +task,metric,value,err,version +arc_challenge,acc,0.20051194539249148,0.01170031805049937,0 +arc_challenge,acc_norm,0.24658703071672355,0.012595726268790127,0 +arc_easy,acc,0.4911616161616162,0.010258180468004828,0 +arc_easy,acc_norm,0.4297138047138047,0.01015790800576368,0 +boolq,acc,0.5651376146788991,0.008670528471841561,1 +hellaswag,acc,0.3211511651065525,0.0046596447333095365,0 +hellaswag,acc_norm,0.36755626369249156,0.004811543077792706,0 +sciq,acc,0.746,0.013772206565168543,0 +sciq,acc_norm,0.662,0.01496596071022449,0 diff --git a/1b121b21b/evaluation/lm1-1b1-21b-oscar-results_lm-eval_global_step39672_2022-12-03-10-25-38.json b/1b121b21b/evaluation/lm1-1b1-21b-oscar-results_lm-eval_global_step39672_2022-12-03-10-25-38.json new file mode 100644 index 0000000000000000000000000000000000000000..31d013262caf0015d08bbd1f243e4f0aba5472cd --- /dev/null +++ b/1b121b21b/evaluation/lm1-1b1-21b-oscar-results_lm-eval_global_step39672_2022-12-03-10-25-38.json @@ -0,0 +1,39 @@ +{ + "results": { + "boolq": { + "acc": 0.5651376146788991, + "acc_stderr": 0.008670528471841561 + }, + "hellaswag": { + "acc": 0.3211511651065525, + "acc_stderr": 0.0046596447333095365, + "acc_norm": 0.36755626369249156, + "acc_norm_stderr": 0.004811543077792706 + }, + "arc_challenge": { + "acc": 0.20051194539249148, + "acc_stderr": 0.01170031805049937, + "acc_norm": 0.24658703071672355, + "acc_norm_stderr": 0.012595726268790127 + }, + "arc_easy": { + "acc": 0.4911616161616162, + "acc_stderr": 0.010258180468004828, + "acc_norm": 0.4297138047138047, + "acc_norm_stderr": 0.01015790800576368 + }, + "sciq": { + "acc": 0.746, + "acc_stderr": 0.013772206565168543, + "acc_norm": 0.662, + "acc_norm_stderr": 0.01496596071022449 + } + }, + "versions": { + "boolq": 1, + "hellaswag": 0, + "arc_challenge": 0, + "arc_easy": 0, + "sciq": 0 + } +} \ No newline at end of file diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e7dd08711ba6d7dba05e13810be0f12217ec90af --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb6fc350a01db90fbd67725018646243240dd5586d0f4e487d649c0c93e9d5d2 +size 51395415 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..20cb6eeb56e028fdfe217969b393a54e1c0e7283 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea972cd60e750c02e020d0a3dd02735e4ddb5a2b260deb6e7bf60d91ff351dfa +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..69a0f59ae5256089c84b58b5a972b805677bc043 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f43464cd355ae8e442bdc4d5dc724684a0a032620725c8c9152ec54c2916291 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1afd818b419d2d965a069429d957b09fd90d4e12 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1fd137bd697aa0175d3e1fd765737620cfeba9d81da1b5e0dd4922912f852df +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..56b67165143fcddcdc4ef20e8adf3f3ab0b3a476 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93805cada78e32629d9e9f3e0d4c8bd75d2c3a1f29e19968378e9020453170ef +size 51395565 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f278de05dc4a99ba2ce5dc6cc272bea4a0c2b72b --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7197a3298591d76013e2f03e4360d795d7fc89169343c3d3855d4c54b0efc9c +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b1229b529066ca6246d5ae484854d1b5931d6ed3 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7fe13bba46cb3ebcff6298a532c55cf974db0d03276abab3efa31af5d329874 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cee35128b7269ae935233ac5ec6110b61293b35f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b40673fc430a77a5560c04c2b2b390f4c0ae04f6e416ebb3f3203f978e5f9d2d +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d51e3b423774e23af6347f2ac6ab5f355ad12a66 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:605a3f4a93b5d756075fbe92050ba1e167605e42ecde84002a384a5bfcf3aadc +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b9b93295669f68479c0bcdedf1f434a4fee306c2 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db25163e0b3ac8d77d97f1b8ec4cd6a3a06d37dbde872b6a3e3e91a9f64e3b5a +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bce43e545bccc2b48cbd2e0d433124fe0a61578d --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfd9bf9c0f7511a0d3cf992191086f113bf5e749b3f2bc25bf79fcbb7df5a32a +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d0d46b68812df60d7529e917a97263f3af770bff --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96f5208e95454f790fb4e75646872f544c536a8e618658553d1714c65460dda8 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f7db5d8f77507d62a83d97186cc11a6070d4529f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbef1bd7ce43647b5bd8844ad517f905a8828c73e87a53db4cda66f3dfb2fa91 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f4ba1c22d33a1d3a695fa70cf8f4edfcadedb868 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:930c60849bdcc340db91ffd5ae0ed8a733f37c066802fc3ccd3d550f6b4a528a +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7dd8d37aa5a3af900685c9f644d8d2bcec8216da --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8127737c2058b57156575ae4064dc8992199d1a92312bf27ec692e7a983af643 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7e4dceaf4c4f84b78d60bf60c1893f1ebac148c9 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a10f68d59475edf383e68f3a249a05ac392b7b6306d0d471666c2d36626cbb5 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..57954c6298f176e4d920b5d815c1e24212063c67 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0c1007cd7ec5d74f4c535cb5a441d1891a0dfb56abffb9926edadeebb4437f8 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..502bd42f001fd5e6a369cc579a3e12c41de6c849 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:829b7115fbceef48613a31d4fae74afaae3b514fb7d7de5b9d9d17cf0314cd1a +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9d9bda2aaf7cd95eea475f53596f54515a54dd2f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f51d6b950b911f57cbdf857e575c10c2442c6d59ad2e1da048dbe7c3f90ff01b +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c88c5c3c46e9fd7fbbe640431388d9ec54fa3061 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b599edcf1b355b59d57531cfe62b4b032cb170b2c2a943508472c0a443f71e7 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b47c3b4e6715179c1d8b80c2b5226b419d6d6cac --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93c1d4309fe1596247d5f3493a8f65be16c130e3c1fac5d45e9ce7355f281e53 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b6f6737cd14a6a9ff6f15d80736929c244d6c71c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb4e255175b699092820c427b68fa126e1db0b638d5cff33641a15bf66f3b7b1 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9be6b7f3e93cecb0d6694b6bf6657ac93a833d45 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de0eb04e65dc8d5de30019fd3b735549eadafdc61eab3928ab39b73df0b5ed48 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..006f41b730b83152e58a85dd0c3397e1530bbb30 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcf45643c23a23bb00b8dbefaee6f053b6fe864c8ddf82d212935aaf9e654b82 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9722311ccc379d52cf5f5ccd9d626a1b6369a28e --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e8c890add12aa992cb58b0ed0cc17ca077ff2de80b7237372e03a88f08856cd +size 51395565 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0e8a9f10def33bd6ae74204f38e1ad053aab0f2d --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3986e8c9a64bbb7e891a2e6540f9184ddadea53552a7025e32ce452fa995736f +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..788cf7ab73ac9f6bae6633b2515ecb56b59dc5a0 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a46411649ac52a03f72802d47d3610923a4ccaa633f9657074ff893cfd8395b0 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bb26e085c2abc3b27ede118ef8ca1bfb5e5cd744 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ee757640f04756022517c2ac849658d2602533bcbf0d1033fc53578591d282e +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7bbffc230ddb1cc0daf8e1a8d28666078b71cb8f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0113ad7891ef0ccad38534b0f0d3d685a41ae7598185b127cc3e61840d3b6350 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..885e3418afeb676ed212b8643bc276f594478b8a --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33f205fabd7e99e93a8e7ddfc249448cc5625275c38897c3e23fc03143c62329 +size 51395565 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..04ad9190b611f9502fb3c9ea3c922a7ee21940db --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e256495a3c9c5fabf6d0caecdb939abf267b3e677873c34b7cbb6b41fa1d3b0 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..af9df7f4802f0f88fa7759bcd2b6df8ac11bd345 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52cc791d7a199457fd026951277dc9c7d963d8e03e32a7ae4fbd429819427e50 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..87df4e1cb96ef3ccb537f7e2ff0a6734d7c315e8 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:597b06f07e1f3332da8de3d9781787d5a38d0fd35c0782738c0241de91746a68 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4f1c9e9da181d1e425e783b398ad54870b0c04b4 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0da5460bd23806c26b3b3537c7aa9a83f32c0126f78249e1f2b007e4190eba5c +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d8ff38a6d19d26e1336542ac3aae935cfe73aef0 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e49f9b30f8b34ac9ae17cccd0b0245e66c95f335cd9c68b494a68441eecd903 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b4971ebb074eaae679a57c8f4af689c00458a9c2 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7edefe167d517a3c1a1c124250444a71e0fd6bcef07ac0d38be14567ebed1093 +size 51395565 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6fd7a01b3dc3c72d64bb450a42dc8dd8cc36f1bf --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a7cf645b3407c17610d28b095476989895d1e958bf5d5f5aac7c558bee6620d +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e712ee74a31c98aa870fb3bb11b664f6ebb54094 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f5a53b6a0e3fcdeca83af29ae3243fcfd535dd1fe33c474d39b8f65f8e846fb +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..27b9c62b0acd5cddb67c27e225b4fb70cb422fe8 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9c555265eb6ff0cf3d432d6942dff73e5a622b927f31e7014974294fc10d1dd +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ac747d8bfa8c44f441ed56af9db55d526d90316d --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56462b47e96ea402964ccbe51c7abd543254277dce38218daadfb54b569d93d7 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..85e776f975ade4cfa70f2244ea3142096c01845e --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2329979ce7278f20825c7c746cf64a88f2fffd9ff74f4c84140aa4ba60a25a7e +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2774d8ac41d522d5b3be9115cf444f55a5199530 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:457315c6ae7c2d5c6d2af7e48b404087273e2d59f668d2451c3966c45f15d58a +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..16b1b0fe05cbc1a9486eb87d1cf5cc6773199a5f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad08726bc157d2f297d0df6da1a33f59c23b5d62c1966f9b0b43d4892c932a15 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..45635d68e03b43a8e8b92d04f42e7d677ed6b7d7 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a1f8e9c7e2efd98102fbcde8d30b771555308fcaa1ba6eeef3608a1333a7942 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2a07bf9c5bfbb02866bebaa57966d6c042ef5afd --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b95d7d90ae07fa5b541d4440977d5b4c576b786b75dda91c473d25ec20fba94 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d2f39c60839691b164bfb5d5d91513883b34be79 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33c1339abf9c5fabdf356bf82c80d4da1df2c7c0cb522d7b625d0caafe5028f8 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..41296a3b315f5207c6e3a0c6a117f0c2d0d87e33 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca4b0682902bdda7ea242a021929da21372861dbb1fb3b8062fa05f8e2d37142 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..78b4c45936378e2d9dc7416c4b5ad0536988875f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d1a6aa4dccb9e7d7e79d42c788d7950481177d0d397dbe544995d9cd270cd33 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4bcf8e5d7f5b5052f4e3d9c1355a6f963f86711e --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24e6ac6960ec191dc58b96de764707a605d56960fb299ed9afe3eeb3326b471c +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..baf84aaa42e73f27df3147807efb640d11453a0c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25973e196f529411fbd6d42eddb8f419e3b6f0b87e11d24e5301445d15927e18 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3f4699428d0a663ae01a3f6c5de96d83aac00447 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d748a22564eac1c23a6040d5834598dd9009a0aa38da6f46527d88d09641bb5 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e808128f9e3c5274e581bcce678b5e3bff8323f9 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82442b17925d72f54bbbff2ab42787955384b57197ecf7c30f4ba8328cc16ae8 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..37a1b92a2f01def38ff44c65b376063c248b0507 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df8001779f4f3f014da26ba2f8ebcdac96722612c9da4fd8296ba8504f8abe00 +size 51395565 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..17dff31ae08252848dfff86f16ec524b08a4fd12 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de3e9ecad3505f6427a952b5a70b03506c070501ea98ae1bd79283d565331c13 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9f85ee24348a05e7998590f74a533ae76cf6e53f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92b1e0b8679a5121fbd1ddb3d6cf198b7d0d2babd023c54fa2df003e49343540 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..93a389d096be8bdce59350aa82b5e8968b4132b2 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a71ba81535cbe38c3b3b1400c4fb99cf5e0d801a9b872b8f68036bb687ecd677 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2cd0cfa11a048e4a7359092572aeaa4f95950831 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d71f4d37817e8a41f0ce9ab98551699795ef4dfe2e9fb4e9a40ff343f7c0593 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7334421996dc71e0c496650aa6b0a5bd48c2a0f1 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:825c9fb2a28b1f4b087d12d6452cc85b05dc2c2eda1abd29bf1120941ca7f710 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ccdb0de0ad61d5f66e6dd556d972a3f00f015794 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:313821690ab734cf7488f7dd5592ddcd9a8ef9005d20dd1bbd9f0119b4f1ea57 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..86a39b008798f65e48ba06e64c1c40cba27516c6 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc2f075a4dd9c4c0e284964def0dd1ee7e364c1e4a8b0f8b1a39d1c457d6a51a +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..31e71e86f2996a4ea741df397b2e56deb7fef04b --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a80af9d502f3868349f020f3cbe6b7793b86fc1060f1b94e5590f30d96cc9638 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f6c044aa01eb18fda71a9d08191b146a1d19f814 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf4fcda262156cef7d44e0851c350dfc270112aa6027a4e68a34b231cb156715 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..64f0075916ad498328eb999f194fffbc9e859d87 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f8c068a9419e2443d939de7aaa34f8397ac5c6f82a16bdca18785baaf570825 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d5fed398561978a595f7e76ab7b02b9d484e9567 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d61f79b979ff5bbcd4ec5def25a8a4da92847199d8ca5d450be447a611db517b +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0d68407ea578e273755d3b8ad427ab1390ad711d --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45dbe2dfe84431f2d73e6db10fee0b4cbb4532901b7a6aa863f5151573cc7fc6 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4c14414c3353807b502b481660d8c457888c58c6 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eec61fa182671e167d3d6ec38b33a593c02b1b5b6da674cddfb4649a78196e46 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..eb628d2d1a95dd46c30f33ae4ffff33d61c153b0 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1edd029f5e843314907f9e13d6cdb2f1ad5c0343cfac0a09ba2310042da5c52d +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..720b3f0c5a8401d1e20a29e419fd91c0b37da106 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9eab80ae9270c3b1648fd7ddee4b6cbcf3a7395a65683e9123ef898c6915072 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c362b357dd20fda04664bc347d5db36439d1ae67 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f83535bd058aa2266ac091c4457f9f95adfdeca8959bc93410eecec70b4e2268 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..112cda67aabd94e4380983845cae061b9e3d7c08 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da9bd3ea976f2570755b5606d279466978d679a220eb40573002cafe2a28a339 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4628c9cc1bf7b352413339337f42609cbea287fd --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0736ed39c0fcc293d983a63fbfcad6233d2e9150cb59389c01748c38c90310f +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ea794bc5a6ad029b2d2d9ccef678537d907f2580 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f76a22edc4cee34d9003d422392d917a7eb502d4119a29841f5c14b79e981a0 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a9f3af5c16aad358ad7066eb5438da1816903d08 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d6c8b88c146e655341738a8319262df78efd251e48eea02582bca21e43fc391 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1360298abc92dd93440b8ac56c29084549dddc9f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:921d10a5bddcd363aebc9b90b975d182fb72e46d8dd40cff1064cde355cf2151 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2f882bae2f8fecd2b9a60b5c4c5b9d58b26f186f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caa5d5e2eaac8827e578081cbb8ce666664dd3408787def9f312930ed969abba +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f4da267bc20bd3ebda66b12d95a0ec39c8cca6ba --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5d694634614061efeeadb878c445cb0d7cf4a932e111586a1a953ad9cd75e9c +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e289d6a8ad526d4cf11ffb58912834a599781f88 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a3d38a21ad4937b52378b08cb5ab35f672da57202ad50463bd76c2db40dc5b5 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..926de18fd97f3e091638fae7db002dc5b1953923 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d03137c04aa322e087a4b81bb448fd79c444b0c01e83df8661c39417a8e21b94 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..88232c5c4037d04b74384adec04c9c6137874fcb --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e3c3c9018c28c78b04d8f8449cb2075d9dd77a245c17892135745e734ffde2c +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0d6b56174d5f696097c64883676e4f1dd61107bb --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4485f11622a1c846b4354a74d78b1eb8aee8749d225717cafb53f6518c04623 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2c6bab1088e468ed9b18e125ef411024e81c29b8 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7733acf5a0419e9347cdcf5762249e51d4e2cec9fc2743eec72accb0970bf853 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3e6493761d646a82dfa889ee14c6f13868e4d136 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1641539c51a541b6d8f0ac7d0dd5ac32c1bee4db6de9cde9b9b2bc7bcbf508f1 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f37a8ea513e926bcf2f68fdba5fc69887a663f5a --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3a90f6b4b4fd59a2add9607239344cd609b4843d9ac8e57556dd6569e0d13ef +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1b624b11a80ac01b24c478fa46caaec888f98e8b --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae60c47b5b4ab32c6b56afe7cd26b120d82940f6d0b863465e247a825787ad9d +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2ff1deb4dc8655b7a7776f5708b6b23672b9996e --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5c3ebf7d5a499cdd7bbb1f5af396ae35238afc142c9e9f638edbdfc18f175e5 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..38edafdecbebd0ae3d435d7adfbbb1049eb601cd --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:739d5d985a2c1ba4086aa4919c19b84cc26829d442e26646030d6f37408f28f7 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b978c2ac52c51c67fb68da00da28f9994f061e0c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65fa5c3bf6fc71dcc7b50d1cf15bcb098cf90e1dcf3cd646bcdef2ae351de1d4 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0cd56276ce60dcc018f77b54d80ea1144ac22953 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d25312fec74d8c6db01940d4af2423f248fb00fab5302cda144052082c0b875 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..02733e3ab0f17fa308693130896bd28606892f26 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67e467e5792744fbadb31b64aae2eb4e2173e1bec07012258d0274ec339c8a1a +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6a00a0b6833e346ecd2c97ddbe23c0d1ccb6b56e --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e76012251d496bd11f867654506c17f9f2f884c74c2c4f8b1aa12efbb13580ef +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..155ff85475e85f52c026334b68eb47c336b0b659 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:270173da2eb0a44ad98da18dacde7d38ba16b7cc5f9cb35e2afbaff519b663e1 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c87ed614471cc5d9408ceb372fc8706bde1abee8 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8698a0bc6d24a0770ccbd848735dd9ac94363657abc388c7774c8ac7066a2712 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6e989609c44efe889c25e15999a2cb62a7106d47 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15d0f7227c9b0b6c965b40714c4285a6ccecb9b480375d39a587ebd32a129c86 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..72c47deafd1606db8720a7845eec208df5209626 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:473aa40293fa92b0a63e81c4c1a8aa3a90d3581bca382ba2ebdccf7163d95901 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..201f373aae91fa98d13def2038dfc3f66e112db9 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13a0ac4739646a26554cc63758eb1b4a17e66ac3a8a1c0dbaf2957edbf85934c +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..57c1407631f322e9cefb43708b49026fc3b47501 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:747e11d05e61613d95555d37d796624f80c58f2114e88d6eb35d25bde9da36b6 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..be3604634b1843aa971a10bdfb61fdfb1bff48c2 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86e5a6f34439071bb2d50e2521ff3d0d4fde09c422c82f9688a4b1921f0c9fe1 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fac773df9bb721e18523c6ed44c282b687fe6271 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f68203ede774c2fe37e686a43aa3b01332afb04ea1f78d0c787b1d6fbcfb0b45 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..80d0edb0c1b789c62da6bb3b243164a39d896cb8 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59c220f4f582987c3027ce1bf6669106f501987c12d0e277f888e19e1462f29b +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dfbde2d94f99e28195c4c834728c3a07332a32df --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:142bf6e2ea26278e341def19dca664613d86545dc86456558666017a7798de4e +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..be8eda65abd123aaf244a3844c290ea8f191e09e --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc029c2fd4c9150f040e351d7f99e54878c5ec8eab2895e615a5a6b0cff328e5 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2ef6ca4ad936071faa18bfa47517cee9a39354a3 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bff7e859e02ac6edec3bb6b0d5ddc628ac68da4bbdb660e89ccb3bb48e48ab0c +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2d1581a837c516b145cea73048c657ddf61fc3c4 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bb3f87ee8e9be1e8c7268cb1cfd64f5035ea17bb2a2b24577bef5b866c18006 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d5a0933acc034d44b151e24a0731163c063c090d --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfeff2ced4bf098210c61f950b79849be10535e14f3ec27decf3ff5195d1c9ec +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1d5344b016671e59b8755819758f204dd6767e7c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33a26264f7019665ebe97a5c9188d87bd4643e7960fca2276236861c9eae3d7f +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1cdb3c8e6cb098b014eba0c6ef5d9a45266ba847 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9b5958c53ada24e2c663664fb79a266e7646b2a51a14ebe5ca7712533fbb519 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..77bb664386b3c4ba117c3e288cb7cca92ee9b7e1 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5ec60ea3e5c4dbb95a4cfa0a91f13931817eba3bdd7f8fac33d3af57bf26f1c +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..da7204674f5b73bd6479d1522e4ddbcd4632ae92 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d67b55c7f5c0df2a4d04e288ad89343e0230845955dd58068b5f869290f50757 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1d6503adfaeee6e44e4ce0f6f4032773abb3845a --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88b02f4bd1e8248b5750c9a3aee51f919685022394cac9a720a3371597aa70fc +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..26ae559e2c8a34bcf06de8b3ccbfefdead01d2b2 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ba48d53e92ece1c1b11c59cf6804c009035ae72a387c09a5391365d9915872d +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f6ff3e5cad7760847c362a45f7fe1f9904886e75 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a382c5be551381ba1f2cd951b8c6ed0dfecf67f386beeb2db48757a8027afe9a +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..385daee7b207f515cfbe3922b1834367256e0a38 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a3bcee49059663af0168e040d7890870d28f41c7cc5041277e3fa602cb45549 +size 51395415 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c48664a054d9ca5a186742946f7fb1bfb51be912 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:922bedebe8640d5e04c1625514b8659a21b9b95f496c10df8cbcbe8904318a01 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f045322b620c5e47f8d37d9c10df19f85d8c424b --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b00ead0a3cbbbef1b9f64f4f5d3e4af0d7cbbed0d8dfb4b3095d31b5ece65b8 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c1a2a78c64b6873230af4edf06c88fa9ad2e7055 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb095b9ceb82ab5c8efe5e6c1615b8ca56a95ccf9ff4f0217685550ee811cb61 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5d3e1341338d19f6de64dc3ac810164b172a6eeb --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edce3368066c1a06513abe9db7e9281eebb435387d8409e3cd3d45d2f2771537 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ac54bf5b2fd3205d288d2d76b046c2d61f81b7ad --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b9d686a105d2e8163e77adeabf3d347372c3624a63360ce6aebba3b693d8073 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b3e04ed383106f002037578228502929fc378be4 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32c8674e5d1c25b47eb63c8ddeec019e4498062d770e1fd1c8b80f99d72a5275 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..530cc9ed180d09d77382331d3e3a490ab90a7fa6 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:363ecedb2d3732c77e2d27e6d6426075def5412869c2f96fcd0a1b18938ee5ce +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7dd0af5f83ccdeeed38b2a0016398218f8bca97d --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8cfc2d4d0154006f2a274cc2138b979b39fd7a47c22667f24336b1eb366910f +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..99c3055cb12c8aea505ea4e6caee9bac954d9e7d --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9abcb1abcbfafa91915f7058ba2ec6a5993bc30473bdd83aaa67ab62366f99c4 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5cf2ac38b8fa1eda1a61b331bae404e5dfbe78f1 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fa6f441796ba1b6ed9af97f0ba607fa9ad6e04bb81b8680f5df2c27647bf2e1 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0df47f54701be3d05b2d841722c36f60510a7088 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5b819fd84ff6fb168bd32dac41e90d00df3062eb52120b834995b15574cf654 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a53c4e283f1a411a95daa366a106300916e5d407 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e998ec688049ec3189307d115631388dd56b9924671ee3835b151a5617cbd027 +size 51395565 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..956a32ff5e20257e9ed39ad46327cb29abc619a9 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f24a81676993e53beb91fb856c33ff79bbf58b239765056e07d4b15cfbc019b +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7d7a0c262afed2b94aa0f59675c4ade14614a1ec --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e406f2c367a45aab30b3adc33a540cf00d557c569ece8f63b49eae042bea0a8f +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c15406dd32af32526872370511577d6294036a3e --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:124d4af978a26878dda00505f5ad782be4a1dc0b3b63ff6afa7f32dc152eaa03 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2531a3e8c0d62c32690d56113a7797c03bee53eb --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e972af69dc725ae875159076d3056c25759e8625d667e3f5e33e5fa55bcca074 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..77a548d3919d5fcc0e00cd167370a6acdae68540 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c4ee3d9277d5d3b6e5357d1c4e8f8779561d841ac62bb9f0e34222a314e8fa4 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..78b7f0b6b313c7d9cc7f2ce9ed657b2611a41029 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf7e82c45d0c936f2ac43a932f5d7204bbac4580b75518126756fee1db3c52d4 +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ca626eae48a1f5f4fa6d11b42c940b52cdbf0410 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47262fa5b93541dd60b14a919407aaf37b146b818c806dec912d4f9ec3ec6b6d +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1e32cee570c2b409fa1685f967c2e8d6fed2ecb6 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdab77b0ad9769972716a5b658340df4d0acc4be90b40229e3a50b3386478abd +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..aa692afda1e0db056933d5eb87fe2ca7b48c5a62 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87dc2eadc478fbd208bb78c947facdbac1fdb276a817a1da55ff89ecfd2b9e9f +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1b95f154126d9bbbfadb971e8920eefbb6a000c7 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c3fd5b827c1b0b1dc957d06d2ffeea05357eda49ef1267db4a97cfc5446c983 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e5de7868e1813a5cbaaf0d1c617a9a21341456cc --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df7628c4d7072e87418471a5f8f11542ce7a49798a4ba06fb8bf30f2ff931151 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..53f74bac75b77884670194e38b2acf5467cc2c2c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:051d3973d738e2477c74703fdb690b661dd0e3894a3ab4073375207aed7eec38 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f6d6ee6a19bb3f4c478358921591ff31dbbad43d --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c61f50454f95fcc2f648b398feb4c7b18962d51a37801ffe8f82372bf7eef4ff +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b54db3301c4aac7d50f3ba133c111d91e2041c34 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:def6fb3da110e3d859e49c4c7e7f6a2ed64cd53d8472c44774be1db578e4eb64 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4ba2fdc6c47db0d69ac871cd498d7d7175040f3f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7140ad9c10fdc25a2e1fe46e8608a87207cd45a15708d452fb7414a4dfeea970 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dd063a431594da2d7a6a2acdb24b2ef50d69dc28 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be5bd9025ee578a847d46d11bdf83a6f6580a083746e6e880ba90401d6642164 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0ee89746acda09582b07509e75ed2adabc0e126e --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb9086af5f8b27464d93da5639ea3fc16a5b0163da7311e377f6c0c2132ab0ad +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dcf18742864edcb4801f037b07020aa644e7d8e0 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4b6f9a465d5b63e886191c9b495a338b11e466ea213e6c3fb04e847e4735d01 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a834494f5a4bc8643d3fe37633e204397d17f43 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54c6b0de33a26b484b4e00d6703d637e0755d9c6d347d3915953fe8714ba11b7 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..88344e63a40609ef372d69219681844175899791 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ca1d30de3e60487151ce605d5167b8bae031bacc871176a3eea1733f6db8ea6 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..595920c41e2628def0d57a1ff5873582e501beaf --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f20513d0e09289fdd0a8ed31b9b7e0eb3105b2798009660d146de50a5941d5e +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b365968a429f57ed3897359ef9064e465e7abd53 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:188af59416bcb58ab324e923da22929f492816d3669e17e2be73506db157264a +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d2ed4b40322b95ea92e0b8b1dccd254bd524d629 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:206aadde1a9ffe5f0bf61bc9bda393c9cffffb26a5e9d3092cc6c75260753dcf +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bd4d29a9d51c50db0b61ca6b410ac4124216f3d3 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d20fa82e577ed2d2a148bec514d6b6fdc5d6676935f42086d4c3a4505a3d17f +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..356035d12ca1e17347bd3ab16eb90ad5c2501cc9 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea7675071b0a49308042b65d585a08e3921155775b7f270eaf977b6a09049654 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1f409c3633f34b563b766fea5ae75055668253ce --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46a466960017da56e7f003f4d678712a4235afce82384e5b7872a11886875146 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5289644e0a27ef04791f0eac270d49d7ffd8fe37 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8863ff207f71357fdb4ee6035094605bf66dcff5899a99a2d242d0e173545e21 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ea9b8675dd5373dd738594ff1baefef3f4fe10c5 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7e632023e9ce895c1976fe3b702cd284303bb6c2fe11f0e7ae17df623f9271a +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..07b6a5d87c0673a8c9f05b257b5364409dc36125 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac228010380512b775bf614f233bb0f247af919e22ace31ff865ea669e7d75ac +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dfc375261c433afaedcb2b50dd35495811b67ab2 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15011d428ddf06869734824657f429569f4215ec7327b97e4b32d9eaa09c2a85 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..41b06dd253022528fdf2d696dafd8ae89f0d949c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b2ca6be35b45078e389e599ec079454f00eb67f77aee2146ecef93be071de8a +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c768201f9f8961e75f78348500c8dacca48b84cc --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:963961c03c7538849ec72de02d8d05205a1bc4a21e87ba9179310e760ce669a9 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..57ff141f7adc15e402234027d663a386eefe1f22 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97a2794bdb5d761dfdc145e61c36fb7aa65777af41bee5036fbfc30ed88b093a +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..194eb1ce8b4558bc754e65cf7a3a6181593abf80 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bbfff7ac363251a3a0e02c0ffe4e90517bf6629fef9ab58cc519c1d48ae2986 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f43c59cbccfc417687dfdfc663fada2df8cd16b7 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5755b7668daac9d20b58bc8ebac919571659c1dd72e0b8823a2124bf1d66124f +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d600d146f6ab2f8f4b1967cd4d1a72808a28941a --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dac572390fb24d42c3f780c46f4552dc449dd880b59e38ef54098922bc7b4058 +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..90e1046dc947af389237d192d388eacbde9ed59f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:032eceabfb2e323abf435fb06ce4e80324a49b507b8e670275a95951b202b26d +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bf0906dfa6aadb37c5095c307c1bfbbbb6d0dfd3 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20693cf4b947453086c0c23f2ac679d6398342ffdd642706e6a224d3237c63f +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e499c5648df87db204fd1afa869460352fd85388 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3354a489cabf49f2f87d28ef61c07ca8ba6c4ca6d60f8c2b57b4318c7608675d +size 51395437 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f863eb0332087e3cea8a6c532d88a091a8e61b92 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:601396f6e7887bdd693bdf81d15182db53cc062af27e5da36a759fc611f24a14 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a12f10ce8eb17d75b4212e359d31961456a48c6e --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:243c4ff31716f047e7cb2868ff8e262fa1b98219940a6cfa3c9706a0ee0d714f +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fb87b359d56ad859da27764227afcb30adbb6faa --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27c97182803b0b86f781b1c80b0d9900ff7a244976d96194c39372d9eab75dfc +size 51395565 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2d3f3ea01e7cc6240b8e15b76d2c68b3f4c5d27d --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3883a6334792b1fabc103a522b1c7b5913384df3fb45523dc1beb7b011c1a91 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..10177e937ea0ee4460af1764f82e447ca73ac7ff --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8aa21212c03890b693adebfd897fb13db90859642aa2ca555248ea7f153d59b +size 51395501 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..60189a5416de741f917a473f57d4ea6ad614aacc --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7db3be01edd5b3e5f84f410bbf0bdc519c19db81720abb95d6690735b33349fa +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..65c114e0fc4016792e3e57b4f89befed1c3d49aa --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b5c99a4d18e166106ea9db0a33f1cd81620ac03b9561aee7a447e74087887ed +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..518adc5adae13e5200aaf460db18bd84eba7f4c3 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2082d87497a4a5593867db30054bd0cb74d088a71108c348b86c549af6bf6804 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ffebdb20bea0a59cda67f5afe736296fbc7b85fb --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33cf7ce4355a1bf36efcc921f28750b21db85fb88a067388303bf3a4602346e7 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1e213a1d142077ce99a42f0502eb148350aa79d2 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f7f23201f6d6d566f540cefe61fe54bb449317669a2eec01cdf43a9013de380 +size 51395373 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..15b16fd8fa8dab0d19b199c16aece6d846a40c05 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c90685342361419db39f8357febee1f345c997f49252a35f6b89b8ae61abf18b +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3139a57b465b97bfc0df57c4ba6ed60b0904c480 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3a52c5ab05514ee2507ab894a3401507cb546f45dd9d76205680cbfc74cc023 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..76cc5cb6704533dc00265f1ab606abbc3b5793ca --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e424343a3dba142e3b79bfcbc84ac6f72eb832d90850b59aac35e8acad04216f +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e3f410376ea10c11428c5c41aff358a95606fb14 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07e979369d8adda0d3e5c8e053de27db89e44b06f7b05eb85c487c6bc7d3d757 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..efc02edf7a5a267478bf986a56a88ca84da5c94a --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74e2ac44b6999a812f960311a98107c2de6a1a3166e4719a37d85c79ed47fd15 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b6c305e0ee7d5976adb04374b3bf046c703b5c5a --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b494385b0e9de92ef0f171bfb3d2fefa7b6c43c8e0d5602d634fd635a4d53167 +size 51395351 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2d31dac2e1362fa06e575f4adf6d9d7c643e2195 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3553ed42c7dc6acd84772805ed0c5317fff123d4a7308c2d6dd30190186da202 +size 51395554 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..81d63103de30cbe36b6515e6590217a3acb35de0 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:196f3f29834020c6e83a31955c8efe0bfc6422e3a39f1e433b06f58c1e7c4ac4 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dce818814d74892dac78546cb8d806d2a6fb36df --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:299328b0d1a6a0ae06a822c82b4c7b1ab08105648eaae42d3e3bb12b68cbee97 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..235b11345c1b4669a0835513baf1099e8a1629cf --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeca0021ff953ddad2313f288344001b415ea11a7c83465fc3e912cc84364825 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1b5822d6dbd44a74e18d0dd000eddfbf01d0c532 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc26c6b0d89d06f235b6288d02ea11a6dc562c46b84b01729ba0d73dd2ecf963 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0e0d383c3f4f4b78c94249c7f6089ce57fd9efe9 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b24c1b3b6feb3b8faaec2d6c27b22b0a7bd4702ee7fc1da03c2a985fc60bb5a +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2face6e2e816b01ed989875de9e4e73d52f2ed1c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2f76208b33f632affac98fdfa362c937cf72e6dcd0bb65220f27abb334c7a2b +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f7698a758b53e1128352709e8ae1c9c4b86b7c73 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2508af97c51dc9e2dbe5c21491eea6f4589c7007c9c36e101c94d24507b6a307 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..078bee1b0b97149b82f850095133a4fd03bc517d --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0d47e0c89e7b7904737b334166e183f1e70e32dec2ab563d2d754ed8e0524a7 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..de7bc1a6417a0df199f188f343e27bae82e514c9 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cd4880bdacc3c854ba4e191aa0a79001c79bf91eed1125edf70043f0948ea19 +size 51395554 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..11f31eb962221190e8a8ef3425b333d41b921ebc --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6db14acc6ede2fb7e43fb4eeabbaa1d71b4e4d44acf63068004e0478342f717b +size 51395415 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..77f47f3ae597d26392d686a6bdbd368cc5a5b989 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a231ed0993aa27f91da303620d3491579b2f3479752d29afbab86803bcc8d8f +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0f98e98aa8946de27cabcde2eeb117f4c74bb36f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b52bdf9af49df528a77753a9498a0ac8ba9faa77cf215e3ac60575c1b6ad789 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..462bee24c9fb2cbe3deda96170fe2bf15cffb258 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77f1ab0ae43f0827e57c637a4c87f87970752b8bf36a060dd0f639715a566e0e +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9e70db4ebc0c03e2e9f421a5a7e000c9e8620b0f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0e55cd8a028c609ad7c75dbc7ce70e83b0ad4d78f2fe50d51dd43f965afda0c +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f3c33a0742e07edaced53d33d986c6b34fd7c693 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0dcdca634e90accea41e3fd458c998dfd246a2d755f8a22050861f627fa6dfb +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f180dc4e36e7d5c39043ae56600a82b3ff0aec81 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b9a9232c5eeafa1353e00c5088dc041979bc7fd417d641f839b7acc8f460bfb +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3d5b181257314ec12e7ed55a58816d9c8112568d --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9e14f411c0f93881510770a205738c6c93eeece2c19899ef5c2ff5bbbb9bb5d +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d04e057d192e92cf2fa068f7a1bfeaefc8342417 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7068c328a81c095e0dadb199197f9fc3b46ae1aebf7227e4f935220b07a32d8e +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3ac34a0e30a654e1ae0eb07005056a77d7645e82 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:486ac8b8d167220c15b3fdac3826ae2d727fc6a93327a1b903ef58fcb5f7880f +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4c7526c434fce5c42eb3393490e36ad49beb6292 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dfe3f8b587d181a014edb18083e70151cf09aeed31e31f5f477191a6b29914b +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9b3907661ca19191d2f3c3e5ab2a1fe2f992506c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11390047d00fb574d359dd3b469114be666dd34eb8416fd02fd4b6601668ebac +size 51395415 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..afb383b34a1607b25910bcca75d92e229b25f24f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc2250e4ae99cd5a15ad25d7b18f7f76f11d2f46808ed9d7e04a30c7020dabe6 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3e882eeb9ee076565a399841b7e0c944bd74dc36 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed90c684c4ec4952840cf7d1c0a2b1dabeb629572e4a71a76f478e4f8ccdbe8a +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2b334be8f9f8cc58bbee6cb9ce71f0144cd476ec --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfa402be225b8d04f5d782fee37d31652bf967d5d112e9885de4d793f76dd24f +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..73c73226f10f03d838b187cc433d348f1625ac4a --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce21846a790d3f12a0e058afd940c149e2e0d7eb0f8e6a1e4a5dc7a8e3ce08b8 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5c9a013139914e4fb9c9bae4e3ee47d1fc779436 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37c4772c53a023a26e0e251e9ac91b5815646779ae2fd3f8b0131c71e09ce302 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a611f11a36cba1adea3bb519785f2e62204ce8e0 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3f30042d20e55b263587f3193d58fab5bbd24b313931642a5752f5765e93d68 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a911c66fef43d5636064d850114fbff9355de8eb --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bab30c7d0cb5f2a627febd69bd40db4b15c051345e9c58680037ad174706a6d2 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..29bf4fe1c05f1b478d8de5aadcb5edcad8bbb4bb --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b33348ca5a2c0dc93f49134f3a8942fdea8aea95c5b6561245fdadf295d92ff9 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7cac1b6c179c48ff42db9ac6f9b6731b7b84f205 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a520fce6086adeab24cde6b2b65700fbd73f6e6850eed53d3764b52c24566676 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4046ea68548e9ecf3fdd38bff43dae914a7889bc --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9930385f73b21f6dd3512497ee2349dd4c075c4c47b892e1dc78052a821df020 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..edc572b73c14f3ac6d0546c0d2b4a709d87b0cdb --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bf75627a11c2fe137e7a4d42d13a8afffc3f37c3b5fcc3cf2becb0986e16e12 +size 51395415 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0c384ef5c76e463fa3db10d8cbec11651bb26eb3 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73bdead254546f47d2ba901f85548af6259ba8101fdfac2dd27fe85a47079773 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8f86cbaf40b7841aac8ea56961cea1712691d474 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1e4cfd640c87d36f5e1905600e84ef633e5be5c89a12be2589e9a99770ab3ad +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c7f0d75ed142712773694e25db2c913f916c2e07 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51422b4f7afe09febea97dad1a122d46d339ed61ee4e74a50d4445f69848c1de +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4fe11616cddd9d31ea48fa6f5be45d7d640c8bd4 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e40f12f51b806ebcab6d1393ae64c0b32541519de32b962a6f9ffbcd64a47c78 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..42805afce23da8491ebbbea5965f9e683b7b8c7a --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f14fb0980b98f32fa0bc18857f2ee3fd972c888a629b167a2f7487d0c9f5d6d2 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..56474dcd8fca9f83c786e1fd7d69af9f9d46d836 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12a272bd9b9ff1e99f6ce59cd34c3a8fa685e90c21b484892d2dd6863763ad72 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8af5fc86aa26298ec97a1c333e21f265be7fa0b4 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c080435fa228df882fe2fb363fd0772d47ca219a620a45dbf0d5fe7c3f94fef3 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fa1ec5d608bb22378d99dc24d01a3baebc70386a --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af08cb33e3f420a0e103ff1a9497267ba0891b86becd72c8b7f9a6e072b0ffde +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b41ad0abb5efd080c51cc3bca943dcd69db34391 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bf653dc8d8bd0b4ba9c0ffd6e8a07e4e3d3bec77db5c004156cdf7a06349a22 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ace5aed8f15742c6c0c149a650816d6ebb451173 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6129b36e01dcd9d0400331e2fc12ecb4a67675b3d2a8875f3e5b675b7a7c13ee +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..78a5e4a847773e0017b94568fab58b22fa500601 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:316d645d86277a46bc543357b3884af265d817a3bc0395a5187f84d69c0f014b +size 51395479 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..43732bdee1ac903858cc84039f004e8b8a9e6643 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:511d206fab69a2bad4740e62eae71c5844b77593bd753f68114a5940b8968616 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..621d88dd4ed9994a67c5997063d07d37b09b225f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8b94acff9f8ab781c2948b1d49f74d82b42d4ae8ec9d338b327f9f752a83a5a +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c3dd67ff66d3c267cf873c355f22f37ae581c2bd --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd1ac4bae9fc5cb4a47b464323b623cab39ba74280a15451bbb566ee260f5d40 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c58e5128b48d164725c382d338f31e6af2c958c5 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:381d73878fc77ef84e6c0c568039615a9bf7bf7c95aba2eb8a5990f0b6a6318a +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b0373d3f67f6c516b2883e2bbcba2847977752f0 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9de381c5d16a9ab081d2610cf7ab4fcebd27107a39782f04809f7e2b7f5c2cc8 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c870b5e8c908e5e7448aadebc50dcdee1b3706af --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49f53e5192a45fe8966f3516a6fe522c98ba399aecf6d717fc2227741540aac7 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8157adfea1092eb2545b7662b8af67468d50e3bc --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9bf70de673b5470eefaf761e906e34748411112f48cfd80e3936494e9efca9c +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bf955d44250a377c8a3258c17af576aafaf13ed8 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bca4ad936228c9cc00f39cfa16ee764799d0e93ac4db9f92883c9cac4bc5f36b +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bef51ef8af1dee9a6c43cc630f4d48dad613c5a0 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf6d0012282f85cc462bced26c0fd815c273fd7b613142add455d9b1b52e5104 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..73ee7885c5d723b9642bc34bee85429b11795760 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:901f6dfe0bbf200a310fc3ac1254f5dbb6923ee91617064d80c0a6c73f78c84e +size 51395554 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8167bdb6a9224012ff921907c4c822e9c487bd97 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e98af083017e06602c1f5d7729cd9d1bca0b7c387dc84dce3f434a73adcd87a4 +size 51395351 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b29b9741823e289fafaded6970aa08a51fa26bae --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29b52ea84d2aa18ce0731f88d50b726f215e92d207e2cfb4a27b7548328c8f12 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ce1cffa8b86a67eb7caaa50473279706ebe2c8d5 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f09084f8957e22dc5475f278fd617edf88974346ea1996301f61dfcc1ac4fb80 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d7443faca7aab4f1172760ec2b9abda3e1301703 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9402571eb0565991df3f0adc3e32caf9091634f9f727db76639c5c63f3fc291b +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..395e87a3cafafed2bda9c9ccdc3ecff89e71c838 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be8fa3c429dfc23bd125360ea918da656a6cf32315bc1c90b439fa142dd0e5a4 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b690d2eb24db8682d2194e244f88b4bd61277c0b --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c08eca48990e5b7d212c9030a5db421f9a784391cc8df3ac21d559e5d0503432 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3fd130719c6376d398147fa5c18db044753b12ca --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc9def568d75eea27ca4d60ef45c6042582c254c498cf8f28e8d9d085e1b285c +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4aaf0b8d82e6754b2fb20d63ba3f5489b4d7b763 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd02e14a27713c64f43fd95a7e8dc223789e6d51e9989af8f6b0dc545df2ba7a +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8533b80ac556834b9ef95d38ccf4c525672a25fc --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4302fe19afb65578102035638fd6f75f77caac798146c7dde6177b03eddd6d7e +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6917a68766529f0fbb75e3f254c0083c29ba4aa2 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05c637ecbc7385337358d30bbf0fa4d298a67885b5ae3e384dec201e9a97c7a1 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ef3adadcd37fead136d99b44f309915a313a6879 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b37809a3909df18fc3d9fcc679b721b4094d0bc2c3b6eac628f8fd05273b8a3 +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6d9ad7bd022af5cd4b8296beee520a2565dcaaff --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b7bd42da13be02cd7fd05950b453d9bf2b79c2071da2f9b660b4167c1fcc2e9 +size 51395351 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6bae611979edc67829f920bfa8fd26ea2fd7fd7d --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:188545befd16a257062d85881a52644d42f3c341230944ea2ee7309190cb8780 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f0d2c95f8adac8a78da2b395ea569adfed57bf9c --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de371fb14da644d98c5df09d5d112c7b8de04c5d2c8ac444337cd492c6307172 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6b4a2f0843741aa2fc88eb272b51a7993e364fd0 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c190bad1735f3a4393ec41bb60606a4fad39a8abf5d63ed688533b9c0571f62a +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..acd2d3b460b635679146936efd8f5213fdd5f163 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8869a5774d70711c2f281540c35b215ddd3bfa27a2371f802c0dd926d9c19a81 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3c58729dad1bba8cc91e8666b24a71c2d70f350a --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ef05b0d5a0995b2b6f1021ebda78fc74adf41b47a1a67c9639bb961fca8eb7a +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bae284bbc1edfdb8c7f36f05fa899ea03ffc988e --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8af47069a188fa78be6909fc31f4848ba253c2bf52f9cbea1958dcea0da12cb4 +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6cfab0b2f408af587bc177d8539969650ac5da84 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:953e34b52f5d45f61fa4b5fa596fea69778b1ac3a466d6e5996fab59bcf27fe0 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4c6f348a0b7451cb631376f02e880026d29a5b7f --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59ed5dbdb1cf740ec208d1915f7b6aed2b918ce9b761cd9bd136631a4bdb5ecc +size 51395490 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..832e42f73ffaa90dd3df2568fb0c67b6475841b3 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:965f51fd9e89e5bdcb24dc9b99d4644f51e8a7f5366674f55260c12e97fdfd6b +size 51395362 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a7ff17f54629a05f9a26c11dc07cb9e0e74a4a84 --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caff833a140a56fc63e52ea23b4608075ee530fe165c076f047e391bd1ae08d4 +size 51395426 diff --git a/1b121b21b/global_step39672/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt b/1b121b21b/global_step39672/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..aad84c5793728e4a0f2b2eb7611f6b537431abda --- /dev/null +++ b/1b121b21b/global_step39672/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbb292e9a35f4a498b236324ea76484b0ed5d5db5c1371c034c8547ca3b52af3 +size 51395479 diff --git a/1b121b21b/global_step39672/layer_01-model_00-model_states.pt b/1b121b21b/global_step39672/layer_01-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b126c61008fe1570fe631be77b66dfa3e2fd69f7 --- /dev/null +++ b/1b121b21b/global_step39672/layer_01-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37fddc05b616958a46538b02742134405aeb8cf09a16c0123472a9e50ce67f6c +size 187630851 diff --git a/1b121b21b/global_step39672/layer_03-model_00-model_states.pt b/1b121b21b/global_step39672/layer_03-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6df66ed25343195465536bf9e5120eb98abf6267 --- /dev/null +++ b/1b121b21b/global_step39672/layer_03-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8d0f8c908d7aeb4a7871457a3a2a5c6fbe5e9e5de8488a673cc97c5b59ecaac +size 77121283 diff --git a/1b121b21b/global_step39672/layer_04-model_00-model_states.pt b/1b121b21b/global_step39672/layer_04-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f50d375998c446cd26a82590d7c4ae7919dc9e85 --- /dev/null +++ b/1b121b21b/global_step39672/layer_04-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c446df4e803e6fbbe7a08a3b1215add3d55241def4546a92ad01a4a5394382ae +size 77121283 diff --git a/1b121b21b/global_step39672/layer_05-model_00-model_states.pt b/1b121b21b/global_step39672/layer_05-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..403c519415134759b7dc3f20ddbb60eec316939e --- /dev/null +++ b/1b121b21b/global_step39672/layer_05-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3d10b0ead147435283811df139f0359fd75740349b3874155601d2185fb29d7 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_06-model_00-model_states.pt b/1b121b21b/global_step39672/layer_06-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..07d35eef57f08ca30e39ecbc921265241b83e715 --- /dev/null +++ b/1b121b21b/global_step39672/layer_06-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edbe46cdaa2249c92207a1f5c06aaa19e14cf8ecf4e9999168cb3fbb69b42ffb +size 77121283 diff --git a/1b121b21b/global_step39672/layer_07-model_00-model_states.pt b/1b121b21b/global_step39672/layer_07-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..460b4ede006bb3fa600b319caf75204b718ef06b --- /dev/null +++ b/1b121b21b/global_step39672/layer_07-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c101aaf8fa4707ec156423a34d5e306c08647bbb66ae67afc1c8b043e201ac83 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_08-model_00-model_states.pt b/1b121b21b/global_step39672/layer_08-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5ebf0d6ba821a1a2869900b1e1178e9255b055d9 --- /dev/null +++ b/1b121b21b/global_step39672/layer_08-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b060b4cbb5161d30a1c625f712dab3151cabbef6771b06d38d510f667277f909 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_09-model_00-model_states.pt b/1b121b21b/global_step39672/layer_09-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..397f28ea02b07d40e4d6f476b2276a2ab3885b20 --- /dev/null +++ b/1b121b21b/global_step39672/layer_09-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c42c1abb235ca2b31c2ab480c9dc1e32f9e5d374a40b3e4edd3cb06a8ea0b602 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_10-model_00-model_states.pt b/1b121b21b/global_step39672/layer_10-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0e8e76992d5b0542f103dbb3fd9125b6fd243959 --- /dev/null +++ b/1b121b21b/global_step39672/layer_10-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60caf623eda027202d52192bd53f5e93650e1220e2515454f192e9f8fbd1c369 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_11-model_00-model_states.pt b/1b121b21b/global_step39672/layer_11-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9b10be976fb7e00a98a807922fbb5e4ac675cc8a --- /dev/null +++ b/1b121b21b/global_step39672/layer_11-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:444e8cdb65aa5035cb35fec2afe38c5a200c64743a2bce8fa8f29242c44f0c85 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_12-model_00-model_states.pt b/1b121b21b/global_step39672/layer_12-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5970b5cd01678a16c8f5f301427500d1aa5f96d2 --- /dev/null +++ b/1b121b21b/global_step39672/layer_12-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0277d6cf78901e7f6d52ff600cd712e46854288fcb12c7ae491d8f6954533a31 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_13-model_00-model_states.pt b/1b121b21b/global_step39672/layer_13-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e0c67952af453fc900ade9e99203244d1578033e --- /dev/null +++ b/1b121b21b/global_step39672/layer_13-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef8a941e2e05c577605daf0f1e575855dc1df6941f2776ab70caa99567acbb80 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_14-model_00-model_states.pt b/1b121b21b/global_step39672/layer_14-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b0cebbf575f02a9c5b28628294c11978244eeed0 --- /dev/null +++ b/1b121b21b/global_step39672/layer_14-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28e3f5974b56cc7abd55e62ca52c131130d0edf57548dd6804b85d6b0f41471d +size 77121283 diff --git a/1b121b21b/global_step39672/layer_15-model_00-model_states.pt b/1b121b21b/global_step39672/layer_15-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6981038694a10383743a68c906a18d42744a879a --- /dev/null +++ b/1b121b21b/global_step39672/layer_15-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c82654db1d91bd0710e3f6b93b6f83181d68a78b997d39b12b979da81047adc9 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_16-model_00-model_states.pt b/1b121b21b/global_step39672/layer_16-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..aad6b22b8d2ac892760da913cc764e988c07e51b --- /dev/null +++ b/1b121b21b/global_step39672/layer_16-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e88b19e93f0a8bac35cfefb764056786f1ac20d22c5ece8e597f416af3202f6 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_17-model_00-model_states.pt b/1b121b21b/global_step39672/layer_17-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3a067f6f45f13bffe2ea239f8547eab4fd4aa583 --- /dev/null +++ b/1b121b21b/global_step39672/layer_17-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3152d1e9cb5297d443e8c03d15956c8295a248193badff5d385f24290a95a5c1 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_18-model_00-model_states.pt b/1b121b21b/global_step39672/layer_18-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..84b5847fdafb1d2e1010585af312b1cf31dd4bad --- /dev/null +++ b/1b121b21b/global_step39672/layer_18-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5db6e93b1686bfe101ba9082106a924293ad26cf5cc8f37383bea6c1a87e0bce +size 77121283 diff --git a/1b121b21b/global_step39672/layer_19-model_00-model_states.pt b/1b121b21b/global_step39672/layer_19-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2765c53513cd90ef4f61fb1886a5abf3f13ecb81 --- /dev/null +++ b/1b121b21b/global_step39672/layer_19-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a70eed6029477dee7fa41587868bc00082b1c42409bb4e7ca72577a60bff7b7 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_20-model_00-model_states.pt b/1b121b21b/global_step39672/layer_20-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cfa1958c47f37060ceeb12b3f04156199df7dd4d --- /dev/null +++ b/1b121b21b/global_step39672/layer_20-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdc28642551d6a025c31e7a89f76b284f315bcc4e71bdb26a89e03630a64bd82 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_21-model_00-model_states.pt b/1b121b21b/global_step39672/layer_21-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..83387838ad393358a280a75410886874f709dfc1 --- /dev/null +++ b/1b121b21b/global_step39672/layer_21-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10ac35b16334537e59f52f3dd706f963e6505762b6719c55915efafe58a899ee +size 77121283 diff --git a/1b121b21b/global_step39672/layer_22-model_00-model_states.pt b/1b121b21b/global_step39672/layer_22-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..57f1bb0be64c71946e616fcf5931e2285be0719f --- /dev/null +++ b/1b121b21b/global_step39672/layer_22-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4edaa584e6e4994d8d2a3715c8dfebfcfdc7fcc25867d62539494d07b51a8e0a +size 77121283 diff --git a/1b121b21b/global_step39672/layer_23-model_00-model_states.pt b/1b121b21b/global_step39672/layer_23-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6e85dd9f11757a59bd875eab4ec2f3cedbd06369 --- /dev/null +++ b/1b121b21b/global_step39672/layer_23-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c35961f025123a95e5b3ede7d4459b2beb3ceaa572b7c5b296e683d02e1d6dc +size 77121283 diff --git a/1b121b21b/global_step39672/layer_24-model_00-model_states.pt b/1b121b21b/global_step39672/layer_24-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1173cfc0ebe065b2b8330c4e431c0e7091be4e8e --- /dev/null +++ b/1b121b21b/global_step39672/layer_24-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc209bb5357a638d411105174cbeeda63523e33c26e6641c2d5dd73dc31268ac +size 77121283 diff --git a/1b121b21b/global_step39672/layer_25-model_00-model_states.pt b/1b121b21b/global_step39672/layer_25-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e22f343d25a18fe3c5e275f1c3a13329ed631a95 --- /dev/null +++ b/1b121b21b/global_step39672/layer_25-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23665cb68694a32ae9bfda6f0fdfc049d4ad6df9a80fc0c0f66d6065c4f54c6f +size 77121283 diff --git a/1b121b21b/global_step39672/layer_26-model_00-model_states.pt b/1b121b21b/global_step39672/layer_26-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4dd8b33a99708dec35b8e79f38b6996b997b6266 --- /dev/null +++ b/1b121b21b/global_step39672/layer_26-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41cb43d62bc7497a60e13383211c3fd209d933c265e795879561c430c9b93463 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_27-model_00-model_states.pt b/1b121b21b/global_step39672/layer_27-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e46271aa8c18be23e677c0cbe3f253bb4ae99dad --- /dev/null +++ b/1b121b21b/global_step39672/layer_27-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5939c49674ccf86fb23b9e66eb56eda50bbe6b640c0fcce81cbe069d26016a25 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_28-model_00-model_states.pt b/1b121b21b/global_step39672/layer_28-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f023267a424be6fa201abc842c953712ca5e9c91 --- /dev/null +++ b/1b121b21b/global_step39672/layer_28-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4efc192940360b58b43ac2a0257a53e9ae303c4dd94b72ee2641e7314920c264 +size 77121283 diff --git a/1b121b21b/global_step39672/layer_30-model_00-model_states.pt b/1b121b21b/global_step39672/layer_30-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..70b6ac626ab3f53564b9f77c56a1cf48e7ff9204 --- /dev/null +++ b/1b121b21b/global_step39672/layer_30-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fb26d5807b3b46e5b6b60f2b5251322c66cb6d19a8ffffd82dde390c584554d +size 8387 diff --git a/1b121b21b/global_step39672/mp_rank_00_model_states.pt b/1b121b21b/global_step39672/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2d3d06f2e9c816361c1a8b6be31661303a4e27af --- /dev/null +++ b/1b121b21b/global_step39672/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:365394180e9b501578b9fbd3a3452a24407c14a8cbd1cffb710463091b1d71fa +size 43571 diff --git a/1b121b21b/launch.sh b/1b121b21b/launch.sh new file mode 100755 index 0000000000000000000000000000000000000000..6c3445845a5dae614feb4b8a1206322cd7bd9050 --- /dev/null +++ b/1b121b21b/launch.sh @@ -0,0 +1,53 @@ +#!/bin/bash + +# Launch script using torch.distributed.run(). Used by slurm +# scripts, don't invoke directly. + +# Samuel's fix for apparent error in SLURM initialization +if [ $SLURM_LOCALID -eq 0 ]; then + rm -rf /dev/shm/* + rocm-smi || true +else + sleep 2 +fi + +export NCCL_SOCKET_IFNAME=hsn0,hsn1,hsn2,hsn3 +export OMP_NUM_THREADS=$SLURM_CPUS_PER_TASK +export FI_CXI_DEFAULT_CQ_SIZE=131072 + +# debugging (noisy) +#export NCCL_DEBUG=INFO +#export RCCL_KERNEL_COLL_TRACE_ENABLE=1 +#export NCCL_DEBUG_SUBSYS=INIT,COLL + +module --quiet purge +module load cray-python + +module load CrayEnv +module load PrgEnv-cray/8.3.3 +module load craype-accel-amd-gfx90a +module load cray-python + +module use /pfs/lustrep2/projappl/project_462000125/samantao-public/mymodules +module load suse-repo-deps/sam-default +module load rocm/sam-5.2.3.lua +module load rccl/sam-develop.lua +module load aws-ofi-rccl/sam-default.lua + +source venv/bin/activate + +MASTER_NODE=$(scontrol show hostnames "$SLURM_JOB_NODELIST" | head -n 1) +MASTER_PORT=9999 + +echo "Launching on $SLURMD_NODENAME ($SLURM_PROCID/$SLURM_JOB_NUM_NODES)," \ + "master $MASTER_NODE port $MASTER_PORT," \ + "GPUs $SLURM_GPUS_ON_NODE," \ + "CUDA: $(python -c 'import torch; print(torch.cuda.is_available())')" + +python -u -m torch.distributed.run \ + --nnodes $SLURM_JOB_NUM_NODES \ + --nproc_per_node $SLURM_GPUS_ON_NODE \ + --node_rank=$SLURM_PROCID \ + --master_addr $MASTER_NODE \ + --master_port $MASTER_PORT \ + "$@" diff --git a/1b121b21b/sbatch_1b121b_oscar.sh b/1b121b21b/sbatch_1b121b_oscar.sh new file mode 100644 index 0000000000000000000000000000000000000000..f352b021899fd79dd493089a1eeb9bdaf33de584 --- /dev/null +++ b/1b121b21b/sbatch_1b121b_oscar.sh @@ -0,0 +1,159 @@ +#!/bin/bash +#SBATCH --exclude=nid007571,nid007112,nid006774,nid007502,nid007506,nid007507,nid005145,nid006692,nid007218,nid007123,nid006124,nid006123,nid007496,nid007237,nid006852,nid007206,nid006947,nid007212,nid006977,nid007222,nid005444,nid007219,nid007493,nid007221,nid005300,nid005619,nid006118,nid005203,nid006113,nid006481,nid007077,nid005208,nid005207,nid005879,nid005901 +#SBATCH --nodes=32 +#SBATCH --ntasks-per-node=1 +#SBATCH --cpus-per-task=32 +#SBATCH --mem=256G +#SBATCH -p pilot +#SBATCH -t 48:00:00 +#SBATCH --gpus-per-node=mi250:8 +#SBATCH --exclusive=user +#SBATCH --hint=nomultithread +#SBATCH --account=project_462000119 +#SBATCH -o logs/%j.out +#SBATCH -e logs/%j.err + +VARIANT=1b121boscar + +# if run without sbatch, invoke here +if [ -z $SLURM_JOB_ID ]; then + mkdir -p logs + sbatch "$0" + exit +fi + +set -euo pipefail + +# symlink logs/latest.out and logs/latest.err +ln -f -s $SLURM_JOB_ID.out logs/latest.out +ln -f -s $SLURM_JOB_ID.err logs/latest.err + +KILL_SWITCH_PATH=kill-switch-$VARIANT +CHECKPOINT_PATH=checkpoints_$VARIANT +TENSORBOARD_PATH=tensorboard_$VARIANT + +# Data +VOCAB_FILE="gpt2/vocab.json" +MERGE_FILE="gpt2/merges.txt" +DATA_PATH="/scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document" + +PP_SIZE=1 +TP_SIZE=1 + +MICRO_BATCH_SIZE=1 +GRADIENT_ACCUMULATION_STEPS=1 +WORLD_SIZE=$((SLURM_GPUS_ON_NODE*SLURM_JOB_NUM_NODES)) +GLOBAL_BATCH_SIZE=$((MICRO_BATCH_SIZE*WORLD_SIZE*GRADIENT_ACCUMULATION_STEPS)) + +# Model parameters +source model_params.sh +MODEL_PARAM=("${PARAM_1143M[@]}") +NHIDDEN=${MODEL_PARAM[0]} +FFN_HIDDEN_SIZE=${MODEL_PARAM[1]} +KV_SIZE=${MODEL_PARAM[2]} +NHEADS=${MODEL_PARAM[3]} +NLAYERS=${MODEL_PARAM[4]} +SEQ_LEN=2048 + +echo "Model parameters: d_model $NHIDDEN ffw_size $FFN_HIDDEN_SIZE kv_size $KV_SIZE n_heads $NHEADS n_layers $NLAYERS" + +SAVE_INTERVAL=10000 + +# Tokens: 20_800_000_000 +# -> Samples: 10156250 +TRAIN_SAMPLES=10_156_250 + +OPTIMIZER_ARGS=" \ + --optimizer adam \ + --adam-beta1 0.9 \ + --adam-beta2 0.999 \ + --adam-eps 1e-8 \ + --lr 2e-4 \ + --min-lr 2e-5 \ + --lr-decay-style cosine \ + --lr-decay-samples $TRAIN_SAMPLES \ + --lr-warmup-samples 101_563 \ + --clip-grad 1.0 \ + --weight-decay 1e-1 \ + " + +GPT_ARGS=" \ + --num-layers $NLAYERS \ + --hidden-size $NHIDDEN \ + --num-attention-heads $NHEADS \ + --kv-channels $KV_SIZE \ + --ffn-hidden-size $FFN_HIDDEN_SIZE \ + --seq-length $SEQ_LEN \ + --max-position-embeddings $SEQ_LEN \ + --micro-batch-size $MICRO_BATCH_SIZE \ + --global-batch-size $GLOBAL_BATCH_SIZE \ + --train-samples $TRAIN_SAMPLES \ + --vocab-file $VOCAB_FILE \ + --merge-file $MERGE_FILE \ + --clip-grad 1.0 \ + --kill-switch-path $KILL_SWITCH_PATH \ + --bf16 \ + $OPTIMIZER_ARGS \ + " + +OUTPUT_ARGS=" \ + --log-interval 10 \ + --save-interval $SAVE_INTERVAL \ + --eval-interval 1000 \ + --eval-iters 1 \ + --tensorboard-dir $TENSORBOARD_PATH \ + --tensorboard-queue-size 5 \ + --log-timers-to-tensorboard \ + --log-batch-size-to-tensorboard \ + --log-validation-ppl-to-tensorboard \ + " + +ZERO_STAGE=0 + +mkdir -p ds_configs +DS_CONFIG_PATH="ds_configs/$SLURM_JOB_ID.json" + +cat < $DS_CONFIG_PATH +{ + "train_micro_batch_size_per_gpu": $MICRO_BATCH_SIZE, + "train_batch_size": $GLOBAL_BATCH_SIZE, + "gradient_clipping": 1.0, + "zero_optimization": { + "stage": $ZERO_STAGE + }, + "bf16": { + "enabled": true + }, + "steps_per_print": 2000, + "wall_clock_breakdown": false +} +EOF + +DEEPSPEED_ARGS=" \ + --deepspeed \ + --deepspeed_config $DS_CONFIG_PATH \ + --zero-stage $ZERO_STAGE \ + " + +CMD=" \ + Megatron-DeepSpeed/pretrain_gpt.py \ + --tensor-model-parallel-size $TP_SIZE \ + --pipeline-model-parallel-size $PP_SIZE \ + $GPT_ARGS \ + $OUTPUT_ARGS \ + --save $CHECKPOINT_PATH \ + --load $CHECKPOINT_PATH \ + --data-path $DATA_PATH \ + --data-impl mmap \ + --split 949,50,1 \ + $DEEPSPEED_ARGS \ + " + +echo $CMD + +echo "START $SLURM_JOBID: $(date)" + +# bash launch_srun.sh $CMD +srun --label launch.sh $CMD + +echo "END $SLURM_JOBID: $(date)" diff --git a/1b121b21b/tensorboard/events.out.tfevents.1669792426.nid006851.49350.0 b/1b121b21b/tensorboard/events.out.tfevents.1669792426.nid006851.49350.0 new file mode 100644 index 0000000000000000000000000000000000000000..aa29f30f684d2e06fdca48b07b59b1fe2e1fa25a --- /dev/null +++ b/1b121b21b/tensorboard/events.out.tfevents.1669792426.nid006851.49350.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8da61f4a234a913780760bbacd35f3ca058d630e675a664d0f6f1c97fcb4cb49 +size 35670473 diff --git a/1b121b21b/tensorboard/events.out.tfevents.1669848605.nid007573.127375.0 b/1b121b21b/tensorboard/events.out.tfevents.1669848605.nid007573.127375.0 new file mode 100644 index 0000000000000000000000000000000000000000..8260e99fa1a43038831bafd72b454a02f2360f71 --- /dev/null +++ b/1b121b21b/tensorboard/events.out.tfevents.1669848605.nid007573.127375.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69caec90a2c275db842457d2ba37a40d3a5394a20a9cc5bb5a418c0579a986b3 +size 40 diff --git a/1b121b21b/tensorboard/events.out.tfevents.1669892297.nid007121.35949.0 b/1b121b21b/tensorboard/events.out.tfevents.1669892297.nid007121.35949.0 new file mode 100644 index 0000000000000000000000000000000000000000..01024a72ba4cef0c032ae30e95b0ad830428f6d2 --- /dev/null +++ b/1b121b21b/tensorboard/events.out.tfevents.1669892297.nid007121.35949.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbcdf6dbb87a2596ecd799aed1b9fde529d03182ce5cb22b64acf7ecc07db35c +size 40 diff --git a/1b121b21b/tensorboard/events.out.tfevents.1669909826.nid007411.67130.0 b/1b121b21b/tensorboard/events.out.tfevents.1669909826.nid007411.67130.0 new file mode 100644 index 0000000000000000000000000000000000000000..b1a1738988c6d920471b04c977666fdffebcc9ad --- /dev/null +++ b/1b121b21b/tensorboard/events.out.tfevents.1669909826.nid007411.67130.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a965fcb0c68540bae68451be8f85c797f4d8c7600ce1c3e80509e53e9259a2b +size 40 diff --git a/1b121b21b/tensorboard/events.out.tfevents.1669910581.nid007140.126284.0 b/1b121b21b/tensorboard/events.out.tfevents.1669910581.nid007140.126284.0 new file mode 100644 index 0000000000000000000000000000000000000000..460205c99256e4fb6879fc3b845b617dc7aa2e52 --- /dev/null +++ b/1b121b21b/tensorboard/events.out.tfevents.1669910581.nid007140.126284.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d409fb795cb407aff6b6fe16f5042f8fbad8684530d01ee0d9da005f77c53beb +size 40 diff --git a/1b121b21b/tensorboard/events.out.tfevents.1669911471.nid007140.18826.0 b/1b121b21b/tensorboard/events.out.tfevents.1669911471.nid007140.18826.0 new file mode 100644 index 0000000000000000000000000000000000000000..fe6c7da2c186c9dab757b055d8f3fa19b03384bc --- /dev/null +++ b/1b121b21b/tensorboard/events.out.tfevents.1669911471.nid007140.18826.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a4ee7e72ffb0bd2b82853dc65372f88bd737c78c1bdc98dd6743b76718f75ed +size 53142281 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..25d7e7135a755770ff7b72edafafbc868985a360 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0318c74805a49a59c6036f5edb38edeb05a31802fd7c12face7535818fb1f84a +size 41353495 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d073334e34b70100fa70901522703eb9f7dae366 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a486c5ed5e6c4397f8e5749617be7c7b8c42f937c69d42a2693a4b763760fc80 +size 41353570 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bdd0a6f762cd52c895d6f0446229ce3781f0bef2 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d31b03fb1658c253d7afb9b0be7c8270377c202b3b8071a2b8e276d9e5cc7cf +size 41353570 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1ec46af05a0de10a6765b2abbaf4dc681f327b0f --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c94386cbed8541665848665fb3031615c58992c222a2aa8b079fd8f5ec09a17d +size 41353570 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6aedaddc6db5c1a856e5ef67d2eb5aaae0d89888 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a468ac744cc53560e4988e5c1f4a90c212f8b6b7a1f7f9fdbaf743ab6ecc1c0 +size 41353506 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c5e935f70b9f43f209f01dbab506a2b311ca489a --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59208abca5354f86c3dafce9022d57dc4d47521e6a0bd084b6a3931e79fe7afd +size 41353506 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4ceebb6387188607245a86986144a0b05025b4d9 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcfd0f5ad11bf250117c6352754345f2f79b546163e440487efbf3c60f0be62d +size 41353506 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..36f904c777142392514fd2db561c6aaecb1b1648 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:504f1d1d8584da2b829aaa3f78474a64d9d8c16822951d28a749c78c424944ec +size 41353442 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7b21af5f7644321fe20a3f0241e41bb6f45c23ad --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fefafa2092910136511861a29bb2fe0e9dabfe0b3ce2d6949b4e70f4be68fb5 +size 41353570 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0316532745f275d02c4a5fad653be29773c899e6 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4abcdd3f4d8d26ad800d9e3f5695ce8d7781cf8d82b8e61659c29f759bfde3b4 +size 41353570 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e8e9296e59ee1e0597069464edda549dbb7d93cf --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4195ff2c451168f376acafd25b1a35d954b08a27bf330c3026e1e5ad57702e5 +size 41353570 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..34847b7283bf28285723325968e8258ad749a272 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca6c9dab7bc9edd985707427e9e674b42521c122fc6adb609cd80ed42e0f3fd6 +size 41353559 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..36a30bbec0e06a2cdb53b3656216f7332946b33d --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da0f559bc60e5aecdeb282a150327de181878ed2a439e7f28d4b4b21cd434ece +size 41353506 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..36f5b7cc458c042682527d740217de368d7ac9d9 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b63640b1d490c12f7b6b37f5cfbe154c77a5bb02a3a589aeef9d33ec2053e46a +size 41353506 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7f101d174c374296bd71c424588b6b4233392bd5 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d15068a8ea8f63f8e53e6e27e7983fb879a2e208ae4778f73ef59108c57276ce +size 41353634 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8ab056817ea4d67e2661086b2ed67a04b3ce0e8e --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1013ee2cc4a7ddd5e58ecc4b525c77460c019ff3b2511b0c4065009fbadfe330 +size 41353570 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..90c8348ae752b8c2d74317f99c656dc3b837dad3 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c309dec762a7f05fb02206cf369fe19591e475261c639d6d616c2a4a5e8487b +size 41353698 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fd7f0ba4ccd259a00c3076e0216c0c0302055366 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec56490dc698162c354e4627621d05f501636d13823722a292d8cc723a352057 +size 41353506 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1b67dfafd4c6b37ccc36ce607d257865f2c819de --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f80b9f65a0b0c5ad4a6f623b03602061bfd386dee554bb9be15aafa7afe67d71 +size 41353634 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3eb77460b402fcaad5d3d580ecfd4a3513cc8b13 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98c7fbcd9500a49f574b26ccb57444a81106baf87c5da99f37c7e0427b868ef4 +size 41353506 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cb884996c4dc02d91ff71b308d2b5a7d143ac550 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b76b6fd3157e352c272843459d048bd436a479abb3a8ac61d51d6b4a8fcfdf28 +size 41353570 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..39771db8425d2f657b5d615f956231480e15d234 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd67b81017b189925dc7440430171ed7a5c926baef04f5bb70807239c5b76df9 +size 41353634 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6b0c87cf5b4f710f0ff7de7ef67af017a8b593b9 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5410a431bad98b09732578631854ceeb536a1817c5ebb00cdf4c07746c723ebe +size 41353495 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..505b3eb9584aeb48bfa0c0f70e822ea359aa14ea --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9b37b1864ff1523b407e9c212c5244e4faa20a452899348d67b91bfac39886b +size 41353570 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0a00e41bfb75249dc269885ff746fd8065ad44a5 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2157842f6b57af10259025809ecdd563dbef30db652d27626a3d27a107897b8 +size 41353506 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e2a00836f9ce9f751f14b6c255813b687ba7b140 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b2b55154a4131117221add311572e8676d75c7f0117f4c82402161170074390 +size 41353506 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a96df6bac60715f59890fa57003434a0411dbe8d --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e40b3d8d0f2328d0342a1221baf39c2bf1d3546911f2231f4012418441e46a36 +size 41353698 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..20035333bb589dfa059a7b9b18bcd6f8633a4fad --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c603ad74e5dd777ece36e630ab857041509f2c3189e73b2e60df90447bb7a3ea +size 41353506 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8f8fc9f36e78d52953e3e701707b0816e90ffd9b --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01852eacca0cd1e1f391a8cd00ff0aa920341d66d9ca7b9b312f0f878e37637a +size 41353570 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f179106f3481184fbe81861dfeecedae51d7c3db --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eccd1475f62b0b75ec21f99f30373f556c37ec90c4dbb5b2eace58287431f487 +size 41353570 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e487d8c0691ba9437a56bc991207d0d31d9f36e8 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a54b7f66b7e678f22dda2225165413d98dbfb956e75dc2bcf108095e39973f24 +size 41353570 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..356591b85759a736c62ba25bbaf4b1cf2ea5b9a0 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cb43f2bfccf28cab43f1962c0fa7c75464bf53dd7b9fadbc1f75de429f1f9ef +size 41353698 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f506dee6efea4fdd4e32040ad27139a25c84070d --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:117c406956501cb21fbd8a82f1fa1471064b290ab75fa7db3286783883c33c16 +size 41353442 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6a13362b08cfaea91232816236575bc3191558a9 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c9e42ab8bd263765d4e5866d0f979186cd392bb8319f1e13d6663cea44ff85d +size 41353495 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ed165215fffab69acf0b96ae639f51fc96da2ebd --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e54f54170f5c0bab715985012802a5ba15f5cdf371f62efb017d97bf8b6f9a8 +size 41353634 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a561bdeb30fa7164953f383f6d9e9f7208af50d9 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf12d32fedfc654a5fdc23283a999e0835c7d28d88f1b75b885971d215f25f99 +size 41353506 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..77609e35f612075eddaf11fcb5b73b0fa11e9d89 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe66f6daec80528b0044d0f81dce116a0c9be63acabe6c1ee9fd313664d88256 +size 41353570 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..af2d25051bdd50b08263cc2fe7624f97ae2d6763 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a93630261062c6e3d5c92ef21e30b60b58f9d9da2458908d4d617879b4a1878f +size 41353698 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3b0445fdc8544805192a2aced67bbd71433d315a --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14ac8dac8d62f2e2d05b92ee5e0d2b10953bf6b858912472583928418125e656 +size 41353506 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..966b34119383bdfc842a0bae6e8b5d3f9740e8ac --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:924865af54284fe518232c78a4313412e5ca5d75b2a28c4d0dc6f7919ea293b9 +size 41353634 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..013abe4c3f536a5638af3d78d11b4064cce641f9 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96717e24fada5d3efcb46abcce1892e3aae3ea4e36fc7c1429b641fc7b82a136 +size 41353570 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0e6d86a2e1568eab43e3cf82441d2759a64ddd7e --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0c84dbba88f85a95a41cf0b5ba1a85b8a93723af94e8b660ce8c3c858052cda +size 41353634 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d8d5ab5b431f799815f9ada7391a255714eb892b --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f24798129e2537cd276b7550e77bbf677e0a0e9146e67f0ef27848ceca887d6f +size 41353378 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8c7c83495c26007b0a338b1166206922b416e533 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3d43c65f2b3c9817913a4def6ffba77003a3e9a144bb6af261152113ce53ba0 +size 41353634 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..382be4071b5ee658ed78d30ce1cbff5083ab80e7 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1000783fbb05b95f4427f7de0689737201b5e7de297829090d68c959aa0a2e85 +size 41353559 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..81f907b309f63c9d918ca46df169acd7bdaf5016 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8fd8e794bda4e1f1cc5beedf7205d51b6da16ed2c293fef170584419cc2694c +size 41353570 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..34fffe1470bc612e9e5bbf9cae3ffe4c200ef0a5 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bfdc57ab5791e7a71c8f42a04b98cacfdfc3ac1a02a64c3abf0fab5c1572663 +size 41353570 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bd3328208310aae846f19bd8bdd3905c51df2e73 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ff1750a0b5b101c12d1fe7f6b07d41293f6f873114130daffaecd7d4ae38fc5 +size 41353634 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3bbca039c88d248bd5e74b33a09275d55d0f78e2 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a53744531760be43cb946df825267873f13f6902dff02088cf633f34832a55a +size 41353442 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3ec87016e30aa57285d87af977974784b3a71d01 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbad513cd754dbfd2f5c51232c9f45ae135777274ba6d14911f8e61a9fb4a063 +size 41353634 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ec6e4322b0c24d4a378eeb4ae2d0b8b27e6744c4 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2077614a3681260b2653f81612c3e07211b414624ff49aef378e78e136b940a7 +size 41353378 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a65df17614b7b30a975ee8999b15301bd8cded79 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ba31dcdd12f2b1bb47e928b90e65d50bd2deed87341b6a26f04c5f019e55936 +size 41353634 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bdc42f393956c8e28f3f64f9f81c597f770e4f08 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3120ef5abaea8d44e3ca5a731894998a0a87a8ce52a1dd5848a58ccf053f9be +size 41353634 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4f864d4ec13a994b0963fe4dbe54b4ba2580597f --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f00c956ddc6225c5b858c499e9ef0e96b449ecf81e6c7732f39f5bb0ad19121c +size 41353634 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3e2d940cf1f4f171dd155378ec684219c8fc3ebf --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abccb2637f5241d8940fba33fc02775274bc91cda687a6d61b6a8ad152e1cab2 +size 41353570 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d014e9b5e4882dab8d65daa7a0db30a278481ba4 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93226981cf6f5e99e5df0a2389c8bcb3067fd5fb1ea74b067fe7d2d437e5cd2d +size 41353495 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..85735ec96e9b4c6bd9d2ed283bdeace8c999d2ea --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8d1eab1beaa60250767e0b387424ff43d8ced998b339eaf8f997a31ae61324a +size 41353570 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b82214bbb06ddc432f50a5ea0ab0dcc2a5fc2965 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab4774129a301610148493524c36f26f2f3b8e6b748b4c2d303eaee3e3968b6f +size 41353634 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5dc36c927f75057597ab6ddd38d06b2a04819322 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be7b9507e0d61f8abe349e625deaa03cdff4b237a4cea0d92c64ce9b2624e181 +size 41353570 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ae37cfb779b7156c19183c5c3341dc5af9b1676b --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2800b4befb1a13bb265c7176296a4893f069ce1beec510e2ff644ec0790799ce +size 41353506 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..60721a51a7706988fcc8e2aac10bae252489b3e0 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2f127604d2aed62456972ae9b109ab30d49d039746ca5b5eed648644b10cf1e +size 41353431 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..673e6a3010cdd216214917e52976855acd7ebdc6 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebafaeadc0d95a1bf7a2325c16acca400ded9f2418105cf6feafa3e0c35bdb67 +size 41353495 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b56e9e66b5334b918bc794c64c76dd5645ca984e --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:162f95b87efdd1748288caa097c01943f97c492655498d85547d80e57c05c10e +size 41353559 diff --git a/220m7b57b5/global_step14324/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt b/220m7b57b5/global_step14324/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5284aa3c6414fc3a65ce296abbffeb37df7b4737 --- /dev/null +++ b/220m7b57b5/global_step14324/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9440a8e3da7b3a64fa832dc5b77e5ec2559eff6036042c1742173fa537672eeb +size 41353495 diff --git a/220m7b57b5/global_step14324/layer_01-model_00-model_states.pt b/220m7b57b5/global_step14324/layer_01-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f070083b79125152b20f15854a39fe7df11d4aa9 --- /dev/null +++ b/220m7b57b5/global_step14324/layer_01-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53f7f4d77c1b0bfa4f71ed79afa0cbc1d1dbb69def1146cc27ae20f92c2ee21b +size 93816067 diff --git a/220m7b57b5/global_step14324/layer_03-model_00-model_states.pt b/220m7b57b5/global_step14324/layer_03-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..089409dacf476c46de7208cf2de4afda84b67259 --- /dev/null +++ b/220m7b57b5/global_step14324/layer_03-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c46adc04751f5e1bd679bdf5b6a062c436923c50da4eb25989eb0eacd03efae5 +size 19295235 diff --git a/220m7b57b5/global_step14324/layer_04-model_00-model_states.pt b/220m7b57b5/global_step14324/layer_04-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..492ce064aaaec3fa6080976dea7a5d161597cbd6 --- /dev/null +++ b/220m7b57b5/global_step14324/layer_04-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f135b9359069109126a5700a0fb062d7ae482ac3c34d9575394ee3d9b0ea0c8 +size 19295235 diff --git a/220m7b57b5/global_step14324/layer_05-model_00-model_states.pt b/220m7b57b5/global_step14324/layer_05-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e96d90e654e49162b54d3ebae6dd3cc9a2a79978 --- /dev/null +++ b/220m7b57b5/global_step14324/layer_05-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16d351f9284e4ec8c7169d5aebf69d262b19a335d98e63b76fc0ddb7e89aa45b +size 19295235 diff --git a/220m7b57b5/global_step14324/layer_06-model_00-model_states.pt b/220m7b57b5/global_step14324/layer_06-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4cdb805d91360c3c7ac78732bfcac793d0654067 --- /dev/null +++ b/220m7b57b5/global_step14324/layer_06-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31c497e03bfdf7b22c68386f5a55a36f99d0db892a56144f6fe9058c340a35a2 +size 19295235 diff --git a/220m7b57b5/global_step14324/layer_07-model_00-model_states.pt b/220m7b57b5/global_step14324/layer_07-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6f74a5b41223acf4a00e86f960f36625746031d6 --- /dev/null +++ b/220m7b57b5/global_step14324/layer_07-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9b9444736ba6c75189a57042059a057eeb3e583920c140729d499b5a01b344a +size 19295235 diff --git a/220m7b57b5/global_step14324/layer_08-model_00-model_states.pt b/220m7b57b5/global_step14324/layer_08-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f4991b6c723ae7129869e16e8317cbceb487f919 --- /dev/null +++ b/220m7b57b5/global_step14324/layer_08-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e99e17f5f28cef2c64b1d91c53e614d1ea38ac6695187b90b8c3d686ff09bb38 +size 19295235 diff --git a/220m7b57b5/global_step14324/layer_09-model_00-model_states.pt b/220m7b57b5/global_step14324/layer_09-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..57126a2c2da9c07adb36e00980cb2e0e685601c3 --- /dev/null +++ b/220m7b57b5/global_step14324/layer_09-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4377253649f53e88c47edf4c042dc1fa54820881777dcdefc543c1f94f69f816 +size 19295235 diff --git a/220m7b57b5/global_step14324/layer_10-model_00-model_states.pt b/220m7b57b5/global_step14324/layer_10-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c65b2c5ee8734f3e69455e5a7f8779961bc28bb7 --- /dev/null +++ b/220m7b57b5/global_step14324/layer_10-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b983c3f4cdec23f2ad6a9fb6e82f7b17fc45b03150a2a456224612610750042f +size 19295235 diff --git a/220m7b57b5/global_step14324/layer_11-model_00-model_states.pt b/220m7b57b5/global_step14324/layer_11-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7bc8776b0f6463cbdb05676637e5e2eae6c74f83 --- /dev/null +++ b/220m7b57b5/global_step14324/layer_11-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:967bef4438f51caf2d92bd72389f7f8ec41bd140135dba129db0367feb8e4417 +size 19295235 diff --git a/220m7b57b5/global_step14324/layer_12-model_00-model_states.pt b/220m7b57b5/global_step14324/layer_12-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f83e1b6cef27ddf8937e47db649d45106a91b073 --- /dev/null +++ b/220m7b57b5/global_step14324/layer_12-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0288c692ee814c74a6b1ca083b0103e37d4ce4efd16d853f266253714642823e +size 19295235 diff --git a/220m7b57b5/global_step14324/layer_13-model_00-model_states.pt b/220m7b57b5/global_step14324/layer_13-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6ed7378584a7a4b40381a5e899f0967b79fbd56c --- /dev/null +++ b/220m7b57b5/global_step14324/layer_13-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11389814bb7599d13e60b85eef30e4b1c4c594e607431a0e523fb18f6ff4659f +size 19295235 diff --git a/220m7b57b5/global_step14324/layer_14-model_00-model_states.pt b/220m7b57b5/global_step14324/layer_14-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..424edb71ec6adcd535ff0a27948f5a6ef11bccb0 --- /dev/null +++ b/220m7b57b5/global_step14324/layer_14-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80fd263606c0d0982e7d326ac5d4bb6461c803d78090ac7d2c48651975216977 +size 19295235 diff --git a/220m7b57b5/global_step14324/layer_15-model_00-model_states.pt b/220m7b57b5/global_step14324/layer_15-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..16c36aafcd89902ba584dac74068e50c55a19826 --- /dev/null +++ b/220m7b57b5/global_step14324/layer_15-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f57e30829a666035f261d54e60645f8955df5c3c5c29be8cb5f989f678c30ba3 +size 19295235 diff --git a/220m7b57b5/global_step14324/layer_16-model_00-model_states.pt b/220m7b57b5/global_step14324/layer_16-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..58655307c487bd9740fb84ca568899c97d28fdc0 --- /dev/null +++ b/220m7b57b5/global_step14324/layer_16-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2266747bd3205a56ffbcaf5e5aef334d8449be8412bcf5d9f9468d14fffe3492 +size 19295235 diff --git a/220m7b57b5/global_step14324/layer_17-model_00-model_states.pt b/220m7b57b5/global_step14324/layer_17-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..82b8f58a555cc3b993bef73c3df3ef7262d375ca --- /dev/null +++ b/220m7b57b5/global_step14324/layer_17-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a449bd2075163bbf135816bac265a43be92a9a454c624fcf32a50887a3dce7d +size 19295235 diff --git a/220m7b57b5/global_step14324/layer_18-model_00-model_states.pt b/220m7b57b5/global_step14324/layer_18-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4d1b4548ec1a8709a78a5929b1f9ecb55d33a302 --- /dev/null +++ b/220m7b57b5/global_step14324/layer_18-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35bb0acba1bde025e62f4ca950677e5c0d8a78a8bd4348a2a2964e8fa51edb38 +size 19295235 diff --git a/220m7b57b5/global_step14324/layer_19-model_00-model_states.pt b/220m7b57b5/global_step14324/layer_19-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e6426dc9447a4edfe8c883ef02703a644d64b20e --- /dev/null +++ b/220m7b57b5/global_step14324/layer_19-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3871492ae0d055e743e94c326850f1bb8ca193393902d59f2c9810d02982e08 +size 19295235 diff --git a/220m7b57b5/global_step14324/layer_20-model_00-model_states.pt b/220m7b57b5/global_step14324/layer_20-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cf13162716752dd3efd5b84489e3fd57aa7e8121 --- /dev/null +++ b/220m7b57b5/global_step14324/layer_20-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:465be928e8e1481744ca21b5a99b518a2f48ba0a68a0fc26a2f9bf0fad401dd9 +size 19295235 diff --git a/220m7b57b5/global_step14324/layer_22-model_00-model_states.pt b/220m7b57b5/global_step14324/layer_22-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ecd3d62d8ea6f2fed9942ad4d92f8832de9e2108 --- /dev/null +++ b/220m7b57b5/global_step14324/layer_22-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85c33d55355ced24d0b7dd9eeb0a84e9ceba68c1b2a3b89b23019ee14a94c17e +size 4803 diff --git a/220m7b57b5/global_step14324/mp_rank_00_model_states.pt b/220m7b57b5/global_step14324/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ecf9fc28c33e4f923c69e50c542595adff809671 --- /dev/null +++ b/220m7b57b5/global_step14324/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e6f921898334ef415655beaf7df50b708973fbf0c2afa4a8651b2fa92a6b606 +size 37427 diff --git a/220m7b57b5/launch.sh b/220m7b57b5/launch.sh new file mode 100755 index 0000000000000000000000000000000000000000..6c3445845a5dae614feb4b8a1206322cd7bd9050 --- /dev/null +++ b/220m7b57b5/launch.sh @@ -0,0 +1,53 @@ +#!/bin/bash + +# Launch script using torch.distributed.run(). Used by slurm +# scripts, don't invoke directly. + +# Samuel's fix for apparent error in SLURM initialization +if [ $SLURM_LOCALID -eq 0 ]; then + rm -rf /dev/shm/* + rocm-smi || true +else + sleep 2 +fi + +export NCCL_SOCKET_IFNAME=hsn0,hsn1,hsn2,hsn3 +export OMP_NUM_THREADS=$SLURM_CPUS_PER_TASK +export FI_CXI_DEFAULT_CQ_SIZE=131072 + +# debugging (noisy) +#export NCCL_DEBUG=INFO +#export RCCL_KERNEL_COLL_TRACE_ENABLE=1 +#export NCCL_DEBUG_SUBSYS=INIT,COLL + +module --quiet purge +module load cray-python + +module load CrayEnv +module load PrgEnv-cray/8.3.3 +module load craype-accel-amd-gfx90a +module load cray-python + +module use /pfs/lustrep2/projappl/project_462000125/samantao-public/mymodules +module load suse-repo-deps/sam-default +module load rocm/sam-5.2.3.lua +module load rccl/sam-develop.lua +module load aws-ofi-rccl/sam-default.lua + +source venv/bin/activate + +MASTER_NODE=$(scontrol show hostnames "$SLURM_JOB_NODELIST" | head -n 1) +MASTER_PORT=9999 + +echo "Launching on $SLURMD_NODENAME ($SLURM_PROCID/$SLURM_JOB_NUM_NODES)," \ + "master $MASTER_NODE port $MASTER_PORT," \ + "GPUs $SLURM_GPUS_ON_NODE," \ + "CUDA: $(python -c 'import torch; print(torch.cuda.is_available())')" + +python -u -m torch.distributed.run \ + --nnodes $SLURM_JOB_NUM_NODES \ + --nproc_per_node $SLURM_GPUS_ON_NODE \ + --node_rank=$SLURM_PROCID \ + --master_addr $MASTER_NODE \ + --master_port $MASTER_PORT \ + "$@" diff --git a/220m7b57b5/logs/2086980.err b/220m7b57b5/logs/2086980.err new file mode 100644 index 0000000000000000000000000000000000000000..58f22d913c34c3ef7c318c81229898ba76af6a3b --- /dev/null +++ b/220m7b57b5/logs/2086980.err @@ -0,0 +1,483 @@ +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module scaled_upper_triang_masked_softmax_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module scaled_upper_triang_masked_softmax_cuda... +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module scaled_masked_softmax_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module scaled_masked_softmax_cuda... +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module fused_mix_prec_layer_norm_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module fused_mix_prec_layer_norm_cuda... +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +1: Successfully preprocessed all matching files. +1: Successfully preprocessed all matching files. +1: Successfully preprocessed all matching files. +5: Successfully preprocessed all matching files. +4: Successfully preprocessed all matching files. +2: Successfully preprocessed all matching files. +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: +0: +0: +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: +3: +3: +3: +3: +3: +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: +6: +6: +6: +6: +6: +6: +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: +7: +7: +7: +7: +7: +7: +0: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja... +0: Building extension module utils... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +2: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +2: Loading extension module utils... +1: Loading extension module utils... +2: Loading extension module utils... +1: Loading extension module utils... +4: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +4: Loading extension module utils... +2: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +0: Loading extension module utils... +3: Loading extension module utils... +7: Loading extension module utils... +3: Loading extension module utils... +3: Loading extension module utils... +6: Loading extension module utils... +3: Loading extension module utils... +6: Loading extension module utils... +7: Loading extension module utils... +3: Loading extension module utils... +6: Loading extension module utils... +3: Loading extension module utils... +6: Loading extension module utils... +7: Loading extension module utils... +6: Loading extension module utils... +3: Loading extension module utils... +7: Loading extension module utils... +6: Loading extension module utils... +3: Loading extension module utils... +7: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: +0: +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: +5: +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: +7: +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: +0: Loading extension module utils...Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +0: +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: +0: Loading extension module utils... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +1: +1: Loading extension module utils...Loading extension module utils... +1: +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +4: +4: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +4: +4: +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +4: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: +2: Loading extension module utils... +2: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +3: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +5: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +5: +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +3: +3: +5: Loading extension module utils...Loading extension module utils... +5: +7: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +7: +7: +5: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils...Loading extension module utils... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: +7: Loading extension module utils... +3: Loading extension module utils...Loading extension module utils... +3: +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +6: +6: Loading extension module utils...Loading extension module utils... +6: +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/utils.py:349: UserWarning: Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings +0: warnings.warn("Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings") diff --git a/220m7b57b5/logs/2086980.out b/220m7b57b5/logs/2086980.out new file mode 100644 index 0000000000000000000000000000000000000000..5515af3c1b716d8c6f70e457f93a4a6f74c2de9a --- /dev/null +++ b/220m7b57b5/logs/2086980.out @@ -0,0 +1,6920 @@ +Model parameters: d_model 896 ffw_size 3584 kv_size 64 n_heads 14 n_layers 18 +Megatron-DeepSpeed/pretrain_gpt.py --tensor-model-parallel-size 1 --pipeline-model-parallel-size 1 --num-layers 18 --hidden-size 896 --num-attention-heads 14 --kv-channels 64 --ffn-hidden-size 3584 --seq-length 2048 --max-position-embeddings 2048 --micro-batch-size 4 --global-batch-size 256 --train-samples 3_666_992 --vocab-file gpt2/vocab.json --merge-file gpt2/merges.txt --clip-grad 1.0 --kill-switch-path kill-switch-220moscar --bf16 --optimizer adam --adam-beta1 0.9 --adam-beta2 0.999 --adam-eps 1e-8 --lr 2e-4 --min-lr 2e-5 --lr-decay-style cosine --lr-decay-samples 3_666_992 --lr-warmup-samples 36_670 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_220moscar --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_220moscar --load checkpoints_220moscar --data-path /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2086980.json --zero-stage 0 +START 2086980: Tue Nov 29 21:55:52 EET 2022 +0: +0: +0: ======================= ROCm System Management Interface ======================= +0: ================================= Concise Info ================================= +0: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +0: 0 44.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 2 41.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 3 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 4 40.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 6 38.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 7 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: ================================================================================ +0: ============================= End of ROCm SMI Log ============================== +3: +3: +3: ======================= ROCm System Management Interface ======================= +3: ================================= Concise Info ================================= +3: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +3: 0 46.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 2 45.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 4 46.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 6 37.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 7 36.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: ================================================================================ +3: ============================= End of ROCm SMI Log ============================== +6: +6: +6: ======================= ROCm System Management Interface ======================= +6: ================================= Concise Info ================================= +6: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +6: 0 46.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 2 43.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 4 43.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 6 39.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: ================================================================================ +6: ============================= End of ROCm SMI Log ============================== +4: +4: +4: ======================= ROCm System Management Interface ======================= +4: ================================= Concise Info ================================= +4: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +4: 0 50.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 2 43.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 3 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 4 48.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 6 44.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: ================================================================================ +4: ============================= End of ROCm SMI Log ============================== +1: +1: +1: ======================= ROCm System Management Interface ======================= +1: ================================= Concise Info ================================= +1: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +1: 0 46.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 2 41.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 4 48.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 6 38.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: ================================================================================ +1: ============================= End of ROCm SMI Log ============================== +5: +5: +5: ======================= ROCm System Management Interface ======================= +5: ================================= Concise Info ================================= +5: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +5: 0 48.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 2 45.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 4 45.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 6 43.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: ================================================================================ +5: ============================= End of ROCm SMI Log ============================== +7: +7: +7: ======================= ROCm System Management Interface ======================= +7: ================================= Concise Info ================================= +7: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +7: 0 47.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 2 43.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 4 39.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 6 43.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: ================================================================================ +7: ============================= End of ROCm SMI Log ============================== +2: +2: +2: ======================= ROCm System Management Interface ======================= +2: ================================= Concise Info ================================= +2: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +2: 0 42.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 2 46.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 4 43.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 6 43.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: ================================================================================ +2: ============================= End of ROCm SMI Log ============================== +7: Launching on nid006703 (7/8), master nid005552 port 9999, GPUs 8, CUDA: True +4: Launching on nid006700 (4/8), master nid005552 port 9999, GPUs 8, CUDA: True +1: Launching on nid005553 (1/8), master nid005552 port 9999, GPUs 8, CUDA: True +0: Launching on nid005552 (0/8), master nid005552 port 9999, GPUs 8, CUDA: True +5: Launching on nid006701 (5/8), master nid005552 port 9999, GPUs 8, CUDA: True +6: Launching on nid006702 (6/8), master nid005552 port 9999, GPUs 8, CUDA: True +2: Launching on nid005554 (2/8), master nid005552 port 9999, GPUs 8, CUDA: True +3: Launching on nid005555 (3/8), master nid005552 port 9999, GPUs 8, CUDA: True +0: using world size: 64, data-parallel-size: 64, tensor-model-parallel size: 1, pipeline-model-parallel size: 1 +0: accumulate and all-reduce gradients in fp32 for bfloat16 data type. +0: using torch.bfloat16 for parameters ... +0: ------------------------ arguments ------------------------ +0: abort_on_unmet_fused_kernel_constraints ......... False +0: accumulate_allreduce_grads_in_fp32 .............. True +0: adam_beta1 ...................................... 0.9 +0: adam_beta2 ...................................... 0.999 +0: adam_eps ........................................ 1e-08 +0: adlr_autoresume ................................. False +0: adlr_autoresume_interval ........................ 1000 +0: apply_query_key_layer_scaling ................... True +0: apply_residual_connection_post_layernorm ........ False +0: attention_dropout ............................... 0.1 +0: attention_softmax_in_fp32 ....................... False +0: bert_binary_head ................................ True +0: bert_load ....................................... None +0: bf16 ............................................ True +0: bias_dropout_fusion ............................. True +0: bias_gelu_fusion ................................ True +0: biencoder_projection_dim ........................ 0 +0: biencoder_shared_query_context_model ............ False +0: block_data_path ................................. None +0: checkpoint_activations .......................... False +0: checkpoint_in_cpu ............................... False +0: checkpoint_num_layers ........................... 1 +0: clip_grad ....................................... 1.0 +0: codecarbon_dir .................................. None +0: consumed_train_samples .......................... 0 +0: consumed_train_tokens ........................... 0 +0: consumed_valid_samples .......................... 0 +0: contigious_checkpointing ........................ False +0: cpu_optimizer ................................... False +0: cpu_torch_adam .................................. False +0: curriculum_learning ............................. False +0: data_impl ....................................... mmap +0: data_parallel_size .............................. 64 +0: data_path ....................................... ['/scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document'] +0: dataloader_type ................................. single +0: DDP_impl ........................................ local +0: decoder_seq_length .............................. None +0: deepscale ....................................... False +0: deepscale_config ................................ None +0: deepspeed ....................................... True +0: deepspeed_activation_checkpointing .............. False +0: deepspeed_config ................................ ds_configs/2086980.json +0: deepspeed_mpi ................................... False +0: distribute_checkpointed_activations ............. False +0: distributed_backend ............................. nccl +0: embed_layernorm ................................. False +0: embedding_path .................................. None +0: encoder_seq_length .............................. 2048 +0: eod_mask_loss ................................... False +0: eval_interval ................................... 1000 +0: eval_iters ...................................... 1 +0: eval_only ....................................... None +0: evidence_data_path .............................. None +0: exit_duration_in_mins ........................... None +0: exit_interval ................................... None +0: ffn_hidden_size ................................. 3584 +0: finetune ........................................ False +0: fp16 ............................................ False +0: fp16_lm_cross_entropy ........................... False +0: fp32_residual_connection ........................ False +0: gigaflos_no_embeds .............................. 0 +0: global_batch_size ............................... 256 +0: glu_activation .................................. None +0: hidden_dropout .................................. 0.1 +0: hidden_size ..................................... 896 +0: hysteresis ...................................... 2 +0: ict_head_size ................................... None +0: ict_load ........................................ None +0: img_dim ......................................... 224 +0: indexer_batch_size .............................. 128 +0: indexer_log_interval ............................ 1000 +0: inference ....................................... False +0: init_method_std ................................. 0.02 +0: init_method_xavier_uniform ...................... False +0: initial_loss_scale .............................. 4294967296 +0: kill_switch_path ................................ kill-switch-220moscar +0: kv_channels ..................................... 64 +0: layer_norm_fusion ............................... True +0: layernorm_epsilon ............................... 1e-05 +0: lazy_mpu_init ................................... None +0: load ............................................ checkpoints_220moscar +0: local_rank ...................................... None +0: log_batch_size_to_tensorboard ................... True +0: log_interval .................................... 10 +0: log_learning_rate_to_tensorboard ................ True +0: log_level ....................................... None +0: log_level_replica ............................... None +0: log_loss_scale_to_tensorboard ................... True +0: log_num_zeros_in_grad ........................... False +0: log_params_norm ................................. False +0: log_path ........................................ None +0: log_timers_to_tensorboard ....................... True +0: log_validation_ppl_to_tensorboard ............... True +0: loss_on_targets_only ............................ False +0: loss_scale ...................................... None +0: loss_scale_window ............................... 1000 +0: lr .............................................. 0.0002 +0: lr_decay_iters .................................. None +0: lr_decay_samples ................................ 3666992 +0: lr_decay_style .................................. cosine +0: lr_decay_tokens ................................. None +0: lr_warmup_fraction .............................. None +0: lr_warmup_iters ................................. 0 +0: lr_warmup_samples ............................... 36670 +0: make_vocab_size_divisible_by .................... 128 +0: mask_prob ....................................... 0.15 +0: masked_softmax_fusion ........................... True +0: max_position_embeddings ......................... 2048 +0: mean_noise_span_length .......................... None +0: memory_centric_tiled_linear ..................... False +0: merge_file ...................................... gpt2/merges.txt +0: micro_batch_size ................................ 4 +0: min_loss_scale .................................. 1.0 +0: min_lr .......................................... 2e-05 +0: mmap_warmup ..................................... False +0: no_load_optim ................................... None +0: no_load_rng ..................................... None +0: no_save_optim ................................... None +0: no_save_rng ..................................... None +0: noise_density ................................... None +0: num_attention_heads ............................. 14 +0: num_channels .................................... 3 +0: num_classes ..................................... 1000 +0: num_layers ...................................... 18 +0: num_layers_per_virtual_pipeline_stage ........... None +0: num_workers ..................................... 2 +0: onnx_safe ....................................... None +0: openai_gelu ..................................... False +0: optimizer ....................................... adam +0: optimizer_fusion ................................ True +0: override_lr_scheduler ........................... False +0: pad_vocab_size_to ............................... None +0: params_dtype .................................... torch.bfloat16 +0: partition_activations ........................... False +0: patch_dim ....................................... 16 +0: pipeline_model_parallel_size .................... 1 +0: position_embedding_type ......................... PositionEmbeddingType.absolute +0: pp_partition_method ............................. None +0: profile_backward ................................ False +0: query_in_block_prob ............................. 0.1 +0: rampup_batch_size ............................... None +0: rank ............................................ 0 +0: remote_device ................................... none +0: reset_attention_mask ............................ False +0: reset_position_ids .............................. False +0: retriever_report_topk_accuracies ................ [] +0: retriever_score_scaling ......................... False +0: retriever_seq_length ............................ 256 +0: reweight_loss_based_on_position_frequency ....... False +0: sample_rate ..................................... 1.0 +0: save ............................................ checkpoints_220moscar +0: save_interval ................................... 1000 +0: scatter_gather_tensors_in_pipeline .............. True +0: scattered_embeddings ............................ False +0: seed ............................................ 1234 +0: seq_length ...................................... 2048 +0: sgd_momentum .................................... 0.9 +0: short_seq_prob .................................. 0.1 +0: skip_train_iteration_range ...................... None +0: split ........................................... 949,50,1 +0: split_transformers .............................. False +0: sync_tp_duplicated_parameters ................... False +0: synchronize_each_layer .......................... False +0: tensor_model_parallel_size ...................... 1 +0: tensorboard_dir ................................. tensorboard_220moscar +0: tensorboard_log_interval ........................ 1 +0: tensorboard_queue_size .......................... 5 +0: test_weighted_split_names ....................... None +0: test_weighted_split_paths ....................... None +0: test_weighted_split_paths_path .................. None +0: test_weighted_split_splits ...................... None +0: test_weighted_split_weights ..................... None +0: tile_factor ..................................... 1 +0: titles_data_path ................................ None +0: tokenizer_name_or_path .......................... None +0: tokenizer_type .................................. GPT2BPETokenizer +0: train_iters ..................................... None +0: train_samples ................................... 3666992 +0: train_tokens .................................... None +0: train_weighted_split_paths ...................... None +0: train_weighted_split_paths_path ................. None +0: universal_checkpoint ............................ False +0: use_bnb_optimizer ............................... False +0: use_checkpoint_lr_scheduler ..................... False +0: use_contiguous_buffers_in_ddp ................... True +0: use_cpu_initialization .......................... None +0: use_one_sent_docs ............................... False +0: use_pin_memory .................................. False +0: valid_num_workers ............................... 2 +0: valid_weighted_split_names ...................... None +0: valid_weighted_split_paths ...................... None +0: valid_weighted_split_paths_path ................. None +0: valid_weighted_split_splits ..................... None +0: valid_weighted_split_weights .................... None +0: virtual_pipeline_model_parallel_size ............ None +0: vocab_extra_ids ................................. 0 +0: vocab_file ...................................... gpt2/vocab.json +0: weight_decay .................................... 0.1 +0: world_size ...................................... 64 +0: zero_allgather_bucket_size ...................... 0.0 +0: zero_contigious_gradients ....................... False +0: zero_reduce_bucket_size ......................... 0.0 +0: zero_reduce_scatter ............................. False +0: zero_stage ...................................... 0 +0: -------------------- end of arguments --------------------- +0: setting number of micro-batches to constant 1 +0: > building GPT2BPETokenizer tokenizer ... +0: > padded vocab (size: 50257) with 47 dummy tokens (new size: 50304) +0: DeepSpeed general environment info: +0: torch install path ............... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch'] +0: torch version .................... 1.13.0+rocm5.2 +0: torch cuda version ............... None +0: torch hip version ................ 5.2.21151-afdc89f8 +0: nvcc version ..................... None +0: deepspeed install path ........... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed'] +0: deepspeed info ................... 0.7.5, unknown, unknown +0: deepspeed wheel compiled w. ...... torch 1.13, hip 5.1 +0: **** Git info for Megatron: git_hash=unknown git_branch=unknown **** +0: > initializing torch distributed ... +0: [2022-11-29 21:57:50,816] [INFO] [comm.py:633:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +7: > setting tensorboard ... +0: > initializing tensor model parallel with size 1 +0: > initializing pipeline model parallel with size 1 +0: > setting random seeds to 1234 ... +0: > initializing model parallel cuda seeds on global rank 0, model parallel rank 0, and data parallel rank 0 with model parallel seed: 3952 and data parallel seed: 1234 +0: > compiling dataset index builder ... +0: make: Entering directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' +0: make: Nothing to be done for 'default'. +0: make: Leaving directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' +0: >>> done with dataset index builder. Compilation time: 0.110 seconds +0: > compiling and loading fused kernels ... +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.cpp [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 87 +0: [1/1] c++ scaled_upper_triang_masked_softmax_hip.o scaled_upper_triang_masked_softmax_hip.cuda.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib -lamdhip64 -o scaled_upper_triang_masked_softmax_cuda.so +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.cpp [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 63 +0: ninja: no work to do. +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda_kernel.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_hip_kernel.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 67 +0: ninja: no work to do. +0: >>> done with compiling and loading fused kernels. Compilation time: 21.699 seconds +0: time to initialize megatron (seconds): 90.154 +0: [after megatron is initialized] datetime: 2022-11-29 21:58:18 +0: building GPT model ... +0: [2022-11-29 21:58:18,221] [INFO] [utils.py:827:see_memory_usage] Before Building Model +0: [2022-11-29 21:58:18,222] [INFO] [utils.py:828:see_memory_usage] MA 0.0 GB Max_MA 0.0 GB CA 0.0 GB Max_CA 0 GB +0: [2022-11-29 21:58:18,222] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 34.75 GB, percent = 6.9% +0: SEED_LAYERS=False BASE_SEED=1234 SEED_FN=None +0: Using topology: {ProcessCoord(pipe=0, data=0, model=0): 0, ProcessCoord(pipe=0, data=1, model=0): 1, ProcessCoord(pipe=0, data=2, model=0): 2, ProcessCoord(pipe=0, data=3, model=0): 3, ProcessCoord(pipe=0, data=4, model=0): 4, ProcessCoord(pipe=0, data=5, model=0): 5, ProcessCoord(pipe=0, data=6, model=0): 6, ProcessCoord(pipe=0, data=7, model=0): 7, ProcessCoord(pipe=0, data=8, model=0): 8, ProcessCoord(pipe=0, data=9, model=0): 9, ProcessCoord(pipe=0, data=10, model=0): 10, ProcessCoord(pipe=0, data=11, model=0): 11, ProcessCoord(pipe=0, data=12, model=0): 12, ProcessCoord(pipe=0, data=13, model=0): 13, ProcessCoord(pipe=0, data=14, model=0): 14, ProcessCoord(pipe=0, data=15, model=0): 15, ProcessCoord(pipe=0, data=16, model=0): 16, ProcessCoord(pipe=0, data=17, model=0): 17, ProcessCoord(pipe=0, data=18, model=0): 18, ProcessCoord(pipe=0, data=19, model=0): 19, ProcessCoord(pipe=0, data=20, model=0): 20, ProcessCoord(pipe=0, data=21, model=0): 21, ProcessCoord(pipe=0, data=22, model=0): 22, ProcessCoord(pi +0: pe=0, data=23, model=0): 23, ProcessCoord(pipe=0, data=24, model=0): 24, ProcessCoord(pipe=0, data=25, model=0): 25, ProcessCoord(pipe=0, data=26, model=0): 26, ProcessCoord(pipe=0, data=27, model=0): 27, ProcessCoord(pipe=0, data=28, model=0): 28, ProcessCoord(pipe=0, data=29, model=0): 29, ProcessCoord(pipe=0, data=30, model=0): 30, ProcessCoord(pipe=0, data=31, model=0): 31, ProcessCoord(pipe=0, data=32, model=0): 32, ProcessCoord(pipe=0, data=33, model=0): 33, ProcessCoord(pipe=0, data=34, model=0): 34, ProcessCoord(pipe=0, data=35, model=0): 35, ProcessCoord(pipe=0, data=36, model=0): 36, ProcessCoord(pipe=0, data=37, model=0): 37, ProcessCoord(pipe=0, data=38, model=0): 38, ProcessCoord(pipe=0, data=39, model=0): 39, ProcessCoord(pipe=0, data=40, model=0): 40, ProcessCoord(pipe=0, data=41, model=0): 41, ProcessCoord(pipe=0, data=42, model=0): 42, ProcessCoord(pipe=0, data=43, model=0): 43, ProcessCoord(pipe=0, data=44, model=0): 44, ProcessCoord(pipe=0, data=45, model=0): 45, ProcessCoord(pipe=0, data=4 +0: 6, model=0): 46, ProcessCoord(pipe=0, data=47, model=0): 47, ProcessCoord(pipe=0, data=48, model=0): 48, ProcessCoord(pipe=0, data=49, model=0): 49, ProcessCoord(pipe=0, data=50, model=0): 50, ProcessCoord(pipe=0, data=51, model=0): 51, ProcessCoord(pipe=0, data=52, model=0): 52, ProcessCoord(pipe=0, data=53, model=0): 53, ProcessCoord(pipe=0, data=54, model=0): 54, ProcessCoord(pipe=0, data=55, model=0): 55, ProcessCoord(pipe=0, data=56, model=0): 56, ProcessCoord(pipe=0, data=57, model=0): 57, ProcessCoord(pipe=0, data=58, model=0): 58, ProcessCoord(pipe=0, data=59, model=0): 59, ProcessCoord(pipe=0, data=60, model=0): 60, ProcessCoord(pipe=0, data=61, model=0): 61, ProcessCoord(pipe=0, data=62, model=0): 62, ProcessCoord(pipe=0, data=63, model=0): 63} +0: [2022-11-29 21:58:20,278] [INFO] [module.py:366:_partition_layers] Partitioning pipeline stages with method type:transformer +0: stage=0 layers=25 +0: 0: _to_float16 +0: 1: EmbeddingPipe +0: 2: +0: 3: ParallelTransformerLayerPipe +0: 4: ParallelTransformerLayerPipe +0: 5: ParallelTransformerLayerPipe +0: 6: ParallelTransformerLayerPipe +0: 7: ParallelTransformerLayerPipe +0: 8: ParallelTransformerLayerPipe +0: 9: ParallelTransformerLayerPipe +0: 10: ParallelTransformerLayerPipe +0: 11: ParallelTransformerLayerPipe +0: 12: ParallelTransformerLayerPipe +0: 13: ParallelTransformerLayerPipe +0: 14: ParallelTransformerLayerPipe +0: 15: ParallelTransformerLayerPipe +0: 16: ParallelTransformerLayerPipe +0: 17: ParallelTransformerLayerPipe +0: 18: ParallelTransformerLayerPipe +0: 19: ParallelTransformerLayerPipe +0: 20: ParallelTransformerLayerPipe +0: 21: undo +0: 22: MixedFusedLayerNorm +0: 23: EmbeddingPipe +0: 24: float16_to_fp32 +0: loss: CrossEntropy +0: [2022-11-29 21:58:20,885] [INFO] [utils.py:827:see_memory_usage] After Building Model +0: [2022-11-29 21:58:20,886] [INFO] [utils.py:828:see_memory_usage] MA 0.42 GB Max_MA 0.42 GB CA 0.46 GB Max_CA 0 GB +0: [2022-11-29 21:58:20,886] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 34.76 GB, percent = 6.9% +0: setting training iterations to 14324 +0: > learning rate decay style: cosine +0: DeepSpeed is enabled. +0: [2022-11-29 21:58:20,887] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed info: version=0.7.5, git-hash=unknown, git-branch=unknown +0: [2022-11-29 21:58:31,479] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False +0: [2022-11-29 21:58:31,480] [INFO] [logging.py:68:log_dist] [Rank 0] Removing param_group that has no 'params' in the client Optimizer +0: [2022-11-29 21:58:31,480] [INFO] [logging.py:68:log_dist] [Rank 0] Using client Optimizer as basic optimizer +0: [2022-11-29 21:58:31,486] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Basic Optimizer = FusedAdam +0: [2022-11-29 21:58:31,486] [INFO] [logging.py:68:log_dist] [Rank 0] Creating BF16 optimizer +0: [2022-11-29 21:58:31,528] [INFO] [utils.py:827:see_memory_usage] begin bf16_optimizer +0: [2022-11-29 21:58:31,528] [INFO] [utils.py:828:see_memory_usage] MA 0.41 GB Max_MA 0.42 GB CA 0.46 GB Max_CA 0 GB +0: [2022-11-29 21:58:31,528] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 35.45 GB, percent = 7.0% +0: ninja: no work to do. +2: Time to load utils op: 0.2675139904022217 seconds +2: Time to load utils op: 0.2685716152191162 seconds +2: Time to load utils op: 0.26852893829345703 seconds +2: Time to load utils op: 0.26740479469299316 secondsTime to load utils op: 0.2674064636230469 seconds +2: +2: Time to load utils op: 0.26806044578552246 secondsTime to load utils op: 0.2678501605987549 seconds +2: +2: Time to load utils op: 0.2677335739135742 seconds +0: Time to load utils op: 0.27078700065612793 seconds +0: Time to load utils op: 0.2707407474517822 seconds +0: Time to load utils op: 0.2708299160003662 seconds +0: Time to load utils op: 0.25880885124206543 secondsTime to load utils op: 0.2706618309020996 seconds +0: Time to load utils op: 0.2701249122619629 seconds +0: +0: Time to load utils op: 0.2707631587982178 seconds +0: Time to load utils op: 0.27068424224853516 seconds +1: Time to load utils op: 0.270035982131958 seconds +1: Time to load utils op: 0.26984429359436035 seconds +1: Time to load utils op: 0.26929163932800293 seconds +7: Time to load utils op: 0.24329018592834473 seconds +7: Time to load utils op: 0.2433004379272461 seconds +7: Time to load utils op: 0.24335908889770508 seconds +7: Time to load utils op: 0.24337148666381836 seconds +7: Time to load utils op: 0.24338054656982422 seconds +7: Time to load utils op: 0.243394136428833 secondsTime to load utils op: 0.24339962005615234 secondsTime to load utils op: 0.2434067726135254 seconds +7: +7: +1: Time to load utils op: 0.26965856552124023 secondsTime to load utils op: 0.27040815353393555 seconds +1: +1: Time to load utils op: 0.27114272117614746 seconds +1: Time to load utils op: 0.2709469795227051 seconds +1: Time to load utils op: 0.2700774669647217 seconds +4: Time to load utils op: 0.2660255432128906 seconds +6: Time to load utils op: 0.24402332305908203 seconds +6: Time to load utils op: 0.24405407905578613 seconds +4: Time to load utils op: 0.26648569107055664 secondsTime to load utils op: 0.267031192779541 seconds +4: +4: Time to load utils op: 0.26659703254699707 seconds +4: Time to load utils op: 0.26622557640075684 secondsTime to load utils op: 0.26706695556640625 seconds +4: +4: Time to load utils op: 0.26645493507385254 seconds +6: Time to load utils op: 0.24408340454101562 seconds +4: Time to load utils op: 0.26746034622192383 seconds +6: Time to load utils op: 0.2440943717956543 seconds +6: Time to load utils op: 0.2441117763519287 secondsTime to load utils op: 0.24411511421203613 seconds +6: +6: Time to load utils op: 0.24412035942077637 secondsTime to load utils op: 0.24412870407104492 seconds +6: +3: Time to load utils op: 0.24495840072631836 seconds +3: Time to load utils op: 0.2449803352355957 seconds +5: Time to load utils op: 0.2655191421508789 secondsTime to load utils op: 0.26645970344543457 seconds +5: +5: Time to load utils op: 0.2668273448944092 seconds +3: Time to load utils op: 0.24501919746398926 seconds +3: Time to load utils op: 0.2450275421142578 secondsTime to load utils op: 0.2450275421142578 seconds +3: +3: Time to load utils op: 0.2450408935546875 seconds +3: Time to load utils op: 0.245042085647583 seconds +3: Time to load utils op: 0.24505043029785156 seconds +5: Time to load utils op: 0.26607847213745117 seconds +5: Time to load utils op: 0.26674699783325195 seconds +5: Time to load utils op: 0.26670169830322266 seconds +5: Time to load utils op: 0.2662358283996582 seconds +5: Time to load utils op: 0.26608943939208984 seconds +0: [2022-11-29 21:58:31,829] [INFO] [utils.py:827:see_memory_usage] before initializing group 0 +0: [2022-11-29 21:58:31,829] [INFO] [utils.py:828:see_memory_usage] MA 0.41 GB Max_MA 0.41 GB CA 0.46 GB Max_CA 0 GB +0: [2022-11-29 21:58:31,829] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 35.45 GB, percent = 7.0% +0: [2022-11-29 21:58:32,290] [INFO] [utils.py:827:see_memory_usage] after initializing group 0 +0: [2022-11-29 21:58:32,290] [INFO] [utils.py:828:see_memory_usage] MA 0.91 GB Max_MA 0.91 GB CA 1.19 GB Max_CA 1 GB +0: [2022-11-29 21:58:32,290] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 35.45 GB, percent = 7.0% +0: [2022-11-29 21:58:32,321] [INFO] [utils.py:827:see_memory_usage] before initializing group 1 +0: [2022-11-29 21:58:32,321] [INFO] [utils.py:828:see_memory_usage] MA 0.91 GB Max_MA 0.91 GB CA 1.19 GB Max_CA 1 GB +0: [2022-11-29 21:58:32,321] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 35.45 GB, percent = 7.0% +0: [2022-11-29 21:58:32,353] [INFO] [utils.py:827:see_memory_usage] after initializing group 1 +0: [2022-11-29 21:58:32,354] [INFO] [utils.py:828:see_memory_usage] MA 1.25 GB Max_MA 1.25 GB CA 1.69 GB Max_CA 2 GB +0: [2022-11-29 21:58:32,354] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 35.45 GB, percent = 7.0% +0: Time to load utils op: 0.0007138252258300781 seconds +0: Time to load utils op: 0.0005977153778076172 seconds +0: Time to load utils op: 0.0010137557983398438 secondsTime to load utils op: 0.0010180473327636719 seconds +0: +0: Time to load utils op: 0.0010521411895751953 seconds +4: Time to load utils op: 0.0013153553009033203 seconds +0: Time to load utils op: 0.0009746551513671875 secondsTime to load utils op: 0.0010628700256347656 seconds +0: +1: Time to load utils op: 0.0012044906616210938 seconds +1: Time to load utils op: 0.0010068416595458984 seconds +2: Time to load utils op: 0.0009410381317138672 seconds +1: Time to load utils op: 0.0013167858123779297 secondsTime to load utils op: 0.0010838508605957031 seconds +1: +1: Time to load utils op: 0.001092672348022461 seconds +1: Time to load utils op: 0.001088857650756836 seconds +1: Time to load utils op: 0.0010929107666015625 seconds +3: Time to load utils op: 0.000993490219116211 seconds +2: Time to load utils op: 0.0009374618530273438 seconds +1: Time to load utils op: 0.0012159347534179688 seconds +4: Time to load utils op: 0.00170135498046875 seconds +4: Time to load utils op: 0.0016777515411376953 seconds +3: Time to load utils op: 0.0014891624450683594 seconds +6: Time to load utils op: 0.0013942718505859375 seconds +7: Time to load utils op: 0.0014963150024414062 seconds +2: Time to load utils op: 0.0015282630920410156 seconds +6: Time to load utils op: 0.0017118453979492188 seconds +4: Time to load utils op: 0.0017409324645996094 seconds +4: Time to load utils op: 0.0018482208251953125 seconds +2: Time to load utils op: 0.0013341903686523438 seconds +5: Time to load utils op: 0.001753091812133789 seconds +4: Time to load utils op: 0.001886606216430664 seconds +2: Time to load utils op: 0.0014286041259765625 seconds +5: Time to load utils op: 0.0017402172088623047 seconds +4: Time to load utils op: 0.0019085407257080078 seconds +4: Time to load utils op: 0.0019829273223876953 seconds +2: Time to load utils op: 0.0016443729400634766 secondsTime to load utils op: 0.0016214847564697266 seconds +2: +2: Time to load utils op: 0.0016946792602539062 seconds +3: Time to load utils op: 0.0017752647399902344 seconds +7: Time to load utils op: 0.0017547607421875 seconds +3: Time to load utils op: 0.0016896724700927734 seconds +5: Time to load utils op: 0.0018801689147949219 seconds +7: Time to load utils op: 0.0016720294952392578 seconds +7: Time to load utils op: 0.0016999244689941406 seconds +3: Time to load utils op: 0.001813650131225586 secondsTime to load utils op: 0.0018029212951660156 seconds +3: +5: Time to load utils op: 0.00189208984375 seconds +3: Time to load utils op: 0.0017039775848388672 seconds +5: Time to load utils op: 0.0018317699432373047 seconds +7: Time to load utils op: 0.0018105506896972656 seconds +3: Time to load utils op: 0.0018253326416015625 seconds +5: Time to load utils op: 0.0019259452819824219 seconds +7: Time to load utils op: 0.0016908645629882812 secondsTime to load utils op: 0.001119852066040039 seconds +7: +7: Time to load utils op: 0.0017242431640625 seconds +5: Time to load utils op: 0.0019075870513916016 seconds +5: Time to load utils op: 0.0019378662109375 seconds +6: Time to load utils op: 0.001997709274291992 seconds +6: Time to load utils op: 0.002098560333251953 seconds +6: Time to load utils op: 0.0019643306732177734 seconds +6: Time to load utils op: 0.001996278762817383 seconds +6: Time to load utils op: 0.0019915103912353516 seconds +6: Time to load utils op: 0.0020055770874023438 seconds +0: [2022-11-29 21:58:32,386] [INFO] [utils.py:827:see_memory_usage] before initializing group 2 +0: [2022-11-29 21:58:32,386] [INFO] [utils.py:828:see_memory_usage] MA 1.25 GB Max_MA 1.25 GB CA 1.69 GB Max_CA 2 GB +0: [2022-11-29 21:58:32,386] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 35.55 GB, percent = 7.1% +0: [2022-11-29 21:58:32,421] [INFO] [utils.py:827:see_memory_usage] after initializing group 2 +0: [2022-11-29 21:58:32,421] [INFO] [utils.py:828:see_memory_usage] MA 1.25 GB Max_MA 1.25 GB CA 1.69 GB Max_CA 2 GB +0: [2022-11-29 21:58:32,421] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 35.58 GB, percent = 7.1% +0: [2022-11-29 21:58:32,453] [INFO] [utils.py:827:see_memory_usage] before initialize_optimizer +0: [2022-11-29 21:58:32,454] [INFO] [utils.py:828:see_memory_usage] MA 1.25 GB Max_MA 1.25 GB CA 1.69 GB Max_CA 2 GB +0: [2022-11-29 21:58:32,454] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 35.6 GB, percent = 7.1% +0: [2022-11-29 21:58:32,490] [INFO] [utils.py:827:see_memory_usage] end initialize_optimizer +0: [2022-11-29 21:58:32,491] [INFO] [utils.py:828:see_memory_usage] MA 1.27 GB Max_MA 1.27 GB CA 1.69 GB Max_CA 2 GB +0: [2022-11-29 21:58:32,491] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 35.6 GB, percent = 7.1% +0: [2022-11-29 21:58:32,522] [INFO] [utils.py:827:see_memory_usage] end bf16_optimizer +0: [2022-11-29 21:58:32,522] [INFO] [utils.py:828:see_memory_usage] MA 1.27 GB Max_MA 1.27 GB CA 1.69 GB Max_CA 2 GB +0: [2022-11-29 21:58:32,522] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 35.6 GB, percent = 7.1% +0: [2022-11-29 21:58:32,523] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Final Optimizer = FusedAdam +0: [2022-11-29 21:58:32,523] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed using client LR scheduler +0: [2022-11-29 21:58:32,523] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed LR Scheduler = +0: [2022-11-29 21:58:32,523] [INFO] [logging.py:68:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0, 0.0, 0.0], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +0: [2022-11-29 21:58:32,523] [INFO] [config.py:1007:print] DeepSpeedEngine configuration: +0: [2022-11-29 21:58:32,523] [INFO] [config.py:1011:print] activation_checkpointing_config { +0: "partition_activations": false, +0: "contiguous_memory_optimization": false, +0: "cpu_checkpointing": false, +0: "number_checkpoints": null, +0: "synchronize_checkpoint_boundary": false, +0: "profile": false +0: } +0: [2022-11-29 21:58:32,523] [INFO] [config.py:1011:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True} +0: [2022-11-29 21:58:32,523] [INFO] [config.py:1011:print] amp_enabled .................. False +0: [2022-11-29 21:58:32,523] [INFO] [config.py:1011:print] amp_params ................... False +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] autotuning_config ............ { +0: "enabled": false, +0: "start_step": null, +0: "end_step": null, +0: "metric_path": null, +0: "arg_mappings": null, +0: "metric": "throughput", +0: "model_info": null, +0: "results_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_results", +0: "exps_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_exps", +0: "overwrite": true, +0: "fast": true, +0: "start_profile_step": 3, +0: "end_profile_step": 5, +0: "tuner_type": "gridsearch", +0: "tuner_early_stopping": 5, +0: "tuner_num_trials": 50, +0: "model_info_path": null, +0: "mp_size": 1, +0: "max_train_batch_size": null, +0: "min_train_batch_size": 1, +0: "max_train_micro_batch_size_per_gpu": 1.024000e+03, +0: "min_train_micro_batch_size_per_gpu": 1, +0: "num_tuning_micro_batch_sizes": 3 +0: } +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] bfloat16_enabled ............. True +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] checkpoint_parallel_write_pipeline False +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] checkpoint_tag_validation_enabled True +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] checkpoint_tag_validation_fail False +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] comms_config ................. +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] communication_data_type ...... None +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] compression_config ........... {'weight_quantization': {'shared_parameters': {'enabled': False, 'quantizer_kernel': False, 'schedule_offset': 0, 'quantize_groups': 1, 'quantize_verbose': False, 'quantization_type': 'symmetric', 'quantize_weight_in_forward': False, 'rounding': 'nearest', 'fp16_mixed_quantize': False, 'quantize_change_ratio': 0.001}, 'different_groups': {}}, 'activation_quantization': {'shared_parameters': {'enabled': False, 'quantization_type': 'symmetric', 'range_calibration': 'dynamic', 'schedule_offset': 1000}, 'different_groups': {}}, 'sparse_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'row_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'head_pruning': {'shared_parameters': {'enabled': False, 'method': 'topk', 'schedule_offset': 1000}, 'different_groups': {}}, 'channel_pruning': {'shared_pa +0: rameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'layer_reduction': {'enabled': False}} +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] curriculum_enabled ........... False +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] curriculum_params ............ False +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] dataloader_drop_last ......... False +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] disable_allgather ............ False +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] dump_state ................... False +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] dynamic_loss_scale_args ...... None +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] eigenvalue_enabled ........... False +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] eigenvalue_gas_boundary_resolution 1 +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] eigenvalue_layer_name ........ bert.encoder.layer +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] eigenvalue_layer_num ......... 0 +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] eigenvalue_max_iter .......... 100 +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] eigenvalue_stability ......... 1e-06 +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] eigenvalue_tol ............... 0.01 +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] eigenvalue_verbose ........... False +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] elasticity_enabled ........... False +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] flops_profiler_config ........ { +0: "enabled": false, +0: "profile_step": 1, +0: "module_depth": -1, +0: "top_modules": 1, +0: "detailed": true, +0: "output_file": null +0: } +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] fp16_auto_cast ............... None +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] fp16_enabled ................. False +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] fp16_master_weights_and_gradients False +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] global_rank .................. 0 +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] gradient_accumulation_steps .. 1 +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] gradient_clipping ............ 1.0 +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] gradient_predivide_factor .... 1.0 +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] initial_dynamic_scale ........ 1 +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] load_universal_checkpoint .... False +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] loss_scale ................... 1.0 +0: [2022-11-29 21:58:32,524] [INFO] [config.py:1011:print] memory_breakdown ............. False +0: [2022-11-29 21:58:32,525] [INFO] [config.py:1011:print] monitor_config ............... +0: [2022-11-29 21:58:32,525] [INFO] [config.py:1011:print] nebula_config ................ { +0: "enabled": false, +0: "persistent_storage_path": null, +0: "persistent_time_interval": 100, +0: "num_of_version_in_retention": 2, +0: "enable_nebula_load": true, +0: "load_path": null +0: } +0: [2022-11-29 21:58:32,525] [INFO] [config.py:1011:print] optimizer_legacy_fusion ...... False +0: [2022-11-29 21:58:32,525] [INFO] [config.py:1011:print] optimizer_name ............... None +0: [2022-11-29 21:58:32,525] [INFO] [config.py:1011:print] optimizer_params ............. None +0: [2022-11-29 21:58:32,525] [INFO] [config.py:1011:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0} +0: [2022-11-29 21:58:32,525] [INFO] [config.py:1011:print] pld_enabled .................. False +0: [2022-11-29 21:58:32,525] [INFO] [config.py:1011:print] pld_params ................... False +0: [2022-11-29 21:58:32,525] [INFO] [config.py:1011:print] prescale_gradients ........... False +0: [2022-11-29 21:58:32,525] [INFO] [config.py:1011:print] scheduler_name ............... None +0: [2022-11-29 21:58:32,525] [INFO] [config.py:1011:print] scheduler_params ............. None +0: [2022-11-29 21:58:32,525] [INFO] [config.py:1011:print] sparse_attention ............. None +0: [2022-11-29 21:58:32,525] [INFO] [config.py:1011:print] sparse_gradients_enabled ..... False +0: [2022-11-29 21:58:32,525] [INFO] [config.py:1011:print] steps_per_print .............. 2000 +0: [2022-11-29 21:58:32,525] [INFO] [config.py:1011:print] train_batch_size ............. 256 +0: [2022-11-29 21:58:32,525] [INFO] [config.py:1011:print] train_micro_batch_size_per_gpu 4 +0: [2022-11-29 21:58:32,525] [INFO] [config.py:1011:print] use_node_local_storage ....... False +0: [2022-11-29 21:58:32,525] [INFO] [config.py:1011:print] wall_clock_breakdown ......... False +0: [2022-11-29 21:58:32,525] [INFO] [config.py:1011:print] world_size ................... 64 +0: [2022-11-29 21:58:32,525] [INFO] [config.py:1011:print] zero_allow_untested_optimizer False +0: [2022-11-29 21:58:32,525] [INFO] [config.py:1011:print] zero_config .................. stage=0 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=500000000 allgather_partitions=True allgather_bucket_size=500000000 overlap_comm=False load_from_fp32_weights=True elastic_checkpoint=False offload_param=None offload_optimizer=None sub_group_size=1000000000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=50000000 param_persistence_threshold=100000 model_persistence_threshold=9223372036854775807 max_live_parameters=1000000000 max_reuse_distance=1000000000 gather_16bit_weights_on_model_save=False stage3_gather_fp16_weights_on_model_save=False ignore_unused_parameters=True legacy_stage1=False round_robin_gradients=False +0: [2022-11-29 21:58:32,525] [INFO] [config.py:1011:print] zero_enabled ................. False +0: [2022-11-29 21:58:32,525] [INFO] [config.py:1011:print] zero_optimization_stage ...... 0 +0: [2022-11-29 21:58:32,525] [INFO] [config.py:996:print_user_config] json = { +0: "train_micro_batch_size_per_gpu": 4, +0: "train_batch_size": 256, +0: "gradient_clipping": 1.0, +0: "zero_optimization": { +0: "stage": 0 +0: }, +0: "bf16": { +0: "enabled": true +0: }, +0: "steps_per_print": 2.000000e+03, +0: "wall_clock_breakdown": false +0: } +0: Time to load utils op: 0.0004153251647949219 seconds +0: [2022-11-29 21:58:32,526] [INFO] [engine.py:87:__init__] CONFIG: micro_batches=1 micro_batch_size=4 +0: [2022-11-29 21:58:32,574] [INFO] [engine.py:145:__init__] RANK=0 STAGE=0 LAYERS=25 [0, 25) STAGE_PARAMS=220527104 (220.527M) TOTAL_PARAMS=220527104 (220.527M) UNIQUE_PARAMS=220527104 (220.527M) +0: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: WARNING: could not find the metadata file checkpoints_220moscar +0: will not load any checkpoints and will start from random +6: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 21:58:32,580] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 21:58:32,580] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 21:58:32,580] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 21:58:32,580] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 21:58:32,582] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 21:58:32,582] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 21:58:32,582] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 21:58:32,581] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_220moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: time (ms) | load-checkpoint: 6.02 +0: estimated model parameters: 0.220527104 +0: estimated model parameters without embeddings: 0.173619712 +0: [after model, optimizer, and learning rate scheduler are built] datetime: 2022-11-29 21:58:33 +0: > building train, validation, and test datasets ... +0: > datasets target sizes (minimum size): +0: train: 3666992 +0: validation: 3840 +0: test: 256 +0: > building train, validation, and test datasets for GPT ... +0: > building dataset index ... +0: reading sizes... +0: reading pointers... +0: reading document index... +0: creating numpy buffer of mmap... +0: creating memory view of numpy buffer... +0: > finished creating indexed dataset in 0.035559 seconds +0: number of documents: 431992659 +0: > dataset split: +0: train: +0: document indices in [0, 409961033) total of 409961033 documents +0: validation: +0: document indices in [409961033, 431560666) total of 21599633 documents +0: test: +0: document indices in [431560666, 431992659) total of 431993 documents +0: > WARNING: could not find index map files, building the indices on rank 0 ... +0: > only one epoch required, setting separate_last_epoch to False +0: > elasped time to build and save doc-idx mapping (seconds): 31.144788 +0: using: +0: number of documents: 409961033 +0: number of epochs: 1 +0: sequence length: 2048 +0: total number of samples: 262636457 +0: > elasped time to build and save sample-idx mapping (seconds): 7.755302 +0: > building shuffle index with split [0, 262636457) and [262636457, 262636457) ... +0: > elasped time to build and save shuffle-idx mapping (seconds): 15.851719 +0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_3666992ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_3666992ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_3666992ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.833 seconds +0: total number of samples: 262636458 +0: total number of epochs: 1 +0: > WARNING: could not find index map files, building the indices on rank 0 ... +0: > only one epoch required, setting separate_last_epoch to False +0: > elasped time to build and save doc-idx mapping (seconds): 1.186154 +0: using: +0: number of documents: 21599633 +0: number of epochs: 1 +0: sequence length: 2048 +0: total number of samples: 13852049 +0: > elasped time to build and save sample-idx mapping (seconds): 0.404655 +0: > building shuffle index with split [0, 13852049) and [13852049, 13852049) ... +0: > elasped time to build and save shuffle-idx mapping (seconds): 0.465371 +0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_3840ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_3840ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_3840ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.044 seconds +0: total number of samples: 13852050 +0: total number of epochs: 1 +0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_256ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_256ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_256ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.082 seconds +0: total number of samples: 276852 +0: total number of epochs: 1 +0: > finished creating GPT datasets ... +0: [after dataloaders are built] datetime: 2022-11-29 22:00:03 +0: done with setup ... +0: training ... +0: Number of parameters: [tensor rank - pipeline rank] w/ and w/o embeddings: +7: time (ms) | model-and-optimizer-setup: 15316.70 | train/valid/test-data-iterators-setup: 90048.11 +0: [000-000] 0.2205B / 0.1736B +0: [before the start of training step] datetime: 2022-11-29 22:00:03 +0: [Rank 0] (after 10 iterations) memory (MB) | allocated: 3312.30078125 | max allocated: 30164.70654296875 | reserved: 30952.0 | max reserved: 30952.0 +7: iteration 10/ 14324 | consumed samples: 2560 | consumed tokens: 5242880 | elapsed time per iteration (s): 1.96 | learning rate: 1.396E-05 | global batch size: 256 | lm loss: 1.040857E+01 | grad norm: 3.075 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 130.599 | TFLOPs: 6.85 | +7: iteration 20/ 14324 | consumed samples: 5120 | consumed tokens: 10485760 | elapsed time per iteration (s): 0.45 | learning rate: 2.792E-05 | global batch size: 256 | lm loss: 9.522927E+00 | grad norm: 1.740 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 573.399 | TFLOPs: 30.09 | +7: iteration 30/ 14324 | consumed samples: 7680 | consumed tokens: 15728640 | elapsed time per iteration (s): 0.44 | learning rate: 4.189E-05 | global batch size: 256 | lm loss: 9.187096E+00 | grad norm: 2.442 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 582.901 | TFLOPs: 30.58 | +7: iteration 40/ 14324 | consumed samples: 10240 | consumed tokens: 20971520 | elapsed time per iteration (s): 0.43 | learning rate: 5.585E-05 | global batch size: 256 | lm loss: 8.679572E+00 | grad norm: 2.083 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.145 | TFLOPs: 31.38 | +7: iteration 50/ 14324 | consumed samples: 12800 | consumed tokens: 26214400 | elapsed time per iteration (s): 0.42 | learning rate: 6.981E-05 | global batch size: 256 | lm loss: 8.183981E+00 | grad norm: 1.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.227 | TFLOPs: 31.70 | +7: iteration 60/ 14324 | consumed samples: 15360 | consumed tokens: 31457280 | elapsed time per iteration (s): 0.43 | learning rate: 8.377E-05 | global batch size: 256 | lm loss: 7.732934E+00 | grad norm: 0.949 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.203 | TFLOPs: 31.18 | +7: iteration 70/ 14324 | consumed samples: 17920 | consumed tokens: 36700160 | elapsed time per iteration (s): 0.44 | learning rate: 9.774E-05 | global batch size: 256 | lm loss: 7.421883E+00 | grad norm: 0.867 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 585.476 | TFLOPs: 30.72 | +7: iteration 80/ 14324 | consumed samples: 20480 | consumed tokens: 41943040 | elapsed time per iteration (s): 0.45 | learning rate: 1.117E-04 | global batch size: 256 | lm loss: 7.249078E+00 | grad norm: 1.377 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 564.788 | TFLOPs: 29.63 | +7: iteration 90/ 14324 | consumed samples: 23040 | consumed tokens: 47185920 | elapsed time per iteration (s): 0.45 | learning rate: 1.257E-04 | global batch size: 256 | lm loss: 7.019980E+00 | grad norm: 0.922 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 571.541 | TFLOPs: 29.99 | +7: iteration 100/ 14324 | consumed samples: 25600 | consumed tokens: 52428800 | elapsed time per iteration (s): 0.47 | learning rate: 1.396E-04 | global batch size: 256 | lm loss: 6.888157E+00 | grad norm: 0.832 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 541.700 | TFLOPs: 28.42 | +7: iteration 110/ 14324 | consumed samples: 28160 | consumed tokens: 57671680 | elapsed time per iteration (s): 0.43 | learning rate: 1.536E-04 | global batch size: 256 | lm loss: 6.767280E+00 | grad norm: 1.086 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.784 | TFLOPs: 31.26 | +7: iteration 120/ 14324 | consumed samples: 30720 | consumed tokens: 62914560 | elapsed time per iteration (s): 0.42 | learning rate: 1.675E-04 | global batch size: 256 | lm loss: 6.684193E+00 | grad norm: 0.738 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.766 | TFLOPs: 32.05 | +7: iteration 130/ 14324 | consumed samples: 33280 | consumed tokens: 68157440 | elapsed time per iteration (s): 0.44 | learning rate: 1.815E-04 | global batch size: 256 | lm loss: 6.554263E+00 | grad norm: 0.570 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 584.257 | TFLOPs: 30.66 | +7: iteration 140/ 14324 | consumed samples: 35840 | consumed tokens: 73400320 | elapsed time per iteration (s): 0.44 | learning rate: 1.955E-04 | global batch size: 256 | lm loss: 6.501231E+00 | grad norm: 0.964 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 579.477 | TFLOPs: 30.40 | +7: iteration 150/ 14324 | consumed samples: 38400 | consumed tokens: 78643200 | elapsed time per iteration (s): 0.45 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.412373E+00 | grad norm: 0.745 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 569.874 | TFLOPs: 29.90 | +7: iteration 160/ 14324 | consumed samples: 40960 | consumed tokens: 83886080 | elapsed time per iteration (s): 0.44 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.362070E+00 | grad norm: 0.771 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 580.246 | TFLOPs: 30.44 | +7: iteration 170/ 14324 | consumed samples: 43520 | consumed tokens: 89128960 | elapsed time per iteration (s): 0.43 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.298890E+00 | grad norm: 0.523 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.981 | TFLOPs: 31.22 | +7: iteration 180/ 14324 | consumed samples: 46080 | consumed tokens: 94371840 | elapsed time per iteration (s): 0.43 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.225459E+00 | grad norm: 0.475 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.983 | TFLOPs: 31.48 | +7: iteration 190/ 14324 | consumed samples: 48640 | consumed tokens: 99614720 | elapsed time per iteration (s): 0.43 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.192514E+00 | grad norm: 0.716 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.028 | TFLOPs: 31.17 | +7: iteration 200/ 14324 | consumed samples: 51200 | consumed tokens: 104857600 | elapsed time per iteration (s): 0.42 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.165696E+00 | grad norm: 0.652 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.199 | TFLOPs: 31.91 | +7: iteration 210/ 14324 | consumed samples: 53760 | consumed tokens: 110100480 | elapsed time per iteration (s): 0.43 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.108098E+00 | grad norm: 0.716 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.371 | TFLOPs: 31.55 | +7: iteration 220/ 14324 | consumed samples: 56320 | consumed tokens: 115343360 | elapsed time per iteration (s): 0.43 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.074185E+00 | grad norm: 0.690 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.731 | TFLOPs: 31.20 | +7: iteration 230/ 14324 | consumed samples: 58880 | consumed tokens: 120586240 | elapsed time per iteration (s): 0.42 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.004517E+00 | grad norm: 0.828 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.216 | TFLOPs: 31.65 | +7: iteration 240/ 14324 | consumed samples: 61440 | consumed tokens: 125829120 | elapsed time per iteration (s): 0.43 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.956846E+00 | grad norm: 1.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.788 | TFLOPs: 31.16 | +7: iteration 250/ 14324 | consumed samples: 64000 | consumed tokens: 131072000 | elapsed time per iteration (s): 0.42 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.959513E+00 | grad norm: 1.075 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.748 | TFLOPs: 31.63 | +7: iteration 260/ 14324 | consumed samples: 66560 | consumed tokens: 136314880 | elapsed time per iteration (s): 0.43 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.923690E+00 | grad norm: 0.684 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.940 | TFLOPs: 31.16 | +7: iteration 270/ 14324 | consumed samples: 69120 | consumed tokens: 141557760 | elapsed time per iteration (s): 0.44 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.884217E+00 | grad norm: 0.637 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 586.193 | TFLOPs: 30.76 | +7: iteration 280/ 14324 | consumed samples: 71680 | consumed tokens: 146800640 | elapsed time per iteration (s): 0.44 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.872056E+00 | grad norm: 0.757 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 587.863 | TFLOPs: 30.84 | +7: iteration 290/ 14324 | consumed samples: 74240 | consumed tokens: 152043520 | elapsed time per iteration (s): 0.44 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.818356E+00 | grad norm: 1.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 587.205 | TFLOPs: 30.81 | +7: iteration 300/ 14324 | consumed samples: 76800 | consumed tokens: 157286400 | elapsed time per iteration (s): 0.43 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.789587E+00 | grad norm: 1.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 590.307 | TFLOPs: 30.97 | +7: iteration 310/ 14324 | consumed samples: 79360 | consumed tokens: 162529280 | elapsed time per iteration (s): 0.44 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.738010E+00 | grad norm: 0.646 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 586.128 | TFLOPs: 30.75 | +7: iteration 320/ 14324 | consumed samples: 81920 | consumed tokens: 167772160 | elapsed time per iteration (s): 0.42 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.703712E+00 | grad norm: 1.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.530 | TFLOPs: 31.72 | +7: iteration 330/ 14324 | consumed samples: 84480 | consumed tokens: 173015040 | elapsed time per iteration (s): 0.45 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.695708E+00 | grad norm: 1.026 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 573.356 | TFLOPs: 30.08 | +7: iteration 340/ 14324 | consumed samples: 87040 | consumed tokens: 178257920 | elapsed time per iteration (s): 0.43 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.665826E+00 | grad norm: 0.653 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.249 | TFLOPs: 31.55 | +7: iteration 350/ 14324 | consumed samples: 89600 | consumed tokens: 183500800 | elapsed time per iteration (s): 0.44 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.600957E+00 | grad norm: 0.838 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 587.265 | TFLOPs: 30.81 | +7: iteration 360/ 14324 | consumed samples: 92160 | consumed tokens: 188743680 | elapsed time per iteration (s): 0.44 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.594424E+00 | grad norm: 0.595 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 581.159 | TFLOPs: 30.49 | +7: iteration 370/ 14324 | consumed samples: 94720 | consumed tokens: 193986560 | elapsed time per iteration (s): 0.43 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.569093E+00 | grad norm: 0.740 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.164 | TFLOPs: 31.28 | +7: iteration 380/ 14324 | consumed samples: 97280 | consumed tokens: 199229440 | elapsed time per iteration (s): 0.42 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.484803E+00 | grad norm: 0.956 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.468 | TFLOPs: 31.66 | +7: iteration 390/ 14324 | consumed samples: 99840 | consumed tokens: 204472320 | elapsed time per iteration (s): 0.43 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.497612E+00 | grad norm: 0.629 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.968 | TFLOPs: 31.16 | +7: iteration 400/ 14324 | consumed samples: 102400 | consumed tokens: 209715200 | elapsed time per iteration (s): 0.43 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.430178E+00 | grad norm: 0.532 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 590.593 | TFLOPs: 30.99 | +7: iteration 410/ 14324 | consumed samples: 104960 | consumed tokens: 214958080 | elapsed time per iteration (s): 0.43 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.392135E+00 | grad norm: 0.823 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.055 | TFLOPs: 31.17 | +7: iteration 420/ 14324 | consumed samples: 107520 | consumed tokens: 220200960 | elapsed time per iteration (s): 0.43 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.401610E+00 | grad norm: 0.616 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.660 | TFLOPs: 31.15 | +7: iteration 430/ 14324 | consumed samples: 110080 | consumed tokens: 225443840 | elapsed time per iteration (s): 0.44 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.342989E+00 | grad norm: 0.951 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 585.135 | TFLOPs: 30.70 | +7: iteration 440/ 14324 | consumed samples: 112640 | consumed tokens: 230686720 | elapsed time per iteration (s): 0.44 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.314455E+00 | grad norm: 1.089 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 580.678 | TFLOPs: 30.47 | +7: iteration 450/ 14324 | consumed samples: 115200 | consumed tokens: 235929600 | elapsed time per iteration (s): 0.42 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.294080E+00 | grad norm: 0.909 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.650 | TFLOPs: 31.62 | +7: iteration 460/ 14324 | consumed samples: 117760 | consumed tokens: 241172480 | elapsed time per iteration (s): 0.43 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.291537E+00 | grad norm: 0.637 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.913 | TFLOPs: 31.27 | +7: iteration 470/ 14324 | consumed samples: 120320 | consumed tokens: 246415360 | elapsed time per iteration (s): 0.43 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.232161E+00 | grad norm: 0.867 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.344 | TFLOPs: 31.39 | +7: iteration 480/ 14324 | consumed samples: 122880 | consumed tokens: 251658240 | elapsed time per iteration (s): 0.44 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 5.246624E+00 | grad norm: 0.657 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 586.097 | TFLOPs: 30.75 | +7: iteration 490/ 14324 | consumed samples: 125440 | consumed tokens: 256901120 | elapsed time per iteration (s): 0.43 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 5.201087E+00 | grad norm: 1.034 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.676 | TFLOPs: 31.52 | +7: iteration 500/ 14324 | consumed samples: 128000 | consumed tokens: 262144000 | elapsed time per iteration (s): 0.43 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 5.166848E+00 | grad norm: 0.641 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.150 | TFLOPs: 31.17 | +7: iteration 510/ 14324 | consumed samples: 130560 | consumed tokens: 267386880 | elapsed time per iteration (s): 0.43 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 5.143713E+00 | grad norm: 0.996 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.456 | TFLOPs: 31.56 | +7: iteration 520/ 14324 | consumed samples: 133120 | consumed tokens: 272629760 | elapsed time per iteration (s): 0.43 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 5.101346E+00 | grad norm: 1.078 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.604 | TFLOPs: 31.46 | +7: iteration 530/ 14324 | consumed samples: 135680 | consumed tokens: 277872640 | elapsed time per iteration (s): 0.43 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 5.072658E+00 | grad norm: 0.955 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.320 | TFLOPs: 31.24 | +7: iteration 540/ 14324 | consumed samples: 138240 | consumed tokens: 283115520 | elapsed time per iteration (s): 0.43 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 5.066663E+00 | grad norm: 0.802 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.922 | TFLOPs: 31.21 | +7: iteration 550/ 14324 | consumed samples: 140800 | consumed tokens: 288358400 | elapsed time per iteration (s): 0.43 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 5.030313E+00 | grad norm: 0.792 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.802 | TFLOPs: 31.26 | +7: iteration 560/ 14324 | consumed samples: 143360 | consumed tokens: 293601280 | elapsed time per iteration (s): 0.43 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.991659E+00 | grad norm: 0.833 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 589.388 | TFLOPs: 30.92 | +7: iteration 570/ 14324 | consumed samples: 145920 | consumed tokens: 298844160 | elapsed time per iteration (s): 0.42 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.950904E+00 | grad norm: 0.609 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.567 | TFLOPs: 31.67 | +7: iteration 580/ 14324 | consumed samples: 148480 | consumed tokens: 304087040 | elapsed time per iteration (s): 0.43 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.929906E+00 | grad norm: 1.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.254 | TFLOPs: 31.44 | +7: iteration 590/ 14324 | consumed samples: 151040 | consumed tokens: 309329920 | elapsed time per iteration (s): 0.43 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.926205E+00 | grad norm: 0.789 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.322 | TFLOPs: 31.13 | +7: iteration 600/ 14324 | consumed samples: 153600 | consumed tokens: 314572800 | elapsed time per iteration (s): 0.43 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.869191E+00 | grad norm: 0.654 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.734 | TFLOPs: 31.26 | +7: iteration 610/ 14324 | consumed samples: 156160 | consumed tokens: 319815680 | elapsed time per iteration (s): 0.43 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.834867E+00 | grad norm: 1.007 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.304 | TFLOPs: 31.02 | +7: iteration 620/ 14324 | consumed samples: 158720 | consumed tokens: 325058560 | elapsed time per iteration (s): 0.43 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.813182E+00 | grad norm: 1.029 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.088 | TFLOPs: 31.07 | +7: iteration 630/ 14324 | consumed samples: 161280 | consumed tokens: 330301440 | elapsed time per iteration (s): 0.42 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.786382E+00 | grad norm: 0.941 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.135 | TFLOPs: 31.80 | +7: iteration 640/ 14324 | consumed samples: 163840 | consumed tokens: 335544320 | elapsed time per iteration (s): 0.43 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.761268E+00 | grad norm: 0.981 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 589.601 | TFLOPs: 30.94 | +7: iteration 650/ 14324 | consumed samples: 166400 | consumed tokens: 340787200 | elapsed time per iteration (s): 0.43 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.680170E+00 | grad norm: 0.772 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.193 | TFLOPs: 31.18 | +7: iteration 660/ 14324 | consumed samples: 168960 | consumed tokens: 346030080 | elapsed time per iteration (s): 0.42 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.678313E+00 | grad norm: 1.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.551 | TFLOPs: 31.61 | +7: iteration 670/ 14324 | consumed samples: 171520 | consumed tokens: 351272960 | elapsed time per iteration (s): 0.43 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.613740E+00 | grad norm: 0.992 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.655 | TFLOPs: 31.20 | +7: iteration 680/ 14324 | consumed samples: 174080 | consumed tokens: 356515840 | elapsed time per iteration (s): 0.43 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.584468E+00 | grad norm: 0.995 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.488 | TFLOPs: 31.30 | +7: iteration 690/ 14324 | consumed samples: 176640 | consumed tokens: 361758720 | elapsed time per iteration (s): 0.44 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.567828E+00 | grad norm: 0.929 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 588.263 | TFLOPs: 30.87 | +7: iteration 700/ 14324 | consumed samples: 179200 | consumed tokens: 367001600 | elapsed time per iteration (s): 0.43 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.551416E+00 | grad norm: 1.041 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.183 | TFLOPs: 31.33 | +7: iteration 710/ 14324 | consumed samples: 181760 | consumed tokens: 372244480 | elapsed time per iteration (s): 0.42 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.487527E+00 | grad norm: 0.967 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.859 | TFLOPs: 32.00 | +7: iteration 720/ 14324 | consumed samples: 184320 | consumed tokens: 377487360 | elapsed time per iteration (s): 0.44 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.492239E+00 | grad norm: 0.967 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 575.852 | TFLOPs: 30.21 | +7: iteration 730/ 14324 | consumed samples: 186880 | consumed tokens: 382730240 | elapsed time per iteration (s): 0.44 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.454773E+00 | grad norm: 0.828 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 586.446 | TFLOPs: 30.77 | +7: iteration 740/ 14324 | consumed samples: 189440 | consumed tokens: 387973120 | elapsed time per iteration (s): 0.45 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.423193E+00 | grad norm: 1.006 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 565.224 | TFLOPs: 29.66 | +7: iteration 750/ 14324 | consumed samples: 192000 | consumed tokens: 393216000 | elapsed time per iteration (s): 0.44 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.378579E+00 | grad norm: 0.735 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 588.317 | TFLOPs: 30.87 | +7: iteration 760/ 14324 | consumed samples: 194560 | consumed tokens: 398458880 | elapsed time per iteration (s): 0.43 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.369504E+00 | grad norm: 0.981 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.256 | TFLOPs: 31.34 | +7: iteration 770/ 14324 | consumed samples: 197120 | consumed tokens: 403701760 | elapsed time per iteration (s): 0.45 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 4.351537E+00 | grad norm: 1.051 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 570.529 | TFLOPs: 29.93 | +7: iteration 780/ 14324 | consumed samples: 199680 | consumed tokens: 408944640 | elapsed time per iteration (s): 0.42 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 4.349411E+00 | grad norm: 0.680 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.177 | TFLOPs: 31.75 | +7: iteration 790/ 14324 | consumed samples: 202240 | consumed tokens: 414187520 | elapsed time per iteration (s): 0.44 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 4.332465E+00 | grad norm: 1.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 587.381 | TFLOPs: 30.82 | +7: iteration 800/ 14324 | consumed samples: 204800 | consumed tokens: 419430400 | elapsed time per iteration (s): 0.42 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 4.338015E+00 | grad norm: 1.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.691 | TFLOPs: 31.62 | +7: iteration 810/ 14324 | consumed samples: 207360 | consumed tokens: 424673280 | elapsed time per iteration (s): 0.43 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 4.304057E+00 | grad norm: 1.086 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.593 | TFLOPs: 31.14 | +7: iteration 820/ 14324 | consumed samples: 209920 | consumed tokens: 429916160 | elapsed time per iteration (s): 0.43 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 4.245202E+00 | grad norm: 0.669 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.373 | TFLOPs: 31.55 | +7: iteration 830/ 14324 | consumed samples: 212480 | consumed tokens: 435159040 | elapsed time per iteration (s): 0.44 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 4.275637E+00 | grad norm: 1.013 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 579.638 | TFLOPs: 30.41 | +7: iteration 840/ 14324 | consumed samples: 215040 | consumed tokens: 440401920 | elapsed time per iteration (s): 0.43 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 4.259696E+00 | grad norm: 1.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.532 | TFLOPs: 31.51 | +7: iteration 850/ 14324 | consumed samples: 217600 | consumed tokens: 445644800 | elapsed time per iteration (s): 0.43 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 4.214845E+00 | grad norm: 0.644 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.385 | TFLOPs: 31.13 | +7: iteration 860/ 14324 | consumed samples: 220160 | consumed tokens: 450887680 | elapsed time per iteration (s): 0.43 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 4.198886E+00 | grad norm: 0.734 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.031 | TFLOPs: 31.33 | +7: iteration 870/ 14324 | consumed samples: 222720 | consumed tokens: 456130560 | elapsed time per iteration (s): 0.44 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 4.184280E+00 | grad norm: 0.606 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 588.196 | TFLOPs: 30.86 | +7: iteration 880/ 14324 | consumed samples: 225280 | consumed tokens: 461373440 | elapsed time per iteration (s): 0.43 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 4.157564E+00 | grad norm: 1.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.845 | TFLOPs: 31.37 | +7: iteration 890/ 14324 | consumed samples: 227840 | consumed tokens: 466616320 | elapsed time per iteration (s): 0.43 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 4.151415E+00 | grad norm: 1.098 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.890 | TFLOPs: 31.16 | +7: iteration 900/ 14324 | consumed samples: 230400 | consumed tokens: 471859200 | elapsed time per iteration (s): 0.43 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 4.189456E+00 | grad norm: 0.631 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.345 | TFLOPs: 31.08 | +7: iteration 910/ 14324 | consumed samples: 232960 | consumed tokens: 477102080 | elapsed time per iteration (s): 0.43 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 4.168726E+00 | grad norm: 0.590 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.570 | TFLOPs: 31.20 | +7: iteration 920/ 14324 | consumed samples: 235520 | consumed tokens: 482344960 | elapsed time per iteration (s): 0.43 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 4.107814E+00 | grad norm: 0.908 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.872 | TFLOPs: 31.32 | +7: iteration 930/ 14324 | consumed samples: 238080 | consumed tokens: 487587840 | elapsed time per iteration (s): 0.44 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 4.099818E+00 | grad norm: 0.534 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 585.991 | TFLOPs: 30.75 | +7: iteration 940/ 14324 | consumed samples: 240640 | consumed tokens: 492830720 | elapsed time per iteration (s): 0.43 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 4.057493E+00 | grad norm: 0.499 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.923 | TFLOPs: 31.53 | +7: iteration 950/ 14324 | consumed samples: 243200 | consumed tokens: 498073600 | elapsed time per iteration (s): 0.42 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 4.073690E+00 | grad norm: 0.644 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.751 | TFLOPs: 31.68 | +7: iteration 960/ 14324 | consumed samples: 245760 | consumed tokens: 503316480 | elapsed time per iteration (s): 0.43 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 4.070171E+00 | grad norm: 0.739 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.887 | TFLOPs: 31.16 | +7: iteration 970/ 14324 | consumed samples: 248320 | consumed tokens: 508559360 | elapsed time per iteration (s): 0.43 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 4.055311E+00 | grad norm: 0.498 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.400 | TFLOPs: 31.40 | +7: iteration 980/ 14324 | consumed samples: 250880 | consumed tokens: 513802240 | elapsed time per iteration (s): 0.43 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 4.056216E+00 | grad norm: 0.876 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.864 | TFLOPs: 31.32 | +7: iteration 990/ 14324 | consumed samples: 253440 | consumed tokens: 519045120 | elapsed time per iteration (s): 0.44 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 4.029556E+00 | grad norm: 0.636 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 577.651 | TFLOPs: 30.31 | +7: iteration 1000/ 14324 | consumed samples: 256000 | consumed tokens: 524288000 | elapsed time per iteration (s): 0.43 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 4.054646E+00 | grad norm: 0.573 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.010 | TFLOPs: 31.11 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 1000 | lm loss value: 3.878476E+00 | lm loss PPL: 4.835048E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 1000 to checkpoints_220moscar +0: [2022-11-29 22:07:31,736] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step1000 is begin to save! +0: [2022-11-29 22:07:31,952] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/layer_01-model_00-model_states.pt... +0: [2022-11-29 22:07:32,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/layer_01-model_00-model_states.pt. +0: [2022-11-29 22:07:32,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/layer_03-model_00-model_states.pt... +0: [2022-11-29 22:07:32,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/layer_03-model_00-model_states.pt. +0: [2022-11-29 22:07:32,142] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/layer_04-model_00-model_states.pt... +0: [2022-11-29 22:07:32,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/layer_04-model_00-model_states.pt. +0: [2022-11-29 22:07:32,166] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/layer_05-model_00-model_states.pt... +0: [2022-11-29 22:07:32,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/layer_05-model_00-model_states.pt. +0: [2022-11-29 22:07:32,190] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/layer_06-model_00-model_states.pt... +0: [2022-11-29 22:07:32,213] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/layer_06-model_00-model_states.pt. +0: [2022-11-29 22:07:32,213] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/layer_07-model_00-model_states.pt... +0: [2022-11-29 22:07:32,237] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/layer_07-model_00-model_states.pt. +0: [2022-11-29 22:07:32,237] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/layer_08-model_00-model_states.pt... +0: [2022-11-29 22:07:32,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/layer_08-model_00-model_states.pt. +0: [2022-11-29 22:07:32,260] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/layer_09-model_00-model_states.pt... +0: [2022-11-29 22:07:32,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/layer_09-model_00-model_states.pt. +0: [2022-11-29 22:07:32,282] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/layer_10-model_00-model_states.pt... +0: [2022-11-29 22:07:32,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/layer_10-model_00-model_states.pt. +0: [2022-11-29 22:07:32,304] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/layer_11-model_00-model_states.pt... +0: [2022-11-29 22:07:32,327] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/layer_11-model_00-model_states.pt. +0: [2022-11-29 22:07:32,328] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/layer_12-model_00-model_states.pt... +0: [2022-11-29 22:07:32,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/layer_12-model_00-model_states.pt. +0: [2022-11-29 22:07:32,351] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/layer_13-model_00-model_states.pt... +0: [2022-11-29 22:07:32,373] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/layer_13-model_00-model_states.pt. +0: [2022-11-29 22:07:32,374] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/layer_14-model_00-model_states.pt... +0: [2022-11-29 22:07:32,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/layer_14-model_00-model_states.pt. +0: [2022-11-29 22:07:32,398] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/layer_15-model_00-model_states.pt... +0: [2022-11-29 22:07:32,420] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/layer_15-model_00-model_states.pt. +0: [2022-11-29 22:07:32,420] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/layer_16-model_00-model_states.pt... +0: [2022-11-29 22:07:32,443] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/layer_16-model_00-model_states.pt. +0: [2022-11-29 22:07:32,444] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/layer_17-model_00-model_states.pt... +0: [2022-11-29 22:07:32,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/layer_17-model_00-model_states.pt. +0: [2022-11-29 22:07:32,465] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/layer_18-model_00-model_states.pt... +0: [2022-11-29 22:07:32,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/layer_18-model_00-model_states.pt. +0: [2022-11-29 22:07:32,488] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/layer_19-model_00-model_states.pt... +0: [2022-11-29 22:07:32,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/layer_19-model_00-model_states.pt. +0: [2022-11-29 22:07:32,511] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/layer_20-model_00-model_states.pt... +0: [2022-11-29 22:07:32,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/layer_20-model_00-model_states.pt. +0: [2022-11-29 22:07:32,535] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/layer_22-model_00-model_states.pt... +0: [2022-11-29 22:07:32,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/layer_22-model_00-model_states.pt. +0: [2022-11-29 22:07:32,540] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_220moscar/global_step1000/mp_rank_00_model_states.pt +0: [2022-11-29 22:07:32,540] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/mp_rank_00_model_states.pt... +0: [2022-11-29 22:07:32,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/mp_rank_00_model_states.pt. +0: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:07:32,561] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:07:32,561] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:07:32,561] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:07:32,561] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:07:32,561] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:07:32,561] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:07:32,561] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:07:32,561] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:07:32,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:07:32,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:07:32,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:07:32,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:07:32,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 22:07:32,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 22:07:32,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 22:07:32,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 22:07:32,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:07:32,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 22:07:32,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 22:07:32,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:07:32,615] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 22:07:32,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 22:07:32,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:07:32,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 22:07:32,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 22:07:32,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:07:32,621] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 22:07:32,621] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 22:07:32,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:07:32,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 22:07:32,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 22:07:32,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:07:32,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 22:07:32,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 22:07:32,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:07:32,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +1: [2022-11-29 22:07:32,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:07:32,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 22:07:32,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 22:07:32,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 22:07:32,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:07:32,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 22:07:32,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 22:07:32,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:07:32,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:07:32,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 22:07:32,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 22:07:32,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 22:07:32,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 22:07:32,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:07:32,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:07:32,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 22:07:32,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 22:07:32,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 22:07:32,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 22:07:32,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:07:32,628] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +5: [2022-11-29 22:07:32,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:07:32,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 22:07:32,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:07:32,628] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 22:07:32,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 22:07:32,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:07:32,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 22:07:32,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 22:07:32,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:07:32,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:07:32,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:07:32,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 22:07:32,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 22:07:32,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 22:07:32,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 22:07:32,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 22:07:32,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 22:07:32,632] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:07:32,632] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 22:07:32,632] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 22:07:32,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:07:32,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:07:32,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:07:32,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:07:32,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 22:07:32,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 22:07:32,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 22:07:32,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 22:07:32,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 22:07:32,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 22:07:32,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 22:07:32,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 22:07:32,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:07:32,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 22:07:32,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:07:32,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 22:07:32,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:07:32,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 22:07:32,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 22:07:32,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 22:07:32,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 22:07:32,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:07:32,635] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 22:07:32,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 22:07:32,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 22:07:32,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 22:07:32,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:07:32,628] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 22:07:32,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 22:07:32,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:07:32,630] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 22:07:32,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 22:07:32,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:07:32,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:07:32,630] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 22:07:32,630] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 22:07:32,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 22:07:32,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 22:07:32,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:07:32,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:07:32,637] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 22:07:32,637] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 22:07:32,637] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 22:07:32,637] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 22:07:32,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:07:32,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 22:07:32,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 22:07:32,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:07:32,642] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 22:07:32,642] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 22:07:32,642] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:07:32,642] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 22:07:32,642] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 22:07:32,642] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:07:32,642] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 22:07:32,642] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 22:07:32,642] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:07:32,642] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 22:07:32,642] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 22:07:32,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:07:32,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:07:32,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:07:32,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:07:32,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:07:32,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:07:32,644] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 22:07:32,645] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 22:07:32,645] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:07:32,645] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 22:07:32,645] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 22:07:32,645] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:07:32,645] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 22:07:32,645] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 22:07:32,645] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:07:32,645] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 22:07:32,645] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 22:07:32,645] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:07:32,645] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:07:32,645] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +3: [2022-11-29 22:07:32,645] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +4: [2022-11-29 22:07:32,645] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 22:07:32,645] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 22:07:32,646] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:07:32,646] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 22:07:32,646] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 22:07:32,646] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:07:32,646] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 22:07:32,646] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 22:07:32,644] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 22:07:32,644] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 22:07:32,644] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 22:07:32,644] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 22:07:32,644] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 22:07:32,644] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 22:07:32,644] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 22:07:32,644] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 22:07:32,644] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 22:07:32,644] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 22:07:32,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:07:32,645] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 22:07:32,645] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 22:07:32,645] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:07:32,645] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:07:32,645] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 22:07:32,645] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 22:07:32,645] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 22:07:32,645] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 22:07:32,647] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:07:32,647] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 22:07:32,647] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 22:07:32,648] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:07:32,648] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3: [2022-11-29 22:07:32,648] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:07:32,648] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:07:32,648] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:07:32,648] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 22:07:32,648] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +0: [2022-11-29 22:07:32,648] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 22:07:32,648] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 22:07:32,648] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 22:07:32,648] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 22:07:32,648] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 22:07:32,679] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 22:07:32,679] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: successfully saved checkpoint at iteration 1000 to checkpoints_220moscar +7: time (ms) | save-checkpoint: 951.45 +7: iteration 1010/ 14324 | consumed samples: 258560 | consumed tokens: 529530880 | elapsed time per iteration (s): 0.54 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 4.022500E+00 | grad norm: 0.577 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 476.164 | TFLOPs: 24.98 | +7: iteration 1020/ 14324 | consumed samples: 261120 | consumed tokens: 534773760 | elapsed time per iteration (s): 0.43 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 4.012740E+00 | grad norm: 0.549 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.650 | TFLOPs: 31.15 | +7: iteration 1030/ 14324 | consumed samples: 263680 | consumed tokens: 540016640 | elapsed time per iteration (s): 0.43 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 4.014014E+00 | grad norm: 0.772 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 590.773 | TFLOPs: 31.00 | +7: iteration 1040/ 14324 | consumed samples: 266240 | consumed tokens: 545259520 | elapsed time per iteration (s): 0.43 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 3.975634E+00 | grad norm: 0.574 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.361 | TFLOPs: 31.45 | +7: iteration 1050/ 14324 | consumed samples: 268800 | consumed tokens: 550502400 | elapsed time per iteration (s): 0.43 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 3.980833E+00 | grad norm: 0.576 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.564 | TFLOPs: 31.46 | +7: iteration 1060/ 14324 | consumed samples: 271360 | consumed tokens: 555745280 | elapsed time per iteration (s): 0.43 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 3.979475E+00 | grad norm: 0.556 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.812 | TFLOPs: 31.42 | +7: iteration 1070/ 14324 | consumed samples: 273920 | consumed tokens: 560988160 | elapsed time per iteration (s): 0.44 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 3.945578E+00 | grad norm: 0.488 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 586.787 | TFLOPs: 30.79 | +7: iteration 1080/ 14324 | consumed samples: 276480 | consumed tokens: 566231040 | elapsed time per iteration (s): 0.43 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 3.942883E+00 | grad norm: 0.488 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.028 | TFLOPs: 31.06 | +7: iteration 1090/ 14324 | consumed samples: 279040 | consumed tokens: 571473920 | elapsed time per iteration (s): 0.44 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 3.951606E+00 | grad norm: 0.871 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 586.329 | TFLOPs: 30.76 | +7: iteration 1100/ 14324 | consumed samples: 281600 | consumed tokens: 576716800 | elapsed time per iteration (s): 0.43 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 3.950763E+00 | grad norm: 0.658 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.692 | TFLOPs: 31.15 | +7: iteration 1110/ 14324 | consumed samples: 284160 | consumed tokens: 581959680 | elapsed time per iteration (s): 0.44 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 3.913642E+00 | grad norm: 0.522 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 584.959 | TFLOPs: 30.69 | +7: iteration 1120/ 14324 | consumed samples: 286720 | consumed tokens: 587202560 | elapsed time per iteration (s): 0.43 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 3.910170E+00 | grad norm: 0.562 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.267 | TFLOPs: 31.55 | +7: iteration 1130/ 14324 | consumed samples: 289280 | consumed tokens: 592445440 | elapsed time per iteration (s): 0.42 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 3.901462E+00 | grad norm: 0.550 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.844 | TFLOPs: 31.63 | +7: iteration 1140/ 14324 | consumed samples: 291840 | consumed tokens: 597688320 | elapsed time per iteration (s): 0.43 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 3.910661E+00 | grad norm: 0.516 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.366 | TFLOPs: 31.08 | +7: iteration 1150/ 14324 | consumed samples: 294400 | consumed tokens: 602931200 | elapsed time per iteration (s): 0.43 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 3.896545E+00 | grad norm: 0.527 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.309 | TFLOPs: 31.60 | +7: iteration 1160/ 14324 | consumed samples: 296960 | consumed tokens: 608174080 | elapsed time per iteration (s): 0.43 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 3.912262E+00 | grad norm: 0.646 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.535 | TFLOPs: 31.51 | +7: iteration 1170/ 14324 | consumed samples: 299520 | consumed tokens: 613416960 | elapsed time per iteration (s): 0.43 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 3.899947E+00 | grad norm: 0.501 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.566 | TFLOPs: 31.30 | +7: iteration 1180/ 14324 | consumed samples: 302080 | consumed tokens: 618659840 | elapsed time per iteration (s): 0.44 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 3.877976E+00 | grad norm: 1.022 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 584.977 | TFLOPs: 30.69 | +7: iteration 1190/ 14324 | consumed samples: 304640 | consumed tokens: 623902720 | elapsed time per iteration (s): 0.43 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 3.945937E+00 | grad norm: 0.450 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.904 | TFLOPs: 31.53 | +7: iteration 1200/ 14324 | consumed samples: 307200 | consumed tokens: 629145600 | elapsed time per iteration (s): 0.43 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 3.876928E+00 | grad norm: 0.575 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.688 | TFLOPs: 31.46 | +7: iteration 1210/ 14324 | consumed samples: 309760 | consumed tokens: 634388480 | elapsed time per iteration (s): 0.42 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 3.865190E+00 | grad norm: 0.502 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.879 | TFLOPs: 31.68 | +7: iteration 1220/ 14324 | consumed samples: 312320 | consumed tokens: 639631360 | elapsed time per iteration (s): 0.42 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 3.864499E+00 | grad norm: 0.509 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.796 | TFLOPs: 31.73 | +7: iteration 1230/ 14324 | consumed samples: 314880 | consumed tokens: 644874240 | elapsed time per iteration (s): 0.43 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 3.852540E+00 | grad norm: 0.400 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.088 | TFLOPs: 31.22 | +7: iteration 1240/ 14324 | consumed samples: 317440 | consumed tokens: 650117120 | elapsed time per iteration (s): 0.44 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 3.875648E+00 | grad norm: 0.704 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 585.866 | TFLOPs: 30.74 | +7: iteration 1250/ 14324 | consumed samples: 320000 | consumed tokens: 655360000 | elapsed time per iteration (s): 0.43 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 3.851114E+00 | grad norm: 0.524 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.495 | TFLOPs: 31.30 | +7: iteration 1260/ 14324 | consumed samples: 322560 | consumed tokens: 660602880 | elapsed time per iteration (s): 0.44 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 3.853362E+00 | grad norm: 0.580 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 576.560 | TFLOPs: 30.25 | +7: iteration 1270/ 14324 | consumed samples: 325120 | consumed tokens: 665845760 | elapsed time per iteration (s): 0.42 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 3.842755E+00 | grad norm: 0.522 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.849 | TFLOPs: 32.05 | +7: iteration 1280/ 14324 | consumed samples: 327680 | consumed tokens: 671088640 | elapsed time per iteration (s): 0.42 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 3.830271E+00 | grad norm: 0.598 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.511 | TFLOPs: 31.61 | +7: iteration 1290/ 14324 | consumed samples: 330240 | consumed tokens: 676331520 | elapsed time per iteration (s): 0.42 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 3.819997E+00 | grad norm: 0.466 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.431 | TFLOPs: 31.87 | +7: iteration 1300/ 14324 | consumed samples: 332800 | consumed tokens: 681574400 | elapsed time per iteration (s): 0.42 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 3.837643E+00 | grad norm: 0.581 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.089 | TFLOPs: 31.80 | +7: iteration 1310/ 14324 | consumed samples: 335360 | consumed tokens: 686817280 | elapsed time per iteration (s): 0.43 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 3.820882E+00 | grad norm: 0.566 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 589.699 | TFLOPs: 30.94 | +7: iteration 1320/ 14324 | consumed samples: 337920 | consumed tokens: 692060160 | elapsed time per iteration (s): 0.44 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 3.811187E+00 | grad norm: 0.488 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 578.982 | TFLOPs: 30.38 | +7: iteration 1330/ 14324 | consumed samples: 340480 | consumed tokens: 697303040 | elapsed time per iteration (s): 0.45 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 3.783651E+00 | grad norm: 0.582 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 565.261 | TFLOPs: 29.66 | +7: iteration 1340/ 14324 | consumed samples: 343040 | consumed tokens: 702545920 | elapsed time per iteration (s): 0.43 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 3.791051E+00 | grad norm: 0.706 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.851 | TFLOPs: 31.32 | +7: iteration 1350/ 14324 | consumed samples: 345600 | consumed tokens: 707788800 | elapsed time per iteration (s): 0.43 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 3.794314E+00 | grad norm: 0.513 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.942 | TFLOPs: 31.27 | +7: iteration 1360/ 14324 | consumed samples: 348160 | consumed tokens: 713031680 | elapsed time per iteration (s): 0.43 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 3.787227E+00 | grad norm: 0.534 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.985 | TFLOPs: 31.27 | +7: iteration 1370/ 14324 | consumed samples: 350720 | consumed tokens: 718274560 | elapsed time per iteration (s): 0.43 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 3.767420E+00 | grad norm: 0.534 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.537 | TFLOPs: 31.35 | +7: iteration 1380/ 14324 | consumed samples: 353280 | consumed tokens: 723517440 | elapsed time per iteration (s): 0.43 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 3.760913E+00 | grad norm: 0.528 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.510 | TFLOPs: 31.40 | +7: iteration 1390/ 14324 | consumed samples: 355840 | consumed tokens: 728760320 | elapsed time per iteration (s): 0.43 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 3.754408E+00 | grad norm: 0.483 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.862 | TFLOPs: 31.53 | +7: iteration 1400/ 14324 | consumed samples: 358400 | consumed tokens: 734003200 | elapsed time per iteration (s): 0.43 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 3.772121E+00 | grad norm: 0.496 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.683 | TFLOPs: 31.20 | +7: iteration 1410/ 14324 | consumed samples: 360960 | consumed tokens: 739246080 | elapsed time per iteration (s): 0.42 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 3.757542E+00 | grad norm: 0.592 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.576 | TFLOPs: 31.67 | +7: iteration 1420/ 14324 | consumed samples: 363520 | consumed tokens: 744488960 | elapsed time per iteration (s): 0.43 | learning rate: 1.964E-04 | global batch size: 256 | lm loss: 3.741103E+00 | grad norm: 0.602 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.312 | TFLOPs: 31.18 | +7: iteration 1430/ 14324 | consumed samples: 366080 | consumed tokens: 749731840 | elapsed time per iteration (s): 0.43 | learning rate: 1.964E-04 | global batch size: 256 | lm loss: 3.783820E+00 | grad norm: 0.596 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.428 | TFLOPs: 31.14 | +7: iteration 1440/ 14324 | consumed samples: 368640 | consumed tokens: 754974720 | elapsed time per iteration (s): 0.42 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 3.737782E+00 | grad norm: 0.460 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.213 | TFLOPs: 31.91 | +7: iteration 1450/ 14324 | consumed samples: 371200 | consumed tokens: 760217600 | elapsed time per iteration (s): 0.43 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 3.757740E+00 | grad norm: 0.495 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.971 | TFLOPs: 31.22 | +7: iteration 1460/ 14324 | consumed samples: 373760 | consumed tokens: 765460480 | elapsed time per iteration (s): 0.42 | learning rate: 1.962E-04 | global batch size: 256 | lm loss: 3.736554E+00 | grad norm: 0.525 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.749 | TFLOPs: 31.63 | +7: iteration 1470/ 14324 | consumed samples: 376320 | consumed tokens: 770703360 | elapsed time per iteration (s): 0.43 | learning rate: 1.961E-04 | global batch size: 256 | lm loss: 3.751579E+00 | grad norm: 0.540 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.757 | TFLOPs: 31.26 | +7: iteration 1480/ 14324 | consumed samples: 378880 | consumed tokens: 775946240 | elapsed time per iteration (s): 0.43 | learning rate: 1.961E-04 | global batch size: 256 | lm loss: 3.757042E+00 | grad norm: 0.488 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.541 | TFLOPs: 31.56 | +7: iteration 1490/ 14324 | consumed samples: 381440 | consumed tokens: 781189120 | elapsed time per iteration (s): 0.42 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 3.704702E+00 | grad norm: 0.853 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.418 | TFLOPs: 31.61 | +7: iteration 1500/ 14324 | consumed samples: 384000 | consumed tokens: 786432000 | elapsed time per iteration (s): 0.42 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 3.729167E+00 | grad norm: 0.588 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.001 | TFLOPs: 31.80 | +7: iteration 1510/ 14324 | consumed samples: 386560 | consumed tokens: 791674880 | elapsed time per iteration (s): 0.43 | learning rate: 1.959E-04 | global batch size: 256 | lm loss: 3.737273E+00 | grad norm: 0.436 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.209 | TFLOPs: 31.60 | +7: iteration 1520/ 14324 | consumed samples: 389120 | consumed tokens: 796917760 | elapsed time per iteration (s): 0.42 | learning rate: 1.958E-04 | global batch size: 256 | lm loss: 3.707175E+00 | grad norm: 0.476 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.622 | TFLOPs: 31.78 | +7: iteration 1530/ 14324 | consumed samples: 391680 | consumed tokens: 802160640 | elapsed time per iteration (s): 0.44 | learning rate: 1.958E-04 | global batch size: 256 | lm loss: 3.692383E+00 | grad norm: 0.464 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 579.648 | TFLOPs: 30.41 | +7: iteration 1540/ 14324 | consumed samples: 394240 | consumed tokens: 807403520 | elapsed time per iteration (s): 0.43 | learning rate: 1.957E-04 | global batch size: 256 | lm loss: 3.728715E+00 | grad norm: 0.406 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.821 | TFLOPs: 31.21 | +7: iteration 1550/ 14324 | consumed samples: 396800 | consumed tokens: 812646400 | elapsed time per iteration (s): 0.44 | learning rate: 1.957E-04 | global batch size: 256 | lm loss: 3.686240E+00 | grad norm: 0.447 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 575.769 | TFLOPs: 30.21 | +7: iteration 1560/ 14324 | consumed samples: 399360 | consumed tokens: 817889280 | elapsed time per iteration (s): 0.44 | learning rate: 1.956E-04 | global batch size: 256 | lm loss: 3.681274E+00 | grad norm: 0.671 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 579.959 | TFLOPs: 30.43 | +7: iteration 1570/ 14324 | consumed samples: 401920 | consumed tokens: 823132160 | elapsed time per iteration (s): 0.42 | learning rate: 1.955E-04 | global batch size: 256 | lm loss: 3.679758E+00 | grad norm: 0.495 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.644 | TFLOPs: 31.72 | +7: iteration 1580/ 14324 | consumed samples: 404480 | consumed tokens: 828375040 | elapsed time per iteration (s): 0.42 | learning rate: 1.955E-04 | global batch size: 256 | lm loss: 3.655305E+00 | grad norm: 0.491 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 615.035 | TFLOPs: 32.27 | +7: iteration 1590/ 14324 | consumed samples: 407040 | consumed tokens: 833617920 | elapsed time per iteration (s): 0.43 | learning rate: 1.954E-04 | global batch size: 256 | lm loss: 3.658696E+00 | grad norm: 0.436 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.139 | TFLOPs: 31.49 | +7: iteration 1600/ 14324 | consumed samples: 409600 | consumed tokens: 838860800 | elapsed time per iteration (s): 0.43 | learning rate: 1.954E-04 | global batch size: 256 | lm loss: 3.698860E+00 | grad norm: 0.744 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.776 | TFLOPs: 31.15 | +7: iteration 1610/ 14324 | consumed samples: 412160 | consumed tokens: 844103680 | elapsed time per iteration (s): 0.42 | learning rate: 1.953E-04 | global batch size: 256 | lm loss: 3.671489E+00 | grad norm: 0.510 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.509 | TFLOPs: 31.82 | +7: iteration 1620/ 14324 | consumed samples: 414720 | consumed tokens: 849346560 | elapsed time per iteration (s): 0.44 | learning rate: 1.952E-04 | global batch size: 256 | lm loss: 3.683220E+00 | grad norm: 0.512 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 586.346 | TFLOPs: 30.76 | +7: iteration 1630/ 14324 | consumed samples: 417280 | consumed tokens: 854589440 | elapsed time per iteration (s): 0.42 | learning rate: 1.952E-04 | global batch size: 256 | lm loss: 3.685461E+00 | grad norm: 0.630 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.661 | TFLOPs: 31.83 | +7: iteration 1640/ 14324 | consumed samples: 419840 | consumed tokens: 859832320 | elapsed time per iteration (s): 0.43 | learning rate: 1.951E-04 | global batch size: 256 | lm loss: 3.670814E+00 | grad norm: 0.514 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.502 | TFLOPs: 31.35 | +7: iteration 1650/ 14324 | consumed samples: 422400 | consumed tokens: 865075200 | elapsed time per iteration (s): 0.43 | learning rate: 1.950E-04 | global batch size: 256 | lm loss: 3.674860E+00 | grad norm: 0.465 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.946 | TFLOPs: 31.58 | +7: iteration 1660/ 14324 | consumed samples: 424960 | consumed tokens: 870318080 | elapsed time per iteration (s): 0.44 | learning rate: 1.950E-04 | global batch size: 256 | lm loss: 3.669577E+00 | grad norm: 0.445 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 582.048 | TFLOPs: 30.54 | +7: iteration 1670/ 14324 | consumed samples: 427520 | consumed tokens: 875560960 | elapsed time per iteration (s): 0.44 | learning rate: 1.949E-04 | global batch size: 256 | lm loss: 3.659756E+00 | grad norm: 0.431 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 580.515 | TFLOPs: 30.46 | +7: iteration 1680/ 14324 | consumed samples: 430080 | consumed tokens: 880803840 | elapsed time per iteration (s): 0.47 | learning rate: 1.948E-04 | global batch size: 256 | lm loss: 3.635770E+00 | grad norm: 0.463 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 548.905 | TFLOPs: 28.80 | +7: iteration 1690/ 14324 | consumed samples: 432640 | consumed tokens: 886046720 | elapsed time per iteration (s): 0.43 | learning rate: 1.948E-04 | global batch size: 256 | lm loss: 3.670488E+00 | grad norm: 0.445 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.726 | TFLOPs: 31.05 | +7: iteration 1700/ 14324 | consumed samples: 435200 | consumed tokens: 891289600 | elapsed time per iteration (s): 0.42 | learning rate: 1.947E-04 | global batch size: 256 | lm loss: 3.630769E+00 | grad norm: 0.440 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.394 | TFLOPs: 31.87 | +7: iteration 1710/ 14324 | consumed samples: 437760 | consumed tokens: 896532480 | elapsed time per iteration (s): 0.43 | learning rate: 1.946E-04 | global batch size: 256 | lm loss: 3.623450E+00 | grad norm: 0.593 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.845 | TFLOPs: 31.58 | +7: iteration 1720/ 14324 | consumed samples: 440320 | consumed tokens: 901775360 | elapsed time per iteration (s): 0.43 | learning rate: 1.946E-04 | global batch size: 256 | lm loss: 3.654461E+00 | grad norm: 0.429 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.790 | TFLOPs: 31.05 | +7: iteration 1730/ 14324 | consumed samples: 442880 | consumed tokens: 907018240 | elapsed time per iteration (s): 0.42 | learning rate: 1.945E-04 | global batch size: 256 | lm loss: 3.629346E+00 | grad norm: 0.510 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.877 | TFLOPs: 31.84 | +7: iteration 1740/ 14324 | consumed samples: 445440 | consumed tokens: 912261120 | elapsed time per iteration (s): 0.42 | learning rate: 1.944E-04 | global batch size: 256 | lm loss: 3.642129E+00 | grad norm: 0.441 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 613.958 | TFLOPs: 32.21 | +7: iteration 1750/ 14324 | consumed samples: 448000 | consumed tokens: 917504000 | elapsed time per iteration (s): 0.44 | learning rate: 1.944E-04 | global batch size: 256 | lm loss: 3.647807E+00 | grad norm: 0.559 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 586.461 | TFLOPs: 30.77 | +7: iteration 1760/ 14324 | consumed samples: 450560 | consumed tokens: 922746880 | elapsed time per iteration (s): 0.42 | learning rate: 1.943E-04 | global batch size: 256 | lm loss: 3.601088E+00 | grad norm: 0.442 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.473 | TFLOPs: 31.77 | +7: iteration 1770/ 14324 | consumed samples: 453120 | consumed tokens: 927989760 | elapsed time per iteration (s): 0.45 | learning rate: 1.942E-04 | global batch size: 256 | lm loss: 3.622975E+00 | grad norm: 0.491 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 567.122 | TFLOPs: 29.76 | +7: iteration 1780/ 14324 | consumed samples: 455680 | consumed tokens: 933232640 | elapsed time per iteration (s): 0.43 | learning rate: 1.941E-04 | global batch size: 256 | lm loss: 3.616568E+00 | grad norm: 0.403 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.797 | TFLOPs: 31.52 | +7: iteration 1790/ 14324 | consumed samples: 458240 | consumed tokens: 938475520 | elapsed time per iteration (s): 0.43 | learning rate: 1.941E-04 | global batch size: 256 | lm loss: 3.620137E+00 | grad norm: 0.431 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.855 | TFLOPs: 31.32 | +7: iteration 1800/ 14324 | consumed samples: 460800 | consumed tokens: 943718400 | elapsed time per iteration (s): 0.43 | learning rate: 1.940E-04 | global batch size: 256 | lm loss: 3.629769E+00 | grad norm: 0.542 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 588.698 | TFLOPs: 30.89 | +7: iteration 1810/ 14324 | consumed samples: 463360 | consumed tokens: 948961280 | elapsed time per iteration (s): 0.43 | learning rate: 1.939E-04 | global batch size: 256 | lm loss: 3.614172E+00 | grad norm: 0.547 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.109 | TFLOPs: 31.07 | +7: iteration 1820/ 14324 | consumed samples: 465920 | consumed tokens: 954204160 | elapsed time per iteration (s): 0.44 | learning rate: 1.939E-04 | global batch size: 256 | lm loss: 3.600595E+00 | grad norm: 0.501 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 581.927 | TFLOPs: 30.53 | +7: iteration 1830/ 14324 | consumed samples: 468480 | consumed tokens: 959447040 | elapsed time per iteration (s): 0.43 | learning rate: 1.938E-04 | global batch size: 256 | lm loss: 3.643715E+00 | grad norm: 0.422 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 589.823 | TFLOPs: 30.95 | +7: iteration 1840/ 14324 | consumed samples: 471040 | consumed tokens: 964689920 | elapsed time per iteration (s): 0.43 | learning rate: 1.937E-04 | global batch size: 256 | lm loss: 3.615316E+00 | grad norm: 0.463 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.051 | TFLOPs: 31.06 | +7: iteration 1850/ 14324 | consumed samples: 473600 | consumed tokens: 969932800 | elapsed time per iteration (s): 0.43 | learning rate: 1.936E-04 | global batch size: 256 | lm loss: 3.623838E+00 | grad norm: 0.716 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.158 | TFLOPs: 31.49 | +7: iteration 1860/ 14324 | consumed samples: 476160 | consumed tokens: 975175680 | elapsed time per iteration (s): 0.43 | learning rate: 1.936E-04 | global batch size: 256 | lm loss: 3.637210E+00 | grad norm: 0.657 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.509 | TFLOPs: 31.09 | +7: iteration 1870/ 14324 | consumed samples: 478720 | consumed tokens: 980418560 | elapsed time per iteration (s): 0.43 | learning rate: 1.935E-04 | global batch size: 256 | lm loss: 3.583680E+00 | grad norm: 0.529 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.161 | TFLOPs: 31.33 | +7: iteration 1880/ 14324 | consumed samples: 481280 | consumed tokens: 985661440 | elapsed time per iteration (s): 0.43 | learning rate: 1.934E-04 | global batch size: 256 | lm loss: 3.582554E+00 | grad norm: 0.416 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.205 | TFLOPs: 31.33 | +7: iteration 1890/ 14324 | consumed samples: 483840 | consumed tokens: 990904320 | elapsed time per iteration (s): 0.42 | learning rate: 1.933E-04 | global batch size: 256 | lm loss: 3.598412E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.286 | TFLOPs: 31.65 | +7: iteration 1900/ 14324 | consumed samples: 486400 | consumed tokens: 996147200 | elapsed time per iteration (s): 0.43 | learning rate: 1.933E-04 | global batch size: 256 | lm loss: 3.587650E+00 | grad norm: 0.408 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.325 | TFLOPs: 31.29 | +7: iteration 1910/ 14324 | consumed samples: 488960 | consumed tokens: 1001390080 | elapsed time per iteration (s): 0.43 | learning rate: 1.932E-04 | global batch size: 256 | lm loss: 3.598455E+00 | grad norm: 0.421 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 589.360 | TFLOPs: 30.92 | +7: iteration 1920/ 14324 | consumed samples: 491520 | consumed tokens: 1006632960 | elapsed time per iteration (s): 0.42 | learning rate: 1.931E-04 | global batch size: 256 | lm loss: 3.558314E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.627 | TFLOPs: 31.62 | +7: iteration 1930/ 14324 | consumed samples: 494080 | consumed tokens: 1011875840 | elapsed time per iteration (s): 0.43 | learning rate: 1.930E-04 | global batch size: 256 | lm loss: 3.569261E+00 | grad norm: 0.554 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.001 | TFLOPs: 31.48 | +7: iteration 1940/ 14324 | consumed samples: 496640 | consumed tokens: 1017118720 | elapsed time per iteration (s): 0.43 | learning rate: 1.930E-04 | global batch size: 256 | lm loss: 3.591293E+00 | grad norm: 0.428 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.431 | TFLOPs: 31.19 | +7: iteration 1950/ 14324 | consumed samples: 499200 | consumed tokens: 1022361600 | elapsed time per iteration (s): 0.43 | learning rate: 1.929E-04 | global batch size: 256 | lm loss: 3.598298E+00 | grad norm: 0.539 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 590.041 | TFLOPs: 30.96 | +7: iteration 1960/ 14324 | consumed samples: 501760 | consumed tokens: 1027604480 | elapsed time per iteration (s): 0.43 | learning rate: 1.928E-04 | global batch size: 256 | lm loss: 3.597366E+00 | grad norm: 0.559 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.790 | TFLOPs: 31.26 | +7: iteration 1970/ 14324 | consumed samples: 504320 | consumed tokens: 1032847360 | elapsed time per iteration (s): 0.43 | learning rate: 1.927E-04 | global batch size: 256 | lm loss: 3.594104E+00 | grad norm: 0.421 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.675 | TFLOPs: 31.04 | +7: iteration 1980/ 14324 | consumed samples: 506880 | consumed tokens: 1038090240 | elapsed time per iteration (s): 0.43 | learning rate: 1.927E-04 | global batch size: 256 | lm loss: 3.568533E+00 | grad norm: 0.390 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.330 | TFLOPs: 31.24 | +7: iteration 1990/ 14324 | consumed samples: 509440 | consumed tokens: 1043333120 | elapsed time per iteration (s): 0.43 | learning rate: 1.926E-04 | global batch size: 256 | lm loss: 3.559230E+00 | grad norm: 0.425 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.016 | TFLOPs: 31.38 | +0: [2022-11-29 22:14:42,793] [INFO] [logging.py:68:log_dist] [Rank 0] step=2000, skipped=0, lr=[0.00019249276153319805, 0.00019249276153319805, 0.00019249276153319805], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 2000/ 14324 | consumed samples: 512000 | consumed tokens: 1048576000 | elapsed time per iteration (s): 0.43 | learning rate: 1.925E-04 | global batch size: 256 | lm loss: 3.569216E+00 | grad norm: 0.433 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.540 | TFLOPs: 31.56 | +0: steps: 2000 loss: 3.5596 iter time (s): 0.437 samples/sec: 586.394 +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 2000 | lm loss value: 3.463711E+00 | lm loss PPL: 3.193528E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 2000 to checkpoints_220moscar +0: [2022-11-29 22:14:42,965] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step2000 is begin to save! +0: [2022-11-29 22:14:42,968] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/layer_01-model_00-model_states.pt... +0: [2022-11-29 22:14:43,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/layer_01-model_00-model_states.pt. +0: [2022-11-29 22:14:43,071] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/layer_03-model_00-model_states.pt... +0: [2022-11-29 22:14:43,093] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/layer_03-model_00-model_states.pt. +0: [2022-11-29 22:14:43,093] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/layer_04-model_00-model_states.pt... +0: [2022-11-29 22:14:43,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/layer_04-model_00-model_states.pt. +0: [2022-11-29 22:14:43,115] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/layer_05-model_00-model_states.pt... +0: [2022-11-29 22:14:43,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/layer_05-model_00-model_states.pt. +0: [2022-11-29 22:14:43,140] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/layer_06-model_00-model_states.pt... +0: [2022-11-29 22:14:43,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/layer_06-model_00-model_states.pt. +0: [2022-11-29 22:14:43,164] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/layer_07-model_00-model_states.pt... +0: [2022-11-29 22:14:43,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/layer_07-model_00-model_states.pt. +0: [2022-11-29 22:14:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/layer_08-model_00-model_states.pt... +0: [2022-11-29 22:14:43,214] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/layer_08-model_00-model_states.pt. +0: [2022-11-29 22:14:43,214] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/layer_09-model_00-model_states.pt... +0: [2022-11-29 22:14:43,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/layer_09-model_00-model_states.pt. +0: [2022-11-29 22:14:43,238] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/layer_10-model_00-model_states.pt... +0: [2022-11-29 22:14:43,261] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/layer_10-model_00-model_states.pt. +0: [2022-11-29 22:14:43,261] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/layer_11-model_00-model_states.pt... +0: [2022-11-29 22:14:43,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/layer_11-model_00-model_states.pt. +0: [2022-11-29 22:14:43,286] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/layer_12-model_00-model_states.pt... +0: [2022-11-29 22:14:43,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/layer_12-model_00-model_states.pt. +0: [2022-11-29 22:14:43,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/layer_13-model_00-model_states.pt... +0: [2022-11-29 22:14:43,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/layer_13-model_00-model_states.pt. +0: [2022-11-29 22:14:43,334] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/layer_14-model_00-model_states.pt... +0: [2022-11-29 22:14:43,357] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/layer_14-model_00-model_states.pt. +0: [2022-11-29 22:14:43,358] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/layer_15-model_00-model_states.pt... +0: [2022-11-29 22:14:43,381] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/layer_15-model_00-model_states.pt. +0: [2022-11-29 22:14:43,381] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/layer_16-model_00-model_states.pt... +0: [2022-11-29 22:14:43,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/layer_16-model_00-model_states.pt. +0: [2022-11-29 22:14:43,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/layer_17-model_00-model_states.pt... +0: [2022-11-29 22:14:43,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/layer_17-model_00-model_states.pt. +0: [2022-11-29 22:14:43,429] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/layer_18-model_00-model_states.pt... +0: [2022-11-29 22:14:43,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/layer_18-model_00-model_states.pt. +0: [2022-11-29 22:14:43,452] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/layer_19-model_00-model_states.pt... +0: [2022-11-29 22:14:43,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/layer_19-model_00-model_states.pt. +0: [2022-11-29 22:14:43,475] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/layer_20-model_00-model_states.pt... +0: [2022-11-29 22:14:43,498] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/layer_20-model_00-model_states.pt. +0: [2022-11-29 22:14:43,498] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/layer_22-model_00-model_states.pt... +0: [2022-11-29 22:14:43,502] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/layer_22-model_00-model_states.pt. +0: [2022-11-29 22:14:43,503] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_220moscar/global_step2000/mp_rank_00_model_states.pt +0: [2022-11-29 22:14:43,503] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/mp_rank_00_model_states.pt... +0: [2022-11-29 22:14:43,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/mp_rank_00_model_states.pt. +0: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:14:43,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:14:43,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:14:43,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 22:14:43,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 22:14:43,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:14:43,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 22:14:43,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 22:14:43,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:14:43,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 22:14:43,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 22:14:43,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:14:43,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:14:43,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:14:43,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +7: [2022-11-29 22:14:43,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +4: [2022-11-29 22:14:43,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +7: [2022-11-29 22:14:43,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 22:14:43,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 22:14:43,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 22:14:43,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:14:43,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 22:14:43,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 22:14:43,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:14:43,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 22:14:43,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 22:14:43,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:14:43,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:14:43,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 22:14:43,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 22:14:43,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 22:14:43,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:14:43,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 22:14:43,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:14:43,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +3: [2022-11-29 22:14:43,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:14:43,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 22:14:43,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:14:43,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 22:14:43,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 22:14:43,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 22:14:43,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 22:14:43,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:14:43,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 22:14:43,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 22:14:43,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:14:43,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:14:43,575] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 22:14:43,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 22:14:43,575] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 22:14:43,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 22:14:43,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:14:43,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:14:43,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:14:43,575] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 22:14:43,575] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 22:14:43,575] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 22:14:43,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 22:14:43,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 22:14:43,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 22:14:43,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:14:43,576] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 22:14:43,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 22:14:43,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:14:43,576] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 22:14:43,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 22:14:43,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:14:43,576] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 22:14:43,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 22:14:43,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:14:43,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +5: [2022-11-29 22:14:43,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 22:14:43,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 22:14:43,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:14:43,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 22:14:43,575] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +3: [2022-11-29 22:14:43,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:14:43,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:14:43,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:14:43,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 22:14:43,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:14:43,575] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 22:14:43,575] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 22:14:43,575] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +3: [2022-11-29 22:14:43,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +5: [2022-11-29 22:14:43,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 22:14:43,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 22:14:43,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 22:14:43,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 22:14:43,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:14:43,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +1: [2022-11-29 22:14:43,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:14:43,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +7: [2022-11-29 22:14:43,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 22:14:43,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 22:14:43,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:14:43,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:14:43,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 22:14:43,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 22:14:43,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:14:43,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:14:43,578] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 22:14:43,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:14:43,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 22:14:43,578] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 22:14:43,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 22:14:43,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:14:43,578] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 22:14:43,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 22:14:43,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:14:43,578] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 22:14:43,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 22:14:43,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:14:43,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:14:43,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +7: [2022-11-29 22:14:43,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +6: [2022-11-29 22:14:43,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:14:43,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 22:14:43,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 22:14:43,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 22:14:43,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 22:14:43,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:14:43,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 22:14:43,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 22:14:43,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:14:43,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 22:14:43,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 22:14:43,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:14:43,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 22:14:43,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 22:14:43,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:14:43,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 22:14:43,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 22:14:43,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:14:43,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 22:14:43,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 22:14:43,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:14:43,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 22:14:43,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 22:14:43,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:14:43,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +7: [2022-11-29 22:14:43,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:14:43,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 22:14:43,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 22:14:43,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 22:14:43,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:14:43,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 22:14:43,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 22:14:43,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:14:43,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:14:43,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:14:43,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:14:43,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 22:14:43,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 22:14:43,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 22:14:43,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 22:14:43,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 22:14:43,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 22:14:43,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 22:14:43,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 22:14:43,578] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 22:14:43,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 22:14:43,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:14:43,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 22:14:43,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 22:14:43,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:14:43,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 22:14:43,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 22:14:43,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:14:43,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 22:14:43,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 22:14:43,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:14:43,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:14:43,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 22:14:43,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 22:14:43,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:14:43,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:14:43,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 22:14:43,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 22:14:43,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 22:14:43,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 22:14:43,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:14:43,588] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 22:14:43,588] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 22:14:43,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 22:14:43,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 22:14:43,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:14:43,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 22:14:43,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 22:14:43,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:14:43,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 22:14:43,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 22:14:43,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 22:14:43,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: successfully saved checkpoint at iteration 2000 to checkpoints_220moscar +7: time (ms) | save-checkpoint: 671.65 +7: iteration 2010/ 14324 | consumed samples: 514560 | consumed tokens: 1053818880 | elapsed time per iteration (s): 0.51 | learning rate: 1.924E-04 | global batch size: 256 | lm loss: 3.547463E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 501.473 | TFLOPs: 26.31 | +7: iteration 2020/ 14324 | consumed samples: 517120 | consumed tokens: 1059061760 | elapsed time per iteration (s): 0.43 | learning rate: 1.923E-04 | global batch size: 256 | lm loss: 3.549597E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.387 | TFLOPs: 31.03 | +7: iteration 2030/ 14324 | consumed samples: 519680 | consumed tokens: 1064304640 | elapsed time per iteration (s): 0.42 | learning rate: 1.923E-04 | global batch size: 256 | lm loss: 3.564291E+00 | grad norm: 0.552 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.580 | TFLOPs: 31.72 | +7: iteration 2040/ 14324 | consumed samples: 522240 | consumed tokens: 1069547520 | elapsed time per iteration (s): 0.43 | learning rate: 1.922E-04 | global batch size: 256 | lm loss: 3.534288E+00 | grad norm: 0.465 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.157 | TFLOPs: 31.59 | +7: iteration 2050/ 14324 | consumed samples: 524800 | consumed tokens: 1074790400 | elapsed time per iteration (s): 0.44 | learning rate: 1.921E-04 | global batch size: 256 | lm loss: 3.536427E+00 | grad norm: 0.430 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 585.208 | TFLOPs: 30.70 | +7: iteration 2060/ 14324 | consumed samples: 527360 | consumed tokens: 1080033280 | elapsed time per iteration (s): 0.43 | learning rate: 1.920E-04 | global batch size: 256 | lm loss: 3.539775E+00 | grad norm: 0.458 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.572 | TFLOPs: 31.20 | +7: iteration 2070/ 14324 | consumed samples: 529920 | consumed tokens: 1085276160 | elapsed time per iteration (s): 0.42 | learning rate: 1.919E-04 | global batch size: 256 | lm loss: 3.518382E+00 | grad norm: 0.377 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.684 | TFLOPs: 31.78 | +7: iteration 2080/ 14324 | consumed samples: 532480 | consumed tokens: 1090519040 | elapsed time per iteration (s): 0.43 | learning rate: 1.918E-04 | global batch size: 256 | lm loss: 3.525445E+00 | grad norm: 0.423 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.624 | TFLOPs: 31.51 | +7: iteration 2090/ 14324 | consumed samples: 535040 | consumed tokens: 1095761920 | elapsed time per iteration (s): 0.43 | learning rate: 1.918E-04 | global batch size: 256 | lm loss: 3.503754E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.827 | TFLOPs: 31.10 | +7: iteration 2100/ 14324 | consumed samples: 537600 | consumed tokens: 1101004800 | elapsed time per iteration (s): 0.43 | learning rate: 1.917E-04 | global batch size: 256 | lm loss: 3.529844E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.104 | TFLOPs: 31.49 | +7: iteration 2110/ 14324 | consumed samples: 540160 | consumed tokens: 1106247680 | elapsed time per iteration (s): 0.43 | learning rate: 1.916E-04 | global batch size: 256 | lm loss: 3.542576E+00 | grad norm: 0.447 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.993 | TFLOPs: 31.43 | +7: iteration 2120/ 14324 | consumed samples: 542720 | consumed tokens: 1111490560 | elapsed time per iteration (s): 0.42 | learning rate: 1.915E-04 | global batch size: 256 | lm loss: 3.520194E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.590 | TFLOPs: 31.67 | +7: iteration 2130/ 14324 | consumed samples: 545280 | consumed tokens: 1116733440 | elapsed time per iteration (s): 0.42 | learning rate: 1.914E-04 | global batch size: 256 | lm loss: 3.511411E+00 | grad norm: 0.392 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.273 | TFLOPs: 31.65 | +7: iteration 2140/ 14324 | consumed samples: 547840 | consumed tokens: 1121976320 | elapsed time per iteration (s): 0.42 | learning rate: 1.913E-04 | global batch size: 256 | lm loss: 3.525777E+00 | grad norm: 0.420 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.396 | TFLOPs: 31.66 | +7: iteration 2150/ 14324 | consumed samples: 550400 | consumed tokens: 1127219200 | elapsed time per iteration (s): 0.43 | learning rate: 1.913E-04 | global batch size: 256 | lm loss: 3.519028E+00 | grad norm: 0.450 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.431 | TFLOPs: 31.40 | +7: iteration 2160/ 14324 | consumed samples: 552960 | consumed tokens: 1132462080 | elapsed time per iteration (s): 0.42 | learning rate: 1.912E-04 | global batch size: 256 | lm loss: 3.539582E+00 | grad norm: 0.430 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.328 | TFLOPs: 32.08 | +7: iteration 2170/ 14324 | consumed samples: 555520 | consumed tokens: 1137704960 | elapsed time per iteration (s): 0.43 | learning rate: 1.911E-04 | global batch size: 256 | lm loss: 3.515117E+00 | grad norm: 0.412 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.178 | TFLOPs: 31.12 | +7: iteration 2180/ 14324 | consumed samples: 558080 | consumed tokens: 1142947840 | elapsed time per iteration (s): 0.43 | learning rate: 1.910E-04 | global batch size: 256 | lm loss: 3.514349E+00 | grad norm: 0.419 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 590.630 | TFLOPs: 30.99 | +7: iteration 2190/ 14324 | consumed samples: 560640 | consumed tokens: 1148190720 | elapsed time per iteration (s): 0.45 | learning rate: 1.909E-04 | global batch size: 256 | lm loss: 3.508955E+00 | grad norm: 0.460 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 574.566 | TFLOPs: 30.15 | +7: iteration 2200/ 14324 | consumed samples: 563200 | consumed tokens: 1153433600 | elapsed time per iteration (s): 0.42 | learning rate: 1.908E-04 | global batch size: 256 | lm loss: 3.502284E+00 | grad norm: 0.397 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 613.936 | TFLOPs: 32.21 | +7: iteration 2210/ 14324 | consumed samples: 565760 | consumed tokens: 1158676480 | elapsed time per iteration (s): 0.43 | learning rate: 1.907E-04 | global batch size: 256 | lm loss: 3.505446E+00 | grad norm: 0.421 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.428 | TFLOPs: 31.56 | +7: iteration 2220/ 14324 | consumed samples: 568320 | consumed tokens: 1163919360 | elapsed time per iteration (s): 0.43 | learning rate: 1.906E-04 | global batch size: 256 | lm loss: 3.509277E+00 | grad norm: 0.424 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.151 | TFLOPs: 31.59 | +7: iteration 2230/ 14324 | consumed samples: 570880 | consumed tokens: 1169162240 | elapsed time per iteration (s): 0.43 | learning rate: 1.906E-04 | global batch size: 256 | lm loss: 3.495916E+00 | grad norm: 0.424 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.700 | TFLOPs: 31.15 | +7: iteration 2240/ 14324 | consumed samples: 573440 | consumed tokens: 1174405120 | elapsed time per iteration (s): 0.45 | learning rate: 1.905E-04 | global batch size: 256 | lm loss: 3.514404E+00 | grad norm: 0.429 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 569.868 | TFLOPs: 29.90 | +7: iteration 2250/ 14324 | consumed samples: 576000 | consumed tokens: 1179648000 | elapsed time per iteration (s): 0.43 | learning rate: 1.904E-04 | global batch size: 256 | lm loss: 3.505566E+00 | grad norm: 0.475 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.105 | TFLOPs: 31.54 | +7: iteration 2260/ 14324 | consumed samples: 578560 | consumed tokens: 1184890880 | elapsed time per iteration (s): 0.44 | learning rate: 1.903E-04 | global batch size: 256 | lm loss: 3.489034E+00 | grad norm: 0.431 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 581.351 | TFLOPs: 30.50 | +7: iteration 2270/ 14324 | consumed samples: 581120 | consumed tokens: 1190133760 | elapsed time per iteration (s): 0.46 | learning rate: 1.902E-04 | global batch size: 256 | lm loss: 3.484706E+00 | grad norm: 0.380 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 558.935 | TFLOPs: 29.33 | +7: iteration 2280/ 14324 | consumed samples: 583680 | consumed tokens: 1195376640 | elapsed time per iteration (s): 0.43 | learning rate: 1.901E-04 | global batch size: 256 | lm loss: 3.495588E+00 | grad norm: 0.479 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 589.772 | TFLOPs: 30.94 | +7: iteration 2290/ 14324 | consumed samples: 586240 | consumed tokens: 1200619520 | elapsed time per iteration (s): 0.44 | learning rate: 1.900E-04 | global batch size: 256 | lm loss: 3.504348E+00 | grad norm: 0.390 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 579.271 | TFLOPs: 30.39 | +7: iteration 2300/ 14324 | consumed samples: 588800 | consumed tokens: 1205862400 | elapsed time per iteration (s): 0.42 | learning rate: 1.899E-04 | global batch size: 256 | lm loss: 3.472914E+00 | grad norm: 0.396 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.540 | TFLOPs: 31.77 | +7: iteration 2310/ 14324 | consumed samples: 591360 | consumed tokens: 1211105280 | elapsed time per iteration (s): 0.43 | learning rate: 1.898E-04 | global batch size: 256 | lm loss: 3.482693E+00 | grad norm: 0.410 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.211 | TFLOPs: 31.49 | +7: iteration 2320/ 14324 | consumed samples: 593920 | consumed tokens: 1216348160 | elapsed time per iteration (s): 0.43 | learning rate: 1.897E-04 | global batch size: 256 | lm loss: 3.467679E+00 | grad norm: 0.449 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.786 | TFLOPs: 31.05 | +7: iteration 2330/ 14324 | consumed samples: 596480 | consumed tokens: 1221591040 | elapsed time per iteration (s): 0.44 | learning rate: 1.896E-04 | global batch size: 256 | lm loss: 3.493863E+00 | grad norm: 0.388 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 586.512 | TFLOPs: 30.77 | +7: iteration 2340/ 14324 | consumed samples: 599040 | consumed tokens: 1226833920 | elapsed time per iteration (s): 0.43 | learning rate: 1.896E-04 | global batch size: 256 | lm loss: 3.482226E+00 | grad norm: 0.628 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.454 | TFLOPs: 31.19 | +7: iteration 2350/ 14324 | consumed samples: 601600 | consumed tokens: 1232076800 | elapsed time per iteration (s): 0.44 | learning rate: 1.895E-04 | global batch size: 256 | lm loss: 3.493258E+00 | grad norm: 0.435 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 587.846 | TFLOPs: 30.84 | +7: iteration 2360/ 14324 | consumed samples: 604160 | consumed tokens: 1237319680 | elapsed time per iteration (s): 0.44 | learning rate: 1.894E-04 | global batch size: 256 | lm loss: 3.459473E+00 | grad norm: 0.451 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 582.547 | TFLOPs: 30.57 | +7: iteration 2370/ 14324 | consumed samples: 606720 | consumed tokens: 1242562560 | elapsed time per iteration (s): 0.44 | learning rate: 1.893E-04 | global batch size: 256 | lm loss: 3.439041E+00 | grad norm: 0.551 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 581.092 | TFLOPs: 30.49 | +7: iteration 2380/ 14324 | consumed samples: 609280 | consumed tokens: 1247805440 | elapsed time per iteration (s): 0.43 | learning rate: 1.892E-04 | global batch size: 256 | lm loss: 3.446994E+00 | grad norm: 0.527 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.703 | TFLOPs: 31.52 | +7: iteration 2390/ 14324 | consumed samples: 611840 | consumed tokens: 1253048320 | elapsed time per iteration (s): 0.43 | learning rate: 1.891E-04 | global batch size: 256 | lm loss: 3.488681E+00 | grad norm: 0.387 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.380 | TFLOPs: 31.08 | +7: iteration 2400/ 14324 | consumed samples: 614400 | consumed tokens: 1258291200 | elapsed time per iteration (s): 0.43 | learning rate: 1.890E-04 | global batch size: 256 | lm loss: 3.444908E+00 | grad norm: 0.388 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.175 | TFLOPs: 31.54 | +7: iteration 2410/ 14324 | consumed samples: 616960 | consumed tokens: 1263534080 | elapsed time per iteration (s): 0.43 | learning rate: 1.889E-04 | global batch size: 256 | lm loss: 3.470644E+00 | grad norm: 0.419 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.412 | TFLOPs: 31.29 | +7: iteration 2420/ 14324 | consumed samples: 619520 | consumed tokens: 1268776960 | elapsed time per iteration (s): 0.43 | learning rate: 1.888E-04 | global batch size: 256 | lm loss: 3.445518E+00 | grad norm: 0.397 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.752 | TFLOPs: 31.31 | +7: iteration 2430/ 14324 | consumed samples: 622080 | consumed tokens: 1274019840 | elapsed time per iteration (s): 0.42 | learning rate: 1.887E-04 | global batch size: 256 | lm loss: 3.469636E+00 | grad norm: 0.475 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.534 | TFLOPs: 31.72 | +7: iteration 2440/ 14324 | consumed samples: 624640 | consumed tokens: 1279262720 | elapsed time per iteration (s): 0.43 | learning rate: 1.886E-04 | global batch size: 256 | lm loss: 3.456642E+00 | grad norm: 0.385 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.331 | TFLOPs: 31.18 | +7: iteration 2450/ 14324 | consumed samples: 627200 | consumed tokens: 1284505600 | elapsed time per iteration (s): 0.42 | learning rate: 1.885E-04 | global batch size: 256 | lm loss: 3.468257E+00 | grad norm: 0.586 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.047 | TFLOPs: 32.06 | +7: iteration 2460/ 14324 | consumed samples: 629760 | consumed tokens: 1289748480 | elapsed time per iteration (s): 0.44 | learning rate: 1.884E-04 | global batch size: 256 | lm loss: 3.440135E+00 | grad norm: 0.390 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 588.218 | TFLOPs: 30.86 | +7: iteration 2470/ 14324 | consumed samples: 632320 | consumed tokens: 1294991360 | elapsed time per iteration (s): 0.43 | learning rate: 1.883E-04 | global batch size: 256 | lm loss: 3.459486E+00 | grad norm: 0.389 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.559 | TFLOPs: 31.51 | +7: iteration 2480/ 14324 | consumed samples: 634880 | consumed tokens: 1300234240 | elapsed time per iteration (s): 0.42 | learning rate: 1.882E-04 | global batch size: 256 | lm loss: 3.463569E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.352 | TFLOPs: 31.87 | +7: iteration 2490/ 14324 | consumed samples: 637440 | consumed tokens: 1305477120 | elapsed time per iteration (s): 0.42 | learning rate: 1.881E-04 | global batch size: 256 | lm loss: 3.454350E+00 | grad norm: 0.479 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.561 | TFLOPs: 31.77 | +7: iteration 2500/ 14324 | consumed samples: 640000 | consumed tokens: 1310720000 | elapsed time per iteration (s): 0.43 | learning rate: 1.880E-04 | global batch size: 256 | lm loss: 3.474146E+00 | grad norm: 0.386 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 588.754 | TFLOPs: 30.89 | +7: iteration 2510/ 14324 | consumed samples: 642560 | consumed tokens: 1315962880 | elapsed time per iteration (s): 0.42 | learning rate: 1.879E-04 | global batch size: 256 | lm loss: 3.460573E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 613.182 | TFLOPs: 32.17 | +7: iteration 2520/ 14324 | consumed samples: 645120 | consumed tokens: 1321205760 | elapsed time per iteration (s): 0.42 | learning rate: 1.878E-04 | global batch size: 256 | lm loss: 3.451218E+00 | grad norm: 0.456 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.009 | TFLOPs: 31.95 | +7: iteration 2530/ 14324 | consumed samples: 647680 | consumed tokens: 1326448640 | elapsed time per iteration (s): 0.43 | learning rate: 1.877E-04 | global batch size: 256 | lm loss: 3.440552E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.683 | TFLOPs: 31.25 | +7: iteration 2540/ 14324 | consumed samples: 650240 | consumed tokens: 1331691520 | elapsed time per iteration (s): 0.43 | learning rate: 1.876E-04 | global batch size: 256 | lm loss: 3.438478E+00 | grad norm: 0.420 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.021 | TFLOPs: 31.01 | +7: iteration 2550/ 14324 | consumed samples: 652800 | consumed tokens: 1336934400 | elapsed time per iteration (s): 0.43 | learning rate: 1.875E-04 | global batch size: 256 | lm loss: 3.443509E+00 | grad norm: 0.434 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.657 | TFLOPs: 31.57 | +7: iteration 2560/ 14324 | consumed samples: 655360 | consumed tokens: 1342177280 | elapsed time per iteration (s): 0.43 | learning rate: 1.874E-04 | global batch size: 256 | lm loss: 3.439032E+00 | grad norm: 0.571 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.746 | TFLOPs: 31.57 | +7: iteration 2570/ 14324 | consumed samples: 657920 | consumed tokens: 1347420160 | elapsed time per iteration (s): 0.43 | learning rate: 1.873E-04 | global batch size: 256 | lm loss: 3.439716E+00 | grad norm: 0.409 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.128 | TFLOPs: 31.59 | +7: iteration 2580/ 14324 | consumed samples: 660480 | consumed tokens: 1352663040 | elapsed time per iteration (s): 0.43 | learning rate: 1.872E-04 | global batch size: 256 | lm loss: 3.440791E+00 | grad norm: 0.385 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.014 | TFLOPs: 31.27 | +7: iteration 2590/ 14324 | consumed samples: 663040 | consumed tokens: 1357905920 | elapsed time per iteration (s): 0.43 | learning rate: 1.871E-04 | global batch size: 256 | lm loss: 3.418180E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.168 | TFLOPs: 31.54 | +7: iteration 2600/ 14324 | consumed samples: 665600 | consumed tokens: 1363148800 | elapsed time per iteration (s): 0.42 | learning rate: 1.870E-04 | global batch size: 256 | lm loss: 3.414641E+00 | grad norm: 0.381 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.635 | TFLOPs: 31.88 | +7: iteration 2610/ 14324 | consumed samples: 668160 | consumed tokens: 1368391680 | elapsed time per iteration (s): 0.43 | learning rate: 1.869E-04 | global batch size: 256 | lm loss: 3.417758E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 590.693 | TFLOPs: 30.99 | +7: iteration 2620/ 14324 | consumed samples: 670720 | consumed tokens: 1373634560 | elapsed time per iteration (s): 0.42 | learning rate: 1.868E-04 | global batch size: 256 | lm loss: 3.415976E+00 | grad norm: 0.411 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.641 | TFLOPs: 31.72 | +7: iteration 2630/ 14324 | consumed samples: 673280 | consumed tokens: 1378877440 | elapsed time per iteration (s): 0.43 | learning rate: 1.867E-04 | global batch size: 256 | lm loss: 3.407783E+00 | grad norm: 0.516 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.058 | TFLOPs: 31.59 | +7: iteration 2640/ 14324 | consumed samples: 675840 | consumed tokens: 1384120320 | elapsed time per iteration (s): 0.43 | learning rate: 1.866E-04 | global batch size: 256 | lm loss: 3.435450E+00 | grad norm: 0.389 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.124 | TFLOPs: 31.23 | +7: iteration 2650/ 14324 | consumed samples: 678400 | consumed tokens: 1389363200 | elapsed time per iteration (s): 0.42 | learning rate: 1.865E-04 | global batch size: 256 | lm loss: 3.390852E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.297 | TFLOPs: 31.76 | +7: iteration 2660/ 14324 | consumed samples: 680960 | consumed tokens: 1394606080 | elapsed time per iteration (s): 0.46 | learning rate: 1.864E-04 | global batch size: 256 | lm loss: 3.466567E+00 | grad norm: 0.422 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 560.517 | TFLOPs: 29.41 | +7: iteration 2670/ 14324 | consumed samples: 683520 | consumed tokens: 1399848960 | elapsed time per iteration (s): 0.42 | learning rate: 1.863E-04 | global batch size: 256 | lm loss: 3.422227E+00 | grad norm: 0.435 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.107 | TFLOPs: 31.64 | +7: iteration 2680/ 14324 | consumed samples: 686080 | consumed tokens: 1405091840 | elapsed time per iteration (s): 0.43 | learning rate: 1.862E-04 | global batch size: 256 | lm loss: 3.406109E+00 | grad norm: 0.409 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.877 | TFLOPs: 31.26 | +7: iteration 2690/ 14324 | consumed samples: 688640 | consumed tokens: 1410334720 | elapsed time per iteration (s): 0.42 | learning rate: 1.861E-04 | global batch size: 256 | lm loss: 3.389524E+00 | grad norm: 0.415 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.757 | TFLOPs: 31.63 | +7: iteration 2700/ 14324 | consumed samples: 691200 | consumed tokens: 1415577600 | elapsed time per iteration (s): 0.42 | learning rate: 1.859E-04 | global batch size: 256 | lm loss: 3.409644E+00 | grad norm: 0.422 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.672 | TFLOPs: 31.83 | +7: iteration 2710/ 14324 | consumed samples: 693760 | consumed tokens: 1420820480 | elapsed time per iteration (s): 0.42 | learning rate: 1.858E-04 | global batch size: 256 | lm loss: 3.408111E+00 | grad norm: 0.386 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.197 | TFLOPs: 31.96 | +7: iteration 2720/ 14324 | consumed samples: 696320 | consumed tokens: 1426063360 | elapsed time per iteration (s): 0.42 | learning rate: 1.857E-04 | global batch size: 256 | lm loss: 3.398222E+00 | grad norm: 0.432 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.812 | TFLOPs: 31.73 | +7: iteration 2730/ 14324 | consumed samples: 698880 | consumed tokens: 1431306240 | elapsed time per iteration (s): 0.43 | learning rate: 1.856E-04 | global batch size: 256 | lm loss: 3.412869E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.012 | TFLOPs: 31.32 | +7: iteration 2740/ 14324 | consumed samples: 701440 | consumed tokens: 1436549120 | elapsed time per iteration (s): 0.42 | learning rate: 1.855E-04 | global batch size: 256 | lm loss: 3.389497E+00 | grad norm: 0.380 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.015 | TFLOPs: 31.90 | +7: iteration 2750/ 14324 | consumed samples: 704000 | consumed tokens: 1441792000 | elapsed time per iteration (s): 0.42 | learning rate: 1.854E-04 | global batch size: 256 | lm loss: 3.393179E+00 | grad norm: 0.430 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.326 | TFLOPs: 31.87 | +7: iteration 2760/ 14324 | consumed samples: 706560 | consumed tokens: 1447034880 | elapsed time per iteration (s): 0.43 | learning rate: 1.853E-04 | global batch size: 256 | lm loss: 3.423373E+00 | grad norm: 0.461 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.938 | TFLOPs: 31.16 | +7: iteration 2770/ 14324 | consumed samples: 709120 | consumed tokens: 1452277760 | elapsed time per iteration (s): 0.43 | learning rate: 1.852E-04 | global batch size: 256 | lm loss: 3.392701E+00 | grad norm: 0.437 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.218 | TFLOPs: 31.23 | +7: iteration 2780/ 14324 | consumed samples: 711680 | consumed tokens: 1457520640 | elapsed time per iteration (s): 0.43 | learning rate: 1.851E-04 | global batch size: 256 | lm loss: 3.386703E+00 | grad norm: 0.575 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 589.279 | TFLOPs: 30.92 | +7: iteration 2790/ 14324 | consumed samples: 714240 | consumed tokens: 1462763520 | elapsed time per iteration (s): 0.43 | learning rate: 1.850E-04 | global batch size: 256 | lm loss: 3.415551E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.791 | TFLOPs: 31.10 | +7: iteration 2800/ 14324 | consumed samples: 716800 | consumed tokens: 1468006400 | elapsed time per iteration (s): 0.43 | learning rate: 1.849E-04 | global batch size: 256 | lm loss: 3.363875E+00 | grad norm: 0.397 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.148 | TFLOPs: 31.07 | +7: iteration 2810/ 14324 | consumed samples: 719360 | consumed tokens: 1473249280 | elapsed time per iteration (s): 0.43 | learning rate: 1.847E-04 | global batch size: 256 | lm loss: 3.387049E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.606 | TFLOPs: 31.36 | +7: iteration 2820/ 14324 | consumed samples: 721920 | consumed tokens: 1478492160 | elapsed time per iteration (s): 0.43 | learning rate: 1.846E-04 | global batch size: 256 | lm loss: 3.392546E+00 | grad norm: 0.381 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.976 | TFLOPs: 31.58 | +7: iteration 2830/ 14324 | consumed samples: 724480 | consumed tokens: 1483735040 | elapsed time per iteration (s): 0.42 | learning rate: 1.845E-04 | global batch size: 256 | lm loss: 3.373003E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.134 | TFLOPs: 31.70 | +7: iteration 2840/ 14324 | consumed samples: 727040 | consumed tokens: 1488977920 | elapsed time per iteration (s): 0.42 | learning rate: 1.844E-04 | global batch size: 256 | lm loss: 3.387976E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.413 | TFLOPs: 31.66 | +7: iteration 2850/ 14324 | consumed samples: 729600 | consumed tokens: 1494220800 | elapsed time per iteration (s): 0.42 | learning rate: 1.843E-04 | global batch size: 256 | lm loss: 3.402811E+00 | grad norm: 0.391 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.904 | TFLOPs: 31.84 | +7: iteration 2860/ 14324 | consumed samples: 732160 | consumed tokens: 1499463680 | elapsed time per iteration (s): 0.43 | learning rate: 1.842E-04 | global batch size: 256 | lm loss: 3.389402E+00 | grad norm: 0.388 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.618 | TFLOPs: 31.46 | +7: iteration 2870/ 14324 | consumed samples: 734720 | consumed tokens: 1504706560 | elapsed time per iteration (s): 0.42 | learning rate: 1.841E-04 | global batch size: 256 | lm loss: 3.399200E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.878 | TFLOPs: 31.84 | +7: iteration 2880/ 14324 | consumed samples: 737280 | consumed tokens: 1509949440 | elapsed time per iteration (s): 0.42 | learning rate: 1.840E-04 | global batch size: 256 | lm loss: 3.366637E+00 | grad norm: 0.377 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.826 | TFLOPs: 31.63 | +7: iteration 2890/ 14324 | consumed samples: 739840 | consumed tokens: 1515192320 | elapsed time per iteration (s): 0.43 | learning rate: 1.838E-04 | global batch size: 256 | lm loss: 3.366512E+00 | grad norm: 0.498 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 589.606 | TFLOPs: 30.94 | +7: iteration 2900/ 14324 | consumed samples: 742400 | consumed tokens: 1520435200 | elapsed time per iteration (s): 0.42 | learning rate: 1.837E-04 | global batch size: 256 | lm loss: 3.389903E+00 | grad norm: 0.415 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.055 | TFLOPs: 31.96 | +7: iteration 2910/ 14324 | consumed samples: 744960 | consumed tokens: 1525678080 | elapsed time per iteration (s): 0.43 | learning rate: 1.836E-04 | global batch size: 256 | lm loss: 3.392749E+00 | grad norm: 0.380 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.691 | TFLOPs: 31.15 | +7: iteration 2920/ 14324 | consumed samples: 747520 | consumed tokens: 1530920960 | elapsed time per iteration (s): 0.42 | learning rate: 1.835E-04 | global batch size: 256 | lm loss: 3.367775E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.757 | TFLOPs: 31.84 | +7: iteration 2930/ 14324 | consumed samples: 750080 | consumed tokens: 1536163840 | elapsed time per iteration (s): 0.43 | learning rate: 1.834E-04 | global batch size: 256 | lm loss: 3.348764E+00 | grad norm: 0.442 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 588.638 | TFLOPs: 30.88 | +7: iteration 2940/ 14324 | consumed samples: 752640 | consumed tokens: 1541406720 | elapsed time per iteration (s): 0.43 | learning rate: 1.833E-04 | global batch size: 256 | lm loss: 3.411065E+00 | grad norm: 0.443 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.687 | TFLOPs: 31.31 | +7: iteration 2950/ 14324 | consumed samples: 755200 | consumed tokens: 1546649600 | elapsed time per iteration (s): 0.42 | learning rate: 1.832E-04 | global batch size: 256 | lm loss: 3.348943E+00 | grad norm: 0.377 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.427 | TFLOPs: 31.61 | +7: iteration 2960/ 14324 | consumed samples: 757760 | consumed tokens: 1551892480 | elapsed time per iteration (s): 0.42 | learning rate: 1.830E-04 | global batch size: 256 | lm loss: 3.347993E+00 | grad norm: 0.394 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.604 | TFLOPs: 31.72 | +7: iteration 2970/ 14324 | consumed samples: 760320 | consumed tokens: 1557135360 | elapsed time per iteration (s): 0.43 | learning rate: 1.829E-04 | global batch size: 256 | lm loss: 3.351265E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.975 | TFLOPs: 31.53 | +7: iteration 2980/ 14324 | consumed samples: 762880 | consumed tokens: 1562378240 | elapsed time per iteration (s): 0.43 | learning rate: 1.828E-04 | global batch size: 256 | lm loss: 3.407333E+00 | grad norm: 0.397 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.870 | TFLOPs: 31.47 | +7: iteration 2990/ 14324 | consumed samples: 765440 | consumed tokens: 1567621120 | elapsed time per iteration (s): 0.42 | learning rate: 1.827E-04 | global batch size: 256 | lm loss: 3.349565E+00 | grad norm: 0.413 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.084 | TFLOPs: 31.85 | +7: iteration 3000/ 14324 | consumed samples: 768000 | consumed tokens: 1572864000 | elapsed time per iteration (s): 0.42 | learning rate: 1.826E-04 | global batch size: 256 | lm loss: 3.348179E+00 | grad norm: 0.426 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.649 | TFLOPs: 31.72 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 3000 | lm loss value: 3.185559E+00 | lm loss PPL: 2.418080E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 3000 to checkpoints_220moscar +0: [2022-11-29 22:21:52,247] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step3000 is begin to save! +0: [2022-11-29 22:21:52,250] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/layer_01-model_00-model_states.pt... +0: [2022-11-29 22:21:52,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/layer_01-model_00-model_states.pt. +0: [2022-11-29 22:21:52,350] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/layer_03-model_00-model_states.pt... +0: [2022-11-29 22:21:52,372] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/layer_03-model_00-model_states.pt. +0: [2022-11-29 22:21:52,372] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/layer_04-model_00-model_states.pt... +0: [2022-11-29 22:21:52,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/layer_04-model_00-model_states.pt. +0: [2022-11-29 22:21:52,395] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/layer_05-model_00-model_states.pt... +0: [2022-11-29 22:21:52,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/layer_05-model_00-model_states.pt. +0: [2022-11-29 22:21:52,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/layer_06-model_00-model_states.pt... +0: [2022-11-29 22:21:52,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/layer_06-model_00-model_states.pt. +0: [2022-11-29 22:21:52,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/layer_07-model_00-model_states.pt... +0: [2022-11-29 22:21:52,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/layer_07-model_00-model_states.pt. +0: [2022-11-29 22:21:52,465] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/layer_08-model_00-model_states.pt... +0: [2022-11-29 22:21:52,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/layer_08-model_00-model_states.pt. +0: [2022-11-29 22:21:52,488] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/layer_09-model_00-model_states.pt... +0: [2022-11-29 22:21:52,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/layer_09-model_00-model_states.pt. +0: [2022-11-29 22:21:52,512] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/layer_10-model_00-model_states.pt... +0: [2022-11-29 22:21:52,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/layer_10-model_00-model_states.pt. +0: [2022-11-29 22:21:52,536] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/layer_11-model_00-model_states.pt... +0: [2022-11-29 22:21:52,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/layer_11-model_00-model_states.pt. +0: [2022-11-29 22:21:52,561] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/layer_12-model_00-model_states.pt... +0: [2022-11-29 22:21:52,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/layer_12-model_00-model_states.pt. +0: [2022-11-29 22:21:52,585] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/layer_13-model_00-model_states.pt... +0: [2022-11-29 22:21:52,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/layer_13-model_00-model_states.pt. +0: [2022-11-29 22:21:52,608] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/layer_14-model_00-model_states.pt... +0: [2022-11-29 22:21:52,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/layer_14-model_00-model_states.pt. +0: [2022-11-29 22:21:52,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/layer_15-model_00-model_states.pt... +0: [2022-11-29 22:21:52,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/layer_15-model_00-model_states.pt. +0: [2022-11-29 22:21:52,654] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/layer_16-model_00-model_states.pt... +0: [2022-11-29 22:21:52,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/layer_16-model_00-model_states.pt. +0: [2022-11-29 22:21:52,678] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/layer_17-model_00-model_states.pt... +0: [2022-11-29 22:21:52,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/layer_17-model_00-model_states.pt. +0: [2022-11-29 22:21:52,701] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/layer_18-model_00-model_states.pt... +0: [2022-11-29 22:21:52,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/layer_18-model_00-model_states.pt. +0: [2022-11-29 22:21:52,725] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/layer_19-model_00-model_states.pt... +0: [2022-11-29 22:21:52,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/layer_19-model_00-model_states.pt. +0: [2022-11-29 22:21:52,747] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/layer_20-model_00-model_states.pt... +0: [2022-11-29 22:21:52,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/layer_20-model_00-model_states.pt. +0: [2022-11-29 22:21:52,771] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/layer_22-model_00-model_states.pt... +0: [2022-11-29 22:21:52,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/layer_22-model_00-model_states.pt. +0: [2022-11-29 22:21:52,776] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_220moscar/global_step3000/mp_rank_00_model_states.pt +0: [2022-11-29 22:21:52,776] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/mp_rank_00_model_states.pt... +0: [2022-11-29 22:21:52,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/mp_rank_00_model_states.pt. +0: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:21:52,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:21:52,841] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:21:52,841] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 22:21:52,841] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 22:21:52,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:21:52,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:21:52,842] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 22:21:52,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 22:21:52,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:21:52,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:21:52,844] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 22:21:52,844] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 22:21:52,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:21:52,844] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 22:21:52,844] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 22:21:52,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:21:52,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +3: [2022-11-29 22:21:52,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:21:52,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 22:21:52,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 22:21:52,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 22:21:52,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:21:52,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +4: [2022-11-29 22:21:52,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:21:52,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 22:21:52,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 22:21:52,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 22:21:52,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:21:52,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 22:21:52,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 22:21:52,846] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:21:52,846] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 22:21:52,846] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 22:21:52,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:21:52,847] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 22:21:52,847] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 22:21:52,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:21:52,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:21:52,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 22:21:52,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 22:21:52,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 22:21:52,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 22:21:52,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:21:52,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 22:21:52,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:21:52,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 22:21:52,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 22:21:52,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 22:21:52,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:21:52,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 22:21:52,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 22:21:52,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:21:52,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:21:52,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 22:21:52,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 22:21:52,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 22:21:52,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 22:21:52,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:21:52,849] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 22:21:52,849] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 22:21:52,844] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 22:21:52,844] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 22:21:52,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:21:52,844] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 22:21:52,844] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 22:21:52,846] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:21:52,847] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 22:21:52,847] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 22:21:52,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:21:52,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 22:21:52,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 22:21:52,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:21:52,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 22:21:52,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 22:21:52,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:21:52,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:21:52,849] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 22:21:52,849] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 22:21:52,849] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 22:21:52,849] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 22:21:52,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:21:52,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 22:21:52,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 22:21:52,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:21:52,849] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 22:21:52,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 22:21:52,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:21:52,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 22:21:52,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 22:21:52,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:21:52,851] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 22:21:52,851] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 22:21:52,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:21:52,851] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 22:21:52,851] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 22:21:52,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:21:52,851] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 22:21:52,851] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 22:21:52,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:21:52,851] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 22:21:52,851] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 22:21:52,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:21:52,851] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 22:21:52,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 22:21:52,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:21:52,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:21:52,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +4: [2022-11-29 22:21:52,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +0: [2022-11-29 22:21:52,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 22:21:52,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 22:21:52,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:21:52,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:21:52,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3: [2022-11-29 22:21:52,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +0: [2022-11-29 22:21:52,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 22:21:52,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 22:21:52,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:21:52,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 22:21:52,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 22:21:52,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:21:52,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 22:21:52,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 22:21:52,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:21:52,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 22:21:52,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 22:21:52,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:21:52,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:21:52,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +4: [2022-11-29 22:21:52,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +5: [2022-11-29 22:21:52,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 22:21:52,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 22:21:52,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:21:52,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:21:52,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 22:21:52,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 22:21:52,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 22:21:52,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 22:21:52,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:21:52,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 22:21:52,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 22:21:52,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:21:52,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:21:52,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +7: [2022-11-29 22:21:52,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +2: [2022-11-29 22:21:52,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 22:21:52,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 22:21:52,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:21:52,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 22:21:52,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 22:21:52,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:21:52,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 22:21:52,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 22:21:52,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:21:52,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:21:52,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 22:21:52,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 22:21:52,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 22:21:52,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 22:21:52,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:21:52,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:21:52,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:21:52,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:21:52,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 22:21:52,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 22:21:52,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 22:21:52,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 22:21:52,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 22:21:52,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 22:21:52,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:21:52,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 22:21:52,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 22:21:52,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:21:52,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 22:21:52,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 22:21:52,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:21:52,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 22:21:52,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 22:21:52,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:21:52,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 22:21:52,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 22:21:52,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:21:52,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 22:21:52,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 22:21:52,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 22:21:52,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 22:21:52,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:21:52,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 22:21:52,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 22:21:52,875] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:21:52,875] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 22:21:52,875] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 22:21:52,906] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 22:21:52,906] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: successfully saved checkpoint at iteration 3000 to checkpoints_220moscar +7: time (ms) | save-checkpoint: 663.35 +7: iteration 3010/ 14324 | consumed samples: 770560 | consumed tokens: 1578106880 | elapsed time per iteration (s): 0.52 | learning rate: 1.825E-04 | global batch size: 256 | lm loss: 3.364346E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 491.934 | TFLOPs: 25.81 | +7: iteration 3020/ 14324 | consumed samples: 773120 | consumed tokens: 1583349760 | elapsed time per iteration (s): 0.45 | learning rate: 1.823E-04 | global batch size: 256 | lm loss: 3.372129E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 574.936 | TFLOPs: 30.17 | +7: iteration 3030/ 14324 | consumed samples: 775680 | consumed tokens: 1588592640 | elapsed time per iteration (s): 0.44 | learning rate: 1.822E-04 | global batch size: 256 | lm loss: 3.349078E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 581.612 | TFLOPs: 30.52 | +7: iteration 3040/ 14324 | consumed samples: 778240 | consumed tokens: 1593835520 | elapsed time per iteration (s): 0.43 | learning rate: 1.821E-04 | global batch size: 256 | lm loss: 3.374450E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.106 | TFLOPs: 31.43 | +7: iteration 3050/ 14324 | consumed samples: 780800 | consumed tokens: 1599078400 | elapsed time per iteration (s): 0.44 | learning rate: 1.820E-04 | global batch size: 256 | lm loss: 3.365945E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 584.906 | TFLOPs: 30.69 | +7: iteration 3060/ 14324 | consumed samples: 783360 | consumed tokens: 1604321280 | elapsed time per iteration (s): 0.43 | learning rate: 1.819E-04 | global batch size: 256 | lm loss: 3.335922E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.212 | TFLOPs: 31.23 | +7: iteration 3070/ 14324 | consumed samples: 785920 | consumed tokens: 1609564160 | elapsed time per iteration (s): 0.43 | learning rate: 1.817E-04 | global batch size: 256 | lm loss: 3.364870E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.886 | TFLOPs: 31.06 | +7: iteration 3080/ 14324 | consumed samples: 788480 | consumed tokens: 1614807040 | elapsed time per iteration (s): 0.43 | learning rate: 1.816E-04 | global batch size: 256 | lm loss: 3.370361E+00 | grad norm: 0.373 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.374 | TFLOPs: 31.29 | +7: iteration 3090/ 14324 | consumed samples: 791040 | consumed tokens: 1620049920 | elapsed time per iteration (s): 0.42 | learning rate: 1.815E-04 | global batch size: 256 | lm loss: 3.365969E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.008 | TFLOPs: 31.69 | +7: iteration 3100/ 14324 | consumed samples: 793600 | consumed tokens: 1625292800 | elapsed time per iteration (s): 0.43 | learning rate: 1.814E-04 | global batch size: 256 | lm loss: 3.350069E+00 | grad norm: 0.389 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.038 | TFLOPs: 31.22 | +7: iteration 3110/ 14324 | consumed samples: 796160 | consumed tokens: 1630535680 | elapsed time per iteration (s): 0.43 | learning rate: 1.813E-04 | global batch size: 256 | lm loss: 3.351130E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.395 | TFLOPs: 31.24 | +7: iteration 3120/ 14324 | consumed samples: 798720 | consumed tokens: 1635778560 | elapsed time per iteration (s): 0.43 | learning rate: 1.811E-04 | global batch size: 256 | lm loss: 3.364456E+00 | grad norm: 0.458 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.520 | TFLOPs: 31.46 | +7: iteration 3130/ 14324 | consumed samples: 801280 | consumed tokens: 1641021440 | elapsed time per iteration (s): 0.42 | learning rate: 1.810E-04 | global batch size: 256 | lm loss: 3.367529E+00 | grad norm: 0.408 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.807 | TFLOPs: 31.63 | +7: iteration 3140/ 14324 | consumed samples: 803840 | consumed tokens: 1646264320 | elapsed time per iteration (s): 0.42 | learning rate: 1.809E-04 | global batch size: 256 | lm loss: 3.342894E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.109 | TFLOPs: 31.70 | +7: iteration 3150/ 14324 | consumed samples: 806400 | consumed tokens: 1651507200 | elapsed time per iteration (s): 0.42 | learning rate: 1.808E-04 | global batch size: 256 | lm loss: 3.333327E+00 | grad norm: 0.459 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.417 | TFLOPs: 31.87 | +7: iteration 3160/ 14324 | consumed samples: 808960 | consumed tokens: 1656750080 | elapsed time per iteration (s): 0.44 | learning rate: 1.806E-04 | global batch size: 256 | lm loss: 3.332548E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 583.057 | TFLOPs: 30.59 | +7: iteration 3170/ 14324 | consumed samples: 811520 | consumed tokens: 1661992960 | elapsed time per iteration (s): 0.42 | learning rate: 1.805E-04 | global batch size: 256 | lm loss: 3.333998E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.270 | TFLOPs: 31.91 | +7: iteration 3180/ 14324 | consumed samples: 814080 | consumed tokens: 1667235840 | elapsed time per iteration (s): 0.43 | learning rate: 1.804E-04 | global batch size: 256 | lm loss: 3.349784E+00 | grad norm: 0.400 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.467 | TFLOPs: 31.35 | +7: iteration 3190/ 14324 | consumed samples: 816640 | consumed tokens: 1672478720 | elapsed time per iteration (s): 0.42 | learning rate: 1.803E-04 | global batch size: 256 | lm loss: 3.323768E+00 | grad norm: 0.436 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.024 | TFLOPs: 31.80 | +7: iteration 3200/ 14324 | consumed samples: 819200 | consumed tokens: 1677721600 | elapsed time per iteration (s): 0.43 | learning rate: 1.801E-04 | global batch size: 256 | lm loss: 3.371930E+00 | grad norm: 0.440 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 588.873 | TFLOPs: 30.90 | +7: iteration 3210/ 14324 | consumed samples: 821760 | consumed tokens: 1682964480 | elapsed time per iteration (s): 0.44 | learning rate: 1.800E-04 | global batch size: 256 | lm loss: 3.340477E+00 | grad norm: 0.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 585.255 | TFLOPs: 30.71 | +7: iteration 3220/ 14324 | consumed samples: 824320 | consumed tokens: 1688207360 | elapsed time per iteration (s): 0.43 | learning rate: 1.799E-04 | global batch size: 256 | lm loss: 3.341964E+00 | grad norm: 0.386 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.584 | TFLOPs: 31.41 | +7: iteration 3230/ 14324 | consumed samples: 826880 | consumed tokens: 1693450240 | elapsed time per iteration (s): 0.43 | learning rate: 1.798E-04 | global batch size: 256 | lm loss: 3.324881E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.796 | TFLOPs: 31.26 | +7: iteration 3240/ 14324 | consumed samples: 829440 | consumed tokens: 1698693120 | elapsed time per iteration (s): 0.43 | learning rate: 1.796E-04 | global batch size: 256 | lm loss: 3.324010E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.126 | TFLOPs: 31.23 | +7: iteration 3250/ 14324 | consumed samples: 832000 | consumed tokens: 1703936000 | elapsed time per iteration (s): 0.43 | learning rate: 1.795E-04 | global batch size: 256 | lm loss: 3.305054E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.899 | TFLOPs: 31.37 | +7: iteration 3260/ 14324 | consumed samples: 834560 | consumed tokens: 1709178880 | elapsed time per iteration (s): 0.43 | learning rate: 1.794E-04 | global batch size: 256 | lm loss: 3.304522E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.777 | TFLOPs: 31.15 | +7: iteration 3270/ 14324 | consumed samples: 837120 | consumed tokens: 1714421760 | elapsed time per iteration (s): 0.42 | learning rate: 1.793E-04 | global batch size: 256 | lm loss: 3.345186E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.472 | TFLOPs: 31.66 | +7: iteration 3280/ 14324 | consumed samples: 839680 | consumed tokens: 1719664640 | elapsed time per iteration (s): 0.44 | learning rate: 1.791E-04 | global batch size: 256 | lm loss: 3.325841E+00 | grad norm: 0.410 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 580.496 | TFLOPs: 30.46 | +7: iteration 3290/ 14324 | consumed samples: 842240 | consumed tokens: 1724907520 | elapsed time per iteration (s): 0.42 | learning rate: 1.790E-04 | global batch size: 256 | lm loss: 3.310142E+00 | grad norm: 0.426 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.446 | TFLOPs: 31.87 | +7: iteration 3300/ 14324 | consumed samples: 844800 | consumed tokens: 1730150400 | elapsed time per iteration (s): 0.43 | learning rate: 1.789E-04 | global batch size: 256 | lm loss: 3.330250E+00 | grad norm: 0.392 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.169 | TFLOPs: 31.49 | +7: iteration 3310/ 14324 | consumed samples: 847360 | consumed tokens: 1735393280 | elapsed time per iteration (s): 0.43 | learning rate: 1.787E-04 | global batch size: 256 | lm loss: 3.328493E+00 | grad norm: 0.437 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.247 | TFLOPs: 31.34 | +7: iteration 3320/ 14324 | consumed samples: 849920 | consumed tokens: 1740636160 | elapsed time per iteration (s): 0.43 | learning rate: 1.786E-04 | global batch size: 256 | lm loss: 3.305272E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.315 | TFLOPs: 31.29 | +7: iteration 3330/ 14324 | consumed samples: 852480 | consumed tokens: 1745879040 | elapsed time per iteration (s): 0.42 | learning rate: 1.785E-04 | global batch size: 256 | lm loss: 3.330803E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.855 | TFLOPs: 31.74 | +7: iteration 3340/ 14324 | consumed samples: 855040 | consumed tokens: 1751121920 | elapsed time per iteration (s): 0.44 | learning rate: 1.784E-04 | global batch size: 256 | lm loss: 3.335735E+00 | grad norm: 0.409 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 586.516 | TFLOPs: 30.77 | +7: iteration 3350/ 14324 | consumed samples: 857600 | consumed tokens: 1756364800 | elapsed time per iteration (s): 0.43 | learning rate: 1.782E-04 | global batch size: 256 | lm loss: 3.313738E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.539 | TFLOPs: 31.25 | +7: iteration 3360/ 14324 | consumed samples: 860160 | consumed tokens: 1761607680 | elapsed time per iteration (s): 0.44 | learning rate: 1.781E-04 | global batch size: 256 | lm loss: 3.299926E+00 | grad norm: 0.412 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 577.733 | TFLOPs: 30.31 | +7: iteration 3370/ 14324 | consumed samples: 862720 | consumed tokens: 1766850560 | elapsed time per iteration (s): 0.43 | learning rate: 1.780E-04 | global batch size: 256 | lm loss: 3.326140E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.034 | TFLOPs: 31.17 | +7: iteration 3380/ 14324 | consumed samples: 865280 | consumed tokens: 1772093440 | elapsed time per iteration (s): 0.43 | learning rate: 1.778E-04 | global batch size: 256 | lm loss: 3.319117E+00 | grad norm: 0.435 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.648 | TFLOPs: 31.46 | +7: iteration 3390/ 14324 | consumed samples: 867840 | consumed tokens: 1777336320 | elapsed time per iteration (s): 0.43 | learning rate: 1.777E-04 | global batch size: 256 | lm loss: 3.329120E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.647 | TFLOPs: 31.25 | +7: iteration 3400/ 14324 | consumed samples: 870400 | consumed tokens: 1782579200 | elapsed time per iteration (s): 0.42 | learning rate: 1.776E-04 | global batch size: 256 | lm loss: 3.285520E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.118 | TFLOPs: 31.64 | +7: iteration 3410/ 14324 | consumed samples: 872960 | consumed tokens: 1787822080 | elapsed time per iteration (s): 0.43 | learning rate: 1.774E-04 | global batch size: 256 | lm loss: 3.306625E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.855 | TFLOPs: 31.11 | +7: iteration 3420/ 14324 | consumed samples: 875520 | consumed tokens: 1793064960 | elapsed time per iteration (s): 0.43 | learning rate: 1.773E-04 | global batch size: 256 | lm loss: 3.279118E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.508 | TFLOPs: 31.40 | +7: iteration 3430/ 14324 | consumed samples: 878080 | consumed tokens: 1798307840 | elapsed time per iteration (s): 0.43 | learning rate: 1.772E-04 | global batch size: 256 | lm loss: 3.316392E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.062 | TFLOPs: 31.54 | +7: iteration 3440/ 14324 | consumed samples: 880640 | consumed tokens: 1803550720 | elapsed time per iteration (s): 0.43 | learning rate: 1.770E-04 | global batch size: 256 | lm loss: 3.317015E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.882 | TFLOPs: 31.42 | +7: iteration 3450/ 14324 | consumed samples: 883200 | consumed tokens: 1808793600 | elapsed time per iteration (s): 0.42 | learning rate: 1.769E-04 | global batch size: 256 | lm loss: 3.330415E+00 | grad norm: 0.404 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.878 | TFLOPs: 31.84 | +7: iteration 3460/ 14324 | consumed samples: 885760 | consumed tokens: 1814036480 | elapsed time per iteration (s): 0.43 | learning rate: 1.768E-04 | global batch size: 256 | lm loss: 3.302302E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.387 | TFLOPs: 31.29 | +7: iteration 3470/ 14324 | consumed samples: 888320 | consumed tokens: 1819279360 | elapsed time per iteration (s): 0.43 | learning rate: 1.766E-04 | global batch size: 256 | lm loss: 3.306469E+00 | grad norm: 0.435 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.770 | TFLOPs: 31.42 | +7: iteration 3480/ 14324 | consumed samples: 890880 | consumed tokens: 1824522240 | elapsed time per iteration (s): 0.43 | learning rate: 1.765E-04 | global batch size: 256 | lm loss: 3.315115E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.406 | TFLOPs: 31.29 | +7: iteration 3490/ 14324 | consumed samples: 893440 | consumed tokens: 1829765120 | elapsed time per iteration (s): 0.42 | learning rate: 1.764E-04 | global batch size: 256 | lm loss: 3.277047E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.345 | TFLOPs: 31.97 | +7: iteration 3500/ 14324 | consumed samples: 896000 | consumed tokens: 1835008000 | elapsed time per iteration (s): 0.43 | learning rate: 1.762E-04 | global batch size: 256 | lm loss: 3.326363E+00 | grad norm: 0.411 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.076 | TFLOPs: 31.59 | +7: iteration 3510/ 14324 | consumed samples: 898560 | consumed tokens: 1840250880 | elapsed time per iteration (s): 0.43 | learning rate: 1.761E-04 | global batch size: 256 | lm loss: 3.279662E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.119 | TFLOPs: 31.38 | +7: iteration 3520/ 14324 | consumed samples: 901120 | consumed tokens: 1845493760 | elapsed time per iteration (s): 0.43 | learning rate: 1.760E-04 | global batch size: 256 | lm loss: 3.299506E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.986 | TFLOPs: 31.06 | +7: iteration 3530/ 14324 | consumed samples: 903680 | consumed tokens: 1850736640 | elapsed time per iteration (s): 0.42 | learning rate: 1.758E-04 | global batch size: 256 | lm loss: 3.293008E+00 | grad norm: 0.435 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.463 | TFLOPs: 31.66 | +7: iteration 3540/ 14324 | consumed samples: 906240 | consumed tokens: 1855979520 | elapsed time per iteration (s): 0.42 | learning rate: 1.757E-04 | global batch size: 256 | lm loss: 3.305611E+00 | grad norm: 0.429 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.893 | TFLOPs: 31.63 | +7: iteration 3550/ 14324 | consumed samples: 908800 | consumed tokens: 1861222400 | elapsed time per iteration (s): 0.43 | learning rate: 1.756E-04 | global batch size: 256 | lm loss: 3.313685E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.642 | TFLOPs: 31.15 | +7: iteration 3560/ 14324 | consumed samples: 911360 | consumed tokens: 1866465280 | elapsed time per iteration (s): 0.43 | learning rate: 1.754E-04 | global batch size: 256 | lm loss: 3.273331E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.530 | TFLOPs: 31.56 | +7: iteration 3570/ 14324 | consumed samples: 913920 | consumed tokens: 1871708160 | elapsed time per iteration (s): 0.42 | learning rate: 1.753E-04 | global batch size: 256 | lm loss: 3.316077E+00 | grad norm: 0.442 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.869 | TFLOPs: 31.95 | +7: iteration 3580/ 14324 | consumed samples: 916480 | consumed tokens: 1876951040 | elapsed time per iteration (s): 0.42 | learning rate: 1.752E-04 | global batch size: 256 | lm loss: 3.289154E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.522 | TFLOPs: 31.67 | +7: iteration 3590/ 14324 | consumed samples: 919040 | consumed tokens: 1882193920 | elapsed time per iteration (s): 0.42 | learning rate: 1.750E-04 | global batch size: 256 | lm loss: 3.284286E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.981 | TFLOPs: 31.74 | +7: iteration 3600/ 14324 | consumed samples: 921600 | consumed tokens: 1887436800 | elapsed time per iteration (s): 0.43 | learning rate: 1.749E-04 | global batch size: 256 | lm loss: 3.297922E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.650 | TFLOPs: 31.20 | +7: iteration 3610/ 14324 | consumed samples: 924160 | consumed tokens: 1892679680 | elapsed time per iteration (s): 0.43 | learning rate: 1.747E-04 | global batch size: 256 | lm loss: 3.279655E+00 | grad norm: 0.396 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.566 | TFLOPs: 31.25 | +7: iteration 3620/ 14324 | consumed samples: 926720 | consumed tokens: 1897922560 | elapsed time per iteration (s): 0.42 | learning rate: 1.746E-04 | global batch size: 256 | lm loss: 3.287960E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.866 | TFLOPs: 31.89 | +7: iteration 3630/ 14324 | consumed samples: 929280 | consumed tokens: 1903165440 | elapsed time per iteration (s): 0.43 | learning rate: 1.745E-04 | global batch size: 256 | lm loss: 3.305168E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.524 | TFLOPs: 31.04 | +7: iteration 3640/ 14324 | consumed samples: 931840 | consumed tokens: 1908408320 | elapsed time per iteration (s): 0.42 | learning rate: 1.743E-04 | global batch size: 256 | lm loss: 3.272394E+00 | grad norm: 0.377 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.558 | TFLOPs: 31.62 | +7: iteration 3650/ 14324 | consumed samples: 934400 | consumed tokens: 1913651200 | elapsed time per iteration (s): 0.43 | learning rate: 1.742E-04 | global batch size: 256 | lm loss: 3.271828E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.766 | TFLOPs: 31.21 | +7: iteration 3660/ 14324 | consumed samples: 936960 | consumed tokens: 1918894080 | elapsed time per iteration (s): 0.43 | learning rate: 1.740E-04 | global batch size: 256 | lm loss: 3.294087E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.731 | TFLOPs: 31.41 | +7: iteration 3670/ 14324 | consumed samples: 939520 | consumed tokens: 1924136960 | elapsed time per iteration (s): 0.42 | learning rate: 1.739E-04 | global batch size: 256 | lm loss: 3.299872E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.642 | TFLOPs: 31.83 | +7: iteration 3680/ 14324 | consumed samples: 942080 | consumed tokens: 1929379840 | elapsed time per iteration (s): 0.45 | learning rate: 1.738E-04 | global batch size: 256 | lm loss: 3.262688E+00 | grad norm: 0.368 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 573.938 | TFLOPs: 30.11 | +7: iteration 3690/ 14324 | consumed samples: 944640 | consumed tokens: 1934622720 | elapsed time per iteration (s): 0.43 | learning rate: 1.736E-04 | global batch size: 256 | lm loss: 3.275679E+00 | grad norm: 0.368 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.648 | TFLOPs: 31.36 | +7: iteration 3700/ 14324 | consumed samples: 947200 | consumed tokens: 1939865600 | elapsed time per iteration (s): 0.43 | learning rate: 1.735E-04 | global batch size: 256 | lm loss: 3.290356E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.277 | TFLOPs: 31.18 | +7: iteration 3710/ 14324 | consumed samples: 949760 | consumed tokens: 1945108480 | elapsed time per iteration (s): 0.43 | learning rate: 1.733E-04 | global batch size: 256 | lm loss: 3.303597E+00 | grad norm: 0.436 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.940 | TFLOPs: 31.32 | +7: iteration 3720/ 14324 | consumed samples: 952320 | consumed tokens: 1950351360 | elapsed time per iteration (s): 0.43 | learning rate: 1.732E-04 | global batch size: 256 | lm loss: 3.296081E+00 | grad norm: 0.380 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.031 | TFLOPs: 31.59 | +7: iteration 3730/ 14324 | consumed samples: 954880 | consumed tokens: 1955594240 | elapsed time per iteration (s): 0.42 | learning rate: 1.731E-04 | global batch size: 256 | lm loss: 3.291822E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.747 | TFLOPs: 31.63 | +7: iteration 3740/ 14324 | consumed samples: 957440 | consumed tokens: 1960837120 | elapsed time per iteration (s): 0.43 | learning rate: 1.729E-04 | global batch size: 256 | lm loss: 3.255224E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.759 | TFLOPs: 31.52 | +7: iteration 3750/ 14324 | consumed samples: 960000 | consumed tokens: 1966080000 | elapsed time per iteration (s): 0.43 | learning rate: 1.728E-04 | global batch size: 256 | lm loss: 3.260754E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.259 | TFLOPs: 31.49 | +7: iteration 3760/ 14324 | consumed samples: 962560 | consumed tokens: 1971322880 | elapsed time per iteration (s): 0.42 | learning rate: 1.726E-04 | global batch size: 256 | lm loss: 3.262444E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.549 | TFLOPs: 31.67 | +7: iteration 3770/ 14324 | consumed samples: 965120 | consumed tokens: 1976565760 | elapsed time per iteration (s): 0.42 | learning rate: 1.725E-04 | global batch size: 256 | lm loss: 3.286022E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.927 | TFLOPs: 31.69 | +7: iteration 3780/ 14324 | consumed samples: 967680 | consumed tokens: 1981808640 | elapsed time per iteration (s): 0.44 | learning rate: 1.723E-04 | global batch size: 256 | lm loss: 3.280702E+00 | grad norm: 0.427 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 580.662 | TFLOPs: 30.47 | +7: iteration 3790/ 14324 | consumed samples: 970240 | consumed tokens: 1987051520 | elapsed time per iteration (s): 0.43 | learning rate: 1.722E-04 | global batch size: 256 | lm loss: 3.254255E+00 | grad norm: 0.438 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.102 | TFLOPs: 31.28 | +7: iteration 3800/ 14324 | consumed samples: 972800 | consumed tokens: 1992294400 | elapsed time per iteration (s): 0.42 | learning rate: 1.720E-04 | global batch size: 256 | lm loss: 3.287524E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.610 | TFLOPs: 31.72 | +7: iteration 3810/ 14324 | consumed samples: 975360 | consumed tokens: 1997537280 | elapsed time per iteration (s): 0.45 | learning rate: 1.719E-04 | global batch size: 256 | lm loss: 3.273001E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 572.309 | TFLOPs: 30.03 | +7: iteration 3820/ 14324 | consumed samples: 977920 | consumed tokens: 2002780160 | elapsed time per iteration (s): 0.43 | learning rate: 1.718E-04 | global batch size: 256 | lm loss: 3.269759E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.084 | TFLOPs: 31.22 | +7: iteration 3830/ 14324 | consumed samples: 980480 | consumed tokens: 2008023040 | elapsed time per iteration (s): 0.42 | learning rate: 1.716E-04 | global batch size: 256 | lm loss: 3.270543E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.673 | TFLOPs: 31.67 | +7: iteration 3840/ 14324 | consumed samples: 983040 | consumed tokens: 2013265920 | elapsed time per iteration (s): 0.42 | learning rate: 1.715E-04 | global batch size: 256 | lm loss: 3.272324E+00 | grad norm: 0.381 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.728 | TFLOPs: 31.68 | +7: iteration 3850/ 14324 | consumed samples: 985600 | consumed tokens: 2018508800 | elapsed time per iteration (s): 0.43 | learning rate: 1.713E-04 | global batch size: 256 | lm loss: 3.297267E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.097 | TFLOPs: 31.01 | +7: iteration 3860/ 14324 | consumed samples: 988160 | consumed tokens: 2023751680 | elapsed time per iteration (s): 0.43 | learning rate: 1.712E-04 | global batch size: 256 | lm loss: 3.256001E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.392 | TFLOPs: 31.50 | +7: iteration 3870/ 14324 | consumed samples: 990720 | consumed tokens: 2028994560 | elapsed time per iteration (s): 0.42 | learning rate: 1.710E-04 | global batch size: 256 | lm loss: 3.261019E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.920 | TFLOPs: 32.00 | +7: iteration 3880/ 14324 | consumed samples: 993280 | consumed tokens: 2034237440 | elapsed time per iteration (s): 0.43 | learning rate: 1.709E-04 | global batch size: 256 | lm loss: 3.248938E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.394 | TFLOPs: 31.13 | +7: iteration 3890/ 14324 | consumed samples: 995840 | consumed tokens: 2039480320 | elapsed time per iteration (s): 0.42 | learning rate: 1.707E-04 | global batch size: 256 | lm loss: 3.252337E+00 | grad norm: 0.400 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.150 | TFLOPs: 31.75 | +7: iteration 3900/ 14324 | consumed samples: 998400 | consumed tokens: 2044723200 | elapsed time per iteration (s): 0.43 | learning rate: 1.706E-04 | global batch size: 256 | lm loss: 3.508163E+00 | grad norm: 17.939 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.794 | TFLOPs: 31.31 | +7: iteration 3910/ 14324 | consumed samples: 1000960 | consumed tokens: 2049966080 | elapsed time per iteration (s): 0.43 | learning rate: 1.704E-04 | global batch size: 256 | lm loss: 3.847674E+00 | grad norm: 1.810 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.284 | TFLOPs: 31.50 | +7: iteration 3920/ 14324 | consumed samples: 1003520 | consumed tokens: 2055208960 | elapsed time per iteration (s): 0.44 | learning rate: 1.703E-04 | global batch size: 256 | lm loss: 3.437549E+00 | grad norm: 1.005 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 586.814 | TFLOPs: 30.79 | +7: iteration 3930/ 14324 | consumed samples: 1006080 | consumed tokens: 2060451840 | elapsed time per iteration (s): 0.43 | learning rate: 1.701E-04 | global batch size: 256 | lm loss: 3.343168E+00 | grad norm: 0.409 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.527 | TFLOPs: 31.25 | +7: iteration 3940/ 14324 | consumed samples: 1008640 | consumed tokens: 2065694720 | elapsed time per iteration (s): 0.44 | learning rate: 1.700E-04 | global batch size: 256 | lm loss: 3.303785E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 579.299 | TFLOPs: 30.39 | +7: iteration 3950/ 14324 | consumed samples: 1011200 | consumed tokens: 2070937600 | elapsed time per iteration (s): 0.43 | learning rate: 1.698E-04 | global batch size: 256 | lm loss: 3.292480E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.781 | TFLOPs: 31.47 | +7: iteration 3960/ 14324 | consumed samples: 1013760 | consumed tokens: 2076180480 | elapsed time per iteration (s): 0.42 | learning rate: 1.697E-04 | global batch size: 256 | lm loss: 3.254505E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.090 | TFLOPs: 31.70 | +7: iteration 3970/ 14324 | consumed samples: 1016320 | consumed tokens: 2081423360 | elapsed time per iteration (s): 0.42 | learning rate: 1.695E-04 | global batch size: 256 | lm loss: 3.278541E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.776 | TFLOPs: 32.15 | +7: iteration 3980/ 14324 | consumed samples: 1018880 | consumed tokens: 2086666240 | elapsed time per iteration (s): 0.44 | learning rate: 1.694E-04 | global batch size: 256 | lm loss: 3.263348E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 580.869 | TFLOPs: 30.48 | +7: iteration 3990/ 14324 | consumed samples: 1021440 | consumed tokens: 2091909120 | elapsed time per iteration (s): 0.42 | learning rate: 1.692E-04 | global batch size: 256 | lm loss: 3.264624E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.476 | TFLOPs: 31.61 | +0: [2022-11-29 22:29:01,860] [INFO] [logging.py:68:log_dist] [Rank 0] step=4000, skipped=0, lr=[0.00016909962506367714, 0.00016909962506367714, 0.00016909962506367714], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 4000/ 14324 | consumed samples: 1024000 | consumed tokens: 2097152000 | elapsed time per iteration (s): 0.43 | learning rate: 1.691E-04 | global batch size: 256 | lm loss: 3.256518E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.489 | TFLOPs: 31.03 | +0: steps: 4000 loss: 3.2539 iter time (s): 0.426 samples/sec: 600.697 +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 4000 | lm loss value: 3.121553E+00 | lm loss PPL: 2.268159E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 4000 to checkpoints_220moscar +0: [2022-11-29 22:29:02,020] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step4000 is begin to save! +0: [2022-11-29 22:29:02,025] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/layer_01-model_00-model_states.pt... +0: [2022-11-29 22:29:02,126] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/layer_01-model_00-model_states.pt. +0: [2022-11-29 22:29:02,126] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/layer_03-model_00-model_states.pt... +0: [2022-11-29 22:29:02,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/layer_03-model_00-model_states.pt. +0: [2022-11-29 22:29:02,148] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/layer_04-model_00-model_states.pt... +0: [2022-11-29 22:29:02,172] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/layer_04-model_00-model_states.pt. +0: [2022-11-29 22:29:02,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/layer_05-model_00-model_states.pt... +0: [2022-11-29 22:29:02,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/layer_05-model_00-model_states.pt. +0: [2022-11-29 22:29:02,195] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/layer_06-model_00-model_states.pt... +0: [2022-11-29 22:29:02,219] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/layer_06-model_00-model_states.pt. +0: [2022-11-29 22:29:02,219] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/layer_07-model_00-model_states.pt... +0: [2022-11-29 22:29:02,242] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/layer_07-model_00-model_states.pt. +0: [2022-11-29 22:29:02,243] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/layer_08-model_00-model_states.pt... +0: [2022-11-29 22:29:02,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/layer_08-model_00-model_states.pt. +0: [2022-11-29 22:29:02,268] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/layer_09-model_00-model_states.pt... +0: [2022-11-29 22:29:02,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/layer_09-model_00-model_states.pt. +0: [2022-11-29 22:29:02,291] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/layer_10-model_00-model_states.pt... +0: [2022-11-29 22:29:02,314] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/layer_10-model_00-model_states.pt. +0: [2022-11-29 22:29:02,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/layer_11-model_00-model_states.pt... +0: [2022-11-29 22:29:02,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/layer_11-model_00-model_states.pt. +0: [2022-11-29 22:29:02,338] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/layer_12-model_00-model_states.pt... +0: [2022-11-29 22:29:02,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/layer_12-model_00-model_states.pt. +0: [2022-11-29 22:29:02,361] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/layer_13-model_00-model_states.pt... +0: [2022-11-29 22:29:02,384] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/layer_13-model_00-model_states.pt. +0: [2022-11-29 22:29:02,384] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/layer_14-model_00-model_states.pt... +0: [2022-11-29 22:29:02,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/layer_14-model_00-model_states.pt. +0: [2022-11-29 22:29:02,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/layer_15-model_00-model_states.pt... +0: [2022-11-29 22:29:02,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/layer_15-model_00-model_states.pt. +0: [2022-11-29 22:29:02,431] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/layer_16-model_00-model_states.pt... +0: [2022-11-29 22:29:02,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/layer_16-model_00-model_states.pt. +0: [2022-11-29 22:29:02,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/layer_17-model_00-model_states.pt... +0: [2022-11-29 22:29:02,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/layer_17-model_00-model_states.pt. +0: [2022-11-29 22:29:02,478] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/layer_18-model_00-model_states.pt... +0: [2022-11-29 22:29:02,501] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/layer_18-model_00-model_states.pt. +0: [2022-11-29 22:29:02,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/layer_19-model_00-model_states.pt... +0: [2022-11-29 22:29:02,524] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/layer_19-model_00-model_states.pt. +0: [2022-11-29 22:29:02,524] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/layer_20-model_00-model_states.pt... +0: [2022-11-29 22:29:02,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/layer_20-model_00-model_states.pt. +0: [2022-11-29 22:29:02,548] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/layer_22-model_00-model_states.pt... +0: [2022-11-29 22:29:02,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/layer_22-model_00-model_states.pt. +0: [2022-11-29 22:29:02,553] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_220moscar/global_step4000/mp_rank_00_model_states.pt +0: [2022-11-29 22:29:02,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/mp_rank_00_model_states.pt... +0: [2022-11-29 22:29:02,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/mp_rank_00_model_states.pt. +0: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:29:02,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:29:02,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:29:02,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:29:02,621] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 22:29:02,621] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 22:29:02,622] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:29:02,622] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 22:29:02,622] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 22:29:02,622] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:29:02,622] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 22:29:02,622] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 22:29:02,622] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:29:02,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 22:29:02,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 22:29:02,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:29:02,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 22:29:02,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 22:29:02,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:29:02,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 22:29:02,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 22:29:02,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:29:02,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:29:02,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +7: [2022-11-29 22:29:02,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:29:02,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 22:29:02,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:29:02,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 22:29:02,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 22:29:02,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 22:29:02,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 22:29:02,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:29:02,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +7: [2022-11-29 22:29:02,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:29:02,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:29:02,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 22:29:02,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +6: [2022-11-29 22:29:02,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:29:02,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 22:29:02,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 22:29:02,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 22:29:02,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 22:29:02,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 22:29:02,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:29:02,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:29:02,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +4: [2022-11-29 22:29:02,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +2: [2022-11-29 22:29:02,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 22:29:02,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 22:29:02,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:29:02,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:29:02,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +1: [2022-11-29 22:29:02,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:29:02,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 22:29:02,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 22:29:02,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 22:29:02,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 22:29:02,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 22:29:02,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:29:02,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 22:29:02,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 22:29:02,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:29:02,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 22:29:02,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 22:29:02,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:29:02,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 22:29:02,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 22:29:02,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:29:02,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:29:02,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 22:29:02,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 22:29:02,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 22:29:02,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 22:29:02,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:29:02,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:29:02,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 22:29:02,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +7: [2022-11-29 22:29:02,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:29:02,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 22:29:02,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 22:29:02,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 22:29:02,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 22:29:02,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:29:02,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 22:29:02,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 22:29:02,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:29:02,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 22:29:02,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 22:29:02,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:29:02,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:29:02,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 22:29:02,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 22:29:02,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 22:29:02,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 22:29:02,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:29:02,628] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 22:29:02,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 22:29:02,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:29:02,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:29:02,628] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 22:29:02,628] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 22:29:02,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 22:29:02,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 22:29:02,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:29:02,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 22:29:02,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 22:29:02,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:29:02,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:29:02,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 22:29:02,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 22:29:02,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 22:29:02,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 22:29:02,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:29:02,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:29:02,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 22:29:02,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 22:29:02,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 22:29:02,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 22:29:02,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:29:02,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:29:02,630] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +6: [2022-11-29 22:29:02,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:29:02,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 22:29:02,630] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 22:29:02,630] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 22:29:02,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 22:29:02,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 22:29:02,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:29:02,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +4: [2022-11-29 22:29:02,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:29:02,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 22:29:02,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 22:29:02,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 22:29:02,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:29:02,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:29:02,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:29:02,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 22:29:02,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 22:29:02,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 22:29:02,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 22:29:02,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 22:29:02,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 22:29:02,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 22:29:02,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 22:29:02,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:29:02,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 22:29:02,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 22:29:02,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:29:02,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 22:29:02,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 22:29:02,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:29:02,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:29:02,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:29:02,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 22:29:02,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 22:29:02,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 22:29:02,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 22:29:02,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 22:29:02,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 22:29:02,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:29:02,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 22:29:02,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 22:29:02,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:29:02,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 22:29:02,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 22:29:02,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:29:02,635] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 22:29:02,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 22:29:02,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:29:02,644] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 22:29:02,644] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 22:29:02,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:29:02,653] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 22:29:02,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:29:02,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:29:02,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:29:02,653] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 22:29:02,653] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 22:29:02,653] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 22:29:02,653] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 22:29:02,653] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 22:29:02,653] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 22:29:02,653] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 22:29:02,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:29:02,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:29:02,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:29:02,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 22:29:02,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 22:29:02,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 22:29:02,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 22:29:02,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 22:29:02,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 22:29:02,682] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 22:29:02,682] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: successfully saved checkpoint at iteration 4000 to checkpoints_220moscar +7: time (ms) | save-checkpoint: 667.07 +7: iteration 4010/ 14324 | consumed samples: 1026560 | consumed tokens: 2102394880 | elapsed time per iteration (s): 0.50 | learning rate: 1.689E-04 | global batch size: 256 | lm loss: 3.260468E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 508.665 | TFLOPs: 26.69 | +7: iteration 4020/ 14324 | consumed samples: 1029120 | consumed tokens: 2107637760 | elapsed time per iteration (s): 0.43 | learning rate: 1.688E-04 | global batch size: 256 | lm loss: 3.275155E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.228 | TFLOPs: 31.60 | +7: iteration 4030/ 14324 | consumed samples: 1031680 | consumed tokens: 2112880640 | elapsed time per iteration (s): 0.42 | learning rate: 1.686E-04 | global batch size: 256 | lm loss: 3.263790E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.898 | TFLOPs: 32.11 | +7: iteration 4040/ 14324 | consumed samples: 1034240 | consumed tokens: 2118123520 | elapsed time per iteration (s): 0.45 | learning rate: 1.685E-04 | global batch size: 256 | lm loss: 3.267887E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 567.875 | TFLOPs: 29.80 | +7: iteration 4050/ 14324 | consumed samples: 1036800 | consumed tokens: 2123366400 | elapsed time per iteration (s): 0.45 | learning rate: 1.683E-04 | global batch size: 256 | lm loss: 3.255621E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 571.996 | TFLOPs: 30.01 | +7: iteration 4060/ 14324 | consumed samples: 1039360 | consumed tokens: 2128609280 | elapsed time per iteration (s): 0.43 | learning rate: 1.682E-04 | global batch size: 256 | lm loss: 3.259543E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.689 | TFLOPs: 31.36 | +7: iteration 4070/ 14324 | consumed samples: 1041920 | consumed tokens: 2133852160 | elapsed time per iteration (s): 0.42 | learning rate: 1.680E-04 | global batch size: 256 | lm loss: 3.233529E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.138 | TFLOPs: 31.91 | +7: iteration 4080/ 14324 | consumed samples: 1044480 | consumed tokens: 2139095040 | elapsed time per iteration (s): 0.42 | learning rate: 1.679E-04 | global batch size: 256 | lm loss: 3.259023E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.905 | TFLOPs: 31.90 | +7: iteration 4090/ 14324 | consumed samples: 1047040 | consumed tokens: 2144337920 | elapsed time per iteration (s): 0.42 | learning rate: 1.677E-04 | global batch size: 256 | lm loss: 3.275707E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.286 | TFLOPs: 31.71 | +7: iteration 4100/ 14324 | consumed samples: 1049600 | consumed tokens: 2149580800 | elapsed time per iteration (s): 0.43 | learning rate: 1.676E-04 | global batch size: 256 | lm loss: 3.248123E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.044 | TFLOPs: 31.38 | +7: iteration 4110/ 14324 | consumed samples: 1052160 | consumed tokens: 2154823680 | elapsed time per iteration (s): 0.42 | learning rate: 1.674E-04 | global batch size: 256 | lm loss: 3.240609E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 613.830 | TFLOPs: 32.21 | +7: iteration 4120/ 14324 | consumed samples: 1054720 | consumed tokens: 2160066560 | elapsed time per iteration (s): 0.42 | learning rate: 1.673E-04 | global batch size: 256 | lm loss: 3.225491E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.942 | TFLOPs: 31.90 | +7: iteration 4130/ 14324 | consumed samples: 1057280 | consumed tokens: 2165309440 | elapsed time per iteration (s): 0.43 | learning rate: 1.671E-04 | global batch size: 256 | lm loss: 3.256840E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.599 | TFLOPs: 31.46 | +7: iteration 4140/ 14324 | consumed samples: 1059840 | consumed tokens: 2170552320 | elapsed time per iteration (s): 0.43 | learning rate: 1.670E-04 | global batch size: 256 | lm loss: 3.233166E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 590.355 | TFLOPs: 30.97 | +7: iteration 4150/ 14324 | consumed samples: 1062400 | consumed tokens: 2175795200 | elapsed time per iteration (s): 0.43 | learning rate: 1.668E-04 | global batch size: 256 | lm loss: 3.245193E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.874 | TFLOPs: 31.21 | +7: iteration 4160/ 14324 | consumed samples: 1064960 | consumed tokens: 2181038080 | elapsed time per iteration (s): 0.42 | learning rate: 1.667E-04 | global batch size: 256 | lm loss: 3.244745E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.123 | TFLOPs: 31.70 | +7: iteration 4170/ 14324 | consumed samples: 1067520 | consumed tokens: 2186280960 | elapsed time per iteration (s): 0.44 | learning rate: 1.665E-04 | global batch size: 256 | lm loss: 3.227494E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 588.231 | TFLOPs: 30.86 | +7: iteration 4180/ 14324 | consumed samples: 1070080 | consumed tokens: 2191523840 | elapsed time per iteration (s): 0.42 | learning rate: 1.663E-04 | global batch size: 256 | lm loss: 3.213708E+00 | grad norm: 0.470 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.285 | TFLOPs: 32.02 | +7: iteration 4190/ 14324 | consumed samples: 1072640 | consumed tokens: 2196766720 | elapsed time per iteration (s): 0.42 | learning rate: 1.662E-04 | global batch size: 256 | lm loss: 3.234359E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.757 | TFLOPs: 31.63 | +7: iteration 4200/ 14324 | consumed samples: 1075200 | consumed tokens: 2202009600 | elapsed time per iteration (s): 0.42 | learning rate: 1.660E-04 | global batch size: 256 | lm loss: 3.233614E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.312 | TFLOPs: 32.07 | +7: iteration 4210/ 14324 | consumed samples: 1077760 | consumed tokens: 2207252480 | elapsed time per iteration (s): 0.42 | learning rate: 1.659E-04 | global batch size: 256 | lm loss: 3.252002E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.933 | TFLOPs: 31.63 | +7: iteration 4220/ 14324 | consumed samples: 1080320 | consumed tokens: 2212495360 | elapsed time per iteration (s): 0.42 | learning rate: 1.657E-04 | global batch size: 256 | lm loss: 3.256789E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.050 | TFLOPs: 31.64 | +7: iteration 4230/ 14324 | consumed samples: 1082880 | consumed tokens: 2217738240 | elapsed time per iteration (s): 0.42 | learning rate: 1.656E-04 | global batch size: 256 | lm loss: 3.233698E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.019 | TFLOPs: 32.01 | +7: iteration 4240/ 14324 | consumed samples: 1085440 | consumed tokens: 2222981120 | elapsed time per iteration (s): 0.42 | learning rate: 1.654E-04 | global batch size: 256 | lm loss: 3.271756E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.433 | TFLOPs: 32.08 | +7: iteration 4250/ 14324 | consumed samples: 1088000 | consumed tokens: 2228224000 | elapsed time per iteration (s): 0.42 | learning rate: 1.653E-04 | global batch size: 256 | lm loss: 3.196148E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.827 | TFLOPs: 31.84 | +7: iteration 4260/ 14324 | consumed samples: 1090560 | consumed tokens: 2233466880 | elapsed time per iteration (s): 0.43 | learning rate: 1.651E-04 | global batch size: 256 | lm loss: 3.272744E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.938 | TFLOPs: 31.27 | +7: iteration 4270/ 14324 | consumed samples: 1093120 | consumed tokens: 2238709760 | elapsed time per iteration (s): 0.42 | learning rate: 1.649E-04 | global batch size: 256 | lm loss: 3.243408E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.409 | TFLOPs: 31.61 | +7: iteration 4280/ 14324 | consumed samples: 1095680 | consumed tokens: 2243952640 | elapsed time per iteration (s): 0.42 | learning rate: 1.648E-04 | global batch size: 256 | lm loss: 3.244387E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.795 | TFLOPs: 31.68 | +7: iteration 4290/ 14324 | consumed samples: 1098240 | consumed tokens: 2249195520 | elapsed time per iteration (s): 0.42 | learning rate: 1.646E-04 | global batch size: 256 | lm loss: 3.244104E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.978 | TFLOPs: 32.06 | +7: iteration 4300/ 14324 | consumed samples: 1100800 | consumed tokens: 2254438400 | elapsed time per iteration (s): 0.44 | learning rate: 1.645E-04 | global batch size: 256 | lm loss: 3.193642E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 582.122 | TFLOPs: 30.54 | +7: iteration 4310/ 14324 | consumed samples: 1103360 | consumed tokens: 2259681280 | elapsed time per iteration (s): 0.43 | learning rate: 1.643E-04 | global batch size: 256 | lm loss: 3.225345E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.365 | TFLOPs: 31.40 | +7: iteration 4320/ 14324 | consumed samples: 1105920 | consumed tokens: 2264924160 | elapsed time per iteration (s): 0.43 | learning rate: 1.641E-04 | global batch size: 256 | lm loss: 3.212550E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.213 | TFLOPs: 31.54 | +7: iteration 4330/ 14324 | consumed samples: 1108480 | consumed tokens: 2270167040 | elapsed time per iteration (s): 0.44 | learning rate: 1.640E-04 | global batch size: 256 | lm loss: 3.221593E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 583.565 | TFLOPs: 30.62 | +7: iteration 4340/ 14324 | consumed samples: 1111040 | consumed tokens: 2275409920 | elapsed time per iteration (s): 0.44 | learning rate: 1.638E-04 | global batch size: 256 | lm loss: 3.260633E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 579.736 | TFLOPs: 30.42 | +7: iteration 4350/ 14324 | consumed samples: 1113600 | consumed tokens: 2280652800 | elapsed time per iteration (s): 0.44 | learning rate: 1.637E-04 | global batch size: 256 | lm loss: 3.201668E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 588.372 | TFLOPs: 30.87 | +7: iteration 4360/ 14324 | consumed samples: 1116160 | consumed tokens: 2285895680 | elapsed time per iteration (s): 0.42 | learning rate: 1.635E-04 | global batch size: 256 | lm loss: 3.199371E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.807 | TFLOPs: 31.84 | +7: iteration 4370/ 14324 | consumed samples: 1118720 | consumed tokens: 2291138560 | elapsed time per iteration (s): 0.43 | learning rate: 1.633E-04 | global batch size: 256 | lm loss: 3.225339E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.046 | TFLOPs: 31.43 | +7: iteration 4380/ 14324 | consumed samples: 1121280 | consumed tokens: 2296381440 | elapsed time per iteration (s): 0.42 | learning rate: 1.632E-04 | global batch size: 256 | lm loss: 3.223943E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.247 | TFLOPs: 31.81 | +7: iteration 4390/ 14324 | consumed samples: 1123840 | consumed tokens: 2301624320 | elapsed time per iteration (s): 0.43 | learning rate: 1.630E-04 | global batch size: 256 | lm loss: 3.211201E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.048 | TFLOPs: 31.27 | +7: iteration 4400/ 14324 | consumed samples: 1126400 | consumed tokens: 2306867200 | elapsed time per iteration (s): 0.43 | learning rate: 1.629E-04 | global batch size: 256 | lm loss: 3.211601E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.587 | TFLOPs: 31.30 | +7: iteration 4410/ 14324 | consumed samples: 1128960 | consumed tokens: 2312110080 | elapsed time per iteration (s): 0.43 | learning rate: 1.627E-04 | global batch size: 256 | lm loss: 3.215958E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.708 | TFLOPs: 31.36 | +7: iteration 4420/ 14324 | consumed samples: 1131520 | consumed tokens: 2317352960 | elapsed time per iteration (s): 0.43 | learning rate: 1.625E-04 | global batch size: 256 | lm loss: 3.214593E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.679 | TFLOPs: 31.36 | +7: iteration 4430/ 14324 | consumed samples: 1134080 | consumed tokens: 2322595840 | elapsed time per iteration (s): 0.43 | learning rate: 1.624E-04 | global batch size: 256 | lm loss: 3.217262E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.791 | TFLOPs: 31.42 | +7: iteration 4440/ 14324 | consumed samples: 1136640 | consumed tokens: 2327838720 | elapsed time per iteration (s): 0.42 | learning rate: 1.622E-04 | global batch size: 256 | lm loss: 3.198843E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.378 | TFLOPs: 31.61 | +7: iteration 4450/ 14324 | consumed samples: 1139200 | consumed tokens: 2333081600 | elapsed time per iteration (s): 0.43 | learning rate: 1.621E-04 | global batch size: 256 | lm loss: 3.212261E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.182 | TFLOPs: 31.18 | +7: iteration 4460/ 14324 | consumed samples: 1141760 | consumed tokens: 2338324480 | elapsed time per iteration (s): 0.43 | learning rate: 1.619E-04 | global batch size: 256 | lm loss: 3.214162E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.192 | TFLOPs: 31.54 | +7: iteration 4470/ 14324 | consumed samples: 1144320 | consumed tokens: 2343567360 | elapsed time per iteration (s): 0.42 | learning rate: 1.617E-04 | global batch size: 256 | lm loss: 3.189904E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 615.179 | TFLOPs: 32.28 | +7: iteration 4480/ 14324 | consumed samples: 1146880 | consumed tokens: 2348810240 | elapsed time per iteration (s): 0.42 | learning rate: 1.616E-04 | global batch size: 256 | lm loss: 3.216476E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.293 | TFLOPs: 31.65 | +7: iteration 4490/ 14324 | consumed samples: 1149440 | consumed tokens: 2354053120 | elapsed time per iteration (s): 0.42 | learning rate: 1.614E-04 | global batch size: 256 | lm loss: 3.215922E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.810 | TFLOPs: 31.68 | +7: iteration 4500/ 14324 | consumed samples: 1152000 | consumed tokens: 2359296000 | elapsed time per iteration (s): 0.42 | learning rate: 1.612E-04 | global batch size: 256 | lm loss: 3.201874E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.927 | TFLOPs: 31.69 | +7: iteration 4510/ 14324 | consumed samples: 1154560 | consumed tokens: 2364538880 | elapsed time per iteration (s): 0.42 | learning rate: 1.611E-04 | global batch size: 256 | lm loss: 3.229429E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.085 | TFLOPs: 31.91 | +7: iteration 4520/ 14324 | consumed samples: 1157120 | consumed tokens: 2369781760 | elapsed time per iteration (s): 0.43 | learning rate: 1.609E-04 | global batch size: 256 | lm loss: 3.198100E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.340 | TFLOPs: 31.13 | +7: iteration 4530/ 14324 | consumed samples: 1159680 | consumed tokens: 2375024640 | elapsed time per iteration (s): 0.43 | learning rate: 1.607E-04 | global batch size: 256 | lm loss: 3.202546E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.465 | TFLOPs: 31.19 | +7: iteration 4540/ 14324 | consumed samples: 1162240 | consumed tokens: 2380267520 | elapsed time per iteration (s): 0.42 | learning rate: 1.606E-04 | global batch size: 256 | lm loss: 3.206226E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.082 | TFLOPs: 32.01 | +7: iteration 4550/ 14324 | consumed samples: 1164800 | consumed tokens: 2385510400 | elapsed time per iteration (s): 0.43 | learning rate: 1.604E-04 | global batch size: 256 | lm loss: 3.204168E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.545 | TFLOPs: 31.19 | +7: iteration 4560/ 14324 | consumed samples: 1167360 | consumed tokens: 2390753280 | elapsed time per iteration (s): 0.43 | learning rate: 1.602E-04 | global batch size: 256 | lm loss: 3.192128E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.999 | TFLOPs: 31.27 | +7: iteration 4570/ 14324 | consumed samples: 1169920 | consumed tokens: 2395996160 | elapsed time per iteration (s): 0.42 | learning rate: 1.601E-04 | global batch size: 256 | lm loss: 3.205219E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.268 | TFLOPs: 31.81 | +7: iteration 4580/ 14324 | consumed samples: 1172480 | consumed tokens: 2401239040 | elapsed time per iteration (s): 0.43 | learning rate: 1.599E-04 | global batch size: 256 | lm loss: 3.194671E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.463 | TFLOPs: 31.35 | +7: iteration 4590/ 14324 | consumed samples: 1175040 | consumed tokens: 2406481920 | elapsed time per iteration (s): 0.42 | learning rate: 1.597E-04 | global batch size: 256 | lm loss: 3.194072E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.432 | TFLOPs: 31.61 | +7: iteration 4600/ 14324 | consumed samples: 1177600 | consumed tokens: 2411724800 | elapsed time per iteration (s): 0.44 | learning rate: 1.596E-04 | global batch size: 256 | lm loss: 3.203775E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 587.649 | TFLOPs: 30.83 | +7: iteration 4610/ 14324 | consumed samples: 1180160 | consumed tokens: 2416967680 | elapsed time per iteration (s): 0.43 | learning rate: 1.594E-04 | global batch size: 256 | lm loss: 3.197576E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.179 | TFLOPs: 31.28 | +7: iteration 4620/ 14324 | consumed samples: 1182720 | consumed tokens: 2422210560 | elapsed time per iteration (s): 0.43 | learning rate: 1.592E-04 | global batch size: 256 | lm loss: 3.184589E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.236 | TFLOPs: 31.55 | +7: iteration 4630/ 14324 | consumed samples: 1185280 | consumed tokens: 2427453440 | elapsed time per iteration (s): 0.43 | learning rate: 1.591E-04 | global batch size: 256 | lm loss: 3.208232E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.288 | TFLOPs: 31.55 | +7: iteration 4640/ 14324 | consumed samples: 1187840 | consumed tokens: 2432696320 | elapsed time per iteration (s): 0.42 | learning rate: 1.589E-04 | global batch size: 256 | lm loss: 3.212314E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.863 | TFLOPs: 31.63 | +7: iteration 4650/ 14324 | consumed samples: 1190400 | consumed tokens: 2437939200 | elapsed time per iteration (s): 0.44 | learning rate: 1.587E-04 | global batch size: 256 | lm loss: 3.188574E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 586.421 | TFLOPs: 30.77 | +7: iteration 4660/ 14324 | consumed samples: 1192960 | consumed tokens: 2443182080 | elapsed time per iteration (s): 0.42 | learning rate: 1.586E-04 | global batch size: 256 | lm loss: 3.190074E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.899 | TFLOPs: 31.63 | +7: iteration 4670/ 14324 | consumed samples: 1195520 | consumed tokens: 2448424960 | elapsed time per iteration (s): 0.43 | learning rate: 1.584E-04 | global batch size: 256 | lm loss: 3.192131E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.824 | TFLOPs: 31.52 | +7: iteration 4680/ 14324 | consumed samples: 1198080 | consumed tokens: 2453667840 | elapsed time per iteration (s): 0.43 | learning rate: 1.582E-04 | global batch size: 256 | lm loss: 3.199743E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.715 | TFLOPs: 31.47 | +7: iteration 4690/ 14324 | consumed samples: 1200640 | consumed tokens: 2458910720 | elapsed time per iteration (s): 0.44 | learning rate: 1.581E-04 | global batch size: 256 | lm loss: 3.209251E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 584.278 | TFLOPs: 30.66 | +7: iteration 4700/ 14324 | consumed samples: 1203200 | consumed tokens: 2464153600 | elapsed time per iteration (s): 0.43 | learning rate: 1.579E-04 | global batch size: 256 | lm loss: 3.191001E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.841 | TFLOPs: 31.42 | +7: iteration 4710/ 14324 | consumed samples: 1205760 | consumed tokens: 2469396480 | elapsed time per iteration (s): 0.42 | learning rate: 1.577E-04 | global batch size: 256 | lm loss: 3.198652E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 614.340 | TFLOPs: 32.23 | +7: iteration 4720/ 14324 | consumed samples: 1208320 | consumed tokens: 2474639360 | elapsed time per iteration (s): 0.43 | learning rate: 1.576E-04 | global batch size: 256 | lm loss: 3.196826E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.166 | TFLOPs: 31.28 | +7: iteration 4730/ 14324 | consumed samples: 1210880 | consumed tokens: 2479882240 | elapsed time per iteration (s): 0.43 | learning rate: 1.574E-04 | global batch size: 256 | lm loss: 3.218894E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.354 | TFLOPs: 31.29 | +7: iteration 4740/ 14324 | consumed samples: 1213440 | consumed tokens: 2485125120 | elapsed time per iteration (s): 0.42 | learning rate: 1.572E-04 | global batch size: 256 | lm loss: 3.192586E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.271 | TFLOPs: 31.81 | +7: iteration 4750/ 14324 | consumed samples: 1216000 | consumed tokens: 2490368000 | elapsed time per iteration (s): 0.43 | learning rate: 1.571E-04 | global batch size: 256 | lm loss: 3.188783E+00 | grad norm: 0.389 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.617 | TFLOPs: 31.46 | +7: iteration 4760/ 14324 | consumed samples: 1218560 | consumed tokens: 2495610880 | elapsed time per iteration (s): 0.42 | learning rate: 1.569E-04 | global batch size: 256 | lm loss: 3.188195E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.465 | TFLOPs: 31.87 | +7: iteration 4770/ 14324 | consumed samples: 1221120 | consumed tokens: 2500853760 | elapsed time per iteration (s): 0.45 | learning rate: 1.567E-04 | global batch size: 256 | lm loss: 3.182001E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 571.825 | TFLOPs: 30.00 | +7: iteration 4780/ 14324 | consumed samples: 1223680 | consumed tokens: 2506096640 | elapsed time per iteration (s): 0.43 | learning rate: 1.565E-04 | global batch size: 256 | lm loss: 3.199105E+00 | grad norm: 0.383 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.760 | TFLOPs: 31.47 | +7: iteration 4790/ 14324 | consumed samples: 1226240 | consumed tokens: 2511339520 | elapsed time per iteration (s): 0.43 | learning rate: 1.564E-04 | global batch size: 256 | lm loss: 3.199781E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.755 | TFLOPs: 31.57 | +7: iteration 4800/ 14324 | consumed samples: 1228800 | consumed tokens: 2516582400 | elapsed time per iteration (s): 0.43 | learning rate: 1.562E-04 | global batch size: 256 | lm loss: 3.153492E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.286 | TFLOPs: 31.39 | +7: iteration 4810/ 14324 | consumed samples: 1231360 | consumed tokens: 2521825280 | elapsed time per iteration (s): 0.43 | learning rate: 1.560E-04 | global batch size: 256 | lm loss: 3.179915E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.003 | TFLOPs: 31.17 | +7: iteration 4820/ 14324 | consumed samples: 1233920 | consumed tokens: 2527068160 | elapsed time per iteration (s): 0.42 | learning rate: 1.559E-04 | global batch size: 256 | lm loss: 3.207141E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.931 | TFLOPs: 31.90 | +7: iteration 4830/ 14324 | consumed samples: 1236480 | consumed tokens: 2532311040 | elapsed time per iteration (s): 0.43 | learning rate: 1.557E-04 | global batch size: 256 | lm loss: 3.167888E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.222 | TFLOPs: 31.39 | +7: iteration 4840/ 14324 | consumed samples: 1239040 | consumed tokens: 2537553920 | elapsed time per iteration (s): 0.42 | learning rate: 1.555E-04 | global batch size: 256 | lm loss: 3.199803E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.306 | TFLOPs: 31.86 | +7: iteration 4850/ 14324 | consumed samples: 1241600 | consumed tokens: 2542796800 | elapsed time per iteration (s): 0.43 | learning rate: 1.553E-04 | global batch size: 256 | lm loss: 3.192036E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.373 | TFLOPs: 31.24 | +7: iteration 4860/ 14324 | consumed samples: 1244160 | consumed tokens: 2548039680 | elapsed time per iteration (s): 0.43 | learning rate: 1.552E-04 | global batch size: 256 | lm loss: 3.167145E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.183 | TFLOPs: 31.49 | +7: iteration 4870/ 14324 | consumed samples: 1246720 | consumed tokens: 2553282560 | elapsed time per iteration (s): 0.42 | learning rate: 1.550E-04 | global batch size: 256 | lm loss: 3.173091E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.493 | TFLOPs: 31.66 | +7: iteration 4880/ 14324 | consumed samples: 1249280 | consumed tokens: 2558525440 | elapsed time per iteration (s): 0.43 | learning rate: 1.548E-04 | global batch size: 256 | lm loss: 3.183400E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 590.583 | TFLOPs: 30.99 | +7: iteration 4890/ 14324 | consumed samples: 1251840 | consumed tokens: 2563768320 | elapsed time per iteration (s): 0.42 | learning rate: 1.547E-04 | global batch size: 256 | lm loss: 3.180051E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.568 | TFLOPs: 31.62 | +7: iteration 4900/ 14324 | consumed samples: 1254400 | consumed tokens: 2569011200 | elapsed time per iteration (s): 0.43 | learning rate: 1.545E-04 | global batch size: 256 | lm loss: 3.171160E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.212 | TFLOPs: 31.39 | +7: iteration 4910/ 14324 | consumed samples: 1256960 | consumed tokens: 2574254080 | elapsed time per iteration (s): 0.43 | learning rate: 1.543E-04 | global batch size: 256 | lm loss: 3.171490E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.357 | TFLOPs: 31.39 | +7: iteration 4920/ 14324 | consumed samples: 1259520 | consumed tokens: 2579496960 | elapsed time per iteration (s): 0.42 | learning rate: 1.541E-04 | global batch size: 256 | lm loss: 3.195875E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.177 | TFLOPs: 31.70 | +7: iteration 4930/ 14324 | consumed samples: 1262080 | consumed tokens: 2584739840 | elapsed time per iteration (s): 0.43 | learning rate: 1.540E-04 | global batch size: 256 | lm loss: 3.156091E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.314 | TFLOPs: 31.13 | +7: iteration 4940/ 14324 | consumed samples: 1264640 | consumed tokens: 2589982720 | elapsed time per iteration (s): 0.43 | learning rate: 1.538E-04 | global batch size: 256 | lm loss: 3.202719E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.997 | TFLOPs: 31.48 | +7: iteration 4950/ 14324 | consumed samples: 1267200 | consumed tokens: 2595225600 | elapsed time per iteration (s): 0.43 | learning rate: 1.536E-04 | global batch size: 256 | lm loss: 3.170465E+00 | grad norm: 0.422 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.087 | TFLOPs: 31.07 | +7: iteration 4960/ 14324 | consumed samples: 1269760 | consumed tokens: 2600468480 | elapsed time per iteration (s): 0.44 | learning rate: 1.534E-04 | global batch size: 256 | lm loss: 3.202246E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 587.475 | TFLOPs: 30.82 | +7: iteration 4970/ 14324 | consumed samples: 1272320 | consumed tokens: 2605711360 | elapsed time per iteration (s): 0.43 | learning rate: 1.533E-04 | global batch size: 256 | lm loss: 3.190139E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.945 | TFLOPs: 31.27 | +7: iteration 4980/ 14324 | consumed samples: 1274880 | consumed tokens: 2610954240 | elapsed time per iteration (s): 0.43 | learning rate: 1.531E-04 | global batch size: 256 | lm loss: 3.162545E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.240 | TFLOPs: 31.60 | +7: iteration 4990/ 14324 | consumed samples: 1277440 | consumed tokens: 2616197120 | elapsed time per iteration (s): 0.42 | learning rate: 1.529E-04 | global batch size: 256 | lm loss: 3.178762E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.359 | TFLOPs: 31.97 | +7: iteration 5000/ 14324 | consumed samples: 1280000 | consumed tokens: 2621440000 | elapsed time per iteration (s): 0.43 | learning rate: 1.527E-04 | global batch size: 256 | lm loss: 3.170929E+00 | grad norm: 0.645 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 589.284 | TFLOPs: 30.92 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 5000 | lm loss value: 3.141081E+00 | lm loss PPL: 2.312885E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 5000 to checkpoints_220moscar +0: [2022-11-29 22:36:10,083] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step5000 is begin to save! +0: [2022-11-29 22:36:10,086] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/layer_01-model_00-model_states.pt... +0: [2022-11-29 22:36:10,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/layer_01-model_00-model_states.pt. +0: [2022-11-29 22:36:10,185] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/layer_03-model_00-model_states.pt... +0: [2022-11-29 22:36:10,206] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/layer_03-model_00-model_states.pt. +0: [2022-11-29 22:36:10,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/layer_04-model_00-model_states.pt... +0: [2022-11-29 22:36:10,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/layer_04-model_00-model_states.pt. +0: [2022-11-29 22:36:10,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/layer_05-model_00-model_states.pt... +0: [2022-11-29 22:36:10,254] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/layer_05-model_00-model_states.pt. +0: [2022-11-29 22:36:10,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/layer_06-model_00-model_states.pt... +0: [2022-11-29 22:36:10,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/layer_06-model_00-model_states.pt. +0: [2022-11-29 22:36:10,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/layer_07-model_00-model_states.pt... +0: [2022-11-29 22:36:10,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/layer_07-model_00-model_states.pt. +0: [2022-11-29 22:36:10,302] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/layer_08-model_00-model_states.pt... +0: [2022-11-29 22:36:10,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/layer_08-model_00-model_states.pt. +0: [2022-11-29 22:36:10,325] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/layer_09-model_00-model_states.pt... +0: [2022-11-29 22:36:10,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/layer_09-model_00-model_states.pt. +0: [2022-11-29 22:36:10,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/layer_10-model_00-model_states.pt... +0: [2022-11-29 22:36:10,371] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/layer_10-model_00-model_states.pt. +0: [2022-11-29 22:36:10,372] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/layer_11-model_00-model_states.pt... +0: [2022-11-29 22:36:10,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/layer_11-model_00-model_states.pt. +0: [2022-11-29 22:36:10,395] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/layer_12-model_00-model_states.pt... +0: [2022-11-29 22:36:10,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/layer_12-model_00-model_states.pt. +0: [2022-11-29 22:36:10,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/layer_13-model_00-model_states.pt... +0: [2022-11-29 22:36:10,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/layer_13-model_00-model_states.pt. +0: [2022-11-29 22:36:10,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/layer_14-model_00-model_states.pt... +0: [2022-11-29 22:36:10,464] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/layer_14-model_00-model_states.pt. +0: [2022-11-29 22:36:10,465] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/layer_15-model_00-model_states.pt... +0: [2022-11-29 22:36:10,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/layer_15-model_00-model_states.pt. +0: [2022-11-29 22:36:10,487] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/layer_16-model_00-model_states.pt... +0: [2022-11-29 22:36:10,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/layer_16-model_00-model_states.pt. +0: [2022-11-29 22:36:10,510] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/layer_17-model_00-model_states.pt... +0: [2022-11-29 22:36:10,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/layer_17-model_00-model_states.pt. +0: [2022-11-29 22:36:10,533] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/layer_18-model_00-model_states.pt... +0: [2022-11-29 22:36:10,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/layer_18-model_00-model_states.pt. +0: [2022-11-29 22:36:10,556] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/layer_19-model_00-model_states.pt... +0: [2022-11-29 22:36:10,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/layer_19-model_00-model_states.pt. +0: [2022-11-29 22:36:10,579] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/layer_20-model_00-model_states.pt... +0: [2022-11-29 22:36:10,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/layer_20-model_00-model_states.pt. +0: [2022-11-29 22:36:10,603] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/layer_22-model_00-model_states.pt... +0: [2022-11-29 22:36:10,606] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/layer_22-model_00-model_states.pt. +0: [2022-11-29 22:36:10,607] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_220moscar/global_step5000/mp_rank_00_model_states.pt +0: [2022-11-29 22:36:10,607] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/mp_rank_00_model_states.pt... +0: [2022-11-29 22:36:10,610] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/mp_rank_00_model_states.pt. +0: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:36:10,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:36:10,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:36:10,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 22:36:10,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 22:36:10,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:36:10,675] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 22:36:10,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 22:36:10,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:36:10,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:36:10,676] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 22:36:10,676] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 22:36:10,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:36:10,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:36:10,677] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 22:36:10,677] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 22:36:10,677] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 22:36:10,677] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 22:36:10,678] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:36:10,680] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:36:10,680] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 22:36:10,680] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 22:36:10,680] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:36:10,680] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 22:36:10,680] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 22:36:10,681] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:36:10,681] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 22:36:10,681] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 22:36:10,681] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:36:10,681] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:36:10,681] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 22:36:10,681] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 22:36:10,681] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 22:36:10,681] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 22:36:10,682] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:36:10,682] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:36:10,682] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 22:36:10,682] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 22:36:10,682] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 22:36:10,682] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 22:36:10,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:36:10,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 22:36:10,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 22:36:10,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:36:10,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 22:36:10,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 22:36:10,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:36:10,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 22:36:10,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 22:36:10,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:36:10,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 22:36:10,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 22:36:10,685] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:36:10,685] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +5: [2022-11-29 22:36:10,675] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 22:36:10,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 22:36:10,682] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:36:10,682] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:36:10,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 22:36:10,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 22:36:10,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 22:36:10,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 22:36:10,685] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 22:36:10,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:36:10,685] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:36:10,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +3: [2022-11-29 22:36:10,685] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:36:10,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 22:36:10,685] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +5: [2022-11-29 22:36:10,684] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:36:10,684] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 22:36:10,684] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 22:36:10,685] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 22:36:10,685] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +5: [2022-11-29 22:36:10,685] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:36:10,685] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 22:36:10,685] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 22:36:10,685] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 22:36:10,686] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:36:10,686] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 22:36:10,686] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 22:36:10,686] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:36:10,687] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:36:10,687] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 22:36:10,687] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 22:36:10,687] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:36:10,687] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:36:10,687] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +7: [2022-11-29 22:36:10,687] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:36:10,687] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 22:36:10,687] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 22:36:10,687] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 22:36:10,687] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 22:36:10,687] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 22:36:10,687] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:36:10,687] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 22:36:10,687] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 22:36:10,688] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:36:10,688] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 22:36:10,688] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 22:36:10,686] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 22:36:10,686] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 22:36:10,687] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:36:10,687] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 22:36:10,688] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 22:36:10,689] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:36:10,689] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 22:36:10,689] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 22:36:10,689] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:36:10,689] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:36:10,689] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:36:10,690] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 22:36:10,690] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 22:36:10,690] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 22:36:10,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 22:36:10,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 22:36:10,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 22:36:10,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:36:10,690] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 22:36:10,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 22:36:10,692] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:36:10,692] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 22:36:10,693] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 22:36:10,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:36:10,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:36:10,693] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 22:36:10,693] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 22:36:10,693] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 22:36:10,693] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 22:36:10,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:36:10,693] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 22:36:10,693] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 22:36:10,678] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 22:36:10,678] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 22:36:10,678] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:36:10,678] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 22:36:10,678] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 22:36:10,680] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:36:10,680] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 22:36:10,680] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 22:36:10,685] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:36:10,685] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 22:36:10,685] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 22:36:10,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:36:10,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:36:10,690] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 22:36:10,690] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 22:36:10,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 22:36:10,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 22:36:10,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:36:10,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 22:36:10,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 22:36:10,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:36:10,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 22:36:10,695] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 22:36:10,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:36:10,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:36:10,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:36:10,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:36:10,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 22:36:10,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 22:36:10,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 22:36:10,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 22:36:10,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 22:36:10,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 22:36:10,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 22:36:10,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 22:36:10,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:36:10,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 22:36:10,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 22:36:10,699] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:36:10,699] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 22:36:10,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 22:36:10,699] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:36:10,699] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 22:36:10,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 22:36:10,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:36:10,699] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:36:10,699] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 22:36:10,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 22:36:10,699] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:36:10,699] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 22:36:10,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 22:36:10,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:36:10,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 22:36:10,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 22:36:10,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:36:10,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 22:36:10,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 22:36:10,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:36:10,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 22:36:10,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 22:36:10,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 22:36:10,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: successfully saved checkpoint at iteration 5000 to checkpoints_220moscar +7: time (ms) | save-checkpoint: 658.18 +7: iteration 5010/ 14324 | consumed samples: 1282560 | consumed tokens: 2626682880 | elapsed time per iteration (s): 0.50 | learning rate: 1.526E-04 | global batch size: 256 | lm loss: 3.184719E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 511.444 | TFLOPs: 26.83 | +7: iteration 5020/ 14324 | consumed samples: 1285120 | consumed tokens: 2631925760 | elapsed time per iteration (s): 0.45 | learning rate: 1.524E-04 | global batch size: 256 | lm loss: 3.183868E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 573.425 | TFLOPs: 30.09 | +7: iteration 5030/ 14324 | consumed samples: 1287680 | consumed tokens: 2637168640 | elapsed time per iteration (s): 0.44 | learning rate: 1.522E-04 | global batch size: 256 | lm loss: 3.155956E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 587.228 | TFLOPs: 30.81 | +7: iteration 5040/ 14324 | consumed samples: 1290240 | consumed tokens: 2642411520 | elapsed time per iteration (s): 0.42 | learning rate: 1.520E-04 | global batch size: 256 | lm loss: 3.191917E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.686 | TFLOPs: 31.62 | +7: iteration 5050/ 14324 | consumed samples: 1292800 | consumed tokens: 2647654400 | elapsed time per iteration (s): 0.42 | learning rate: 1.519E-04 | global batch size: 256 | lm loss: 3.169351E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.607 | TFLOPs: 31.83 | +7: iteration 5060/ 14324 | consumed samples: 1295360 | consumed tokens: 2652897280 | elapsed time per iteration (s): 0.42 | learning rate: 1.517E-04 | global batch size: 256 | lm loss: 3.175194E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.511 | TFLOPs: 31.72 | +7: iteration 5070/ 14324 | consumed samples: 1297920 | consumed tokens: 2658140160 | elapsed time per iteration (s): 0.42 | learning rate: 1.515E-04 | global batch size: 256 | lm loss: 3.171827E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.789 | TFLOPs: 31.94 | +7: iteration 5080/ 14324 | consumed samples: 1300480 | consumed tokens: 2663383040 | elapsed time per iteration (s): 0.43 | learning rate: 1.513E-04 | global batch size: 256 | lm loss: 3.189736E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.681 | TFLOPs: 31.15 | +7: iteration 5090/ 14324 | consumed samples: 1303040 | consumed tokens: 2668625920 | elapsed time per iteration (s): 0.43 | learning rate: 1.512E-04 | global batch size: 256 | lm loss: 3.192057E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 590.899 | TFLOPs: 31.00 | +7: iteration 5100/ 14324 | consumed samples: 1305600 | consumed tokens: 2673868800 | elapsed time per iteration (s): 0.44 | learning rate: 1.510E-04 | global batch size: 256 | lm loss: 3.191299E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 579.118 | TFLOPs: 30.39 | +7: iteration 5110/ 14324 | consumed samples: 1308160 | consumed tokens: 2679111680 | elapsed time per iteration (s): 0.42 | learning rate: 1.508E-04 | global batch size: 256 | lm loss: 3.183458E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.915 | TFLOPs: 31.63 | +7: iteration 5120/ 14324 | consumed samples: 1310720 | consumed tokens: 2684354560 | elapsed time per iteration (s): 0.43 | learning rate: 1.506E-04 | global batch size: 256 | lm loss: 3.157040E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.757 | TFLOPs: 31.26 | +7: iteration 5130/ 14324 | consumed samples: 1313280 | consumed tokens: 2689597440 | elapsed time per iteration (s): 0.43 | learning rate: 1.504E-04 | global batch size: 256 | lm loss: 3.183425E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.052 | TFLOPs: 31.06 | +7: iteration 5140/ 14324 | consumed samples: 1315840 | consumed tokens: 2694840320 | elapsed time per iteration (s): 0.42 | learning rate: 1.503E-04 | global batch size: 256 | lm loss: 3.184926E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.551 | TFLOPs: 31.88 | +7: iteration 5150/ 14324 | consumed samples: 1318400 | consumed tokens: 2700083200 | elapsed time per iteration (s): 0.43 | learning rate: 1.501E-04 | global batch size: 256 | lm loss: 3.179648E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.321 | TFLOPs: 31.13 | +7: iteration 5160/ 14324 | consumed samples: 1320960 | consumed tokens: 2705326080 | elapsed time per iteration (s): 0.42 | learning rate: 1.499E-04 | global batch size: 256 | lm loss: 3.173734E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.906 | TFLOPs: 31.69 | +7: iteration 5170/ 14324 | consumed samples: 1323520 | consumed tokens: 2710568960 | elapsed time per iteration (s): 0.44 | learning rate: 1.497E-04 | global batch size: 256 | lm loss: 3.185091E+00 | grad norm: 0.367 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 586.707 | TFLOPs: 30.78 | +7: iteration 5180/ 14324 | consumed samples: 1326080 | consumed tokens: 2715811840 | elapsed time per iteration (s): 0.44 | learning rate: 1.495E-04 | global batch size: 256 | lm loss: 3.162555E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 583.050 | TFLOPs: 30.59 | +7: iteration 5190/ 14324 | consumed samples: 1328640 | consumed tokens: 2721054720 | elapsed time per iteration (s): 0.43 | learning rate: 1.494E-04 | global batch size: 256 | lm loss: 3.164879E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.037 | TFLOPs: 31.48 | +7: iteration 5200/ 14324 | consumed samples: 1331200 | consumed tokens: 2726297600 | elapsed time per iteration (s): 0.42 | learning rate: 1.492E-04 | global batch size: 256 | lm loss: 3.171636E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.171 | TFLOPs: 31.80 | +7: iteration 5210/ 14324 | consumed samples: 1333760 | consumed tokens: 2731540480 | elapsed time per iteration (s): 0.43 | learning rate: 1.490E-04 | global batch size: 256 | lm loss: 3.162206E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.528 | TFLOPs: 31.46 | +7: iteration 5220/ 14324 | consumed samples: 1336320 | consumed tokens: 2736783360 | elapsed time per iteration (s): 0.43 | learning rate: 1.488E-04 | global batch size: 256 | lm loss: 3.162057E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.221 | TFLOPs: 31.44 | +7: iteration 5230/ 14324 | consumed samples: 1338880 | consumed tokens: 2742026240 | elapsed time per iteration (s): 0.44 | learning rate: 1.487E-04 | global batch size: 256 | lm loss: 3.127545E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 580.538 | TFLOPs: 30.46 | +7: iteration 5240/ 14324 | consumed samples: 1341440 | consumed tokens: 2747269120 | elapsed time per iteration (s): 0.42 | learning rate: 1.485E-04 | global batch size: 256 | lm loss: 3.142963E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.081 | TFLOPs: 31.85 | +7: iteration 5250/ 14324 | consumed samples: 1344000 | consumed tokens: 2752512000 | elapsed time per iteration (s): 0.44 | learning rate: 1.483E-04 | global batch size: 256 | lm loss: 3.164644E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 588.439 | TFLOPs: 30.87 | +7: iteration 5260/ 14324 | consumed samples: 1346560 | consumed tokens: 2757754880 | elapsed time per iteration (s): 0.43 | learning rate: 1.481E-04 | global batch size: 256 | lm loss: 3.148620E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.884 | TFLOPs: 31.21 | +7: iteration 5270/ 14324 | consumed samples: 1349120 | consumed tokens: 2762997760 | elapsed time per iteration (s): 0.45 | learning rate: 1.479E-04 | global batch size: 256 | lm loss: 3.150280E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 572.748 | TFLOPs: 30.05 | +7: iteration 5280/ 14324 | consumed samples: 1351680 | consumed tokens: 2768240640 | elapsed time per iteration (s): 0.44 | learning rate: 1.477E-04 | global batch size: 256 | lm loss: 3.147223E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 587.426 | TFLOPs: 30.82 | +7: iteration 5290/ 14324 | consumed samples: 1354240 | consumed tokens: 2773483520 | elapsed time per iteration (s): 0.44 | learning rate: 1.476E-04 | global batch size: 256 | lm loss: 3.169297E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 576.226 | TFLOPs: 30.23 | +7: iteration 5300/ 14324 | consumed samples: 1356800 | consumed tokens: 2778726400 | elapsed time per iteration (s): 0.43 | learning rate: 1.474E-04 | global batch size: 256 | lm loss: 3.148917E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.658 | TFLOPs: 31.46 | +7: iteration 5310/ 14324 | consumed samples: 1359360 | consumed tokens: 2783969280 | elapsed time per iteration (s): 0.43 | learning rate: 1.472E-04 | global batch size: 256 | lm loss: 3.126761E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.715 | TFLOPs: 31.20 | +7: iteration 5320/ 14324 | consumed samples: 1361920 | consumed tokens: 2789212160 | elapsed time per iteration (s): 0.43 | learning rate: 1.470E-04 | global batch size: 256 | lm loss: 3.182406E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.870 | TFLOPs: 31.11 | +7: iteration 5330/ 14324 | consumed samples: 1364480 | consumed tokens: 2794455040 | elapsed time per iteration (s): 0.42 | learning rate: 1.468E-04 | global batch size: 256 | lm loss: 3.147882E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.359 | TFLOPs: 31.81 | +7: iteration 5340/ 14324 | consumed samples: 1367040 | consumed tokens: 2799697920 | elapsed time per iteration (s): 0.43 | learning rate: 1.467E-04 | global batch size: 256 | lm loss: 3.152025E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.109 | TFLOPs: 31.49 | +7: iteration 5350/ 14324 | consumed samples: 1369600 | consumed tokens: 2804940800 | elapsed time per iteration (s): 0.43 | learning rate: 1.465E-04 | global batch size: 256 | lm loss: 3.160993E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.372 | TFLOPs: 31.34 | +7: iteration 5360/ 14324 | consumed samples: 1372160 | consumed tokens: 2810183680 | elapsed time per iteration (s): 0.45 | learning rate: 1.463E-04 | global batch size: 256 | lm loss: 3.131500E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 572.538 | TFLOPs: 30.04 | +7: iteration 5370/ 14324 | consumed samples: 1374720 | consumed tokens: 2815426560 | elapsed time per iteration (s): 0.43 | learning rate: 1.461E-04 | global batch size: 256 | lm loss: 3.145603E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.423 | TFLOPs: 31.35 | +7: iteration 5380/ 14324 | consumed samples: 1377280 | consumed tokens: 2820669440 | elapsed time per iteration (s): 0.44 | learning rate: 1.459E-04 | global batch size: 256 | lm loss: 3.172030E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 586.829 | TFLOPs: 30.79 | +7: iteration 5390/ 14324 | consumed samples: 1379840 | consumed tokens: 2825912320 | elapsed time per iteration (s): 0.44 | learning rate: 1.457E-04 | global batch size: 256 | lm loss: 3.145975E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 581.642 | TFLOPs: 30.52 | +7: iteration 5400/ 14324 | consumed samples: 1382400 | consumed tokens: 2831155200 | elapsed time per iteration (s): 0.43 | learning rate: 1.456E-04 | global batch size: 256 | lm loss: 3.108312E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.284 | TFLOPs: 31.29 | +7: iteration 5410/ 14324 | consumed samples: 1384960 | consumed tokens: 2836398080 | elapsed time per iteration (s): 0.42 | learning rate: 1.454E-04 | global batch size: 256 | lm loss: 3.146992E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.524 | TFLOPs: 31.67 | +7: iteration 5420/ 14324 | consumed samples: 1387520 | consumed tokens: 2841640960 | elapsed time per iteration (s): 0.43 | learning rate: 1.452E-04 | global batch size: 256 | lm loss: 3.180104E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 588.740 | TFLOPs: 30.89 | +7: iteration 5430/ 14324 | consumed samples: 1390080 | consumed tokens: 2846883840 | elapsed time per iteration (s): 0.42 | learning rate: 1.450E-04 | global batch size: 256 | lm loss: 3.154561E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.451 | TFLOPs: 31.77 | +7: iteration 5440/ 14324 | consumed samples: 1392640 | consumed tokens: 2852126720 | elapsed time per iteration (s): 0.43 | learning rate: 1.448E-04 | global batch size: 256 | lm loss: 3.160724E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.154 | TFLOPs: 31.33 | +7: iteration 5450/ 14324 | consumed samples: 1395200 | consumed tokens: 2857369600 | elapsed time per iteration (s): 0.43 | learning rate: 1.446E-04 | global batch size: 256 | lm loss: 3.116495E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.815 | TFLOPs: 31.37 | +7: iteration 5460/ 14324 | consumed samples: 1397760 | consumed tokens: 2862612480 | elapsed time per iteration (s): 0.43 | learning rate: 1.445E-04 | global batch size: 256 | lm loss: 3.143531E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.500 | TFLOPs: 31.35 | +7: iteration 5470/ 14324 | consumed samples: 1400320 | consumed tokens: 2867855360 | elapsed time per iteration (s): 0.45 | learning rate: 1.443E-04 | global batch size: 256 | lm loss: 3.143794E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 567.024 | TFLOPs: 29.75 | +7: iteration 5480/ 14324 | consumed samples: 1402880 | consumed tokens: 2873098240 | elapsed time per iteration (s): 0.43 | learning rate: 1.441E-04 | global batch size: 256 | lm loss: 3.157535E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.676 | TFLOPs: 31.25 | +7: iteration 5490/ 14324 | consumed samples: 1405440 | consumed tokens: 2878341120 | elapsed time per iteration (s): 0.43 | learning rate: 1.439E-04 | global batch size: 256 | lm loss: 3.139786E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.358 | TFLOPs: 31.45 | +7: iteration 5500/ 14324 | consumed samples: 1408000 | consumed tokens: 2883584000 | elapsed time per iteration (s): 0.43 | learning rate: 1.437E-04 | global batch size: 256 | lm loss: 3.171481E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.258 | TFLOPs: 31.28 | +7: iteration 5510/ 14324 | consumed samples: 1410560 | consumed tokens: 2888826880 | elapsed time per iteration (s): 0.42 | learning rate: 1.435E-04 | global batch size: 256 | lm loss: 3.118989E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.176 | TFLOPs: 31.81 | +7: iteration 5520/ 14324 | consumed samples: 1413120 | consumed tokens: 2894069760 | elapsed time per iteration (s): 0.42 | learning rate: 1.434E-04 | global batch size: 256 | lm loss: 3.124584E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.256 | TFLOPs: 31.81 | +7: iteration 5530/ 14324 | consumed samples: 1415680 | consumed tokens: 2899312640 | elapsed time per iteration (s): 0.42 | learning rate: 1.432E-04 | global batch size: 256 | lm loss: 3.124644E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.050 | TFLOPs: 31.85 | +7: iteration 5540/ 14324 | consumed samples: 1418240 | consumed tokens: 2904555520 | elapsed time per iteration (s): 0.44 | learning rate: 1.430E-04 | global batch size: 256 | lm loss: 3.148060E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 583.993 | TFLOPs: 30.64 | +7: iteration 5550/ 14324 | consumed samples: 1420800 | consumed tokens: 2909798400 | elapsed time per iteration (s): 0.43 | learning rate: 1.428E-04 | global batch size: 256 | lm loss: 3.140011E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.612 | TFLOPs: 31.36 | +7: iteration 5560/ 14324 | consumed samples: 1423360 | consumed tokens: 2915041280 | elapsed time per iteration (s): 0.43 | learning rate: 1.426E-04 | global batch size: 256 | lm loss: 3.123942E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.183 | TFLOPs: 31.49 | +7: iteration 5570/ 14324 | consumed samples: 1425920 | consumed tokens: 2920284160 | elapsed time per iteration (s): 0.43 | learning rate: 1.424E-04 | global batch size: 256 | lm loss: 3.127097E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.294 | TFLOPs: 31.60 | +7: iteration 5580/ 14324 | consumed samples: 1428480 | consumed tokens: 2925527040 | elapsed time per iteration (s): 0.42 | learning rate: 1.422E-04 | global batch size: 256 | lm loss: 3.143382E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.100 | TFLOPs: 31.75 | +7: iteration 5590/ 14324 | consumed samples: 1431040 | consumed tokens: 2930769920 | elapsed time per iteration (s): 0.42 | learning rate: 1.421E-04 | global batch size: 256 | lm loss: 3.102041E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.589 | TFLOPs: 32.09 | +7: iteration 5600/ 14324 | consumed samples: 1433600 | consumed tokens: 2936012800 | elapsed time per iteration (s): 0.43 | learning rate: 1.419E-04 | global batch size: 256 | lm loss: 3.136273E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.804 | TFLOPs: 31.58 | +7: iteration 5610/ 14324 | consumed samples: 1436160 | consumed tokens: 2941255680 | elapsed time per iteration (s): 0.42 | learning rate: 1.417E-04 | global batch size: 256 | lm loss: 3.123215E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.062 | TFLOPs: 31.75 | +7: iteration 5620/ 14324 | consumed samples: 1438720 | consumed tokens: 2946498560 | elapsed time per iteration (s): 0.42 | learning rate: 1.415E-04 | global batch size: 256 | lm loss: 3.135095E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.972 | TFLOPs: 31.64 | +7: iteration 5630/ 14324 | consumed samples: 1441280 | consumed tokens: 2951741440 | elapsed time per iteration (s): 0.44 | learning rate: 1.413E-04 | global batch size: 256 | lm loss: 3.121027E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 583.868 | TFLOPs: 30.63 | +7: iteration 5640/ 14324 | consumed samples: 1443840 | consumed tokens: 2956984320 | elapsed time per iteration (s): 0.42 | learning rate: 1.411E-04 | global batch size: 256 | lm loss: 3.134102E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.290 | TFLOPs: 31.86 | +7: iteration 5650/ 14324 | consumed samples: 1446400 | consumed tokens: 2962227200 | elapsed time per iteration (s): 0.43 | learning rate: 1.409E-04 | global batch size: 256 | lm loss: 3.156570E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.441 | TFLOPs: 31.40 | +7: iteration 5660/ 14324 | consumed samples: 1448960 | consumed tokens: 2967470080 | elapsed time per iteration (s): 0.43 | learning rate: 1.407E-04 | global batch size: 256 | lm loss: 3.152253E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.584 | TFLOPs: 31.35 | +7: iteration 5670/ 14324 | consumed samples: 1451520 | consumed tokens: 2972712960 | elapsed time per iteration (s): 0.43 | learning rate: 1.406E-04 | global batch size: 256 | lm loss: 3.126071E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.987 | TFLOPs: 31.53 | +7: iteration 5680/ 14324 | consumed samples: 1454080 | consumed tokens: 2977955840 | elapsed time per iteration (s): 0.42 | learning rate: 1.404E-04 | global batch size: 256 | lm loss: 3.135388E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.708 | TFLOPs: 31.83 | +7: iteration 5690/ 14324 | consumed samples: 1456640 | consumed tokens: 2983198720 | elapsed time per iteration (s): 0.43 | learning rate: 1.402E-04 | global batch size: 256 | lm loss: 3.116244E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.669 | TFLOPs: 31.36 | +7: iteration 5700/ 14324 | consumed samples: 1459200 | consumed tokens: 2988441600 | elapsed time per iteration (s): 0.42 | learning rate: 1.400E-04 | global batch size: 256 | lm loss: 3.138599E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.519 | TFLOPs: 31.88 | +7: iteration 5710/ 14324 | consumed samples: 1461760 | consumed tokens: 2993684480 | elapsed time per iteration (s): 0.43 | learning rate: 1.398E-04 | global batch size: 256 | lm loss: 3.136431E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.735 | TFLOPs: 31.57 | +7: iteration 5720/ 14324 | consumed samples: 1464320 | consumed tokens: 2998927360 | elapsed time per iteration (s): 0.43 | learning rate: 1.396E-04 | global batch size: 256 | lm loss: 3.116471E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.791 | TFLOPs: 31.58 | +7: iteration 5730/ 14324 | consumed samples: 1466880 | consumed tokens: 3004170240 | elapsed time per iteration (s): 0.43 | learning rate: 1.394E-04 | global batch size: 256 | lm loss: 3.103837E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.255 | TFLOPs: 31.60 | +7: iteration 5740/ 14324 | consumed samples: 1469440 | consumed tokens: 3009413120 | elapsed time per iteration (s): 0.43 | learning rate: 1.392E-04 | global batch size: 256 | lm loss: 3.135303E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.905 | TFLOPs: 31.42 | +7: iteration 5750/ 14324 | consumed samples: 1472000 | consumed tokens: 3014656000 | elapsed time per iteration (s): 0.44 | learning rate: 1.391E-04 | global batch size: 256 | lm loss: 3.123209E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 582.722 | TFLOPs: 30.57 | +7: iteration 5760/ 14324 | consumed samples: 1474560 | consumed tokens: 3019898880 | elapsed time per iteration (s): 0.43 | learning rate: 1.389E-04 | global batch size: 256 | lm loss: 3.100846E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 588.661 | TFLOPs: 30.89 | +7: iteration 5770/ 14324 | consumed samples: 1477120 | consumed tokens: 3025141760 | elapsed time per iteration (s): 0.43 | learning rate: 1.387E-04 | global batch size: 256 | lm loss: 3.136662E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.818 | TFLOPs: 31.16 | +7: iteration 5780/ 14324 | consumed samples: 1479680 | consumed tokens: 3030384640 | elapsed time per iteration (s): 0.43 | learning rate: 1.385E-04 | global batch size: 256 | lm loss: 3.117080E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.301 | TFLOPs: 31.60 | +7: iteration 5790/ 14324 | consumed samples: 1482240 | consumed tokens: 3035627520 | elapsed time per iteration (s): 0.42 | learning rate: 1.383E-04 | global batch size: 256 | lm loss: 3.141878E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.561 | TFLOPs: 31.77 | +7: iteration 5800/ 14324 | consumed samples: 1484800 | consumed tokens: 3040870400 | elapsed time per iteration (s): 0.42 | learning rate: 1.381E-04 | global batch size: 256 | lm loss: 3.122855E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.744 | TFLOPs: 31.73 | +7: iteration 5810/ 14324 | consumed samples: 1487360 | consumed tokens: 3046113280 | elapsed time per iteration (s): 0.43 | learning rate: 1.379E-04 | global batch size: 256 | lm loss: 3.142717E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.875 | TFLOPs: 31.37 | +7: iteration 5820/ 14324 | consumed samples: 1489920 | consumed tokens: 3051356160 | elapsed time per iteration (s): 0.42 | learning rate: 1.377E-04 | global batch size: 256 | lm loss: 3.138383E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.119 | TFLOPs: 31.80 | +7: iteration 5830/ 14324 | consumed samples: 1492480 | consumed tokens: 3056599040 | elapsed time per iteration (s): 0.43 | learning rate: 1.375E-04 | global batch size: 256 | lm loss: 3.112963E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.124 | TFLOPs: 31.59 | +7: iteration 5840/ 14324 | consumed samples: 1495040 | consumed tokens: 3061841920 | elapsed time per iteration (s): 0.43 | learning rate: 1.373E-04 | global batch size: 256 | lm loss: 3.121640E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.258 | TFLOPs: 31.23 | +7: iteration 5850/ 14324 | consumed samples: 1497600 | consumed tokens: 3067084800 | elapsed time per iteration (s): 0.42 | learning rate: 1.372E-04 | global batch size: 256 | lm loss: 3.148872E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.899 | TFLOPs: 31.74 | +7: iteration 5860/ 14324 | consumed samples: 1500160 | consumed tokens: 3072327680 | elapsed time per iteration (s): 0.43 | learning rate: 1.370E-04 | global batch size: 256 | lm loss: 3.103885E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.334 | TFLOPs: 31.03 | +7: iteration 5870/ 14324 | consumed samples: 1502720 | consumed tokens: 3077570560 | elapsed time per iteration (s): 0.43 | learning rate: 1.368E-04 | global batch size: 256 | lm loss: 3.127122E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.261 | TFLOPs: 31.13 | +7: iteration 5880/ 14324 | consumed samples: 1505280 | consumed tokens: 3082813440 | elapsed time per iteration (s): 0.44 | learning rate: 1.366E-04 | global batch size: 256 | lm loss: 3.115460E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 576.335 | TFLOPs: 30.24 | +7: iteration 5890/ 14324 | consumed samples: 1507840 | consumed tokens: 3088056320 | elapsed time per iteration (s): 0.44 | learning rate: 1.364E-04 | global batch size: 256 | lm loss: 3.096558E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 577.779 | TFLOPs: 30.32 | +7: iteration 5900/ 14324 | consumed samples: 1510400 | consumed tokens: 3093299200 | elapsed time per iteration (s): 0.43 | learning rate: 1.362E-04 | global batch size: 256 | lm loss: 3.090215E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 588.729 | TFLOPs: 30.89 | +7: iteration 5910/ 14324 | consumed samples: 1512960 | consumed tokens: 3098542080 | elapsed time per iteration (s): 0.43 | learning rate: 1.360E-04 | global batch size: 256 | lm loss: 3.135409E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.864 | TFLOPs: 31.11 | +7: iteration 5920/ 14324 | consumed samples: 1515520 | consumed tokens: 3103784960 | elapsed time per iteration (s): 0.45 | learning rate: 1.358E-04 | global batch size: 256 | lm loss: 3.115731E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 574.010 | TFLOPs: 30.12 | +7: iteration 5930/ 14324 | consumed samples: 1518080 | consumed tokens: 3109027840 | elapsed time per iteration (s): 0.43 | learning rate: 1.356E-04 | global batch size: 256 | lm loss: 3.131042E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.533 | TFLOPs: 31.04 | +7: iteration 5940/ 14324 | consumed samples: 1520640 | consumed tokens: 3114270720 | elapsed time per iteration (s): 0.43 | learning rate: 1.354E-04 | global batch size: 256 | lm loss: 3.129781E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.230 | TFLOPs: 31.28 | +7: iteration 5950/ 14324 | consumed samples: 1523200 | consumed tokens: 3119513600 | elapsed time per iteration (s): 0.44 | learning rate: 1.353E-04 | global batch size: 256 | lm loss: 3.126079E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 581.277 | TFLOPs: 30.50 | +7: iteration 5960/ 14324 | consumed samples: 1525760 | consumed tokens: 3124756480 | elapsed time per iteration (s): 0.43 | learning rate: 1.351E-04 | global batch size: 256 | lm loss: 3.122614E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.762 | TFLOPs: 31.36 | +7: iteration 5970/ 14324 | consumed samples: 1528320 | consumed tokens: 3129999360 | elapsed time per iteration (s): 0.43 | learning rate: 1.349E-04 | global batch size: 256 | lm loss: 3.119445E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.878 | TFLOPs: 31.53 | +7: iteration 5980/ 14324 | consumed samples: 1530880 | consumed tokens: 3135242240 | elapsed time per iteration (s): 0.42 | learning rate: 1.347E-04 | global batch size: 256 | lm loss: 3.100858E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.786 | TFLOPs: 31.63 | +7: iteration 5990/ 14324 | consumed samples: 1533440 | consumed tokens: 3140485120 | elapsed time per iteration (s): 0.42 | learning rate: 1.345E-04 | global batch size: 256 | lm loss: 3.139393E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.837 | TFLOPs: 31.79 | +0: [2022-11-29 22:43:20,392] [INFO] [logging.py:68:log_dist] [Rank 0] step=6000, skipped=0, lr=[0.00013429302050146897, 0.00013429302050146897, 0.00013429302050146897], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 6000/ 14324 | consumed samples: 1536000 | consumed tokens: 3145728000 | elapsed time per iteration (s): 0.43 | learning rate: 1.343E-04 | global batch size: 256 | lm loss: 3.108689E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.589 | TFLOPs: 31.30 | +0: steps: 6000 loss: 3.0650 iter time (s): 0.426 samples/sec: 601.005 +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 6000 | lm loss value: 2.997779E+00 | lm loss PPL: 2.004098E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 6000 to checkpoints_220moscar +0: [2022-11-29 22:43:20,586] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step6000 is begin to save! +0: [2022-11-29 22:43:20,589] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/layer_01-model_00-model_states.pt... +0: [2022-11-29 22:43:20,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/layer_01-model_00-model_states.pt. +0: [2022-11-29 22:43:20,691] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/layer_03-model_00-model_states.pt... +0: [2022-11-29 22:43:20,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/layer_03-model_00-model_states.pt. +0: [2022-11-29 22:43:20,712] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/layer_04-model_00-model_states.pt... +0: [2022-11-29 22:43:20,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/layer_04-model_00-model_states.pt. +0: [2022-11-29 22:43:20,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/layer_05-model_00-model_states.pt... +0: [2022-11-29 22:43:20,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/layer_05-model_00-model_states.pt. +0: [2022-11-29 22:43:20,759] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/layer_06-model_00-model_states.pt... +0: [2022-11-29 22:43:20,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/layer_06-model_00-model_states.pt. +0: [2022-11-29 22:43:20,782] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/layer_07-model_00-model_states.pt... +0: [2022-11-29 22:43:20,805] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/layer_07-model_00-model_states.pt. +0: [2022-11-29 22:43:20,806] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/layer_08-model_00-model_states.pt... +0: [2022-11-29 22:43:20,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/layer_08-model_00-model_states.pt. +0: [2022-11-29 22:43:20,831] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/layer_09-model_00-model_states.pt... +0: [2022-11-29 22:43:20,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/layer_09-model_00-model_states.pt. +0: [2022-11-29 22:43:20,855] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/layer_10-model_00-model_states.pt... +0: [2022-11-29 22:43:20,878] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/layer_10-model_00-model_states.pt. +0: [2022-11-29 22:43:20,878] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/layer_11-model_00-model_states.pt... +0: [2022-11-29 22:43:20,901] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/layer_11-model_00-model_states.pt. +0: [2022-11-29 22:43:20,901] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/layer_12-model_00-model_states.pt... +0: [2022-11-29 22:43:20,924] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/layer_12-model_00-model_states.pt. +0: [2022-11-29 22:43:20,924] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/layer_13-model_00-model_states.pt... +0: [2022-11-29 22:43:20,947] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/layer_13-model_00-model_states.pt. +0: [2022-11-29 22:43:20,947] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/layer_14-model_00-model_states.pt... +0: [2022-11-29 22:43:20,971] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/layer_14-model_00-model_states.pt. +0: [2022-11-29 22:43:20,971] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/layer_15-model_00-model_states.pt... +0: [2022-11-29 22:43:20,995] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/layer_15-model_00-model_states.pt. +0: [2022-11-29 22:43:20,995] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/layer_16-model_00-model_states.pt... +0: [2022-11-29 22:43:21,018] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/layer_16-model_00-model_states.pt. +0: [2022-11-29 22:43:21,019] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/layer_17-model_00-model_states.pt... +0: [2022-11-29 22:43:21,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/layer_17-model_00-model_states.pt. +0: [2022-11-29 22:43:21,042] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/layer_18-model_00-model_states.pt... +0: [2022-11-29 22:43:21,066] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/layer_18-model_00-model_states.pt. +0: [2022-11-29 22:43:21,066] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/layer_19-model_00-model_states.pt... +0: [2022-11-29 22:43:21,091] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/layer_19-model_00-model_states.pt. +0: [2022-11-29 22:43:21,092] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/layer_20-model_00-model_states.pt... +0: [2022-11-29 22:43:21,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/layer_20-model_00-model_states.pt. +0: [2022-11-29 22:43:21,115] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/layer_22-model_00-model_states.pt... +0: [2022-11-29 22:43:21,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/layer_22-model_00-model_states.pt. +0: [2022-11-29 22:43:21,119] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_220moscar/global_step6000/mp_rank_00_model_states.pt +0: [2022-11-29 22:43:21,119] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/mp_rank_00_model_states.pt... +0: [2022-11-29 22:43:21,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/mp_rank_00_model_states.pt. +0: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:43:21,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:43:21,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:43:21,186] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 22:43:21,186] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 22:43:21,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:43:21,189] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 22:43:21,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 22:43:21,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:43:21,189] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 22:43:21,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 22:43:21,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:43:21,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 22:43:21,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 22:43:21,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:43:21,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:43:21,191] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 22:43:21,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 22:43:21,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:43:21,191] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 22:43:21,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 22:43:21,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:43:21,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:43:21,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:43:21,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:43:21,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 22:43:21,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 22:43:21,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 22:43:21,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 22:43:21,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 22:43:21,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 22:43:21,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 22:43:21,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 22:43:21,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:43:21,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 22:43:21,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 22:43:21,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:43:21,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:43:21,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 22:43:21,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 22:43:21,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:43:21,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 22:43:21,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 22:43:21,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:43:21,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 22:43:21,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 22:43:21,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:43:21,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 22:43:21,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 22:43:21,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:43:21,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 22:43:21,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:43:21,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 22:43:21,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 22:43:21,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:43:21,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 22:43:21,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 22:43:21,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 22:43:21,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:43:21,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 22:43:21,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 22:43:21,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:43:21,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 22:43:21,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 22:43:21,197] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:43:21,197] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:43:21,197] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +6: [2022-11-29 22:43:21,197] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +3: [2022-11-29 22:43:21,197] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 22:43:21,197] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 22:43:21,197] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:43:21,197] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 22:43:21,197] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 22:43:21,197] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:43:21,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 22:43:21,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 22:43:21,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:43:21,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:43:21,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 22:43:21,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 22:43:21,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 22:43:21,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 22:43:21,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:43:21,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 22:43:21,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 22:43:21,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:43:21,200] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 22:43:21,200] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 22:43:21,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:43:21,200] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 22:43:21,200] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 22:43:21,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:43:21,200] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 22:43:21,201] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 22:43:21,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:43:21,201] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 22:43:21,201] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 22:43:21,201] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:43:21,201] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 22:43:21,201] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 22:43:21,201] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:43:21,201] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 22:43:21,201] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 22:43:21,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:43:21,202] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 22:43:21,202] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 22:43:21,204] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:43:21,204] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:43:21,204] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 22:43:21,204] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 22:43:21,204] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 22:43:21,204] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 22:43:21,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 22:43:21,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 22:43:21,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:43:21,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 22:43:21,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 22:43:21,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:43:21,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 22:43:21,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 22:43:21,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:43:21,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 22:43:21,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 22:43:21,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:43:21,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 22:43:21,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 22:43:21,197] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:43:21,197] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 22:43:21,197] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 22:43:21,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:43:21,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:43:21,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 22:43:21,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 22:43:21,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 22:43:21,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 22:43:21,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:43:21,207] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 22:43:21,208] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 22:43:21,208] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:43:21,208] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:43:21,208] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:43:21,208] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 22:43:21,208] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 22:43:21,208] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 22:43:21,208] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 22:43:21,208] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 22:43:21,208] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 22:43:21,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 22:43:21,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 22:43:21,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:43:21,191] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 22:43:21,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 22:43:21,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:43:21,191] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 22:43:21,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 22:43:21,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:43:21,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 22:43:21,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 22:43:21,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:43:21,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 22:43:21,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 22:43:21,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:43:21,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 22:43:21,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 22:43:21,196] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:43:21,196] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 22:43:21,196] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 22:43:21,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:43:21,207] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 22:43:21,207] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 22:43:21,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:43:21,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:43:21,213] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 22:43:21,213] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 22:43:21,213] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:43:21,213] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 22:43:21,213] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 22:43:21,214] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:43:21,214] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 22:43:21,214] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 22:43:21,215] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:43:21,215] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 22:43:21,215] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 22:43:21,219] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:43:21,219] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:43:21,219] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 22:43:21,219] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 22:43:21,219] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 22:43:21,219] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 22:43:21,219] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:43:21,219] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 22:43:21,219] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 22:43:21,245] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step6000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 22:43:21,245] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: successfully saved checkpoint at iteration 6000 to checkpoints_220moscar +7: time (ms) | save-checkpoint: 672.17 +7: iteration 6010/ 14324 | consumed samples: 1538560 | consumed tokens: 3150970880 | elapsed time per iteration (s): 0.51 | learning rate: 1.341E-04 | global batch size: 256 | lm loss: 3.122769E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 506.441 | TFLOPs: 26.57 | +7: iteration 6020/ 14324 | consumed samples: 1541120 | consumed tokens: 3156213760 | elapsed time per iteration (s): 0.44 | learning rate: 1.339E-04 | global batch size: 256 | lm loss: 3.129491E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 577.811 | TFLOPs: 30.32 | +7: iteration 6030/ 14324 | consumed samples: 1543680 | consumed tokens: 3161456640 | elapsed time per iteration (s): 0.44 | learning rate: 1.337E-04 | global batch size: 256 | lm loss: 3.139824E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 580.677 | TFLOPs: 30.47 | +7: iteration 6040/ 14324 | consumed samples: 1546240 | consumed tokens: 3166699520 | elapsed time per iteration (s): 0.42 | learning rate: 1.335E-04 | global batch size: 256 | lm loss: 3.089727E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.072 | TFLOPs: 31.69 | +7: iteration 6050/ 14324 | consumed samples: 1548800 | consumed tokens: 3171942400 | elapsed time per iteration (s): 0.43 | learning rate: 1.333E-04 | global batch size: 256 | lm loss: 3.090973E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.112 | TFLOPs: 31.54 | +7: iteration 6060/ 14324 | consumed samples: 1551360 | consumed tokens: 3177185280 | elapsed time per iteration (s): 0.43 | learning rate: 1.331E-04 | global batch size: 256 | lm loss: 3.105990E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 589.740 | TFLOPs: 30.94 | +7: iteration 6070/ 14324 | consumed samples: 1553920 | consumed tokens: 3182428160 | elapsed time per iteration (s): 0.43 | learning rate: 1.329E-04 | global batch size: 256 | lm loss: 3.136652E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.492 | TFLOPs: 31.56 | +7: iteration 6080/ 14324 | consumed samples: 1556480 | consumed tokens: 3187671040 | elapsed time per iteration (s): 0.43 | learning rate: 1.328E-04 | global batch size: 256 | lm loss: 3.090331E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.373 | TFLOPs: 31.40 | +7: iteration 6090/ 14324 | consumed samples: 1559040 | consumed tokens: 3192913920 | elapsed time per iteration (s): 0.43 | learning rate: 1.326E-04 | global batch size: 256 | lm loss: 3.154204E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 589.629 | TFLOPs: 30.94 | +7: iteration 6100/ 14324 | consumed samples: 1561600 | consumed tokens: 3198156800 | elapsed time per iteration (s): 0.43 | learning rate: 1.324E-04 | global batch size: 256 | lm loss: 3.112397E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.478 | TFLOPs: 31.03 | +7: iteration 6110/ 14324 | consumed samples: 1564160 | consumed tokens: 3203399680 | elapsed time per iteration (s): 0.42 | learning rate: 1.322E-04 | global batch size: 256 | lm loss: 3.124814E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.727 | TFLOPs: 31.78 | +7: iteration 6120/ 14324 | consumed samples: 1566720 | consumed tokens: 3208642560 | elapsed time per iteration (s): 0.43 | learning rate: 1.320E-04 | global batch size: 256 | lm loss: 3.107064E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.158 | TFLOPs: 31.49 | +7: iteration 6130/ 14324 | consumed samples: 1569280 | consumed tokens: 3213885440 | elapsed time per iteration (s): 0.42 | learning rate: 1.318E-04 | global batch size: 256 | lm loss: 3.103277E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.563 | TFLOPs: 31.72 | +7: iteration 6140/ 14324 | consumed samples: 1571840 | consumed tokens: 3219128320 | elapsed time per iteration (s): 0.43 | learning rate: 1.316E-04 | global batch size: 256 | lm loss: 3.081936E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.281 | TFLOPs: 31.08 | +7: iteration 6150/ 14324 | consumed samples: 1574400 | consumed tokens: 3224371200 | elapsed time per iteration (s): 0.42 | learning rate: 1.314E-04 | global batch size: 256 | lm loss: 3.105936E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.874 | TFLOPs: 31.68 | +7: iteration 6160/ 14324 | consumed samples: 1576960 | consumed tokens: 3229614080 | elapsed time per iteration (s): 0.43 | learning rate: 1.312E-04 | global batch size: 256 | lm loss: 3.107174E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.672 | TFLOPs: 31.20 | +7: iteration 6170/ 14324 | consumed samples: 1579520 | consumed tokens: 3234856960 | elapsed time per iteration (s): 0.44 | learning rate: 1.310E-04 | global batch size: 256 | lm loss: 3.112344E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 581.009 | TFLOPs: 30.48 | +7: iteration 6180/ 14324 | consumed samples: 1582080 | consumed tokens: 3240099840 | elapsed time per iteration (s): 0.43 | learning rate: 1.308E-04 | global batch size: 256 | lm loss: 3.111002E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.561 | TFLOPs: 31.14 | +7: iteration 6190/ 14324 | consumed samples: 1584640 | consumed tokens: 3245342720 | elapsed time per iteration (s): 0.43 | learning rate: 1.306E-04 | global batch size: 256 | lm loss: 3.092962E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 589.390 | TFLOPs: 30.92 | +7: iteration 6200/ 14324 | consumed samples: 1587200 | consumed tokens: 3250585600 | elapsed time per iteration (s): 0.42 | learning rate: 1.304E-04 | global batch size: 256 | lm loss: 3.104265E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.421 | TFLOPs: 31.82 | +7: iteration 6210/ 14324 | consumed samples: 1589760 | consumed tokens: 3255828480 | elapsed time per iteration (s): 0.43 | learning rate: 1.302E-04 | global batch size: 256 | lm loss: 3.077032E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.777 | TFLOPs: 31.57 | +7: iteration 6220/ 14324 | consumed samples: 1592320 | consumed tokens: 3261071360 | elapsed time per iteration (s): 0.43 | learning rate: 1.300E-04 | global batch size: 256 | lm loss: 3.132410E+00 | grad norm: 0.474 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.696 | TFLOPs: 31.20 | +7: iteration 6230/ 14324 | consumed samples: 1594880 | consumed tokens: 3266314240 | elapsed time per iteration (s): 0.42 | learning rate: 1.298E-04 | global batch size: 256 | lm loss: 3.117193E+00 | grad norm: 0.455 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.575 | TFLOPs: 31.67 | +7: iteration 6240/ 14324 | consumed samples: 1597440 | consumed tokens: 3271557120 | elapsed time per iteration (s): 0.44 | learning rate: 1.297E-04 | global batch size: 256 | lm loss: 3.107580E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 583.473 | TFLOPs: 30.61 | +7: iteration 6250/ 14324 | consumed samples: 1600000 | consumed tokens: 3276800000 | elapsed time per iteration (s): 0.42 | learning rate: 1.295E-04 | global batch size: 256 | lm loss: 3.104695E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.674 | TFLOPs: 31.73 | +7: iteration 6260/ 14324 | consumed samples: 1602560 | consumed tokens: 3282042880 | elapsed time per iteration (s): 0.43 | learning rate: 1.293E-04 | global batch size: 256 | lm loss: 3.116899E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 589.933 | TFLOPs: 30.95 | +7: iteration 6270/ 14324 | consumed samples: 1605120 | consumed tokens: 3287285760 | elapsed time per iteration (s): 0.42 | learning rate: 1.291E-04 | global batch size: 256 | lm loss: 3.126271E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.417 | TFLOPs: 31.61 | +7: iteration 6280/ 14324 | consumed samples: 1607680 | consumed tokens: 3292528640 | elapsed time per iteration (s): 0.45 | learning rate: 1.289E-04 | global batch size: 256 | lm loss: 3.091992E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 571.100 | TFLOPs: 29.96 | +7: iteration 6290/ 14324 | consumed samples: 1610240 | consumed tokens: 3297771520 | elapsed time per iteration (s): 0.43 | learning rate: 1.287E-04 | global batch size: 256 | lm loss: 3.096645E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.827 | TFLOPs: 31.37 | +7: iteration 6300/ 14324 | consumed samples: 1612800 | consumed tokens: 3303014400 | elapsed time per iteration (s): 0.42 | learning rate: 1.285E-04 | global batch size: 256 | lm loss: 3.108934E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.771 | TFLOPs: 31.63 | +7: iteration 6310/ 14324 | consumed samples: 1615360 | consumed tokens: 3308257280 | elapsed time per iteration (s): 0.43 | learning rate: 1.283E-04 | global batch size: 256 | lm loss: 3.083715E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 589.283 | TFLOPs: 30.92 | +7: iteration 6320/ 14324 | consumed samples: 1617920 | consumed tokens: 3313500160 | elapsed time per iteration (s): 0.43 | learning rate: 1.281E-04 | global batch size: 256 | lm loss: 3.086958E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.300 | TFLOPs: 31.23 | +7: iteration 6330/ 14324 | consumed samples: 1620480 | consumed tokens: 3318743040 | elapsed time per iteration (s): 0.43 | learning rate: 1.279E-04 | global batch size: 256 | lm loss: 3.085415E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.826 | TFLOPs: 31.21 | +7: iteration 6340/ 14324 | consumed samples: 1623040 | consumed tokens: 3323985920 | elapsed time per iteration (s): 0.43 | learning rate: 1.277E-04 | global batch size: 256 | lm loss: 3.096159E+00 | grad norm: 0.686 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.536 | TFLOPs: 31.19 | +7: iteration 6350/ 14324 | consumed samples: 1625600 | consumed tokens: 3329228800 | elapsed time per iteration (s): 0.43 | learning rate: 1.275E-04 | global batch size: 256 | lm loss: 3.124378E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.929 | TFLOPs: 31.27 | +7: iteration 6360/ 14324 | consumed samples: 1628160 | consumed tokens: 3334471680 | elapsed time per iteration (s): 0.42 | learning rate: 1.273E-04 | global batch size: 256 | lm loss: 3.079340E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.330 | TFLOPs: 32.02 | +7: iteration 6370/ 14324 | consumed samples: 1630720 | consumed tokens: 3339714560 | elapsed time per iteration (s): 0.45 | learning rate: 1.271E-04 | global batch size: 256 | lm loss: 3.099089E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 569.648 | TFLOPs: 29.89 | +7: iteration 6380/ 14324 | consumed samples: 1633280 | consumed tokens: 3344957440 | elapsed time per iteration (s): 0.44 | learning rate: 1.269E-04 | global batch size: 256 | lm loss: 3.094303E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 587.123 | TFLOPs: 30.81 | +7: iteration 6390/ 14324 | consumed samples: 1635840 | consumed tokens: 3350200320 | elapsed time per iteration (s): 0.43 | learning rate: 1.267E-04 | global batch size: 256 | lm loss: 3.099346E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.503 | TFLOPs: 31.40 | +7: iteration 6400/ 14324 | consumed samples: 1638400 | consumed tokens: 3355443200 | elapsed time per iteration (s): 0.45 | learning rate: 1.265E-04 | global batch size: 256 | lm loss: 3.119956E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 572.400 | TFLOPs: 30.03 | +7: iteration 6410/ 14324 | consumed samples: 1640960 | consumed tokens: 3360686080 | elapsed time per iteration (s): 0.43 | learning rate: 1.263E-04 | global batch size: 256 | lm loss: 3.096670E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.738 | TFLOPs: 31.41 | +7: iteration 6420/ 14324 | consumed samples: 1643520 | consumed tokens: 3365928960 | elapsed time per iteration (s): 0.43 | learning rate: 1.261E-04 | global batch size: 256 | lm loss: 3.103992E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.067 | TFLOPs: 31.43 | +7: iteration 6430/ 14324 | consumed samples: 1646080 | consumed tokens: 3371171840 | elapsed time per iteration (s): 0.43 | learning rate: 1.259E-04 | global batch size: 256 | lm loss: 3.102613E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.890 | TFLOPs: 31.42 | +7: iteration 6440/ 14324 | consumed samples: 1648640 | consumed tokens: 3376414720 | elapsed time per iteration (s): 0.43 | learning rate: 1.257E-04 | global batch size: 256 | lm loss: 3.096601E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.182 | TFLOPs: 31.23 | +7: iteration 6450/ 14324 | consumed samples: 1651200 | consumed tokens: 3381657600 | elapsed time per iteration (s): 0.43 | learning rate: 1.255E-04 | global batch size: 256 | lm loss: 3.105725E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.390 | TFLOPs: 31.45 | +7: iteration 6460/ 14324 | consumed samples: 1653760 | consumed tokens: 3386900480 | elapsed time per iteration (s): 0.42 | learning rate: 1.254E-04 | global batch size: 256 | lm loss: 3.094625E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.913 | TFLOPs: 31.79 | +7: iteration 6470/ 14324 | consumed samples: 1656320 | consumed tokens: 3392143360 | elapsed time per iteration (s): 0.43 | learning rate: 1.252E-04 | global batch size: 256 | lm loss: 3.119243E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.965 | TFLOPs: 31.48 | +7: iteration 6480/ 14324 | consumed samples: 1658880 | consumed tokens: 3397386240 | elapsed time per iteration (s): 0.43 | learning rate: 1.250E-04 | global batch size: 256 | lm loss: 3.091654E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.365 | TFLOPs: 31.29 | +7: iteration 6490/ 14324 | consumed samples: 1661440 | consumed tokens: 3402629120 | elapsed time per iteration (s): 0.43 | learning rate: 1.248E-04 | global batch size: 256 | lm loss: 3.097129E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.189 | TFLOPs: 31.39 | +7: iteration 6500/ 14324 | consumed samples: 1664000 | consumed tokens: 3407872000 | elapsed time per iteration (s): 0.42 | learning rate: 1.246E-04 | global batch size: 256 | lm loss: 3.092258E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.006 | TFLOPs: 31.74 | +7: iteration 6510/ 14324 | consumed samples: 1666560 | consumed tokens: 3413114880 | elapsed time per iteration (s): 0.43 | learning rate: 1.244E-04 | global batch size: 256 | lm loss: 3.078282E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.420 | TFLOPs: 31.40 | +7: iteration 6520/ 14324 | consumed samples: 1669120 | consumed tokens: 3418357760 | elapsed time per iteration (s): 0.43 | learning rate: 1.242E-04 | global batch size: 256 | lm loss: 3.083643E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.981 | TFLOPs: 31.58 | +7: iteration 6530/ 14324 | consumed samples: 1671680 | consumed tokens: 3423600640 | elapsed time per iteration (s): 0.43 | learning rate: 1.240E-04 | global batch size: 256 | lm loss: 3.058769E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.521 | TFLOPs: 31.56 | +7: iteration 6540/ 14324 | consumed samples: 1674240 | consumed tokens: 3428843520 | elapsed time per iteration (s): 0.42 | learning rate: 1.238E-04 | global batch size: 256 | lm loss: 3.075410E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.535 | TFLOPs: 31.82 | +7: iteration 6550/ 14324 | consumed samples: 1676800 | consumed tokens: 3434086400 | elapsed time per iteration (s): 0.43 | learning rate: 1.236E-04 | global batch size: 256 | lm loss: 3.095991E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.940 | TFLOPs: 31.48 | +7: iteration 6560/ 14324 | consumed samples: 1679360 | consumed tokens: 3439329280 | elapsed time per iteration (s): 0.43 | learning rate: 1.234E-04 | global batch size: 256 | lm loss: 3.073340E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.364 | TFLOPs: 31.24 | +7: iteration 6570/ 14324 | consumed samples: 1681920 | consumed tokens: 3444572160 | elapsed time per iteration (s): 0.42 | learning rate: 1.232E-04 | global batch size: 256 | lm loss: 3.076906E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.841 | TFLOPs: 31.74 | +7: iteration 6580/ 14324 | consumed samples: 1684480 | consumed tokens: 3449815040 | elapsed time per iteration (s): 0.44 | learning rate: 1.230E-04 | global batch size: 256 | lm loss: 3.103157E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 579.249 | TFLOPs: 30.39 | +7: iteration 6590/ 14324 | consumed samples: 1687040 | consumed tokens: 3455057920 | elapsed time per iteration (s): 0.42 | learning rate: 1.228E-04 | global batch size: 256 | lm loss: 3.092741E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.369 | TFLOPs: 31.76 | +7: iteration 6600/ 14324 | consumed samples: 1689600 | consumed tokens: 3460300800 | elapsed time per iteration (s): 0.42 | learning rate: 1.226E-04 | global batch size: 256 | lm loss: 3.121839E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.179 | TFLOPs: 31.86 | +7: iteration 6610/ 14324 | consumed samples: 1692160 | consumed tokens: 3465543680 | elapsed time per iteration (s): 0.42 | learning rate: 1.224E-04 | global batch size: 256 | lm loss: 3.097747E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.191 | TFLOPs: 31.65 | +7: iteration 6620/ 14324 | consumed samples: 1694720 | consumed tokens: 3470786560 | elapsed time per iteration (s): 0.43 | learning rate: 1.222E-04 | global batch size: 256 | lm loss: 3.065794E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.050 | TFLOPs: 31.17 | +7: iteration 6630/ 14324 | consumed samples: 1697280 | consumed tokens: 3476029440 | elapsed time per iteration (s): 0.43 | learning rate: 1.220E-04 | global batch size: 256 | lm loss: 3.091212E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.555 | TFLOPs: 31.09 | +7: iteration 6640/ 14324 | consumed samples: 1699840 | consumed tokens: 3481272320 | elapsed time per iteration (s): 0.43 | learning rate: 1.218E-04 | global batch size: 256 | lm loss: 3.072179E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.726 | TFLOPs: 31.41 | +7: iteration 6650/ 14324 | consumed samples: 1702400 | consumed tokens: 3486515200 | elapsed time per iteration (s): 0.43 | learning rate: 1.216E-04 | global batch size: 256 | lm loss: 3.078905E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.499 | TFLOPs: 31.51 | +7: iteration 6660/ 14324 | consumed samples: 1704960 | consumed tokens: 3491758080 | elapsed time per iteration (s): 0.43 | learning rate: 1.214E-04 | global batch size: 256 | lm loss: 3.099359E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.294 | TFLOPs: 31.39 | +7: iteration 6670/ 14324 | consumed samples: 1707520 | consumed tokens: 3497000960 | elapsed time per iteration (s): 0.42 | learning rate: 1.212E-04 | global batch size: 256 | lm loss: 3.078979E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.045 | TFLOPs: 32.01 | +7: iteration 6680/ 14324 | consumed samples: 1710080 | consumed tokens: 3502243840 | elapsed time per iteration (s): 0.43 | learning rate: 1.210E-04 | global batch size: 256 | lm loss: 3.088789E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.176 | TFLOPs: 31.02 | +7: iteration 6690/ 14324 | consumed samples: 1712640 | consumed tokens: 3507486720 | elapsed time per iteration (s): 0.43 | learning rate: 1.208E-04 | global batch size: 256 | lm loss: 3.089614E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.502 | TFLOPs: 31.56 | +7: iteration 6700/ 14324 | consumed samples: 1715200 | consumed tokens: 3512729600 | elapsed time per iteration (s): 0.42 | learning rate: 1.206E-04 | global batch size: 256 | lm loss: 3.065908E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.526 | TFLOPs: 31.82 | +7: iteration 6710/ 14324 | consumed samples: 1717760 | consumed tokens: 3517972480 | elapsed time per iteration (s): 0.45 | learning rate: 1.204E-04 | global batch size: 256 | lm loss: 3.091195E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 574.406 | TFLOPs: 30.14 | +7: iteration 6720/ 14324 | consumed samples: 1720320 | consumed tokens: 3523215360 | elapsed time per iteration (s): 0.43 | learning rate: 1.202E-04 | global batch size: 256 | lm loss: 3.067017E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.145 | TFLOPs: 31.59 | +7: iteration 6730/ 14324 | consumed samples: 1722880 | consumed tokens: 3528458240 | elapsed time per iteration (s): 0.43 | learning rate: 1.200E-04 | global batch size: 256 | lm loss: 3.083548E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.267 | TFLOPs: 31.08 | +7: iteration 6740/ 14324 | consumed samples: 1725440 | consumed tokens: 3533701120 | elapsed time per iteration (s): 0.43 | learning rate: 1.198E-04 | global batch size: 256 | lm loss: 3.099006E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.452 | TFLOPs: 31.08 | +7: iteration 6750/ 14324 | consumed samples: 1728000 | consumed tokens: 3538944000 | elapsed time per iteration (s): 0.43 | learning rate: 1.196E-04 | global batch size: 256 | lm loss: 3.095235E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.530 | TFLOPs: 31.46 | +7: iteration 6760/ 14324 | consumed samples: 1730560 | consumed tokens: 3544186880 | elapsed time per iteration (s): 0.43 | learning rate: 1.194E-04 | global batch size: 256 | lm loss: 3.076719E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.784 | TFLOPs: 31.42 | +7: iteration 6770/ 14324 | consumed samples: 1733120 | consumed tokens: 3549429760 | elapsed time per iteration (s): 0.43 | learning rate: 1.192E-04 | global batch size: 256 | lm loss: 3.110544E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.182 | TFLOPs: 31.33 | +7: iteration 6780/ 14324 | consumed samples: 1735680 | consumed tokens: 3554672640 | elapsed time per iteration (s): 0.43 | learning rate: 1.190E-04 | global batch size: 256 | lm loss: 3.058544E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.336 | TFLOPs: 31.55 | +7: iteration 6790/ 14324 | consumed samples: 1738240 | consumed tokens: 3559915520 | elapsed time per iteration (s): 0.43 | learning rate: 1.188E-04 | global batch size: 256 | lm loss: 3.071261E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.261 | TFLOPs: 31.60 | +7: iteration 6800/ 14324 | consumed samples: 1740800 | consumed tokens: 3565158400 | elapsed time per iteration (s): 0.42 | learning rate: 1.186E-04 | global batch size: 256 | lm loss: 3.126271E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.846 | TFLOPs: 31.79 | +7: iteration 6810/ 14324 | consumed samples: 1743360 | consumed tokens: 3570401280 | elapsed time per iteration (s): 0.42 | learning rate: 1.184E-04 | global batch size: 256 | lm loss: 3.052689E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.866 | TFLOPs: 31.95 | +7: iteration 6820/ 14324 | consumed samples: 1745920 | consumed tokens: 3575644160 | elapsed time per iteration (s): 0.43 | learning rate: 1.182E-04 | global batch size: 256 | lm loss: 3.088702E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.447 | TFLOPs: 31.40 | +7: iteration 6830/ 14324 | consumed samples: 1748480 | consumed tokens: 3580887040 | elapsed time per iteration (s): 0.43 | learning rate: 1.180E-04 | global batch size: 256 | lm loss: 3.082067E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.867 | TFLOPs: 31.47 | +7: iteration 6840/ 14324 | consumed samples: 1751040 | consumed tokens: 3586129920 | elapsed time per iteration (s): 0.43 | learning rate: 1.178E-04 | global batch size: 256 | lm loss: 3.088606E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.866 | TFLOPs: 31.21 | +7: iteration 6850/ 14324 | consumed samples: 1753600 | consumed tokens: 3591372800 | elapsed time per iteration (s): 0.42 | learning rate: 1.176E-04 | global batch size: 256 | lm loss: 3.066836E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.032 | TFLOPs: 31.75 | +7: iteration 6860/ 14324 | consumed samples: 1756160 | consumed tokens: 3596615680 | elapsed time per iteration (s): 0.43 | learning rate: 1.174E-04 | global batch size: 256 | lm loss: 3.050017E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.205 | TFLOPs: 31.60 | +7: iteration 6870/ 14324 | consumed samples: 1758720 | consumed tokens: 3601858560 | elapsed time per iteration (s): 0.43 | learning rate: 1.172E-04 | global batch size: 256 | lm loss: 3.060190E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.775 | TFLOPs: 31.47 | +7: iteration 6880/ 14324 | consumed samples: 1761280 | consumed tokens: 3607101440 | elapsed time per iteration (s): 0.42 | learning rate: 1.170E-04 | global batch size: 256 | lm loss: 3.057983E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.582 | TFLOPs: 31.83 | +7: iteration 6890/ 14324 | consumed samples: 1763840 | consumed tokens: 3612344320 | elapsed time per iteration (s): 0.42 | learning rate: 1.168E-04 | global batch size: 256 | lm loss: 3.081608E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.629 | TFLOPs: 31.88 | +7: iteration 6900/ 14324 | consumed samples: 1766400 | consumed tokens: 3617587200 | elapsed time per iteration (s): 0.43 | learning rate: 1.166E-04 | global batch size: 256 | lm loss: 3.082106E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.690 | TFLOPs: 31.20 | +7: iteration 6910/ 14324 | consumed samples: 1768960 | consumed tokens: 3622830080 | elapsed time per iteration (s): 0.42 | learning rate: 1.164E-04 | global batch size: 256 | lm loss: 3.067920E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.351 | TFLOPs: 31.92 | +7: iteration 6920/ 14324 | consumed samples: 1771520 | consumed tokens: 3628072960 | elapsed time per iteration (s): 0.42 | learning rate: 1.162E-04 | global batch size: 256 | lm loss: 3.079460E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.777 | TFLOPs: 31.63 | +7: iteration 6930/ 14324 | consumed samples: 1774080 | consumed tokens: 3633315840 | elapsed time per iteration (s): 0.44 | learning rate: 1.161E-04 | global batch size: 256 | lm loss: 3.064230E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 578.028 | TFLOPs: 30.33 | +7: iteration 6940/ 14324 | consumed samples: 1776640 | consumed tokens: 3638558720 | elapsed time per iteration (s): 0.42 | learning rate: 1.159E-04 | global batch size: 256 | lm loss: 3.058955E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.456 | TFLOPs: 31.61 | +7: iteration 6950/ 14324 | consumed samples: 1779200 | consumed tokens: 3643801600 | elapsed time per iteration (s): 0.42 | learning rate: 1.157E-04 | global batch size: 256 | lm loss: 3.078575E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.928 | TFLOPs: 32.16 | +7: iteration 6960/ 14324 | consumed samples: 1781760 | consumed tokens: 3649044480 | elapsed time per iteration (s): 0.43 | learning rate: 1.155E-04 | global batch size: 256 | lm loss: 3.050710E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.250 | TFLOPs: 31.49 | +7: iteration 6970/ 14324 | consumed samples: 1784320 | consumed tokens: 3654287360 | elapsed time per iteration (s): 0.42 | learning rate: 1.153E-04 | global batch size: 256 | lm loss: 3.066114E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.573 | TFLOPs: 31.62 | +7: iteration 6980/ 14324 | consumed samples: 1786880 | consumed tokens: 3659530240 | elapsed time per iteration (s): 0.43 | learning rate: 1.151E-04 | global batch size: 256 | lm loss: 3.027691E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.755 | TFLOPs: 31.57 | +7: iteration 6990/ 14324 | consumed samples: 1789440 | consumed tokens: 3664773120 | elapsed time per iteration (s): 0.42 | learning rate: 1.149E-04 | global batch size: 256 | lm loss: 3.055424E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.559 | TFLOPs: 31.67 | +7: iteration 7000/ 14324 | consumed samples: 1792000 | consumed tokens: 3670016000 | elapsed time per iteration (s): 0.43 | learning rate: 1.147E-04 | global batch size: 256 | lm loss: 3.072550E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.170 | TFLOPs: 31.59 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 7000 | lm loss value: 2.953317E+00 | lm loss PPL: 1.916944E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 7000 to checkpoints_220moscar +0: [2022-11-29 22:50:29,852] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step7000 is begin to save! +0: [2022-11-29 22:50:29,856] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/layer_01-model_00-model_states.pt... +0: [2022-11-29 22:50:29,999] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/layer_01-model_00-model_states.pt. +0: [2022-11-29 22:50:30,000] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/layer_03-model_00-model_states.pt... +0: [2022-11-29 22:50:30,027] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/layer_03-model_00-model_states.pt. +0: [2022-11-29 22:50:30,028] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/layer_04-model_00-model_states.pt... +0: [2022-11-29 22:50:30,051] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/layer_04-model_00-model_states.pt. +0: [2022-11-29 22:50:30,052] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/layer_05-model_00-model_states.pt... +0: [2022-11-29 22:50:30,074] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/layer_05-model_00-model_states.pt. +0: [2022-11-29 22:50:30,074] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/layer_06-model_00-model_states.pt... +0: [2022-11-29 22:50:30,097] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/layer_06-model_00-model_states.pt. +0: [2022-11-29 22:50:30,097] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/layer_07-model_00-model_states.pt... +0: [2022-11-29 22:50:30,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/layer_07-model_00-model_states.pt. +0: [2022-11-29 22:50:30,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/layer_08-model_00-model_states.pt... +0: [2022-11-29 22:50:30,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/layer_08-model_00-model_states.pt. +0: [2022-11-29 22:50:30,146] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/layer_09-model_00-model_states.pt... +0: [2022-11-29 22:50:30,171] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/layer_09-model_00-model_states.pt. +0: [2022-11-29 22:50:30,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/layer_10-model_00-model_states.pt... +0: [2022-11-29 22:50:30,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/layer_10-model_00-model_states.pt. +0: [2022-11-29 22:50:30,195] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/layer_11-model_00-model_states.pt... +0: [2022-11-29 22:50:30,217] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/layer_11-model_00-model_states.pt. +0: [2022-11-29 22:50:30,217] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/layer_12-model_00-model_states.pt... +0: [2022-11-29 22:50:30,239] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/layer_12-model_00-model_states.pt. +0: [2022-11-29 22:50:30,239] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/layer_13-model_00-model_states.pt... +0: [2022-11-29 22:50:30,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/layer_13-model_00-model_states.pt. +0: [2022-11-29 22:50:30,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/layer_14-model_00-model_states.pt... +0: [2022-11-29 22:50:30,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/layer_14-model_00-model_states.pt. +0: [2022-11-29 22:50:30,286] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/layer_15-model_00-model_states.pt... +0: [2022-11-29 22:50:30,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/layer_15-model_00-model_states.pt. +0: [2022-11-29 22:50:30,310] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/layer_16-model_00-model_states.pt... +0: [2022-11-29 22:50:30,332] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/layer_16-model_00-model_states.pt. +0: [2022-11-29 22:50:30,332] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/layer_17-model_00-model_states.pt... +0: [2022-11-29 22:50:30,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/layer_17-model_00-model_states.pt. +0: [2022-11-29 22:50:30,355] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/layer_18-model_00-model_states.pt... +0: [2022-11-29 22:50:30,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/layer_18-model_00-model_states.pt. +0: [2022-11-29 22:50:30,378] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/layer_19-model_00-model_states.pt... +0: [2022-11-29 22:50:30,402] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/layer_19-model_00-model_states.pt. +0: [2022-11-29 22:50:30,402] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/layer_20-model_00-model_states.pt... +0: [2022-11-29 22:50:30,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/layer_20-model_00-model_states.pt. +0: [2022-11-29 22:50:30,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/layer_22-model_00-model_states.pt... +0: [2022-11-29 22:50:30,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/layer_22-model_00-model_states.pt. +0: [2022-11-29 22:50:30,431] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_220moscar/global_step7000/mp_rank_00_model_states.pt +0: [2022-11-29 22:50:30,431] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/mp_rank_00_model_states.pt... +0: [2022-11-29 22:50:30,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/mp_rank_00_model_states.pt. +0: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:50:30,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:50:30,495] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:50:30,495] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 22:50:30,495] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 22:50:30,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:50:30,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 22:50:30,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 22:50:30,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:50:30,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:50:30,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 22:50:30,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 22:50:30,501] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:50:30,501] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:50:30,501] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 22:50:30,501] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 22:50:30,501] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:50:30,501] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 22:50:30,502] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 22:50:30,501] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:50:30,501] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:50:30,502] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 22:50:30,502] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 22:50:30,502] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 22:50:30,502] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 22:50:30,502] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:50:30,502] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:50:30,502] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +0: [2022-11-29 22:50:30,502] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3: [2022-11-29 22:50:30,502] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 22:50:30,502] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 22:50:30,502] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:50:30,502] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 22:50:30,502] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 22:50:30,502] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:50:30,502] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:50:30,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:50:30,503] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 22:50:30,503] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 22:50:30,504] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:50:30,504] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 22:50:30,504] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 22:50:30,504] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:50:30,504] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 22:50:30,504] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 22:50:30,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:50:30,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 22:50:30,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 22:50:30,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:50:30,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 22:50:30,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 22:50:30,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:50:30,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3: [2022-11-29 22:50:30,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:50:30,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 22:50:30,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 22:50:30,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 22:50:30,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:50:30,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:50:30,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:50:30,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +6: [2022-11-29 22:50:30,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 22:50:30,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +3: [2022-11-29 22:50:30,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 22:50:30,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 22:50:30,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 22:50:30,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:50:30,506] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 22:50:30,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:50:30,506] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 22:50:30,506] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 22:50:30,506] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 22:50:30,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:50:30,506] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 22:50:30,506] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 22:50:30,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:50:30,507] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 22:50:30,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 22:50:30,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:50:30,507] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 22:50:30,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 22:50:30,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:50:30,507] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 22:50:30,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 22:50:30,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:50:30,508] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 22:50:30,508] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 22:50:30,509] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:50:30,509] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 22:50:30,509] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 22:50:30,501] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 22:50:30,501] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 22:50:30,501] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:50:30,502] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 22:50:30,502] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 22:50:30,504] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:50:30,504] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 22:50:30,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 22:50:30,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:50:30,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 22:50:30,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 22:50:30,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:50:30,507] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 22:50:30,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 22:50:30,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:50:30,507] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 22:50:30,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 22:50:30,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:50:30,508] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 22:50:30,508] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 22:50:30,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:50:30,510] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 22:50:30,510] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 22:50:30,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:50:30,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:50:30,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:50:30,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:50:30,511] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 22:50:30,511] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 22:50:30,511] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 22:50:30,511] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 22:50:30,511] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 22:50:30,511] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 22:50:30,511] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 22:50:30,512] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 22:50:30,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:50:30,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:50:30,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:50:30,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:50:30,512] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 22:50:30,512] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 22:50:30,512] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 22:50:30,512] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 22:50:30,512] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 22:50:30,512] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 22:50:30,512] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 22:50:30,512] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 22:50:30,513] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:50:30,513] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:50:30,513] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:50:30,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 22:50:30,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 22:50:30,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 22:50:30,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 22:50:30,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 22:50:30,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 22:50:30,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:50:30,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 22:50:30,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 22:50:30,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:50:30,503] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 22:50:30,503] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +7: [2022-11-29 22:50:30,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +5: [2022-11-29 22:50:30,503] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 22:50:30,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:50:30,503] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 22:50:30,503] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +7: [2022-11-29 22:50:30,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 22:50:30,503] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 22:50:30,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:50:30,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:50:30,503] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 22:50:30,503] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 22:50:30,503] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 22:50:30,503] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 22:50:30,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:50:30,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 22:50:30,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 22:50:30,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:50:30,506] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 22:50:30,506] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 22:50:30,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:50:30,512] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 22:50:30,512] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 22:50:30,516] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:50:30,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:50:30,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:50:30,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:50:30,519] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 22:50:30,519] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 22:50:30,519] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 22:50:30,519] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 22:50:30,519] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 22:50:30,519] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 22:50:30,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:50:30,519] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 22:50:30,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:50:30,519] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 22:50:30,519] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 22:50:30,519] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 22:50:30,516] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 22:50:30,516] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 22:50:30,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step7000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 22:50:30,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: successfully saved checkpoint at iteration 7000 to checkpoints_220moscar +7: time (ms) | save-checkpoint: 700.03 +7: iteration 7010/ 14324 | consumed samples: 1794560 | consumed tokens: 3675258880 | elapsed time per iteration (s): 0.51 | learning rate: 1.145E-04 | global batch size: 256 | lm loss: 3.085147E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 506.135 | TFLOPs: 26.56 | +7: iteration 7020/ 14324 | consumed samples: 1797120 | consumed tokens: 3680501760 | elapsed time per iteration (s): 0.42 | learning rate: 1.143E-04 | global batch size: 256 | lm loss: 3.065345E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.594 | TFLOPs: 31.62 | +7: iteration 7030/ 14324 | consumed samples: 1799680 | consumed tokens: 3685744640 | elapsed time per iteration (s): 0.43 | learning rate: 1.141E-04 | global batch size: 256 | lm loss: 3.069247E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 590.431 | TFLOPs: 30.98 | +7: iteration 7040/ 14324 | consumed samples: 1802240 | consumed tokens: 3690987520 | elapsed time per iteration (s): 0.43 | learning rate: 1.139E-04 | global batch size: 256 | lm loss: 3.072461E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.641 | TFLOPs: 31.36 | +7: iteration 7050/ 14324 | consumed samples: 1804800 | consumed tokens: 3696230400 | elapsed time per iteration (s): 0.42 | learning rate: 1.137E-04 | global batch size: 256 | lm loss: 3.078997E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.481 | TFLOPs: 31.82 | +7: iteration 7060/ 14324 | consumed samples: 1807360 | consumed tokens: 3701473280 | elapsed time per iteration (s): 0.43 | learning rate: 1.135E-04 | global batch size: 256 | lm loss: 3.086327E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.666 | TFLOPs: 31.31 | +7: iteration 7070/ 14324 | consumed samples: 1809920 | consumed tokens: 3706716160 | elapsed time per iteration (s): 0.43 | learning rate: 1.133E-04 | global batch size: 256 | lm loss: 3.043785E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.358 | TFLOPs: 31.50 | +7: iteration 7080/ 14324 | consumed samples: 1812480 | consumed tokens: 3711959040 | elapsed time per iteration (s): 0.42 | learning rate: 1.131E-04 | global batch size: 256 | lm loss: 3.064484E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 613.607 | TFLOPs: 32.19 | +7: iteration 7090/ 14324 | consumed samples: 1815040 | consumed tokens: 3717201920 | elapsed time per iteration (s): 0.43 | learning rate: 1.129E-04 | global batch size: 256 | lm loss: 3.065307E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.758 | TFLOPs: 31.21 | +7: iteration 7100/ 14324 | consumed samples: 1817600 | consumed tokens: 3722444800 | elapsed time per iteration (s): 0.42 | learning rate: 1.127E-04 | global batch size: 256 | lm loss: 3.063396E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.305 | TFLOPs: 31.92 | +7: iteration 7110/ 14324 | consumed samples: 1820160 | consumed tokens: 3727687680 | elapsed time per iteration (s): 0.42 | learning rate: 1.125E-04 | global batch size: 256 | lm loss: 3.078368E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.583 | TFLOPs: 31.77 | +7: iteration 7120/ 14324 | consumed samples: 1822720 | consumed tokens: 3732930560 | elapsed time per iteration (s): 0.43 | learning rate: 1.123E-04 | global batch size: 256 | lm loss: 3.084543E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.228 | TFLOPs: 31.55 | +7: iteration 7130/ 14324 | consumed samples: 1825280 | consumed tokens: 3738173440 | elapsed time per iteration (s): 0.42 | learning rate: 1.121E-04 | global batch size: 256 | lm loss: 3.085682E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.471 | TFLOPs: 31.93 | +7: iteration 7140/ 14324 | consumed samples: 1827840 | consumed tokens: 3743416320 | elapsed time per iteration (s): 0.42 | learning rate: 1.119E-04 | global batch size: 256 | lm loss: 3.072555E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.776 | TFLOPs: 31.63 | +7: iteration 7150/ 14324 | consumed samples: 1830400 | consumed tokens: 3748659200 | elapsed time per iteration (s): 0.43 | learning rate: 1.117E-04 | global batch size: 256 | lm loss: 3.079471E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.067 | TFLOPs: 31.48 | +7: iteration 7160/ 14324 | consumed samples: 1832960 | consumed tokens: 3753902080 | elapsed time per iteration (s): 0.43 | learning rate: 1.115E-04 | global batch size: 256 | lm loss: 3.058343E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 590.176 | TFLOPs: 30.97 | +7: iteration 7170/ 14324 | consumed samples: 1835520 | consumed tokens: 3759144960 | elapsed time per iteration (s): 0.42 | learning rate: 1.113E-04 | global batch size: 256 | lm loss: 3.050376E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.936 | TFLOPs: 32.00 | +7: iteration 7180/ 14324 | consumed samples: 1838080 | consumed tokens: 3764387840 | elapsed time per iteration (s): 0.43 | learning rate: 1.111E-04 | global batch size: 256 | lm loss: 3.059013E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.716 | TFLOPs: 31.41 | +7: iteration 7190/ 14324 | consumed samples: 1840640 | consumed tokens: 3769630720 | elapsed time per iteration (s): 0.43 | learning rate: 1.109E-04 | global batch size: 256 | lm loss: 3.086543E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.140 | TFLOPs: 31.28 | +7: iteration 7200/ 14324 | consumed samples: 1843200 | consumed tokens: 3774873600 | elapsed time per iteration (s): 0.42 | learning rate: 1.107E-04 | global batch size: 256 | lm loss: 3.022469E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.559 | TFLOPs: 31.72 | +7: iteration 7210/ 14324 | consumed samples: 1845760 | consumed tokens: 3780116480 | elapsed time per iteration (s): 0.42 | learning rate: 1.105E-04 | global batch size: 256 | lm loss: 3.086433E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.002 | TFLOPs: 31.80 | +7: iteration 7220/ 14324 | consumed samples: 1848320 | consumed tokens: 3785359360 | elapsed time per iteration (s): 0.42 | learning rate: 1.103E-04 | global batch size: 256 | lm loss: 3.064370E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.196 | TFLOPs: 31.70 | +7: iteration 7230/ 14324 | consumed samples: 1850880 | consumed tokens: 3790602240 | elapsed time per iteration (s): 0.43 | learning rate: 1.101E-04 | global batch size: 256 | lm loss: 3.058028E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.411 | TFLOPs: 31.24 | +7: iteration 7240/ 14324 | consumed samples: 1853440 | consumed tokens: 3795845120 | elapsed time per iteration (s): 0.43 | learning rate: 1.099E-04 | global batch size: 256 | lm loss: 3.043273E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.053 | TFLOPs: 31.48 | +7: iteration 7250/ 14324 | consumed samples: 1856000 | consumed tokens: 3801088000 | elapsed time per iteration (s): 0.42 | learning rate: 1.097E-04 | global batch size: 256 | lm loss: 3.071281E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.545 | TFLOPs: 31.77 | +7: iteration 7260/ 14324 | consumed samples: 1858560 | consumed tokens: 3806330880 | elapsed time per iteration (s): 0.42 | learning rate: 1.095E-04 | global batch size: 256 | lm loss: 3.053231E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.645 | TFLOPs: 31.88 | +7: iteration 7270/ 14324 | consumed samples: 1861120 | consumed tokens: 3811573760 | elapsed time per iteration (s): 0.43 | learning rate: 1.093E-04 | global batch size: 256 | lm loss: 3.076493E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.213 | TFLOPs: 31.54 | +7: iteration 7280/ 14324 | consumed samples: 1863680 | consumed tokens: 3816816640 | elapsed time per iteration (s): 0.42 | learning rate: 1.091E-04 | global batch size: 256 | lm loss: 3.041008E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.923 | TFLOPs: 32.16 | +7: iteration 7290/ 14324 | consumed samples: 1866240 | consumed tokens: 3822059520 | elapsed time per iteration (s): 0.43 | learning rate: 1.089E-04 | global batch size: 256 | lm loss: 3.055821E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.589 | TFLOPs: 31.20 | +7: iteration 7300/ 14324 | consumed samples: 1868800 | consumed tokens: 3827302400 | elapsed time per iteration (s): 0.42 | learning rate: 1.087E-04 | global batch size: 256 | lm loss: 3.074231E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.541 | TFLOPs: 31.93 | +7: iteration 7310/ 14324 | consumed samples: 1871360 | consumed tokens: 3832545280 | elapsed time per iteration (s): 0.42 | learning rate: 1.085E-04 | global batch size: 256 | lm loss: 3.062446E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.385 | TFLOPs: 32.08 | +7: iteration 7320/ 14324 | consumed samples: 1873920 | consumed tokens: 3837788160 | elapsed time per iteration (s): 0.43 | learning rate: 1.083E-04 | global batch size: 256 | lm loss: 3.063330E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.816 | TFLOPs: 31.47 | +7: iteration 7330/ 14324 | consumed samples: 1876480 | consumed tokens: 3843031040 | elapsed time per iteration (s): 0.43 | learning rate: 1.081E-04 | global batch size: 256 | lm loss: 3.047588E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.660 | TFLOPs: 31.36 | +7: iteration 7340/ 14324 | consumed samples: 1879040 | consumed tokens: 3848273920 | elapsed time per iteration (s): 0.42 | learning rate: 1.079E-04 | global batch size: 256 | lm loss: 3.039314E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.008 | TFLOPs: 31.69 | +7: iteration 7350/ 14324 | consumed samples: 1881600 | consumed tokens: 3853516800 | elapsed time per iteration (s): 0.43 | learning rate: 1.077E-04 | global batch size: 256 | lm loss: 3.087372E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.281 | TFLOPs: 31.60 | +7: iteration 7360/ 14324 | consumed samples: 1884160 | consumed tokens: 3858759680 | elapsed time per iteration (s): 0.42 | learning rate: 1.075E-04 | global batch size: 256 | lm loss: 3.077896E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.603 | TFLOPs: 31.67 | +7: iteration 7370/ 14324 | consumed samples: 1886720 | consumed tokens: 3864002560 | elapsed time per iteration (s): 0.42 | learning rate: 1.073E-04 | global batch size: 256 | lm loss: 3.045775E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.033 | TFLOPs: 31.69 | +7: iteration 7380/ 14324 | consumed samples: 1889280 | consumed tokens: 3869245440 | elapsed time per iteration (s): 0.42 | learning rate: 1.071E-04 | global batch size: 256 | lm loss: 3.049575E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.175 | TFLOPs: 31.81 | +7: iteration 7390/ 14324 | consumed samples: 1891840 | consumed tokens: 3874488320 | elapsed time per iteration (s): 0.43 | learning rate: 1.069E-04 | global batch size: 256 | lm loss: 3.034968E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.640 | TFLOPs: 31.51 | +7: iteration 7400/ 14324 | consumed samples: 1894400 | consumed tokens: 3879731200 | elapsed time per iteration (s): 0.42 | learning rate: 1.067E-04 | global batch size: 256 | lm loss: 3.051011E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.559 | TFLOPs: 31.88 | +7: iteration 7410/ 14324 | consumed samples: 1896960 | consumed tokens: 3884974080 | elapsed time per iteration (s): 0.42 | learning rate: 1.065E-04 | global batch size: 256 | lm loss: 3.039815E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.472 | TFLOPs: 31.98 | +7: iteration 7420/ 14324 | consumed samples: 1899520 | consumed tokens: 3890216960 | elapsed time per iteration (s): 0.42 | learning rate: 1.063E-04 | global batch size: 256 | lm loss: 3.049610E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.861 | TFLOPs: 31.79 | +7: iteration 7430/ 14324 | consumed samples: 1902080 | consumed tokens: 3895459840 | elapsed time per iteration (s): 0.42 | learning rate: 1.061E-04 | global batch size: 256 | lm loss: 3.053927E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.190 | TFLOPs: 31.70 | +7: iteration 7440/ 14324 | consumed samples: 1904640 | consumed tokens: 3900702720 | elapsed time per iteration (s): 0.42 | learning rate: 1.059E-04 | global batch size: 256 | lm loss: 3.051123E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.285 | TFLOPs: 31.76 | +7: iteration 7450/ 14324 | consumed samples: 1907200 | consumed tokens: 3905945600 | elapsed time per iteration (s): 0.42 | learning rate: 1.057E-04 | global batch size: 256 | lm loss: 3.061496E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.998 | TFLOPs: 31.74 | +7: iteration 7460/ 14324 | consumed samples: 1909760 | consumed tokens: 3911188480 | elapsed time per iteration (s): 0.42 | learning rate: 1.055E-04 | global batch size: 256 | lm loss: 3.067733E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.496 | TFLOPs: 31.66 | +7: iteration 7470/ 14324 | consumed samples: 1912320 | consumed tokens: 3916431360 | elapsed time per iteration (s): 0.42 | learning rate: 1.053E-04 | global batch size: 256 | lm loss: 3.047499E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.148 | TFLOPs: 31.96 | +7: iteration 7480/ 14324 | consumed samples: 1914880 | consumed tokens: 3921674240 | elapsed time per iteration (s): 0.42 | learning rate: 1.051E-04 | global batch size: 256 | lm loss: 3.024664E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.811 | TFLOPs: 31.68 | +7: iteration 7490/ 14324 | consumed samples: 1917440 | consumed tokens: 3926917120 | elapsed time per iteration (s): 0.42 | learning rate: 1.049E-04 | global batch size: 256 | lm loss: 3.044473E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.258 | TFLOPs: 31.76 | +7: iteration 7500/ 14324 | consumed samples: 1920000 | consumed tokens: 3932160000 | elapsed time per iteration (s): 0.43 | learning rate: 1.047E-04 | global batch size: 256 | lm loss: 3.059227E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.001 | TFLOPs: 31.59 | +7: iteration 7510/ 14324 | consumed samples: 1922560 | consumed tokens: 3937402880 | elapsed time per iteration (s): 0.43 | learning rate: 1.045E-04 | global batch size: 256 | lm loss: 3.044876E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.838 | TFLOPs: 31.47 | +7: iteration 7520/ 14324 | consumed samples: 1925120 | consumed tokens: 3942645760 | elapsed time per iteration (s): 0.42 | learning rate: 1.043E-04 | global batch size: 256 | lm loss: 3.056052E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.897 | TFLOPs: 32.11 | +7: iteration 7530/ 14324 | consumed samples: 1927680 | consumed tokens: 3947888640 | elapsed time per iteration (s): 0.42 | learning rate: 1.041E-04 | global batch size: 256 | lm loss: 3.048501E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.186 | TFLOPs: 31.96 | +7: iteration 7540/ 14324 | consumed samples: 1930240 | consumed tokens: 3953131520 | elapsed time per iteration (s): 0.43 | learning rate: 1.039E-04 | global batch size: 256 | lm loss: 3.063492E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.498 | TFLOPs: 31.19 | +7: iteration 7550/ 14324 | consumed samples: 1932800 | consumed tokens: 3958374400 | elapsed time per iteration (s): 0.42 | learning rate: 1.037E-04 | global batch size: 256 | lm loss: 3.051426E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.067 | TFLOPs: 32.01 | +7: iteration 7560/ 14324 | consumed samples: 1935360 | consumed tokens: 3963617280 | elapsed time per iteration (s): 0.43 | learning rate: 1.035E-04 | global batch size: 256 | lm loss: 3.039402E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.498 | TFLOPs: 31.45 | +7: iteration 7570/ 14324 | consumed samples: 1937920 | consumed tokens: 3968860160 | elapsed time per iteration (s): 0.42 | learning rate: 1.033E-04 | global batch size: 256 | lm loss: 3.055937E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.376 | TFLOPs: 32.13 | +7: iteration 7580/ 14324 | consumed samples: 1940480 | consumed tokens: 3974103040 | elapsed time per iteration (s): 0.43 | learning rate: 1.031E-04 | global batch size: 256 | lm loss: 3.049120E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 588.830 | TFLOPs: 30.89 | +7: iteration 7590/ 14324 | consumed samples: 1943040 | consumed tokens: 3979345920 | elapsed time per iteration (s): 0.42 | learning rate: 1.029E-04 | global batch size: 256 | lm loss: 3.035209E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.424 | TFLOPs: 31.82 | +7: iteration 7600/ 14324 | consumed samples: 1945600 | consumed tokens: 3984588800 | elapsed time per iteration (s): 0.43 | learning rate: 1.027E-04 | global batch size: 256 | lm loss: 3.022589E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.510 | TFLOPs: 31.46 | +7: iteration 7610/ 14324 | consumed samples: 1948160 | consumed tokens: 3989831680 | elapsed time per iteration (s): 0.43 | learning rate: 1.025E-04 | global batch size: 256 | lm loss: 3.057786E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.637 | TFLOPs: 31.46 | +7: iteration 7620/ 14324 | consumed samples: 1950720 | consumed tokens: 3995074560 | elapsed time per iteration (s): 0.44 | learning rate: 1.023E-04 | global batch size: 256 | lm loss: 3.041739E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 581.337 | TFLOPs: 30.50 | +7: iteration 7630/ 14324 | consumed samples: 1953280 | consumed tokens: 4000317440 | elapsed time per iteration (s): 0.42 | learning rate: 1.021E-04 | global batch size: 256 | lm loss: 3.047166E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.470 | TFLOPs: 31.87 | +7: iteration 7640/ 14324 | consumed samples: 1955840 | consumed tokens: 4005560320 | elapsed time per iteration (s): 0.43 | learning rate: 1.019E-04 | global batch size: 256 | lm loss: 3.045340E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 589.417 | TFLOPs: 30.93 | +7: iteration 7650/ 14324 | consumed samples: 1958400 | consumed tokens: 4010803200 | elapsed time per iteration (s): 0.42 | learning rate: 1.017E-04 | global batch size: 256 | lm loss: 3.057473E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.205 | TFLOPs: 32.02 | +7: iteration 7660/ 14324 | consumed samples: 1960960 | consumed tokens: 4016046080 | elapsed time per iteration (s): 0.43 | learning rate: 1.015E-04 | global batch size: 256 | lm loss: 3.067915E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.215 | TFLOPs: 31.44 | +7: iteration 7670/ 14324 | consumed samples: 1963520 | consumed tokens: 4021288960 | elapsed time per iteration (s): 0.42 | learning rate: 1.013E-04 | global batch size: 256 | lm loss: 3.062222E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.488 | TFLOPs: 31.87 | +7: iteration 7680/ 14324 | consumed samples: 1966080 | consumed tokens: 4026531840 | elapsed time per iteration (s): 0.42 | learning rate: 1.011E-04 | global batch size: 256 | lm loss: 3.031198E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.294 | TFLOPs: 31.86 | +7: iteration 7690/ 14324 | consumed samples: 1968640 | consumed tokens: 4031774720 | elapsed time per iteration (s): 0.42 | learning rate: 1.009E-04 | global batch size: 256 | lm loss: 3.013897E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.662 | TFLOPs: 31.73 | +7: iteration 7700/ 14324 | consumed samples: 1971200 | consumed tokens: 4037017600 | elapsed time per iteration (s): 0.42 | learning rate: 1.007E-04 | global batch size: 256 | lm loss: 3.040802E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.684 | TFLOPs: 31.67 | +7: iteration 7710/ 14324 | consumed samples: 1973760 | consumed tokens: 4042260480 | elapsed time per iteration (s): 0.43 | learning rate: 1.005E-04 | global batch size: 256 | lm loss: 3.035958E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.771 | TFLOPs: 31.10 | +7: iteration 7720/ 14324 | consumed samples: 1976320 | consumed tokens: 4047503360 | elapsed time per iteration (s): 0.43 | learning rate: 1.003E-04 | global batch size: 256 | lm loss: 3.029207E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.731 | TFLOPs: 31.52 | +7: iteration 7730/ 14324 | consumed samples: 1978880 | consumed tokens: 4052746240 | elapsed time per iteration (s): 0.43 | learning rate: 1.001E-04 | global batch size: 256 | lm loss: 3.046028E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.135 | TFLOPs: 31.33 | +7: iteration 7740/ 14324 | consumed samples: 1981440 | consumed tokens: 4057989120 | elapsed time per iteration (s): 0.43 | learning rate: 9.993E-05 | global batch size: 256 | lm loss: 3.048787E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.953 | TFLOPs: 31.27 | +7: iteration 7750/ 14324 | consumed samples: 1984000 | consumed tokens: 4063232000 | elapsed time per iteration (s): 0.43 | learning rate: 9.973E-05 | global batch size: 256 | lm loss: 3.036498E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.320 | TFLOPs: 31.13 | +7: iteration 7760/ 14324 | consumed samples: 1986560 | consumed tokens: 4068474880 | elapsed time per iteration (s): 0.43 | learning rate: 9.953E-05 | global batch size: 256 | lm loss: 3.035170E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.986 | TFLOPs: 31.53 | +7: iteration 7770/ 14324 | consumed samples: 1989120 | consumed tokens: 4073717760 | elapsed time per iteration (s): 0.42 | learning rate: 9.933E-05 | global batch size: 256 | lm loss: 3.009686E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.036 | TFLOPs: 31.96 | +7: iteration 7780/ 14324 | consumed samples: 1991680 | consumed tokens: 4078960640 | elapsed time per iteration (s): 0.43 | learning rate: 9.913E-05 | global batch size: 256 | lm loss: 3.025430E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.459 | TFLOPs: 31.19 | +7: iteration 7790/ 14324 | consumed samples: 1994240 | consumed tokens: 4084203520 | elapsed time per iteration (s): 0.43 | learning rate: 9.894E-05 | global batch size: 256 | lm loss: 3.032293E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.170 | TFLOPs: 31.49 | +7: iteration 7800/ 14324 | consumed samples: 1996800 | consumed tokens: 4089446400 | elapsed time per iteration (s): 0.43 | learning rate: 9.874E-05 | global batch size: 256 | lm loss: 3.049176E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.390 | TFLOPs: 31.19 | +7: iteration 7810/ 14324 | consumed samples: 1999360 | consumed tokens: 4094689280 | elapsed time per iteration (s): 0.43 | learning rate: 9.854E-05 | global batch size: 256 | lm loss: 3.005905E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.289 | TFLOPs: 31.60 | +7: iteration 7820/ 14324 | consumed samples: 2001920 | consumed tokens: 4099932160 | elapsed time per iteration (s): 0.42 | learning rate: 9.834E-05 | global batch size: 256 | lm loss: 3.052331E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.042 | TFLOPs: 31.80 | +7: iteration 7830/ 14324 | consumed samples: 2004480 | consumed tokens: 4105175040 | elapsed time per iteration (s): 0.42 | learning rate: 9.815E-05 | global batch size: 256 | lm loss: 3.033839E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.689 | TFLOPs: 31.83 | +7: iteration 7840/ 14324 | consumed samples: 2007040 | consumed tokens: 4110417920 | elapsed time per iteration (s): 0.43 | learning rate: 9.795E-05 | global batch size: 256 | lm loss: 3.039133E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.924 | TFLOPs: 31.58 | +7: iteration 7850/ 14324 | consumed samples: 2009600 | consumed tokens: 4115660800 | elapsed time per iteration (s): 0.43 | learning rate: 9.775E-05 | global batch size: 256 | lm loss: 3.060153E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.651 | TFLOPs: 31.25 | +7: iteration 7860/ 14324 | consumed samples: 2012160 | consumed tokens: 4120903680 | elapsed time per iteration (s): 0.42 | learning rate: 9.755E-05 | global batch size: 256 | lm loss: 3.042126E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.414 | TFLOPs: 31.87 | +7: iteration 7870/ 14324 | consumed samples: 2014720 | consumed tokens: 4126146560 | elapsed time per iteration (s): 0.42 | learning rate: 9.736E-05 | global batch size: 256 | lm loss: 3.005772E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.424 | TFLOPs: 31.71 | +7: iteration 7880/ 14324 | consumed samples: 2017280 | consumed tokens: 4131389440 | elapsed time per iteration (s): 0.42 | learning rate: 9.716E-05 | global batch size: 256 | lm loss: 3.038618E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.663 | TFLOPs: 31.99 | +7: iteration 7890/ 14324 | consumed samples: 2019840 | consumed tokens: 4136632320 | elapsed time per iteration (s): 0.44 | learning rate: 9.696E-05 | global batch size: 256 | lm loss: 3.048712E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 586.529 | TFLOPs: 30.77 | +7: iteration 7900/ 14324 | consumed samples: 2022400 | consumed tokens: 4141875200 | elapsed time per iteration (s): 0.43 | learning rate: 9.676E-05 | global batch size: 256 | lm loss: 3.006503E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.244 | TFLOPs: 31.28 | +7: iteration 7910/ 14324 | consumed samples: 2024960 | consumed tokens: 4147118080 | elapsed time per iteration (s): 0.42 | learning rate: 9.657E-05 | global batch size: 256 | lm loss: 3.063582E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.810 | TFLOPs: 31.73 | +7: iteration 7920/ 14324 | consumed samples: 2027520 | consumed tokens: 4152360960 | elapsed time per iteration (s): 0.42 | learning rate: 9.637E-05 | global batch size: 256 | lm loss: 3.003328E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.344 | TFLOPs: 31.81 | +7: iteration 7930/ 14324 | consumed samples: 2030080 | consumed tokens: 4157603840 | elapsed time per iteration (s): 0.44 | learning rate: 9.617E-05 | global batch size: 256 | lm loss: 3.022380E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 581.027 | TFLOPs: 30.49 | +7: iteration 7940/ 14324 | consumed samples: 2032640 | consumed tokens: 4162846720 | elapsed time per iteration (s): 0.43 | learning rate: 9.598E-05 | global batch size: 256 | lm loss: 3.029490E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.036 | TFLOPs: 31.59 | +7: iteration 7950/ 14324 | consumed samples: 2035200 | consumed tokens: 4168089600 | elapsed time per iteration (s): 0.43 | learning rate: 9.578E-05 | global batch size: 256 | lm loss: 3.038344E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.553 | TFLOPs: 31.20 | +7: iteration 7960/ 14324 | consumed samples: 2037760 | consumed tokens: 4173332480 | elapsed time per iteration (s): 0.42 | learning rate: 9.558E-05 | global batch size: 256 | lm loss: 3.036780E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.351 | TFLOPs: 31.97 | +7: iteration 7970/ 14324 | consumed samples: 2040320 | consumed tokens: 4178575360 | elapsed time per iteration (s): 0.42 | learning rate: 9.538E-05 | global batch size: 256 | lm loss: 3.048225E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.062 | TFLOPs: 31.90 | +7: iteration 7980/ 14324 | consumed samples: 2042880 | consumed tokens: 4183818240 | elapsed time per iteration (s): 0.42 | learning rate: 9.519E-05 | global batch size: 256 | lm loss: 3.030444E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.768 | TFLOPs: 32.05 | +7: iteration 7990/ 14324 | consumed samples: 2045440 | consumed tokens: 4189061120 | elapsed time per iteration (s): 0.43 | learning rate: 9.499E-05 | global batch size: 256 | lm loss: 3.037925E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.310 | TFLOPs: 31.29 | +0: [2022-11-29 22:57:35,832] [INFO] [logging.py:68:log_dist] [Rank 0] step=8000, skipped=0, lr=[9.479488677863128e-05, 9.479488677863128e-05, 9.479488677863128e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 8000/ 14324 | consumed samples: 2048000 | consumed tokens: 4194304000 | elapsed time per iteration (s): 0.44 | learning rate: 9.479E-05 | global batch size: 256 | lm loss: 3.010360E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 583.274 | TFLOPs: 30.60 | +0: steps: 8000 loss: 3.0314 iter time (s): 0.424 samples/sec: 603.183 +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 8000 | lm loss value: 3.057510E+00 | lm loss PPL: 2.127452E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 8000 to checkpoints_220moscar +0: [2022-11-29 22:57:36,028] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step8000 is begin to save! +0: [2022-11-29 22:57:36,033] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/layer_01-model_00-model_states.pt... +0: [2022-11-29 22:57:36,132] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/layer_01-model_00-model_states.pt. +0: [2022-11-29 22:57:36,132] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/layer_03-model_00-model_states.pt... +0: [2022-11-29 22:57:36,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/layer_03-model_00-model_states.pt. +0: [2022-11-29 22:57:36,154] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/layer_04-model_00-model_states.pt... +0: [2022-11-29 22:57:36,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/layer_04-model_00-model_states.pt. +0: [2022-11-29 22:57:36,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/layer_05-model_00-model_states.pt... +0: [2022-11-29 22:57:36,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/layer_05-model_00-model_states.pt. +0: [2022-11-29 22:57:36,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/layer_06-model_00-model_states.pt... +0: [2022-11-29 22:57:36,223] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/layer_06-model_00-model_states.pt. +0: [2022-11-29 22:57:36,223] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/layer_07-model_00-model_states.pt... +0: [2022-11-29 22:57:36,248] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/layer_07-model_00-model_states.pt. +0: [2022-11-29 22:57:36,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/layer_08-model_00-model_states.pt... +0: [2022-11-29 22:57:36,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/layer_08-model_00-model_states.pt. +0: [2022-11-29 22:57:36,272] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/layer_09-model_00-model_states.pt... +0: [2022-11-29 22:57:36,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/layer_09-model_00-model_states.pt. +0: [2022-11-29 22:57:36,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/layer_10-model_00-model_states.pt... +0: [2022-11-29 22:57:36,319] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/layer_10-model_00-model_states.pt. +0: [2022-11-29 22:57:36,319] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/layer_11-model_00-model_states.pt... +0: [2022-11-29 22:57:36,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/layer_11-model_00-model_states.pt. +0: [2022-11-29 22:57:36,341] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/layer_12-model_00-model_states.pt... +0: [2022-11-29 22:57:36,364] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/layer_12-model_00-model_states.pt. +0: [2022-11-29 22:57:36,364] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/layer_13-model_00-model_states.pt... +0: [2022-11-29 22:57:36,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/layer_13-model_00-model_states.pt. +0: [2022-11-29 22:57:36,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/layer_14-model_00-model_states.pt... +0: [2022-11-29 22:57:36,411] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/layer_14-model_00-model_states.pt. +0: [2022-11-29 22:57:36,411] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/layer_15-model_00-model_states.pt... +0: [2022-11-29 22:57:36,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/layer_15-model_00-model_states.pt. +0: [2022-11-29 22:57:36,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/layer_16-model_00-model_states.pt... +0: [2022-11-29 22:57:36,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/layer_16-model_00-model_states.pt. +0: [2022-11-29 22:57:36,457] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/layer_17-model_00-model_states.pt... +0: [2022-11-29 22:57:36,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/layer_17-model_00-model_states.pt. +0: [2022-11-29 22:57:36,480] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/layer_18-model_00-model_states.pt... +0: [2022-11-29 22:57:36,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/layer_18-model_00-model_states.pt. +0: [2022-11-29 22:57:36,503] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/layer_19-model_00-model_states.pt... +0: [2022-11-29 22:57:36,525] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/layer_19-model_00-model_states.pt. +0: [2022-11-29 22:57:36,526] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/layer_20-model_00-model_states.pt... +0: [2022-11-29 22:57:36,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/layer_20-model_00-model_states.pt. +0: [2022-11-29 22:57:36,549] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/layer_22-model_00-model_states.pt... +0: [2022-11-29 22:57:36,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/layer_22-model_00-model_states.pt. +0: [2022-11-29 22:57:36,553] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_220moscar/global_step8000/mp_rank_00_model_states.pt +0: [2022-11-29 22:57:36,554] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/mp_rank_00_model_states.pt... +0: [2022-11-29 22:57:36,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/mp_rank_00_model_states.pt. +0: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +0: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 22:57:36,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +7: [2022-11-29 22:57:36,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:57:36,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 22:57:36,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 22:57:36,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:57:36,620] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 22:57:36,620] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 22:57:36,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:57:36,621] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 22:57:36,621] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 22:57:36,622] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:57:36,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:57:36,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 22:57:36,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 22:57:36,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:57:36,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 22:57:36,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 22:57:36,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:57:36,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 22:57:36,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 22:57:36,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:57:36,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 22:57:36,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 22:57:36,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:57:36,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 22:57:36,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 22:57:36,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:57:36,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 22:57:36,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 22:57:36,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:57:36,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 22:57:36,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 22:57:36,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:57:36,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:57:36,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:57:36,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +6: [2022-11-29 22:57:36,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:57:36,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:57:36,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +7: [2022-11-29 22:57:36,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 22:57:36,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +7: [2022-11-29 22:57:36,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:57:36,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 22:57:36,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 22:57:36,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 22:57:36,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 22:57:36,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:57:36,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 22:57:36,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 22:57:36,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:57:36,628] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 22:57:36,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:57:36,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 22:57:36,628] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 22:57:36,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 22:57:36,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:57:36,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 22:57:36,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 22:57:36,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:57:36,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 22:57:36,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 22:57:36,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:57:36,630] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 22:57:36,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 22:57:36,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:57:36,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 22:57:36,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 22:57:36,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:57:36,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:57:36,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +7: [2022-11-29 22:57:36,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +0: [2022-11-29 22:57:36,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 22:57:36,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 22:57:36,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:57:36,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 22:57:36,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 22:57:36,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:57:36,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:57:36,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:57:36,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +6: [2022-11-29 22:57:36,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +7: [2022-11-29 22:57:36,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +3: [2022-11-29 22:57:36,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 22:57:36,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 22:57:36,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 22:57:36,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:57:36,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:57:36,632] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 22:57:36,632] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 22:57:36,632] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 22:57:36,632] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 22:57:36,632] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:57:36,632] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 22:57:36,632] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 22:57:36,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:57:36,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 22:57:36,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 22:57:36,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 22:57:36,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 22:57:36,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 22:57:36,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:57:36,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:57:36,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 22:57:36,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 22:57:36,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 22:57:36,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 22:57:36,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:57:36,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:57:36,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +3: [2022-11-29 22:57:36,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +7: [2022-11-29 22:57:36,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 22:57:36,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 22:57:36,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +3: [2022-11-29 22:57:36,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:57:36,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3: [2022-11-29 22:57:36,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 22:57:36,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 22:57:36,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 22:57:36,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 22:57:36,635] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 22:57:36,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 22:57:36,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 22:57:36,637] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 22:57:36,637] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 22:57:36,622] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 22:57:36,622] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 22:57:36,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:57:36,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 22:57:36,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 22:57:36,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:57:36,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 22:57:36,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 22:57:36,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:57:36,628] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 22:57:36,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 22:57:36,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:57:36,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:57:36,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:57:36,630] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 22:57:36,630] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 22:57:36,630] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 22:57:36,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 22:57:36,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 22:57:36,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 22:57:36,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 22:57:36,638] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 22:57:36,638] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 22:57:36,639] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:57:36,639] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 22:57:36,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 22:57:36,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 22:57:36,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 22:57:36,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 22:57:36,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:57:36,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 22:57:36,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 22:57:36,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 22:57:36,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 22:57:36,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:57:36,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:57:36,628] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 22:57:36,628] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 22:57:36,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 22:57:36,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 22:57:36,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:57:36,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:57:36,630] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 22:57:36,630] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 22:57:36,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 22:57:36,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 22:57:36,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:57:36,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 22:57:36,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 22:57:36,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 22:57:36,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 22:57:36,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 22:57:36,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:57:36,664] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 22:57:36,664] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 22:57:36,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:57:36,665] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 22:57:36,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:57:36,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 22:57:36,665] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 22:57:36,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 22:57:36,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:57:36,665] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 22:57:36,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 22:57:36,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 22:57:36,665] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 22:57:36,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 22:57:36,686] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step8000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 22:57:36,686] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: successfully saved checkpoint at iteration 8000 to checkpoints_220moscar +7: time (ms) | save-checkpoint: 662.93 +7: iteration 8010/ 14324 | consumed samples: 2050560 | consumed tokens: 4199546880 | elapsed time per iteration (s): 0.50 | learning rate: 9.460E-05 | global batch size: 256 | lm loss: 3.024148E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 510.142 | TFLOPs: 26.77 | +7: iteration 8020/ 14324 | consumed samples: 2053120 | consumed tokens: 4204789760 | elapsed time per iteration (s): 0.43 | learning rate: 9.440E-05 | global batch size: 256 | lm loss: 3.019699E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.358 | TFLOPs: 31.39 | +7: iteration 8030/ 14324 | consumed samples: 2055680 | consumed tokens: 4210032640 | elapsed time per iteration (s): 0.42 | learning rate: 9.421E-05 | global batch size: 256 | lm loss: 3.016794E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.274 | TFLOPs: 31.71 | +7: iteration 8040/ 14324 | consumed samples: 2058240 | consumed tokens: 4215275520 | elapsed time per iteration (s): 0.42 | learning rate: 9.401E-05 | global batch size: 256 | lm loss: 3.029972E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.153 | TFLOPs: 31.86 | +7: iteration 8050/ 14324 | consumed samples: 2060800 | consumed tokens: 4220518400 | elapsed time per iteration (s): 0.42 | learning rate: 9.381E-05 | global batch size: 256 | lm loss: 3.035773E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.520 | TFLOPs: 32.03 | +7: iteration 8060/ 14324 | consumed samples: 2063360 | consumed tokens: 4225761280 | elapsed time per iteration (s): 0.42 | learning rate: 9.362E-05 | global batch size: 256 | lm loss: 3.029747E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.452 | TFLOPs: 32.08 | +7: iteration 8070/ 14324 | consumed samples: 2065920 | consumed tokens: 4231004160 | elapsed time per iteration (s): 0.42 | learning rate: 9.342E-05 | global batch size: 256 | lm loss: 3.066607E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.551 | TFLOPs: 31.61 | +7: iteration 8080/ 14324 | consumed samples: 2068480 | consumed tokens: 4236247040 | elapsed time per iteration (s): 0.42 | learning rate: 9.323E-05 | global batch size: 256 | lm loss: 3.012569E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.682 | TFLOPs: 31.88 | +7: iteration 8090/ 14324 | consumed samples: 2071040 | consumed tokens: 4241489920 | elapsed time per iteration (s): 0.42 | learning rate: 9.303E-05 | global batch size: 256 | lm loss: 3.005057E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.107 | TFLOPs: 31.64 | +7: iteration 8100/ 14324 | consumed samples: 2073600 | consumed tokens: 4246732800 | elapsed time per iteration (s): 0.42 | learning rate: 9.283E-05 | global batch size: 256 | lm loss: 3.026248E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.622 | TFLOPs: 31.62 | +7: iteration 8110/ 14324 | consumed samples: 2076160 | consumed tokens: 4251975680 | elapsed time per iteration (s): 0.43 | learning rate: 9.264E-05 | global batch size: 256 | lm loss: 3.024335E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.260 | TFLOPs: 31.39 | +7: iteration 8120/ 14324 | consumed samples: 2078720 | consumed tokens: 4257218560 | elapsed time per iteration (s): 0.42 | learning rate: 9.244E-05 | global batch size: 256 | lm loss: 3.043299E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.080 | TFLOPs: 31.96 | +7: iteration 8130/ 14324 | consumed samples: 2081280 | consumed tokens: 4262461440 | elapsed time per iteration (s): 0.45 | learning rate: 9.225E-05 | global batch size: 256 | lm loss: 3.008546E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 569.654 | TFLOPs: 29.89 | +7: iteration 8140/ 14324 | consumed samples: 2083840 | consumed tokens: 4267704320 | elapsed time per iteration (s): 0.43 | learning rate: 9.205E-05 | global batch size: 256 | lm loss: 2.995661E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.779 | TFLOPs: 31.05 | +7: iteration 8150/ 14324 | consumed samples: 2086400 | consumed tokens: 4272947200 | elapsed time per iteration (s): 0.45 | learning rate: 9.186E-05 | global batch size: 256 | lm loss: 3.050956E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 574.443 | TFLOPs: 30.14 | +7: iteration 8160/ 14324 | consumed samples: 2088960 | consumed tokens: 4278190080 | elapsed time per iteration (s): 0.43 | learning rate: 9.166E-05 | global batch size: 256 | lm loss: 3.024003E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.196 | TFLOPs: 31.54 | +7: iteration 8170/ 14324 | consumed samples: 2091520 | consumed tokens: 4283432960 | elapsed time per iteration (s): 0.43 | learning rate: 9.147E-05 | global batch size: 256 | lm loss: 3.005982E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.766 | TFLOPs: 31.42 | +7: iteration 8180/ 14324 | consumed samples: 2094080 | consumed tokens: 4288675840 | elapsed time per iteration (s): 0.43 | learning rate: 9.127E-05 | global batch size: 256 | lm loss: 3.019412E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.862 | TFLOPs: 31.32 | +7: iteration 8190/ 14324 | consumed samples: 2096640 | consumed tokens: 4293918720 | elapsed time per iteration (s): 0.42 | learning rate: 9.108E-05 | global batch size: 256 | lm loss: 3.031451E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.948 | TFLOPs: 31.64 | +7: iteration 8200/ 14324 | consumed samples: 2099200 | consumed tokens: 4299161600 | elapsed time per iteration (s): 0.43 | learning rate: 9.088E-05 | global batch size: 256 | lm loss: 3.029776E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.380 | TFLOPs: 31.24 | +7: iteration 8210/ 14324 | consumed samples: 2101760 | consumed tokens: 4304404480 | elapsed time per iteration (s): 0.42 | learning rate: 9.069E-05 | global batch size: 256 | lm loss: 3.061495E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.277 | TFLOPs: 31.76 | +7: iteration 8220/ 14324 | consumed samples: 2104320 | consumed tokens: 4309647360 | elapsed time per iteration (s): 0.42 | learning rate: 9.049E-05 | global batch size: 256 | lm loss: 3.029126E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.800 | TFLOPs: 31.63 | +7: iteration 8230/ 14324 | consumed samples: 2106880 | consumed tokens: 4314890240 | elapsed time per iteration (s): 0.43 | learning rate: 9.030E-05 | global batch size: 256 | lm loss: 3.039232E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.133 | TFLOPs: 31.38 | +7: iteration 8240/ 14324 | consumed samples: 2109440 | consumed tokens: 4320133120 | elapsed time per iteration (s): 0.43 | learning rate: 9.010E-05 | global batch size: 256 | lm loss: 3.050983E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.901 | TFLOPs: 31.53 | +7: iteration 8250/ 14324 | consumed samples: 2112000 | consumed tokens: 4325376000 | elapsed time per iteration (s): 0.42 | learning rate: 8.991E-05 | global batch size: 256 | lm loss: 3.022376E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 614.498 | TFLOPs: 32.24 | +7: iteration 8260/ 14324 | consumed samples: 2114560 | consumed tokens: 4330618880 | elapsed time per iteration (s): 0.43 | learning rate: 8.971E-05 | global batch size: 256 | lm loss: 3.029842E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.609 | TFLOPs: 31.30 | +7: iteration 8270/ 14324 | consumed samples: 2117120 | consumed tokens: 4335861760 | elapsed time per iteration (s): 0.43 | learning rate: 8.952E-05 | global batch size: 256 | lm loss: 3.030940E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.404 | TFLOPs: 31.40 | +7: iteration 8280/ 14324 | consumed samples: 2119680 | consumed tokens: 4341104640 | elapsed time per iteration (s): 0.43 | learning rate: 8.933E-05 | global batch size: 256 | lm loss: 3.052605E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.231 | TFLOPs: 31.28 | +7: iteration 8290/ 14324 | consumed samples: 2122240 | consumed tokens: 4346347520 | elapsed time per iteration (s): 0.43 | learning rate: 8.913E-05 | global batch size: 256 | lm loss: 3.044704E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.521 | TFLOPs: 31.51 | +7: iteration 8300/ 14324 | consumed samples: 2124800 | consumed tokens: 4351590400 | elapsed time per iteration (s): 0.43 | learning rate: 8.894E-05 | global batch size: 256 | lm loss: 2.996620E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.073 | TFLOPs: 31.59 | +7: iteration 8310/ 14324 | consumed samples: 2127360 | consumed tokens: 4356833280 | elapsed time per iteration (s): 0.42 | learning rate: 8.874E-05 | global batch size: 256 | lm loss: 3.011487E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.541 | TFLOPs: 31.88 | +7: iteration 8320/ 14324 | consumed samples: 2129920 | consumed tokens: 4362076160 | elapsed time per iteration (s): 0.43 | learning rate: 8.855E-05 | global batch size: 256 | lm loss: 3.022614E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.946 | TFLOPs: 31.32 | +7: iteration 8330/ 14324 | consumed samples: 2132480 | consumed tokens: 4367319040 | elapsed time per iteration (s): 0.42 | learning rate: 8.836E-05 | global batch size: 256 | lm loss: 3.012204E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.582 | TFLOPs: 31.67 | +7: iteration 8340/ 14324 | consumed samples: 2135040 | consumed tokens: 4372561920 | elapsed time per iteration (s): 0.44 | learning rate: 8.816E-05 | global batch size: 256 | lm loss: 3.019489E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 585.009 | TFLOPs: 30.69 | +7: iteration 8350/ 14324 | consumed samples: 2137600 | consumed tokens: 4377804800 | elapsed time per iteration (s): 0.42 | learning rate: 8.797E-05 | global batch size: 256 | lm loss: 3.019345E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.131 | TFLOPs: 31.96 | +7: iteration 8360/ 14324 | consumed samples: 2140160 | consumed tokens: 4383047680 | elapsed time per iteration (s): 0.42 | learning rate: 8.778E-05 | global batch size: 256 | lm loss: 3.036752E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.896 | TFLOPs: 31.95 | +7: iteration 8370/ 14324 | consumed samples: 2142720 | consumed tokens: 4388290560 | elapsed time per iteration (s): 0.43 | learning rate: 8.758E-05 | global batch size: 256 | lm loss: 3.019492E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.253 | TFLOPs: 31.07 | +7: iteration 8380/ 14324 | consumed samples: 2145280 | consumed tokens: 4393533440 | elapsed time per iteration (s): 0.42 | learning rate: 8.739E-05 | global batch size: 256 | lm loss: 3.011031E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.416 | TFLOPs: 31.66 | +7: iteration 8390/ 14324 | consumed samples: 2147840 | consumed tokens: 4398776320 | elapsed time per iteration (s): 0.43 | learning rate: 8.720E-05 | global batch size: 256 | lm loss: 3.036727E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.654 | TFLOPs: 31.57 | +7: iteration 8400/ 14324 | consumed samples: 2150400 | consumed tokens: 4404019200 | elapsed time per iteration (s): 0.42 | learning rate: 8.700E-05 | global batch size: 256 | lm loss: 2.997528E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.934 | TFLOPs: 31.84 | +7: iteration 8410/ 14324 | consumed samples: 2152960 | consumed tokens: 4409262080 | elapsed time per iteration (s): 0.42 | learning rate: 8.681E-05 | global batch size: 256 | lm loss: 3.014035E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.016 | TFLOPs: 31.69 | +7: iteration 8420/ 14324 | consumed samples: 2155520 | consumed tokens: 4414504960 | elapsed time per iteration (s): 0.42 | learning rate: 8.662E-05 | global batch size: 256 | lm loss: 3.020839E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.054 | TFLOPs: 31.96 | +7: iteration 8430/ 14324 | consumed samples: 2158080 | consumed tokens: 4419747840 | elapsed time per iteration (s): 0.43 | learning rate: 8.643E-05 | global batch size: 256 | lm loss: 3.008243E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.512 | TFLOPs: 31.25 | +7: iteration 8440/ 14324 | consumed samples: 2160640 | consumed tokens: 4424990720 | elapsed time per iteration (s): 0.44 | learning rate: 8.623E-05 | global batch size: 256 | lm loss: 3.008901E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 585.911 | TFLOPs: 30.74 | +7: iteration 8450/ 14324 | consumed samples: 2163200 | consumed tokens: 4430233600 | elapsed time per iteration (s): 0.42 | learning rate: 8.604E-05 | global batch size: 256 | lm loss: 3.011307E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.037 | TFLOPs: 31.69 | +7: iteration 8460/ 14324 | consumed samples: 2165760 | consumed tokens: 4435476480 | elapsed time per iteration (s): 0.42 | learning rate: 8.585E-05 | global batch size: 256 | lm loss: 3.027341E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.426 | TFLOPs: 32.08 | +7: iteration 8470/ 14324 | consumed samples: 2168320 | consumed tokens: 4440719360 | elapsed time per iteration (s): 0.42 | learning rate: 8.566E-05 | global batch size: 256 | lm loss: 3.024079E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 614.611 | TFLOPs: 32.25 | +7: iteration 8480/ 14324 | consumed samples: 2170880 | consumed tokens: 4445962240 | elapsed time per iteration (s): 0.45 | learning rate: 8.547E-05 | global batch size: 256 | lm loss: 3.011238E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 570.969 | TFLOPs: 29.96 | +7: iteration 8490/ 14324 | consumed samples: 2173440 | consumed tokens: 4451205120 | elapsed time per iteration (s): 0.42 | learning rate: 8.527E-05 | global batch size: 256 | lm loss: 3.032846E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.048 | TFLOPs: 32.11 | +7: iteration 8500/ 14324 | consumed samples: 2176000 | consumed tokens: 4456448000 | elapsed time per iteration (s): 0.43 | learning rate: 8.508E-05 | global batch size: 256 | lm loss: 3.059016E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.250 | TFLOPs: 31.23 | +7: iteration 8510/ 14324 | consumed samples: 2178560 | consumed tokens: 4461690880 | elapsed time per iteration (s): 0.42 | learning rate: 8.489E-05 | global batch size: 256 | lm loss: 3.025435E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.416 | TFLOPs: 32.03 | +7: iteration 8520/ 14324 | consumed samples: 2181120 | consumed tokens: 4466933760 | elapsed time per iteration (s): 0.44 | learning rate: 8.470E-05 | global batch size: 256 | lm loss: 3.018655E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 575.348 | TFLOPs: 30.19 | +7: iteration 8530/ 14324 | consumed samples: 2183680 | consumed tokens: 4472176640 | elapsed time per iteration (s): 0.42 | learning rate: 8.451E-05 | global batch size: 256 | lm loss: 3.032512E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.995 | TFLOPs: 31.85 | +7: iteration 8540/ 14324 | consumed samples: 2186240 | consumed tokens: 4477419520 | elapsed time per iteration (s): 0.42 | learning rate: 8.432E-05 | global batch size: 256 | lm loss: 3.015247E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.159 | TFLOPs: 32.07 | +7: iteration 8550/ 14324 | consumed samples: 2188800 | consumed tokens: 4482662400 | elapsed time per iteration (s): 0.43 | learning rate: 8.413E-05 | global batch size: 256 | lm loss: 3.023681E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 590.093 | TFLOPs: 30.96 | +7: iteration 8560/ 14324 | consumed samples: 2191360 | consumed tokens: 4487905280 | elapsed time per iteration (s): 0.42 | learning rate: 8.394E-05 | global batch size: 256 | lm loss: 2.994256E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.373 | TFLOPs: 31.92 | +7: iteration 8570/ 14324 | consumed samples: 2193920 | consumed tokens: 4493148160 | elapsed time per iteration (s): 0.42 | learning rate: 8.374E-05 | global batch size: 256 | lm loss: 3.024393E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.824 | TFLOPs: 32.05 | +7: iteration 8580/ 14324 | consumed samples: 2196480 | consumed tokens: 4498391040 | elapsed time per iteration (s): 0.43 | learning rate: 8.355E-05 | global batch size: 256 | lm loss: 2.988397E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.958 | TFLOPs: 31.22 | +7: iteration 8590/ 14324 | consumed samples: 2199040 | consumed tokens: 4503633920 | elapsed time per iteration (s): 0.42 | learning rate: 8.336E-05 | global batch size: 256 | lm loss: 3.027460E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.173 | TFLOPs: 31.96 | +7: iteration 8600/ 14324 | consumed samples: 2201600 | consumed tokens: 4508876800 | elapsed time per iteration (s): 0.43 | learning rate: 8.317E-05 | global batch size: 256 | lm loss: 2.992558E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.514 | TFLOPs: 31.56 | +7: iteration 8610/ 14324 | consumed samples: 2204160 | consumed tokens: 4514119680 | elapsed time per iteration (s): 0.43 | learning rate: 8.298E-05 | global batch size: 256 | lm loss: 3.006396E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.781 | TFLOPs: 31.57 | +7: iteration 8620/ 14324 | consumed samples: 2206720 | consumed tokens: 4519362560 | elapsed time per iteration (s): 0.43 | learning rate: 8.279E-05 | global batch size: 256 | lm loss: 2.989005E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.042 | TFLOPs: 31.54 | +7: iteration 8630/ 14324 | consumed samples: 2209280 | consumed tokens: 4524605440 | elapsed time per iteration (s): 0.42 | learning rate: 8.260E-05 | global batch size: 256 | lm loss: 3.049271E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.509 | TFLOPs: 31.67 | +7: iteration 8640/ 14324 | consumed samples: 2211840 | consumed tokens: 4529848320 | elapsed time per iteration (s): 0.43 | learning rate: 8.241E-05 | global batch size: 256 | lm loss: 3.056828E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.158 | TFLOPs: 31.23 | +7: iteration 8650/ 14324 | consumed samples: 2214400 | consumed tokens: 4535091200 | elapsed time per iteration (s): 0.43 | learning rate: 8.222E-05 | global batch size: 256 | lm loss: 3.002451E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.137 | TFLOPs: 31.28 | +7: iteration 8660/ 14324 | consumed samples: 2216960 | consumed tokens: 4540334080 | elapsed time per iteration (s): 0.43 | learning rate: 8.203E-05 | global batch size: 256 | lm loss: 3.001473E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.671 | TFLOPs: 31.46 | +7: iteration 8670/ 14324 | consumed samples: 2219520 | consumed tokens: 4545576960 | elapsed time per iteration (s): 0.43 | learning rate: 8.184E-05 | global batch size: 256 | lm loss: 3.020627E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.277 | TFLOPs: 31.34 | +7: iteration 8680/ 14324 | consumed samples: 2222080 | consumed tokens: 4550819840 | elapsed time per iteration (s): 0.42 | learning rate: 8.165E-05 | global batch size: 256 | lm loss: 2.989781E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.205 | TFLOPs: 31.65 | +7: iteration 8690/ 14324 | consumed samples: 2224640 | consumed tokens: 4556062720 | elapsed time per iteration (s): 0.42 | learning rate: 8.147E-05 | global batch size: 256 | lm loss: 2.983568E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.359 | TFLOPs: 31.66 | +7: iteration 8700/ 14324 | consumed samples: 2227200 | consumed tokens: 4561305600 | elapsed time per iteration (s): 0.42 | learning rate: 8.128E-05 | global batch size: 256 | lm loss: 3.030231E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.265 | TFLOPs: 31.81 | +7: iteration 8710/ 14324 | consumed samples: 2229760 | consumed tokens: 4566548480 | elapsed time per iteration (s): 0.44 | learning rate: 8.109E-05 | global batch size: 256 | lm loss: 3.024949E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 588.176 | TFLOPs: 30.86 | +7: iteration 8720/ 14324 | consumed samples: 2232320 | consumed tokens: 4571791360 | elapsed time per iteration (s): 0.42 | learning rate: 8.090E-05 | global batch size: 256 | lm loss: 2.998247E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.452 | TFLOPs: 32.08 | +7: iteration 8730/ 14324 | consumed samples: 2234880 | consumed tokens: 4577034240 | elapsed time per iteration (s): 0.43 | learning rate: 8.071E-05 | global batch size: 256 | lm loss: 3.018421E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.769 | TFLOPs: 31.47 | +7: iteration 8740/ 14324 | consumed samples: 2237440 | consumed tokens: 4582277120 | elapsed time per iteration (s): 0.44 | learning rate: 8.052E-05 | global batch size: 256 | lm loss: 3.014248E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 584.827 | TFLOPs: 30.68 | +7: iteration 8750/ 14324 | consumed samples: 2240000 | consumed tokens: 4587520000 | elapsed time per iteration (s): 0.43 | learning rate: 8.033E-05 | global batch size: 256 | lm loss: 2.995281E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.266 | TFLOPs: 31.29 | +7: iteration 8760/ 14324 | consumed samples: 2242560 | consumed tokens: 4592762880 | elapsed time per iteration (s): 0.48 | learning rate: 8.015E-05 | global batch size: 256 | lm loss: 2.999558E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.129 | TFLOPs: 28.13 | +7: iteration 8770/ 14324 | consumed samples: 2245120 | consumed tokens: 4598005760 | elapsed time per iteration (s): 0.43 | learning rate: 7.996E-05 | global batch size: 256 | lm loss: 3.009244E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.292 | TFLOPs: 31.34 | +7: iteration 8780/ 14324 | consumed samples: 2247680 | consumed tokens: 4603248640 | elapsed time per iteration (s): 0.44 | learning rate: 7.977E-05 | global batch size: 256 | lm loss: 3.025314E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 581.083 | TFLOPs: 30.49 | +7: iteration 8790/ 14324 | consumed samples: 2250240 | consumed tokens: 4608491520 | elapsed time per iteration (s): 0.44 | learning rate: 7.958E-05 | global batch size: 256 | lm loss: 3.023857E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 587.044 | TFLOPs: 30.80 | +7: iteration 8800/ 14324 | consumed samples: 2252800 | consumed tokens: 4613734400 | elapsed time per iteration (s): 0.44 | learning rate: 7.939E-05 | global batch size: 256 | lm loss: 3.008845E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 579.228 | TFLOPs: 30.39 | +7: iteration 8810/ 14324 | consumed samples: 2255360 | consumed tokens: 4618977280 | elapsed time per iteration (s): 0.53 | learning rate: 7.921E-05 | global batch size: 256 | lm loss: 3.008878E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 484.205 | TFLOPs: 25.41 | +7: iteration 8820/ 14324 | consumed samples: 2257920 | consumed tokens: 4624220160 | elapsed time per iteration (s): 0.44 | learning rate: 7.902E-05 | global batch size: 256 | lm loss: 3.001427E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 586.209 | TFLOPs: 30.76 | +7: iteration 8830/ 14324 | consumed samples: 2260480 | consumed tokens: 4629463040 | elapsed time per iteration (s): 0.43 | learning rate: 7.883E-05 | global batch size: 256 | lm loss: 3.015940E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.474 | TFLOPs: 31.51 | +7: iteration 8840/ 14324 | consumed samples: 2263040 | consumed tokens: 4634705920 | elapsed time per iteration (s): 0.58 | learning rate: 7.865E-05 | global batch size: 256 | lm loss: 3.006571E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.243 | TFLOPs: 23.05 | +7: iteration 8850/ 14324 | consumed samples: 2265600 | consumed tokens: 4639948800 | elapsed time per iteration (s): 0.42 | learning rate: 7.846E-05 | global batch size: 256 | lm loss: 3.030397E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.854 | TFLOPs: 31.68 | +7: iteration 8860/ 14324 | consumed samples: 2268160 | consumed tokens: 4645191680 | elapsed time per iteration (s): 0.43 | learning rate: 7.827E-05 | global batch size: 256 | lm loss: 3.005455E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.344 | TFLOPs: 31.45 | +7: iteration 8870/ 14324 | consumed samples: 2270720 | consumed tokens: 4650434560 | elapsed time per iteration (s): 0.42 | learning rate: 7.809E-05 | global batch size: 256 | lm loss: 3.024313E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.528 | TFLOPs: 31.98 | +7: iteration 8880/ 14324 | consumed samples: 2273280 | consumed tokens: 4655677440 | elapsed time per iteration (s): 0.43 | learning rate: 7.790E-05 | global batch size: 256 | lm loss: 3.007896E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.811 | TFLOPs: 31.47 | +7: iteration 8890/ 14324 | consumed samples: 2275840 | consumed tokens: 4660920320 | elapsed time per iteration (s): 0.42 | learning rate: 7.771E-05 | global batch size: 256 | lm loss: 3.018329E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.082 | TFLOPs: 31.80 | +7: iteration 8900/ 14324 | consumed samples: 2278400 | consumed tokens: 4666163200 | elapsed time per iteration (s): 0.42 | learning rate: 7.753E-05 | global batch size: 256 | lm loss: 3.006076E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.428 | TFLOPs: 31.82 | +7: iteration 8910/ 14324 | consumed samples: 2280960 | consumed tokens: 4671406080 | elapsed time per iteration (s): 0.42 | learning rate: 7.734E-05 | global batch size: 256 | lm loss: 3.026728E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.804 | TFLOPs: 31.84 | +7: iteration 8920/ 14324 | consumed samples: 2283520 | consumed tokens: 4676648960 | elapsed time per iteration (s): 0.42 | learning rate: 7.715E-05 | global batch size: 256 | lm loss: 3.004606E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.383 | TFLOPs: 31.92 | +7: iteration 8930/ 14324 | consumed samples: 2286080 | consumed tokens: 4681891840 | elapsed time per iteration (s): 0.42 | learning rate: 7.697E-05 | global batch size: 256 | lm loss: 3.016050E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.912 | TFLOPs: 31.79 | +7: iteration 8940/ 14324 | consumed samples: 2288640 | consumed tokens: 4687134720 | elapsed time per iteration (s): 0.42 | learning rate: 7.678E-05 | global batch size: 256 | lm loss: 3.016356E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.515 | TFLOPs: 31.72 | +7: iteration 8950/ 14324 | consumed samples: 2291200 | consumed tokens: 4692377600 | elapsed time per iteration (s): 0.42 | learning rate: 7.660E-05 | global batch size: 256 | lm loss: 3.001362E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.173 | TFLOPs: 31.80 | +7: iteration 8960/ 14324 | consumed samples: 2293760 | consumed tokens: 4697620480 | elapsed time per iteration (s): 0.42 | learning rate: 7.641E-05 | global batch size: 256 | lm loss: 3.011364E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.299 | TFLOPs: 32.13 | +7: iteration 8970/ 14324 | consumed samples: 2296320 | consumed tokens: 4702863360 | elapsed time per iteration (s): 0.42 | learning rate: 7.623E-05 | global batch size: 256 | lm loss: 3.015723E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.440 | TFLOPs: 32.03 | +7: iteration 8980/ 14324 | consumed samples: 2298880 | consumed tokens: 4708106240 | elapsed time per iteration (s): 0.43 | learning rate: 7.604E-05 | global batch size: 256 | lm loss: 2.981132E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.719 | TFLOPs: 31.52 | +7: iteration 8990/ 14324 | consumed samples: 2301440 | consumed tokens: 4713349120 | elapsed time per iteration (s): 0.42 | learning rate: 7.586E-05 | global batch size: 256 | lm loss: 3.010715E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.226 | TFLOPs: 31.81 | +7: iteration 9000/ 14324 | consumed samples: 2304000 | consumed tokens: 4718592000 | elapsed time per iteration (s): 0.43 | learning rate: 7.568E-05 | global batch size: 256 | lm loss: 3.026762E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.043 | TFLOPs: 31.38 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 9000 | lm loss value: 2.838673E+00 | lm loss PPL: 1.709306E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 9000 to checkpoints_220moscar +0: [2022-11-29 23:04:46,359] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step9000 is begin to save! +0: [2022-11-29 23:04:46,365] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/layer_01-model_00-model_states.pt... +0: [2022-11-29 23:04:46,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/layer_01-model_00-model_states.pt. +0: [2022-11-29 23:04:46,505] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/layer_03-model_00-model_states.pt... +0: [2022-11-29 23:04:46,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/layer_03-model_00-model_states.pt. +0: [2022-11-29 23:04:46,529] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/layer_04-model_00-model_states.pt... +0: [2022-11-29 23:04:46,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/layer_04-model_00-model_states.pt. +0: [2022-11-29 23:04:46,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/layer_05-model_00-model_states.pt... +0: [2022-11-29 23:04:46,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/layer_05-model_00-model_states.pt. +0: [2022-11-29 23:04:46,577] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/layer_06-model_00-model_states.pt... +0: [2022-11-29 23:04:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/layer_06-model_00-model_states.pt. +0: [2022-11-29 23:04:46,603] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/layer_07-model_00-model_states.pt... +0: [2022-11-29 23:04:46,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/layer_07-model_00-model_states.pt. +0: [2022-11-29 23:04:46,626] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/layer_08-model_00-model_states.pt... +0: [2022-11-29 23:04:46,649] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/layer_08-model_00-model_states.pt. +0: [2022-11-29 23:04:46,650] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/layer_09-model_00-model_states.pt... +0: [2022-11-29 23:04:46,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/layer_09-model_00-model_states.pt. +0: [2022-11-29 23:04:46,676] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/layer_10-model_00-model_states.pt... +0: [2022-11-29 23:04:46,699] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/layer_10-model_00-model_states.pt. +0: [2022-11-29 23:04:46,699] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/layer_11-model_00-model_states.pt... +0: [2022-11-29 23:04:46,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/layer_11-model_00-model_states.pt. +0: [2022-11-29 23:04:46,723] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/layer_12-model_00-model_states.pt... +0: [2022-11-29 23:04:46,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/layer_12-model_00-model_states.pt. +0: [2022-11-29 23:04:46,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/layer_13-model_00-model_states.pt... +0: [2022-11-29 23:04:46,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/layer_13-model_00-model_states.pt. +0: [2022-11-29 23:04:46,769] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/layer_14-model_00-model_states.pt... +0: [2022-11-29 23:04:46,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/layer_14-model_00-model_states.pt. +0: [2022-11-29 23:04:46,793] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/layer_15-model_00-model_states.pt... +0: [2022-11-29 23:04:46,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/layer_15-model_00-model_states.pt. +0: [2022-11-29 23:04:46,816] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/layer_16-model_00-model_states.pt... +0: [2022-11-29 23:04:46,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/layer_16-model_00-model_states.pt. +0: [2022-11-29 23:04:46,840] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/layer_17-model_00-model_states.pt... +0: [2022-11-29 23:04:46,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/layer_17-model_00-model_states.pt. +0: [2022-11-29 23:04:46,864] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/layer_18-model_00-model_states.pt... +0: [2022-11-29 23:04:46,887] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/layer_18-model_00-model_states.pt. +0: [2022-11-29 23:04:46,887] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/layer_19-model_00-model_states.pt... +0: [2022-11-29 23:04:46,910] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/layer_19-model_00-model_states.pt. +0: [2022-11-29 23:04:46,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/layer_20-model_00-model_states.pt... +0: [2022-11-29 23:04:46,933] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/layer_20-model_00-model_states.pt. +0: [2022-11-29 23:04:46,934] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/layer_22-model_00-model_states.pt... +0: [2022-11-29 23:04:46,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/layer_22-model_00-model_states.pt. +0: [2022-11-29 23:04:46,938] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_220moscar/global_step9000/mp_rank_00_model_states.pt +0: [2022-11-29 23:04:46,938] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/mp_rank_00_model_states.pt... +0: [2022-11-29 23:04:46,942] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/mp_rank_00_model_states.pt. +0: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:04:46,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:04:47,013] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:04:47,013] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 23:04:47,013] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 23:04:47,013] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:04:47,013] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 23:04:47,014] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 23:04:47,014] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:04:47,014] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:04:47,014] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:04:47,014] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 23:04:47,014] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 23:04:47,014] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 23:04:47,015] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 23:04:47,015] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 23:04:47,015] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 23:04:47,015] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:04:47,015] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 23:04:47,015] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 23:04:47,015] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:04:47,015] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 23:04:47,015] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 23:04:47,015] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:04:47,016] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 23:04:47,016] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 23:04:47,017] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:04:47,017] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 23:04:47,017] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 23:04:47,018] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:04:47,018] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 23:04:47,018] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 23:04:47,020] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:04:47,020] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 23:04:47,020] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 23:04:47,023] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:04:47,023] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:04:47,023] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:04:47,023] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:04:47,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 23:04:47,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 23:04:47,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 23:04:47,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 23:04:47,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 23:04:47,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 23:04:47,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:04:47,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 23:04:47,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 23:04:47,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:04:47,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 23:04:47,025] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 23:04:47,025] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:04:47,025] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 23:04:47,025] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 23:04:47,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:04:47,026] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 23:04:47,026] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 23:04:47,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:04:47,026] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 23:04:47,026] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 23:04:47,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:04:47,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:04:47,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:04:47,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 23:04:47,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 23:04:47,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 23:04:47,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 23:04:47,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 23:04:47,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 23:04:47,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:04:47,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 23:04:47,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 23:04:47,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:04:47,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:04:47,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:04:47,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:04:47,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:04:47,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:04:47,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:04:47,043] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 23:04:47,043] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 23:04:47,043] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 23:04:47,043] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 23:04:47,043] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 23:04:47,043] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 23:04:47,043] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 23:04:47,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 23:04:47,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 23:04:47,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 23:04:47,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 23:04:47,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 23:04:47,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 23:04:47,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 23:04:47,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:04:47,043] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 23:04:47,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:04:47,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 23:04:47,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 23:04:47,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 23:04:47,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 23:04:47,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 23:04:47,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 23:04:47,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 23:04:47,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:04:47,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 23:04:47,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 23:04:47,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 23:04:47,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 23:04:47,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 23:04:47,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 23:04:47,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 23:04:47,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 23:04:47,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 23:04:47,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:04:47,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:04:47,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:04:47,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:04:47,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:04:47,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:04:47,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:04:47,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:04:47,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 23:04:47,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 23:04:47,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 23:04:47,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 23:04:47,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 23:04:47,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 23:04:47,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 23:04:47,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 23:04:47,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 23:04:47,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 23:04:47,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 23:04:47,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 23:04:47,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 23:04:47,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 23:04:47,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 23:04:47,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 23:04:47,073] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:04:47,073] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:04:47,073] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:04:47,073] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:04:47,073] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 23:04:47,073] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:04:47,073] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 23:04:47,073] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 23:04:47,073] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:04:47,073] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:04:47,073] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:04:47,074] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 23:04:47,074] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 23:04:47,074] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 23:04:47,074] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 23:04:47,074] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 23:04:47,074] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 23:04:47,074] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 23:04:47,074] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 23:04:47,074] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 23:04:47,074] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 23:04:47,074] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 23:04:47,074] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 23:04:47,074] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 23:04:47,088] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step9000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 23:04:47,088] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: successfully saved checkpoint at iteration 9000 to checkpoints_220moscar +7: time (ms) | save-checkpoint: 762.34 +7: iteration 9010/ 14324 | consumed samples: 2306560 | consumed tokens: 4723834880 | elapsed time per iteration (s): 0.52 | learning rate: 7.549E-05 | global batch size: 256 | lm loss: 3.003588E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 492.808 | TFLOPs: 25.86 | +7: iteration 9020/ 14324 | consumed samples: 2309120 | consumed tokens: 4729077760 | elapsed time per iteration (s): 0.42 | learning rate: 7.531E-05 | global batch size: 256 | lm loss: 2.994782E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.304 | TFLOPs: 31.97 | +7: iteration 9030/ 14324 | consumed samples: 2311680 | consumed tokens: 4734320640 | elapsed time per iteration (s): 0.43 | learning rate: 7.512E-05 | global batch size: 256 | lm loss: 2.998959E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.642 | TFLOPs: 31.36 | +7: iteration 9040/ 14324 | consumed samples: 2314240 | consumed tokens: 4739563520 | elapsed time per iteration (s): 0.43 | learning rate: 7.494E-05 | global batch size: 256 | lm loss: 2.982408E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.520 | TFLOPs: 31.04 | +7: iteration 9050/ 14324 | consumed samples: 2316800 | consumed tokens: 4744806400 | elapsed time per iteration (s): 0.43 | learning rate: 7.476E-05 | global batch size: 256 | lm loss: 2.993701E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 590.119 | TFLOPs: 30.96 | +7: iteration 9060/ 14324 | consumed samples: 2319360 | consumed tokens: 4750049280 | elapsed time per iteration (s): 0.43 | learning rate: 7.457E-05 | global batch size: 256 | lm loss: 2.974734E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.242 | TFLOPs: 31.07 | +7: iteration 9070/ 14324 | consumed samples: 2321920 | consumed tokens: 4755292160 | elapsed time per iteration (s): 0.43 | learning rate: 7.439E-05 | global batch size: 256 | lm loss: 3.005685E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.783 | TFLOPs: 31.42 | +7: iteration 9080/ 14324 | consumed samples: 2324480 | consumed tokens: 4760535040 | elapsed time per iteration (s): 0.42 | learning rate: 7.421E-05 | global batch size: 256 | lm loss: 3.019920E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.093 | TFLOPs: 31.91 | +7: iteration 9090/ 14324 | consumed samples: 2327040 | consumed tokens: 4765777920 | elapsed time per iteration (s): 0.42 | learning rate: 7.402E-05 | global batch size: 256 | lm loss: 3.023948E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.914 | TFLOPs: 31.79 | +7: iteration 9100/ 14324 | consumed samples: 2329600 | consumed tokens: 4771020800 | elapsed time per iteration (s): 0.43 | learning rate: 7.384E-05 | global batch size: 256 | lm loss: 2.984293E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.913 | TFLOPs: 31.06 | +7: iteration 9110/ 14324 | consumed samples: 2332160 | consumed tokens: 4776263680 | elapsed time per iteration (s): 0.42 | learning rate: 7.366E-05 | global batch size: 256 | lm loss: 2.991941E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.709 | TFLOPs: 31.73 | +7: iteration 9120/ 14324 | consumed samples: 2334720 | consumed tokens: 4781506560 | elapsed time per iteration (s): 0.44 | learning rate: 7.348E-05 | global batch size: 256 | lm loss: 2.986980E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 587.047 | TFLOPs: 30.80 | +7: iteration 9130/ 14324 | consumed samples: 2337280 | consumed tokens: 4786749440 | elapsed time per iteration (s): 0.43 | learning rate: 7.329E-05 | global batch size: 256 | lm loss: 2.996066E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.217 | TFLOPs: 31.23 | +7: iteration 9140/ 14324 | consumed samples: 2339840 | consumed tokens: 4791992320 | elapsed time per iteration (s): 0.43 | learning rate: 7.311E-05 | global batch size: 256 | lm loss: 2.995538E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.463 | TFLOPs: 31.40 | +7: iteration 9150/ 14324 | consumed samples: 2342400 | consumed tokens: 4797235200 | elapsed time per iteration (s): 0.43 | learning rate: 7.293E-05 | global batch size: 256 | lm loss: 2.966483E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.406 | TFLOPs: 31.19 | +7: iteration 9160/ 14324 | consumed samples: 2344960 | consumed tokens: 4802478080 | elapsed time per iteration (s): 0.43 | learning rate: 7.275E-05 | global batch size: 256 | lm loss: 3.003354E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.659 | TFLOPs: 31.46 | +7: iteration 9170/ 14324 | consumed samples: 2347520 | consumed tokens: 4807720960 | elapsed time per iteration (s): 0.43 | learning rate: 7.257E-05 | global batch size: 256 | lm loss: 2.997318E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 588.723 | TFLOPs: 30.89 | +7: iteration 9180/ 14324 | consumed samples: 2350080 | consumed tokens: 4812963840 | elapsed time per iteration (s): 0.43 | learning rate: 7.239E-05 | global batch size: 256 | lm loss: 2.986908E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.043 | TFLOPs: 31.38 | +7: iteration 9190/ 14324 | consumed samples: 2352640 | consumed tokens: 4818206720 | elapsed time per iteration (s): 0.43 | learning rate: 7.220E-05 | global batch size: 256 | lm loss: 2.988094E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.535 | TFLOPs: 31.30 | +7: iteration 9200/ 14324 | consumed samples: 2355200 | consumed tokens: 4823449600 | elapsed time per iteration (s): 0.42 | learning rate: 7.202E-05 | global batch size: 256 | lm loss: 3.021176E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.783 | TFLOPs: 31.73 | +7: iteration 9210/ 14324 | consumed samples: 2357760 | consumed tokens: 4828692480 | elapsed time per iteration (s): 0.43 | learning rate: 7.184E-05 | global batch size: 256 | lm loss: 3.017167E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.842 | TFLOPs: 31.21 | +7: iteration 9220/ 14324 | consumed samples: 2360320 | consumed tokens: 4833935360 | elapsed time per iteration (s): 0.42 | learning rate: 7.166E-05 | global batch size: 256 | lm loss: 3.013925E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.668 | TFLOPs: 31.83 | +7: iteration 9230/ 14324 | consumed samples: 2362880 | consumed tokens: 4839178240 | elapsed time per iteration (s): 0.42 | learning rate: 7.148E-05 | global batch size: 256 | lm loss: 3.001825E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.071 | TFLOPs: 32.01 | +7: iteration 9240/ 14324 | consumed samples: 2365440 | consumed tokens: 4844421120 | elapsed time per iteration (s): 0.43 | learning rate: 7.130E-05 | global batch size: 256 | lm loss: 3.030872E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.431 | TFLOPs: 31.08 | +7: iteration 9250/ 14324 | consumed samples: 2368000 | consumed tokens: 4849664000 | elapsed time per iteration (s): 0.42 | learning rate: 7.112E-05 | global batch size: 256 | lm loss: 3.022028E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.610 | TFLOPs: 31.62 | +7: iteration 9260/ 14324 | consumed samples: 2370560 | consumed tokens: 4854906880 | elapsed time per iteration (s): 0.42 | learning rate: 7.094E-05 | global batch size: 256 | lm loss: 2.975941E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.810 | TFLOPs: 31.79 | +7: iteration 9270/ 14324 | consumed samples: 2373120 | consumed tokens: 4860149760 | elapsed time per iteration (s): 0.42 | learning rate: 7.076E-05 | global batch size: 256 | lm loss: 2.965026E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.997 | TFLOPs: 31.95 | +7: iteration 9280/ 14324 | consumed samples: 2375680 | consumed tokens: 4865392640 | elapsed time per iteration (s): 0.42 | learning rate: 7.058E-05 | global batch size: 256 | lm loss: 3.011081E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.661 | TFLOPs: 32.04 | +7: iteration 9290/ 14324 | consumed samples: 2378240 | consumed tokens: 4870635520 | elapsed time per iteration (s): 0.44 | learning rate: 7.040E-05 | global batch size: 256 | lm loss: 2.990460E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 582.901 | TFLOPs: 30.58 | +7: iteration 9300/ 14324 | consumed samples: 2380800 | consumed tokens: 4875878400 | elapsed time per iteration (s): 0.42 | learning rate: 7.023E-05 | global batch size: 256 | lm loss: 2.979782E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.892 | TFLOPs: 31.74 | +7: iteration 9310/ 14324 | consumed samples: 2383360 | consumed tokens: 4881121280 | elapsed time per iteration (s): 0.42 | learning rate: 7.005E-05 | global batch size: 256 | lm loss: 2.999165E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.395 | TFLOPs: 31.71 | +7: iteration 9320/ 14324 | consumed samples: 2385920 | consumed tokens: 4886364160 | elapsed time per iteration (s): 0.43 | learning rate: 6.987E-05 | global batch size: 256 | lm loss: 2.971122E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.680 | TFLOPs: 31.52 | +7: iteration 9330/ 14324 | consumed samples: 2388480 | consumed tokens: 4891607040 | elapsed time per iteration (s): 0.44 | learning rate: 6.969E-05 | global batch size: 256 | lm loss: 2.977760E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 582.209 | TFLOPs: 30.55 | +7: iteration 9340/ 14324 | consumed samples: 2391040 | consumed tokens: 4896849920 | elapsed time per iteration (s): 0.43 | learning rate: 6.951E-05 | global batch size: 256 | lm loss: 2.991643E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.870 | TFLOPs: 31.21 | +7: iteration 9350/ 14324 | consumed samples: 2393600 | consumed tokens: 4902092800 | elapsed time per iteration (s): 0.43 | learning rate: 6.933E-05 | global batch size: 256 | lm loss: 3.002050E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.265 | TFLOPs: 31.49 | +7: iteration 9360/ 14324 | consumed samples: 2396160 | consumed tokens: 4907335680 | elapsed time per iteration (s): 0.42 | learning rate: 6.916E-05 | global batch size: 256 | lm loss: 2.987187E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.230 | TFLOPs: 32.12 | +7: iteration 9370/ 14324 | consumed samples: 2398720 | consumed tokens: 4912578560 | elapsed time per iteration (s): 0.43 | learning rate: 6.898E-05 | global batch size: 256 | lm loss: 2.987012E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 590.800 | TFLOPs: 31.00 | +7: iteration 9380/ 14324 | consumed samples: 2401280 | consumed tokens: 4917821440 | elapsed time per iteration (s): 0.42 | learning rate: 6.880E-05 | global batch size: 256 | lm loss: 2.995406E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.719 | TFLOPs: 31.83 | +7: iteration 9390/ 14324 | consumed samples: 2403840 | consumed tokens: 4923064320 | elapsed time per iteration (s): 0.42 | learning rate: 6.862E-05 | global batch size: 256 | lm loss: 2.982496E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.683 | TFLOPs: 31.94 | +7: iteration 9400/ 14324 | consumed samples: 2406400 | consumed tokens: 4928307200 | elapsed time per iteration (s): 0.44 | learning rate: 6.845E-05 | global batch size: 256 | lm loss: 2.991111E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 581.513 | TFLOPs: 30.51 | +7: iteration 9410/ 14324 | consumed samples: 2408960 | consumed tokens: 4933550080 | elapsed time per iteration (s): 0.42 | learning rate: 6.827E-05 | global batch size: 256 | lm loss: 3.003658E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.234 | TFLOPs: 31.86 | +7: iteration 9420/ 14324 | consumed samples: 2411520 | consumed tokens: 4938792960 | elapsed time per iteration (s): 0.42 | learning rate: 6.809E-05 | global batch size: 256 | lm loss: 2.989027E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.969 | TFLOPs: 31.95 | +7: iteration 9430/ 14324 | consumed samples: 2414080 | consumed tokens: 4944035840 | elapsed time per iteration (s): 0.42 | learning rate: 6.792E-05 | global batch size: 256 | lm loss: 3.013395E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.642 | TFLOPs: 31.78 | +7: iteration 9440/ 14324 | consumed samples: 2416640 | consumed tokens: 4949278720 | elapsed time per iteration (s): 0.42 | learning rate: 6.774E-05 | global batch size: 256 | lm loss: 3.020386E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.884 | TFLOPs: 31.63 | +7: iteration 9450/ 14324 | consumed samples: 2419200 | consumed tokens: 4954521600 | elapsed time per iteration (s): 0.43 | learning rate: 6.757E-05 | global batch size: 256 | lm loss: 2.968862E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.333 | TFLOPs: 31.60 | +7: iteration 9460/ 14324 | consumed samples: 2421760 | consumed tokens: 4959764480 | elapsed time per iteration (s): 0.42 | learning rate: 6.739E-05 | global batch size: 256 | lm loss: 2.986077E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.847 | TFLOPs: 31.84 | +7: iteration 9470/ 14324 | consumed samples: 2424320 | consumed tokens: 4965007360 | elapsed time per iteration (s): 0.42 | learning rate: 6.721E-05 | global batch size: 256 | lm loss: 3.015929E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.266 | TFLOPs: 31.76 | +7: iteration 9480/ 14324 | consumed samples: 2426880 | consumed tokens: 4970250240 | elapsed time per iteration (s): 0.42 | learning rate: 6.704E-05 | global batch size: 256 | lm loss: 2.974741E+00 | grad norm: 0.443 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.740 | TFLOPs: 31.83 | +7: iteration 9490/ 14324 | consumed samples: 2429440 | consumed tokens: 4975493120 | elapsed time per iteration (s): 0.44 | learning rate: 6.686E-05 | global batch size: 256 | lm loss: 2.958925E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 584.111 | TFLOPs: 30.65 | +7: iteration 9500/ 14324 | consumed samples: 2432000 | consumed tokens: 4980736000 | elapsed time per iteration (s): 0.42 | learning rate: 6.669E-05 | global batch size: 256 | lm loss: 2.997204E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.830 | TFLOPs: 32.00 | +7: iteration 9510/ 14324 | consumed samples: 2434560 | consumed tokens: 4985978880 | elapsed time per iteration (s): 0.42 | learning rate: 6.651E-05 | global batch size: 256 | lm loss: 2.997874E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.436 | TFLOPs: 31.71 | +7: iteration 9520/ 14324 | consumed samples: 2437120 | consumed tokens: 4991221760 | elapsed time per iteration (s): 0.43 | learning rate: 6.634E-05 | global batch size: 256 | lm loss: 3.014476E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.345 | TFLOPs: 31.60 | +7: iteration 9530/ 14324 | consumed samples: 2439680 | consumed tokens: 4996464640 | elapsed time per iteration (s): 0.42 | learning rate: 6.617E-05 | global batch size: 256 | lm loss: 2.980772E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.550 | TFLOPs: 31.88 | +7: iteration 9540/ 14324 | consumed samples: 2442240 | consumed tokens: 5001707520 | elapsed time per iteration (s): 0.42 | learning rate: 6.599E-05 | global batch size: 256 | lm loss: 3.001985E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.287 | TFLOPs: 31.71 | +7: iteration 9550/ 14324 | consumed samples: 2444800 | consumed tokens: 5006950400 | elapsed time per iteration (s): 0.42 | learning rate: 6.582E-05 | global batch size: 256 | lm loss: 2.993887E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.020 | TFLOPs: 32.01 | +7: iteration 9560/ 14324 | consumed samples: 2447360 | consumed tokens: 5012193280 | elapsed time per iteration (s): 0.42 | learning rate: 6.564E-05 | global batch size: 256 | lm loss: 2.979920E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.690 | TFLOPs: 31.62 | +7: iteration 9570/ 14324 | consumed samples: 2449920 | consumed tokens: 5017436160 | elapsed time per iteration (s): 0.42 | learning rate: 6.547E-05 | global batch size: 256 | lm loss: 2.966392E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.532 | TFLOPs: 31.93 | +7: iteration 9580/ 14324 | consumed samples: 2452480 | consumed tokens: 5022679040 | elapsed time per iteration (s): 0.42 | learning rate: 6.530E-05 | global batch size: 256 | lm loss: 2.992603E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.868 | TFLOPs: 31.74 | +7: iteration 9590/ 14324 | consumed samples: 2455040 | consumed tokens: 5027921920 | elapsed time per iteration (s): 0.42 | learning rate: 6.512E-05 | global batch size: 256 | lm loss: 3.003476E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.985 | TFLOPs: 31.80 | +7: iteration 9600/ 14324 | consumed samples: 2457600 | consumed tokens: 5033164800 | elapsed time per iteration (s): 0.44 | learning rate: 6.495E-05 | global batch size: 256 | lm loss: 2.983917E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 579.975 | TFLOPs: 30.43 | +7: iteration 9610/ 14324 | consumed samples: 2460160 | consumed tokens: 5038407680 | elapsed time per iteration (s): 0.42 | learning rate: 6.478E-05 | global batch size: 256 | lm loss: 2.950654E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.585 | TFLOPs: 31.62 | +7: iteration 9620/ 14324 | consumed samples: 2462720 | consumed tokens: 5043650560 | elapsed time per iteration (s): 0.42 | learning rate: 6.461E-05 | global batch size: 256 | lm loss: 2.999655E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.685 | TFLOPs: 31.83 | +7: iteration 9630/ 14324 | consumed samples: 2465280 | consumed tokens: 5048893440 | elapsed time per iteration (s): 0.42 | learning rate: 6.443E-05 | global batch size: 256 | lm loss: 2.985914E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.503 | TFLOPs: 31.61 | +7: iteration 9640/ 14324 | consumed samples: 2467840 | consumed tokens: 5054136320 | elapsed time per iteration (s): 0.43 | learning rate: 6.426E-05 | global batch size: 256 | lm loss: 2.986856E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.505 | TFLOPs: 31.40 | +7: iteration 9650/ 14324 | consumed samples: 2470400 | consumed tokens: 5059379200 | elapsed time per iteration (s): 0.42 | learning rate: 6.409E-05 | global batch size: 256 | lm loss: 2.988157E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.581 | TFLOPs: 32.14 | +7: iteration 9660/ 14324 | consumed samples: 2472960 | consumed tokens: 5064622080 | elapsed time per iteration (s): 0.42 | learning rate: 6.392E-05 | global batch size: 256 | lm loss: 2.980061E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.359 | TFLOPs: 32.13 | +7: iteration 9670/ 14324 | consumed samples: 2475520 | consumed tokens: 5069864960 | elapsed time per iteration (s): 0.42 | learning rate: 6.375E-05 | global batch size: 256 | lm loss: 2.982352E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.740 | TFLOPs: 31.94 | +7: iteration 9680/ 14324 | consumed samples: 2478080 | consumed tokens: 5075107840 | elapsed time per iteration (s): 0.42 | learning rate: 6.358E-05 | global batch size: 256 | lm loss: 2.945091E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.031 | TFLOPs: 31.80 | +7: iteration 9690/ 14324 | consumed samples: 2480640 | consumed tokens: 5080350720 | elapsed time per iteration (s): 0.42 | learning rate: 6.341E-05 | global batch size: 256 | lm loss: 2.994606E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.950 | TFLOPs: 32.00 | +7: iteration 9700/ 14324 | consumed samples: 2483200 | consumed tokens: 5085593600 | elapsed time per iteration (s): 0.43 | learning rate: 6.324E-05 | global batch size: 256 | lm loss: 2.968988E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.202 | TFLOPs: 31.33 | +7: iteration 9710/ 14324 | consumed samples: 2485760 | consumed tokens: 5090836480 | elapsed time per iteration (s): 0.42 | learning rate: 6.307E-05 | global batch size: 256 | lm loss: 3.001221E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.999 | TFLOPs: 31.90 | +7: iteration 9720/ 14324 | consumed samples: 2488320 | consumed tokens: 5096079360 | elapsed time per iteration (s): 0.42 | learning rate: 6.290E-05 | global batch size: 256 | lm loss: 2.968165E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.353 | TFLOPs: 31.66 | +7: iteration 9730/ 14324 | consumed samples: 2490880 | consumed tokens: 5101322240 | elapsed time per iteration (s): 0.42 | learning rate: 6.273E-05 | global batch size: 256 | lm loss: 2.987117E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.115 | TFLOPs: 31.80 | +7: iteration 9740/ 14324 | consumed samples: 2493440 | consumed tokens: 5106565120 | elapsed time per iteration (s): 0.42 | learning rate: 6.256E-05 | global batch size: 256 | lm loss: 2.950229E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.929 | TFLOPs: 31.79 | +7: iteration 9750/ 14324 | consumed samples: 2496000 | consumed tokens: 5111808000 | elapsed time per iteration (s): 0.42 | learning rate: 6.239E-05 | global batch size: 256 | lm loss: 3.002647E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.049 | TFLOPs: 32.06 | +7: iteration 9760/ 14324 | consumed samples: 2498560 | consumed tokens: 5117050880 | elapsed time per iteration (s): 0.43 | learning rate: 6.222E-05 | global batch size: 256 | lm loss: 3.007329E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.980 | TFLOPs: 31.11 | +7: iteration 9770/ 14324 | consumed samples: 2501120 | consumed tokens: 5122293760 | elapsed time per iteration (s): 0.42 | learning rate: 6.205E-05 | global batch size: 256 | lm loss: 2.977344E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.221 | TFLOPs: 31.75 | +7: iteration 9780/ 14324 | consumed samples: 2503680 | consumed tokens: 5127536640 | elapsed time per iteration (s): 0.43 | learning rate: 6.188E-05 | global batch size: 256 | lm loss: 2.970011E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.473 | TFLOPs: 31.56 | +7: iteration 9790/ 14324 | consumed samples: 2506240 | consumed tokens: 5132779520 | elapsed time per iteration (s): 0.42 | learning rate: 6.171E-05 | global batch size: 256 | lm loss: 2.986938E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.856 | TFLOPs: 32.16 | +7: iteration 9800/ 14324 | consumed samples: 2508800 | consumed tokens: 5138022400 | elapsed time per iteration (s): 0.42 | learning rate: 6.154E-05 | global batch size: 256 | lm loss: 2.997107E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.608 | TFLOPs: 31.78 | +7: iteration 9810/ 14324 | consumed samples: 2511360 | consumed tokens: 5143265280 | elapsed time per iteration (s): 0.42 | learning rate: 6.138E-05 | global batch size: 256 | lm loss: 2.964766E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.019 | TFLOPs: 31.74 | +7: iteration 9820/ 14324 | consumed samples: 2513920 | consumed tokens: 5148508160 | elapsed time per iteration (s): 0.42 | learning rate: 6.121E-05 | global batch size: 256 | lm loss: 2.964380E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.663 | TFLOPs: 31.78 | +7: iteration 9830/ 14324 | consumed samples: 2516480 | consumed tokens: 5153751040 | elapsed time per iteration (s): 0.42 | learning rate: 6.104E-05 | global batch size: 256 | lm loss: 2.971513E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.463 | TFLOPs: 31.77 | +7: iteration 9840/ 14324 | consumed samples: 2519040 | consumed tokens: 5158993920 | elapsed time per iteration (s): 0.42 | learning rate: 6.087E-05 | global batch size: 256 | lm loss: 2.997450E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.217 | TFLOPs: 31.96 | +7: iteration 9850/ 14324 | consumed samples: 2521600 | consumed tokens: 5164236800 | elapsed time per iteration (s): 0.43 | learning rate: 6.071E-05 | global batch size: 256 | lm loss: 2.968197E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.546 | TFLOPs: 31.19 | +7: iteration 9860/ 14324 | consumed samples: 2524160 | consumed tokens: 5169479680 | elapsed time per iteration (s): 0.42 | learning rate: 6.054E-05 | global batch size: 256 | lm loss: 2.945776E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.191 | TFLOPs: 31.86 | +7: iteration 9870/ 14324 | consumed samples: 2526720 | consumed tokens: 5174722560 | elapsed time per iteration (s): 0.42 | learning rate: 6.037E-05 | global batch size: 256 | lm loss: 2.970087E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.485 | TFLOPs: 31.87 | +7: iteration 9880/ 14324 | consumed samples: 2529280 | consumed tokens: 5179965440 | elapsed time per iteration (s): 0.42 | learning rate: 6.021E-05 | global batch size: 256 | lm loss: 2.990600E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.102 | TFLOPs: 31.96 | +7: iteration 9890/ 14324 | consumed samples: 2531840 | consumed tokens: 5185208320 | elapsed time per iteration (s): 0.43 | learning rate: 6.004E-05 | global batch size: 256 | lm loss: 2.993665E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.616 | TFLOPs: 31.25 | +7: iteration 9900/ 14324 | consumed samples: 2534400 | consumed tokens: 5190451200 | elapsed time per iteration (s): 0.42 | learning rate: 5.988E-05 | global batch size: 256 | lm loss: 2.997473E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.468 | TFLOPs: 31.66 | +7: iteration 9910/ 14324 | consumed samples: 2536960 | consumed tokens: 5195694080 | elapsed time per iteration (s): 0.43 | learning rate: 5.971E-05 | global batch size: 256 | lm loss: 3.003090E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.245 | TFLOPs: 31.34 | +7: iteration 9920/ 14324 | consumed samples: 2539520 | consumed tokens: 5200936960 | elapsed time per iteration (s): 0.44 | learning rate: 5.955E-05 | global batch size: 256 | lm loss: 2.974053E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 585.509 | TFLOPs: 30.72 | +7: iteration 9930/ 14324 | consumed samples: 2542080 | consumed tokens: 5206179840 | elapsed time per iteration (s): 0.42 | learning rate: 5.938E-05 | global batch size: 256 | lm loss: 2.983067E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.806 | TFLOPs: 32.15 | +7: iteration 9940/ 14324 | consumed samples: 2544640 | consumed tokens: 5211422720 | elapsed time per iteration (s): 0.42 | learning rate: 5.922E-05 | global batch size: 256 | lm loss: 2.988001E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.408 | TFLOPs: 31.61 | +7: iteration 9950/ 14324 | consumed samples: 2547200 | consumed tokens: 5216665600 | elapsed time per iteration (s): 0.42 | learning rate: 5.905E-05 | global batch size: 256 | lm loss: 2.996903E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.322 | TFLOPs: 31.71 | +7: iteration 9960/ 14324 | consumed samples: 2549760 | consumed tokens: 5221908480 | elapsed time per iteration (s): 0.45 | learning rate: 5.889E-05 | global batch size: 256 | lm loss: 2.985364E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 575.206 | TFLOPs: 30.18 | +7: iteration 9970/ 14324 | consumed samples: 2552320 | consumed tokens: 5227151360 | elapsed time per iteration (s): 0.42 | learning rate: 5.872E-05 | global batch size: 256 | lm loss: 2.974518E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.733 | TFLOPs: 32.15 | +7: iteration 9980/ 14324 | consumed samples: 2554880 | consumed tokens: 5232394240 | elapsed time per iteration (s): 0.42 | learning rate: 5.856E-05 | global batch size: 256 | lm loss: 2.953467E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.485 | TFLOPs: 31.66 | +7: iteration 9990/ 14324 | consumed samples: 2557440 | consumed tokens: 5237637120 | elapsed time per iteration (s): 0.42 | learning rate: 5.840E-05 | global batch size: 256 | lm loss: 2.987188E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.807 | TFLOPs: 32.00 | +0: [2022-11-29 23:11:52,519] [INFO] [logging.py:68:log_dist] [Rank 0] step=10000, skipped=0, lr=[5.823320272718836e-05, 5.823320272718836e-05, 5.823320272718836e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 10000/ 14324 | consumed samples: 2560000 | consumed tokens: 5242880000 | elapsed time per iteration (s): 0.42 | learning rate: 5.823E-05 | global batch size: 256 | lm loss: 2.990233E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.331 | TFLOPs: 31.81 | +0: steps: 10000 loss: 2.9922 iter time (s): 0.424 samples/sec: 603.505 +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 10000 | lm loss value: 2.883906E+00 | lm loss PPL: 1.788400E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 10000 to checkpoints_220moscar +0: [2022-11-29 23:11:52,680] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step10000 is begin to save! +0: [2022-11-29 23:11:52,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/layer_01-model_00-model_states.pt... +0: [2022-11-29 23:11:52,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/layer_01-model_00-model_states.pt. +0: [2022-11-29 23:11:52,784] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/layer_03-model_00-model_states.pt... +0: [2022-11-29 23:11:52,806] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/layer_03-model_00-model_states.pt. +0: [2022-11-29 23:11:52,806] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/layer_04-model_00-model_states.pt... +0: [2022-11-29 23:11:52,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/layer_04-model_00-model_states.pt. +0: [2022-11-29 23:11:52,830] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/layer_05-model_00-model_states.pt... +0: [2022-11-29 23:11:52,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/layer_05-model_00-model_states.pt. +0: [2022-11-29 23:11:52,853] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/layer_06-model_00-model_states.pt... +0: [2022-11-29 23:11:52,877] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/layer_06-model_00-model_states.pt. +0: [2022-11-29 23:11:52,877] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/layer_07-model_00-model_states.pt... +0: [2022-11-29 23:11:52,900] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/layer_07-model_00-model_states.pt. +0: [2022-11-29 23:11:52,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/layer_08-model_00-model_states.pt... +0: [2022-11-29 23:11:52,924] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/layer_08-model_00-model_states.pt. +0: [2022-11-29 23:11:52,924] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/layer_09-model_00-model_states.pt... +0: [2022-11-29 23:11:52,948] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/layer_09-model_00-model_states.pt. +0: [2022-11-29 23:11:52,948] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/layer_10-model_00-model_states.pt... +0: [2022-11-29 23:11:52,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/layer_10-model_00-model_states.pt. +0: [2022-11-29 23:11:52,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/layer_11-model_00-model_states.pt... +0: [2022-11-29 23:11:52,995] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/layer_11-model_00-model_states.pt. +0: [2022-11-29 23:11:52,995] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/layer_12-model_00-model_states.pt... +0: [2022-11-29 23:11:53,018] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/layer_12-model_00-model_states.pt. +0: [2022-11-29 23:11:53,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/layer_13-model_00-model_states.pt... +0: [2022-11-29 23:11:53,040] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/layer_13-model_00-model_states.pt. +0: [2022-11-29 23:11:53,041] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/layer_14-model_00-model_states.pt... +0: [2022-11-29 23:11:53,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/layer_14-model_00-model_states.pt. +0: [2022-11-29 23:11:53,064] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/layer_15-model_00-model_states.pt... +0: [2022-11-29 23:11:53,087] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/layer_15-model_00-model_states.pt. +0: [2022-11-29 23:11:53,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/layer_16-model_00-model_states.pt... +0: [2022-11-29 23:11:53,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/layer_16-model_00-model_states.pt. +0: [2022-11-29 23:11:53,111] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/layer_17-model_00-model_states.pt... +0: [2022-11-29 23:11:53,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/layer_17-model_00-model_states.pt. +0: [2022-11-29 23:11:53,135] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/layer_18-model_00-model_states.pt... +0: [2022-11-29 23:11:53,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/layer_18-model_00-model_states.pt. +0: [2022-11-29 23:11:53,157] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/layer_19-model_00-model_states.pt... +0: [2022-11-29 23:11:53,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/layer_19-model_00-model_states.pt. +0: [2022-11-29 23:11:53,180] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/layer_20-model_00-model_states.pt... +0: [2022-11-29 23:11:53,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/layer_20-model_00-model_states.pt. +0: [2022-11-29 23:11:53,203] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/layer_22-model_00-model_states.pt... +0: [2022-11-29 23:11:53,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/layer_22-model_00-model_states.pt. +0: [2022-11-29 23:11:53,208] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_220moscar/global_step10000/mp_rank_00_model_states.pt +0: [2022-11-29 23:11:53,208] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/mp_rank_00_model_states.pt... +0: [2022-11-29 23:11:53,210] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/mp_rank_00_model_states.pt. +0: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:11:53,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:11:53,276] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:11:53,276] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 23:11:53,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 23:11:53,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:11:53,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 23:11:53,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 23:11:53,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:11:53,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 23:11:53,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 23:11:53,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:11:53,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 23:11:53,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 23:11:53,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:11:53,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:11:53,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 23:11:53,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 23:11:53,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:11:53,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +5: [2022-11-29 23:11:53,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +4: [2022-11-29 23:11:53,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 23:11:53,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 23:11:53,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:11:53,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:11:53,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 23:11:53,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 23:11:53,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:11:53,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +0: [2022-11-29 23:11:53,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 23:11:53,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 23:11:53,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 23:11:53,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:11:53,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 23:11:53,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 23:11:53,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:11:53,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:11:53,280] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 23:11:53,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 23:11:53,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:11:53,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 23:11:53,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 23:11:53,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:11:53,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 23:11:53,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 23:11:53,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:11:53,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 23:11:53,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 23:11:53,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:11:53,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 23:11:53,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 23:11:53,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:11:53,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 23:11:53,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 23:11:53,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:11:53,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 23:11:53,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 23:11:53,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:11:53,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 23:11:53,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 23:11:53,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:11:53,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:11:53,284] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +7: [2022-11-29 23:11:53,284] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +1: [2022-11-29 23:11:53,284] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 23:11:53,284] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 23:11:53,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:11:53,285] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 23:11:53,285] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 23:11:53,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:11:53,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 23:11:53,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 23:11:53,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:11:53,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 23:11:53,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 23:11:53,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:11:53,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:11:53,287] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 23:11:53,287] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 23:11:53,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 23:11:53,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 23:11:53,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 23:11:53,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 23:11:53,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:11:53,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:11:53,280] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 23:11:53,280] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 23:11:53,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:11:53,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 23:11:53,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 23:11:53,280] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 23:11:53,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 23:11:53,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:11:53,280] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 23:11:53,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 23:11:53,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:11:53,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 23:11:53,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 23:11:53,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:11:53,285] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 23:11:53,285] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 23:11:53,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:11:53,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 23:11:53,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 23:11:53,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:11:53,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:11:53,287] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 23:11:53,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 23:11:53,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:11:53,287] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 23:11:53,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 23:11:53,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:11:53,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 23:11:53,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 23:11:53,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:11:53,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 23:11:53,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 23:11:53,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:11:53,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 23:11:53,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 23:11:53,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:11:53,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 23:11:53,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 23:11:53,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:11:53,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 23:11:53,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 23:11:53,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:11:53,284] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 23:11:53,284] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 23:11:53,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:11:53,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 23:11:53,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 23:11:53,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:11:53,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 23:11:53,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 23:11:53,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:11:53,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 23:11:53,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 23:11:53,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:11:53,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:11:53,294] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 23:11:53,294] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 23:11:53,294] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 23:11:53,294] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 23:11:53,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:11:53,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:11:53,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:11:53,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:11:53,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:11:53,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:11:53,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:11:53,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:11:53,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 23:11:53,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 23:11:53,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 23:11:53,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 23:11:53,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 23:11:53,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 23:11:53,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 23:11:53,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 23:11:53,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 23:11:53,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 23:11:53,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 23:11:53,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 23:11:53,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 23:11:53,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 23:11:53,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 23:11:53,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 23:11:53,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:11:53,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:11:53,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:11:53,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:11:53,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:11:53,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:11:53,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:11:53,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:11:53,322] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 23:11:53,322] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 23:11:53,322] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 23:11:53,322] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 23:11:53,322] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 23:11:53,322] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 23:11:53,322] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 23:11:53,322] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 23:11:53,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 23:11:53,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 23:11:53,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 23:11:53,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 23:11:53,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 23:11:53,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 23:11:53,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 23:11:53,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 23:11:53,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 23:11:53,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: successfully saved checkpoint at iteration 10000 to checkpoints_220moscar +7: time (ms) | save-checkpoint: 668.15 +7: iteration 10010/ 14324 | consumed samples: 2562560 | consumed tokens: 5248122880 | elapsed time per iteration (s): 0.50 | learning rate: 5.807E-05 | global batch size: 256 | lm loss: 3.004501E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 508.667 | TFLOPs: 26.69 | +7: iteration 10020/ 14324 | consumed samples: 2565120 | consumed tokens: 5253365760 | elapsed time per iteration (s): 0.42 | learning rate: 5.791E-05 | global batch size: 256 | lm loss: 2.956229E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.119 | TFLOPs: 31.64 | +7: iteration 10030/ 14324 | consumed samples: 2567680 | consumed tokens: 5258608640 | elapsed time per iteration (s): 0.42 | learning rate: 5.775E-05 | global batch size: 256 | lm loss: 2.988751E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.148 | TFLOPs: 32.12 | +7: iteration 10040/ 14324 | consumed samples: 2570240 | consumed tokens: 5263851520 | elapsed time per iteration (s): 0.43 | learning rate: 5.758E-05 | global batch size: 256 | lm loss: 3.002833E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.483 | TFLOPs: 31.51 | +7: iteration 10050/ 14324 | consumed samples: 2572800 | consumed tokens: 5269094400 | elapsed time per iteration (s): 0.42 | learning rate: 5.742E-05 | global batch size: 256 | lm loss: 2.966657E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.598 | TFLOPs: 31.77 | +7: iteration 10060/ 14324 | consumed samples: 2575360 | consumed tokens: 5274337280 | elapsed time per iteration (s): 0.42 | learning rate: 5.726E-05 | global batch size: 256 | lm loss: 2.995886E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.524 | TFLOPs: 31.93 | +7: iteration 10070/ 14324 | consumed samples: 2577920 | consumed tokens: 5279580160 | elapsed time per iteration (s): 0.42 | learning rate: 5.710E-05 | global batch size: 256 | lm loss: 2.983446E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.034 | TFLOPs: 31.90 | +7: iteration 10080/ 14324 | consumed samples: 2580480 | consumed tokens: 5284823040 | elapsed time per iteration (s): 0.42 | learning rate: 5.694E-05 | global batch size: 256 | lm loss: 2.968686E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.897 | TFLOPs: 31.95 | +7: iteration 10090/ 14324 | consumed samples: 2583040 | consumed tokens: 5290065920 | elapsed time per iteration (s): 0.42 | learning rate: 5.678E-05 | global batch size: 256 | lm loss: 2.968668E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.970 | TFLOPs: 31.90 | +7: iteration 10100/ 14324 | consumed samples: 2585600 | consumed tokens: 5295308800 | elapsed time per iteration (s): 0.43 | learning rate: 5.662E-05 | global batch size: 256 | lm loss: 2.946566E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.102 | TFLOPs: 31.38 | +7: iteration 10110/ 14324 | consumed samples: 2588160 | consumed tokens: 5300551680 | elapsed time per iteration (s): 0.44 | learning rate: 5.645E-05 | global batch size: 256 | lm loss: 2.982031E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 579.864 | TFLOPs: 30.42 | +7: iteration 10120/ 14324 | consumed samples: 2590720 | consumed tokens: 5305794560 | elapsed time per iteration (s): 0.45 | learning rate: 5.629E-05 | global batch size: 256 | lm loss: 2.978062E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 563.816 | TFLOPs: 29.58 | +7: iteration 10130/ 14324 | consumed samples: 2593280 | consumed tokens: 5311037440 | elapsed time per iteration (s): 0.42 | learning rate: 5.613E-05 | global batch size: 256 | lm loss: 2.968175E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.184 | TFLOPs: 32.12 | +7: iteration 10140/ 14324 | consumed samples: 2595840 | consumed tokens: 5316280320 | elapsed time per iteration (s): 0.42 | learning rate: 5.598E-05 | global batch size: 256 | lm loss: 2.985434E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.815 | TFLOPs: 31.79 | +7: iteration 10150/ 14324 | consumed samples: 2598400 | consumed tokens: 5321523200 | elapsed time per iteration (s): 0.42 | learning rate: 5.582E-05 | global batch size: 256 | lm loss: 2.992184E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.546 | TFLOPs: 32.09 | +7: iteration 10160/ 14324 | consumed samples: 2600960 | consumed tokens: 5326766080 | elapsed time per iteration (s): 0.42 | learning rate: 5.566E-05 | global batch size: 256 | lm loss: 3.017445E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.439 | TFLOPs: 32.13 | +7: iteration 10170/ 14324 | consumed samples: 2603520 | consumed tokens: 5332008960 | elapsed time per iteration (s): 0.43 | learning rate: 5.550E-05 | global batch size: 256 | lm loss: 3.000475E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.156 | TFLOPs: 31.49 | +7: iteration 10180/ 14324 | consumed samples: 2606080 | consumed tokens: 5337251840 | elapsed time per iteration (s): 0.42 | learning rate: 5.534E-05 | global batch size: 256 | lm loss: 2.964194E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.548 | TFLOPs: 31.88 | +7: iteration 10190/ 14324 | consumed samples: 2608640 | consumed tokens: 5342494720 | elapsed time per iteration (s): 0.42 | learning rate: 5.518E-05 | global batch size: 256 | lm loss: 2.977621E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.868 | TFLOPs: 31.74 | +7: iteration 10200/ 14324 | consumed samples: 2611200 | consumed tokens: 5347737600 | elapsed time per iteration (s): 0.42 | learning rate: 5.502E-05 | global batch size: 256 | lm loss: 2.978911E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.085 | TFLOPs: 31.96 | +7: iteration 10210/ 14324 | consumed samples: 2613760 | consumed tokens: 5352980480 | elapsed time per iteration (s): 0.42 | learning rate: 5.487E-05 | global batch size: 256 | lm loss: 2.955081E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.225 | TFLOPs: 31.70 | +7: iteration 10220/ 14324 | consumed samples: 2616320 | consumed tokens: 5358223360 | elapsed time per iteration (s): 0.42 | learning rate: 5.471E-05 | global batch size: 256 | lm loss: 2.972689E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.093 | TFLOPs: 32.01 | +7: iteration 10230/ 14324 | consumed samples: 2618880 | consumed tokens: 5363466240 | elapsed time per iteration (s): 0.42 | learning rate: 5.455E-05 | global batch size: 256 | lm loss: 2.989494E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 613.112 | TFLOPs: 32.17 | +7: iteration 10240/ 14324 | consumed samples: 2621440 | consumed tokens: 5368709120 | elapsed time per iteration (s): 0.42 | learning rate: 5.439E-05 | global batch size: 256 | lm loss: 2.980847E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.539 | TFLOPs: 31.93 | +7: iteration 10250/ 14324 | consumed samples: 2624000 | consumed tokens: 5373952000 | elapsed time per iteration (s): 0.43 | learning rate: 5.424E-05 | global batch size: 256 | lm loss: 2.973306E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.716 | TFLOPs: 31.52 | +7: iteration 10260/ 14324 | consumed samples: 2626560 | consumed tokens: 5379194880 | elapsed time per iteration (s): 0.42 | learning rate: 5.408E-05 | global batch size: 256 | lm loss: 2.965532E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.936 | TFLOPs: 31.84 | +7: iteration 10270/ 14324 | consumed samples: 2629120 | consumed tokens: 5384437760 | elapsed time per iteration (s): 0.44 | learning rate: 5.392E-05 | global batch size: 256 | lm loss: 2.974616E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 587.533 | TFLOPs: 30.83 | +7: iteration 10280/ 14324 | consumed samples: 2631680 | consumed tokens: 5389680640 | elapsed time per iteration (s): 0.42 | learning rate: 5.377E-05 | global batch size: 256 | lm loss: 2.952071E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.605 | TFLOPs: 32.14 | +7: iteration 10290/ 14324 | consumed samples: 2634240 | consumed tokens: 5394923520 | elapsed time per iteration (s): 0.42 | learning rate: 5.361E-05 | global batch size: 256 | lm loss: 2.956335E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.585 | TFLOPs: 32.04 | +7: iteration 10300/ 14324 | consumed samples: 2636800 | consumed tokens: 5400166400 | elapsed time per iteration (s): 0.42 | learning rate: 5.346E-05 | global batch size: 256 | lm loss: 2.962662E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.831 | TFLOPs: 31.89 | +7: iteration 10310/ 14324 | consumed samples: 2639360 | consumed tokens: 5405409280 | elapsed time per iteration (s): 0.44 | learning rate: 5.330E-05 | global batch size: 256 | lm loss: 2.975687E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 579.363 | TFLOPs: 30.40 | +7: iteration 10320/ 14324 | consumed samples: 2641920 | consumed tokens: 5410652160 | elapsed time per iteration (s): 0.42 | learning rate: 5.315E-05 | global batch size: 256 | lm loss: 3.009303E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.675 | TFLOPs: 32.04 | +7: iteration 10330/ 14324 | consumed samples: 2644480 | consumed tokens: 5415895040 | elapsed time per iteration (s): 0.43 | learning rate: 5.299E-05 | global batch size: 256 | lm loss: 2.980803E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.986 | TFLOPs: 31.27 | +7: iteration 10340/ 14324 | consumed samples: 2647040 | consumed tokens: 5421137920 | elapsed time per iteration (s): 0.42 | learning rate: 5.284E-05 | global batch size: 256 | lm loss: 2.984498E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.398 | TFLOPs: 31.87 | +7: iteration 10350/ 14324 | consumed samples: 2649600 | consumed tokens: 5426380800 | elapsed time per iteration (s): 0.43 | learning rate: 5.269E-05 | global batch size: 256 | lm loss: 2.991060E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.216 | TFLOPs: 31.44 | +7: iteration 10360/ 14324 | consumed samples: 2652160 | consumed tokens: 5431623680 | elapsed time per iteration (s): 0.42 | learning rate: 5.253E-05 | global batch size: 256 | lm loss: 2.988901E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.545 | TFLOPs: 31.67 | +7: iteration 10370/ 14324 | consumed samples: 2654720 | consumed tokens: 5436866560 | elapsed time per iteration (s): 0.44 | learning rate: 5.238E-05 | global batch size: 256 | lm loss: 2.975112E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 588.467 | TFLOPs: 30.88 | +7: iteration 10380/ 14324 | consumed samples: 2657280 | consumed tokens: 5442109440 | elapsed time per iteration (s): 0.43 | learning rate: 5.223E-05 | global batch size: 256 | lm loss: 2.960938E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.134 | TFLOPs: 31.17 | +7: iteration 10390/ 14324 | consumed samples: 2659840 | consumed tokens: 5447352320 | elapsed time per iteration (s): 0.42 | learning rate: 5.207E-05 | global batch size: 256 | lm loss: 2.999334E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.870 | TFLOPs: 31.68 | +7: iteration 10400/ 14324 | consumed samples: 2662400 | consumed tokens: 5452595200 | elapsed time per iteration (s): 0.43 | learning rate: 5.192E-05 | global batch size: 256 | lm loss: 2.970548E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.234 | TFLOPs: 31.55 | +7: iteration 10410/ 14324 | consumed samples: 2664960 | consumed tokens: 5457838080 | elapsed time per iteration (s): 0.42 | learning rate: 5.177E-05 | global batch size: 256 | lm loss: 2.986160E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.882 | TFLOPs: 32.16 | +7: iteration 10420/ 14324 | consumed samples: 2667520 | consumed tokens: 5463080960 | elapsed time per iteration (s): 0.42 | learning rate: 5.162E-05 | global batch size: 256 | lm loss: 2.970215E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.315 | TFLOPs: 31.86 | +7: iteration 10430/ 14324 | consumed samples: 2670080 | consumed tokens: 5468323840 | elapsed time per iteration (s): 0.42 | learning rate: 5.147E-05 | global batch size: 256 | lm loss: 2.949253E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.729 | TFLOPs: 31.73 | +7: iteration 10440/ 14324 | consumed samples: 2672640 | consumed tokens: 5473566720 | elapsed time per iteration (s): 0.43 | learning rate: 5.131E-05 | global batch size: 256 | lm loss: 2.986128E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.951 | TFLOPs: 31.58 | +7: iteration 10450/ 14324 | consumed samples: 2675200 | consumed tokens: 5478809600 | elapsed time per iteration (s): 0.43 | learning rate: 5.116E-05 | global batch size: 256 | lm loss: 2.951256E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.301 | TFLOPs: 31.60 | +7: iteration 10460/ 14324 | consumed samples: 2677760 | consumed tokens: 5484052480 | elapsed time per iteration (s): 0.42 | learning rate: 5.101E-05 | global batch size: 256 | lm loss: 2.980893E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.014 | TFLOPs: 32.06 | +7: iteration 10470/ 14324 | consumed samples: 2680320 | consumed tokens: 5489295360 | elapsed time per iteration (s): 0.42 | learning rate: 5.086E-05 | global batch size: 256 | lm loss: 2.948101E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.322 | TFLOPs: 32.13 | +7: iteration 10480/ 14324 | consumed samples: 2682880 | consumed tokens: 5494538240 | elapsed time per iteration (s): 0.42 | learning rate: 5.071E-05 | global batch size: 256 | lm loss: 2.951611E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.069 | TFLOPs: 32.01 | +7: iteration 10490/ 14324 | consumed samples: 2685440 | consumed tokens: 5499781120 | elapsed time per iteration (s): 0.42 | learning rate: 5.056E-05 | global batch size: 256 | lm loss: 2.993694E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.588 | TFLOPs: 31.67 | +7: iteration 10500/ 14324 | consumed samples: 2688000 | consumed tokens: 5505024000 | elapsed time per iteration (s): 0.42 | learning rate: 5.041E-05 | global batch size: 256 | lm loss: 2.976048E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.620 | TFLOPs: 31.83 | +7: iteration 10510/ 14324 | consumed samples: 2690560 | consumed tokens: 5510266880 | elapsed time per iteration (s): 0.43 | learning rate: 5.026E-05 | global batch size: 256 | lm loss: 2.977700E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.117 | TFLOPs: 31.49 | +7: iteration 10520/ 14324 | consumed samples: 2693120 | consumed tokens: 5515509760 | elapsed time per iteration (s): 0.42 | learning rate: 5.011E-05 | global batch size: 256 | lm loss: 2.965367E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.783 | TFLOPs: 31.63 | +7: iteration 10530/ 14324 | consumed samples: 2695680 | consumed tokens: 5520752640 | elapsed time per iteration (s): 0.42 | learning rate: 4.997E-05 | global batch size: 256 | lm loss: 2.955046E+00 | grad norm: 0.431 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.613 | TFLOPs: 31.93 | +7: iteration 10540/ 14324 | consumed samples: 2698240 | consumed tokens: 5525995520 | elapsed time per iteration (s): 0.43 | learning rate: 4.982E-05 | global batch size: 256 | lm loss: 2.934086E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.006 | TFLOPs: 31.53 | +7: iteration 10550/ 14324 | consumed samples: 2700800 | consumed tokens: 5531238400 | elapsed time per iteration (s): 0.42 | learning rate: 4.967E-05 | global batch size: 256 | lm loss: 2.967671E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.503 | TFLOPs: 31.87 | +7: iteration 10560/ 14324 | consumed samples: 2703360 | consumed tokens: 5536481280 | elapsed time per iteration (s): 0.42 | learning rate: 4.952E-05 | global batch size: 256 | lm loss: 2.916680E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.686 | TFLOPs: 31.88 | +7: iteration 10570/ 14324 | consumed samples: 2705920 | consumed tokens: 5541724160 | elapsed time per iteration (s): 0.42 | learning rate: 4.937E-05 | global batch size: 256 | lm loss: 2.987196E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.934 | TFLOPs: 31.90 | +7: iteration 10580/ 14324 | consumed samples: 2708480 | consumed tokens: 5546967040 | elapsed time per iteration (s): 0.43 | learning rate: 4.923E-05 | global batch size: 256 | lm loss: 3.001905E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.516 | TFLOPs: 31.51 | +7: iteration 10590/ 14324 | consumed samples: 2711040 | consumed tokens: 5552209920 | elapsed time per iteration (s): 0.42 | learning rate: 4.908E-05 | global batch size: 256 | lm loss: 2.950205E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.719 | TFLOPs: 31.68 | +7: iteration 10600/ 14324 | consumed samples: 2713600 | consumed tokens: 5557452800 | elapsed time per iteration (s): 0.42 | learning rate: 4.893E-05 | global batch size: 256 | lm loss: 3.000275E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.573 | TFLOPs: 31.72 | +7: iteration 10610/ 14324 | consumed samples: 2716160 | consumed tokens: 5562695680 | elapsed time per iteration (s): 0.42 | learning rate: 4.879E-05 | global batch size: 256 | lm loss: 2.981966E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.249 | TFLOPs: 31.70 | +7: iteration 10620/ 14324 | consumed samples: 2718720 | consumed tokens: 5567938560 | elapsed time per iteration (s): 0.42 | learning rate: 4.864E-05 | global batch size: 256 | lm loss: 2.944401E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.515 | TFLOPs: 31.88 | +7: iteration 10630/ 14324 | consumed samples: 2721280 | consumed tokens: 5573181440 | elapsed time per iteration (s): 0.43 | learning rate: 4.849E-05 | global batch size: 256 | lm loss: 2.951977E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 590.269 | TFLOPs: 30.97 | +7: iteration 10640/ 14324 | consumed samples: 2723840 | consumed tokens: 5578424320 | elapsed time per iteration (s): 0.42 | learning rate: 4.835E-05 | global batch size: 256 | lm loss: 2.957825E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.545 | TFLOPs: 31.72 | +7: iteration 10650/ 14324 | consumed samples: 2726400 | consumed tokens: 5583667200 | elapsed time per iteration (s): 0.42 | learning rate: 4.820E-05 | global batch size: 256 | lm loss: 2.961949E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.856 | TFLOPs: 32.00 | +7: iteration 10660/ 14324 | consumed samples: 2728960 | consumed tokens: 5588910080 | elapsed time per iteration (s): 0.43 | learning rate: 4.806E-05 | global batch size: 256 | lm loss: 2.985025E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.880 | TFLOPs: 31.05 | +7: iteration 10670/ 14324 | consumed samples: 2731520 | consumed tokens: 5594152960 | elapsed time per iteration (s): 0.43 | learning rate: 4.791E-05 | global batch size: 256 | lm loss: 2.951670E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.530 | TFLOPs: 31.56 | +7: iteration 10680/ 14324 | consumed samples: 2734080 | consumed tokens: 5599395840 | elapsed time per iteration (s): 0.42 | learning rate: 4.777E-05 | global batch size: 256 | lm loss: 2.973675E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.913 | TFLOPs: 32.16 | +7: iteration 10690/ 14324 | consumed samples: 2736640 | consumed tokens: 5604638720 | elapsed time per iteration (s): 0.42 | learning rate: 4.763E-05 | global batch size: 256 | lm loss: 2.954679E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.737 | TFLOPs: 31.73 | +7: iteration 10700/ 14324 | consumed samples: 2739200 | consumed tokens: 5609881600 | elapsed time per iteration (s): 0.42 | learning rate: 4.748E-05 | global batch size: 256 | lm loss: 2.986087E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.608 | TFLOPs: 31.83 | +7: iteration 10710/ 14324 | consumed samples: 2741760 | consumed tokens: 5615124480 | elapsed time per iteration (s): 0.42 | learning rate: 4.734E-05 | global batch size: 256 | lm loss: 2.973630E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.609 | TFLOPs: 31.93 | +7: iteration 10720/ 14324 | consumed samples: 2744320 | consumed tokens: 5620367360 | elapsed time per iteration (s): 0.42 | learning rate: 4.720E-05 | global batch size: 256 | lm loss: 3.006094E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.624 | TFLOPs: 31.78 | +7: iteration 10730/ 14324 | consumed samples: 2746880 | consumed tokens: 5625610240 | elapsed time per iteration (s): 0.42 | learning rate: 4.705E-05 | global batch size: 256 | lm loss: 2.972488E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.851 | TFLOPs: 32.16 | +7: iteration 10740/ 14324 | consumed samples: 2749440 | consumed tokens: 5630853120 | elapsed time per iteration (s): 0.42 | learning rate: 4.691E-05 | global batch size: 256 | lm loss: 2.941165E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.491 | TFLOPs: 32.08 | +7: iteration 10750/ 14324 | consumed samples: 2752000 | consumed tokens: 5636096000 | elapsed time per iteration (s): 0.42 | learning rate: 4.677E-05 | global batch size: 256 | lm loss: 2.971814E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.437 | TFLOPs: 31.71 | +7: iteration 10760/ 14324 | consumed samples: 2754560 | consumed tokens: 5641338880 | elapsed time per iteration (s): 0.42 | learning rate: 4.663E-05 | global batch size: 256 | lm loss: 2.955273E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.905 | TFLOPs: 32.11 | +7: iteration 10770/ 14324 | consumed samples: 2757120 | consumed tokens: 5646581760 | elapsed time per iteration (s): 0.42 | learning rate: 4.649E-05 | global batch size: 256 | lm loss: 2.963508E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.118 | TFLOPs: 31.96 | +7: iteration 10780/ 14324 | consumed samples: 2759680 | consumed tokens: 5651824640 | elapsed time per iteration (s): 0.43 | learning rate: 4.635E-05 | global batch size: 256 | lm loss: 2.992453E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.824 | TFLOPs: 31.42 | +7: iteration 10790/ 14324 | consumed samples: 2762240 | consumed tokens: 5657067520 | elapsed time per iteration (s): 0.42 | learning rate: 4.620E-05 | global batch size: 256 | lm loss: 2.938925E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.141 | TFLOPs: 32.12 | +7: iteration 10800/ 14324 | consumed samples: 2764800 | consumed tokens: 5662310400 | elapsed time per iteration (s): 0.42 | learning rate: 4.606E-05 | global batch size: 256 | lm loss: 2.982173E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.487 | TFLOPs: 32.14 | +7: iteration 10810/ 14324 | consumed samples: 2767360 | consumed tokens: 5667553280 | elapsed time per iteration (s): 0.42 | learning rate: 4.592E-05 | global batch size: 256 | lm loss: 2.941224E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.664 | TFLOPs: 31.88 | +7: iteration 10820/ 14324 | consumed samples: 2769920 | consumed tokens: 5672796160 | elapsed time per iteration (s): 0.42 | learning rate: 4.578E-05 | global batch size: 256 | lm loss: 2.963996E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.487 | TFLOPs: 31.87 | +7: iteration 10830/ 14324 | consumed samples: 2772480 | consumed tokens: 5678039040 | elapsed time per iteration (s): 0.42 | learning rate: 4.564E-05 | global batch size: 256 | lm loss: 2.965964E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.454 | TFLOPs: 31.98 | +7: iteration 10840/ 14324 | consumed samples: 2775040 | consumed tokens: 5683281920 | elapsed time per iteration (s): 0.43 | learning rate: 4.551E-05 | global batch size: 256 | lm loss: 2.954231E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.301 | TFLOPs: 31.29 | +7: iteration 10850/ 14324 | consumed samples: 2777600 | consumed tokens: 5688524800 | elapsed time per iteration (s): 0.42 | learning rate: 4.537E-05 | global batch size: 256 | lm loss: 2.981075E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.530 | TFLOPs: 31.93 | +7: iteration 10860/ 14324 | consumed samples: 2780160 | consumed tokens: 5693767680 | elapsed time per iteration (s): 0.42 | learning rate: 4.523E-05 | global batch size: 256 | lm loss: 2.995726E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.978 | TFLOPs: 31.74 | +7: iteration 10870/ 14324 | consumed samples: 2782720 | consumed tokens: 5699010560 | elapsed time per iteration (s): 0.43 | learning rate: 4.509E-05 | global batch size: 256 | lm loss: 2.996622E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.114 | TFLOPs: 31.28 | +7: iteration 10880/ 14324 | consumed samples: 2785280 | consumed tokens: 5704253440 | elapsed time per iteration (s): 0.42 | learning rate: 4.495E-05 | global batch size: 256 | lm loss: 2.945098E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.133 | TFLOPs: 31.91 | +7: iteration 10890/ 14324 | consumed samples: 2787840 | consumed tokens: 5709496320 | elapsed time per iteration (s): 0.42 | learning rate: 4.481E-05 | global batch size: 256 | lm loss: 2.941568E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.402 | TFLOPs: 31.76 | +7: iteration 10900/ 14324 | consumed samples: 2790400 | consumed tokens: 5714739200 | elapsed time per iteration (s): 0.42 | learning rate: 4.468E-05 | global batch size: 256 | lm loss: 2.958677E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.958 | TFLOPs: 32.16 | +7: iteration 10910/ 14324 | consumed samples: 2792960 | consumed tokens: 5719982080 | elapsed time per iteration (s): 0.42 | learning rate: 4.454E-05 | global batch size: 256 | lm loss: 2.952553E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.306 | TFLOPs: 31.76 | +7: iteration 10920/ 14324 | consumed samples: 2795520 | consumed tokens: 5725224960 | elapsed time per iteration (s): 0.42 | learning rate: 4.440E-05 | global batch size: 256 | lm loss: 2.968164E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.355 | TFLOPs: 32.13 | +7: iteration 10930/ 14324 | consumed samples: 2798080 | consumed tokens: 5730467840 | elapsed time per iteration (s): 0.43 | learning rate: 4.427E-05 | global batch size: 256 | lm loss: 2.970490E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 590.259 | TFLOPs: 30.97 | +7: iteration 10940/ 14324 | consumed samples: 2800640 | consumed tokens: 5735710720 | elapsed time per iteration (s): 0.42 | learning rate: 4.413E-05 | global batch size: 256 | lm loss: 2.930047E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.067 | TFLOPs: 31.96 | +7: iteration 10950/ 14324 | consumed samples: 2803200 | consumed tokens: 5740953600 | elapsed time per iteration (s): 0.43 | learning rate: 4.400E-05 | global batch size: 256 | lm loss: 2.971302E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.914 | TFLOPs: 31.48 | +7: iteration 10960/ 14324 | consumed samples: 2805760 | consumed tokens: 5746196480 | elapsed time per iteration (s): 0.42 | learning rate: 4.386E-05 | global batch size: 256 | lm loss: 2.948804E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.693 | TFLOPs: 32.15 | +7: iteration 10970/ 14324 | consumed samples: 2808320 | consumed tokens: 5751439360 | elapsed time per iteration (s): 0.43 | learning rate: 4.372E-05 | global batch size: 256 | lm loss: 2.974209E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.466 | TFLOPs: 31.56 | +7: iteration 10980/ 14324 | consumed samples: 2810880 | consumed tokens: 5756682240 | elapsed time per iteration (s): 0.44 | learning rate: 4.359E-05 | global batch size: 256 | lm loss: 2.971346E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 581.822 | TFLOPs: 30.53 | +7: iteration 10990/ 14324 | consumed samples: 2813440 | consumed tokens: 5761925120 | elapsed time per iteration (s): 0.42 | learning rate: 4.346E-05 | global batch size: 256 | lm loss: 2.951764E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.542 | TFLOPs: 32.09 | +7: iteration 11000/ 14324 | consumed samples: 2816000 | consumed tokens: 5767168000 | elapsed time per iteration (s): 0.42 | learning rate: 4.332E-05 | global batch size: 256 | lm loss: 2.953627E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.566 | TFLOPs: 31.77 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 11000 | lm loss value: 2.891453E+00 | lm loss PPL: 1.801946E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 11000 to checkpoints_220moscar +0: [2022-11-29 23:18:57,138] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step11000 is begin to save! +0: [2022-11-29 23:18:57,142] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/layer_01-model_00-model_states.pt... +0: [2022-11-29 23:18:57,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/layer_01-model_00-model_states.pt. +0: [2022-11-29 23:18:57,241] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/layer_03-model_00-model_states.pt... +0: [2022-11-29 23:18:57,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/layer_03-model_00-model_states.pt. +0: [2022-11-29 23:18:57,263] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/layer_04-model_00-model_states.pt... +0: [2022-11-29 23:18:57,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/layer_04-model_00-model_states.pt. +0: [2022-11-29 23:18:57,286] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/layer_05-model_00-model_states.pt... +0: [2022-11-29 23:18:57,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/layer_05-model_00-model_states.pt. +0: [2022-11-29 23:18:57,310] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/layer_06-model_00-model_states.pt... +0: [2022-11-29 23:18:57,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/layer_06-model_00-model_states.pt. +0: [2022-11-29 23:18:57,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/layer_07-model_00-model_states.pt... +0: [2022-11-29 23:18:57,359] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/layer_07-model_00-model_states.pt. +0: [2022-11-29 23:18:57,359] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/layer_08-model_00-model_states.pt... +0: [2022-11-29 23:18:57,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/layer_08-model_00-model_states.pt. +0: [2022-11-29 23:18:57,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/layer_09-model_00-model_states.pt... +0: [2022-11-29 23:18:57,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/layer_09-model_00-model_states.pt. +0: [2022-11-29 23:18:57,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/layer_10-model_00-model_states.pt... +0: [2022-11-29 23:18:57,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/layer_10-model_00-model_states.pt. +0: [2022-11-29 23:18:57,429] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/layer_11-model_00-model_states.pt... +0: [2022-11-29 23:18:57,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/layer_11-model_00-model_states.pt. +0: [2022-11-29 23:18:57,453] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/layer_12-model_00-model_states.pt... +0: [2022-11-29 23:18:57,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/layer_12-model_00-model_states.pt. +0: [2022-11-29 23:18:57,477] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/layer_13-model_00-model_states.pt... +0: [2022-11-29 23:18:57,500] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/layer_13-model_00-model_states.pt. +0: [2022-11-29 23:18:57,500] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/layer_14-model_00-model_states.pt... +0: [2022-11-29 23:18:57,523] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/layer_14-model_00-model_states.pt. +0: [2022-11-29 23:18:57,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/layer_15-model_00-model_states.pt... +0: [2022-11-29 23:18:57,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/layer_15-model_00-model_states.pt. +0: [2022-11-29 23:18:57,547] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/layer_16-model_00-model_states.pt... +0: [2022-11-29 23:18:57,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/layer_16-model_00-model_states.pt. +0: [2022-11-29 23:18:57,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/layer_17-model_00-model_states.pt... +0: [2022-11-29 23:18:57,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/layer_17-model_00-model_states.pt. +0: [2022-11-29 23:18:57,592] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/layer_18-model_00-model_states.pt... +0: [2022-11-29 23:18:57,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/layer_18-model_00-model_states.pt. +0: [2022-11-29 23:18:57,616] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/layer_19-model_00-model_states.pt... +0: [2022-11-29 23:18:57,639] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/layer_19-model_00-model_states.pt. +0: [2022-11-29 23:18:57,639] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/layer_20-model_00-model_states.pt... +0: [2022-11-29 23:18:57,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/layer_20-model_00-model_states.pt. +0: [2022-11-29 23:18:57,663] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/layer_22-model_00-model_states.pt... +0: [2022-11-29 23:18:57,666] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/layer_22-model_00-model_states.pt. +0: [2022-11-29 23:18:57,667] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_220moscar/global_step11000/mp_rank_00_model_states.pt +0: [2022-11-29 23:18:57,667] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/mp_rank_00_model_states.pt... +0: [2022-11-29 23:18:57,669] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/mp_rank_00_model_states.pt. +0: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:18:57,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:18:57,733] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:18:57,734] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:18:57,734] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:18:57,735] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 23:18:57,735] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 23:18:57,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:18:57,734] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 23:18:57,734] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 23:18:57,734] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:18:57,734] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 23:18:57,734] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 23:18:57,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:18:57,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 23:18:57,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 23:18:57,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:18:57,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 23:18:57,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 23:18:57,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:18:57,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 23:18:57,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 23:18:57,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:18:57,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +5: [2022-11-29 23:18:57,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:18:57,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +1: [2022-11-29 23:18:57,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 23:18:57,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 23:18:57,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:18:57,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 23:18:57,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 23:18:57,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:18:57,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:18:57,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 23:18:57,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 23:18:57,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:18:57,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 23:18:57,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 23:18:57,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:18:57,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:18:57,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:18:57,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:18:57,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 23:18:57,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:18:57,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:18:57,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:18:57,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 23:18:57,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 23:18:57,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 23:18:57,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 23:18:57,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 23:18:57,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 23:18:57,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 23:18:57,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 23:18:57,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 23:18:57,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 23:18:57,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 23:18:57,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 23:18:57,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 23:18:57,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:18:57,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 23:18:57,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 23:18:57,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:18:57,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:18:57,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:18:57,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:18:57,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:18:57,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 23:18:57,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:18:57,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 23:18:57,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 23:18:57,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 23:18:57,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 23:18:57,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 23:18:57,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 23:18:57,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 23:18:57,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 23:18:57,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 23:18:57,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 23:18:57,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 23:18:57,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:18:57,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 23:18:57,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 23:18:57,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 23:18:57,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 23:18:57,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:18:57,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 23:18:57,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 23:18:57,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:18:57,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 23:18:57,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 23:18:57,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:18:57,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 23:18:57,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 23:18:57,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:18:57,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:18:57,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:18:57,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:18:57,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 23:18:57,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 23:18:57,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:18:57,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:18:57,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:18:57,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 23:18:57,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 23:18:57,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 23:18:57,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 23:18:57,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 23:18:57,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 23:18:57,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 23:18:57,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 23:18:57,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 23:18:57,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 23:18:57,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 23:18:57,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 23:18:57,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:18:57,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:18:57,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 23:18:57,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 23:18:57,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 23:18:57,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 23:18:57,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:18:57,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 23:18:57,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 23:18:57,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:18:57,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 23:18:57,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 23:18:57,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:18:57,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 23:18:57,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:18:57,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 23:18:57,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 23:18:57,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 23:18:57,735] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 23:18:57,735] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 23:18:57,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:18:57,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:18:57,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 23:18:57,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 23:18:57,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 23:18:57,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 23:18:57,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:18:57,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 23:18:57,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 23:18:57,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:18:57,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 23:18:57,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 23:18:57,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:18:57,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 23:18:57,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 23:18:57,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:18:57,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 23:18:57,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 23:18:57,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:18:57,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 23:18:57,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 23:18:57,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:18:57,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:18:57,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 23:18:57,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 23:18:57,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 23:18:57,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 23:18:57,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:18:57,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 23:18:57,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 23:18:57,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:18:57,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 23:18:57,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 23:18:57,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 23:18:57,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 23:18:57,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:18:57,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 23:18:57,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:18:57,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 23:18:57,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 23:18:57,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 23:18:57,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:18:57,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 23:18:57,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 23:18:57,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:18:57,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 23:18:57,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 23:18:57,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:18:57,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:18:57,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:18:57,812] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 23:18:57,812] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 23:18:57,812] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 23:18:57,812] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 23:18:57,812] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 23:18:57,812] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 23:18:57,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:18:57,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step11000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 23:18:57,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: successfully saved checkpoint at iteration 11000 to checkpoints_220moscar +7: time (ms) | save-checkpoint: 681.45 +7: iteration 11010/ 14324 | consumed samples: 2818560 | consumed tokens: 5772410880 | elapsed time per iteration (s): 0.51 | learning rate: 4.319E-05 | global batch size: 256 | lm loss: 2.949723E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 506.017 | TFLOPs: 26.55 | +7: iteration 11020/ 14324 | consumed samples: 2821120 | consumed tokens: 5777653760 | elapsed time per iteration (s): 0.43 | learning rate: 4.305E-05 | global batch size: 256 | lm loss: 2.944307E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.428 | TFLOPs: 31.14 | +7: iteration 11030/ 14324 | consumed samples: 2823680 | consumed tokens: 5782896640 | elapsed time per iteration (s): 0.42 | learning rate: 4.292E-05 | global batch size: 256 | lm loss: 2.969794E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.435 | TFLOPs: 32.08 | +7: iteration 11040/ 14324 | consumed samples: 2826240 | consumed tokens: 5788139520 | elapsed time per iteration (s): 0.42 | learning rate: 4.279E-05 | global batch size: 256 | lm loss: 2.981402E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.465 | TFLOPs: 31.82 | +7: iteration 11050/ 14324 | consumed samples: 2828800 | consumed tokens: 5793382400 | elapsed time per iteration (s): 0.42 | learning rate: 4.266E-05 | global batch size: 256 | lm loss: 2.954008E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.182 | TFLOPs: 31.65 | +7: iteration 11060/ 14324 | consumed samples: 2831360 | consumed tokens: 5798625280 | elapsed time per iteration (s): 0.42 | learning rate: 4.252E-05 | global batch size: 256 | lm loss: 2.975674E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.056 | TFLOPs: 31.96 | +7: iteration 11070/ 14324 | consumed samples: 2833920 | consumed tokens: 5803868160 | elapsed time per iteration (s): 0.42 | learning rate: 4.239E-05 | global batch size: 256 | lm loss: 2.973948E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.803 | TFLOPs: 31.89 | +7: iteration 11080/ 14324 | consumed samples: 2836480 | consumed tokens: 5809111040 | elapsed time per iteration (s): 0.42 | learning rate: 4.226E-05 | global batch size: 256 | lm loss: 2.924265E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.900 | TFLOPs: 31.84 | +7: iteration 11090/ 14324 | consumed samples: 2839040 | consumed tokens: 5814353920 | elapsed time per iteration (s): 0.42 | learning rate: 4.213E-05 | global batch size: 256 | lm loss: 2.952178E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.364 | TFLOPs: 32.13 | +7: iteration 11100/ 14324 | consumed samples: 2841600 | consumed tokens: 5819596800 | elapsed time per iteration (s): 0.43 | learning rate: 4.200E-05 | global batch size: 256 | lm loss: 2.939990E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.487 | TFLOPs: 31.30 | +7: iteration 11110/ 14324 | consumed samples: 2844160 | consumed tokens: 5824839680 | elapsed time per iteration (s): 0.42 | learning rate: 4.187E-05 | global batch size: 256 | lm loss: 2.959286E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.862 | TFLOPs: 31.89 | +7: iteration 11120/ 14324 | consumed samples: 2846720 | consumed tokens: 5830082560 | elapsed time per iteration (s): 0.42 | learning rate: 4.174E-05 | global batch size: 256 | lm loss: 2.967037E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.926 | TFLOPs: 31.90 | +7: iteration 11130/ 14324 | consumed samples: 2849280 | consumed tokens: 5835325440 | elapsed time per iteration (s): 0.42 | learning rate: 4.161E-05 | global batch size: 256 | lm loss: 2.978209E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.684 | TFLOPs: 31.94 | +7: iteration 11140/ 14324 | consumed samples: 2851840 | consumed tokens: 5840568320 | elapsed time per iteration (s): 0.42 | learning rate: 4.148E-05 | global batch size: 256 | lm loss: 2.954336E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.582 | TFLOPs: 31.88 | +7: iteration 11150/ 14324 | consumed samples: 2854400 | consumed tokens: 5845811200 | elapsed time per iteration (s): 0.42 | learning rate: 4.135E-05 | global batch size: 256 | lm loss: 2.974408E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.758 | TFLOPs: 31.68 | +7: iteration 11160/ 14324 | consumed samples: 2856960 | consumed tokens: 5851054080 | elapsed time per iteration (s): 0.42 | learning rate: 4.122E-05 | global batch size: 256 | lm loss: 2.945807E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.681 | TFLOPs: 31.88 | +7: iteration 11170/ 14324 | consumed samples: 2859520 | consumed tokens: 5856296960 | elapsed time per iteration (s): 0.42 | learning rate: 4.109E-05 | global batch size: 256 | lm loss: 2.951327E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.642 | TFLOPs: 32.09 | +7: iteration 11180/ 14324 | consumed samples: 2862080 | consumed tokens: 5861539840 | elapsed time per iteration (s): 0.42 | learning rate: 4.096E-05 | global batch size: 256 | lm loss: 2.956562E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.003 | TFLOPs: 31.90 | +7: iteration 11190/ 14324 | consumed samples: 2864640 | consumed tokens: 5866782720 | elapsed time per iteration (s): 0.42 | learning rate: 4.084E-05 | global batch size: 256 | lm loss: 2.937404E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.934 | TFLOPs: 32.11 | +7: iteration 11200/ 14324 | consumed samples: 2867200 | consumed tokens: 5872025600 | elapsed time per iteration (s): 0.42 | learning rate: 4.071E-05 | global batch size: 256 | lm loss: 2.976291E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.829 | TFLOPs: 31.84 | +7: iteration 11210/ 14324 | consumed samples: 2869760 | consumed tokens: 5877268480 | elapsed time per iteration (s): 0.43 | learning rate: 4.058E-05 | global batch size: 256 | lm loss: 2.961150E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.286 | TFLOPs: 31.60 | +7: iteration 11220/ 14324 | consumed samples: 2872320 | consumed tokens: 5882511360 | elapsed time per iteration (s): 0.42 | learning rate: 4.046E-05 | global batch size: 256 | lm loss: 2.943244E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.278 | TFLOPs: 32.13 | +7: iteration 11230/ 14324 | consumed samples: 2874880 | consumed tokens: 5887754240 | elapsed time per iteration (s): 0.43 | learning rate: 4.033E-05 | global batch size: 256 | lm loss: 2.965275E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.878 | TFLOPs: 31.58 | +7: iteration 11240/ 14324 | consumed samples: 2877440 | consumed tokens: 5892997120 | elapsed time per iteration (s): 0.43 | learning rate: 4.020E-05 | global batch size: 256 | lm loss: 2.963460E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.293 | TFLOPs: 31.29 | +7: iteration 11250/ 14324 | consumed samples: 2880000 | consumed tokens: 5898240000 | elapsed time per iteration (s): 0.43 | learning rate: 4.008E-05 | global batch size: 256 | lm loss: 2.937617E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.288 | TFLOPs: 31.23 | +7: iteration 11260/ 14324 | consumed samples: 2882560 | consumed tokens: 5903482880 | elapsed time per iteration (s): 0.42 | learning rate: 3.995E-05 | global batch size: 256 | lm loss: 2.939359E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.658 | TFLOPs: 31.94 | +7: iteration 11270/ 14324 | consumed samples: 2885120 | consumed tokens: 5908725760 | elapsed time per iteration (s): 0.42 | learning rate: 3.983E-05 | global batch size: 256 | lm loss: 2.957795E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.544 | TFLOPs: 31.88 | +7: iteration 11280/ 14324 | consumed samples: 2887680 | consumed tokens: 5913968640 | elapsed time per iteration (s): 0.42 | learning rate: 3.970E-05 | global batch size: 256 | lm loss: 2.959642E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.852 | TFLOPs: 31.89 | +7: iteration 11290/ 14324 | consumed samples: 2890240 | consumed tokens: 5919211520 | elapsed time per iteration (s): 0.43 | learning rate: 3.958E-05 | global batch size: 256 | lm loss: 2.952113E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.331 | TFLOPs: 31.60 | +7: iteration 11300/ 14324 | consumed samples: 2892800 | consumed tokens: 5924454400 | elapsed time per iteration (s): 0.43 | learning rate: 3.945E-05 | global batch size: 256 | lm loss: 2.958037E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.939 | TFLOPs: 31.58 | +7: iteration 11310/ 14324 | consumed samples: 2895360 | consumed tokens: 5929697280 | elapsed time per iteration (s): 0.42 | learning rate: 3.933E-05 | global batch size: 256 | lm loss: 2.966364E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.915 | TFLOPs: 31.79 | +7: iteration 11320/ 14324 | consumed samples: 2897920 | consumed tokens: 5934940160 | elapsed time per iteration (s): 0.42 | learning rate: 3.921E-05 | global batch size: 256 | lm loss: 2.947823E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.145 | TFLOPs: 31.96 | +7: iteration 11330/ 14324 | consumed samples: 2900480 | consumed tokens: 5940183040 | elapsed time per iteration (s): 0.43 | learning rate: 3.908E-05 | global batch size: 256 | lm loss: 2.950936E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.776 | TFLOPs: 31.47 | +7: iteration 11340/ 14324 | consumed samples: 2903040 | consumed tokens: 5945425920 | elapsed time per iteration (s): 0.44 | learning rate: 3.896E-05 | global batch size: 256 | lm loss: 2.985057E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 584.814 | TFLOPs: 30.68 | +7: iteration 11350/ 14324 | consumed samples: 2905600 | consumed tokens: 5950668800 | elapsed time per iteration (s): 0.42 | learning rate: 3.884E-05 | global batch size: 256 | lm loss: 2.959857E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.089 | TFLOPs: 31.96 | +7: iteration 11360/ 14324 | consumed samples: 2908160 | consumed tokens: 5955911680 | elapsed time per iteration (s): 0.43 | learning rate: 3.872E-05 | global batch size: 256 | lm loss: 2.979616E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.230 | TFLOPs: 31.55 | +7: iteration 11370/ 14324 | consumed samples: 2910720 | consumed tokens: 5961154560 | elapsed time per iteration (s): 0.44 | learning rate: 3.860E-05 | global batch size: 256 | lm loss: 2.966364E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 581.553 | TFLOPs: 30.51 | +7: iteration 11380/ 14324 | consumed samples: 2913280 | consumed tokens: 5966397440 | elapsed time per iteration (s): 0.42 | learning rate: 3.847E-05 | global batch size: 256 | lm loss: 2.920258E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.908 | TFLOPs: 31.95 | +7: iteration 11390/ 14324 | consumed samples: 2915840 | consumed tokens: 5971640320 | elapsed time per iteration (s): 0.42 | learning rate: 3.835E-05 | global batch size: 256 | lm loss: 2.948490E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.766 | TFLOPs: 31.94 | +7: iteration 11400/ 14324 | consumed samples: 2918400 | consumed tokens: 5976883200 | elapsed time per iteration (s): 0.42 | learning rate: 3.823E-05 | global batch size: 256 | lm loss: 2.956792E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.256 | TFLOPs: 31.86 | +7: iteration 11410/ 14324 | consumed samples: 2920960 | consumed tokens: 5982126080 | elapsed time per iteration (s): 0.42 | learning rate: 3.811E-05 | global batch size: 256 | lm loss: 2.950908E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.290 | TFLOPs: 31.86 | +7: iteration 11420/ 14324 | consumed samples: 2923520 | consumed tokens: 5987368960 | elapsed time per iteration (s): 0.42 | learning rate: 3.799E-05 | global batch size: 256 | lm loss: 2.964945E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.226 | TFLOPs: 32.12 | +7: iteration 11430/ 14324 | consumed samples: 2926080 | consumed tokens: 5992611840 | elapsed time per iteration (s): 0.42 | learning rate: 3.787E-05 | global batch size: 256 | lm loss: 2.939868E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.531 | TFLOPs: 32.09 | +7: iteration 11440/ 14324 | consumed samples: 2928640 | consumed tokens: 5997854720 | elapsed time per iteration (s): 0.42 | learning rate: 3.776E-05 | global batch size: 256 | lm loss: 3.005311E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.743 | TFLOPs: 32.10 | +7: iteration 11450/ 14324 | consumed samples: 2931200 | consumed tokens: 6003097600 | elapsed time per iteration (s): 0.45 | learning rate: 3.764E-05 | global batch size: 256 | lm loss: 2.932573E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 573.980 | TFLOPs: 30.12 | +7: iteration 11460/ 14324 | consumed samples: 2933760 | consumed tokens: 6008340480 | elapsed time per iteration (s): 0.44 | learning rate: 3.752E-05 | global batch size: 256 | lm loss: 2.943851E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 586.011 | TFLOPs: 30.75 | +7: iteration 11470/ 14324 | consumed samples: 2936320 | consumed tokens: 6013583360 | elapsed time per iteration (s): 0.43 | learning rate: 3.740E-05 | global batch size: 256 | lm loss: 2.940939E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.689 | TFLOPs: 31.57 | +7: iteration 11480/ 14324 | consumed samples: 2938880 | consumed tokens: 6018826240 | elapsed time per iteration (s): 0.43 | learning rate: 3.728E-05 | global batch size: 256 | lm loss: 2.976934E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.945 | TFLOPs: 31.16 | +7: iteration 11490/ 14324 | consumed samples: 2941440 | consumed tokens: 6024069120 | elapsed time per iteration (s): 0.43 | learning rate: 3.717E-05 | global batch size: 256 | lm loss: 2.977746E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.370 | TFLOPs: 31.40 | +7: iteration 11500/ 14324 | consumed samples: 2944000 | consumed tokens: 6029312000 | elapsed time per iteration (s): 0.42 | learning rate: 3.705E-05 | global batch size: 256 | lm loss: 2.927921E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.887 | TFLOPs: 31.89 | +7: iteration 11510/ 14324 | consumed samples: 2946560 | consumed tokens: 6034554880 | elapsed time per iteration (s): 0.42 | learning rate: 3.693E-05 | global batch size: 256 | lm loss: 2.975245E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.345 | TFLOPs: 32.13 | +7: iteration 11520/ 14324 | consumed samples: 2949120 | consumed tokens: 6039797760 | elapsed time per iteration (s): 0.42 | learning rate: 3.682E-05 | global batch size: 256 | lm loss: 2.967148E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.060 | TFLOPs: 32.11 | +7: iteration 11530/ 14324 | consumed samples: 2951680 | consumed tokens: 6045040640 | elapsed time per iteration (s): 0.43 | learning rate: 3.670E-05 | global batch size: 256 | lm loss: 2.938524E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.212 | TFLOPs: 31.07 | +7: iteration 11540/ 14324 | consumed samples: 2954240 | consumed tokens: 6050283520 | elapsed time per iteration (s): 0.42 | learning rate: 3.658E-05 | global batch size: 256 | lm loss: 2.943104E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.476 | TFLOPs: 32.14 | +7: iteration 11550/ 14324 | consumed samples: 2956800 | consumed tokens: 6055526400 | elapsed time per iteration (s): 0.42 | learning rate: 3.647E-05 | global batch size: 256 | lm loss: 2.957185E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.787 | TFLOPs: 31.68 | +7: iteration 11560/ 14324 | consumed samples: 2959360 | consumed tokens: 6060769280 | elapsed time per iteration (s): 0.42 | learning rate: 3.635E-05 | global batch size: 256 | lm loss: 2.990669E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.067 | TFLOPs: 31.64 | +7: iteration 11570/ 14324 | consumed samples: 2961920 | consumed tokens: 6066012160 | elapsed time per iteration (s): 0.43 | learning rate: 3.624E-05 | global batch size: 256 | lm loss: 2.962755E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.074 | TFLOPs: 31.48 | +7: iteration 11580/ 14324 | consumed samples: 2964480 | consumed tokens: 6071255040 | elapsed time per iteration (s): 0.42 | learning rate: 3.613E-05 | global batch size: 256 | lm loss: 2.974457E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.731 | TFLOPs: 31.99 | +7: iteration 11590/ 14324 | consumed samples: 2967040 | consumed tokens: 6076497920 | elapsed time per iteration (s): 0.43 | learning rate: 3.601E-05 | global batch size: 256 | lm loss: 2.947660E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.837 | TFLOPs: 31.42 | +7: iteration 11600/ 14324 | consumed samples: 2969600 | consumed tokens: 6081740800 | elapsed time per iteration (s): 0.42 | learning rate: 3.590E-05 | global batch size: 256 | lm loss: 2.923773E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.656 | TFLOPs: 31.99 | +7: iteration 11610/ 14324 | consumed samples: 2972160 | consumed tokens: 6086983680 | elapsed time per iteration (s): 0.42 | learning rate: 3.579E-05 | global batch size: 256 | lm loss: 2.961894E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.024 | TFLOPs: 32.01 | +7: iteration 11620/ 14324 | consumed samples: 2974720 | consumed tokens: 6092226560 | elapsed time per iteration (s): 0.44 | learning rate: 3.567E-05 | global batch size: 256 | lm loss: 2.976593E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 582.784 | TFLOPs: 30.58 | +7: iteration 11630/ 14324 | consumed samples: 2977280 | consumed tokens: 6097469440 | elapsed time per iteration (s): 0.42 | learning rate: 3.556E-05 | global batch size: 256 | lm loss: 2.945638E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.173 | TFLOPs: 31.80 | +7: iteration 11640/ 14324 | consumed samples: 2979840 | consumed tokens: 6102712320 | elapsed time per iteration (s): 0.42 | learning rate: 3.545E-05 | global batch size: 256 | lm loss: 2.934620E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.783 | TFLOPs: 31.84 | +7: iteration 11650/ 14324 | consumed samples: 2982400 | consumed tokens: 6107955200 | elapsed time per iteration (s): 0.42 | learning rate: 3.534E-05 | global batch size: 256 | lm loss: 2.942464E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.409 | TFLOPs: 31.82 | +7: iteration 11660/ 14324 | consumed samples: 2984960 | consumed tokens: 6113198080 | elapsed time per iteration (s): 0.43 | learning rate: 3.523E-05 | global batch size: 256 | lm loss: 2.961124E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.247 | TFLOPs: 31.13 | +7: iteration 11670/ 14324 | consumed samples: 2987520 | consumed tokens: 6118440960 | elapsed time per iteration (s): 0.42 | learning rate: 3.512E-05 | global batch size: 256 | lm loss: 2.931797E+00 | grad norm: 0.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.979 | TFLOPs: 31.95 | +7: iteration 11680/ 14324 | consumed samples: 2990080 | consumed tokens: 6123683840 | elapsed time per iteration (s): 0.42 | learning rate: 3.500E-05 | global batch size: 256 | lm loss: 2.950957E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.486 | TFLOPs: 31.82 | +7: iteration 11690/ 14324 | consumed samples: 2992640 | consumed tokens: 6128926720 | elapsed time per iteration (s): 0.44 | learning rate: 3.489E-05 | global batch size: 256 | lm loss: 2.959449E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 581.746 | TFLOPs: 30.52 | +7: iteration 11700/ 14324 | consumed samples: 2995200 | consumed tokens: 6134169600 | elapsed time per iteration (s): 0.42 | learning rate: 3.479E-05 | global batch size: 256 | lm loss: 2.955982E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.357 | TFLOPs: 31.71 | +7: iteration 11710/ 14324 | consumed samples: 2997760 | consumed tokens: 6139412480 | elapsed time per iteration (s): 0.42 | learning rate: 3.468E-05 | global batch size: 256 | lm loss: 2.960404E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.683 | TFLOPs: 31.78 | +7: iteration 11720/ 14324 | consumed samples: 3000320 | consumed tokens: 6144655360 | elapsed time per iteration (s): 0.43 | learning rate: 3.457E-05 | global batch size: 256 | lm loss: 2.927220E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.059 | TFLOPs: 31.48 | +7: iteration 11730/ 14324 | consumed samples: 3002880 | consumed tokens: 6149898240 | elapsed time per iteration (s): 0.42 | learning rate: 3.446E-05 | global batch size: 256 | lm loss: 2.936987E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.513 | TFLOPs: 31.82 | +7: iteration 11740/ 14324 | consumed samples: 3005440 | consumed tokens: 6155141120 | elapsed time per iteration (s): 0.43 | learning rate: 3.435E-05 | global batch size: 256 | lm loss: 2.914851E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.075 | TFLOPs: 31.07 | +7: iteration 11750/ 14324 | consumed samples: 3008000 | consumed tokens: 6160384000 | elapsed time per iteration (s): 0.43 | learning rate: 3.424E-05 | global batch size: 256 | lm loss: 2.950955E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.235 | TFLOPs: 31.55 | +7: iteration 11760/ 14324 | consumed samples: 3010560 | consumed tokens: 6165626880 | elapsed time per iteration (s): 0.42 | learning rate: 3.413E-05 | global batch size: 256 | lm loss: 2.969761E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.475 | TFLOPs: 31.82 | +7: iteration 11770/ 14324 | consumed samples: 3013120 | consumed tokens: 6170869760 | elapsed time per iteration (s): 0.43 | learning rate: 3.403E-05 | global batch size: 256 | lm loss: 2.935368E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.341 | TFLOPs: 31.03 | +7: iteration 11780/ 14324 | consumed samples: 3015680 | consumed tokens: 6176112640 | elapsed time per iteration (s): 0.43 | learning rate: 3.392E-05 | global batch size: 256 | lm loss: 2.953605E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.163 | TFLOPs: 31.28 | +7: iteration 11790/ 14324 | consumed samples: 3018240 | consumed tokens: 6181355520 | elapsed time per iteration (s): 0.42 | learning rate: 3.381E-05 | global batch size: 256 | lm loss: 2.937467E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.090 | TFLOPs: 31.75 | +7: iteration 11800/ 14324 | consumed samples: 3020800 | consumed tokens: 6186598400 | elapsed time per iteration (s): 0.42 | learning rate: 3.371E-05 | global batch size: 256 | lm loss: 2.944011E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.872 | TFLOPs: 31.79 | +7: iteration 11810/ 14324 | consumed samples: 3023360 | consumed tokens: 6191841280 | elapsed time per iteration (s): 0.43 | learning rate: 3.360E-05 | global batch size: 256 | lm loss: 2.964631E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.997 | TFLOPs: 31.22 | +7: iteration 11820/ 14324 | consumed samples: 3025920 | consumed tokens: 6197084160 | elapsed time per iteration (s): 0.42 | learning rate: 3.350E-05 | global batch size: 256 | lm loss: 2.953618E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.170 | TFLOPs: 31.96 | +7: iteration 11830/ 14324 | consumed samples: 3028480 | consumed tokens: 6202327040 | elapsed time per iteration (s): 0.42 | learning rate: 3.339E-05 | global batch size: 256 | lm loss: 2.965413E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.098 | TFLOPs: 31.85 | +7: iteration 11840/ 14324 | consumed samples: 3031040 | consumed tokens: 6207569920 | elapsed time per iteration (s): 0.43 | learning rate: 3.329E-05 | global batch size: 256 | lm loss: 2.947622E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.058 | TFLOPs: 31.59 | +7: iteration 11850/ 14324 | consumed samples: 3033600 | consumed tokens: 6212812800 | elapsed time per iteration (s): 0.42 | learning rate: 3.318E-05 | global batch size: 256 | lm loss: 2.962975E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.714 | TFLOPs: 31.73 | +7: iteration 11860/ 14324 | consumed samples: 3036160 | consumed tokens: 6218055680 | elapsed time per iteration (s): 0.42 | learning rate: 3.308E-05 | global batch size: 256 | lm loss: 2.973296E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.389 | TFLOPs: 31.71 | +7: iteration 11870/ 14324 | consumed samples: 3038720 | consumed tokens: 6223298560 | elapsed time per iteration (s): 0.42 | learning rate: 3.298E-05 | global batch size: 256 | lm loss: 2.978154E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.351 | TFLOPs: 31.81 | +7: iteration 11880/ 14324 | consumed samples: 3041280 | consumed tokens: 6228541440 | elapsed time per iteration (s): 0.43 | learning rate: 3.287E-05 | global batch size: 256 | lm loss: 2.900114E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.010 | TFLOPs: 31.53 | +7: iteration 11890/ 14324 | consumed samples: 3043840 | consumed tokens: 6233784320 | elapsed time per iteration (s): 0.43 | learning rate: 3.277E-05 | global batch size: 256 | lm loss: 2.916830E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.121 | TFLOPs: 31.38 | +7: iteration 11900/ 14324 | consumed samples: 3046400 | consumed tokens: 6239027200 | elapsed time per iteration (s): 0.42 | learning rate: 3.267E-05 | global batch size: 256 | lm loss: 2.942963E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.783 | TFLOPs: 31.89 | +7: iteration 11910/ 14324 | consumed samples: 3048960 | consumed tokens: 6244270080 | elapsed time per iteration (s): 0.43 | learning rate: 3.257E-05 | global batch size: 256 | lm loss: 2.933218E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.736 | TFLOPs: 31.26 | +7: iteration 11920/ 14324 | consumed samples: 3051520 | consumed tokens: 6249512960 | elapsed time per iteration (s): 0.43 | learning rate: 3.247E-05 | global batch size: 256 | lm loss: 2.932380E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.502 | TFLOPs: 31.14 | +7: iteration 11930/ 14324 | consumed samples: 3054080 | consumed tokens: 6254755840 | elapsed time per iteration (s): 0.43 | learning rate: 3.237E-05 | global batch size: 256 | lm loss: 2.951554E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.983 | TFLOPs: 31.32 | +7: iteration 11940/ 14324 | consumed samples: 3056640 | consumed tokens: 6259998720 | elapsed time per iteration (s): 0.42 | learning rate: 3.226E-05 | global batch size: 256 | lm loss: 2.925414E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.086 | TFLOPs: 31.96 | +7: iteration 11950/ 14324 | consumed samples: 3059200 | consumed tokens: 6265241600 | elapsed time per iteration (s): 0.42 | learning rate: 3.216E-05 | global batch size: 256 | lm loss: 2.936817E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.305 | TFLOPs: 31.81 | +7: iteration 11960/ 14324 | consumed samples: 3061760 | consumed tokens: 6270484480 | elapsed time per iteration (s): 0.42 | learning rate: 3.206E-05 | global batch size: 256 | lm loss: 2.959429E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.973 | TFLOPs: 31.79 | +7: iteration 11970/ 14324 | consumed samples: 3064320 | consumed tokens: 6275727360 | elapsed time per iteration (s): 0.43 | learning rate: 3.197E-05 | global batch size: 256 | lm loss: 2.951171E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.715 | TFLOPs: 31.57 | +7: iteration 11980/ 14324 | consumed samples: 3066880 | consumed tokens: 6280970240 | elapsed time per iteration (s): 0.42 | learning rate: 3.187E-05 | global batch size: 256 | lm loss: 2.937293E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.119 | TFLOPs: 31.70 | +7: iteration 11990/ 14324 | consumed samples: 3069440 | consumed tokens: 6286213120 | elapsed time per iteration (s): 0.43 | learning rate: 3.177E-05 | global batch size: 256 | lm loss: 2.912948E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.267 | TFLOPs: 31.50 | +0: [2022-11-29 23:26:02,280] [INFO] [logging.py:68:log_dist] [Rank 0] step=12000, skipped=0, lr=[3.1668852640169795e-05, 3.1668852640169795e-05, 3.1668852640169795e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 12000/ 14324 | consumed samples: 3072000 | consumed tokens: 6291456000 | elapsed time per iteration (s): 0.42 | learning rate: 3.167E-05 | global batch size: 256 | lm loss: 2.919190E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.416 | TFLOPs: 31.92 | +0: steps: 12000 loss: 2.9023 iter time (s): 0.422 samples/sec: 606.549 +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 12000 | lm loss value: 2.806943E+00 | lm loss PPL: 1.655922E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 12000 to checkpoints_220moscar +0: [2022-11-29 23:26:02,440] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step12000 is begin to save! +0: [2022-11-29 23:26:02,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/layer_01-model_00-model_states.pt... +0: [2022-11-29 23:26:02,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/layer_01-model_00-model_states.pt. +0: [2022-11-29 23:26:02,548] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/layer_03-model_00-model_states.pt... +0: [2022-11-29 23:26:02,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/layer_03-model_00-model_states.pt. +0: [2022-11-29 23:26:02,571] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/layer_04-model_00-model_states.pt... +0: [2022-11-29 23:26:02,594] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/layer_04-model_00-model_states.pt. +0: [2022-11-29 23:26:02,594] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/layer_05-model_00-model_states.pt... +0: [2022-11-29 23:26:02,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/layer_05-model_00-model_states.pt. +0: [2022-11-29 23:26:02,618] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/layer_06-model_00-model_states.pt... +0: [2022-11-29 23:26:02,639] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/layer_06-model_00-model_states.pt. +0: [2022-11-29 23:26:02,640] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/layer_07-model_00-model_states.pt... +0: [2022-11-29 23:26:02,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/layer_07-model_00-model_states.pt. +0: [2022-11-29 23:26:02,664] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/layer_08-model_00-model_states.pt... +0: [2022-11-29 23:26:02,687] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/layer_08-model_00-model_states.pt. +0: [2022-11-29 23:26:02,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/layer_09-model_00-model_states.pt... +0: [2022-11-29 23:26:02,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/layer_09-model_00-model_states.pt. +0: [2022-11-29 23:26:02,709] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/layer_10-model_00-model_states.pt... +0: [2022-11-29 23:26:02,731] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/layer_10-model_00-model_states.pt. +0: [2022-11-29 23:26:02,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/layer_11-model_00-model_states.pt... +0: [2022-11-29 23:26:02,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/layer_11-model_00-model_states.pt. +0: [2022-11-29 23:26:02,755] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/layer_12-model_00-model_states.pt... +0: [2022-11-29 23:26:02,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/layer_12-model_00-model_states.pt. +0: [2022-11-29 23:26:02,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/layer_13-model_00-model_states.pt... +0: [2022-11-29 23:26:02,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/layer_13-model_00-model_states.pt. +0: [2022-11-29 23:26:02,802] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/layer_14-model_00-model_states.pt... +0: [2022-11-29 23:26:02,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/layer_14-model_00-model_states.pt. +0: [2022-11-29 23:26:02,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/layer_15-model_00-model_states.pt... +0: [2022-11-29 23:26:02,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/layer_15-model_00-model_states.pt. +0: [2022-11-29 23:26:02,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/layer_16-model_00-model_states.pt... +0: [2022-11-29 23:26:02,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/layer_16-model_00-model_states.pt. +0: [2022-11-29 23:26:02,872] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/layer_17-model_00-model_states.pt... +0: [2022-11-29 23:26:02,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/layer_17-model_00-model_states.pt. +0: [2022-11-29 23:26:02,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/layer_18-model_00-model_states.pt... +0: [2022-11-29 23:26:02,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/layer_18-model_00-model_states.pt. +0: [2022-11-29 23:26:02,916] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/layer_19-model_00-model_states.pt... +0: [2022-11-29 23:26:02,938] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/layer_19-model_00-model_states.pt. +0: [2022-11-29 23:26:02,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/layer_20-model_00-model_states.pt... +0: [2022-11-29 23:26:02,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/layer_20-model_00-model_states.pt. +0: [2022-11-29 23:26:02,963] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/layer_22-model_00-model_states.pt... +0: [2022-11-29 23:26:02,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/layer_22-model_00-model_states.pt. +0: [2022-11-29 23:26:02,968] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_220moscar/global_step12000/mp_rank_00_model_states.pt +0: [2022-11-29 23:26:02,968] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/mp_rank_00_model_states.pt... +0: [2022-11-29 23:26:02,970] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/mp_rank_00_model_states.pt. +0: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:26:02,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:26:03,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:26:03,037] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:26:03,037] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 23:26:03,037] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +1: [2022-11-29 23:26:03,038] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:26:03,038] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 23:26:03,038] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 23:26:03,038] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:26:03,039] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 23:26:03,039] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 23:26:03,039] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:26:03,039] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 23:26:03,039] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 23:26:03,039] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:26:03,039] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 23:26:03,039] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 23:26:03,039] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:26:03,039] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 23:26:03,039] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +1: [2022-11-29 23:26:03,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:26:03,041] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 23:26:03,041] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +7: [2022-11-29 23:26:03,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:26:03,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:26:03,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 23:26:03,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 23:26:03,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:26:03,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:26:03,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 23:26:03,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 23:26:03,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 23:26:03,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +7: [2022-11-29 23:26:03,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:26:03,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 23:26:03,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 23:26:03,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:26:03,043] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +1: [2022-11-29 23:26:03,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:26:03,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +1: [2022-11-29 23:26:03,043] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 23:26:03,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +7: [2022-11-29 23:26:03,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:26:03,043] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 23:26:03,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 23:26:03,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:26:03,043] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 23:26:03,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:26:03,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 23:26:03,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +1: [2022-11-29 23:26:03,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +4: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 23:26:03,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:26:03,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 23:26:03,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +2: [2022-11-29 23:26:03,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 23:26:03,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +2: [2022-11-29 23:26:03,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:26:03,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 23:26:03,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 23:26:03,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 23:26:03,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 23:26:03,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +1: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:26:03,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +5: [2022-11-29 23:26:03,035] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +7: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +1: [2022-11-29 23:26:03,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +5: [2022-11-29 23:26:03,035] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +1: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +5: [2022-11-29 23:26:03,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:26:03,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:26:03,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:26:03,041] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 23:26:03,041] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 23:26:03,041] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 23:26:03,041] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +5: [2022-11-29 23:26:03,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:26:03,041] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +5: [2022-11-29 23:26:03,041] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +5: [2022-11-29 23:26:03,041] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 23:26:03,041] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +5: [2022-11-29 23:26:03,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:26:03,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 23:26:03,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +5: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:26:03,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 23:26:03,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +2: [2022-11-29 23:26:03,045] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:26:03,045] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:26:03,045] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 23:26:03,045] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 23:26:03,045] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:26:03,045] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +2: [2022-11-29 23:26:03,045] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +2: [2022-11-29 23:26:03,045] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 23:26:03,045] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +2: [2022-11-29 23:26:03,046] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:26:03,046] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +7: [2022-11-29 23:26:03,045] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:26:03,045] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 23:26:03,046] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +2: [2022-11-29 23:26:03,046] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 23:26:03,046] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:26:03,046] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:26:03,046] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +7: [2022-11-29 23:26:03,046] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +3: [2022-11-29 23:26:03,046] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +7: [2022-11-29 23:26:03,046] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 23:26:03,046] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:26:03,047] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 23:26:03,047] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +7: [2022-11-29 23:26:03,047] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:26:03,047] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 23:26:03,047] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +7: [2022-11-29 23:26:03,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:26:03,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:26:03,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +2: [2022-11-29 23:26:03,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 23:26:03,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +7: [2022-11-29 23:26:03,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 23:26:03,052] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:26:03,052] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 23:26:03,052] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 23:26:03,052] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:26:03,052] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +5: [2022-11-29 23:26:03,052] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:26:03,052] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +2: [2022-11-29 23:26:03,053] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:26:03,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:26:03,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:26:03,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:26:03,060] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +2: [2022-11-29 23:26:03,053] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +0: [2022-11-29 23:26:03,060] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +2: [2022-11-29 23:26:03,053] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 23:26:03,060] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 23:26:03,060] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +1: [2022-11-29 23:26:03,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:26:03,060] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 23:26:03,060] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +1: [2022-11-29 23:26:03,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:26:03,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +6: [2022-11-29 23:26:03,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:26:03,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:26:03,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:26:03,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:26:03,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:26:03,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 23:26:03,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 23:26:03,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 23:26:03,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:26:03,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 23:26:03,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +1: [2022-11-29 23:26:03,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 23:26:03,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 23:26:03,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 23:26:03,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 23:26:03,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 23:26:03,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 23:26:03,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 23:26:03,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 23:26:03,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:26:03,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 23:26:03,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +5: [2022-11-29 23:26:03,052] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 23:26:03,052] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 23:26:03,078] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:26:03,079] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 23:26:03,079] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 23:26:03,078] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:26:03,079] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 23:26:03,079] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 23:26:03,093] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step12000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 23:26:03,094] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: successfully saved checkpoint at iteration 12000 to checkpoints_220moscar +7: time (ms) | save-checkpoint: 661.12 +7: iteration 12010/ 14324 | consumed samples: 3074560 | consumed tokens: 6296698880 | elapsed time per iteration (s): 0.50 | learning rate: 3.157E-05 | global batch size: 256 | lm loss: 2.952857E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 508.026 | TFLOPs: 26.66 | +7: iteration 12020/ 14324 | consumed samples: 3077120 | consumed tokens: 6301941760 | elapsed time per iteration (s): 0.42 | learning rate: 3.147E-05 | global batch size: 256 | lm loss: 2.971215E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.198 | TFLOPs: 31.81 | +7: iteration 12030/ 14324 | consumed samples: 3079680 | consumed tokens: 6307184640 | elapsed time per iteration (s): 0.43 | learning rate: 3.138E-05 | global batch size: 256 | lm loss: 2.941483E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.562 | TFLOPs: 31.20 | +7: iteration 12040/ 14324 | consumed samples: 3082240 | consumed tokens: 6312427520 | elapsed time per iteration (s): 0.42 | learning rate: 3.128E-05 | global batch size: 256 | lm loss: 2.933222E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.735 | TFLOPs: 32.15 | +7: iteration 12050/ 14324 | consumed samples: 3084800 | consumed tokens: 6317670400 | elapsed time per iteration (s): 0.43 | learning rate: 3.118E-05 | global batch size: 256 | lm loss: 2.915377E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.089 | TFLOPs: 31.43 | +7: iteration 12060/ 14324 | consumed samples: 3087360 | consumed tokens: 6322913280 | elapsed time per iteration (s): 0.44 | learning rate: 3.109E-05 | global batch size: 256 | lm loss: 2.964569E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 577.808 | TFLOPs: 30.32 | +7: iteration 12070/ 14324 | consumed samples: 3089920 | consumed tokens: 6328156160 | elapsed time per iteration (s): 0.45 | learning rate: 3.099E-05 | global batch size: 256 | lm loss: 2.968671E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 573.755 | TFLOPs: 30.10 | +7: iteration 12080/ 14324 | consumed samples: 3092480 | consumed tokens: 6333399040 | elapsed time per iteration (s): 0.42 | learning rate: 3.090E-05 | global batch size: 256 | lm loss: 2.936081E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.589 | TFLOPs: 31.77 | +7: iteration 12090/ 14324 | consumed samples: 3095040 | consumed tokens: 6338641920 | elapsed time per iteration (s): 0.43 | learning rate: 3.080E-05 | global batch size: 256 | lm loss: 2.967149E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.756 | TFLOPs: 31.36 | +7: iteration 12100/ 14324 | consumed samples: 3097600 | consumed tokens: 6343884800 | elapsed time per iteration (s): 0.42 | learning rate: 3.071E-05 | global batch size: 256 | lm loss: 2.943685E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.420 | TFLOPs: 31.92 | +7: iteration 12110/ 14324 | consumed samples: 3100160 | consumed tokens: 6349127680 | elapsed time per iteration (s): 0.43 | learning rate: 3.061E-05 | global batch size: 256 | lm loss: 2.933238E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.151 | TFLOPs: 31.59 | +7: iteration 12120/ 14324 | consumed samples: 3102720 | consumed tokens: 6354370560 | elapsed time per iteration (s): 0.43 | learning rate: 3.052E-05 | global batch size: 256 | lm loss: 2.973354E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.216 | TFLOPs: 31.54 | +7: iteration 12130/ 14324 | consumed samples: 3105280 | consumed tokens: 6359613440 | elapsed time per iteration (s): 0.42 | learning rate: 3.043E-05 | global batch size: 256 | lm loss: 2.920891E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.716 | TFLOPs: 32.10 | +7: iteration 12140/ 14324 | consumed samples: 3107840 | consumed tokens: 6364856320 | elapsed time per iteration (s): 0.43 | learning rate: 3.033E-05 | global batch size: 256 | lm loss: 2.928959E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.272 | TFLOPs: 31.08 | +7: iteration 12150/ 14324 | consumed samples: 3110400 | consumed tokens: 6370099200 | elapsed time per iteration (s): 0.42 | learning rate: 3.024E-05 | global batch size: 256 | lm loss: 2.958064E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.231 | TFLOPs: 32.07 | +7: iteration 12160/ 14324 | consumed samples: 3112960 | consumed tokens: 6375342080 | elapsed time per iteration (s): 0.42 | learning rate: 3.015E-05 | global batch size: 256 | lm loss: 2.951598E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.511 | TFLOPs: 31.93 | +7: iteration 12170/ 14324 | consumed samples: 3115520 | consumed tokens: 6380584960 | elapsed time per iteration (s): 0.44 | learning rate: 3.006E-05 | global batch size: 256 | lm loss: 2.952401E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 576.022 | TFLOPs: 30.22 | +7: iteration 12180/ 14324 | consumed samples: 3118080 | consumed tokens: 6385827840 | elapsed time per iteration (s): 0.43 | learning rate: 2.996E-05 | global batch size: 256 | lm loss: 2.904541E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.510 | TFLOPs: 31.46 | +7: iteration 12190/ 14324 | consumed samples: 3120640 | consumed tokens: 6391070720 | elapsed time per iteration (s): 0.43 | learning rate: 2.987E-05 | global batch size: 256 | lm loss: 2.934521E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.461 | TFLOPs: 31.40 | +7: iteration 12200/ 14324 | consumed samples: 3123200 | consumed tokens: 6396313600 | elapsed time per iteration (s): 0.42 | learning rate: 2.978E-05 | global batch size: 256 | lm loss: 2.964416E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.131 | TFLOPs: 31.65 | +7: iteration 12210/ 14324 | consumed samples: 3125760 | consumed tokens: 6401556480 | elapsed time per iteration (s): 0.43 | learning rate: 2.969E-05 | global batch size: 256 | lm loss: 2.938282E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.420 | TFLOPs: 31.08 | +7: iteration 12220/ 14324 | consumed samples: 3128320 | consumed tokens: 6406799360 | elapsed time per iteration (s): 0.42 | learning rate: 2.960E-05 | global batch size: 256 | lm loss: 2.952868E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.716 | TFLOPs: 31.73 | +7: iteration 12230/ 14324 | consumed samples: 3130880 | consumed tokens: 6412042240 | elapsed time per iteration (s): 0.42 | learning rate: 2.951E-05 | global batch size: 256 | lm loss: 2.950183E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.565 | TFLOPs: 31.93 | +7: iteration 12240/ 14324 | consumed samples: 3133440 | consumed tokens: 6417285120 | elapsed time per iteration (s): 0.42 | learning rate: 2.942E-05 | global batch size: 256 | lm loss: 2.954229E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.265 | TFLOPs: 32.02 | +7: iteration 12250/ 14324 | consumed samples: 3136000 | consumed tokens: 6422528000 | elapsed time per iteration (s): 0.42 | learning rate: 2.934E-05 | global batch size: 256 | lm loss: 2.957066E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.931 | TFLOPs: 31.90 | +7: iteration 12260/ 14324 | consumed samples: 3138560 | consumed tokens: 6427770880 | elapsed time per iteration (s): 0.42 | learning rate: 2.925E-05 | global batch size: 256 | lm loss: 2.933387E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.270 | TFLOPs: 31.71 | +7: iteration 12270/ 14324 | consumed samples: 3141120 | consumed tokens: 6433013760 | elapsed time per iteration (s): 0.42 | learning rate: 2.916E-05 | global batch size: 256 | lm loss: 2.962971E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.473 | TFLOPs: 31.93 | +7: iteration 12280/ 14324 | consumed samples: 3143680 | consumed tokens: 6438256640 | elapsed time per iteration (s): 0.43 | learning rate: 2.907E-05 | global batch size: 256 | lm loss: 2.943555E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.555 | TFLOPs: 31.56 | +7: iteration 12290/ 14324 | consumed samples: 3146240 | consumed tokens: 6443499520 | elapsed time per iteration (s): 0.42 | learning rate: 2.899E-05 | global batch size: 256 | lm loss: 2.940317E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.611 | TFLOPs: 31.83 | +7: iteration 12300/ 14324 | consumed samples: 3148800 | consumed tokens: 6448742400 | elapsed time per iteration (s): 0.43 | learning rate: 2.890E-05 | global batch size: 256 | lm loss: 2.939704E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.219 | TFLOPs: 31.18 | +7: iteration 12310/ 14324 | consumed samples: 3151360 | consumed tokens: 6453985280 | elapsed time per iteration (s): 0.42 | learning rate: 2.881E-05 | global batch size: 256 | lm loss: 2.936632E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.903 | TFLOPs: 31.69 | +7: iteration 12320/ 14324 | consumed samples: 3153920 | consumed tokens: 6459228160 | elapsed time per iteration (s): 0.42 | learning rate: 2.873E-05 | global batch size: 256 | lm loss: 2.951670E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.697 | TFLOPs: 31.99 | +7: iteration 12330/ 14324 | consumed samples: 3156480 | consumed tokens: 6464471040 | elapsed time per iteration (s): 0.43 | learning rate: 2.864E-05 | global batch size: 256 | lm loss: 2.933920E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.561 | TFLOPs: 31.14 | +7: iteration 12340/ 14324 | consumed samples: 3159040 | consumed tokens: 6469713920 | elapsed time per iteration (s): 0.42 | learning rate: 2.856E-05 | global batch size: 256 | lm loss: 2.922142E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.504 | TFLOPs: 31.87 | +7: iteration 12350/ 14324 | consumed samples: 3161600 | consumed tokens: 6474956800 | elapsed time per iteration (s): 0.43 | learning rate: 2.847E-05 | global batch size: 256 | lm loss: 2.947509E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.011 | TFLOPs: 31.43 | +7: iteration 12360/ 14324 | consumed samples: 3164160 | consumed tokens: 6480199680 | elapsed time per iteration (s): 0.44 | learning rate: 2.839E-05 | global batch size: 256 | lm loss: 2.951586E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 583.822 | TFLOPs: 30.63 | +7: iteration 12370/ 14324 | consumed samples: 3166720 | consumed tokens: 6485442560 | elapsed time per iteration (s): 0.43 | learning rate: 2.830E-05 | global batch size: 256 | lm loss: 2.946788E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.505 | TFLOPs: 31.19 | +7: iteration 12380/ 14324 | consumed samples: 3169280 | consumed tokens: 6490685440 | elapsed time per iteration (s): 0.44 | learning rate: 2.822E-05 | global batch size: 256 | lm loss: 2.932215E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 581.607 | TFLOPs: 30.52 | +7: iteration 12390/ 14324 | consumed samples: 3171840 | consumed tokens: 6495928320 | elapsed time per iteration (s): 0.43 | learning rate: 2.814E-05 | global batch size: 256 | lm loss: 2.918263E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.562 | TFLOPs: 31.46 | +7: iteration 12400/ 14324 | consumed samples: 3174400 | consumed tokens: 6501171200 | elapsed time per iteration (s): 0.44 | learning rate: 2.805E-05 | global batch size: 256 | lm loss: 2.975998E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 582.572 | TFLOPs: 30.57 | +7: iteration 12410/ 14324 | consumed samples: 3176960 | consumed tokens: 6506414080 | elapsed time per iteration (s): 0.42 | learning rate: 2.797E-05 | global batch size: 256 | lm loss: 2.950467E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.455 | TFLOPs: 31.77 | +7: iteration 12420/ 14324 | consumed samples: 3179520 | consumed tokens: 6511656960 | elapsed time per iteration (s): 0.43 | learning rate: 2.789E-05 | global batch size: 256 | lm loss: 2.943436E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.135 | TFLOPs: 31.59 | +7: iteration 12430/ 14324 | consumed samples: 3182080 | consumed tokens: 6516899840 | elapsed time per iteration (s): 0.45 | learning rate: 2.781E-05 | global batch size: 256 | lm loss: 2.950958E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 571.172 | TFLOPs: 29.97 | +7: iteration 12440/ 14324 | consumed samples: 3184640 | consumed tokens: 6522142720 | elapsed time per iteration (s): 0.43 | learning rate: 2.773E-05 | global batch size: 256 | lm loss: 2.945851E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.574 | TFLOPs: 31.35 | +7: iteration 12450/ 14324 | consumed samples: 3187200 | consumed tokens: 6527385600 | elapsed time per iteration (s): 0.42 | learning rate: 2.765E-05 | global batch size: 256 | lm loss: 2.944384E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.332 | TFLOPs: 32.08 | +7: iteration 12460/ 14324 | consumed samples: 3189760 | consumed tokens: 6532628480 | elapsed time per iteration (s): 0.42 | learning rate: 2.757E-05 | global batch size: 256 | lm loss: 2.951977E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.010 | TFLOPs: 31.74 | +7: iteration 12470/ 14324 | consumed samples: 3192320 | consumed tokens: 6537871360 | elapsed time per iteration (s): 0.42 | learning rate: 2.749E-05 | global batch size: 256 | lm loss: 2.941858E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.201 | TFLOPs: 31.91 | +7: iteration 12480/ 14324 | consumed samples: 3194880 | consumed tokens: 6543114240 | elapsed time per iteration (s): 0.42 | learning rate: 2.741E-05 | global batch size: 256 | lm loss: 2.955655E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.075 | TFLOPs: 32.06 | +7: iteration 12490/ 14324 | consumed samples: 3197440 | consumed tokens: 6548357120 | elapsed time per iteration (s): 0.44 | learning rate: 2.733E-05 | global batch size: 256 | lm loss: 2.929358E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 584.409 | TFLOPs: 30.66 | +7: iteration 12500/ 14324 | consumed samples: 3200000 | consumed tokens: 6553600000 | elapsed time per iteration (s): 0.44 | learning rate: 2.725E-05 | global batch size: 256 | lm loss: 2.922373E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 584.447 | TFLOPs: 30.66 | +7: iteration 12510/ 14324 | consumed samples: 3202560 | consumed tokens: 6558842880 | elapsed time per iteration (s): 0.43 | learning rate: 2.717E-05 | global batch size: 256 | lm loss: 2.926508E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 590.113 | TFLOPs: 30.96 | +7: iteration 12520/ 14324 | consumed samples: 3205120 | consumed tokens: 6564085760 | elapsed time per iteration (s): 0.44 | learning rate: 2.709E-05 | global batch size: 256 | lm loss: 2.945577E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 576.823 | TFLOPs: 30.26 | +7: iteration 12530/ 14324 | consumed samples: 3207680 | consumed tokens: 6569328640 | elapsed time per iteration (s): 0.43 | learning rate: 2.702E-05 | global batch size: 256 | lm loss: 2.936161E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.277 | TFLOPs: 31.60 | +7: iteration 12540/ 14324 | consumed samples: 3210240 | consumed tokens: 6574571520 | elapsed time per iteration (s): 0.42 | learning rate: 2.694E-05 | global batch size: 256 | lm loss: 2.936613E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.734 | TFLOPs: 31.68 | +7: iteration 12550/ 14324 | consumed samples: 3212800 | consumed tokens: 6579814400 | elapsed time per iteration (s): 0.42 | learning rate: 2.686E-05 | global batch size: 256 | lm loss: 2.920664E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.714 | TFLOPs: 31.73 | +7: iteration 12560/ 14324 | consumed samples: 3215360 | consumed tokens: 6585057280 | elapsed time per iteration (s): 0.42 | learning rate: 2.679E-05 | global batch size: 256 | lm loss: 2.951000E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.579 | TFLOPs: 31.93 | +7: iteration 12570/ 14324 | consumed samples: 3217920 | consumed tokens: 6590300160 | elapsed time per iteration (s): 0.42 | learning rate: 2.671E-05 | global batch size: 256 | lm loss: 2.957055E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.021 | TFLOPs: 31.80 | +7: iteration 12580/ 14324 | consumed samples: 3220480 | consumed tokens: 6595543040 | elapsed time per iteration (s): 0.42 | learning rate: 2.664E-05 | global batch size: 256 | lm loss: 2.945057E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.970 | TFLOPs: 32.11 | +7: iteration 12590/ 14324 | consumed samples: 3223040 | consumed tokens: 6600785920 | elapsed time per iteration (s): 0.44 | learning rate: 2.656E-05 | global batch size: 256 | lm loss: 2.947194E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 588.156 | TFLOPs: 30.86 | +7: iteration 12600/ 14324 | consumed samples: 3225600 | consumed tokens: 6606028800 | elapsed time per iteration (s): 0.43 | learning rate: 2.649E-05 | global batch size: 256 | lm loss: 2.936209E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.923 | TFLOPs: 31.11 | +7: iteration 12610/ 14324 | consumed samples: 3228160 | consumed tokens: 6611271680 | elapsed time per iteration (s): 0.43 | learning rate: 2.641E-05 | global batch size: 256 | lm loss: 2.924619E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.069 | TFLOPs: 31.48 | +7: iteration 12620/ 14324 | consumed samples: 3230720 | consumed tokens: 6616514560 | elapsed time per iteration (s): 0.42 | learning rate: 2.634E-05 | global batch size: 256 | lm loss: 2.920010E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.279 | TFLOPs: 31.71 | +7: iteration 12630/ 14324 | consumed samples: 3233280 | consumed tokens: 6621757440 | elapsed time per iteration (s): 0.42 | learning rate: 2.626E-05 | global batch size: 256 | lm loss: 2.926886E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.651 | TFLOPs: 31.83 | +7: iteration 12640/ 14324 | consumed samples: 3235840 | consumed tokens: 6627000320 | elapsed time per iteration (s): 0.42 | learning rate: 2.619E-05 | global batch size: 256 | lm loss: 2.934097E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.080 | TFLOPs: 31.80 | +7: iteration 12650/ 14324 | consumed samples: 3238400 | consumed tokens: 6632243200 | elapsed time per iteration (s): 0.42 | learning rate: 2.612E-05 | global batch size: 256 | lm loss: 2.923907E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.215 | TFLOPs: 31.70 | +7: iteration 12660/ 14324 | consumed samples: 3240960 | consumed tokens: 6637486080 | elapsed time per iteration (s): 0.45 | learning rate: 2.605E-05 | global batch size: 256 | lm loss: 2.918577E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 573.293 | TFLOPs: 30.08 | +7: iteration 12670/ 14324 | consumed samples: 3243520 | consumed tokens: 6642728960 | elapsed time per iteration (s): 0.44 | learning rate: 2.598E-05 | global batch size: 256 | lm loss: 2.924800E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 578.769 | TFLOPs: 30.37 | +7: iteration 12680/ 14324 | consumed samples: 3246080 | consumed tokens: 6647971840 | elapsed time per iteration (s): 0.42 | learning rate: 2.590E-05 | global batch size: 256 | lm loss: 2.915295E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.009 | TFLOPs: 31.85 | +7: iteration 12690/ 14324 | consumed samples: 3248640 | consumed tokens: 6653214720 | elapsed time per iteration (s): 0.43 | learning rate: 2.583E-05 | global batch size: 256 | lm loss: 2.940659E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.677 | TFLOPs: 31.41 | +7: iteration 12700/ 14324 | consumed samples: 3251200 | consumed tokens: 6658457600 | elapsed time per iteration (s): 0.43 | learning rate: 2.576E-05 | global batch size: 256 | lm loss: 2.919144E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 597.748 | TFLOPs: 31.36 | +7: iteration 12710/ 14324 | consumed samples: 3253760 | consumed tokens: 6663700480 | elapsed time per iteration (s): 0.42 | learning rate: 2.569E-05 | global batch size: 256 | lm loss: 2.934486E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.316 | TFLOPs: 31.81 | +7: iteration 12720/ 14324 | consumed samples: 3256320 | consumed tokens: 6668943360 | elapsed time per iteration (s): 0.44 | learning rate: 2.562E-05 | global batch size: 256 | lm loss: 2.926636E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 586.571 | TFLOPs: 30.78 | +7: iteration 12730/ 14324 | consumed samples: 3258880 | consumed tokens: 6674186240 | elapsed time per iteration (s): 0.42 | learning rate: 2.555E-05 | global batch size: 256 | lm loss: 2.935342E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.988 | TFLOPs: 31.74 | +7: iteration 12740/ 14324 | consumed samples: 3261440 | consumed tokens: 6679429120 | elapsed time per iteration (s): 0.42 | learning rate: 2.549E-05 | global batch size: 256 | lm loss: 2.953873E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.434 | TFLOPs: 32.08 | +7: iteration 12750/ 14324 | consumed samples: 3264000 | consumed tokens: 6684672000 | elapsed time per iteration (s): 0.42 | learning rate: 2.542E-05 | global batch size: 256 | lm loss: 2.943516E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.219 | TFLOPs: 31.81 | +7: iteration 12760/ 14324 | consumed samples: 3266560 | consumed tokens: 6689914880 | elapsed time per iteration (s): 0.42 | learning rate: 2.535E-05 | global batch size: 256 | lm loss: 2.914801E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.288 | TFLOPs: 32.07 | +7: iteration 12770/ 14324 | consumed samples: 3269120 | consumed tokens: 6695157760 | elapsed time per iteration (s): 0.42 | learning rate: 2.528E-05 | global batch size: 256 | lm loss: 2.930993E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.665 | TFLOPs: 31.62 | +7: iteration 12780/ 14324 | consumed samples: 3271680 | consumed tokens: 6700400640 | elapsed time per iteration (s): 0.42 | learning rate: 2.522E-05 | global batch size: 256 | lm loss: 2.931244E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.485 | TFLOPs: 31.82 | +7: iteration 12790/ 14324 | consumed samples: 3274240 | consumed tokens: 6705643520 | elapsed time per iteration (s): 0.43 | learning rate: 2.515E-05 | global batch size: 256 | lm loss: 2.962565E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.111 | TFLOPs: 31.49 | +7: iteration 12800/ 14324 | consumed samples: 3276800 | consumed tokens: 6710886400 | elapsed time per iteration (s): 0.42 | learning rate: 2.508E-05 | global batch size: 256 | lm loss: 2.927681E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.820 | TFLOPs: 31.73 | +7: iteration 12810/ 14324 | consumed samples: 3279360 | consumed tokens: 6716129280 | elapsed time per iteration (s): 0.43 | learning rate: 2.502E-05 | global batch size: 256 | lm loss: 2.925678E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.961 | TFLOPs: 31.32 | +7: iteration 12820/ 14324 | consumed samples: 3281920 | consumed tokens: 6721372160 | elapsed time per iteration (s): 0.43 | learning rate: 2.495E-05 | global batch size: 256 | lm loss: 2.904156E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.258 | TFLOPs: 31.60 | +7: iteration 12830/ 14324 | consumed samples: 3284480 | consumed tokens: 6726615040 | elapsed time per iteration (s): 0.43 | learning rate: 2.489E-05 | global batch size: 256 | lm loss: 2.893895E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.051 | TFLOPs: 31.54 | +7: iteration 12840/ 14324 | consumed samples: 3287040 | consumed tokens: 6731857920 | elapsed time per iteration (s): 0.43 | learning rate: 2.482E-05 | global batch size: 256 | lm loss: 2.933097E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.053 | TFLOPs: 31.01 | +7: iteration 12850/ 14324 | consumed samples: 3289600 | consumed tokens: 6737100800 | elapsed time per iteration (s): 0.42 | learning rate: 2.476E-05 | global batch size: 256 | lm loss: 2.926212E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.699 | TFLOPs: 31.68 | +7: iteration 12860/ 14324 | consumed samples: 3292160 | consumed tokens: 6742343680 | elapsed time per iteration (s): 0.43 | learning rate: 2.469E-05 | global batch size: 256 | lm loss: 2.920928E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.146 | TFLOPs: 31.12 | +7: iteration 12870/ 14324 | consumed samples: 3294720 | consumed tokens: 6747586560 | elapsed time per iteration (s): 0.42 | learning rate: 2.463E-05 | global batch size: 256 | lm loss: 2.936716E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.511 | TFLOPs: 31.72 | +7: iteration 12880/ 14324 | consumed samples: 3297280 | consumed tokens: 6752829440 | elapsed time per iteration (s): 0.42 | learning rate: 2.457E-05 | global batch size: 256 | lm loss: 2.924611E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.760 | TFLOPs: 32.10 | +7: iteration 12890/ 14324 | consumed samples: 3299840 | consumed tokens: 6758072320 | elapsed time per iteration (s): 0.43 | learning rate: 2.450E-05 | global batch size: 256 | lm loss: 2.907119E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 590.801 | TFLOPs: 31.00 | +7: iteration 12900/ 14324 | consumed samples: 3302400 | consumed tokens: 6763315200 | elapsed time per iteration (s): 0.42 | learning rate: 2.444E-05 | global batch size: 256 | lm loss: 2.946513E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.386 | TFLOPs: 32.08 | +7: iteration 12910/ 14324 | consumed samples: 3304960 | consumed tokens: 6768558080 | elapsed time per iteration (s): 0.42 | learning rate: 2.438E-05 | global batch size: 256 | lm loss: 2.924133E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.899 | TFLOPs: 31.74 | +7: iteration 12920/ 14324 | consumed samples: 3307520 | consumed tokens: 6773800960 | elapsed time per iteration (s): 0.42 | learning rate: 2.432E-05 | global batch size: 256 | lm loss: 2.926297E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.754 | TFLOPs: 31.68 | +7: iteration 12930/ 14324 | consumed samples: 3310080 | consumed tokens: 6779043840 | elapsed time per iteration (s): 0.42 | learning rate: 2.426E-05 | global batch size: 256 | lm loss: 2.925506E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.223 | TFLOPs: 31.91 | +7: iteration 12940/ 14324 | consumed samples: 3312640 | consumed tokens: 6784286720 | elapsed time per iteration (s): 0.45 | learning rate: 2.420E-05 | global batch size: 256 | lm loss: 2.943053E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 563.420 | TFLOPs: 29.56 | +7: iteration 12950/ 14324 | consumed samples: 3315200 | consumed tokens: 6789529600 | elapsed time per iteration (s): 0.42 | learning rate: 2.414E-05 | global batch size: 256 | lm loss: 2.937198E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.282 | TFLOPs: 31.97 | +7: iteration 12960/ 14324 | consumed samples: 3317760 | consumed tokens: 6794772480 | elapsed time per iteration (s): 0.45 | learning rate: 2.408E-05 | global batch size: 256 | lm loss: 2.948057E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 570.841 | TFLOPs: 29.95 | +7: iteration 12970/ 14324 | consumed samples: 3320320 | consumed tokens: 6800015360 | elapsed time per iteration (s): 0.42 | learning rate: 2.402E-05 | global batch size: 256 | lm loss: 2.938955E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.399 | TFLOPs: 31.71 | +7: iteration 12980/ 14324 | consumed samples: 3322880 | consumed tokens: 6805258240 | elapsed time per iteration (s): 0.43 | learning rate: 2.396E-05 | global batch size: 256 | lm loss: 2.937659E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.889 | TFLOPs: 31.06 | +7: iteration 12990/ 14324 | consumed samples: 3325440 | consumed tokens: 6810501120 | elapsed time per iteration (s): 0.43 | learning rate: 2.390E-05 | global batch size: 256 | lm loss: 2.914632E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.674 | TFLOPs: 31.15 | +7: iteration 13000/ 14324 | consumed samples: 3328000 | consumed tokens: 6815744000 | elapsed time per iteration (s): 0.43 | learning rate: 2.384E-05 | global batch size: 256 | lm loss: 2.930290E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.935 | TFLOPs: 31.27 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 13000 | lm loss value: 2.887346E+00 | lm loss PPL: 1.794562E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 13000 to checkpoints_220moscar +0: [2022-11-29 23:33:10,648] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step13000 is begin to save! +0: [2022-11-29 23:33:10,652] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/layer_01-model_00-model_states.pt... +0: [2022-11-29 23:33:10,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/layer_01-model_00-model_states.pt. +0: [2022-11-29 23:33:10,756] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/layer_03-model_00-model_states.pt... +0: [2022-11-29 23:33:10,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/layer_03-model_00-model_states.pt. +0: [2022-11-29 23:33:10,777] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/layer_04-model_00-model_states.pt... +0: [2022-11-29 23:33:10,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/layer_04-model_00-model_states.pt. +0: [2022-11-29 23:33:10,800] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/layer_05-model_00-model_states.pt... +0: [2022-11-29 23:33:10,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/layer_05-model_00-model_states.pt. +0: [2022-11-29 23:33:10,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/layer_06-model_00-model_states.pt... +0: [2022-11-29 23:33:10,846] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/layer_06-model_00-model_states.pt. +0: [2022-11-29 23:33:10,846] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/layer_07-model_00-model_states.pt... +0: [2022-11-29 23:33:10,869] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/layer_07-model_00-model_states.pt. +0: [2022-11-29 23:33:10,869] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/layer_08-model_00-model_states.pt... +0: [2022-11-29 23:33:10,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/layer_08-model_00-model_states.pt. +0: [2022-11-29 23:33:10,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/layer_09-model_00-model_states.pt... +0: [2022-11-29 23:33:10,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/layer_09-model_00-model_states.pt. +0: [2022-11-29 23:33:10,918] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/layer_10-model_00-model_states.pt... +0: [2022-11-29 23:33:10,941] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/layer_10-model_00-model_states.pt. +0: [2022-11-29 23:33:10,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/layer_11-model_00-model_states.pt... +0: [2022-11-29 23:33:10,964] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/layer_11-model_00-model_states.pt. +0: [2022-11-29 23:33:10,964] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/layer_12-model_00-model_states.pt... +0: [2022-11-29 23:33:10,988] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/layer_12-model_00-model_states.pt. +0: [2022-11-29 23:33:10,988] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/layer_13-model_00-model_states.pt... +0: [2022-11-29 23:33:11,011] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/layer_13-model_00-model_states.pt. +0: [2022-11-29 23:33:11,011] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/layer_14-model_00-model_states.pt... +0: [2022-11-29 23:33:11,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/layer_14-model_00-model_states.pt. +0: [2022-11-29 23:33:11,033] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/layer_15-model_00-model_states.pt... +0: [2022-11-29 23:33:11,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/layer_15-model_00-model_states.pt. +0: [2022-11-29 23:33:11,057] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/layer_16-model_00-model_states.pt... +0: [2022-11-29 23:33:11,079] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/layer_16-model_00-model_states.pt. +0: [2022-11-29 23:33:11,080] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/layer_17-model_00-model_states.pt... +0: [2022-11-29 23:33:11,103] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/layer_17-model_00-model_states.pt. +0: [2022-11-29 23:33:11,103] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/layer_18-model_00-model_states.pt... +0: [2022-11-29 23:33:11,126] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/layer_18-model_00-model_states.pt. +0: [2022-11-29 23:33:11,126] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/layer_19-model_00-model_states.pt... +0: [2022-11-29 23:33:11,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/layer_19-model_00-model_states.pt. +0: [2022-11-29 23:33:11,149] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/layer_20-model_00-model_states.pt... +0: [2022-11-29 23:33:11,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/layer_20-model_00-model_states.pt. +0: [2022-11-29 23:33:11,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/layer_22-model_00-model_states.pt... +0: [2022-11-29 23:33:11,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/layer_22-model_00-model_states.pt. +0: [2022-11-29 23:33:11,179] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_220moscar/global_step13000/mp_rank_00_model_states.pt +0: [2022-11-29 23:33:11,179] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/mp_rank_00_model_states.pt... +0: [2022-11-29 23:33:11,181] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/mp_rank_00_model_states.pt. +0: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:33:11,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:33:11,244] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:33:11,245] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:33:11,246] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 23:33:11,246] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 23:33:11,246] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:33:11,246] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 23:33:11,246] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +6: [2022-11-29 23:33:11,246] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:33:11,247] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 23:33:11,247] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 23:33:11,244] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 23:33:11,244] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 23:33:11,246] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:33:11,246] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 23:33:11,246] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 23:33:11,247] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:33:11,247] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 23:33:11,247] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +6: [2022-11-29 23:33:11,247] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:33:11,247] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 23:33:11,247] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +3: [2022-11-29 23:33:11,247] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:33:11,247] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 23:33:11,247] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +6: [2022-11-29 23:33:11,248] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:33:11,248] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 23:33:11,248] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 23:33:11,249] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:33:11,249] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 23:33:11,249] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 23:33:11,249] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:33:11,249] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 23:33:11,249] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 23:33:11,249] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:33:11,250] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 23:33:11,250] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +6: [2022-11-29 23:33:11,250] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:33:11,250] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 23:33:11,250] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +6: [2022-11-29 23:33:11,250] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:33:11,250] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:33:11,250] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 23:33:11,250] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 23:33:11,250] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 23:33:11,250] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +3: [2022-11-29 23:33:11,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:33:11,251] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 23:33:11,251] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 23:33:11,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:33:11,251] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 23:33:11,251] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +3: [2022-11-29 23:33:11,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:33:11,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:33:11,251] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 23:33:11,251] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 23:33:11,252] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +3: [2022-11-29 23:33:11,252] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +3: [2022-11-29 23:33:11,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:33:11,252] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 23:33:11,252] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 23:33:11,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:33:11,253] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 23:33:11,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:33:11,253] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 23:33:11,253] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 23:33:11,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:33:11,253] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 23:33:11,253] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +6: [2022-11-29 23:33:11,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:33:11,254] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +6: [2022-11-29 23:33:11,254] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 23:33:11,254] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +6: [2022-11-29 23:33:11,254] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:33:11,254] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 23:33:11,254] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 23:33:11,254] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:33:11,254] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:33:11,254] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 23:33:11,254] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 23:33:11,255] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:33:11,255] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 23:33:11,255] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 23:33:11,255] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:33:11,255] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 23:33:11,255] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +3: [2022-11-29 23:33:11,255] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:33:11,255] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 23:33:11,255] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 23:33:11,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:33:11,256] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 23:33:11,256] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 23:33:11,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:33:11,256] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 23:33:11,256] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 23:33:11,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:33:11,257] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 23:33:11,257] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +6: [2022-11-29 23:33:11,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:33:11,257] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 23:33:11,257] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 23:33:11,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:33:11,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 23:33:11,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 23:33:11,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:33:11,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:33:11,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:33:11,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:33:11,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +7: [2022-11-29 23:33:11,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 23:33:11,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +2: [2022-11-29 23:33:11,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +7: [2022-11-29 23:33:11,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 23:33:11,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 23:33:11,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 23:33:11,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 23:33:11,254] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:33:11,254] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 23:33:11,254] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 23:33:11,254] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 23:33:11,254] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 23:33:11,255] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:33:11,255] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 23:33:11,255] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 23:33:11,255] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:33:11,255] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 23:33:11,255] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 23:33:11,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:33:11,259] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 23:33:11,259] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +3: [2022-11-29 23:33:11,259] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:33:11,259] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 23:33:11,259] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +3: [2022-11-29 23:33:11,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:33:11,260] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 23:33:11,260] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 23:33:11,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:33:11,260] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 23:33:11,260] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 23:33:11,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:33:11,261] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 23:33:11,261] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 23:33:11,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:33:11,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 23:33:11,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:33:11,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:33:11,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +1: [2022-11-29 23:33:11,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 23:33:11,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +0: [2022-11-29 23:33:11,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 23:33:11,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: [2022-11-29 23:33:11,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:33:11,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 23:33:11,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 23:33:11,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:33:11,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:33:11,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +0: [2022-11-29 23:33:11,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +1: [2022-11-29 23:33:11,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: [2022-11-29 23:33:11,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 23:33:11,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:33:11,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:33:11,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:33:11,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:33:11,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 23:33:11,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 23:33:11,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 23:33:11,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 23:33:11,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 23:33:11,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 23:33:11,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 23:33:11,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: [2022-11-29 23:33:11,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:33:11,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 23:33:11,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 23:33:11,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:33:11,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 23:33:11,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: [2022-11-29 23:33:11,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:33:11,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 23:33:11,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 23:33:11,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:33:11,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 23:33:11,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: [2022-11-29 23:33:11,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:33:11,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:33:11,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 23:33:11,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 23:33:11,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: [2022-11-29 23:33:11,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: [2022-11-29 23:33:11,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:33:11,316] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step13000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 23:33:11,316] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: successfully saved checkpoint at iteration 13000 to checkpoints_220moscar +7: time (ms) | save-checkpoint: 673.44 +7: iteration 13010/ 14324 | consumed samples: 3330560 | consumed tokens: 6820986880 | elapsed time per iteration (s): 0.50 | learning rate: 2.379E-05 | global batch size: 256 | lm loss: 2.928469E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 513.709 | TFLOPs: 26.95 | +7: iteration 13020/ 14324 | consumed samples: 3333120 | consumed tokens: 6826229760 | elapsed time per iteration (s): 0.42 | learning rate: 2.373E-05 | global batch size: 256 | lm loss: 2.941930E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.455 | TFLOPs: 31.77 | +7: iteration 13030/ 14324 | consumed samples: 3335680 | consumed tokens: 6831472640 | elapsed time per iteration (s): 0.42 | learning rate: 2.367E-05 | global batch size: 256 | lm loss: 2.942564E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.332 | TFLOPs: 31.87 | +7: iteration 13040/ 14324 | consumed samples: 3338240 | consumed tokens: 6836715520 | elapsed time per iteration (s): 0.42 | learning rate: 2.362E-05 | global batch size: 256 | lm loss: 2.918880E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.358 | TFLOPs: 31.92 | +7: iteration 13050/ 14324 | consumed samples: 3340800 | consumed tokens: 6841958400 | elapsed time per iteration (s): 0.43 | learning rate: 2.356E-05 | global batch size: 256 | lm loss: 2.910979E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.206 | TFLOPs: 31.54 | +7: iteration 13060/ 14324 | consumed samples: 3343360 | consumed tokens: 6847201280 | elapsed time per iteration (s): 0.42 | learning rate: 2.351E-05 | global batch size: 256 | lm loss: 2.952824E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.586 | TFLOPs: 31.77 | +7: iteration 13070/ 14324 | consumed samples: 3345920 | consumed tokens: 6852444160 | elapsed time per iteration (s): 0.42 | learning rate: 2.345E-05 | global batch size: 256 | lm loss: 2.904351E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.181 | TFLOPs: 31.86 | +7: iteration 13080/ 14324 | consumed samples: 3348480 | consumed tokens: 6857687040 | elapsed time per iteration (s): 0.43 | learning rate: 2.340E-05 | global batch size: 256 | lm loss: 2.947685E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.745 | TFLOPs: 31.57 | +7: iteration 13090/ 14324 | consumed samples: 3351040 | consumed tokens: 6862929920 | elapsed time per iteration (s): 0.44 | learning rate: 2.334E-05 | global batch size: 256 | lm loss: 2.955192E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 585.520 | TFLOPs: 30.72 | +7: iteration 13100/ 14324 | consumed samples: 3353600 | consumed tokens: 6868172800 | elapsed time per iteration (s): 0.43 | learning rate: 2.329E-05 | global batch size: 256 | lm loss: 2.963472E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 589.249 | TFLOPs: 30.92 | +7: iteration 13110/ 14324 | consumed samples: 3356160 | consumed tokens: 6873415680 | elapsed time per iteration (s): 0.42 | learning rate: 2.324E-05 | global batch size: 256 | lm loss: 2.904518E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.145 | TFLOPs: 31.70 | +7: iteration 13120/ 14324 | consumed samples: 3358720 | consumed tokens: 6878658560 | elapsed time per iteration (s): 0.43 | learning rate: 2.318E-05 | global batch size: 256 | lm loss: 2.920759E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.055 | TFLOPs: 31.17 | +7: iteration 13130/ 14324 | consumed samples: 3361280 | consumed tokens: 6883901440 | elapsed time per iteration (s): 0.42 | learning rate: 2.313E-05 | global batch size: 256 | lm loss: 2.925327E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.772 | TFLOPs: 31.78 | +7: iteration 13140/ 14324 | consumed samples: 3363840 | consumed tokens: 6889144320 | elapsed time per iteration (s): 0.43 | learning rate: 2.308E-05 | global batch size: 256 | lm loss: 2.928693E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 588.603 | TFLOPs: 30.88 | +7: iteration 13150/ 14324 | consumed samples: 3366400 | consumed tokens: 6894387200 | elapsed time per iteration (s): 0.43 | learning rate: 2.303E-05 | global batch size: 256 | lm loss: 2.944343E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.308 | TFLOPs: 31.02 | +7: iteration 13160/ 14324 | consumed samples: 3368960 | consumed tokens: 6899630080 | elapsed time per iteration (s): 0.43 | learning rate: 2.298E-05 | global batch size: 256 | lm loss: 2.939494E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 593.491 | TFLOPs: 31.14 | +7: iteration 13170/ 14324 | consumed samples: 3371520 | consumed tokens: 6904872960 | elapsed time per iteration (s): 0.43 | learning rate: 2.293E-05 | global batch size: 256 | lm loss: 2.950021E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 590.677 | TFLOPs: 30.99 | +7: iteration 13180/ 14324 | consumed samples: 3374080 | consumed tokens: 6910115840 | elapsed time per iteration (s): 0.42 | learning rate: 2.288E-05 | global batch size: 256 | lm loss: 2.933508E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.670 | TFLOPs: 31.94 | +7: iteration 13190/ 14324 | consumed samples: 3376640 | consumed tokens: 6915358720 | elapsed time per iteration (s): 0.42 | learning rate: 2.283E-05 | global batch size: 256 | lm loss: 2.928442E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.654 | TFLOPs: 31.88 | +7: iteration 13200/ 14324 | consumed samples: 3379200 | consumed tokens: 6920601600 | elapsed time per iteration (s): 0.42 | learning rate: 2.278E-05 | global batch size: 256 | lm loss: 2.935106E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.839 | TFLOPs: 31.79 | +7: iteration 13210/ 14324 | consumed samples: 3381760 | consumed tokens: 6925844480 | elapsed time per iteration (s): 0.42 | learning rate: 2.273E-05 | global batch size: 256 | lm loss: 2.927901E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.631 | TFLOPs: 31.83 | +7: iteration 13220/ 14324 | consumed samples: 3384320 | consumed tokens: 6931087360 | elapsed time per iteration (s): 0.45 | learning rate: 2.268E-05 | global batch size: 256 | lm loss: 2.911977E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 568.916 | TFLOPs: 29.85 | +7: iteration 13230/ 14324 | consumed samples: 3386880 | consumed tokens: 6936330240 | elapsed time per iteration (s): 0.43 | learning rate: 2.263E-05 | global batch size: 256 | lm loss: 2.903421E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.886 | TFLOPs: 31.53 | +7: iteration 13240/ 14324 | consumed samples: 3389440 | consumed tokens: 6941573120 | elapsed time per iteration (s): 0.43 | learning rate: 2.258E-05 | global batch size: 256 | lm loss: 2.918479E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.649 | TFLOPs: 31.46 | +7: iteration 13250/ 14324 | consumed samples: 3392000 | consumed tokens: 6946816000 | elapsed time per iteration (s): 0.42 | learning rate: 2.254E-05 | global batch size: 256 | lm loss: 2.954408E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.110 | TFLOPs: 31.75 | +7: iteration 13260/ 14324 | consumed samples: 3394560 | consumed tokens: 6952058880 | elapsed time per iteration (s): 0.44 | learning rate: 2.249E-05 | global batch size: 256 | lm loss: 2.914378E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 578.889 | TFLOPs: 30.37 | +7: iteration 13270/ 14324 | consumed samples: 3397120 | consumed tokens: 6957301760 | elapsed time per iteration (s): 0.43 | learning rate: 2.244E-05 | global batch size: 256 | lm loss: 2.943221E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 592.222 | TFLOPs: 31.07 | +7: iteration 13280/ 14324 | consumed samples: 3399680 | consumed tokens: 6962544640 | elapsed time per iteration (s): 0.42 | learning rate: 2.240E-05 | global batch size: 256 | lm loss: 2.939942E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.823 | TFLOPs: 31.84 | +7: iteration 13290/ 14324 | consumed samples: 3402240 | consumed tokens: 6967787520 | elapsed time per iteration (s): 0.42 | learning rate: 2.235E-05 | global batch size: 256 | lm loss: 2.927115E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.994 | TFLOPs: 31.69 | +7: iteration 13300/ 14324 | consumed samples: 3404800 | consumed tokens: 6973030400 | elapsed time per iteration (s): 0.42 | learning rate: 2.231E-05 | global batch size: 256 | lm loss: 2.924053E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.012 | TFLOPs: 31.69 | +7: iteration 13310/ 14324 | consumed samples: 3407360 | consumed tokens: 6978273280 | elapsed time per iteration (s): 0.43 | learning rate: 2.226E-05 | global batch size: 256 | lm loss: 2.895738E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.431 | TFLOPs: 31.50 | +7: iteration 13320/ 14324 | consumed samples: 3409920 | consumed tokens: 6983516160 | elapsed time per iteration (s): 0.42 | learning rate: 2.222E-05 | global batch size: 256 | lm loss: 2.920852E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.454 | TFLOPs: 31.66 | +7: iteration 13330/ 14324 | consumed samples: 3412480 | consumed tokens: 6988759040 | elapsed time per iteration (s): 0.42 | learning rate: 2.217E-05 | global batch size: 256 | lm loss: 2.951178E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.894 | TFLOPs: 31.90 | +7: iteration 13340/ 14324 | consumed samples: 3415040 | consumed tokens: 6994001920 | elapsed time per iteration (s): 0.43 | learning rate: 2.213E-05 | global batch size: 256 | lm loss: 2.953241E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 595.251 | TFLOPs: 31.23 | +7: iteration 13350/ 14324 | consumed samples: 3417600 | consumed tokens: 6999244800 | elapsed time per iteration (s): 0.44 | learning rate: 2.209E-05 | global batch size: 256 | lm loss: 2.933724E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 587.409 | TFLOPs: 30.82 | +7: iteration 13360/ 14324 | consumed samples: 3420160 | consumed tokens: 7004487680 | elapsed time per iteration (s): 0.42 | learning rate: 2.205E-05 | global batch size: 256 | lm loss: 2.956272E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.149 | TFLOPs: 31.65 | +7: iteration 13370/ 14324 | consumed samples: 3422720 | consumed tokens: 7009730560 | elapsed time per iteration (s): 0.42 | learning rate: 2.200E-05 | global batch size: 256 | lm loss: 2.956753E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.988 | TFLOPs: 32.11 | +7: iteration 13380/ 14324 | consumed samples: 3425280 | consumed tokens: 7014973440 | elapsed time per iteration (s): 0.45 | learning rate: 2.196E-05 | global batch size: 256 | lm loss: 2.947885E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 565.649 | TFLOPs: 29.68 | +7: iteration 13390/ 14324 | consumed samples: 3427840 | consumed tokens: 7020216320 | elapsed time per iteration (s): 0.42 | learning rate: 2.192E-05 | global batch size: 256 | lm loss: 2.934987E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.977 | TFLOPs: 32.06 | +7: iteration 13400/ 14324 | consumed samples: 3430400 | consumed tokens: 7025459200 | elapsed time per iteration (s): 0.42 | learning rate: 2.188E-05 | global batch size: 256 | lm loss: 2.911558E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.498 | TFLOPs: 31.98 | +7: iteration 13410/ 14324 | consumed samples: 3432960 | consumed tokens: 7030702080 | elapsed time per iteration (s): 0.43 | learning rate: 2.184E-05 | global batch size: 256 | lm loss: 2.928505E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.804 | TFLOPs: 31.42 | +7: iteration 13420/ 14324 | consumed samples: 3435520 | consumed tokens: 7035944960 | elapsed time per iteration (s): 0.43 | learning rate: 2.180E-05 | global batch size: 256 | lm loss: 2.922271E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 591.611 | TFLOPs: 31.04 | +7: iteration 13430/ 14324 | consumed samples: 3438080 | consumed tokens: 7041187840 | elapsed time per iteration (s): 0.43 | learning rate: 2.176E-05 | global batch size: 256 | lm loss: 2.936565E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.546 | TFLOPs: 31.30 | +7: iteration 13440/ 14324 | consumed samples: 3440640 | consumed tokens: 7046430720 | elapsed time per iteration (s): 0.44 | learning rate: 2.172E-05 | global batch size: 256 | lm loss: 2.919967E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 586.877 | TFLOPs: 30.79 | +7: iteration 13450/ 14324 | consumed samples: 3443200 | consumed tokens: 7051673600 | elapsed time per iteration (s): 0.42 | learning rate: 2.168E-05 | global batch size: 256 | lm loss: 2.925498E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.807 | TFLOPs: 32.05 | +7: iteration 13460/ 14324 | consumed samples: 3445760 | consumed tokens: 7056916480 | elapsed time per iteration (s): 0.42 | learning rate: 2.164E-05 | global batch size: 256 | lm loss: 2.940224E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.788 | TFLOPs: 32.10 | +7: iteration 13470/ 14324 | consumed samples: 3448320 | consumed tokens: 7062159360 | elapsed time per iteration (s): 0.42 | learning rate: 2.161E-05 | global batch size: 256 | lm loss: 2.917079E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.167 | TFLOPs: 32.12 | +7: iteration 13480/ 14324 | consumed samples: 3450880 | consumed tokens: 7067402240 | elapsed time per iteration (s): 0.42 | learning rate: 2.157E-05 | global batch size: 256 | lm loss: 2.928622E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.794 | TFLOPs: 31.99 | +7: iteration 13490/ 14324 | consumed samples: 3453440 | consumed tokens: 7072645120 | elapsed time per iteration (s): 0.42 | learning rate: 2.153E-05 | global batch size: 256 | lm loss: 2.941368E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.621 | TFLOPs: 31.93 | +7: iteration 13500/ 14324 | consumed samples: 3456000 | consumed tokens: 7077888000 | elapsed time per iteration (s): 0.42 | learning rate: 2.150E-05 | global batch size: 256 | lm loss: 2.925244E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.193 | TFLOPs: 32.02 | +7: iteration 13510/ 14324 | consumed samples: 3458560 | consumed tokens: 7083130880 | elapsed time per iteration (s): 0.42 | learning rate: 2.146E-05 | global batch size: 256 | lm loss: 2.943528E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.885 | TFLOPs: 31.89 | +7: iteration 13520/ 14324 | consumed samples: 3461120 | consumed tokens: 7088373760 | elapsed time per iteration (s): 0.42 | learning rate: 2.142E-05 | global batch size: 256 | lm loss: 2.929094E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.977 | TFLOPs: 31.90 | +7: iteration 13530/ 14324 | consumed samples: 3463680 | consumed tokens: 7093616640 | elapsed time per iteration (s): 0.43 | learning rate: 2.139E-05 | global batch size: 256 | lm loss: 2.901349E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.852 | TFLOPs: 31.47 | +7: iteration 13540/ 14324 | consumed samples: 3466240 | consumed tokens: 7098859520 | elapsed time per iteration (s): 0.42 | learning rate: 2.135E-05 | global batch size: 256 | lm loss: 2.911200E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.883 | TFLOPs: 32.10 | +7: iteration 13550/ 14324 | consumed samples: 3468800 | consumed tokens: 7104102400 | elapsed time per iteration (s): 0.43 | learning rate: 2.132E-05 | global batch size: 256 | lm loss: 2.915185E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 596.958 | TFLOPs: 31.32 | +7: iteration 13560/ 14324 | consumed samples: 3471360 | consumed tokens: 7109345280 | elapsed time per iteration (s): 0.42 | learning rate: 2.129E-05 | global batch size: 256 | lm loss: 2.943394E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.206 | TFLOPs: 32.12 | +7: iteration 13570/ 14324 | consumed samples: 3473920 | consumed tokens: 7114588160 | elapsed time per iteration (s): 0.43 | learning rate: 2.125E-05 | global batch size: 256 | lm loss: 2.936988E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 599.338 | TFLOPs: 31.45 | +7: iteration 13580/ 14324 | consumed samples: 3476480 | consumed tokens: 7119831040 | elapsed time per iteration (s): 0.42 | learning rate: 2.122E-05 | global batch size: 256 | lm loss: 2.936148E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.648 | TFLOPs: 32.14 | +7: iteration 13590/ 14324 | consumed samples: 3479040 | consumed tokens: 7125073920 | elapsed time per iteration (s): 0.43 | learning rate: 2.119E-05 | global batch size: 256 | lm loss: 2.958969E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 601.817 | TFLOPs: 31.58 | +7: iteration 13600/ 14324 | consumed samples: 3481600 | consumed tokens: 7130316800 | elapsed time per iteration (s): 0.42 | learning rate: 2.116E-05 | global batch size: 256 | lm loss: 2.932259E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 613.057 | TFLOPs: 32.17 | +7: iteration 13610/ 14324 | consumed samples: 3484160 | consumed tokens: 7135559680 | elapsed time per iteration (s): 0.42 | learning rate: 2.112E-05 | global batch size: 256 | lm loss: 2.932924E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.792 | TFLOPs: 32.15 | +7: iteration 13620/ 14324 | consumed samples: 3486720 | consumed tokens: 7140802560 | elapsed time per iteration (s): 0.42 | learning rate: 2.109E-05 | global batch size: 256 | lm loss: 2.893748E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.293 | TFLOPs: 32.13 | +7: iteration 13630/ 14324 | consumed samples: 3489280 | consumed tokens: 7146045440 | elapsed time per iteration (s): 0.42 | learning rate: 2.106E-05 | global batch size: 256 | lm loss: 2.957840E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.206 | TFLOPs: 31.70 | +7: iteration 13640/ 14324 | consumed samples: 3491840 | consumed tokens: 7151288320 | elapsed time per iteration (s): 0.42 | learning rate: 2.103E-05 | global batch size: 256 | lm loss: 2.946584E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.303 | TFLOPs: 32.13 | +7: iteration 13650/ 14324 | consumed samples: 3494400 | consumed tokens: 7156531200 | elapsed time per iteration (s): 0.43 | learning rate: 2.100E-05 | global batch size: 256 | lm loss: 2.944176E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.271 | TFLOPs: 31.60 | +7: iteration 13660/ 14324 | consumed samples: 3496960 | consumed tokens: 7161774080 | elapsed time per iteration (s): 0.43 | learning rate: 2.097E-05 | global batch size: 256 | lm loss: 2.948374E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 600.375 | TFLOPs: 31.50 | +7: iteration 13670/ 14324 | consumed samples: 3499520 | consumed tokens: 7167016960 | elapsed time per iteration (s): 0.42 | learning rate: 2.094E-05 | global batch size: 256 | lm loss: 2.921758E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.652 | TFLOPs: 32.09 | +7: iteration 13680/ 14324 | consumed samples: 3502080 | consumed tokens: 7172259840 | elapsed time per iteration (s): 0.42 | learning rate: 2.091E-05 | global batch size: 256 | lm loss: 2.933095E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.421 | TFLOPs: 31.92 | +7: iteration 13690/ 14324 | consumed samples: 3504640 | consumed tokens: 7177502720 | elapsed time per iteration (s): 0.42 | learning rate: 2.089E-05 | global batch size: 256 | lm loss: 2.904503E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.208 | TFLOPs: 32.12 | +7: iteration 13700/ 14324 | consumed samples: 3507200 | consumed tokens: 7182745600 | elapsed time per iteration (s): 0.42 | learning rate: 2.086E-05 | global batch size: 256 | lm loss: 2.919557E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.887 | TFLOPs: 32.10 | +7: iteration 13710/ 14324 | consumed samples: 3509760 | consumed tokens: 7187988480 | elapsed time per iteration (s): 0.42 | learning rate: 2.083E-05 | global batch size: 256 | lm loss: 2.954798E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.672 | TFLOPs: 32.09 | +7: iteration 13720/ 14324 | consumed samples: 3512320 | consumed tokens: 7193231360 | elapsed time per iteration (s): 0.43 | learning rate: 2.081E-05 | global batch size: 256 | lm loss: 2.905770E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.209 | TFLOPs: 31.60 | +7: iteration 13730/ 14324 | consumed samples: 3514880 | consumed tokens: 7198474240 | elapsed time per iteration (s): 0.42 | learning rate: 2.078E-05 | global batch size: 256 | lm loss: 2.940979E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.914 | TFLOPs: 32.11 | +7: iteration 13740/ 14324 | consumed samples: 3517440 | consumed tokens: 7203717120 | elapsed time per iteration (s): 0.42 | learning rate: 2.075E-05 | global batch size: 256 | lm loss: 2.911843E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.733 | TFLOPs: 31.68 | +7: iteration 13750/ 14324 | consumed samples: 3520000 | consumed tokens: 7208960000 | elapsed time per iteration (s): 0.42 | learning rate: 2.073E-05 | global batch size: 256 | lm loss: 2.935234E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.623 | TFLOPs: 32.04 | +7: iteration 13760/ 14324 | consumed samples: 3522560 | consumed tokens: 7214202880 | elapsed time per iteration (s): 0.43 | learning rate: 2.070E-05 | global batch size: 256 | lm loss: 2.912178E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.128 | TFLOPs: 31.59 | +7: iteration 13770/ 14324 | consumed samples: 3525120 | consumed tokens: 7219445760 | elapsed time per iteration (s): 0.42 | learning rate: 2.068E-05 | global batch size: 256 | lm loss: 2.939418E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.934 | TFLOPs: 32.16 | +7: iteration 13780/ 14324 | consumed samples: 3527680 | consumed tokens: 7224688640 | elapsed time per iteration (s): 0.42 | learning rate: 2.065E-05 | global batch size: 256 | lm loss: 2.913724E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 603.239 | TFLOPs: 31.65 | +7: iteration 13790/ 14324 | consumed samples: 3530240 | consumed tokens: 7229931520 | elapsed time per iteration (s): 0.42 | learning rate: 2.063E-05 | global batch size: 256 | lm loss: 2.930502E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.426 | TFLOPs: 32.08 | +7: iteration 13800/ 14324 | consumed samples: 3532800 | consumed tokens: 7235174400 | elapsed time per iteration (s): 0.42 | learning rate: 2.061E-05 | global batch size: 256 | lm loss: 2.917452E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.675 | TFLOPs: 32.09 | +7: iteration 13810/ 14324 | consumed samples: 3535360 | consumed tokens: 7240417280 | elapsed time per iteration (s): 0.43 | learning rate: 2.058E-05 | global batch size: 256 | lm loss: 2.930224E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 588.865 | TFLOPs: 30.90 | +7: iteration 13820/ 14324 | consumed samples: 3537920 | consumed tokens: 7245660160 | elapsed time per iteration (s): 0.42 | learning rate: 2.056E-05 | global batch size: 256 | lm loss: 2.922497E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.161 | TFLOPs: 32.07 | +7: iteration 13830/ 14324 | consumed samples: 3540480 | consumed tokens: 7250903040 | elapsed time per iteration (s): 0.42 | learning rate: 2.054E-05 | global batch size: 256 | lm loss: 2.932594E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.341 | TFLOPs: 31.92 | +7: iteration 13840/ 14324 | consumed samples: 3543040 | consumed tokens: 7256145920 | elapsed time per iteration (s): 0.42 | learning rate: 2.052E-05 | global batch size: 256 | lm loss: 2.919073E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.643 | TFLOPs: 31.88 | +7: iteration 13850/ 14324 | consumed samples: 3545600 | consumed tokens: 7261388800 | elapsed time per iteration (s): 0.42 | learning rate: 2.050E-05 | global batch size: 256 | lm loss: 2.899955E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.049 | TFLOPs: 31.96 | +7: iteration 13860/ 14324 | consumed samples: 3548160 | consumed tokens: 7266631680 | elapsed time per iteration (s): 0.42 | learning rate: 2.048E-05 | global batch size: 256 | lm loss: 2.926166E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 613.035 | TFLOPs: 32.16 | +7: iteration 13870/ 14324 | consumed samples: 3550720 | consumed tokens: 7271874560 | elapsed time per iteration (s): 0.42 | learning rate: 2.046E-05 | global batch size: 256 | lm loss: 2.917636E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.396 | TFLOPs: 32.13 | +7: iteration 13880/ 14324 | consumed samples: 3553280 | consumed tokens: 7277117440 | elapsed time per iteration (s): 0.42 | learning rate: 2.044E-05 | global batch size: 256 | lm loss: 2.907571E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.856 | TFLOPs: 32.05 | +7: iteration 13890/ 14324 | consumed samples: 3555840 | consumed tokens: 7282360320 | elapsed time per iteration (s): 0.42 | learning rate: 2.042E-05 | global batch size: 256 | lm loss: 2.928637E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.131 | TFLOPs: 32.07 | +7: iteration 13900/ 14324 | consumed samples: 3558400 | consumed tokens: 7287603200 | elapsed time per iteration (s): 0.42 | learning rate: 2.040E-05 | global batch size: 256 | lm loss: 2.926067E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.629 | TFLOPs: 32.09 | +7: iteration 13910/ 14324 | consumed samples: 3560960 | consumed tokens: 7292846080 | elapsed time per iteration (s): 0.42 | learning rate: 2.038E-05 | global batch size: 256 | lm loss: 2.911186E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.533 | TFLOPs: 32.14 | +7: iteration 13920/ 14324 | consumed samples: 3563520 | consumed tokens: 7298088960 | elapsed time per iteration (s): 0.42 | learning rate: 2.036E-05 | global batch size: 256 | lm loss: 2.918723E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.033 | TFLOPs: 32.06 | +7: iteration 13930/ 14324 | consumed samples: 3566080 | consumed tokens: 7303331840 | elapsed time per iteration (s): 0.42 | learning rate: 2.034E-05 | global batch size: 256 | lm loss: 2.916365E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.004 | TFLOPs: 31.85 | +7: iteration 13940/ 14324 | consumed samples: 3568640 | consumed tokens: 7308574720 | elapsed time per iteration (s): 0.42 | learning rate: 2.033E-05 | global batch size: 256 | lm loss: 2.917108E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.914 | TFLOPs: 32.11 | +7: iteration 13950/ 14324 | consumed samples: 3571200 | consumed tokens: 7313817600 | elapsed time per iteration (s): 0.42 | learning rate: 2.031E-05 | global batch size: 256 | lm loss: 2.954911E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.201 | TFLOPs: 32.02 | +7: iteration 13960/ 14324 | consumed samples: 3573760 | consumed tokens: 7319060480 | elapsed time per iteration (s): 0.42 | learning rate: 2.029E-05 | global batch size: 256 | lm loss: 2.904364E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.109 | TFLOPs: 31.70 | +7: iteration 13970/ 14324 | consumed samples: 3576320 | consumed tokens: 7324303360 | elapsed time per iteration (s): 0.42 | learning rate: 2.028E-05 | global batch size: 256 | lm loss: 2.939186E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.677 | TFLOPs: 32.09 | +7: iteration 13980/ 14324 | consumed samples: 3578880 | consumed tokens: 7329546240 | elapsed time per iteration (s): 0.42 | learning rate: 2.026E-05 | global batch size: 256 | lm loss: 2.939961E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.026 | TFLOPs: 32.11 | +7: iteration 13990/ 14324 | consumed samples: 3581440 | consumed tokens: 7334789120 | elapsed time per iteration (s): 0.42 | learning rate: 2.025E-05 | global batch size: 256 | lm loss: 2.919561E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.456 | TFLOPs: 31.87 | +0: [2022-11-29 23:40:15,022] [INFO] [logging.py:68:log_dist] [Rank 0] step=14000, skipped=0, lr=[2.0232010554965626e-05, 2.0232010554965626e-05, 2.0232010554965626e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 14000/ 14324 | consumed samples: 3584000 | consumed tokens: 7340032000 | elapsed time per iteration (s): 0.42 | learning rate: 2.023E-05 | global batch size: 256 | lm loss: 2.897883E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.724 | TFLOPs: 32.10 | +0: steps: 14000 loss: 2.9372 iter time (s): 0.424 samples/sec: 604.023 +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 14000 | lm loss value: 2.930006E+00 | lm loss PPL: 1.872774E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 14000 to checkpoints_220moscar +0: [2022-11-29 23:40:15,182] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step14000 is begin to save! +0: [2022-11-29 23:40:15,185] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/layer_01-model_00-model_states.pt... +0: [2022-11-29 23:40:15,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/layer_01-model_00-model_states.pt. +0: [2022-11-29 23:40:15,285] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/layer_03-model_00-model_states.pt... +0: [2022-11-29 23:40:15,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/layer_03-model_00-model_states.pt. +0: [2022-11-29 23:40:15,307] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/layer_04-model_00-model_states.pt... +0: [2022-11-29 23:40:15,329] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/layer_04-model_00-model_states.pt. +0: [2022-11-29 23:40:15,329] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/layer_05-model_00-model_states.pt... +0: [2022-11-29 23:40:15,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/layer_05-model_00-model_states.pt. +0: [2022-11-29 23:40:15,352] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/layer_06-model_00-model_states.pt... +0: [2022-11-29 23:40:15,375] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/layer_06-model_00-model_states.pt. +0: [2022-11-29 23:40:15,376] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/layer_07-model_00-model_states.pt... +0: [2022-11-29 23:40:15,400] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/layer_07-model_00-model_states.pt. +0: [2022-11-29 23:40:15,400] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/layer_08-model_00-model_states.pt... +0: [2022-11-29 23:40:15,424] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/layer_08-model_00-model_states.pt. +0: [2022-11-29 23:40:15,424] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/layer_09-model_00-model_states.pt... +0: [2022-11-29 23:40:15,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/layer_09-model_00-model_states.pt. +0: [2022-11-29 23:40:15,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/layer_10-model_00-model_states.pt... +0: [2022-11-29 23:40:15,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/layer_10-model_00-model_states.pt. +0: [2022-11-29 23:40:15,469] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/layer_11-model_00-model_states.pt... +0: [2022-11-29 23:40:15,492] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/layer_11-model_00-model_states.pt. +0: [2022-11-29 23:40:15,492] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/layer_12-model_00-model_states.pt... +0: [2022-11-29 23:40:15,516] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/layer_12-model_00-model_states.pt. +0: [2022-11-29 23:40:15,516] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/layer_13-model_00-model_states.pt... +0: [2022-11-29 23:40:15,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/layer_13-model_00-model_states.pt. +0: [2022-11-29 23:40:15,540] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/layer_14-model_00-model_states.pt... +0: [2022-11-29 23:40:15,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/layer_14-model_00-model_states.pt. +0: [2022-11-29 23:40:15,563] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/layer_15-model_00-model_states.pt... +0: [2022-11-29 23:40:15,587] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/layer_15-model_00-model_states.pt. +0: [2022-11-29 23:40:15,587] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/layer_16-model_00-model_states.pt... +0: [2022-11-29 23:40:15,610] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/layer_16-model_00-model_states.pt. +0: [2022-11-29 23:40:15,611] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/layer_17-model_00-model_states.pt... +0: [2022-11-29 23:40:15,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/layer_17-model_00-model_states.pt. +0: [2022-11-29 23:40:15,634] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/layer_18-model_00-model_states.pt... +0: [2022-11-29 23:40:15,657] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/layer_18-model_00-model_states.pt. +0: [2022-11-29 23:40:15,657] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/layer_19-model_00-model_states.pt... +0: [2022-11-29 23:40:15,680] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/layer_19-model_00-model_states.pt. +0: [2022-11-29 23:40:15,680] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/layer_20-model_00-model_states.pt... +0: [2022-11-29 23:40:15,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/layer_20-model_00-model_states.pt. +0: [2022-11-29 23:40:15,704] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/layer_22-model_00-model_states.pt... +0: [2022-11-29 23:40:15,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/layer_22-model_00-model_states.pt. +0: [2022-11-29 23:40:15,709] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_220moscar/global_step14000/mp_rank_00_model_states.pt +0: [2022-11-29 23:40:15,709] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/mp_rank_00_model_states.pt... +0: [2022-11-29 23:40:15,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/mp_rank_00_model_states.pt. +0: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:40:15,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:40:15,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:40:15,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:40:15,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 23:40:15,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 23:40:15,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:40:15,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 23:40:15,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 23:40:15,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:40:15,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:40:15,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 23:40:15,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 23:40:15,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:40:15,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 23:40:15,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 23:40:15,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:40:15,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 23:40:15,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +6: [2022-11-29 23:40:15,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:40:15,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 23:40:15,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 23:40:15,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:40:15,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 23:40:15,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 23:40:15,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:40:15,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:40:15,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 23:40:15,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 23:40:15,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 23:40:15,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 23:40:15,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:40:15,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 23:40:15,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 23:40:15,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 23:40:15,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 23:40:15,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:40:15,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:40:15,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:40:15,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 23:40:15,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 23:40:15,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 23:40:15,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 23:40:15,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 23:40:15,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 23:40:15,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:40:15,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +4: [2022-11-29 23:40:15,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:40:15,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 23:40:15,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:40:15,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +4: [2022-11-29 23:40:15,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:40:15,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +4: [2022-11-29 23:40:15,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +2: [2022-11-29 23:40:15,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:40:15,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 23:40:15,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +4: [2022-11-29 23:40:15,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +2: [2022-11-29 23:40:15,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +4: [2022-11-29 23:40:15,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 23:40:15,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:40:15,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 23:40:15,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 23:40:15,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:40:15,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 23:40:15,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 23:40:15,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:40:15,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 23:40:15,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 23:40:15,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:40:15,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:40:15,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:40:15,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 23:40:15,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +1: [2022-11-29 23:40:15,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 23:40:15,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:40:15,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 23:40:15,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 23:40:15,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 23:40:15,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 23:40:15,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +6: [2022-11-29 23:40:15,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:40:15,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:40:15,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:40:15,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +7: [2022-11-29 23:40:15,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:40:15,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 23:40:15,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +7: [2022-11-29 23:40:15,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +6: [2022-11-29 23:40:15,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +6: [2022-11-29 23:40:15,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +6: [2022-11-29 23:40:15,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +7: [2022-11-29 23:40:15,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +7: [2022-11-29 23:40:15,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:40:15,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 23:40:15,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +6: [2022-11-29 23:40:15,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:40:15,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:40:15,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +6: [2022-11-29 23:40:15,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +2: [2022-11-29 23:40:15,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:40:15,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +6: [2022-11-29 23:40:15,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +6: [2022-11-29 23:40:15,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:40:15,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:40:15,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 23:40:15,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 23:40:15,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +6: [2022-11-29 23:40:15,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +7: [2022-11-29 23:40:15,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:40:15,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 23:40:15,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +4: [2022-11-29 23:40:15,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:40:15,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:40:15,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:40:15,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:40:15,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 23:40:15,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 23:40:15,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +3: [2022-11-29 23:40:15,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:40:15,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:40:15,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +4: [2022-11-29 23:40:15,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +4: [2022-11-29 23:40:15,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +4: [2022-11-29 23:40:15,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 23:40:15,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 23:40:15,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 23:40:15,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 23:40:15,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 23:40:15,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 23:40:15,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:40:15,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 23:40:15,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 23:40:15,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:40:15,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 23:40:15,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +4: [2022-11-29 23:40:15,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:40:15,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 23:40:15,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 23:40:15,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:40:15,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:40:15,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +0: [2022-11-29 23:40:15,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:40:15,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 23:40:15,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 23:40:15,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +4: [2022-11-29 23:40:15,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:40:15,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 23:40:15,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +4: [2022-11-29 23:40:15,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:40:15,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 23:40:15,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +5: [2022-11-29 23:40:15,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 23:40:15,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +5: [2022-11-29 23:40:15,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:40:15,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 23:40:15,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +5: [2022-11-29 23:40:15,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:40:15,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 23:40:15,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +5: [2022-11-29 23:40:15,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:40:15,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 23:40:15,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +5: [2022-11-29 23:40:15,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:40:15,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 23:40:15,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +5: [2022-11-29 23:40:15,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:40:15,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 23:40:15,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +5: [2022-11-29 23:40:15,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:40:15,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 23:40:15,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +5: [2022-11-29 23:40:15,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:40:15,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 23:40:15,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +7: [2022-11-29 23:40:15,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:40:15,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:40:15,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:40:15,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 23:40:15,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 23:40:15,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 23:40:15,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +7: [2022-11-29 23:40:15,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +7: [2022-11-29 23:40:15,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +7: [2022-11-29 23:40:15,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:40:15,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 23:40:15,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 23:40:15,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 23:40:15,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 23:40:15,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:40:15,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 23:40:15,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 23:40:15,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 23:40:15,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: successfully saved checkpoint at iteration 14000 to checkpoints_220moscar +7: time (ms) | save-checkpoint: 662.03 +7: iteration 14010/ 14324 | consumed samples: 3586560 | consumed tokens: 7345274880 | elapsed time per iteration (s): 0.50 | learning rate: 2.022E-05 | global batch size: 256 | lm loss: 2.948068E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 507.697 | TFLOPs: 26.64 | +7: iteration 14020/ 14324 | consumed samples: 3589120 | consumed tokens: 7350517760 | elapsed time per iteration (s): 0.42 | learning rate: 2.020E-05 | global batch size: 256 | lm loss: 2.895857E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 602.527 | TFLOPs: 31.61 | +7: iteration 14030/ 14324 | consumed samples: 3591680 | consumed tokens: 7355760640 | elapsed time per iteration (s): 0.42 | learning rate: 2.019E-05 | global batch size: 256 | lm loss: 2.917943E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 608.326 | TFLOPs: 31.92 | +7: iteration 14040/ 14324 | consumed samples: 3594240 | consumed tokens: 7361003520 | elapsed time per iteration (s): 0.42 | learning rate: 2.018E-05 | global batch size: 256 | lm loss: 2.906426E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.485 | TFLOPs: 31.72 | +7: iteration 14050/ 14324 | consumed samples: 3596800 | consumed tokens: 7366246400 | elapsed time per iteration (s): 0.42 | learning rate: 2.017E-05 | global batch size: 256 | lm loss: 2.924629E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.982 | TFLOPs: 32.16 | +7: iteration 14060/ 14324 | consumed samples: 3599360 | consumed tokens: 7371489280 | elapsed time per iteration (s): 0.42 | learning rate: 2.015E-05 | global batch size: 256 | lm loss: 2.930024E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 613.014 | TFLOPs: 32.16 | +7: iteration 14070/ 14324 | consumed samples: 3601920 | consumed tokens: 7376732160 | elapsed time per iteration (s): 0.42 | learning rate: 2.014E-05 | global batch size: 256 | lm loss: 2.912740E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 613.014 | TFLOPs: 32.16 | +7: iteration 14080/ 14324 | consumed samples: 3604480 | consumed tokens: 7381975040 | elapsed time per iteration (s): 0.42 | learning rate: 2.013E-05 | global batch size: 256 | lm loss: 2.931173E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 611.080 | TFLOPs: 32.06 | +7: iteration 14090/ 14324 | consumed samples: 3607040 | consumed tokens: 7387217920 | elapsed time per iteration (s): 0.42 | learning rate: 2.012E-05 | global batch size: 256 | lm loss: 2.932660E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.221 | TFLOPs: 31.75 | +7: iteration 14100/ 14324 | consumed samples: 3609600 | consumed tokens: 7392460800 | elapsed time per iteration (s): 0.42 | learning rate: 2.011E-05 | global batch size: 256 | lm loss: 2.906140E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.367 | TFLOPs: 32.13 | +7: iteration 14110/ 14324 | consumed samples: 3612160 | consumed tokens: 7397703680 | elapsed time per iteration (s): 0.42 | learning rate: 2.010E-05 | global batch size: 256 | lm loss: 2.927584E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 606.980 | TFLOPs: 31.85 | +7: iteration 14120/ 14324 | consumed samples: 3614720 | consumed tokens: 7402946560 | elapsed time per iteration (s): 0.42 | learning rate: 2.009E-05 | global batch size: 256 | lm loss: 2.934944E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.556 | TFLOPs: 32.14 | +7: iteration 14130/ 14324 | consumed samples: 3617280 | consumed tokens: 7408189440 | elapsed time per iteration (s): 0.42 | learning rate: 2.008E-05 | global batch size: 256 | lm loss: 2.933431E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.620 | TFLOPs: 31.88 | +7: iteration 14140/ 14324 | consumed samples: 3619840 | consumed tokens: 7413432320 | elapsed time per iteration (s): 0.43 | learning rate: 2.007E-05 | global batch size: 256 | lm loss: 2.889276E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 594.808 | TFLOPs: 31.21 | +7: iteration 14150/ 14324 | consumed samples: 3622400 | consumed tokens: 7418675200 | elapsed time per iteration (s): 0.42 | learning rate: 2.007E-05 | global batch size: 256 | lm loss: 2.893818E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 613.338 | TFLOPs: 32.18 | +7: iteration 14160/ 14324 | consumed samples: 3624960 | consumed tokens: 7423918080 | elapsed time per iteration (s): 0.42 | learning rate: 2.006E-05 | global batch size: 256 | lm loss: 2.942091E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 613.584 | TFLOPs: 32.19 | +7: iteration 14170/ 14324 | consumed samples: 3627520 | consumed tokens: 7429160960 | elapsed time per iteration (s): 0.44 | learning rate: 2.005E-05 | global batch size: 256 | lm loss: 2.908898E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 587.259 | TFLOPs: 30.81 | +7: iteration 14180/ 14324 | consumed samples: 3630080 | consumed tokens: 7434403840 | elapsed time per iteration (s): 0.42 | learning rate: 2.005E-05 | global batch size: 256 | lm loss: 2.930390E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 613.597 | TFLOPs: 32.19 | +7: iteration 14190/ 14324 | consumed samples: 3632640 | consumed tokens: 7439646720 | elapsed time per iteration (s): 0.42 | learning rate: 2.004E-05 | global batch size: 256 | lm loss: 2.927872E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.229 | TFLOPs: 31.97 | +7: iteration 14200/ 14324 | consumed samples: 3635200 | consumed tokens: 7444889600 | elapsed time per iteration (s): 0.42 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 2.936593E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 610.400 | TFLOPs: 32.03 | +7: iteration 14210/ 14324 | consumed samples: 3637760 | consumed tokens: 7450132480 | elapsed time per iteration (s): 0.42 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 2.905920E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.988 | TFLOPs: 32.16 | +7: iteration 14220/ 14324 | consumed samples: 3640320 | consumed tokens: 7455375360 | elapsed time per iteration (s): 0.42 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 2.908926E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.936 | TFLOPs: 32.16 | +7: iteration 14230/ 14324 | consumed samples: 3642880 | consumed tokens: 7460618240 | elapsed time per iteration (s): 0.42 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 2.929812E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.274 | TFLOPs: 32.13 | +7: iteration 14240/ 14324 | consumed samples: 3645440 | consumed tokens: 7465861120 | elapsed time per iteration (s): 0.42 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 2.911132E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 613.585 | TFLOPs: 32.19 | +7: iteration 14250/ 14324 | consumed samples: 3648000 | consumed tokens: 7471104000 | elapsed time per iteration (s): 0.42 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.919987E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.623 | TFLOPs: 32.14 | +7: iteration 14260/ 14324 | consumed samples: 3650560 | consumed tokens: 7476346880 | elapsed time per iteration (s): 0.42 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.918732E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 613.725 | TFLOPs: 32.20 | +7: iteration 14270/ 14324 | consumed samples: 3653120 | consumed tokens: 7481589760 | elapsed time per iteration (s): 0.42 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.927381E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 613.810 | TFLOPs: 32.21 | +7: iteration 14280/ 14324 | consumed samples: 3655680 | consumed tokens: 7486832640 | elapsed time per iteration (s): 0.42 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.937317E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 613.846 | TFLOPs: 32.21 | +7: iteration 14290/ 14324 | consumed samples: 3658240 | consumed tokens: 7492075520 | elapsed time per iteration (s): 0.43 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.924752E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 598.894 | TFLOPs: 31.42 | +7: iteration 14300/ 14324 | consumed samples: 3660800 | consumed tokens: 7497318400 | elapsed time per iteration (s): 0.42 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.923213E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 613.457 | TFLOPs: 32.19 | +7: iteration 14310/ 14324 | consumed samples: 3663360 | consumed tokens: 7502561280 | elapsed time per iteration (s): 0.42 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.882543E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 612.975 | TFLOPs: 32.16 | +7: iteration 14320/ 14324 | consumed samples: 3665920 | consumed tokens: 7507804160 | elapsed time per iteration (s): 0.42 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.929223E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 609.337 | TFLOPs: 31.97 | +0: [after training is done] datetime: 2022-11-29 23:42:32 +0: saving checkpoint at iteration 14324 to checkpoints_220moscar +7: ------------------------------------------------------------------------------------------------------------ +7: valid loss at the end of training for val data | lm loss value: 2.871260E+00 | lm loss PPL: 1.765925E+01 | +7: ------------------------------------------------------------------------------------------------------------ +0: [2022-11-29 23:42:32,142] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step14324 is begin to save! +0: [2022-11-29 23:42:32,147] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/layer_01-model_00-model_states.pt... +0: [2022-11-29 23:42:32,246] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/layer_01-model_00-model_states.pt. +0: [2022-11-29 23:42:32,246] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/layer_03-model_00-model_states.pt... +0: [2022-11-29 23:42:32,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/layer_03-model_00-model_states.pt. +0: [2022-11-29 23:42:32,268] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/layer_04-model_00-model_states.pt... +0: [2022-11-29 23:42:32,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/layer_04-model_00-model_states.pt. +0: [2022-11-29 23:42:32,291] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/layer_05-model_00-model_states.pt... +0: [2022-11-29 23:42:32,314] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/layer_05-model_00-model_states.pt. +0: [2022-11-29 23:42:32,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/layer_06-model_00-model_states.pt... +0: [2022-11-29 23:42:32,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/layer_06-model_00-model_states.pt. +0: [2022-11-29 23:42:32,336] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/layer_07-model_00-model_states.pt... +0: [2022-11-29 23:42:32,359] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/layer_07-model_00-model_states.pt. +0: [2022-11-29 23:42:32,359] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/layer_08-model_00-model_states.pt... +0: [2022-11-29 23:42:32,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/layer_08-model_00-model_states.pt. +0: [2022-11-29 23:42:32,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/layer_09-model_00-model_states.pt... +0: [2022-11-29 23:42:32,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/layer_09-model_00-model_states.pt. +0: [2022-11-29 23:42:32,407] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/layer_10-model_00-model_states.pt... +0: [2022-11-29 23:42:32,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/layer_10-model_00-model_states.pt. +0: [2022-11-29 23:42:32,431] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/layer_11-model_00-model_states.pt... +0: [2022-11-29 23:42:32,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/layer_11-model_00-model_states.pt. +0: [2022-11-29 23:42:32,454] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/layer_12-model_00-model_states.pt... +0: [2022-11-29 23:42:32,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/layer_12-model_00-model_states.pt. +0: [2022-11-29 23:42:32,478] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/layer_13-model_00-model_states.pt... +0: [2022-11-29 23:42:32,501] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/layer_13-model_00-model_states.pt. +0: [2022-11-29 23:42:32,502] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/layer_14-model_00-model_states.pt... +0: [2022-11-29 23:42:32,525] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/layer_14-model_00-model_states.pt. +0: [2022-11-29 23:42:32,526] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/layer_15-model_00-model_states.pt... +0: [2022-11-29 23:42:32,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/layer_15-model_00-model_states.pt. +0: [2022-11-29 23:42:32,549] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/layer_16-model_00-model_states.pt... +0: [2022-11-29 23:42:32,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/layer_16-model_00-model_states.pt. +0: [2022-11-29 23:42:32,572] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/layer_17-model_00-model_states.pt... +0: [2022-11-29 23:42:32,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/layer_17-model_00-model_states.pt. +0: [2022-11-29 23:42:32,595] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/layer_18-model_00-model_states.pt... +0: [2022-11-29 23:42:32,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/layer_18-model_00-model_states.pt. +0: [2022-11-29 23:42:32,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/layer_19-model_00-model_states.pt... +0: [2022-11-29 23:42:32,642] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/layer_19-model_00-model_states.pt. +0: [2022-11-29 23:42:32,643] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/layer_20-model_00-model_states.pt... +0: [2022-11-29 23:42:32,666] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/layer_20-model_00-model_states.pt. +0: [2022-11-29 23:42:32,667] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/layer_22-model_00-model_states.pt... +0: [2022-11-29 23:42:32,670] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/layer_22-model_00-model_states.pt. +0: [2022-11-29 23:42:32,671] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_220moscar/global_step14324/mp_rank_00_model_states.pt +0: [2022-11-29 23:42:32,671] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/mp_rank_00_model_states.pt... +0: [2022-11-29 23:42:32,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/mp_rank_00_model_states.pt. +0: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +0: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:42:32,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 23:42:32,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:42:32,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:42:32,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:42:32,739] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 23:42:32,739] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +2: [2022-11-29 23:42:32,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:42:32,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 23:42:32,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +3: [2022-11-29 23:42:32,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:42:32,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 23:42:32,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +3: [2022-11-29 23:42:32,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:42:32,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 23:42:32,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +2: [2022-11-29 23:42:32,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:42:32,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 23:42:32,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +7: [2022-11-29 23:42:32,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:42:32,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 23:42:32,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +7: [2022-11-29 23:42:32,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:42:32,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:42:32,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 23:42:32,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +4: [2022-11-29 23:42:32,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 23:42:32,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +4: [2022-11-29 23:42:32,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:42:32,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:42:32,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 23:42:32,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 23:42:32,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +4: [2022-11-29 23:42:32,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +2: [2022-11-29 23:42:32,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:42:32,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 23:42:32,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +2: [2022-11-29 23:42:32,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:42:32,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 23:42:32,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +4: [2022-11-29 23:42:32,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:42:32,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 23:42:32,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +0: [2022-11-29 23:42:32,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:42:32,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +0: [2022-11-29 23:42:32,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +5: [2022-11-29 23:42:32,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +5: [2022-11-29 23:42:32,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:42:32,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:42:32,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +5: [2022-11-29 23:42:32,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 23:42:32,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 23:42:32,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +5: [2022-11-29 23:42:32,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +5: [2022-11-29 23:42:32,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:42:32,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 23:42:32,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +5: [2022-11-29 23:42:32,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:42:32,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 23:42:32,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +3: [2022-11-29 23:42:32,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:42:32,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 23:42:32,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +3: [2022-11-29 23:42:32,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:42:32,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 23:42:32,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +2: [2022-11-29 23:42:32,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:42:32,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 23:42:32,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +4: [2022-11-29 23:42:32,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:42:32,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 23:42:32,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +3: [2022-11-29 23:42:32,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:42:32,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:42:32,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 23:42:32,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 23:42:32,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +3: [2022-11-29 23:42:32,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +0: [2022-11-29 23:42:32,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:42:32,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 23:42:32,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +5: [2022-11-29 23:42:32,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:42:32,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:42:32,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 23:42:32,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +4: [2022-11-29 23:42:32,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:42:32,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 23:42:32,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 23:42:32,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 23:42:32,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +4: [2022-11-29 23:42:32,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +1: [2022-11-29 23:42:32,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:42:32,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:42:32,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 23:42:32,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 23:42:32,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +1: [2022-11-29 23:42:32,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +2: [2022-11-29 23:42:32,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:42:32,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 23:42:32,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +0: [2022-11-29 23:42:32,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:42:32,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 23:42:32,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +3: [2022-11-29 23:42:32,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:42:32,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 23:42:32,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +1: [2022-11-29 23:42:32,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:42:32,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:42:32,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 23:42:32,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 23:42:32,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +1: [2022-11-29 23:42:32,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +1: [2022-11-29 23:42:32,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:42:32,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:42:32,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 23:42:32,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 23:42:32,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +1: [2022-11-29 23:42:32,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +2: [2022-11-29 23:42:32,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:42:32,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +0: [2022-11-29 23:42:32,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:42:32,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +0: [2022-11-29 23:42:32,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 23:42:32,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +7: [2022-11-29 23:42:32,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:42:32,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 23:42:32,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +7: [2022-11-29 23:42:32,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:42:32,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:42:32,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:42:32,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 23:42:32,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 23:42:32,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 23:42:32,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +7: [2022-11-29 23:42:32,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +7: [2022-11-29 23:42:32,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +3: [2022-11-29 23:42:32,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +2: [2022-11-29 23:42:32,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +3: [2022-11-29 23:42:32,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +2: [2022-11-29 23:42:32,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +3: [2022-11-29 23:42:32,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +2: [2022-11-29 23:42:32,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +7: [2022-11-29 23:42:32,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:42:32,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 23:42:32,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +7: [2022-11-29 23:42:32,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 23:42:32,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 23:42:32,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +1: [2022-11-29 23:42:32,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:42:32,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 23:42:32,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +6: [2022-11-29 23:42:32,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:42:32,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 23:42:32,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +6: [2022-11-29 23:42:32,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:42:32,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 23:42:32,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +6: [2022-11-29 23:42:32,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:42:32,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 23:42:32,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +5: [2022-11-29 23:42:32,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 23:42:32,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +5: [2022-11-29 23:42:32,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:42:32,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 23:42:32,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +5: [2022-11-29 23:42:32,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 23:42:32,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 23:42:32,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +0: [2022-11-29 23:42:32,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:42:32,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 23:42:32,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +0: [2022-11-29 23:42:32,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 23:42:32,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 23:42:32,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +1: [2022-11-29 23:42:32,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 23:42:32,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 23:42:32,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +6: [2022-11-29 23:42:32,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:42:32,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:42:32,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:42:32,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:42:32,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 23:42:32,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 23:42:32,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 23:42:32,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 23:42:32,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 23:42:32,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 23:42:32,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +6: [2022-11-29 23:42:32,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +6: [2022-11-29 23:42:32,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +6: [2022-11-29 23:42:32,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +6: [2022-11-29 23:42:32,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +0: [2022-11-29 23:42:32,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_220moscar/global_step14324/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 23:42:32,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14324 is ready now! +0: successfully saved checkpoint at iteration 14324 to checkpoints_220moscar +7: ------------------------------------------------------------------------------------------------------------ +7: test loss at the end of training for test data | lm loss value: 2.833576E+00 | lm loss PPL: 1.700617E+01 | +7: ------------------------------------------------------------------------------------------------------------ +END 2086980: Tue Nov 29 23:42:41 EET 2022 diff --git a/220m7b57b5/sbatch_220m_oscar.sh b/220m7b57b5/sbatch_220m_oscar.sh new file mode 100644 index 0000000000000000000000000000000000000000..a6f893604a28b05bb5ff638c901ce94e265a78c9 --- /dev/null +++ b/220m7b57b5/sbatch_220m_oscar.sh @@ -0,0 +1,160 @@ +#!/bin/bash +#SBATCH --nodes=8 +#SBATCH --ntasks-per-node=1 +#SBATCH --cpus-per-task=32 +#SBATCH --mem=256G +#SBATCH -p pilot +#SBATCH -t 48:00:00 +#SBATCH --gpus-per-node=mi250:8 +#SBATCH --exclusive=user +#SBATCH --hint=nomultithread +#SBATCH --account=project_462000119 +#SBATCH -o logs/%j.out +#SBATCH -e logs/%j.err + +VARIANT=220moscar + +# if run without sbatch, invoke here +if [ -z $SLURM_JOB_ID ]; then + mkdir -p logs + sbatch "$0" + exit +fi + +set -euo pipefail + +# symlink logs/latest.out and logs/latest.err +ln -f -s $SLURM_JOB_ID.out logs/latest.out +ln -f -s $SLURM_JOB_ID.err logs/latest.err + +KILL_SWITCH_PATH=kill-switch-$VARIANT +CHECKPOINT_PATH=checkpoints_$VARIANT +TENSORBOARD_PATH=tensorboard_$VARIANT +# Start from scratch +rm -rf "$CHECKPOINT_PATH" "$TENSORBOARD_PATH" + +# Data +VOCAB_FILE="gpt2/vocab.json" +MERGE_FILE="gpt2/merges.txt" +DATA_PATH="/scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document" + +PP_SIZE=1 +TP_SIZE=1 + +MICRO_BATCH_SIZE=4 +GRADIENT_ACCUMULATION_STEPS=1 +WORLD_SIZE=$((SLURM_GPUS_ON_NODE*SLURM_JOB_NUM_NODES)) +GLOBAL_BATCH_SIZE=$((MICRO_BATCH_SIZE*WORLD_SIZE*GRADIENT_ACCUMULATION_STEPS)) + +# Model parameters +source model_params.sh +MODEL_PARAM=("${PARAM_217M[@]}") +NHIDDEN=${MODEL_PARAM[0]} +FFN_HIDDEN_SIZE=${MODEL_PARAM[1]} +KV_SIZE=${MODEL_PARAM[2]} +NHEADS=${MODEL_PARAM[3]} +NLAYERS=${MODEL_PARAM[4]} +SEQ_LEN=2048 + +echo "Model parameters: d_model $NHIDDEN ffw_size $FFN_HIDDEN_SIZE kv_size $KV_SIZE n_heads $NHEADS n_layers $NLAYERS" + +SAVE_INTERVAL=1000 + +# Tokens: 7510000000 +# -> Samples: 3_666_992 +TRAIN_SAMPLES=3_666_992 + +OPTIMIZER_ARGS=" \ + --optimizer adam \ + --adam-beta1 0.9 \ + --adam-beta2 0.999 \ + --adam-eps 1e-8 \ + --lr 2e-4 \ + --min-lr 2e-5 \ + --lr-decay-style cosine \ + --lr-decay-samples $TRAIN_SAMPLES \ + --lr-warmup-samples 36_670 \ + --clip-grad 1.0 \ + --weight-decay 1e-1 \ + " + +GPT_ARGS=" \ + --num-layers $NLAYERS \ + --hidden-size $NHIDDEN \ + --num-attention-heads $NHEADS \ + --kv-channels $KV_SIZE \ + --ffn-hidden-size $FFN_HIDDEN_SIZE \ + --seq-length $SEQ_LEN \ + --max-position-embeddings $SEQ_LEN \ + --micro-batch-size $MICRO_BATCH_SIZE \ + --global-batch-size $GLOBAL_BATCH_SIZE \ + --train-samples $TRAIN_SAMPLES \ + --vocab-file $VOCAB_FILE \ + --merge-file $MERGE_FILE \ + --clip-grad 1.0 \ + --kill-switch-path $KILL_SWITCH_PATH \ + --bf16 \ + $OPTIMIZER_ARGS \ + " + +OUTPUT_ARGS=" \ + --log-interval 10 \ + --save-interval $SAVE_INTERVAL \ + --eval-interval 1000 \ + --eval-iters 1 \ + --tensorboard-dir $TENSORBOARD_PATH \ + --tensorboard-queue-size 5 \ + --log-timers-to-tensorboard \ + --log-batch-size-to-tensorboard \ + --log-validation-ppl-to-tensorboard \ + " + +ZERO_STAGE=0 + +mkdir -p ds_configs +DS_CONFIG_PATH="ds_configs/$SLURM_JOB_ID.json" + +cat < $DS_CONFIG_PATH +{ + "train_micro_batch_size_per_gpu": $MICRO_BATCH_SIZE, + "train_batch_size": $GLOBAL_BATCH_SIZE, + "gradient_clipping": 1.0, + "zero_optimization": { + "stage": $ZERO_STAGE + }, + "bf16": { + "enabled": true + }, + "steps_per_print": 2000, + "wall_clock_breakdown": false +} +EOF + +DEEPSPEED_ARGS=" \ + --deepspeed \ + --deepspeed_config $DS_CONFIG_PATH \ + --zero-stage $ZERO_STAGE \ + " + +CMD=" \ + Megatron-DeepSpeed/pretrain_gpt.py \ + --tensor-model-parallel-size $TP_SIZE \ + --pipeline-model-parallel-size $PP_SIZE \ + $GPT_ARGS \ + $OUTPUT_ARGS \ + --save $CHECKPOINT_PATH \ + --load $CHECKPOINT_PATH \ + --data-path $DATA_PATH \ + --data-impl mmap \ + --split 949,50,1 \ + $DEEPSPEED_ARGS \ + " + +echo $CMD + +echo "START $SLURM_JOBID: $(date)" + +# bash launch_srun.sh $CMD +srun --label launch.sh $CMD + +echo "END $SLURM_JOBID: $(date)" diff --git a/220m7b57b5/tensorboard/events.out.tfevents.1669733304.nid006772.19647.0 b/220m7b57b5/tensorboard/events.out.tfevents.1669733304.nid006772.19647.0 new file mode 100644 index 0000000000000000000000000000000000000000..e00754c9e0911c23dce6bbb57880a6985955f3ff --- /dev/null +++ b/220m7b57b5/tensorboard/events.out.tfevents.1669733304.nid006772.19647.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c71bb7e6f863ba3dc12f8e09c96dbb351e64d1b66fed6386b4116a7908f5527 +size 40 diff --git a/220m7b57b5/tensorboard/tensorboard_220moscar/events.out.tfevents.1669751873.nid006703.105420.0 b/220m7b57b5/tensorboard/tensorboard_220moscar/events.out.tfevents.1669751873.nid006703.105420.0 new file mode 100644 index 0000000000000000000000000000000000000000..6fcc8021924e27f1cc2e90840fe0602627b70046 --- /dev/null +++ b/220m7b57b5/tensorboard/tensorboard_220moscar/events.out.tfevents.1669751873.nid006703.105420.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a43cf7fc759c5b2e2269b9c2cff46490f1f1344dfae97f405a351e3f9ddcd1b5 +size 25510727 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..459230a952ee1d206a78192fb6e7269a1186c977 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bea9ff8f0382d3ce7a992a0d41b9e5f3b95c5aee2a40f0eb9f935995b17b5297 +size 52568791 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5272d5fa3a8d0d9937d7cfb4fbc0113e0b8b8e00 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4618711ab5c70cd1a6077cee77ffccd17c0a16682f6274f1310e03bda44f83a +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fc68802615e3ac4bdb01f8683208ca2fe8b89045 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8e4061297d3f8244d3862bfd531d1ae3163eef9773bf6a0c1540f4632c2b0d1 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9e70a08aeec58a25843fa6d9a14ff7b65a494225 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b69899d52285798312fb155d756cd1cd266be6555d912db5f921dab5244df597 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..67136a4354b79c1fc3db8c8c2eb023474598d7b7 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1b6006959862b89e81326a72c9fadd6536140bed1c5bed5e880cba3cb9454e8 +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..80774b3f45c7f434330bfb6b66bd44eb69de6f4e --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d68758f553c48e2271d65ef0064e622cd714ecc306227df959cfa05bff73774f +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7657dbcdcfa3fc45653f486d12f02e2c8a8c7e6b --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44d8986a4bebedef39aaea05b0869b40da4d03050136668a516c34a7fb3da777 +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..72f5d241963d2ff0ab2fe0943247dd2b1399f395 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aef9b2a6584505061b88440df273c0771eeda57bd6f46307fa9ba9aa1edb93e +size 52568738 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..acb19fec618e6bc91e47a9af1449559f56538638 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8ba45f977650fa4ac7aef60398d0152258a69667b32ff3fa2b573b0507bfcc6 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ac255b6ee56603db3a1b8397cc3a99deaf01c16a --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:440c768aba03a156b808abc2ec23d0882f303d8e1d1db109b1c687c6bdbdbef9 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..96337e6cab876011221880b811393cbd2e24f58e --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e975331a207578fca6222b8bd2b75bc0879c6f5f06ae2ab05d6b88e67bbdd1c +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..00d9ac7a0989a11a91f1b2cfc80735458f2765b7 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:581d5be594db2f724996faf8827a809d45154b842ba294d596c3872b1c722c22 +size 52568855 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..335f2921048705e742fc5e36736056b700e1e564 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbc14ed0028a74c72c75477d0f26055dd43b941229393dc98590bd3c8e84627a +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4484d7b14b47d11fc3a9933ff242bb338bf50072 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ab9e5657dbcd0419060cf70d3cf48f63836570681412c82d5af34bd62d39a1c +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..76e8944e041d5ebbe72a9acb444a099ce16aa084 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5fc21d1095cb5d4d063fb91e83f100475a486bf10ca21f3f3e5253b6bfded6c +size 52568994 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d6ce760adaccb18bb70bd9a5ef12d74cfa376363 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75e7adf067155123ebaf7b35b6ec8b7ab35707acede242b199dc6215ed6e92fa +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8816b8096097f83c3a73c469a24f1eac4feae942 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7321c252c8b291d7375877b7717f98c76138506ca6c5469e161263616c695278 +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3310d081f1c0a1b4387ebb41213a8f65a6015511 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b1c606c4ebfde965f6c1162cfbb475e4a6f9728bcf28201ba0fec4246bb0f29 +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b81486748338e85e6ace98b00e0bf44db61e31c2 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ce77c416d39b6ab37d8f0b5a34bc1ddce06f944a0fa7a0b331f557bf47e7f16 +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..22136754a65c13a5046a7971f07978ed5ab57f51 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b14177b8c77d2dc81c4cbbbdea4fe30c6fb8831e4b2faa13de43e49e3f8a105 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..78bf2c11ad714a36502d8bbd3b8998d454841a28 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:417480f8601ec8e9e2a4490c49a298a13bbba37ae67f35f278e0a3dda886b6b9 +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ef090c64623b198a9492747a91b860f572095625 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b140a6cb597486c940ec8c277336a11afe0284cbed263fa2a5abd6f6d8c68967 +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..59bb73b8cba31e54ac44c3f8764f5505fe4833f5 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:634b2ca8fb9b6e3e7fa25717a0995ecfb512544d52575a9a4e4e8089a1206d70 +size 52568791 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ee926e4ccdcf5bdebc961265d1e66fd68bafb7c2 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8df7c37774cbd130f8035e4b0e90ef116831077be6b9b0f00988ab3bb585542 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..629379d7079e400f3603bf61a115d5f23d2c8334 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83ad82a015c759143dd8124ce67925e7a39c1daef9631e43d494fcea33bed6f4 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1e43cf393153177f803e3d4d3b1e18f49708ed8d --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca562e7d9ce074e44f8f362365baa0a4ea0474c04d956bf8c29dc74c0b60af56 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..67c7d17bf0d314897cc7a285c73769725ef76546 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09971e2463883550bc0a085f707b9ff9a32c5675497e23beb4998c14c3909a98 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c71571c09299fcbb37a1d0ea070defe8858a7315 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f88ef240d4646ef88838906797ddb32f5a737a6d3cc8c935773e2fd6f0168a07 +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3d624e9e78dc7946c2df8bbbc9696c852ead35c6 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b99f6cffab919c7156277cc144dd43672e8cda76d8d29b49dfce311a07a3b688 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..77117307c4b86b8c106d35e91d1596c4c663c6d7 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f8723fb43d8312dbb1887db6499fb9018ecfaea3f470a3e861a4658574d95fa +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..afaa440c4f7625619aca79ec90fd44996d6d30d8 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24cbc3fb87641be72206137058b2ffadc80e91e9fd595cca07fc19606b99566d +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3945a3f54cca9aee6b117bc3217c22d70807d986 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e7cf5952bb657f9547dde298c42190bd6a7beeed3d8b158b607403f993dccc7 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..70a8fc189fd4294fc1161743b8e3e9b1c67238cc --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3607a6e85adbaff984717a343b1880219876ab3eace39dab998fd3ae987a51a4 +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6cda542d112e1927bb1262122664f703c4c12fc0 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c7cbcc50f5ae583ff278d4965bfb008ca8722d4871d950b3a80e837ecf2be79 +size 52568791 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ca54720da09c0c66d0b13b405e411060d4454ff3 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4de0473301a4c6804b8e936a8ce8bf6668a3265a40ecd8cecd45c3411b0b2730 +size 52568994 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f3d332e4931619c668145f1be3687625603d40e0 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c3635b44896376d85cb28b72abb0262238106cef47b19f49abfc4701cb2e3ae +size 52568738 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c73e9199b1d1f655d0790439de3a59bf9f89b895 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9820d5add19a30547c65b04a511d8d43b407f42adda8b8358632e929cbb6d55 +size 52568994 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..78e7b5aff86d6f936f0c54cc92e9724991156cec --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b36db3d6433ddabd3ee9dab709443c38c83172cce58cce597a51ed0b8bd31ef0 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..03ca45c869308fb85a841408d2ee9456abce51bd --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b1e0da094b89944ad25a6c281f2f9d326225c07b626d9f48e519a85f811233b +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..15f5e1e3872eb2c99b5e1605aca4a15882448468 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b88f612093554ee8c0de0c7e4f017d04c62dfbfb0b74b01261d8d99015bbe8cc +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..688a2873ea68ad841d436a7132b6145fb0318b3f --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1762347c5b336625b8a0f04d1d749a25bf527801efa5fc979ed7836c80f4304f +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6ade3461d97ea78efb37d76d0ab71cb8e6ba81da --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae5a950d8e427d937d576e0f8741612bf354b9020561fbfb3013ea5a56c3839c +size 52568994 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a4912e3a3400944328e0fd09501c6dcab5b51129 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12e62ba4e9d80ddfc0c1e05d3303f1c843f5feab9ed53bd2e789b001a4e4f4da +size 52568610 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..907e4c1be6e31711f3395940e22ef6c152d5a9d8 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4d5c9e2a03e1d735c67e649d3b3e50af4c673afdac7caaafa5dce3190b90078 +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2ff56ecc71ab81465dd21a6246b27f446c6aaa3d --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df9e8faaad36ccc1c78b095d010fef063095a276be379667f12de1311550c014 +size 52568855 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..46df6ed0e37737780e1bda7d4f9cfea2d1b97a34 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa9772ae17361887a99b413e32c76f98aa7ddc2eeb70615a7a3f5f55f4e5b544 +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9916ae46c885df1637f97ddf22ffa69ae3dfc593 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2e4cc067243800bb22181e46961ebc306aba8f363e6b39462347446213e22e7 +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b310237b802b8d0ff60d36e07557312d02a5c52d --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dae10be5e1a45d90ac62d7f1d47f97240ed5abbde5550ea6b7aad21ce9885dc +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..be56e06a838d79ec5f66bb17a8de11f0b16999ee --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5a04ae6b0bfb6fcc429148f118f07c63ee4620c838ebffe324880c2c9c14d30 +size 52568738 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f61aa606756fab8a7776ea509134bb3c2694c257 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c00996acd6b48dc66228cd88491fb962ad3ef406c62ee0b465ea949f0d6c116 +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5016a566a36942c3b91a9ab2399e51c8d78e7a19 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01c63ee694b5591c6fc5ef5e89c7378269ebd80a8db95d9407d4aac43d5b02a3 +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..36b48649c1581cf8a52d4c17e1d447b8020cf6cc --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61d9f5a0da0eb765c7c23a6f12a64078ab879f46cc5efdbb31a892150fffa30b +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c2253e9c5992f9fffb3cce16c6ea7a155a6fd0d5 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acbd375ed86481bbe9050119c55cca4b4ccbd9e9bb44a59b40b484f02f489257 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2e4de3539640e87c35b3d66f0a1ce8a014ba83f7 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e00ea2c957839795970353c506c41e4e997f6f3995865ab47a9a435efa6cbd5 +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..398814abaea42a5bd9a429edc2cd27d7f0af80ab --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9695ad1e922f26409f00e7829865b47a90b7fc00f32e717a48f899703fa8862 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9db860a33702ed1552da6cf36cfa30b9d8d0cd39 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f9bb54ec4f41ff4adf3cb6151007719f75ae7aba4cf7ccbede2702917605c2b +size 52568791 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b468793a20f882c0aa42d0a7067cd649a138a919 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bece0b72bcf799bf08e93c1be32f91c2cdd79bd2dfc221f629222374771162a7 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..38776344e7a9204535ad16d6702e02c07008db49 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b21520d872ff203df6a434bfc2ff2fe53c71e1aab9ae9e362361b06fb2dc6ff3 +size 52568994 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b0d5bcfdab43dbd01a86ce6b6613e620b0e19406 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30d717c011450c2363b6820c5d94161014f97bc57b594dd67a0f8b73c6499dd6 +size 52568738 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3ad8a5019274da3629d31341fe5d508ce60465d9 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bab7a7f60adf2cb027ec18666104155b5c3fe6fbfb7638a4ba006f295b4c6a03 +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..82eafbb676e632ec6c181849d9c56c2b36dfb1d5 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e18845e860aaf016c0f99d0d3c1bd462bf74e4ec23f05aa159edb06b3137de03 +size 52568727 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1c5729899b1b3d15472b26d91aba6e6a21c7ba6f --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a98376b5961ca502f3963a5cfb1d93f1493e66825c24ce8ca741d3dab5032ebb +size 52568791 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..be1e21de778cabdc3141da4732b65b204870bda2 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e069c239f8b1c311b1808673e09222097eeb945975a7c9ef314aef5be0e8f67 +size 52568855 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c3491d289eef82b9f375b9c4fad7e64cc16385dc --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e433cd1ccd544083a880c751f99c0896b2bb54363c7cfa17a278a5f2f786942 +size 52568791 diff --git a/280m5b95b9/global_step11269/layer_01-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_01-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f7ff17093d4406260f7ce5200f034ba6d6856722 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_01-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:003022864fd63fb0f64d7e9a5020b623c98ce95efa25974230696c1318bfce47 +size 107218179 diff --git a/280m5b95b9/global_step11269/layer_03-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_03-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c6be13f04088553c41ad39c254eb60723649f630 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_03-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54d4ff20b2f1f2c17d0d057f8bdbd7cfb60b41bcf9be7732e273b3a8f198fa16 +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_04-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_04-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..484d54f1ad478bde26d59a96180b9b1029fe2c54 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_04-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec03beba7e19478f9357307b4dab734bfa2612c97cd5d74ca319286448054550 +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_05-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_05-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0f5cb07eef6a50ae1161bca597d41995b32d14b6 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_05-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d51084300fd93cd8101e2634307e791c05fddba336393a0b437b3c3a849b7bcc +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_06-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_06-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2c74059a42967e34092b7a867d23f531d8da9cb4 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_06-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0ff3deec7dd7f178e7440d449bdaf7c0eb59ab294d474fbf244fd853e830d8c +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_07-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_07-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..69d039e79058db31bf05b3ff23d33f9ffe433209 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_07-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55b1149098823296716a4647fe90f94e82aa80680f61cb4b146246998643792a +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_08-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_08-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f2232cce933a5276e4c7e085081086ee1a155c7e --- /dev/null +++ b/280m5b95b9/global_step11269/layer_08-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ed4e5ec46df0532a288c13ebbce7e4b031ccdc7f7554a25678dd15af31b7de1 +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_09-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_09-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..27ba137c1d3db6598f47c1c9755f63b42f7ab308 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_09-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e930e38fbca897e83919913fcc326f6b544d01cf9f7bbf9a823b19c3326b7c3c +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_10-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_10-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5ecc55f259195d9d8591a4f4a893fbe6b468f43e --- /dev/null +++ b/280m5b95b9/global_step11269/layer_10-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b545f09d3e2b5a43f074299fea975d6791edc359810a4e33f9bc8acab89913b +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_11-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_11-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..511aa3b5b1b28226aef40260e1091041f45db23e --- /dev/null +++ b/280m5b95b9/global_step11269/layer_11-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11a3aa0d44ed07511508769949c23d445e02bed5a91470a52fad934077057f67 +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_12-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_12-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..309e9f807725338c461fb5584ed8d9ec40837cdc --- /dev/null +++ b/280m5b95b9/global_step11269/layer_12-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:080497d25276a1c99cd1285fd028f7aecd6ad199d3218107624c9855aff5d793 +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_13-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_13-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0b3875ab813563b0d5f8a667a76feb60583dc41f --- /dev/null +++ b/280m5b95b9/global_step11269/layer_13-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdecd71a83088f364950b62c25ac39bdf8930f31f907bd5f09f9d3257661bfc2 +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_14-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_14-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9ae0deda0e462918b122d25f72f8496ebb0fa193 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_14-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:834c7abe05a114016dc1614bc009b927e4fd5a185f539987c40af63856572e7b +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_15-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_15-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..92d29b89cbcb41ecfb8f95bf198538885a646576 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_15-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:237523fda243c7554817aad82b018e51e28e2e9f25c903c5d9daa0d99a087607 +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_16-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_16-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..65030db3f997aeaee4dd5db9bf2a69cd900a917f --- /dev/null +++ b/280m5b95b9/global_step11269/layer_16-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e2ac6ab030b7935d6a154fbdc98b31b2ffa52a4d9fa762786c31b8a678faa55 +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_17-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_17-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..633983c162b199a8f726042500f31a6a77dfcfd1 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_17-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4770025d6491a23edcba56a588f1f9ab59ccea082783cddb4508c730bd20cac +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_18-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_18-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f9cd963e9efcab79a59672906c52a2ff220fdd5a --- /dev/null +++ b/280m5b95b9/global_step11269/layer_18-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f923cf520008c8faf8c3606c38ecaf893e9472b80202db6ea83a8b2f113fb067 +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_19-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_19-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..185e7e62374d325c8ff816f7396428e15b2e34f5 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_19-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1f5981386dd032125771feabddcb029bce82154c8642bf8724cee8194cc1c69 +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_20-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_20-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ff424bad5c12655e479fe5c1167ef21e7d839517 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_20-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9576a4517c1b523e64d1adb9c8ab449900f35344cc4812b217291eaf97730a5e +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_22-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_22-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d25b9dc082ec3fceca6443eef9225fcb79a96051 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_22-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a60ab374e37b229882ce8c994db4180d8e9ebd4c3c758bfa33a4757843848cb8 +size 5315 diff --git a/280m5b95b9/global_step11269/mp_rank_00_model_states.pt b/280m5b95b9/global_step11269/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d3c640dbf3ade60c5d5a6b06cdc914e040d394bd --- /dev/null +++ b/280m5b95b9/global_step11269/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:703901b18f3a678bdf2212ae69788f50d8fcccfe5d5775d3e6e527dd25bb87fb +size 37427 diff --git a/280m5b95b9/launch.sh b/280m5b95b9/launch.sh new file mode 100755 index 0000000000000000000000000000000000000000..6c3445845a5dae614feb4b8a1206322cd7bd9050 --- /dev/null +++ b/280m5b95b9/launch.sh @@ -0,0 +1,53 @@ +#!/bin/bash + +# Launch script using torch.distributed.run(). Used by slurm +# scripts, don't invoke directly. + +# Samuel's fix for apparent error in SLURM initialization +if [ $SLURM_LOCALID -eq 0 ]; then + rm -rf /dev/shm/* + rocm-smi || true +else + sleep 2 +fi + +export NCCL_SOCKET_IFNAME=hsn0,hsn1,hsn2,hsn3 +export OMP_NUM_THREADS=$SLURM_CPUS_PER_TASK +export FI_CXI_DEFAULT_CQ_SIZE=131072 + +# debugging (noisy) +#export NCCL_DEBUG=INFO +#export RCCL_KERNEL_COLL_TRACE_ENABLE=1 +#export NCCL_DEBUG_SUBSYS=INIT,COLL + +module --quiet purge +module load cray-python + +module load CrayEnv +module load PrgEnv-cray/8.3.3 +module load craype-accel-amd-gfx90a +module load cray-python + +module use /pfs/lustrep2/projappl/project_462000125/samantao-public/mymodules +module load suse-repo-deps/sam-default +module load rocm/sam-5.2.3.lua +module load rccl/sam-develop.lua +module load aws-ofi-rccl/sam-default.lua + +source venv/bin/activate + +MASTER_NODE=$(scontrol show hostnames "$SLURM_JOB_NODELIST" | head -n 1) +MASTER_PORT=9999 + +echo "Launching on $SLURMD_NODENAME ($SLURM_PROCID/$SLURM_JOB_NUM_NODES)," \ + "master $MASTER_NODE port $MASTER_PORT," \ + "GPUs $SLURM_GPUS_ON_NODE," \ + "CUDA: $(python -c 'import torch; print(torch.cuda.is_available())')" + +python -u -m torch.distributed.run \ + --nnodes $SLURM_JOB_NUM_NODES \ + --nproc_per_node $SLURM_GPUS_ON_NODE \ + --node_rank=$SLURM_PROCID \ + --master_addr $MASTER_NODE \ + --master_port $MASTER_PORT \ + "$@" diff --git a/280m5b95b9/logs/2085609.err b/280m5b95b9/logs/2085609.err new file mode 100644 index 0000000000000000000000000000000000000000..886b6851c2a57a37b5fe6375aa9717a19606e9af --- /dev/null +++ b/280m5b95b9/logs/2085609.err @@ -0,0 +1,475 @@ +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module scaled_upper_triang_masked_softmax_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module scaled_upper_triang_masked_softmax_cuda... +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module scaled_masked_softmax_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module scaled_masked_softmax_cuda... +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module fused_mix_prec_layer_norm_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module fused_mix_prec_layer_norm_cuda... +7: Successfully preprocessed all matching files. +7: Successfully preprocessed all matching files. +7: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja... +1: Building extension module utils... +1: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: +2: +2: +2: +2: +2: +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: +5: +5: +5: +5: +5: +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: +6: +6: +6: +6: +6: +6: +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Loading extension module utils... +3: Loading extension module utils... +7: Loading extension module utils... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +0: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +3: Loading extension module utils... +3: Loading extension module utils... +3: Loading extension module utils... +3: Loading extension module utils... +3: Loading extension module utils... +3: Loading extension module utils... +3: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +0: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +6: Loading extension module utils... +5: Loading extension module utils... +6: Loading extension module utils... +5: Loading extension module utils... +6: Loading extension module utils... +5: Loading extension module utils... +6: Loading extension module utils... +5: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +5: Loading extension module utils... +6: Loading extension module utils... +5: Loading extension module utils... +6: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...No modifications detected for re-loaded extension module utils, skipping build step... +1: +1: Loading extension module utils... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +3: +3: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +3: +3: +3: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +3: +3: Loading extension module utils... +3: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: +0: +0: +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +0: +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils...Loading extension module utils... +0: +0: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +0: Loading extension module utils... +0: +0: +0: Loading extension module utils... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +4: +4: Loading extension module utils... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: +4: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +4: +4: Loading extension module utils...Loading extension module utils... +4: +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/utils.py:349: UserWarning: Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings +0: warnings.warn("Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings") diff --git a/280m5b95b9/logs/2085609.out b/280m5b95b9/logs/2085609.out new file mode 100644 index 0000000000000000000000000000000000000000..a6841c85235433333c8cae5b042d8701832711ed --- /dev/null +++ b/280m5b95b9/logs/2085609.out @@ -0,0 +1,5703 @@ +Model parameters: d_model 1024 ffw_size 4096 kv_size 64 n_heads 16 n_layers 18 +Megatron-DeepSpeed/pretrain_gpt.py --tensor-model-parallel-size 1 --pipeline-model-parallel-size 1 --num-layers 18 --hidden-size 1024 --num-attention-heads 16 --kv-channels 64 --ffn-hidden-size 4096 --seq-length 2048 --max-position-embeddings 2048 --micro-batch-size 4 --global-batch-size 256 --train-samples 2_884_878 --vocab-file gpt2/vocab.json --merge-file gpt2/merges.txt --clip-grad 1.0 --kill-switch-path kill-switch-280moscar --bf16 --optimizer adam --adam-beta1 0.9 --adam-beta2 0.999 --adam-eps 1e-8 --lr 2e-4 --min-lr 2e-5 --lr-decay-style cosine --lr-decay-samples 2_884_878 --lr-warmup-samples 28_849 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_280moscar --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_280moscar --load checkpoints_280moscar --data-path /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2085609.json --zero-stage 0 +START 2085609: Tue Nov 29 16:50:08 EET 2022 +0: +0: +0: ======================= ROCm System Management Interface ======================= +0: ================================= Concise Info ================================= +0: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +0: 0 43.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 2 42.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 3 38.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 4 43.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 6 42.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: ================================================================================ +0: ============================= End of ROCm SMI Log ============================== +7: +7: +7: ======================= ROCm System Management Interface ======================= +7: ================================= Concise Info ================================= +7: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +7: 0 42.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 2 45.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 4 42.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 6 42.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: ================================================================================ +7: ============================= End of ROCm SMI Log ============================== +1: +1: +1: ======================= ROCm System Management Interface ======================= +1: ================================= Concise Info ================================= +1: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +1: 0 46.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 2 37.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 4 42.0c 82.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 5 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 6 42.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: ================================================================================ +1: ============================= End of ROCm SMI Log ============================== +5: +5: +5: ======================= ROCm System Management Interface ======================= +5: ================================= Concise Info ================================= +5: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +5: 0 43.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 2 44.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 4 42.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 6 42.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: ================================================================================ +5: ============================= End of ROCm SMI Log ============================== +4: +4: +4: ======================= ROCm System Management Interface ======================= +4: ================================= Concise Info ================================= +4: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +4: 0 44.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 2 45.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 4 48.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 6 38.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: ================================================================================ +4: ============================= End of ROCm SMI Log ============================== +2: +2: +2: ======================= ROCm System Management Interface ======================= +2: ================================= Concise Info ================================= +2: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +2: 0 47.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 2 35.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 4 46.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 6 40.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: ================================================================================ +2: ============================= End of ROCm SMI Log ============================== +3: +3: +3: ======================= ROCm System Management Interface ======================= +3: ================================= Concise Info ================================= +3: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +3: 0 41.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 2 42.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 4 40.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 5 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 6 43.0c 80.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: ================================================================================ +3: ============================= End of ROCm SMI Log ============================== +6: +6: +6: ======================= ROCm System Management Interface ======================= +6: ================================= Concise Info ================================= +6: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +6: 0 42.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 2 43.0c 80.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 3 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 4 44.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 6 38.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: ================================================================================ +6: ============================= End of ROCm SMI Log ============================== +0: Launching on nid005072 (0/8), master nid005072 port 9999, GPUs 8, CUDA: True +5: Launching on nid005077 (5/8), master nid005072 port 9999, GPUs 8, CUDA: True +7: Launching on nid005079 (7/8), master nid005072 port 9999, GPUs 8, CUDA: True +2: Launching on nid005074 (2/8), master nid005072 port 9999, GPUs 8, CUDA: True +4: Launching on nid005076 (4/8), master nid005072 port 9999, GPUs 8, CUDA: True +1: Launching on nid005073 (1/8), master nid005072 port 9999, GPUs 8, CUDA: True +3: Launching on nid005075 (3/8), master nid005072 port 9999, GPUs 8, CUDA: True +6: Launching on nid005078 (6/8), master nid005072 port 9999, GPUs 8, CUDA: True +0: using world size: 64, data-parallel-size: 64, tensor-model-parallel size: 1, pipeline-model-parallel size: 1 +0: accumulate and all-reduce gradients in fp32 for bfloat16 data type. +0: using torch.bfloat16 for parameters ... +0: ------------------------ arguments ------------------------ +0: abort_on_unmet_fused_kernel_constraints ......... False +0: accumulate_allreduce_grads_in_fp32 .............. True +0: adam_beta1 ...................................... 0.9 +0: adam_beta2 ...................................... 0.999 +0: adam_eps ........................................ 1e-08 +0: adlr_autoresume ................................. False +0: adlr_autoresume_interval ........................ 1000 +0: apply_query_key_layer_scaling ................... True +0: apply_residual_connection_post_layernorm ........ False +0: attention_dropout ............................... 0.1 +0: attention_softmax_in_fp32 ....................... False +0: bert_binary_head ................................ True +0: bert_load ....................................... None +0: bf16 ............................................ True +0: bias_dropout_fusion ............................. True +0: bias_gelu_fusion ................................ True +0: biencoder_projection_dim ........................ 0 +0: biencoder_shared_query_context_model ............ False +0: block_data_path ................................. None +0: checkpoint_activations .......................... False +0: checkpoint_in_cpu ............................... False +0: checkpoint_num_layers ........................... 1 +0: clip_grad ....................................... 1.0 +0: codecarbon_dir .................................. None +0: consumed_train_samples .......................... 0 +0: consumed_train_tokens ........................... 0 +0: consumed_valid_samples .......................... 0 +0: contigious_checkpointing ........................ False +0: cpu_optimizer ................................... False +0: cpu_torch_adam .................................. False +0: curriculum_learning ............................. False +0: data_impl ....................................... mmap +0: data_parallel_size .............................. 64 +0: data_path ....................................... ['/scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document'] +0: dataloader_type ................................. single +0: DDP_impl ........................................ local +0: decoder_seq_length .............................. None +0: deepscale ....................................... False +0: deepscale_config ................................ None +0: deepspeed ....................................... True +0: deepspeed_activation_checkpointing .............. False +0: deepspeed_config ................................ ds_configs/2085609.json +0: deepspeed_mpi ................................... False +0: distribute_checkpointed_activations ............. False +0: distributed_backend ............................. nccl +0: embed_layernorm ................................. False +0: embedding_path .................................. None +0: encoder_seq_length .............................. 2048 +0: eod_mask_loss ................................... False +0: eval_interval ................................... 1000 +0: eval_iters ...................................... 1 +0: eval_only ....................................... None +0: evidence_data_path .............................. None +0: exit_duration_in_mins ........................... None +0: exit_interval ................................... None +0: ffn_hidden_size ................................. 4096 +0: finetune ........................................ False +0: fp16 ............................................ False +0: fp16_lm_cross_entropy ........................... False +0: fp32_residual_connection ........................ False +0: gigaflos_no_embeds .............................. 0 +0: global_batch_size ............................... 256 +0: glu_activation .................................. None +0: hidden_dropout .................................. 0.1 +0: hidden_size ..................................... 1024 +0: hysteresis ...................................... 2 +0: ict_head_size ................................... None +0: ict_load ........................................ None +0: img_dim ......................................... 224 +0: indexer_batch_size .............................. 128 +0: indexer_log_interval ............................ 1000 +0: inference ....................................... False +0: init_method_std ................................. 0.02 +0: init_method_xavier_uniform ...................... False +0: initial_loss_scale .............................. 4294967296 +0: kill_switch_path ................................ kill-switch-280moscar +0: kv_channels ..................................... 64 +0: layer_norm_fusion ............................... True +0: layernorm_epsilon ............................... 1e-05 +0: lazy_mpu_init ................................... None +0: load ............................................ checkpoints_280moscar +0: local_rank ...................................... None +0: log_batch_size_to_tensorboard ................... True +0: log_interval .................................... 10 +0: log_learning_rate_to_tensorboard ................ True +0: log_level ....................................... None +0: log_level_replica ............................... None +0: log_loss_scale_to_tensorboard ................... True +0: log_num_zeros_in_grad ........................... False +0: log_params_norm ................................. False +0: log_path ........................................ None +0: log_timers_to_tensorboard ....................... True +0: log_validation_ppl_to_tensorboard ............... True +0: loss_on_targets_only ............................ False +0: loss_scale ...................................... None +0: loss_scale_window ............................... 1000 +0: lr .............................................. 0.0002 +0: lr_decay_iters .................................. None +0: lr_decay_samples ................................ 2884878 +0: lr_decay_style .................................. cosine +0: lr_decay_tokens ................................. None +0: lr_warmup_fraction .............................. None +0: lr_warmup_iters ................................. 0 +0: lr_warmup_samples ............................... 28849 +0: make_vocab_size_divisible_by .................... 128 +0: mask_prob ....................................... 0.15 +0: masked_softmax_fusion ........................... True +0: max_position_embeddings ......................... 2048 +0: mean_noise_span_length .......................... None +0: memory_centric_tiled_linear ..................... False +0: merge_file ...................................... gpt2/merges.txt +0: micro_batch_size ................................ 4 +0: min_loss_scale .................................. 1.0 +0: min_lr .......................................... 2e-05 +0: mmap_warmup ..................................... False +0: no_load_optim ................................... None +0: no_load_rng ..................................... None +0: no_save_optim ................................... None +0: no_save_rng ..................................... None +0: noise_density ................................... None +0: num_attention_heads ............................. 16 +0: num_channels .................................... 3 +0: num_classes ..................................... 1000 +0: num_layers ...................................... 18 +0: num_layers_per_virtual_pipeline_stage ........... None +0: num_workers ..................................... 2 +0: onnx_safe ....................................... None +0: openai_gelu ..................................... False +0: optimizer ....................................... adam +0: optimizer_fusion ................................ True +0: override_lr_scheduler ........................... False +0: pad_vocab_size_to ............................... None +0: params_dtype .................................... torch.bfloat16 +0: partition_activations ........................... False +0: patch_dim ....................................... 16 +0: pipeline_model_parallel_size .................... 1 +0: position_embedding_type ......................... PositionEmbeddingType.absolute +0: pp_partition_method ............................. None +0: profile_backward ................................ False +0: query_in_block_prob ............................. 0.1 +0: rampup_batch_size ............................... None +0: rank ............................................ 0 +0: remote_device ................................... none +0: reset_attention_mask ............................ False +0: reset_position_ids .............................. False +0: retriever_report_topk_accuracies ................ [] +0: retriever_score_scaling ......................... False +0: retriever_seq_length ............................ 256 +0: reweight_loss_based_on_position_frequency ....... False +0: sample_rate ..................................... 1.0 +0: save ............................................ checkpoints_280moscar +0: save_interval ................................... 1000 +0: scatter_gather_tensors_in_pipeline .............. True +0: scattered_embeddings ............................ False +0: seed ............................................ 1234 +0: seq_length ...................................... 2048 +0: sgd_momentum .................................... 0.9 +0: short_seq_prob .................................. 0.1 +0: skip_train_iteration_range ...................... None +0: split ........................................... 949,50,1 +0: split_transformers .............................. False +0: sync_tp_duplicated_parameters ................... False +0: synchronize_each_layer .......................... False +0: tensor_model_parallel_size ...................... 1 +0: tensorboard_dir ................................. tensorboard_280moscar +0: tensorboard_log_interval ........................ 1 +0: tensorboard_queue_size .......................... 5 +0: test_weighted_split_names ....................... None +0: test_weighted_split_paths ....................... None +0: test_weighted_split_paths_path .................. None +0: test_weighted_split_splits ...................... None +0: test_weighted_split_weights ..................... None +0: tile_factor ..................................... 1 +0: titles_data_path ................................ None +0: tokenizer_name_or_path .......................... None +0: tokenizer_type .................................. GPT2BPETokenizer +0: train_iters ..................................... None +0: train_samples ................................... 2884878 +0: train_tokens .................................... None +0: train_weighted_split_paths ...................... None +0: train_weighted_split_paths_path ................. None +0: universal_checkpoint ............................ False +0: use_bnb_optimizer ............................... False +0: use_checkpoint_lr_scheduler ..................... False +0: use_contiguous_buffers_in_ddp ................... True +0: use_cpu_initialization .......................... None +0: use_one_sent_docs ............................... False +0: use_pin_memory .................................. False +0: valid_num_workers ............................... 2 +0: valid_weighted_split_names ...................... None +0: valid_weighted_split_paths ...................... None +0: valid_weighted_split_paths_path ................. None +0: valid_weighted_split_splits ..................... None +0: valid_weighted_split_weights .................... None +0: virtual_pipeline_model_parallel_size ............ None +0: vocab_extra_ids ................................. 0 +0: vocab_file ...................................... gpt2/vocab.json +0: weight_decay .................................... 0.1 +0: world_size ...................................... 64 +0: zero_allgather_bucket_size ...................... 0.0 +0: zero_contigious_gradients ....................... False +0: zero_reduce_bucket_size ......................... 0.0 +0: zero_reduce_scatter ............................. False +0: zero_stage ...................................... 0 +0: -------------------- end of arguments --------------------- +0: setting number of micro-batches to constant 1 +0: > building GPT2BPETokenizer tokenizer ... +0: > padded vocab (size: 50257) with 47 dummy tokens (new size: 50304) +0: DeepSpeed general environment info: +0: torch install path ............... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch'] +0: torch version .................... 1.13.0+rocm5.2 +0: torch cuda version ............... None +0: torch hip version ................ 5.2.21151-afdc89f8 +0: nvcc version ..................... None +0: deepspeed install path ........... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed'] +0: deepspeed info ................... 0.7.5, unknown, unknown +0: deepspeed wheel compiled w. ...... torch 1.13, hip 5.1 +0: **** Git info for Megatron: git_hash=unknown git_branch=unknown **** +0: > initializing torch distributed ... +0: [2022-11-29 16:50:29,405] [INFO] [comm.py:633:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +7: > setting tensorboard ... +0: > initializing tensor model parallel with size 1 +0: > initializing pipeline model parallel with size 1 +0: > setting random seeds to 1234 ... +0: > initializing model parallel cuda seeds on global rank 0, model parallel rank 0, and data parallel rank 0 with model parallel seed: 3952 and data parallel seed: 1234 +0: > compiling dataset index builder ... +0: make: Entering directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' +0: make: Nothing to be done for 'default'. +0: make: Leaving directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' +0: >>> done with dataset index builder. Compilation time: 0.077 seconds +0: > compiling and loading fused kernels ... +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.cpp [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 87 +0: [1/1] c++ scaled_upper_triang_masked_softmax_hip.o scaled_upper_triang_masked_softmax_hip.cuda.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib -lamdhip64 -o scaled_upper_triang_masked_softmax_cuda.so +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.cpp [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 63 +0: [1/1] c++ scaled_masked_softmax_hip.o scaled_masked_softmax_hip.cuda.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib -lamdhip64 -o scaled_masked_softmax_cuda.so +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda_kernel.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_hip_kernel.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 67 +0: ninja: no work to do. +0: >>> done with compiling and loading fused kernels. Compilation time: 13.854 seconds +0: time to initialize megatron (seconds): 70.355 +0: [after megatron is initialized] datetime: 2022-11-29 16:50:46 +0: building GPT model ... +0: [2022-11-29 16:50:46,410] [INFO] [utils.py:827:see_memory_usage] Before Building Model +0: [2022-11-29 16:50:46,410] [INFO] [utils.py:828:see_memory_usage] MA 0.0 GB Max_MA 0.0 GB CA 0.0 GB Max_CA 0 GB +0: [2022-11-29 16:50:46,410] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 29.34 GB, percent = 5.8% +0: SEED_LAYERS=False BASE_SEED=1234 SEED_FN=None +0: Using topology: {ProcessCoord(pipe=0, data=0, model=0): 0, ProcessCoord(pipe=0, data=1, model=0): 1, ProcessCoord(pipe=0, data=2, model=0): 2, ProcessCoord(pipe=0, data=3, model=0): 3, ProcessCoord(pipe=0, data=4, model=0): 4, ProcessCoord(pipe=0, data=5, model=0): 5, ProcessCoord(pipe=0, data=6, model=0): 6, ProcessCoord(pipe=0, data=7, model=0): 7, ProcessCoord(pipe=0, data=8, model=0): 8, ProcessCoord(pipe=0, data=9, model=0): 9, ProcessCoord(pipe=0, data=10, model=0): 10, ProcessCoord(pipe=0, data=11, model=0): 11, ProcessCoord(pipe=0, data=12, model=0): 12, ProcessCoord(pipe=0, data=13, model=0): 13, ProcessCoord(pipe=0, data=14, model=0): 14, ProcessCoord(pipe=0, data=15, model=0): 15, ProcessCoord(pipe=0, data=16, model=0): 16, ProcessCoord(pipe=0, data=17, model=0): 17, ProcessCoord(pipe=0, data=18, model=0): 18, ProcessCoord(pipe=0, data=19, model=0): 19, ProcessCoord(pipe=0, data=20, model=0): 20, ProcessCoord(pipe=0, data=21, model=0): 21, ProcessCoord(pipe=0, data=22, model=0): 22, ProcessCoord(pi +0: pe=0, data=23, model=0): 23, ProcessCoord(pipe=0, data=24, model=0): 24, ProcessCoord(pipe=0, data=25, model=0): 25, ProcessCoord(pipe=0, data=26, model=0): 26, ProcessCoord(pipe=0, data=27, model=0): 27, ProcessCoord(pipe=0, data=28, model=0): 28, ProcessCoord(pipe=0, data=29, model=0): 29, ProcessCoord(pipe=0, data=30, model=0): 30, ProcessCoord(pipe=0, data=31, model=0): 31, ProcessCoord(pipe=0, data=32, model=0): 32, ProcessCoord(pipe=0, data=33, model=0): 33, ProcessCoord(pipe=0, data=34, model=0): 34, ProcessCoord(pipe=0, data=35, model=0): 35, ProcessCoord(pipe=0, data=36, model=0): 36, ProcessCoord(pipe=0, data=37, model=0): 37, ProcessCoord(pipe=0, data=38, model=0): 38, ProcessCoord(pipe=0, data=39, model=0): 39, ProcessCoord(pipe=0, data=40, model=0): 40, ProcessCoord(pipe=0, data=41, model=0): 41, ProcessCoord(pipe=0, data=42, model=0): 42, ProcessCoord(pipe=0, data=43, model=0): 43, ProcessCoord(pipe=0, data=44, model=0): 44, ProcessCoord(pipe=0, data=45, model=0): 45, ProcessCoord(pipe=0, data=4 +0: 6, model=0): 46, ProcessCoord(pipe=0, data=47, model=0): 47, ProcessCoord(pipe=0, data=48, model=0): 48, ProcessCoord(pipe=0, data=49, model=0): 49, ProcessCoord(pipe=0, data=50, model=0): 50, ProcessCoord(pipe=0, data=51, model=0): 51, ProcessCoord(pipe=0, data=52, model=0): 52, ProcessCoord(pipe=0, data=53, model=0): 53, ProcessCoord(pipe=0, data=54, model=0): 54, ProcessCoord(pipe=0, data=55, model=0): 55, ProcessCoord(pipe=0, data=56, model=0): 56, ProcessCoord(pipe=0, data=57, model=0): 57, ProcessCoord(pipe=0, data=58, model=0): 58, ProcessCoord(pipe=0, data=59, model=0): 59, ProcessCoord(pipe=0, data=60, model=0): 60, ProcessCoord(pipe=0, data=61, model=0): 61, ProcessCoord(pipe=0, data=62, model=0): 62, ProcessCoord(pipe=0, data=63, model=0): 63} +0: [2022-11-29 16:50:48,423] [INFO] [module.py:366:_partition_layers] Partitioning pipeline stages with method type:transformer +0: stage=0 layers=25 +0: 0: _to_float16 +0: 1: EmbeddingPipe +0: 2: +0: 3: ParallelTransformerLayerPipe +0: 4: ParallelTransformerLayerPipe +0: 5: ParallelTransformerLayerPipe +0: 6: ParallelTransformerLayerPipe +0: 7: ParallelTransformerLayerPipe +0: 8: ParallelTransformerLayerPipe +0: 9: ParallelTransformerLayerPipe +0: 10: ParallelTransformerLayerPipe +0: 11: ParallelTransformerLayerPipe +0: 12: ParallelTransformerLayerPipe +0: 13: ParallelTransformerLayerPipe +0: 14: ParallelTransformerLayerPipe +0: 15: ParallelTransformerLayerPipe +0: 16: ParallelTransformerLayerPipe +0: 17: ParallelTransformerLayerPipe +0: 18: ParallelTransformerLayerPipe +0: 19: ParallelTransformerLayerPipe +0: 20: ParallelTransformerLayerPipe +0: 21: undo +0: 22: MixedFusedLayerNorm +0: 23: EmbeddingPipe +0: 24: float16_to_fp32 +0: loss: CrossEntropy +0: [2022-11-29 16:50:48,559] [INFO] [utils.py:827:see_memory_usage] After Building Model +0: [2022-11-29 16:50:48,559] [INFO] [utils.py:828:see_memory_usage] MA 0.53 GB Max_MA 0.53 GB CA 0.57 GB Max_CA 1 GB +0: [2022-11-29 16:50:48,559] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 29.36 GB, percent = 5.8% +0: setting training iterations to 11269 +0: > learning rate decay style: cosine +0: DeepSpeed is enabled. +0: [2022-11-29 16:50:48,561] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed info: version=0.7.5, git-hash=unknown, git-branch=unknown +0: [2022-11-29 16:51:00,210] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False +0: [2022-11-29 16:51:00,211] [INFO] [logging.py:68:log_dist] [Rank 0] Removing param_group that has no 'params' in the client Optimizer +0: [2022-11-29 16:51:00,211] [INFO] [logging.py:68:log_dist] [Rank 0] Using client Optimizer as basic optimizer +0: [2022-11-29 16:51:00,217] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Basic Optimizer = FusedAdam +0: [2022-11-29 16:51:00,217] [INFO] [logging.py:68:log_dist] [Rank 0] Creating BF16 optimizer +0: [2022-11-29 16:51:00,260] [INFO] [utils.py:827:see_memory_usage] begin bf16_optimizer +0: [2022-11-29 16:51:00,261] [INFO] [utils.py:828:see_memory_usage] MA 0.52 GB Max_MA 0.53 GB CA 0.57 GB Max_CA 1 GB +0: [2022-11-29 16:51:00,261] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.04 GB, percent = 6.0% +1: ninja: no work to do. +1: Time to load utils op: 0.16243410110473633 seconds +3: Time to load utils op: 0.2097475528717041 seconds +7: Time to load utils op: 0.2096853256225586 seconds +1: Time to load utils op: 0.0009136199951171875 seconds +1: Time to load utils op: 0.10221242904663086 secondsTime to load utils op: 0.10139298439025879 seconds +1: +1: Time to load utils op: 0.10212540626525879 seconds +1: Time to load utils op: 0.10247373580932617 seconds +1: Time to load utils op: 0.10174679756164551 seconds +1: Time to load utils op: 0.10164833068847656 seconds +1: Time to load utils op: 0.10143160820007324 seconds +3: Time to load utils op: 0.10190868377685547 seconds +3: Time to load utils op: 0.10239911079406738 seconds +3: Time to load utils op: 0.10186457633972168 seconds +3: Time to load utils op: 0.10216951370239258 secondsTime to load utils op: 0.10265207290649414 seconds +3: +3: Time to load utils op: 0.10231947898864746 seconds +3: Time to load utils op: 0.10222434997558594 seconds +7: Time to load utils op: 0.10243964195251465 seconds +0: Time to load utils op: 0.10985040664672852 seconds +0: Time to load utils op: 0.1103217601776123 secondsTime to load utils op: 0.11018490791320801 seconds +0: Time to load utils op: 0.10999393463134766 seconds +0: +7: Time to load utils op: 0.10239076614379883 seconds +0: Time to load utils op: 0.11001873016357422 secondsTime to load utils op: 0.11012792587280273 seconds +0: +0: Time to load utils op: 0.11023497581481934 seconds +7: Time to load utils op: 0.10150861740112305 seconds +7: Time to load utils op: 0.10181999206542969 seconds +7: Time to load utils op: 0.1021585464477539 seconds +7: Time to load utils op: 0.1029818058013916 seconds +7: Time to load utils op: 0.10263967514038086 seconds +0: Time to load utils op: 0.2037360668182373 seconds +2: Time to load utils op: 0.11113739013671875 seconds +2: Time to load utils op: 0.11114501953125 seconds +2: Time to load utils op: 0.11114907264709473 seconds +2: Time to load utils op: 0.1111598014831543 seconds +2: Time to load utils op: 0.11117243766784668 secondsTime to load utils op: 0.11117148399353027 seconds +2: +2: Time to load utils op: 0.11118102073669434 seconds +2: Time to load utils op: 0.11118650436401367 seconds +4: Time to load utils op: 0.10821104049682617 secondsTime to load utils op: 0.10909414291381836 secondsTime to load utils op: 0.10909271240234375 seconds +4: +4: +4: Time to load utils op: 0.10311198234558105 seconds +4: Time to load utils op: 0.10324478149414062 seconds +4: Time to load utils op: 0.10311770439147949 seconds +1: Time to load utils op: 0.0003421306610107422 seconds +1: Time to load utils op: 0.0003418922424316406 seconds +1: Time to load utils op: 0.0003428459167480469 seconds +1: Time to load utils op: 0.00043082237243652344 seconds +4: Time to load utils op: 0.10257172584533691 seconds +1: Time to load utils op: 0.0003917217254638672 seconds +1: Time to load utils op: 0.0003764629364013672 seconds +4: Time to load utils op: 0.10251522064208984 seconds +1: Time to load utils op: 0.00039386749267578125 seconds +6: Time to load utils op: 0.11052584648132324 seconds +6: Time to load utils op: 0.11053204536437988 seconds +6: Time to load utils op: 0.11056637763977051 secondsTime to load utils op: 0.11057090759277344 seconds +6: +6: Time to load utils op: 0.11058521270751953 seconds +6: Time to load utils op: 0.11060094833374023 secondsTime to load utils op: 0.11059379577636719 seconds +6: +6: Time to load utils op: 0.11060070991516113 seconds +5: Time to load utils op: 0.11212682723999023 seconds +5: Time to load utils op: 0.11212849617004395 secondsTime to load utils op: 0.11213397979736328 seconds +5: +5: Time to load utils op: 0.11214184761047363 seconds +5: Time to load utils op: 0.11214280128479004 seconds +5: Time to load utils op: 0.11215972900390625 seconds +5: Time to load utils op: 0.11216521263122559 secondsTime to load utils op: 0.11217427253723145 seconds +5: +7: Time to load utils op: 0.0004506111145019531 seconds +7: Time to load utils op: 0.000370025634765625 seconds +7: Time to load utils op: 0.0004875659942626953 seconds +7: Time to load utils op: 0.0005223751068115234 seconds +7: Time to load utils op: 0.0005371570587158203 seconds +7: Time to load utils op: 0.0005335807800292969 seconds +7: Time to load utils op: 0.0005497932434082031 seconds +7: Time to load utils op: 0.00034046173095703125 seconds +3: Time to load utils op: 0.00047659873962402344 seconds +3: Time to load utils op: 0.0005040168762207031 seconds +3: Time to load utils op: 0.0005459785461425781 seconds +3: Time to load utils op: 0.0005788803100585938 secondsTime to load utils op: 0.0005326271057128906 secondsTime to load utils op: 0.000576019287109375 seconds +3: +3: +3: Time to load utils op: 0.0006222724914550781 secondsTime to load utils op: 0.0006406307220458984 seconds +3: +0: [2022-11-29 16:51:00,501] [INFO] [utils.py:827:see_memory_usage] before initializing group 0 +0: [2022-11-29 16:51:00,502] [INFO] [utils.py:828:see_memory_usage] MA 0.52 GB Max_MA 0.52 GB CA 0.57 GB Max_CA 1 GB +0: [2022-11-29 16:51:00,502] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.04 GB, percent = 6.0% +0: Time to load utils op: 0.00044536590576171875 seconds +0: Time to load utils op: 0.0004513263702392578 seconds +0: Time to load utils op: 0.00046944618225097656 seconds +0: Time to load utils op: 0.00043964385986328125 secondsTime to load utils op: 0.00047206878662109375 secondsTime to load utils op: 0.00044846534729003906 seconds +0: +0: +0: Time to load utils op: 0.0005216598510742188 seconds +6: Time to load utils op: 0.0008327960968017578 seconds +2: Time to load utils op: 0.001188516616821289 secondsTime to load utils op: 0.0011987686157226562 seconds +2: +6: Time to load utils op: 0.0011780261993408203 seconds +6: Time to load utils op: 0.00121307373046875 seconds +6: Time to load utils op: 0.001230478286743164 seconds +6: Time to load utils op: 0.0012059211730957031 seconds +6: Time to load utils op: 0.0012998580932617188 seconds +6: Time to load utils op: 0.0011780261993408203 seconds +6: Time to load utils op: 0.001291513442993164 seconds +2: Time to load utils op: 0.0014619827270507812 seconds +2: Time to load utils op: 0.0014231204986572266 seconds +2: Time to load utils op: 0.001439809799194336 seconds +2: Time to load utils op: 0.0014574527740478516 secondsTime to load utils op: 0.0014297962188720703 seconds +2: +2: Time to load utils op: 0.0014960765838623047 seconds +5: Time to load utils op: 0.0006690025329589844 seconds +5: Time to load utils op: 0.0009007453918457031 seconds +5: Time to load utils op: 0.0009245872497558594 secondsTime to load utils op: 0.0009043216705322266 seconds +5: Time to load utils op: 0.0008988380432128906 seconds +5: +5: Time to load utils op: 0.000989675521850586 secondsTime to load utils op: 0.0010607242584228516 seconds +5: +5: Time to load utils op: 0.001100778579711914 seconds +4: Time to load utils op: 0.0005459785461425781 seconds +4: Time to load utils op: 0.000415802001953125 seconds +4: Time to load utils op: 0.0006129741668701172 seconds +4: Time to load utils op: 0.00047588348388671875 seconds +4: Time to load utils op: 0.00048470497131347656 seconds +4: Time to load utils op: 0.0004985332489013672 seconds +4: Time to load utils op: 0.0005288124084472656 secondsTime to load utils op: 0.0005245208740234375 seconds +4: +0: [2022-11-29 16:51:00,557] [INFO] [utils.py:827:see_memory_usage] after initializing group 0 +0: [2022-11-29 16:51:00,558] [INFO] [utils.py:828:see_memory_usage] MA 1.14 GB Max_MA 1.14 GB CA 1.48 GB Max_CA 1 GB +0: [2022-11-29 16:51:00,558] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.17 GB, percent = 6.0% +0: [2022-11-29 16:51:00,595] [INFO] [utils.py:827:see_memory_usage] before initializing group 1 +0: [2022-11-29 16:51:00,595] [INFO] [utils.py:828:see_memory_usage] MA 1.14 GB Max_MA 1.14 GB CA 1.48 GB Max_CA 1 GB +0: [2022-11-29 16:51:00,595] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.18 GB, percent = 6.0% +0: [2022-11-29 16:51:00,630] [INFO] [utils.py:827:see_memory_usage] after initializing group 1 +0: [2022-11-29 16:51:00,631] [INFO] [utils.py:828:see_memory_usage] MA 1.58 GB Max_MA 1.58 GB CA 2.14 GB Max_CA 2 GB +0: [2022-11-29 16:51:00,631] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.18 GB, percent = 6.0% +0: [2022-11-29 16:51:00,664] [INFO] [utils.py:827:see_memory_usage] before initializing group 2 +0: [2022-11-29 16:51:00,664] [INFO] [utils.py:828:see_memory_usage] MA 1.58 GB Max_MA 1.58 GB CA 2.14 GB Max_CA 2 GB +0: [2022-11-29 16:51:00,664] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.18 GB, percent = 6.0% +0: [2022-11-29 16:51:00,699] [INFO] [utils.py:827:see_memory_usage] after initializing group 2 +0: [2022-11-29 16:51:00,700] [INFO] [utils.py:828:see_memory_usage] MA 1.58 GB Max_MA 1.58 GB CA 2.14 GB Max_CA 2 GB +0: [2022-11-29 16:51:00,700] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.18 GB, percent = 6.0% +0: [2022-11-29 16:51:00,732] [INFO] [utils.py:827:see_memory_usage] before initialize_optimizer +0: [2022-11-29 16:51:00,732] [INFO] [utils.py:828:see_memory_usage] MA 1.58 GB Max_MA 1.58 GB CA 2.14 GB Max_CA 2 GB +0: [2022-11-29 16:51:00,733] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.18 GB, percent = 6.0% +0: [2022-11-29 16:51:00,770] [INFO] [utils.py:827:see_memory_usage] end initialize_optimizer +0: [2022-11-29 16:51:00,770] [INFO] [utils.py:828:see_memory_usage] MA 1.62 GB Max_MA 1.62 GB CA 2.14 GB Max_CA 2 GB +0: [2022-11-29 16:51:00,770] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.18 GB, percent = 6.0% +0: [2022-11-29 16:51:00,802] [INFO] [utils.py:827:see_memory_usage] end bf16_optimizer +0: [2022-11-29 16:51:00,803] [INFO] [utils.py:828:see_memory_usage] MA 1.62 GB Max_MA 1.62 GB CA 2.14 GB Max_CA 2 GB +0: [2022-11-29 16:51:00,803] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.18 GB, percent = 6.0% +0: [2022-11-29 16:51:00,803] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Final Optimizer = FusedAdam +0: [2022-11-29 16:51:00,803] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed using client LR scheduler +0: [2022-11-29 16:51:00,803] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed LR Scheduler = +0: [2022-11-29 16:51:00,803] [INFO] [logging.py:68:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0, 0.0, 0.0], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +0: [2022-11-29 16:51:00,804] [INFO] [config.py:1007:print] DeepSpeedEngine configuration: +0: [2022-11-29 16:51:00,804] [INFO] [config.py:1011:print] activation_checkpointing_config { +0: "partition_activations": false, +0: "contiguous_memory_optimization": false, +0: "cpu_checkpointing": false, +0: "number_checkpoints": null, +0: "synchronize_checkpoint_boundary": false, +0: "profile": false +0: } +0: [2022-11-29 16:51:00,804] [INFO] [config.py:1011:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True} +0: [2022-11-29 16:51:00,804] [INFO] [config.py:1011:print] amp_enabled .................. False +0: [2022-11-29 16:51:00,804] [INFO] [config.py:1011:print] amp_params ................... False +0: [2022-11-29 16:51:00,804] [INFO] [config.py:1011:print] autotuning_config ............ { +0: "enabled": false, +0: "start_step": null, +0: "end_step": null, +0: "metric_path": null, +0: "arg_mappings": null, +0: "metric": "throughput", +0: "model_info": null, +0: "results_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_results", +0: "exps_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_exps", +0: "overwrite": true, +0: "fast": true, +0: "start_profile_step": 3, +0: "end_profile_step": 5, +0: "tuner_type": "gridsearch", +0: "tuner_early_stopping": 5, +0: "tuner_num_trials": 50, +0: "model_info_path": null, +0: "mp_size": 1, +0: "max_train_batch_size": null, +0: "min_train_batch_size": 1, +0: "max_train_micro_batch_size_per_gpu": 1.024000e+03, +0: "min_train_micro_batch_size_per_gpu": 1, +0: "num_tuning_micro_batch_sizes": 3 +0: } +0: [2022-11-29 16:51:00,804] [INFO] [config.py:1011:print] bfloat16_enabled ............. True +0: [2022-11-29 16:51:00,804] [INFO] [config.py:1011:print] checkpoint_parallel_write_pipeline False +0: [2022-11-29 16:51:00,804] [INFO] [config.py:1011:print] checkpoint_tag_validation_enabled True +0: [2022-11-29 16:51:00,804] [INFO] [config.py:1011:print] checkpoint_tag_validation_fail False +0: [2022-11-29 16:51:00,804] [INFO] [config.py:1011:print] comms_config ................. +0: [2022-11-29 16:51:00,804] [INFO] [config.py:1011:print] communication_data_type ...... None +0: [2022-11-29 16:51:00,804] [INFO] [config.py:1011:print] compression_config ........... {'weight_quantization': {'shared_parameters': {'enabled': False, 'quantizer_kernel': False, 'schedule_offset': 0, 'quantize_groups': 1, 'quantize_verbose': False, 'quantization_type': 'symmetric', 'quantize_weight_in_forward': False, 'rounding': 'nearest', 'fp16_mixed_quantize': False, 'quantize_change_ratio': 0.001}, 'different_groups': {}}, 'activation_quantization': {'shared_parameters': {'enabled': False, 'quantization_type': 'symmetric', 'range_calibration': 'dynamic', 'schedule_offset': 1000}, 'different_groups': {}}, 'sparse_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'row_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'head_pruning': {'shared_parameters': {'enabled': False, 'method': 'topk', 'schedule_offset': 1000}, 'different_groups': {}}, 'channel_pruning': {'shared_pa +0: rameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'layer_reduction': {'enabled': False}} +0: [2022-11-29 16:51:00,804] [INFO] [config.py:1011:print] curriculum_enabled ........... False +0: [2022-11-29 16:51:00,804] [INFO] [config.py:1011:print] curriculum_params ............ False +0: [2022-11-29 16:51:00,804] [INFO] [config.py:1011:print] dataloader_drop_last ......... False +0: [2022-11-29 16:51:00,804] [INFO] [config.py:1011:print] disable_allgather ............ False +0: [2022-11-29 16:51:00,804] [INFO] [config.py:1011:print] dump_state ................... False +0: [2022-11-29 16:51:00,804] [INFO] [config.py:1011:print] dynamic_loss_scale_args ...... None +0: [2022-11-29 16:51:00,804] [INFO] [config.py:1011:print] eigenvalue_enabled ........... False +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] eigenvalue_gas_boundary_resolution 1 +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] eigenvalue_layer_name ........ bert.encoder.layer +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] eigenvalue_layer_num ......... 0 +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] eigenvalue_max_iter .......... 100 +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] eigenvalue_stability ......... 1e-06 +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] eigenvalue_tol ............... 0.01 +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] eigenvalue_verbose ........... False +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] elasticity_enabled ........... False +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] flops_profiler_config ........ { +0: "enabled": false, +0: "profile_step": 1, +0: "module_depth": -1, +0: "top_modules": 1, +0: "detailed": true, +0: "output_file": null +0: } +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] fp16_auto_cast ............... None +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] fp16_enabled ................. False +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] fp16_master_weights_and_gradients False +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] global_rank .................. 0 +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] gradient_accumulation_steps .. 1 +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] gradient_clipping ............ 1.0 +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] gradient_predivide_factor .... 1.0 +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] initial_dynamic_scale ........ 1 +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] load_universal_checkpoint .... False +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] loss_scale ................... 1.0 +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] memory_breakdown ............. False +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] monitor_config ............... +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] nebula_config ................ { +0: "enabled": false, +0: "persistent_storage_path": null, +0: "persistent_time_interval": 100, +0: "num_of_version_in_retention": 2, +0: "enable_nebula_load": true, +0: "load_path": null +0: } +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] optimizer_legacy_fusion ...... False +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] optimizer_name ............... None +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] optimizer_params ............. None +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0} +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] pld_enabled .................. False +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] pld_params ................... False +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] prescale_gradients ........... False +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] scheduler_name ............... None +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] scheduler_params ............. None +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] sparse_attention ............. None +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] sparse_gradients_enabled ..... False +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] steps_per_print .............. 2000 +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] train_batch_size ............. 256 +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] train_micro_batch_size_per_gpu 4 +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] use_node_local_storage ....... False +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] wall_clock_breakdown ......... False +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] world_size ................... 64 +0: [2022-11-29 16:51:00,805] [INFO] [config.py:1011:print] zero_allow_untested_optimizer False +0: [2022-11-29 16:51:00,806] [INFO] [config.py:1011:print] zero_config .................. stage=0 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=500000000 allgather_partitions=True allgather_bucket_size=500000000 overlap_comm=False load_from_fp32_weights=True elastic_checkpoint=False offload_param=None offload_optimizer=None sub_group_size=1000000000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=50000000 param_persistence_threshold=100000 model_persistence_threshold=9223372036854775807 max_live_parameters=1000000000 max_reuse_distance=1000000000 gather_16bit_weights_on_model_save=False stage3_gather_fp16_weights_on_model_save=False ignore_unused_parameters=True legacy_stage1=False round_robin_gradients=False +0: [2022-11-29 16:51:00,806] [INFO] [config.py:1011:print] zero_enabled ................. False +0: [2022-11-29 16:51:00,806] [INFO] [config.py:1011:print] zero_optimization_stage ...... 0 +0: [2022-11-29 16:51:00,806] [INFO] [config.py:996:print_user_config] json = { +0: "train_micro_batch_size_per_gpu": 4, +0: "train_batch_size": 256, +0: "gradient_clipping": 1.0, +0: "zero_optimization": { +0: "stage": 0 +0: }, +0: "bf16": { +0: "enabled": true +0: }, +0: "steps_per_print": 2.000000e+03, +0: "wall_clock_breakdown": false +0: } +0: Time to load utils op: 0.0004215240478515625 seconds +0: [2022-11-29 16:51:00,806] [INFO] [engine.py:87:__init__] CONFIG: micro_batches=1 micro_batch_size=4 +0: [2022-11-29 16:51:00,817] [INFO] [engine.py:145:__init__] RANK=0 STAGE=0 LAYERS=25 [0, 25) STAGE_PARAMS=280342528 (280.343M) TOTAL_PARAMS=280342528 (280.343M) UNIQUE_PARAMS=280342528 (280.343M) +0: [2022-11-29 16:51:00,823] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:51:00,823] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 16:51:00,823] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 16:51:00,823] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 16:51:00,823] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: WARNING: could not find the metadata file checkpoints_280moscar +0: will not load any checkpoints and will start from random +3: [2022-11-29 16:51:00,823] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:51:00,823] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:51:00,823] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 16:51:00,823] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 16:51:00,823] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:51:00,823] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 16:51:00,823] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 16:51:00,823] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 16:51:00,823] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 16:51:00,823] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:51:00,823] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 16:51:00,823] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 16:51:00,823] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:51:00,825] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 16:51:00,824] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:51:00,825] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:51:00,825] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_280moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: time (ms) | load-checkpoint: 6.41 +0: estimated model parameters: 0.280342528 +0: estimated model parameters without embeddings: 0.22673408 +0: [after model, optimizer, and learning rate scheduler are built] datetime: 2022-11-29 16:51:01 +0: > building train, validation, and test datasets ... +0: > datasets target sizes (minimum size): +0: train: 2884878 +0: validation: 3072 +0: test: 256 +0: > building train, validation, and test datasets for GPT ... +0: > building dataset index ... +0: reading sizes... +0: reading pointers... +0: reading document index... +0: creating numpy buffer of mmap... +0: creating memory view of numpy buffer... +0: > finished creating indexed dataset in 0.017917 seconds +0: number of documents: 431992659 +0: > dataset split: +0: train: +0: document indices in [0, 409961033) total of 409961033 documents +0: validation: +0: document indices in [409961033, 431560666) total of 21599633 documents +0: test: +0: document indices in [431560666, 431992659) total of 431993 documents +0: > WARNING: could not find index map files, building the indices on rank 0 ... +0: > only one epoch required, setting separate_last_epoch to False +0: > elasped time to build and save doc-idx mapping (seconds): 30.499815 +0: using: +0: number of documents: 409961033 +0: number of epochs: 1 +0: sequence length: 2048 +0: total number of samples: 262636457 +0: > elasped time to build and save sample-idx mapping (seconds): 7.767112 +0: > building shuffle index with split [0, 262636457) and [262636457, 262636457) ... +0: > elasped time to build and save shuffle-idx mapping (seconds): 16.050910 +0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_2884878ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_2884878ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_2884878ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.990 seconds +0: total number of samples: 262636458 +0: total number of epochs: 1 +0: > WARNING: could not find index map files, building the indices on rank 0 ... +0: > only one epoch required, setting separate_last_epoch to False +0: > elasped time to build and save doc-idx mapping (seconds): 1.289695 +0: using: +0: number of documents: 21599633 +0: number of epochs: 1 +0: sequence length: 2048 +0: total number of samples: 13852049 +0: > elasped time to build and save sample-idx mapping (seconds): 0.416417 +0: > building shuffle index with split [0, 13852049) and [13852049, 13852049) ... +0: > elasped time to build and save shuffle-idx mapping (seconds): 0.503516 +0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_3072ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_3072ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_3072ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.057 seconds +0: total number of samples: 13852050 +0: total number of epochs: 1 +0: > WARNING: could not find index map files, building the indices on rank 0 ... +0: > only one epoch required, setting separate_last_epoch to False +0: > elasped time to build and save doc-idx mapping (seconds): 0.014962 +0: using: +0: number of documents: 431993 +0: number of epochs: 1 +0: sequence length: 2048 +0: total number of samples: 276851 +0: > elasped time to build and save sample-idx mapping (seconds): 0.006079 +0: > building shuffle index with split [0, 276851) and [276851, 276851) ... +0: > elasped time to build and save shuffle-idx mapping (seconds): 0.007364 +0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_256ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_256ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_256ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.013 seconds +0: total number of samples: 276852 +0: total number of epochs: 1 +0: > finished creating GPT datasets ... +0: [after dataloaders are built] datetime: 2022-11-29 16:52:25 +0: done with setup ... +0: training ... +0: Number of parameters: [tensor rank - pipeline rank] w/ and w/o embeddings: +7: time (ms) | model-and-optimizer-setup: 14644.24 | train/valid/test-data-iterators-setup: 84768.25 +0: [000-000] 0.2803B / 0.2267B +0: [before the start of training step] datetime: 2022-11-29 16:52:25 +0: [Rank 0] (after 10 iterations) memory (MB) | allocated: 3766.3056640625 | max allocated: 34106.49267578125 | reserved: 35064.0 | max reserved: 35064.0 +7: iteration 10/ 11269 | consumed samples: 2560 | consumed tokens: 5242880 | elapsed time per iteration (s): 1.77 | learning rate: 1.775E-05 | global batch size: 256 | lm loss: 1.032044E+01 | grad norm: 2.971 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 144.271 | TFLOPs: 9.44 | +7: iteration 20/ 11269 | consumed samples: 5120 | consumed tokens: 10485760 | elapsed time per iteration (s): 0.49 | learning rate: 3.550E-05 | global batch size: 256 | lm loss: 9.399584E+00 | grad norm: 1.808 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.090 | TFLOPs: 34.41 | +7: iteration 30/ 11269 | consumed samples: 7680 | consumed tokens: 15728640 | elapsed time per iteration (s): 0.53 | learning rate: 5.324E-05 | global batch size: 256 | lm loss: 8.949076E+00 | grad norm: 3.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 483.637 | TFLOPs: 31.63 | +7: iteration 40/ 11269 | consumed samples: 10240 | consumed tokens: 20971520 | elapsed time per iteration (s): 0.50 | learning rate: 7.099E-05 | global batch size: 256 | lm loss: 8.363860E+00 | grad norm: 1.560 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 509.601 | TFLOPs: 33.33 | +7: iteration 50/ 11269 | consumed samples: 12800 | consumed tokens: 26214400 | elapsed time per iteration (s): 0.50 | learning rate: 8.874E-05 | global batch size: 256 | lm loss: 7.831068E+00 | grad norm: 1.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 513.821 | TFLOPs: 33.60 | +7: iteration 60/ 11269 | consumed samples: 15360 | consumed tokens: 31457280 | elapsed time per iteration (s): 0.49 | learning rate: 1.065E-04 | global batch size: 256 | lm loss: 7.441724E+00 | grad norm: 0.727 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.369 | TFLOPs: 34.10 | +7: iteration 70/ 11269 | consumed samples: 17920 | consumed tokens: 36700160 | elapsed time per iteration (s): 0.50 | learning rate: 1.242E-04 | global batch size: 256 | lm loss: 7.219479E+00 | grad norm: 1.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 513.996 | TFLOPs: 33.62 | +7: iteration 80/ 11269 | consumed samples: 20480 | consumed tokens: 41943040 | elapsed time per iteration (s): 0.51 | learning rate: 1.420E-04 | global batch size: 256 | lm loss: 7.107240E+00 | grad norm: 1.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 498.192 | TFLOPs: 32.58 | +7: iteration 90/ 11269 | consumed samples: 23040 | consumed tokens: 47185920 | elapsed time per iteration (s): 0.50 | learning rate: 1.597E-04 | global batch size: 256 | lm loss: 6.895432E+00 | grad norm: 0.950 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 511.791 | TFLOPs: 33.47 | +7: iteration 100/ 11269 | consumed samples: 25600 | consumed tokens: 52428800 | elapsed time per iteration (s): 0.51 | learning rate: 1.775E-04 | global batch size: 256 | lm loss: 6.768747E+00 | grad norm: 1.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 500.935 | TFLOPs: 32.76 | +7: iteration 110/ 11269 | consumed samples: 28160 | consumed tokens: 57671680 | elapsed time per iteration (s): 0.48 | learning rate: 1.952E-04 | global batch size: 256 | lm loss: 6.651917E+00 | grad norm: 0.581 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.198 | TFLOPs: 34.54 | +7: iteration 120/ 11269 | consumed samples: 30720 | consumed tokens: 62914560 | elapsed time per iteration (s): 0.50 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.575565E+00 | grad norm: 0.845 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 510.071 | TFLOPs: 33.36 | +7: iteration 130/ 11269 | consumed samples: 33280 | consumed tokens: 68157440 | elapsed time per iteration (s): 0.50 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.459740E+00 | grad norm: 0.770 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 511.974 | TFLOPs: 33.48 | +7: iteration 140/ 11269 | consumed samples: 35840 | consumed tokens: 73400320 | elapsed time per iteration (s): 0.51 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.394947E+00 | grad norm: 0.686 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 497.315 | TFLOPs: 32.52 | +7: iteration 150/ 11269 | consumed samples: 38400 | consumed tokens: 78643200 | elapsed time per iteration (s): 0.49 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.306021E+00 | grad norm: 0.561 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.852 | TFLOPs: 33.87 | +7: iteration 160/ 11269 | consumed samples: 40960 | consumed tokens: 83886080 | elapsed time per iteration (s): 0.50 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.274498E+00 | grad norm: 0.614 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 513.033 | TFLOPs: 33.55 | +7: iteration 170/ 11269 | consumed samples: 43520 | consumed tokens: 89128960 | elapsed time per iteration (s): 0.50 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.222653E+00 | grad norm: 0.613 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 508.131 | TFLOPs: 33.23 | +7: iteration 180/ 11269 | consumed samples: 46080 | consumed tokens: 94371840 | elapsed time per iteration (s): 0.51 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.156484E+00 | grad norm: 0.668 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 505.270 | TFLOPs: 33.04 | +7: iteration 190/ 11269 | consumed samples: 48640 | consumed tokens: 99614720 | elapsed time per iteration (s): 0.50 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.117565E+00 | grad norm: 0.570 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 515.922 | TFLOPs: 33.74 | +7: iteration 200/ 11269 | consumed samples: 51200 | consumed tokens: 104857600 | elapsed time per iteration (s): 0.50 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.101613E+00 | grad norm: 0.885 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 513.488 | TFLOPs: 33.58 | +7: iteration 210/ 11269 | consumed samples: 53760 | consumed tokens: 110100480 | elapsed time per iteration (s): 0.51 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.034433E+00 | grad norm: 0.608 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 506.265 | TFLOPs: 33.11 | +7: iteration 220/ 11269 | consumed samples: 56320 | consumed tokens: 115343360 | elapsed time per iteration (s): 0.50 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.009595E+00 | grad norm: 0.808 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 510.014 | TFLOPs: 33.35 | +7: iteration 230/ 11269 | consumed samples: 58880 | consumed tokens: 120586240 | elapsed time per iteration (s): 0.52 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.946698E+00 | grad norm: 0.835 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 496.184 | TFLOPs: 32.45 | +7: iteration 240/ 11269 | consumed samples: 61440 | consumed tokens: 125829120 | elapsed time per iteration (s): 0.49 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.895729E+00 | grad norm: 0.459 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.588 | TFLOPs: 34.05 | +7: iteration 250/ 11269 | consumed samples: 64000 | consumed tokens: 131072000 | elapsed time per iteration (s): 0.49 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.899978E+00 | grad norm: 1.367 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.193 | TFLOPs: 34.02 | +7: iteration 260/ 11269 | consumed samples: 66560 | consumed tokens: 136314880 | elapsed time per iteration (s): 0.49 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.874543E+00 | grad norm: 0.817 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.624 | TFLOPs: 34.44 | +7: iteration 270/ 11269 | consumed samples: 69120 | consumed tokens: 141557760 | elapsed time per iteration (s): 0.49 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.821027E+00 | grad norm: 0.674 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.400 | TFLOPs: 34.36 | +7: iteration 280/ 11269 | consumed samples: 71680 | consumed tokens: 146800640 | elapsed time per iteration (s): 0.49 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.794529E+00 | grad norm: 0.718 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.614 | TFLOPs: 34.44 | +7: iteration 290/ 11269 | consumed samples: 74240 | consumed tokens: 152043520 | elapsed time per iteration (s): 0.50 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.761044E+00 | grad norm: 0.785 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 512.577 | TFLOPs: 33.52 | +7: iteration 300/ 11269 | consumed samples: 76800 | consumed tokens: 157286400 | elapsed time per iteration (s): 0.49 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.709947E+00 | grad norm: 0.510 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.170 | TFLOPs: 34.15 | +7: iteration 310/ 11269 | consumed samples: 79360 | consumed tokens: 162529280 | elapsed time per iteration (s): 0.49 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.660912E+00 | grad norm: 0.913 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.259 | TFLOPs: 34.35 | +7: iteration 320/ 11269 | consumed samples: 81920 | consumed tokens: 167772160 | elapsed time per iteration (s): 0.50 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.639745E+00 | grad norm: 0.832 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 514.997 | TFLOPs: 33.68 | +7: iteration 330/ 11269 | consumed samples: 84480 | consumed tokens: 173015040 | elapsed time per iteration (s): 0.50 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.623890E+00 | grad norm: 0.612 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 510.007 | TFLOPs: 33.35 | +7: iteration 340/ 11269 | consumed samples: 87040 | consumed tokens: 178257920 | elapsed time per iteration (s): 0.48 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.567944E+00 | grad norm: 0.420 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.008 | TFLOPs: 34.60 | +7: iteration 350/ 11269 | consumed samples: 89600 | consumed tokens: 183500800 | elapsed time per iteration (s): 0.50 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.525057E+00 | grad norm: 0.731 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 514.722 | TFLOPs: 33.66 | +7: iteration 360/ 11269 | consumed samples: 92160 | consumed tokens: 188743680 | elapsed time per iteration (s): 0.49 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.533379E+00 | grad norm: 0.697 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.012 | TFLOPs: 34.27 | +7: iteration 370/ 11269 | consumed samples: 94720 | consumed tokens: 193986560 | elapsed time per iteration (s): 0.49 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.492405E+00 | grad norm: 0.551 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.398 | TFLOPs: 34.36 | +7: iteration 380/ 11269 | consumed samples: 97280 | consumed tokens: 199229440 | elapsed time per iteration (s): 0.50 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 5.422787E+00 | grad norm: 0.612 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 510.850 | TFLOPs: 33.41 | +7: iteration 390/ 11269 | consumed samples: 99840 | consumed tokens: 204472320 | elapsed time per iteration (s): 0.50 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 5.415775E+00 | grad norm: 0.709 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 508.257 | TFLOPs: 33.24 | +7: iteration 400/ 11269 | consumed samples: 102400 | consumed tokens: 209715200 | elapsed time per iteration (s): 0.50 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 5.365007E+00 | grad norm: 1.014 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 512.074 | TFLOPs: 33.49 | +7: iteration 410/ 11269 | consumed samples: 104960 | consumed tokens: 214958080 | elapsed time per iteration (s): 0.50 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 5.319305E+00 | grad norm: 0.494 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 510.138 | TFLOPs: 33.36 | +7: iteration 420/ 11269 | consumed samples: 107520 | consumed tokens: 220200960 | elapsed time per iteration (s): 0.49 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 5.305619E+00 | grad norm: 0.734 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.413 | TFLOPs: 34.30 | +7: iteration 430/ 11269 | consumed samples: 110080 | consumed tokens: 225443840 | elapsed time per iteration (s): 0.49 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 5.270193E+00 | grad norm: 0.918 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.001 | TFLOPs: 34.07 | +7: iteration 440/ 11269 | consumed samples: 112640 | consumed tokens: 230686720 | elapsed time per iteration (s): 0.50 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 5.244946E+00 | grad norm: 0.681 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.140 | TFLOPs: 33.82 | +7: iteration 450/ 11269 | consumed samples: 115200 | consumed tokens: 235929600 | elapsed time per iteration (s): 0.53 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 5.196004E+00 | grad norm: 0.735 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 487.426 | TFLOPs: 31.88 | +7: iteration 460/ 11269 | consumed samples: 117760 | consumed tokens: 241172480 | elapsed time per iteration (s): 0.50 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 5.211095E+00 | grad norm: 0.589 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 509.094 | TFLOPs: 33.29 | +7: iteration 470/ 11269 | consumed samples: 120320 | consumed tokens: 246415360 | elapsed time per iteration (s): 0.49 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 5.147875E+00 | grad norm: 0.767 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.369 | TFLOPs: 34.29 | +7: iteration 480/ 11269 | consumed samples: 122880 | consumed tokens: 251658240 | elapsed time per iteration (s): 0.50 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 5.170478E+00 | grad norm: 0.650 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 512.914 | TFLOPs: 33.54 | +7: iteration 490/ 11269 | consumed samples: 125440 | consumed tokens: 256901120 | elapsed time per iteration (s): 0.49 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 5.113095E+00 | grad norm: 0.589 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.053 | TFLOPs: 34.01 | +7: iteration 500/ 11269 | consumed samples: 128000 | consumed tokens: 262144000 | elapsed time per iteration (s): 0.50 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 5.086443E+00 | grad norm: 0.863 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 516.934 | TFLOPs: 33.81 | +7: iteration 510/ 11269 | consumed samples: 130560 | consumed tokens: 267386880 | elapsed time per iteration (s): 0.48 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 5.055627E+00 | grad norm: 0.953 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.951 | TFLOPs: 34.53 | +7: iteration 520/ 11269 | consumed samples: 133120 | consumed tokens: 272629760 | elapsed time per iteration (s): 0.50 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 5.003594E+00 | grad norm: 0.661 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 510.825 | TFLOPs: 33.41 | +7: iteration 530/ 11269 | consumed samples: 135680 | consumed tokens: 277872640 | elapsed time per iteration (s): 0.50 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.979019E+00 | grad norm: 0.820 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 510.024 | TFLOPs: 33.36 | +7: iteration 540/ 11269 | consumed samples: 138240 | consumed tokens: 283115520 | elapsed time per iteration (s): 0.49 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.979314E+00 | grad norm: 0.736 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.574 | TFLOPs: 34.24 | +7: iteration 550/ 11269 | consumed samples: 140800 | consumed tokens: 288358400 | elapsed time per iteration (s): 0.49 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.937137E+00 | grad norm: 0.861 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.792 | TFLOPs: 34.06 | +7: iteration 560/ 11269 | consumed samples: 143360 | consumed tokens: 293601280 | elapsed time per iteration (s): 0.49 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.910243E+00 | grad norm: 0.786 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.209 | TFLOPs: 34.35 | +7: iteration 570/ 11269 | consumed samples: 145920 | consumed tokens: 298844160 | elapsed time per iteration (s): 0.49 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.883640E+00 | grad norm: 0.754 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.476 | TFLOPs: 33.84 | +7: iteration 580/ 11269 | consumed samples: 148480 | consumed tokens: 304087040 | elapsed time per iteration (s): 0.49 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.842192E+00 | grad norm: 0.645 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.132 | TFLOPs: 34.08 | +7: iteration 590/ 11269 | consumed samples: 151040 | consumed tokens: 309329920 | elapsed time per iteration (s): 0.51 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.829807E+00 | grad norm: 1.088 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 506.679 | TFLOPs: 33.14 | +7: iteration 600/ 11269 | consumed samples: 153600 | consumed tokens: 314572800 | elapsed time per iteration (s): 0.51 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.773558E+00 | grad norm: 1.030 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 498.385 | TFLOPs: 32.59 | +7: iteration 610/ 11269 | consumed samples: 156160 | consumed tokens: 319815680 | elapsed time per iteration (s): 0.48 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 4.745735E+00 | grad norm: 1.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.320 | TFLOPs: 34.55 | +7: iteration 620/ 11269 | consumed samples: 158720 | consumed tokens: 325058560 | elapsed time per iteration (s): 0.51 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 4.707542E+00 | grad norm: 0.823 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 497.200 | TFLOPs: 32.52 | +7: iteration 630/ 11269 | consumed samples: 161280 | consumed tokens: 330301440 | elapsed time per iteration (s): 0.50 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 4.679865E+00 | grad norm: 1.012 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 516.309 | TFLOPs: 33.77 | +7: iteration 640/ 11269 | consumed samples: 163840 | consumed tokens: 335544320 | elapsed time per iteration (s): 0.51 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 4.654753E+00 | grad norm: 0.755 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 504.892 | TFLOPs: 33.02 | +7: iteration 650/ 11269 | consumed samples: 166400 | consumed tokens: 340787200 | elapsed time per iteration (s): 0.49 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 4.567943E+00 | grad norm: 0.858 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.157 | TFLOPs: 34.02 | +7: iteration 660/ 11269 | consumed samples: 168960 | consumed tokens: 346030080 | elapsed time per iteration (s): 0.50 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 4.555643E+00 | grad norm: 0.813 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 516.390 | TFLOPs: 33.77 | +7: iteration 670/ 11269 | consumed samples: 171520 | consumed tokens: 351272960 | elapsed time per iteration (s): 0.49 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 4.503219E+00 | grad norm: 0.740 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.983 | TFLOPs: 34.20 | +7: iteration 680/ 11269 | consumed samples: 174080 | consumed tokens: 356515840 | elapsed time per iteration (s): 0.49 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 4.481804E+00 | grad norm: 0.872 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 519.632 | TFLOPs: 33.98 | +7: iteration 690/ 11269 | consumed samples: 176640 | consumed tokens: 361758720 | elapsed time per iteration (s): 0.49 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 4.460097E+00 | grad norm: 1.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.993 | TFLOPs: 34.47 | +7: iteration 700/ 11269 | consumed samples: 179200 | consumed tokens: 367001600 | elapsed time per iteration (s): 0.49 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 4.439820E+00 | grad norm: 0.869 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.388 | TFLOPs: 33.90 | +7: iteration 710/ 11269 | consumed samples: 181760 | consumed tokens: 372244480 | elapsed time per iteration (s): 0.51 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 4.381787E+00 | grad norm: 1.094 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 501.154 | TFLOPs: 32.78 | +7: iteration 720/ 11269 | consumed samples: 184320 | consumed tokens: 377487360 | elapsed time per iteration (s): 0.49 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 4.381667E+00 | grad norm: 0.667 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.559 | TFLOPs: 33.91 | +7: iteration 730/ 11269 | consumed samples: 186880 | consumed tokens: 382730240 | elapsed time per iteration (s): 0.48 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 4.342009E+00 | grad norm: 0.835 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.560 | TFLOPs: 34.63 | +7: iteration 740/ 11269 | consumed samples: 189440 | consumed tokens: 387973120 | elapsed time per iteration (s): 0.49 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 4.324191E+00 | grad norm: 0.808 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.531 | TFLOPs: 34.11 | +7: iteration 750/ 11269 | consumed samples: 192000 | consumed tokens: 393216000 | elapsed time per iteration (s): 0.49 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 4.275132E+00 | grad norm: 0.989 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.492 | TFLOPs: 33.91 | +7: iteration 760/ 11269 | consumed samples: 194560 | consumed tokens: 398458880 | elapsed time per iteration (s): 0.50 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 4.273450E+00 | grad norm: 0.547 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 515.859 | TFLOPs: 33.74 | +7: iteration 770/ 11269 | consumed samples: 197120 | consumed tokens: 403701760 | elapsed time per iteration (s): 0.50 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 4.244367E+00 | grad norm: 0.642 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 514.450 | TFLOPs: 33.64 | +7: iteration 780/ 11269 | consumed samples: 199680 | consumed tokens: 408944640 | elapsed time per iteration (s): 0.49 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 4.242305E+00 | grad norm: 0.608 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.239 | TFLOPs: 34.35 | +7: iteration 790/ 11269 | consumed samples: 202240 | consumed tokens: 414187520 | elapsed time per iteration (s): 0.50 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 4.234189E+00 | grad norm: 1.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 511.652 | TFLOPs: 33.46 | +7: iteration 800/ 11269 | consumed samples: 204800 | consumed tokens: 419430400 | elapsed time per iteration (s): 0.49 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 4.241808E+00 | grad norm: 0.603 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 519.904 | TFLOPs: 34.00 | +7: iteration 810/ 11269 | consumed samples: 207360 | consumed tokens: 424673280 | elapsed time per iteration (s): 0.49 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 4.200556E+00 | grad norm: 0.583 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.077 | TFLOPs: 34.01 | +7: iteration 820/ 11269 | consumed samples: 209920 | consumed tokens: 429916160 | elapsed time per iteration (s): 0.50 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 4.145718E+00 | grad norm: 0.774 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 507.612 | TFLOPs: 33.20 | +7: iteration 830/ 11269 | consumed samples: 212480 | consumed tokens: 435159040 | elapsed time per iteration (s): 0.49 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 4.187480E+00 | grad norm: 0.587 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.410 | TFLOPs: 34.10 | +7: iteration 840/ 11269 | consumed samples: 215040 | consumed tokens: 440401920 | elapsed time per iteration (s): 0.49 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 4.164037E+00 | grad norm: 0.578 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.116 | TFLOPs: 34.15 | +7: iteration 850/ 11269 | consumed samples: 217600 | consumed tokens: 445644800 | elapsed time per iteration (s): 0.49 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 4.119492E+00 | grad norm: 0.469 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.711 | TFLOPs: 33.92 | +7: iteration 860/ 11269 | consumed samples: 220160 | consumed tokens: 450887680 | elapsed time per iteration (s): 0.49 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 4.105123E+00 | grad norm: 0.809 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.987 | TFLOPs: 34.14 | +7: iteration 870/ 11269 | consumed samples: 222720 | consumed tokens: 456130560 | elapsed time per iteration (s): 0.49 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 4.112428E+00 | grad norm: 0.606 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.733 | TFLOPs: 34.45 | +7: iteration 880/ 11269 | consumed samples: 225280 | consumed tokens: 461373440 | elapsed time per iteration (s): 0.50 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 4.077282E+00 | grad norm: 0.702 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 512.190 | TFLOPs: 33.50 | +7: iteration 890/ 11269 | consumed samples: 227840 | consumed tokens: 466616320 | elapsed time per iteration (s): 0.49 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 4.076788E+00 | grad norm: 0.571 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.781 | TFLOPs: 33.93 | +7: iteration 900/ 11269 | consumed samples: 230400 | consumed tokens: 471859200 | elapsed time per iteration (s): 0.50 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 4.104634E+00 | grad norm: 0.814 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 509.255 | TFLOPs: 33.31 | +7: iteration 910/ 11269 | consumed samples: 232960 | consumed tokens: 477102080 | elapsed time per iteration (s): 0.52 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 4.091375E+00 | grad norm: 0.665 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 490.986 | TFLOPs: 32.11 | +7: iteration 920/ 11269 | consumed samples: 235520 | consumed tokens: 482344960 | elapsed time per iteration (s): 0.49 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 4.034367E+00 | grad norm: 0.614 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.520 | TFLOPs: 34.11 | +7: iteration 930/ 11269 | consumed samples: 238080 | consumed tokens: 487587840 | elapsed time per iteration (s): 0.49 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 4.036394E+00 | grad norm: 0.486 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.809 | TFLOPs: 34.19 | +7: iteration 940/ 11269 | consumed samples: 240640 | consumed tokens: 492830720 | elapsed time per iteration (s): 0.51 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 3.998262E+00 | grad norm: 0.493 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 497.283 | TFLOPs: 32.52 | +7: iteration 950/ 11269 | consumed samples: 243200 | consumed tokens: 498073600 | elapsed time per iteration (s): 0.49 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 3.998190E+00 | grad norm: 0.587 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.137 | TFLOPs: 33.89 | +7: iteration 960/ 11269 | consumed samples: 245760 | consumed tokens: 503316480 | elapsed time per iteration (s): 0.49 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 3.995633E+00 | grad norm: 0.416 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.764 | TFLOPs: 33.86 | +7: iteration 970/ 11269 | consumed samples: 248320 | consumed tokens: 508559360 | elapsed time per iteration (s): 0.49 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 3.988679E+00 | grad norm: 0.490 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.774 | TFLOPs: 34.39 | +7: iteration 980/ 11269 | consumed samples: 250880 | consumed tokens: 513802240 | elapsed time per iteration (s): 0.49 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 3.985878E+00 | grad norm: 0.457 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.906 | TFLOPs: 34.20 | +7: iteration 990/ 11269 | consumed samples: 253440 | consumed tokens: 519045120 | elapsed time per iteration (s): 0.49 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 3.954536E+00 | grad norm: 0.503 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.627 | TFLOPs: 34.44 | +7: iteration 1000/ 11269 | consumed samples: 256000 | consumed tokens: 524288000 | elapsed time per iteration (s): 0.50 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 3.983698E+00 | grad norm: 0.647 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 516.058 | TFLOPs: 33.75 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 1000 | lm loss value: 3.822810E+00 | lm loss PPL: 4.573252E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 1000 to checkpoints_280moscar +0: [2022-11-29 17:00:55,649] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step1000 is begin to save! +0: [2022-11-29 17:00:55,686] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:00:55,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:00:55,803] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:00:55,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:00:55,829] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:00:55,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:00:55,854] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:00:55,878] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:00:55,878] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:00:55,902] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:00:55,903] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:00:55,928] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:00:55,929] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:00:55,953] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:00:55,953] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:00:55,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:00:55,977] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:00:56,001] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:00:56,002] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:00:56,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:00:56,026] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:00:56,050] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:00:56,050] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:00:56,074] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:00:56,074] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:00:56,098] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:00:56,098] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:00:56,123] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:00:56,124] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:00:56,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:00:56,148] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:00:56,172] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:00:56,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/layer_18-model_00-model_states.pt... +0: [2022-11-29 17:00:56,196] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/layer_18-model_00-model_states.pt. +0: [2022-11-29 17:00:56,196] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:00:56,220] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:00:56,221] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/layer_20-model_00-model_states.pt... +0: [2022-11-29 17:00:56,244] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/layer_20-model_00-model_states.pt. +0: [2022-11-29 17:00:56,245] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/layer_22-model_00-model_states.pt... +0: [2022-11-29 17:00:56,245] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/layer_22-model_00-model_states.pt. +0: [2022-11-29 17:00:56,246] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_280moscar/global_step1000/mp_rank_00_model_states.pt +0: [2022-11-29 17:00:56,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:00:56,249] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:00:56,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:00:56,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:00:56,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:00:56,355] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:00:56,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:00:56,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:00:56,355] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:00:56,356] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:00:56,356] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:00:56,356] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:00:56,356] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:00:56,356] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:00:56,356] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:00:56,356] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:00:56,356] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:00:56,356] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:00:56,357] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:00:56,357] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:00:56,358] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:00:56,358] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:00:56,358] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:00:56,358] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:00:56,358] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:00:56,358] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:00:56,358] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:00:56,358] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:00:56,358] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:00:56,359] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:00:56,359] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:00:56,359] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:00:56,359] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:00:56,359] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:00:56,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:00:56,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:00:56,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:00:56,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:00:56,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:00:56,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:00:56,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:00:56,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:00:56,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:00:56,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:00:56,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:00:56,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:00:56,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:00:56,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:00:56,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:00:56,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:00:56,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:00:56,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:00:56,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:00:56,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:00:56,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:00:56,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:00:56,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:00:56,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:00:56,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:00:56,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:00:56,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:00:56,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:00:56,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:00:56,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:00:56,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:00:56,345] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:00:56,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:00:56,366] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:00:56,366] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:00:56,366] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:00:56,367] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:00:56,367] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:00:56,367] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:00:56,367] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:00:56,367] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:00:56,367] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:00:56,367] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:00:56,368] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:00:56,368] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:00:56,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:00:56,368] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:00:56,368] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:00:56,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:00:56,368] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:00:56,368] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:00:56,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:00:56,369] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:00:56,369] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:00:56,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:00:56,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:00:56,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:00:56,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:00:56,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:00:56,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:00:56,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:00:56,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:00:56,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:00:56,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:00:56,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:00:56,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:00:56,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:00:56,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:00:56,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:00:56,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:00:56,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:00:56,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:00:56,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:00:56,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:00:56,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:00:56,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:00:56,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:00:56,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:00:56,369] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:00:56,369] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:00:56,370] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:00:56,370] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:00:56,370] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:00:56,381] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:00:56,381] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:00:56,381] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:00:56,390] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:00:56,391] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:00:56,391] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:00:56,391] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:00:56,391] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:00:56,391] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:00:56,391] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:00:56,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:00:56,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:00:56,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:00:56,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:00:56,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:00:56,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:00:56,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:00:56,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:00:56,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +5: [2022-11-29 17:00:56,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +4: [2022-11-29 17:00:56,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:00:56,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:00:56,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:00:56,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:00:56,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:00:56,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:00:56,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:00:56,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:00:56,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:00:56,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:00:56,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:00:56,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:00:56,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:00:56,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:00:56,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:00:56,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:00:56,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:00:56,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:00:56,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:00:56,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:00:56,399] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:00:56,399] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:00:56,399] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:00:56,399] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:00:56,399] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:00:56,399] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:00:56,399] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:00:56,399] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:00:56,399] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:00:56,399] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:00:56,399] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:00:56,399] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:00:56,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:00:56,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:00:56,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:00:56,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:00:56,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:00:56,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:00:56,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:00:56,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:00:56,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:00:56,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:00:56,406] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:00:56,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:00:56,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:00:56,406] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:00:56,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:00:56,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:00:56,406] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:00:56,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:00:56,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:00:56,406] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:00:56,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:00:56,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:00:56,410] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:00:56,410] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:00:56,431] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:00:56,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: successfully saved checkpoint at iteration 1000 to checkpoints_280moscar +7: time (ms) | save-checkpoint: 794.23 +7: iteration 1010/ 11269 | consumed samples: 258560 | consumed tokens: 529530880 | elapsed time per iteration (s): 0.58 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 3.946331E+00 | grad norm: 0.465 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.522 | TFLOPs: 28.68 | +7: iteration 1020/ 11269 | consumed samples: 261120 | consumed tokens: 534773760 | elapsed time per iteration (s): 0.48 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 3.944511E+00 | grad norm: 0.624 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.633 | TFLOPs: 34.77 | +7: iteration 1030/ 11269 | consumed samples: 263680 | consumed tokens: 540016640 | elapsed time per iteration (s): 0.49 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 3.934938E+00 | grad norm: 0.555 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.200 | TFLOPs: 34.41 | +7: iteration 1040/ 11269 | consumed samples: 266240 | consumed tokens: 545259520 | elapsed time per iteration (s): 0.50 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 3.899381E+00 | grad norm: 0.531 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 515.322 | TFLOPs: 33.70 | +7: iteration 1050/ 11269 | consumed samples: 268800 | consumed tokens: 550502400 | elapsed time per iteration (s): 0.49 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 3.907783E+00 | grad norm: 0.447 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.946 | TFLOPs: 34.20 | +7: iteration 1060/ 11269 | consumed samples: 271360 | consumed tokens: 555745280 | elapsed time per iteration (s): 0.49 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 3.911126E+00 | grad norm: 0.615 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.366 | TFLOPs: 34.10 | +7: iteration 1070/ 11269 | consumed samples: 273920 | consumed tokens: 560988160 | elapsed time per iteration (s): 0.50 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 3.883450E+00 | grad norm: 0.427 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 512.844 | TFLOPs: 33.54 | +7: iteration 1080/ 11269 | consumed samples: 276480 | consumed tokens: 566231040 | elapsed time per iteration (s): 0.49 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 3.881864E+00 | grad norm: 0.561 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.334 | TFLOPs: 34.10 | +7: iteration 1090/ 11269 | consumed samples: 279040 | consumed tokens: 571473920 | elapsed time per iteration (s): 0.49 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 3.888571E+00 | grad norm: 0.557 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.518 | TFLOPs: 33.91 | +7: iteration 1100/ 11269 | consumed samples: 281600 | consumed tokens: 576716800 | elapsed time per iteration (s): 0.50 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 3.873519E+00 | grad norm: 0.435 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 511.575 | TFLOPs: 33.46 | +7: iteration 1110/ 11269 | consumed samples: 284160 | consumed tokens: 581959680 | elapsed time per iteration (s): 0.49 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 3.833746E+00 | grad norm: 0.537 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.489 | TFLOPs: 34.04 | +7: iteration 1120/ 11269 | consumed samples: 286720 | consumed tokens: 587202560 | elapsed time per iteration (s): 0.49 | learning rate: 1.964E-04 | global batch size: 256 | lm loss: 3.848864E+00 | grad norm: 0.858 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.026 | TFLOPs: 34.34 | +7: iteration 1130/ 11269 | consumed samples: 289280 | consumed tokens: 592445440 | elapsed time per iteration (s): 0.50 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 3.851189E+00 | grad norm: 0.457 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 515.234 | TFLOPs: 33.70 | +7: iteration 1140/ 11269 | consumed samples: 291840 | consumed tokens: 597688320 | elapsed time per iteration (s): 0.49 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 3.851610E+00 | grad norm: 0.459 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.373 | TFLOPs: 34.36 | +7: iteration 1150/ 11269 | consumed samples: 294400 | consumed tokens: 602931200 | elapsed time per iteration (s): 0.49 | learning rate: 1.962E-04 | global batch size: 256 | lm loss: 3.827748E+00 | grad norm: 0.462 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.512 | TFLOPs: 34.43 | +7: iteration 1160/ 11269 | consumed samples: 296960 | consumed tokens: 608174080 | elapsed time per iteration (s): 0.49 | learning rate: 1.961E-04 | global batch size: 256 | lm loss: 3.856986E+00 | grad norm: 0.617 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.928 | TFLOPs: 34.13 | +7: iteration 1170/ 11269 | consumed samples: 299520 | consumed tokens: 613416960 | elapsed time per iteration (s): 0.50 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 3.844683E+00 | grad norm: 0.411 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 514.556 | TFLOPs: 33.65 | +7: iteration 1180/ 11269 | consumed samples: 302080 | consumed tokens: 618659840 | elapsed time per iteration (s): 0.50 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 3.814069E+00 | grad norm: 0.568 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 516.371 | TFLOPs: 33.77 | +7: iteration 1190/ 11269 | consumed samples: 304640 | consumed tokens: 623902720 | elapsed time per iteration (s): 0.50 | learning rate: 1.959E-04 | global batch size: 256 | lm loss: 3.886897E+00 | grad norm: 0.674 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 516.614 | TFLOPs: 33.79 | +7: iteration 1200/ 11269 | consumed samples: 307200 | consumed tokens: 629145600 | elapsed time per iteration (s): 0.48 | learning rate: 1.958E-04 | global batch size: 256 | lm loss: 3.822720E+00 | grad norm: 0.470 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.307 | TFLOPs: 34.75 | +7: iteration 1210/ 11269 | consumed samples: 309760 | consumed tokens: 634388480 | elapsed time per iteration (s): 0.51 | learning rate: 1.957E-04 | global batch size: 256 | lm loss: 3.802046E+00 | grad norm: 0.523 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 505.510 | TFLOPs: 33.06 | +7: iteration 1220/ 11269 | consumed samples: 312320 | consumed tokens: 639631360 | elapsed time per iteration (s): 0.50 | learning rate: 1.957E-04 | global batch size: 256 | lm loss: 3.802422E+00 | grad norm: 0.488 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 513.566 | TFLOPs: 33.59 | +7: iteration 1230/ 11269 | consumed samples: 314880 | consumed tokens: 644874240 | elapsed time per iteration (s): 0.50 | learning rate: 1.956E-04 | global batch size: 256 | lm loss: 3.791408E+00 | grad norm: 0.461 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 512.707 | TFLOPs: 33.53 | +7: iteration 1240/ 11269 | consumed samples: 317440 | consumed tokens: 650117120 | elapsed time per iteration (s): 0.48 | learning rate: 1.955E-04 | global batch size: 256 | lm loss: 3.816681E+00 | grad norm: 0.552 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.492 | TFLOPs: 34.82 | +7: iteration 1250/ 11269 | consumed samples: 320000 | consumed tokens: 655360000 | elapsed time per iteration (s): 0.49 | learning rate: 1.954E-04 | global batch size: 256 | lm loss: 3.786155E+00 | grad norm: 0.428 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.813 | TFLOPs: 33.86 | +7: iteration 1260/ 11269 | consumed samples: 322560 | consumed tokens: 660602880 | elapsed time per iteration (s): 0.50 | learning rate: 1.953E-04 | global batch size: 256 | lm loss: 3.787183E+00 | grad norm: 0.534 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 516.054 | TFLOPs: 33.75 | +7: iteration 1270/ 11269 | consumed samples: 325120 | consumed tokens: 665845760 | elapsed time per iteration (s): 0.50 | learning rate: 1.953E-04 | global batch size: 256 | lm loss: 3.778396E+00 | grad norm: 0.600 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 513.050 | TFLOPs: 33.55 | +7: iteration 1280/ 11269 | consumed samples: 327680 | consumed tokens: 671088640 | elapsed time per iteration (s): 0.49 | learning rate: 1.952E-04 | global batch size: 256 | lm loss: 3.768424E+00 | grad norm: 0.589 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.992 | TFLOPs: 34.33 | +7: iteration 1290/ 11269 | consumed samples: 330240 | consumed tokens: 676331520 | elapsed time per iteration (s): 0.49 | learning rate: 1.951E-04 | global batch size: 256 | lm loss: 3.757653E+00 | grad norm: 0.424 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.886 | TFLOPs: 34.20 | +7: iteration 1300/ 11269 | consumed samples: 332800 | consumed tokens: 681574400 | elapsed time per iteration (s): 0.51 | learning rate: 1.950E-04 | global batch size: 256 | lm loss: 3.772801E+00 | grad norm: 0.430 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 504.143 | TFLOPs: 32.97 | +7: iteration 1310/ 11269 | consumed samples: 335360 | consumed tokens: 686817280 | elapsed time per iteration (s): 0.48 | learning rate: 1.949E-04 | global batch size: 256 | lm loss: 3.761455E+00 | grad norm: 0.703 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.099 | TFLOPs: 34.80 | +7: iteration 1320/ 11269 | consumed samples: 337920 | consumed tokens: 692060160 | elapsed time per iteration (s): 0.49 | learning rate: 1.948E-04 | global batch size: 256 | lm loss: 3.759308E+00 | grad norm: 0.656 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.742 | TFLOPs: 34.32 | +7: iteration 1330/ 11269 | consumed samples: 340480 | consumed tokens: 697303040 | elapsed time per iteration (s): 0.49 | learning rate: 1.948E-04 | global batch size: 256 | lm loss: 3.736424E+00 | grad norm: 0.598 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.313 | TFLOPs: 33.90 | +7: iteration 1340/ 11269 | consumed samples: 343040 | consumed tokens: 702545920 | elapsed time per iteration (s): 0.50 | learning rate: 1.947E-04 | global batch size: 256 | lm loss: 3.726904E+00 | grad norm: 0.483 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 511.762 | TFLOPs: 33.47 | +7: iteration 1350/ 11269 | consumed samples: 345600 | consumed tokens: 707788800 | elapsed time per iteration (s): 0.49 | learning rate: 1.946E-04 | global batch size: 256 | lm loss: 3.727308E+00 | grad norm: 0.516 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.510 | TFLOPs: 34.24 | +7: iteration 1360/ 11269 | consumed samples: 348160 | consumed tokens: 713031680 | elapsed time per iteration (s): 0.48 | learning rate: 1.945E-04 | global batch size: 256 | lm loss: 3.723028E+00 | grad norm: 0.618 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.477 | TFLOPs: 34.56 | +7: iteration 1370/ 11269 | consumed samples: 350720 | consumed tokens: 718274560 | elapsed time per iteration (s): 0.49 | learning rate: 1.944E-04 | global batch size: 256 | lm loss: 3.705416E+00 | grad norm: 0.469 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.745 | TFLOPs: 34.45 | +7: iteration 1380/ 11269 | consumed samples: 353280 | consumed tokens: 723517440 | elapsed time per iteration (s): 0.49 | learning rate: 1.943E-04 | global batch size: 256 | lm loss: 3.705625E+00 | grad norm: 0.686 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.400 | TFLOPs: 34.43 | +7: iteration 1390/ 11269 | consumed samples: 355840 | consumed tokens: 728760320 | elapsed time per iteration (s): 0.49 | learning rate: 1.942E-04 | global batch size: 256 | lm loss: 3.701799E+00 | grad norm: 0.501 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.008 | TFLOPs: 34.47 | +7: iteration 1400/ 11269 | consumed samples: 358400 | consumed tokens: 734003200 | elapsed time per iteration (s): 0.49 | learning rate: 1.942E-04 | global batch size: 256 | lm loss: 3.713981E+00 | grad norm: 0.419 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.043 | TFLOPs: 34.27 | +7: iteration 1410/ 11269 | consumed samples: 360960 | consumed tokens: 739246080 | elapsed time per iteration (s): 0.49 | learning rate: 1.941E-04 | global batch size: 256 | lm loss: 3.695519E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.708 | TFLOPs: 34.38 | +7: iteration 1420/ 11269 | consumed samples: 363520 | consumed tokens: 744488960 | elapsed time per iteration (s): 0.49 | learning rate: 1.940E-04 | global batch size: 256 | lm loss: 3.679111E+00 | grad norm: 0.532 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.353 | TFLOPs: 34.03 | +7: iteration 1430/ 11269 | consumed samples: 366080 | consumed tokens: 749731840 | elapsed time per iteration (s): 0.49 | learning rate: 1.939E-04 | global batch size: 256 | lm loss: 3.718058E+00 | grad norm: 0.439 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.917 | TFLOPs: 34.20 | +7: iteration 1440/ 11269 | consumed samples: 368640 | consumed tokens: 754974720 | elapsed time per iteration (s): 0.48 | learning rate: 1.938E-04 | global batch size: 256 | lm loss: 3.676295E+00 | grad norm: 0.466 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.716 | TFLOPs: 35.04 | +7: iteration 1450/ 11269 | consumed samples: 371200 | consumed tokens: 760217600 | elapsed time per iteration (s): 0.49 | learning rate: 1.937E-04 | global batch size: 256 | lm loss: 3.698036E+00 | grad norm: 0.504 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.172 | TFLOPs: 34.28 | +7: iteration 1460/ 11269 | consumed samples: 373760 | consumed tokens: 765460480 | elapsed time per iteration (s): 0.50 | learning rate: 1.936E-04 | global batch size: 256 | lm loss: 3.678895E+00 | grad norm: 0.479 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 515.315 | TFLOPs: 33.70 | +7: iteration 1470/ 11269 | consumed samples: 376320 | consumed tokens: 770703360 | elapsed time per iteration (s): 0.49 | learning rate: 1.935E-04 | global batch size: 256 | lm loss: 3.691276E+00 | grad norm: 0.397 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.899 | TFLOPs: 33.87 | +7: iteration 1480/ 11269 | consumed samples: 378880 | consumed tokens: 775946240 | elapsed time per iteration (s): 0.49 | learning rate: 1.934E-04 | global batch size: 256 | lm loss: 3.694860E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.073 | TFLOPs: 34.27 | +7: iteration 1490/ 11269 | consumed samples: 381440 | consumed tokens: 781189120 | elapsed time per iteration (s): 0.51 | learning rate: 1.933E-04 | global batch size: 256 | lm loss: 3.641002E+00 | grad norm: 0.454 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 501.776 | TFLOPs: 32.82 | +7: iteration 1500/ 11269 | consumed samples: 384000 | consumed tokens: 786432000 | elapsed time per iteration (s): 0.49 | learning rate: 1.932E-04 | global batch size: 256 | lm loss: 3.662987E+00 | grad norm: 0.472 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.835 | TFLOPs: 34.06 | +7: iteration 1510/ 11269 | consumed samples: 386560 | consumed tokens: 791674880 | elapsed time per iteration (s): 0.48 | learning rate: 1.931E-04 | global batch size: 256 | lm loss: 3.677065E+00 | grad norm: 0.552 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.359 | TFLOPs: 34.62 | +7: iteration 1520/ 11269 | consumed samples: 389120 | consumed tokens: 796917760 | elapsed time per iteration (s): 0.50 | learning rate: 1.930E-04 | global batch size: 256 | lm loss: 3.650162E+00 | grad norm: 0.421 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 516.114 | TFLOPs: 33.75 | +7: iteration 1530/ 11269 | consumed samples: 391680 | consumed tokens: 802160640 | elapsed time per iteration (s): 0.49 | learning rate: 1.929E-04 | global batch size: 256 | lm loss: 3.632182E+00 | grad norm: 0.406 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.069 | TFLOPs: 34.21 | +7: iteration 1540/ 11269 | consumed samples: 394240 | consumed tokens: 807403520 | elapsed time per iteration (s): 0.49 | learning rate: 1.928E-04 | global batch size: 256 | lm loss: 3.671456E+00 | grad norm: 0.541 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.387 | TFLOPs: 34.16 | +7: iteration 1550/ 11269 | consumed samples: 396800 | consumed tokens: 812646400 | elapsed time per iteration (s): 0.49 | learning rate: 1.927E-04 | global batch size: 256 | lm loss: 3.628587E+00 | grad norm: 0.442 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.224 | TFLOPs: 34.09 | +7: iteration 1560/ 11269 | consumed samples: 399360 | consumed tokens: 817889280 | elapsed time per iteration (s): 0.49 | learning rate: 1.926E-04 | global batch size: 256 | lm loss: 3.619406E+00 | grad norm: 0.444 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.978 | TFLOPs: 34.27 | +7: iteration 1570/ 11269 | consumed samples: 401920 | consumed tokens: 823132160 | elapsed time per iteration (s): 0.49 | learning rate: 1.925E-04 | global batch size: 256 | lm loss: 3.618292E+00 | grad norm: 0.528 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.375 | TFLOPs: 34.10 | +7: iteration 1580/ 11269 | consumed samples: 404480 | consumed tokens: 828375040 | elapsed time per iteration (s): 0.49 | learning rate: 1.924E-04 | global batch size: 256 | lm loss: 3.593557E+00 | grad norm: 0.442 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 519.634 | TFLOPs: 33.98 | +7: iteration 1590/ 11269 | consumed samples: 407040 | consumed tokens: 833617920 | elapsed time per iteration (s): 0.49 | learning rate: 1.923E-04 | global batch size: 256 | lm loss: 3.601604E+00 | grad norm: 0.518 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.515 | TFLOPs: 34.11 | +7: iteration 1600/ 11269 | consumed samples: 409600 | consumed tokens: 838860800 | elapsed time per iteration (s): 0.49 | learning rate: 1.922E-04 | global batch size: 256 | lm loss: 3.640145E+00 | grad norm: 0.429 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.252 | TFLOPs: 34.09 | +7: iteration 1610/ 11269 | consumed samples: 412160 | consumed tokens: 844103680 | elapsed time per iteration (s): 0.50 | learning rate: 1.921E-04 | global batch size: 256 | lm loss: 3.604926E+00 | grad norm: 0.429 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 513.748 | TFLOPs: 33.60 | +7: iteration 1620/ 11269 | consumed samples: 414720 | consumed tokens: 849346560 | elapsed time per iteration (s): 0.48 | learning rate: 1.920E-04 | global batch size: 256 | lm loss: 3.620449E+00 | grad norm: 0.626 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.042 | TFLOPs: 34.86 | +7: iteration 1630/ 11269 | consumed samples: 417280 | consumed tokens: 854589440 | elapsed time per iteration (s): 0.49 | learning rate: 1.919E-04 | global batch size: 256 | lm loss: 3.623421E+00 | grad norm: 0.429 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.883 | TFLOPs: 34.39 | +7: iteration 1640/ 11269 | consumed samples: 419840 | consumed tokens: 859832320 | elapsed time per iteration (s): 0.50 | learning rate: 1.918E-04 | global batch size: 256 | lm loss: 3.607831E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.159 | TFLOPs: 33.82 | +7: iteration 1650/ 11269 | consumed samples: 422400 | consumed tokens: 865075200 | elapsed time per iteration (s): 0.50 | learning rate: 1.917E-04 | global batch size: 256 | lm loss: 3.616831E+00 | grad norm: 0.472 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 515.879 | TFLOPs: 33.74 | +7: iteration 1660/ 11269 | consumed samples: 424960 | consumed tokens: 870318080 | elapsed time per iteration (s): 0.49 | learning rate: 1.916E-04 | global batch size: 256 | lm loss: 3.616000E+00 | grad norm: 0.631 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.724 | TFLOPs: 34.25 | +7: iteration 1670/ 11269 | consumed samples: 427520 | consumed tokens: 875560960 | elapsed time per iteration (s): 0.50 | learning rate: 1.915E-04 | global batch size: 256 | lm loss: 3.608172E+00 | grad norm: 0.462 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 515.187 | TFLOPs: 33.69 | +7: iteration 1680/ 11269 | consumed samples: 430080 | consumed tokens: 880803840 | elapsed time per iteration (s): 0.51 | learning rate: 1.914E-04 | global batch size: 256 | lm loss: 3.579284E+00 | grad norm: 0.397 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 504.975 | TFLOPs: 33.03 | +7: iteration 1690/ 11269 | consumed samples: 432640 | consumed tokens: 886046720 | elapsed time per iteration (s): 0.51 | learning rate: 1.913E-04 | global batch size: 256 | lm loss: 3.614458E+00 | grad norm: 0.415 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 498.401 | TFLOPs: 32.60 | +7: iteration 1700/ 11269 | consumed samples: 435200 | consumed tokens: 891289600 | elapsed time per iteration (s): 0.49 | learning rate: 1.912E-04 | global batch size: 256 | lm loss: 3.572315E+00 | grad norm: 0.388 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 519.096 | TFLOPs: 33.95 | +7: iteration 1710/ 11269 | consumed samples: 437760 | consumed tokens: 896532480 | elapsed time per iteration (s): 0.49 | learning rate: 1.910E-04 | global batch size: 256 | lm loss: 3.565073E+00 | grad norm: 0.511 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.638 | TFLOPs: 33.85 | +7: iteration 1720/ 11269 | consumed samples: 440320 | consumed tokens: 901775360 | elapsed time per iteration (s): 0.50 | learning rate: 1.909E-04 | global batch size: 256 | lm loss: 3.592551E+00 | grad norm: 0.400 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 515.363 | TFLOPs: 33.70 | +7: iteration 1730/ 11269 | consumed samples: 442880 | consumed tokens: 907018240 | elapsed time per iteration (s): 0.50 | learning rate: 1.908E-04 | global batch size: 256 | lm loss: 3.569707E+00 | grad norm: 0.392 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 516.073 | TFLOPs: 33.75 | +7: iteration 1740/ 11269 | consumed samples: 445440 | consumed tokens: 912261120 | elapsed time per iteration (s): 0.49 | learning rate: 1.907E-04 | global batch size: 256 | lm loss: 3.579277E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.761 | TFLOPs: 34.19 | +7: iteration 1750/ 11269 | consumed samples: 448000 | consumed tokens: 917504000 | elapsed time per iteration (s): 0.50 | learning rate: 1.906E-04 | global batch size: 256 | lm loss: 3.585079E+00 | grad norm: 0.460 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 506.991 | TFLOPs: 33.16 | +7: iteration 1760/ 11269 | consumed samples: 450560 | consumed tokens: 922746880 | elapsed time per iteration (s): 0.50 | learning rate: 1.905E-04 | global batch size: 256 | lm loss: 3.542014E+00 | grad norm: 0.421 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 514.601 | TFLOPs: 33.65 | +7: iteration 1770/ 11269 | consumed samples: 453120 | consumed tokens: 927989760 | elapsed time per iteration (s): 0.48 | learning rate: 1.904E-04 | global batch size: 256 | lm loss: 3.564766E+00 | grad norm: 0.446 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.072 | TFLOPs: 34.67 | +7: iteration 1780/ 11269 | consumed samples: 455680 | consumed tokens: 933232640 | elapsed time per iteration (s): 0.49 | learning rate: 1.903E-04 | global batch size: 256 | lm loss: 3.559685E+00 | grad norm: 0.408 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.038 | TFLOPs: 34.34 | +7: iteration 1790/ 11269 | consumed samples: 458240 | consumed tokens: 938475520 | elapsed time per iteration (s): 0.48 | learning rate: 1.901E-04 | global batch size: 256 | lm loss: 3.562748E+00 | grad norm: 0.442 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.819 | TFLOPs: 34.85 | +7: iteration 1800/ 11269 | consumed samples: 460800 | consumed tokens: 943718400 | elapsed time per iteration (s): 0.49 | learning rate: 1.900E-04 | global batch size: 256 | lm loss: 3.571491E+00 | grad norm: 0.490 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.330 | TFLOPs: 33.83 | +7: iteration 1810/ 11269 | consumed samples: 463360 | consumed tokens: 948961280 | elapsed time per iteration (s): 0.49 | learning rate: 1.899E-04 | global batch size: 256 | lm loss: 3.554251E+00 | grad norm: 0.404 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.396 | TFLOPs: 34.43 | +7: iteration 1820/ 11269 | consumed samples: 465920 | consumed tokens: 954204160 | elapsed time per iteration (s): 0.51 | learning rate: 1.898E-04 | global batch size: 256 | lm loss: 3.536426E+00 | grad norm: 0.442 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 504.407 | TFLOPs: 32.99 | +7: iteration 1830/ 11269 | consumed samples: 468480 | consumed tokens: 959447040 | elapsed time per iteration (s): 0.48 | learning rate: 1.897E-04 | global batch size: 256 | lm loss: 3.584848E+00 | grad norm: 0.486 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.771 | TFLOPs: 34.65 | +7: iteration 1840/ 11269 | consumed samples: 471040 | consumed tokens: 964689920 | elapsed time per iteration (s): 0.50 | learning rate: 1.896E-04 | global batch size: 256 | lm loss: 3.555804E+00 | grad norm: 0.422 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 512.233 | TFLOPs: 33.50 | +7: iteration 1850/ 11269 | consumed samples: 473600 | consumed tokens: 969932800 | elapsed time per iteration (s): 0.50 | learning rate: 1.894E-04 | global batch size: 256 | lm loss: 3.543233E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 510.794 | TFLOPs: 33.41 | +7: iteration 1860/ 11269 | consumed samples: 476160 | consumed tokens: 975175680 | elapsed time per iteration (s): 0.49 | learning rate: 1.893E-04 | global batch size: 256 | lm loss: 3.539039E+00 | grad norm: 0.414 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.035 | TFLOPs: 34.14 | +7: iteration 1870/ 11269 | consumed samples: 478720 | consumed tokens: 980418560 | elapsed time per iteration (s): 0.48 | learning rate: 1.892E-04 | global batch size: 256 | lm loss: 3.500973E+00 | grad norm: 0.388 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.581 | TFLOPs: 34.70 | +7: iteration 1880/ 11269 | consumed samples: 481280 | consumed tokens: 985661440 | elapsed time per iteration (s): 0.49 | learning rate: 1.891E-04 | global batch size: 256 | lm loss: 3.510388E+00 | grad norm: 0.451 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.936 | TFLOPs: 34.40 | +7: iteration 1890/ 11269 | consumed samples: 483840 | consumed tokens: 990904320 | elapsed time per iteration (s): 0.48 | learning rate: 1.890E-04 | global batch size: 256 | lm loss: 3.535760E+00 | grad norm: 0.417 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.669 | TFLOPs: 34.57 | +7: iteration 1900/ 11269 | consumed samples: 486400 | consumed tokens: 996147200 | elapsed time per iteration (s): 0.50 | learning rate: 1.888E-04 | global batch size: 256 | lm loss: 3.527752E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 509.698 | TFLOPs: 33.33 | +7: iteration 1910/ 11269 | consumed samples: 488960 | consumed tokens: 1001390080 | elapsed time per iteration (s): 0.49 | learning rate: 1.887E-04 | global batch size: 256 | lm loss: 3.538177E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 519.328 | TFLOPs: 33.96 | +7: iteration 1920/ 11269 | consumed samples: 491520 | consumed tokens: 1006632960 | elapsed time per iteration (s): 0.50 | learning rate: 1.886E-04 | global batch size: 256 | lm loss: 3.498287E+00 | grad norm: 0.425 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 512.141 | TFLOPs: 33.49 | +7: iteration 1930/ 11269 | consumed samples: 494080 | consumed tokens: 1011875840 | elapsed time per iteration (s): 0.47 | learning rate: 1.885E-04 | global batch size: 256 | lm loss: 3.515381E+00 | grad norm: 0.548 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 539.184 | TFLOPs: 35.26 | +7: iteration 1940/ 11269 | consumed samples: 496640 | consumed tokens: 1017118720 | elapsed time per iteration (s): 0.49 | learning rate: 1.883E-04 | global batch size: 256 | lm loss: 3.536624E+00 | grad norm: 0.415 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.660 | TFLOPs: 34.31 | +7: iteration 1950/ 11269 | consumed samples: 499200 | consumed tokens: 1022361600 | elapsed time per iteration (s): 0.49 | learning rate: 1.882E-04 | global batch size: 256 | lm loss: 3.535177E+00 | grad norm: 0.435 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.460 | TFLOPs: 34.30 | +7: iteration 1960/ 11269 | consumed samples: 501760 | consumed tokens: 1027604480 | elapsed time per iteration (s): 0.48 | learning rate: 1.881E-04 | global batch size: 256 | lm loss: 3.532045E+00 | grad norm: 0.394 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.313 | TFLOPs: 34.81 | +7: iteration 1970/ 11269 | consumed samples: 504320 | consumed tokens: 1032847360 | elapsed time per iteration (s): 0.50 | learning rate: 1.880E-04 | global batch size: 256 | lm loss: 3.530872E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 508.002 | TFLOPs: 33.22 | +7: iteration 1980/ 11269 | consumed samples: 506880 | consumed tokens: 1038090240 | elapsed time per iteration (s): 0.49 | learning rate: 1.878E-04 | global batch size: 256 | lm loss: 3.511605E+00 | grad norm: 0.421 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.367 | TFLOPs: 34.36 | +7: iteration 1990/ 11269 | consumed samples: 509440 | consumed tokens: 1043333120 | elapsed time per iteration (s): 0.49 | learning rate: 1.877E-04 | global batch size: 256 | lm loss: 3.499475E+00 | grad norm: 0.436 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.992 | TFLOPs: 34.40 | +0: [2022-11-29 17:09:08,370] [INFO] [logging.py:68:log_dist] [Rank 0] step=2000, skipped=0, lr=[0.00018758615112345138, 0.00018758615112345138, 0.00018758615112345138], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 2000/ 11269 | consumed samples: 512000 | consumed tokens: 1048576000 | elapsed time per iteration (s): 0.49 | learning rate: 1.876E-04 | global batch size: 256 | lm loss: 3.503494E+00 | grad norm: 0.405 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.273 | TFLOPs: 33.89 | +0: steps: 2000 loss: 3.4992 iter time (s): 0.498 samples/sec: 513.823 +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 2000 | lm loss value: 3.396381E+00 | lm loss PPL: 2.985585E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 2000 to checkpoints_280moscar +0: [2022-11-29 17:09:08,550] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step2000 is begin to save! +0: [2022-11-29 17:09:08,555] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:09:08,668] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:09:08,669] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:09:08,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:09:08,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:09:08,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:09:08,719] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:09:08,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:09:08,744] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:09:08,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:09:08,769] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:09:08,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:09:08,794] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:09:08,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:09:08,819] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:09:08,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:09:08,844] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:09:08,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:09:08,869] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:09:08,893] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:09:08,893] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:09:08,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:09:08,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:09:08,948] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:09:08,948] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:09:08,974] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:09:08,975] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:09:09,000] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:09:09,000] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:09:09,027] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:09:09,027] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:09:09,053] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:09:09,053] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/layer_18-model_00-model_states.pt... +0: [2022-11-29 17:09:09,080] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/layer_18-model_00-model_states.pt. +0: [2022-11-29 17:09:09,080] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:09:09,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:09:09,105] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/layer_20-model_00-model_states.pt... +0: [2022-11-29 17:09:09,130] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/layer_20-model_00-model_states.pt. +0: [2022-11-29 17:09:09,130] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/layer_22-model_00-model_states.pt... +0: [2022-11-29 17:09:09,131] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/layer_22-model_00-model_states.pt. +0: [2022-11-29 17:09:09,132] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_280moscar/global_step2000/mp_rank_00_model_states.pt +0: [2022-11-29 17:09:09,132] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:09:09,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:09:09,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:09:09,209] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:09:09,209] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:09:09,209] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:09:09,209] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:09:09,209] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:09:09,209] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:09:09,211] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:09:09,211] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:09:09,211] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:09:09,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:09:09,212] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:09:09,212] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:09:09,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:09:09,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:09:09,212] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +2: [2022-11-29 17:09:09,212] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:09:09,212] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:09:09,212] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:09:09,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:09:09,212] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:09:09,212] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:09:09,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:09:09,213] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:09:09,213] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:09:09,213] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:09:09,213] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:09:09,213] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:09:09,214] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:09:09,214] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:09:09,214] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:09:09,215] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:09:09,215] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:09:09,215] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:09:09,216] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:09:09,216] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:09:09,216] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:09:09,215] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:09:09,215] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:09:09,215] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:09:09,218] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:09:09,218] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:09:09,218] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:09:09,218] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:09:09,218] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:09:09,218] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:09:09,219] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:09:09,219] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:09:09,219] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:09:09,219] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:09:09,219] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:09:09,219] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:09:09,219] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:09:09,219] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:09:09,219] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:09:09,221] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:09:09,221] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:09:09,221] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +4: [2022-11-29 17:09:09,221] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:09:09,221] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:09:09,221] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:09:09,222] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:09:09,222] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:09:09,222] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3: [2022-11-29 17:09:09,222] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:09:09,222] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:09:09,222] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:09:09,222] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:09:09,222] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:09:09,222] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:09:09,222] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:09:09,222] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:09:09,223] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:09:09,223] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:09:09,222] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:09:09,223] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:09:09,223] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:09:09,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:09:09,224] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:09:09,224] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:09:09,225] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:09:09,225] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:09:09,225] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:09:09,227] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:09:09,227] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:09:09,227] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:09:09,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:09:09,228] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:09:09,228] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:09:09,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:09:09,229] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:09:09,229] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:09:09,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:09:09,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:09:09,229] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +0: [2022-11-29 17:09:09,229] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +1: [2022-11-29 17:09:09,229] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:09:09,229] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:09:09,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:09:09,229] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:09:09,229] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:09:09,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:09:09,229] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:09:09,229] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:09:09,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:09:09,229] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:09:09,229] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:09:09,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:09:09,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:09:09,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:09:09,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:09:09,229] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:09:09,229] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:09:09,229] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:09:09,229] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:09:09,229] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:09:09,229] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:09:09,229] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:09:09,229] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:09:09,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:09:09,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:09:09,230] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:09:09,230] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:09:09,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:09:09,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:09:09,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:09:09,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:09:09,224] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:09:09,224] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:09:09,224] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:09:09,224] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:09:09,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:09:09,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:09:09,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:09:09,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:09:09,224] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:09:09,224] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:09:09,224] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:09:09,225] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:09:09,225] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:09:09,225] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:09:09,225] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:09:09,225] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:09:09,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:09:09,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:09:09,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:09:09,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:09:09,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:09:09,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:09:09,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:09:09,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:09:09,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:09:09,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:09:09,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:09:09,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:09:09,232] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:09:09,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:09:09,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:09:09,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:09:09,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:09:09,234] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:09:09,234] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:09:09,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:09:09,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:09:09,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:09:09,234] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:09:09,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:09:09,236] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:09:09,236] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:09:09,236] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:09:09,236] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:09:09,236] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:09:09,236] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:09:09,236] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:09:09,236] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:09:09,236] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:09:09,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:09:09,241] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:09:09,241] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:09:09,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:09:09,241] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:09:09,241] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:09:09,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:09:09,241] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:09:09,242] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:09:09,242] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:09:09,242] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:09:09,242] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:09:09,250] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:09:09,251] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:09:09,251] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:09:09,305] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:09:09,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: successfully saved checkpoint at iteration 2000 to checkpoints_280moscar +7: time (ms) | save-checkpoint: 760.86 +7: iteration 2010/ 11269 | consumed samples: 514560 | consumed tokens: 1053818880 | elapsed time per iteration (s): 0.59 | learning rate: 1.875E-04 | global batch size: 256 | lm loss: 3.486458E+00 | grad norm: 0.423 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 433.624 | TFLOPs: 28.36 | +7: iteration 2020/ 11269 | consumed samples: 517120 | consumed tokens: 1059061760 | elapsed time per iteration (s): 0.48 | learning rate: 1.873E-04 | global batch size: 256 | lm loss: 3.490071E+00 | grad norm: 0.391 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.031 | TFLOPs: 34.73 | +7: iteration 2030/ 11269 | consumed samples: 519680 | consumed tokens: 1064304640 | elapsed time per iteration (s): 0.48 | learning rate: 1.872E-04 | global batch size: 256 | lm loss: 3.502809E+00 | grad norm: 0.404 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.621 | TFLOPs: 34.96 | +7: iteration 2040/ 11269 | consumed samples: 522240 | consumed tokens: 1069547520 | elapsed time per iteration (s): 0.49 | learning rate: 1.871E-04 | global batch size: 256 | lm loss: 3.473956E+00 | grad norm: 0.544 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.650 | TFLOPs: 34.05 | +7: iteration 2050/ 11269 | consumed samples: 524800 | consumed tokens: 1074790400 | elapsed time per iteration (s): 0.51 | learning rate: 1.869E-04 | global batch size: 256 | lm loss: 3.504304E+00 | grad norm: 0.773 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 501.631 | TFLOPs: 32.81 | +7: iteration 2060/ 11269 | consumed samples: 527360 | consumed tokens: 1080033280 | elapsed time per iteration (s): 0.49 | learning rate: 1.868E-04 | global batch size: 256 | lm loss: 3.542669E+00 | grad norm: 1.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.940 | TFLOPs: 33.94 | +7: iteration 2070/ 11269 | consumed samples: 529920 | consumed tokens: 1085276160 | elapsed time per iteration (s): 0.48 | learning rate: 1.867E-04 | global batch size: 256 | lm loss: 3.545784E+00 | grad norm: 0.643 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.856 | TFLOPs: 34.52 | +7: iteration 2080/ 11269 | consumed samples: 532480 | consumed tokens: 1090519040 | elapsed time per iteration (s): 0.48 | learning rate: 1.865E-04 | global batch size: 256 | lm loss: 3.513686E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.260 | TFLOPs: 34.61 | +7: iteration 2090/ 11269 | consumed samples: 535040 | consumed tokens: 1095761920 | elapsed time per iteration (s): 0.49 | learning rate: 1.864E-04 | global batch size: 256 | lm loss: 3.472852E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.135 | TFLOPs: 34.41 | +7: iteration 2100/ 11269 | consumed samples: 537600 | consumed tokens: 1101004800 | elapsed time per iteration (s): 0.49 | learning rate: 1.863E-04 | global batch size: 256 | lm loss: 3.489860E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.286 | TFLOPs: 34.35 | +7: iteration 2110/ 11269 | consumed samples: 540160 | consumed tokens: 1106247680 | elapsed time per iteration (s): 0.49 | learning rate: 1.861E-04 | global batch size: 256 | lm loss: 3.496206E+00 | grad norm: 0.383 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.257 | TFLOPs: 34.16 | +7: iteration 2120/ 11269 | consumed samples: 542720 | consumed tokens: 1111490560 | elapsed time per iteration (s): 0.49 | learning rate: 1.860E-04 | global batch size: 256 | lm loss: 3.470588E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.386 | TFLOPs: 34.49 | +7: iteration 2130/ 11269 | consumed samples: 545280 | consumed tokens: 1116733440 | elapsed time per iteration (s): 0.50 | learning rate: 1.859E-04 | global batch size: 256 | lm loss: 3.460014E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 513.513 | TFLOPs: 33.58 | +7: iteration 2140/ 11269 | consumed samples: 547840 | consumed tokens: 1121976320 | elapsed time per iteration (s): 0.48 | learning rate: 1.857E-04 | global batch size: 256 | lm loss: 3.472399E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.418 | TFLOPs: 35.02 | +7: iteration 2150/ 11269 | consumed samples: 550400 | consumed tokens: 1127219200 | elapsed time per iteration (s): 0.49 | learning rate: 1.856E-04 | global batch size: 256 | lm loss: 3.465211E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.400 | TFLOPs: 34.43 | +7: iteration 2160/ 11269 | consumed samples: 552960 | consumed tokens: 1132462080 | elapsed time per iteration (s): 0.50 | learning rate: 1.855E-04 | global batch size: 256 | lm loss: 3.487571E+00 | grad norm: 0.444 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 512.070 | TFLOPs: 33.49 | +7: iteration 2170/ 11269 | consumed samples: 555520 | consumed tokens: 1137704960 | elapsed time per iteration (s): 0.48 | learning rate: 1.853E-04 | global batch size: 256 | lm loss: 3.461234E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.366 | TFLOPs: 34.69 | +7: iteration 2180/ 11269 | consumed samples: 558080 | consumed tokens: 1142947840 | elapsed time per iteration (s): 0.48 | learning rate: 1.852E-04 | global batch size: 256 | lm loss: 3.457051E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.077 | TFLOPs: 34.73 | +7: iteration 2190/ 11269 | consumed samples: 560640 | consumed tokens: 1148190720 | elapsed time per iteration (s): 0.48 | learning rate: 1.850E-04 | global batch size: 256 | lm loss: 3.454500E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.940 | TFLOPs: 34.53 | +7: iteration 2200/ 11269 | consumed samples: 563200 | consumed tokens: 1153433600 | elapsed time per iteration (s): 0.48 | learning rate: 1.849E-04 | global batch size: 256 | lm loss: 3.448019E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.084 | TFLOPs: 34.60 | +7: iteration 2210/ 11269 | consumed samples: 565760 | consumed tokens: 1158676480 | elapsed time per iteration (s): 0.48 | learning rate: 1.848E-04 | global batch size: 256 | lm loss: 3.452511E+00 | grad norm: 0.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.491 | TFLOPs: 34.69 | +7: iteration 2220/ 11269 | consumed samples: 568320 | consumed tokens: 1163919360 | elapsed time per iteration (s): 0.49 | learning rate: 1.846E-04 | global batch size: 256 | lm loss: 3.455171E+00 | grad norm: 0.394 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.835 | TFLOPs: 34.39 | +7: iteration 2230/ 11269 | consumed samples: 570880 | consumed tokens: 1169162240 | elapsed time per iteration (s): 0.48 | learning rate: 1.845E-04 | global batch size: 256 | lm loss: 3.441755E+00 | grad norm: 0.410 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.285 | TFLOPs: 34.88 | +7: iteration 2240/ 11269 | consumed samples: 573440 | consumed tokens: 1174405120 | elapsed time per iteration (s): 0.49 | learning rate: 1.843E-04 | global batch size: 256 | lm loss: 3.467740E+00 | grad norm: 0.435 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.074 | TFLOPs: 34.21 | +7: iteration 2250/ 11269 | consumed samples: 576000 | consumed tokens: 1179648000 | elapsed time per iteration (s): 0.48 | learning rate: 1.842E-04 | global batch size: 256 | lm loss: 3.454001E+00 | grad norm: 0.425 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.727 | TFLOPs: 34.77 | +7: iteration 2260/ 11269 | consumed samples: 578560 | consumed tokens: 1184890880 | elapsed time per iteration (s): 0.49 | learning rate: 1.840E-04 | global batch size: 256 | lm loss: 3.435934E+00 | grad norm: 0.391 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 519.960 | TFLOPs: 34.01 | +7: iteration 2270/ 11269 | consumed samples: 581120 | consumed tokens: 1190133760 | elapsed time per iteration (s): 0.49 | learning rate: 1.839E-04 | global batch size: 256 | lm loss: 3.431268E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.045 | TFLOPs: 34.34 | +7: iteration 2280/ 11269 | consumed samples: 583680 | consumed tokens: 1195376640 | elapsed time per iteration (s): 0.50 | learning rate: 1.838E-04 | global batch size: 256 | lm loss: 3.444518E+00 | grad norm: 0.417 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 515.878 | TFLOPs: 33.74 | +7: iteration 2290/ 11269 | consumed samples: 586240 | consumed tokens: 1200619520 | elapsed time per iteration (s): 0.50 | learning rate: 1.836E-04 | global batch size: 256 | lm loss: 3.454397E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 510.456 | TFLOPs: 33.38 | +7: iteration 2300/ 11269 | consumed samples: 588800 | consumed tokens: 1205862400 | elapsed time per iteration (s): 0.48 | learning rate: 1.835E-04 | global batch size: 256 | lm loss: 3.423719E+00 | grad norm: 0.408 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.171 | TFLOPs: 34.61 | +7: iteration 2310/ 11269 | consumed samples: 591360 | consumed tokens: 1211105280 | elapsed time per iteration (s): 0.49 | learning rate: 1.833E-04 | global batch size: 256 | lm loss: 3.432936E+00 | grad norm: 0.421 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.377 | TFLOPs: 34.36 | +7: iteration 2320/ 11269 | consumed samples: 593920 | consumed tokens: 1216348160 | elapsed time per iteration (s): 0.50 | learning rate: 1.832E-04 | global batch size: 256 | lm loss: 3.416427E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 515.870 | TFLOPs: 33.74 | +7: iteration 2330/ 11269 | consumed samples: 596480 | consumed tokens: 1221591040 | elapsed time per iteration (s): 0.48 | learning rate: 1.830E-04 | global batch size: 256 | lm loss: 3.444173E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.516 | TFLOPs: 34.56 | +7: iteration 2340/ 11269 | consumed samples: 599040 | consumed tokens: 1226833920 | elapsed time per iteration (s): 0.49 | learning rate: 1.829E-04 | global batch size: 256 | lm loss: 3.436779E+00 | grad norm: 0.870 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.417 | TFLOPs: 34.49 | +7: iteration 2350/ 11269 | consumed samples: 601600 | consumed tokens: 1232076800 | elapsed time per iteration (s): 0.49 | learning rate: 1.827E-04 | global batch size: 256 | lm loss: 3.459921E+00 | grad norm: 0.440 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 519.018 | TFLOPs: 33.94 | +7: iteration 2360/ 11269 | consumed samples: 604160 | consumed tokens: 1237319680 | elapsed time per iteration (s): 0.50 | learning rate: 1.826E-04 | global batch size: 256 | lm loss: 3.418805E+00 | grad norm: 0.381 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 516.141 | TFLOPs: 33.76 | +7: iteration 2370/ 11269 | consumed samples: 606720 | consumed tokens: 1242562560 | elapsed time per iteration (s): 0.49 | learning rate: 1.824E-04 | global batch size: 256 | lm loss: 3.410075E+00 | grad norm: 0.713 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.156 | TFLOPs: 34.35 | +7: iteration 2380/ 11269 | consumed samples: 609280 | consumed tokens: 1247805440 | elapsed time per iteration (s): 0.48 | learning rate: 1.823E-04 | global batch size: 256 | lm loss: 3.416851E+00 | grad norm: 0.423 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.139 | TFLOPs: 34.67 | +7: iteration 2390/ 11269 | consumed samples: 611840 | consumed tokens: 1253048320 | elapsed time per iteration (s): 0.49 | learning rate: 1.821E-04 | global batch size: 256 | lm loss: 3.447997E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.691 | TFLOPs: 34.18 | +7: iteration 2400/ 11269 | consumed samples: 614400 | consumed tokens: 1258291200 | elapsed time per iteration (s): 0.48 | learning rate: 1.820E-04 | global batch size: 256 | lm loss: 3.398949E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.543 | TFLOPs: 34.63 | +7: iteration 2410/ 11269 | consumed samples: 616960 | consumed tokens: 1263534080 | elapsed time per iteration (s): 0.49 | learning rate: 1.818E-04 | global batch size: 256 | lm loss: 3.421989E+00 | grad norm: 0.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.951 | TFLOPs: 34.20 | +7: iteration 2420/ 11269 | consumed samples: 619520 | consumed tokens: 1268776960 | elapsed time per iteration (s): 0.48 | learning rate: 1.817E-04 | global batch size: 256 | lm loss: 3.395298E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.255 | TFLOPs: 34.61 | +7: iteration 2430/ 11269 | consumed samples: 622080 | consumed tokens: 1274019840 | elapsed time per iteration (s): 0.50 | learning rate: 1.815E-04 | global batch size: 256 | lm loss: 3.419765E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 514.379 | TFLOPs: 33.64 | +7: iteration 2440/ 11269 | consumed samples: 624640 | consumed tokens: 1279262720 | elapsed time per iteration (s): 0.48 | learning rate: 1.814E-04 | global batch size: 256 | lm loss: 3.405205E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.305 | TFLOPs: 34.88 | +7: iteration 2450/ 11269 | consumed samples: 627200 | consumed tokens: 1284505600 | elapsed time per iteration (s): 0.49 | learning rate: 1.812E-04 | global batch size: 256 | lm loss: 3.414911E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.640 | TFLOPs: 33.92 | +7: iteration 2460/ 11269 | consumed samples: 629760 | consumed tokens: 1289748480 | elapsed time per iteration (s): 0.48 | learning rate: 1.810E-04 | global batch size: 256 | lm loss: 3.386184E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.240 | TFLOPs: 34.81 | +7: iteration 2470/ 11269 | consumed samples: 632320 | consumed tokens: 1294991360 | elapsed time per iteration (s): 0.49 | learning rate: 1.809E-04 | global batch size: 256 | lm loss: 3.406841E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.140 | TFLOPs: 33.89 | +7: iteration 2480/ 11269 | consumed samples: 634880 | consumed tokens: 1300234240 | elapsed time per iteration (s): 0.50 | learning rate: 1.807E-04 | global batch size: 256 | lm loss: 3.411943E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 514.961 | TFLOPs: 33.68 | +7: iteration 2490/ 11269 | consumed samples: 637440 | consumed tokens: 1305477120 | elapsed time per iteration (s): 0.50 | learning rate: 1.806E-04 | global batch size: 256 | lm loss: 3.402354E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 511.250 | TFLOPs: 33.44 | +7: iteration 2500/ 11269 | consumed samples: 640000 | consumed tokens: 1310720000 | elapsed time per iteration (s): 0.50 | learning rate: 1.804E-04 | global batch size: 256 | lm loss: 3.423024E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 514.543 | TFLOPs: 33.65 | +7: iteration 2510/ 11269 | consumed samples: 642560 | consumed tokens: 1315962880 | elapsed time per iteration (s): 0.48 | learning rate: 1.803E-04 | global batch size: 256 | lm loss: 3.411778E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.292 | TFLOPs: 34.62 | +7: iteration 2520/ 11269 | consumed samples: 645120 | consumed tokens: 1321205760 | elapsed time per iteration (s): 0.49 | learning rate: 1.801E-04 | global batch size: 256 | lm loss: 3.400008E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.707 | TFLOPs: 34.12 | +7: iteration 2530/ 11269 | consumed samples: 647680 | consumed tokens: 1326448640 | elapsed time per iteration (s): 0.50 | learning rate: 1.799E-04 | global batch size: 256 | lm loss: 3.389493E+00 | grad norm: 0.381 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 510.433 | TFLOPs: 33.38 | +7: iteration 2540/ 11269 | consumed samples: 650240 | consumed tokens: 1331691520 | elapsed time per iteration (s): 0.48 | learning rate: 1.798E-04 | global batch size: 256 | lm loss: 3.387372E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.960 | TFLOPs: 34.86 | +7: iteration 2550/ 11269 | consumed samples: 652800 | consumed tokens: 1336934400 | elapsed time per iteration (s): 0.49 | learning rate: 1.796E-04 | global batch size: 256 | lm loss: 3.389775E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 519.823 | TFLOPs: 34.00 | +7: iteration 2560/ 11269 | consumed samples: 655360 | consumed tokens: 1342177280 | elapsed time per iteration (s): 0.49 | learning rate: 1.795E-04 | global batch size: 256 | lm loss: 3.386180E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.541 | TFLOPs: 34.50 | +7: iteration 2570/ 11269 | consumed samples: 657920 | consumed tokens: 1347420160 | elapsed time per iteration (s): 0.49 | learning rate: 1.793E-04 | global batch size: 256 | lm loss: 3.384830E+00 | grad norm: 0.407 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.164 | TFLOPs: 34.08 | +7: iteration 2580/ 11269 | consumed samples: 660480 | consumed tokens: 1352663040 | elapsed time per iteration (s): 0.49 | learning rate: 1.791E-04 | global batch size: 256 | lm loss: 3.391388E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.213 | TFLOPs: 34.35 | +7: iteration 2590/ 11269 | consumed samples: 663040 | consumed tokens: 1357905920 | elapsed time per iteration (s): 0.48 | learning rate: 1.790E-04 | global batch size: 256 | lm loss: 3.369614E+00 | grad norm: 0.381 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.844 | TFLOPs: 34.65 | +7: iteration 2600/ 11269 | consumed samples: 665600 | consumed tokens: 1363148800 | elapsed time per iteration (s): 0.49 | learning rate: 1.788E-04 | global batch size: 256 | lm loss: 3.369175E+00 | grad norm: 0.402 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.952 | TFLOPs: 34.33 | +7: iteration 2610/ 11269 | consumed samples: 668160 | consumed tokens: 1368391680 | elapsed time per iteration (s): 0.50 | learning rate: 1.786E-04 | global batch size: 256 | lm loss: 3.369935E+00 | grad norm: 0.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 516.203 | TFLOPs: 33.76 | +7: iteration 2620/ 11269 | consumed samples: 670720 | consumed tokens: 1373634560 | elapsed time per iteration (s): 0.49 | learning rate: 1.785E-04 | global batch size: 256 | lm loss: 3.368736E+00 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.589 | TFLOPs: 34.44 | +7: iteration 2630/ 11269 | consumed samples: 673280 | consumed tokens: 1378877440 | elapsed time per iteration (s): 0.50 | learning rate: 1.783E-04 | global batch size: 256 | lm loss: 3.357176E+00 | grad norm: 0.483 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 512.188 | TFLOPs: 33.50 | +7: iteration 2640/ 11269 | consumed samples: 675840 | consumed tokens: 1384120320 | elapsed time per iteration (s): 0.49 | learning rate: 1.782E-04 | global batch size: 256 | lm loss: 3.386967E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 519.188 | TFLOPs: 33.95 | +7: iteration 2650/ 11269 | consumed samples: 678400 | consumed tokens: 1389363200 | elapsed time per iteration (s): 0.48 | learning rate: 1.780E-04 | global batch size: 256 | lm loss: 3.343266E+00 | grad norm: 0.875 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.886 | TFLOPs: 34.59 | +7: iteration 2660/ 11269 | consumed samples: 680960 | consumed tokens: 1394606080 | elapsed time per iteration (s): 0.49 | learning rate: 1.778E-04 | global batch size: 256 | lm loss: 3.424061E+00 | grad norm: 0.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.346 | TFLOPs: 34.49 | +7: iteration 2670/ 11269 | consumed samples: 683520 | consumed tokens: 1399848960 | elapsed time per iteration (s): 0.48 | learning rate: 1.777E-04 | global batch size: 256 | lm loss: 3.379863E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.937 | TFLOPs: 34.53 | +7: iteration 2680/ 11269 | consumed samples: 686080 | consumed tokens: 1405091840 | elapsed time per iteration (s): 0.49 | learning rate: 1.775E-04 | global batch size: 256 | lm loss: 3.356110E+00 | grad norm: 0.377 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.434 | TFLOPs: 34.49 | +7: iteration 2690/ 11269 | consumed samples: 688640 | consumed tokens: 1410334720 | elapsed time per iteration (s): 0.48 | learning rate: 1.773E-04 | global batch size: 256 | lm loss: 3.341007E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.963 | TFLOPs: 34.72 | +7: iteration 2700/ 11269 | consumed samples: 691200 | consumed tokens: 1415577600 | elapsed time per iteration (s): 0.48 | learning rate: 1.772E-04 | global batch size: 256 | lm loss: 3.358539E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.234 | TFLOPs: 34.68 | +7: iteration 2710/ 11269 | consumed samples: 693760 | consumed tokens: 1420820480 | elapsed time per iteration (s): 0.48 | learning rate: 1.770E-04 | global batch size: 256 | lm loss: 3.358268E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.654 | TFLOPs: 34.57 | +7: iteration 2720/ 11269 | consumed samples: 696320 | consumed tokens: 1426063360 | elapsed time per iteration (s): 0.49 | learning rate: 1.768E-04 | global batch size: 256 | lm loss: 3.346249E+00 | grad norm: 0.463 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.636 | TFLOPs: 34.51 | +7: iteration 2730/ 11269 | consumed samples: 698880 | consumed tokens: 1431306240 | elapsed time per iteration (s): 0.49 | learning rate: 1.766E-04 | global batch size: 256 | lm loss: 3.359521E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.556 | TFLOPs: 34.24 | +7: iteration 2740/ 11269 | consumed samples: 701440 | consumed tokens: 1436549120 | elapsed time per iteration (s): 0.48 | learning rate: 1.765E-04 | global batch size: 256 | lm loss: 3.336089E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.959 | TFLOPs: 34.86 | +7: iteration 2750/ 11269 | consumed samples: 704000 | consumed tokens: 1441792000 | elapsed time per iteration (s): 0.50 | learning rate: 1.763E-04 | global batch size: 256 | lm loss: 3.351630E+00 | grad norm: 2.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 513.195 | TFLOPs: 33.56 | +7: iteration 2760/ 11269 | consumed samples: 706560 | consumed tokens: 1447034880 | elapsed time per iteration (s): 0.49 | learning rate: 1.761E-04 | global batch size: 256 | lm loss: 3.412474E+00 | grad norm: 0.577 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.512 | TFLOPs: 34.24 | +7: iteration 2770/ 11269 | consumed samples: 709120 | consumed tokens: 1452277760 | elapsed time per iteration (s): 0.49 | learning rate: 1.760E-04 | global batch size: 256 | lm loss: 3.411522E+00 | grad norm: 1.048 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.972 | TFLOPs: 33.88 | +7: iteration 2780/ 11269 | consumed samples: 711680 | consumed tokens: 1457520640 | elapsed time per iteration (s): 0.49 | learning rate: 1.758E-04 | global batch size: 256 | lm loss: 3.421719E+00 | grad norm: 3.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.759 | TFLOPs: 34.06 | +7: iteration 2790/ 11269 | consumed samples: 714240 | consumed tokens: 1462763520 | elapsed time per iteration (s): 0.48 | learning rate: 1.756E-04 | global batch size: 256 | lm loss: 3.478624E+00 | grad norm: 0.818 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.198 | TFLOPs: 34.87 | +7: iteration 2800/ 11269 | consumed samples: 716800 | consumed tokens: 1468006400 | elapsed time per iteration (s): 0.48 | learning rate: 1.754E-04 | global batch size: 256 | lm loss: 3.436840E+00 | grad norm: 0.463 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.813 | TFLOPs: 34.72 | +7: iteration 2810/ 11269 | consumed samples: 719360 | consumed tokens: 1473249280 | elapsed time per iteration (s): 0.48 | learning rate: 1.753E-04 | global batch size: 256 | lm loss: 3.402664E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.739 | TFLOPs: 34.64 | +7: iteration 2820/ 11269 | consumed samples: 721920 | consumed tokens: 1478492160 | elapsed time per iteration (s): 0.49 | learning rate: 1.751E-04 | global batch size: 256 | lm loss: 3.390200E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.305 | TFLOPs: 34.42 | +7: iteration 2830/ 11269 | consumed samples: 724480 | consumed tokens: 1483735040 | elapsed time per iteration (s): 0.49 | learning rate: 1.749E-04 | global batch size: 256 | lm loss: 3.356696E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.678 | TFLOPs: 33.92 | +7: iteration 2840/ 11269 | consumed samples: 727040 | consumed tokens: 1488977920 | elapsed time per iteration (s): 0.48 | learning rate: 1.747E-04 | global batch size: 256 | lm loss: 3.361257E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.579 | TFLOPs: 34.70 | +7: iteration 2850/ 11269 | consumed samples: 729600 | consumed tokens: 1494220800 | elapsed time per iteration (s): 0.49 | learning rate: 1.746E-04 | global batch size: 256 | lm loss: 3.378594E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.419 | TFLOPs: 34.43 | +7: iteration 2860/ 11269 | consumed samples: 732160 | consumed tokens: 1499463680 | elapsed time per iteration (s): 0.49 | learning rate: 1.744E-04 | global batch size: 256 | lm loss: 3.359027E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.727 | TFLOPs: 34.19 | +7: iteration 2870/ 11269 | consumed samples: 734720 | consumed tokens: 1504706560 | elapsed time per iteration (s): 0.48 | learning rate: 1.742E-04 | global batch size: 256 | lm loss: 3.364589E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.861 | TFLOPs: 35.18 | +7: iteration 2880/ 11269 | consumed samples: 737280 | consumed tokens: 1509949440 | elapsed time per iteration (s): 0.49 | learning rate: 1.740E-04 | global batch size: 256 | lm loss: 3.328471E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.799 | TFLOPs: 34.06 | +7: iteration 2890/ 11269 | consumed samples: 739840 | consumed tokens: 1515192320 | elapsed time per iteration (s): 0.48 | learning rate: 1.739E-04 | global batch size: 256 | lm loss: 3.325008E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.099 | TFLOPs: 34.80 | +7: iteration 2900/ 11269 | consumed samples: 742400 | consumed tokens: 1520435200 | elapsed time per iteration (s): 0.50 | learning rate: 1.737E-04 | global batch size: 256 | lm loss: 3.346202E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 511.522 | TFLOPs: 33.45 | +7: iteration 2910/ 11269 | consumed samples: 744960 | consumed tokens: 1525678080 | elapsed time per iteration (s): 0.51 | learning rate: 1.735E-04 | global batch size: 256 | lm loss: 3.348462E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 506.364 | TFLOPs: 33.12 | +7: iteration 2920/ 11269 | consumed samples: 747520 | consumed tokens: 1530920960 | elapsed time per iteration (s): 0.49 | learning rate: 1.733E-04 | global batch size: 256 | lm loss: 3.325143E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.492 | TFLOPs: 34.04 | +7: iteration 2930/ 11269 | consumed samples: 750080 | consumed tokens: 1536163840 | elapsed time per iteration (s): 0.51 | learning rate: 1.731E-04 | global batch size: 256 | lm loss: 3.303571E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 503.280 | TFLOPs: 32.91 | +7: iteration 2940/ 11269 | consumed samples: 752640 | consumed tokens: 1541406720 | elapsed time per iteration (s): 0.51 | learning rate: 1.730E-04 | global batch size: 256 | lm loss: 3.366065E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 506.870 | TFLOPs: 33.15 | +7: iteration 2950/ 11269 | consumed samples: 755200 | consumed tokens: 1546649600 | elapsed time per iteration (s): 0.50 | learning rate: 1.728E-04 | global batch size: 256 | lm loss: 3.304288E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 513.290 | TFLOPs: 33.57 | +7: iteration 2960/ 11269 | consumed samples: 757760 | consumed tokens: 1551892480 | elapsed time per iteration (s): 0.49 | learning rate: 1.726E-04 | global batch size: 256 | lm loss: 3.303240E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.438 | TFLOPs: 34.49 | +7: iteration 2970/ 11269 | consumed samples: 760320 | consumed tokens: 1557135360 | elapsed time per iteration (s): 0.48 | learning rate: 1.724E-04 | global batch size: 256 | lm loss: 3.305698E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.679 | TFLOPs: 35.10 | +7: iteration 2980/ 11269 | consumed samples: 762880 | consumed tokens: 1562378240 | elapsed time per iteration (s): 0.49 | learning rate: 1.722E-04 | global batch size: 256 | lm loss: 3.360927E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.703 | TFLOPs: 34.32 | +7: iteration 2990/ 11269 | consumed samples: 765440 | consumed tokens: 1567621120 | elapsed time per iteration (s): 0.48 | learning rate: 1.720E-04 | global batch size: 256 | lm loss: 3.299805E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.028 | TFLOPs: 34.53 | +7: iteration 3000/ 11269 | consumed samples: 768000 | consumed tokens: 1572864000 | elapsed time per iteration (s): 0.49 | learning rate: 1.719E-04 | global batch size: 256 | lm loss: 3.302173E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.017 | TFLOPs: 34.14 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 3000 | lm loss value: 3.140520E+00 | lm loss PPL: 2.311589E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 3000 to checkpoints_280moscar +0: [2022-11-29 17:17:18,429] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step3000 is begin to save! +0: [2022-11-29 17:17:18,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:17:18,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:17:18,548] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:17:18,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:17:18,573] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:17:18,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:17:18,598] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:17:18,622] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:17:18,623] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:17:18,647] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:17:18,647] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:17:18,672] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:17:18,672] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:17:18,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:17:18,697] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:17:18,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:17:18,721] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:17:18,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:17:18,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:17:18,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:17:18,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:17:18,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:17:18,795] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:17:18,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:17:18,819] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:17:18,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:17:18,844] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:17:18,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:17:18,868] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:17:18,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:17:18,908] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:17:18,953] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:17:18,953] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/layer_18-model_00-model_states.pt... +0: [2022-11-29 17:17:18,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/layer_18-model_00-model_states.pt. +0: [2022-11-29 17:17:18,978] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:17:19,002] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:17:19,002] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/layer_20-model_00-model_states.pt... +0: [2022-11-29 17:17:19,027] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/layer_20-model_00-model_states.pt. +0: [2022-11-29 17:17:19,027] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/layer_22-model_00-model_states.pt... +0: [2022-11-29 17:17:19,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/layer_22-model_00-model_states.pt. +0: [2022-11-29 17:17:19,029] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_280moscar/global_step3000/mp_rank_00_model_states.pt +0: [2022-11-29 17:17:19,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:17:19,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:17:19,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:17:19,103] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:17:19,107] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:17:19,107] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:17:19,107] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:17:19,109] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:17:19,109] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:17:19,109] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:17:19,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:17:19,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:17:19,110] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:17:19,110] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:17:19,110] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:17:19,110] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:17:19,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:17:19,111] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:17:19,111] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:17:19,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:17:19,112] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:17:19,112] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:17:19,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:17:19,112] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:17:19,112] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:17:19,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:17:19,109] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:17:19,112] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:17:19,112] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:17:19,114] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:17:19,114] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:17:19,114] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:17:19,114] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:17:19,114] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:17:19,114] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:17:19,114] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:17:19,114] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:17:19,114] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:17:19,114] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:17:19,115] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:17:19,115] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:17:19,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:17:19,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:17:19,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:17:19,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:17:19,120] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:17:19,120] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:17:19,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:17:19,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:17:19,121] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:17:19,121] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:17:19,121] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:17:19,122] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:17:19,122] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:17:19,122] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:17:19,122] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:17:19,123] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:17:19,123] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:17:19,123] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:17:19,123] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:17:19,123] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:17:19,124] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:17:19,124] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:17:19,124] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:17:19,124] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:17:19,124] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:17:19,124] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:17:19,107] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:17:19,124] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:17:19,124] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:17:19,124] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:17:19,124] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:17:19,124] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:17:19,124] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:17:19,107] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:17:19,107] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:17:19,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:17:19,124] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:17:19,111] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:17:19,111] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:17:19,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:17:19,112] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:17:19,112] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:17:19,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:17:19,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:17:19,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:17:19,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:17:19,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:17:19,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:17:19,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:17:19,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:17:19,120] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:17:19,120] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:17:19,120] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:17:19,120] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:17:19,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:17:19,121] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:17:19,121] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:17:19,109] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:17:19,109] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:17:19,113] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:17:19,113] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:17:19,113] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:17:19,114] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:17:19,114] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:17:19,114] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:17:19,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:17:19,118] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:17:19,118] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:17:19,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:17:19,118] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:17:19,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:17:19,122] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:17:19,122] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:17:19,122] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:17:19,123] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:17:19,123] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:17:19,123] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:17:19,125] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:17:19,125] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:17:19,125] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:17:19,125] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:17:19,125] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:17:19,125] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:17:19,125] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:17:19,125] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:17:19,125] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:17:19,128] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:17:19,128] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:17:19,128] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:17:19,128] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:17:19,128] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:17:19,128] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:17:19,128] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +0: [2022-11-29 17:17:19,128] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:17:19,128] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +7: [2022-11-29 17:17:19,128] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:17:19,128] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:17:19,128] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:17:19,128] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:17:19,128] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:17:19,128] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:17:19,128] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:17:19,129] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:17:19,129] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:17:19,130] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:17:19,130] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:17:19,130] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:17:19,130] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:17:19,130] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:17:19,130] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:17:19,131] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:17:19,131] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:17:19,131] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:17:19,131] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:17:19,131] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:17:19,131] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:17:19,131] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:17:19,131] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:17:19,131] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:17:19,131] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:17:19,131] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:17:19,131] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:17:19,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:17:19,140] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:17:19,140] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:17:19,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:17:19,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:17:19,140] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:17:19,140] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:17:19,140] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:17:19,140] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:17:19,141] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:17:19,141] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:17:19,141] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:17:19,141] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:17:19,142] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:17:19,142] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:17:19,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:17:19,142] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:17:19,142] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:17:19,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:17:19,143] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:17:19,143] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:17:19,129] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:17:19,129] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:17:19,129] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:17:19,152] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:17:19,152] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:17:19,152] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:17:19,152] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:17:19,152] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:17:19,152] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:17:19,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:17:19,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: successfully saved checkpoint at iteration 3000 to checkpoints_280moscar +7: time (ms) | save-checkpoint: 772.71 +7: iteration 3010/ 11269 | consumed samples: 770560 | consumed tokens: 1578106880 | elapsed time per iteration (s): 0.58 | learning rate: 1.717E-04 | global batch size: 256 | lm loss: 3.319137E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.625 | TFLOPs: 28.95 | +7: iteration 3020/ 11269 | consumed samples: 773120 | consumed tokens: 1583349760 | elapsed time per iteration (s): 0.48 | learning rate: 1.715E-04 | global batch size: 256 | lm loss: 3.326492E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.840 | TFLOPs: 34.85 | +7: iteration 3030/ 11269 | consumed samples: 775680 | consumed tokens: 1588592640 | elapsed time per iteration (s): 0.48 | learning rate: 1.713E-04 | global batch size: 256 | lm loss: 3.301016E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.096 | TFLOPs: 35.00 | +7: iteration 3040/ 11269 | consumed samples: 778240 | consumed tokens: 1593835520 | elapsed time per iteration (s): 0.48 | learning rate: 1.711E-04 | global batch size: 256 | lm loss: 3.324797E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.241 | TFLOPs: 35.07 | +7: iteration 3050/ 11269 | consumed samples: 780800 | consumed tokens: 1599078400 | elapsed time per iteration (s): 0.48 | learning rate: 1.709E-04 | global batch size: 256 | lm loss: 3.317037E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.411 | TFLOPs: 34.56 | +7: iteration 3060/ 11269 | consumed samples: 783360 | consumed tokens: 1604321280 | elapsed time per iteration (s): 0.48 | learning rate: 1.707E-04 | global batch size: 256 | lm loss: 3.286342E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.667 | TFLOPs: 34.64 | +7: iteration 3070/ 11269 | consumed samples: 785920 | consumed tokens: 1609564160 | elapsed time per iteration (s): 0.48 | learning rate: 1.706E-04 | global batch size: 256 | lm loss: 3.315489E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.700 | TFLOPs: 35.03 | +7: iteration 3080/ 11269 | consumed samples: 788480 | consumed tokens: 1614807040 | elapsed time per iteration (s): 0.49 | learning rate: 1.704E-04 | global batch size: 256 | lm loss: 3.322235E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.247 | TFLOPs: 33.89 | +7: iteration 3090/ 11269 | consumed samples: 791040 | consumed tokens: 1620049920 | elapsed time per iteration (s): 0.49 | learning rate: 1.702E-04 | global batch size: 256 | lm loss: 3.317073E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.255 | TFLOPs: 34.42 | +7: iteration 3100/ 11269 | consumed samples: 793600 | consumed tokens: 1625292800 | elapsed time per iteration (s): 0.48 | learning rate: 1.700E-04 | global batch size: 256 | lm loss: 3.303051E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.808 | TFLOPs: 35.04 | +7: iteration 3110/ 11269 | consumed samples: 796160 | consumed tokens: 1630535680 | elapsed time per iteration (s): 0.48 | learning rate: 1.698E-04 | global batch size: 256 | lm loss: 3.303169E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.425 | TFLOPs: 35.02 | +7: iteration 3120/ 11269 | consumed samples: 798720 | consumed tokens: 1635778560 | elapsed time per iteration (s): 0.49 | learning rate: 1.696E-04 | global batch size: 256 | lm loss: 3.317271E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.156 | TFLOPs: 34.28 | +7: iteration 3130/ 11269 | consumed samples: 801280 | consumed tokens: 1641021440 | elapsed time per iteration (s): 0.49 | learning rate: 1.694E-04 | global batch size: 256 | lm loss: 3.318497E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.137 | TFLOPs: 34.21 | +7: iteration 3140/ 11269 | consumed samples: 803840 | consumed tokens: 1646264320 | elapsed time per iteration (s): 0.50 | learning rate: 1.692E-04 | global batch size: 256 | lm loss: 3.293530E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 511.844 | TFLOPs: 33.47 | +7: iteration 3150/ 11269 | consumed samples: 806400 | consumed tokens: 1651507200 | elapsed time per iteration (s): 0.49 | learning rate: 1.690E-04 | global batch size: 256 | lm loss: 3.284908E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.801 | TFLOPs: 34.45 | +7: iteration 3160/ 11269 | consumed samples: 808960 | consumed tokens: 1656750080 | elapsed time per iteration (s): 0.49 | learning rate: 1.688E-04 | global batch size: 256 | lm loss: 3.283961E+00 | grad norm: 0.399 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.680 | TFLOPs: 34.25 | +7: iteration 3170/ 11269 | consumed samples: 811520 | consumed tokens: 1661992960 | elapsed time per iteration (s): 0.49 | learning rate: 1.687E-04 | global batch size: 256 | lm loss: 3.287147E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.538 | TFLOPs: 34.44 | +7: iteration 3180/ 11269 | consumed samples: 814080 | consumed tokens: 1667235840 | elapsed time per iteration (s): 0.49 | learning rate: 1.685E-04 | global batch size: 256 | lm loss: 3.304942E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.110 | TFLOPs: 34.41 | +7: iteration 3190/ 11269 | consumed samples: 816640 | consumed tokens: 1672478720 | elapsed time per iteration (s): 0.48 | learning rate: 1.683E-04 | global batch size: 256 | lm loss: 3.277026E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.417 | TFLOPs: 34.75 | +7: iteration 3200/ 11269 | consumed samples: 819200 | consumed tokens: 1677721600 | elapsed time per iteration (s): 0.51 | learning rate: 1.681E-04 | global batch size: 256 | lm loss: 3.322816E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 500.376 | TFLOPs: 32.72 | +7: iteration 3210/ 11269 | consumed samples: 821760 | consumed tokens: 1682964480 | elapsed time per iteration (s): 0.48 | learning rate: 1.679E-04 | global batch size: 256 | lm loss: 3.287775E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.280 | TFLOPs: 34.94 | +7: iteration 3220/ 11269 | consumed samples: 824320 | consumed tokens: 1688207360 | elapsed time per iteration (s): 0.48 | learning rate: 1.677E-04 | global batch size: 256 | lm loss: 3.292045E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.667 | TFLOPs: 34.71 | +7: iteration 3230/ 11269 | consumed samples: 826880 | consumed tokens: 1693450240 | elapsed time per iteration (s): 0.50 | learning rate: 1.675E-04 | global batch size: 256 | lm loss: 3.276307E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 509.322 | TFLOPs: 33.31 | +7: iteration 3240/ 11269 | consumed samples: 829440 | consumed tokens: 1698693120 | elapsed time per iteration (s): 0.49 | learning rate: 1.673E-04 | global batch size: 256 | lm loss: 3.278205E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.805 | TFLOPs: 34.39 | +7: iteration 3250/ 11269 | consumed samples: 832000 | consumed tokens: 1703936000 | elapsed time per iteration (s): 0.49 | learning rate: 1.671E-04 | global batch size: 256 | lm loss: 3.258368E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.209 | TFLOPs: 33.83 | +7: iteration 3260/ 11269 | consumed samples: 834560 | consumed tokens: 1709178880 | elapsed time per iteration (s): 0.49 | learning rate: 1.669E-04 | global batch size: 256 | lm loss: 3.259803E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 519.493 | TFLOPs: 33.97 | +7: iteration 3270/ 11269 | consumed samples: 837120 | consumed tokens: 1714421760 | elapsed time per iteration (s): 0.48 | learning rate: 1.667E-04 | global batch size: 256 | lm loss: 3.299592E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.925 | TFLOPs: 35.05 | +7: iteration 3280/ 11269 | consumed samples: 839680 | consumed tokens: 1719664640 | elapsed time per iteration (s): 0.49 | learning rate: 1.665E-04 | global batch size: 256 | lm loss: 3.278499E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.255 | TFLOPs: 34.22 | +7: iteration 3290/ 11269 | consumed samples: 842240 | consumed tokens: 1724907520 | elapsed time per iteration (s): 0.49 | learning rate: 1.663E-04 | global batch size: 256 | lm loss: 3.263840E+00 | grad norm: 0.373 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.053 | TFLOPs: 33.88 | +7: iteration 3300/ 11269 | consumed samples: 844800 | consumed tokens: 1730150400 | elapsed time per iteration (s): 0.51 | learning rate: 1.661E-04 | global batch size: 256 | lm loss: 3.282739E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 505.628 | TFLOPs: 33.07 | +7: iteration 3310/ 11269 | consumed samples: 847360 | consumed tokens: 1735393280 | elapsed time per iteration (s): 0.49 | learning rate: 1.659E-04 | global batch size: 256 | lm loss: 3.281604E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.321 | TFLOPs: 33.83 | +7: iteration 3320/ 11269 | consumed samples: 849920 | consumed tokens: 1740636160 | elapsed time per iteration (s): 0.49 | learning rate: 1.657E-04 | global batch size: 256 | lm loss: 3.257940E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.936 | TFLOPs: 34.46 | +7: iteration 3330/ 11269 | consumed samples: 852480 | consumed tokens: 1745879040 | elapsed time per iteration (s): 0.49 | learning rate: 1.655E-04 | global batch size: 256 | lm loss: 3.283009E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.866 | TFLOPs: 34.06 | +7: iteration 3340/ 11269 | consumed samples: 855040 | consumed tokens: 1751121920 | elapsed time per iteration (s): 0.50 | learning rate: 1.653E-04 | global batch size: 256 | lm loss: 3.286466E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.071 | TFLOPs: 33.82 | +7: iteration 3350/ 11269 | consumed samples: 857600 | consumed tokens: 1756364800 | elapsed time per iteration (s): 0.48 | learning rate: 1.651E-04 | global batch size: 256 | lm loss: 3.265931E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.159 | TFLOPs: 34.87 | +7: iteration 3360/ 11269 | consumed samples: 860160 | consumed tokens: 1761607680 | elapsed time per iteration (s): 0.48 | learning rate: 1.649E-04 | global batch size: 256 | lm loss: 3.252147E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.958 | TFLOPs: 34.99 | +7: iteration 3370/ 11269 | consumed samples: 862720 | consumed tokens: 1766850560 | elapsed time per iteration (s): 0.49 | learning rate: 1.647E-04 | global batch size: 256 | lm loss: 3.278196E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.367 | TFLOPs: 34.16 | +7: iteration 3380/ 11269 | consumed samples: 865280 | consumed tokens: 1772093440 | elapsed time per iteration (s): 0.49 | learning rate: 1.645E-04 | global batch size: 256 | lm loss: 3.269576E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.771 | TFLOPs: 34.52 | +7: iteration 3390/ 11269 | consumed samples: 867840 | consumed tokens: 1777336320 | elapsed time per iteration (s): 0.48 | learning rate: 1.643E-04 | global batch size: 256 | lm loss: 3.279225E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.592 | TFLOPs: 34.77 | +7: iteration 3400/ 11269 | consumed samples: 870400 | consumed tokens: 1782579200 | elapsed time per iteration (s): 0.48 | learning rate: 1.641E-04 | global batch size: 256 | lm loss: 3.238159E+00 | grad norm: 0.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.874 | TFLOPs: 35.05 | +7: iteration 3410/ 11269 | consumed samples: 872960 | consumed tokens: 1787822080 | elapsed time per iteration (s): 0.49 | learning rate: 1.639E-04 | global batch size: 256 | lm loss: 3.268597E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.698 | TFLOPs: 34.25 | +7: iteration 3420/ 11269 | consumed samples: 875520 | consumed tokens: 1793064960 | elapsed time per iteration (s): 0.49 | learning rate: 1.637E-04 | global batch size: 256 | lm loss: 3.238940E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.773 | TFLOPs: 33.93 | +7: iteration 3430/ 11269 | consumed samples: 878080 | consumed tokens: 1798307840 | elapsed time per iteration (s): 0.48 | learning rate: 1.635E-04 | global batch size: 256 | lm loss: 3.272628E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.188 | TFLOPs: 34.54 | +7: iteration 3440/ 11269 | consumed samples: 880640 | consumed tokens: 1803550720 | elapsed time per iteration (s): 0.48 | learning rate: 1.633E-04 | global batch size: 256 | lm loss: 3.271558E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.777 | TFLOPs: 34.58 | +7: iteration 3450/ 11269 | consumed samples: 883200 | consumed tokens: 1808793600 | elapsed time per iteration (s): 0.49 | learning rate: 1.631E-04 | global batch size: 256 | lm loss: 3.281933E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.829 | TFLOPs: 34.45 | +7: iteration 3460/ 11269 | consumed samples: 885760 | consumed tokens: 1814036480 | elapsed time per iteration (s): 0.49 | learning rate: 1.629E-04 | global batch size: 256 | lm loss: 3.256512E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.325 | TFLOPs: 34.36 | +7: iteration 3470/ 11269 | consumed samples: 888320 | consumed tokens: 1819279360 | elapsed time per iteration (s): 0.49 | learning rate: 1.627E-04 | global batch size: 256 | lm loss: 3.258695E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.051 | TFLOPs: 34.14 | +7: iteration 3480/ 11269 | consumed samples: 890880 | consumed tokens: 1824522240 | elapsed time per iteration (s): 0.49 | learning rate: 1.625E-04 | global batch size: 256 | lm loss: 3.266991E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.161 | TFLOPs: 34.02 | +7: iteration 3490/ 11269 | consumed samples: 893440 | consumed tokens: 1829765120 | elapsed time per iteration (s): 0.48 | learning rate: 1.623E-04 | global batch size: 256 | lm loss: 3.229772E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.043 | TFLOPs: 34.53 | +7: iteration 3500/ 11269 | consumed samples: 896000 | consumed tokens: 1835008000 | elapsed time per iteration (s): 0.51 | learning rate: 1.621E-04 | global batch size: 256 | lm loss: 3.276263E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 505.252 | TFLOPs: 33.04 | +7: iteration 3510/ 11269 | consumed samples: 898560 | consumed tokens: 1840250880 | elapsed time per iteration (s): 0.49 | learning rate: 1.619E-04 | global batch size: 256 | lm loss: 3.231759E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.865 | TFLOPs: 34.33 | +7: iteration 3520/ 11269 | consumed samples: 901120 | consumed tokens: 1845493760 | elapsed time per iteration (s): 0.48 | learning rate: 1.617E-04 | global batch size: 256 | lm loss: 3.251577E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.663 | TFLOPs: 34.57 | +7: iteration 3530/ 11269 | consumed samples: 903680 | consumed tokens: 1850736640 | elapsed time per iteration (s): 0.49 | learning rate: 1.614E-04 | global batch size: 256 | lm loss: 3.243116E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.106 | TFLOPs: 34.01 | +7: iteration 3540/ 11269 | consumed samples: 906240 | consumed tokens: 1855979520 | elapsed time per iteration (s): 0.49 | learning rate: 1.612E-04 | global batch size: 256 | lm loss: 3.255746E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.998 | TFLOPs: 34.27 | +7: iteration 3550/ 11269 | consumed samples: 908800 | consumed tokens: 1861222400 | elapsed time per iteration (s): 0.50 | learning rate: 1.610E-04 | global batch size: 256 | lm loss: 3.266895E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 516.238 | TFLOPs: 33.76 | +7: iteration 3560/ 11269 | consumed samples: 911360 | consumed tokens: 1866465280 | elapsed time per iteration (s): 0.49 | learning rate: 1.608E-04 | global batch size: 256 | lm loss: 3.225822E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.621 | TFLOPs: 34.38 | +7: iteration 3570/ 11269 | consumed samples: 913920 | consumed tokens: 1871708160 | elapsed time per iteration (s): 0.48 | learning rate: 1.606E-04 | global batch size: 256 | lm loss: 3.266941E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.096 | TFLOPs: 34.60 | +7: iteration 3580/ 11269 | consumed samples: 916480 | consumed tokens: 1876951040 | elapsed time per iteration (s): 0.50 | learning rate: 1.604E-04 | global batch size: 256 | lm loss: 3.240483E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 516.901 | TFLOPs: 33.81 | +7: iteration 3590/ 11269 | consumed samples: 919040 | consumed tokens: 1882193920 | elapsed time per iteration (s): 0.49 | learning rate: 1.602E-04 | global batch size: 256 | lm loss: 3.237268E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 519.117 | TFLOPs: 33.95 | +7: iteration 3600/ 11269 | consumed samples: 921600 | consumed tokens: 1887436800 | elapsed time per iteration (s): 0.50 | learning rate: 1.600E-04 | global batch size: 256 | lm loss: 3.251830E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 516.741 | TFLOPs: 33.79 | +7: iteration 3610/ 11269 | consumed samples: 924160 | consumed tokens: 1892679680 | elapsed time per iteration (s): 0.49 | learning rate: 1.598E-04 | global batch size: 256 | lm loss: 3.232803E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 519.192 | TFLOPs: 33.95 | +7: iteration 3620/ 11269 | consumed samples: 926720 | consumed tokens: 1897922560 | elapsed time per iteration (s): 0.49 | learning rate: 1.596E-04 | global batch size: 256 | lm loss: 3.240752E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.276 | TFLOPs: 33.90 | +7: iteration 3630/ 11269 | consumed samples: 929280 | consumed tokens: 1903165440 | elapsed time per iteration (s): 0.49 | learning rate: 1.593E-04 | global batch size: 256 | lm loss: 3.257949E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.653 | TFLOPs: 34.25 | +7: iteration 3640/ 11269 | consumed samples: 931840 | consumed tokens: 1908408320 | elapsed time per iteration (s): 0.48 | learning rate: 1.591E-04 | global batch size: 256 | lm loss: 3.222973E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.677 | TFLOPs: 34.84 | +7: iteration 3650/ 11269 | consumed samples: 934400 | consumed tokens: 1913651200 | elapsed time per iteration (s): 0.48 | learning rate: 1.589E-04 | global batch size: 256 | lm loss: 3.224478E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.675 | TFLOPs: 35.03 | +7: iteration 3660/ 11269 | consumed samples: 936960 | consumed tokens: 1918894080 | elapsed time per iteration (s): 0.50 | learning rate: 1.587E-04 | global batch size: 256 | lm loss: 3.245363E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 512.791 | TFLOPs: 33.54 | +7: iteration 3670/ 11269 | consumed samples: 939520 | consumed tokens: 1924136960 | elapsed time per iteration (s): 0.49 | learning rate: 1.585E-04 | global batch size: 256 | lm loss: 3.251417E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.165 | TFLOPs: 34.41 | +7: iteration 3680/ 11269 | consumed samples: 942080 | consumed tokens: 1929379840 | elapsed time per iteration (s): 0.49 | learning rate: 1.583E-04 | global batch size: 256 | lm loss: 3.213481E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.355 | TFLOPs: 34.10 | +7: iteration 3690/ 11269 | consumed samples: 944640 | consumed tokens: 1934622720 | elapsed time per iteration (s): 0.55 | learning rate: 1.581E-04 | global batch size: 256 | lm loss: 3.227158E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 464.769 | TFLOPs: 30.40 | +7: iteration 3700/ 11269 | consumed samples: 947200 | consumed tokens: 1939865600 | elapsed time per iteration (s): 0.50 | learning rate: 1.579E-04 | global batch size: 256 | lm loss: 3.240149E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 514.689 | TFLOPs: 33.66 | +7: iteration 3710/ 11269 | consumed samples: 949760 | consumed tokens: 1945108480 | elapsed time per iteration (s): 0.48 | learning rate: 1.576E-04 | global batch size: 256 | lm loss: 3.254907E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 538.084 | TFLOPs: 35.19 | +7: iteration 3720/ 11269 | consumed samples: 952320 | consumed tokens: 1950351360 | elapsed time per iteration (s): 0.49 | learning rate: 1.574E-04 | global batch size: 256 | lm loss: 3.245842E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.999 | TFLOPs: 34.14 | +7: iteration 3730/ 11269 | consumed samples: 954880 | consumed tokens: 1955594240 | elapsed time per iteration (s): 0.49 | learning rate: 1.572E-04 | global batch size: 256 | lm loss: 3.243960E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.103 | TFLOPs: 34.47 | +7: iteration 3740/ 11269 | consumed samples: 957440 | consumed tokens: 1960837120 | elapsed time per iteration (s): 0.49 | learning rate: 1.570E-04 | global batch size: 256 | lm loss: 3.207339E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.027 | TFLOPs: 34.47 | +7: iteration 3750/ 11269 | consumed samples: 960000 | consumed tokens: 1966080000 | elapsed time per iteration (s): 0.48 | learning rate: 1.568E-04 | global batch size: 256 | lm loss: 3.212664E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.885 | TFLOPs: 34.79 | +7: iteration 3760/ 11269 | consumed samples: 962560 | consumed tokens: 1971322880 | elapsed time per iteration (s): 0.49 | learning rate: 1.566E-04 | global batch size: 256 | lm loss: 3.214348E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.737 | TFLOPs: 34.32 | +7: iteration 3770/ 11269 | consumed samples: 965120 | consumed tokens: 1976565760 | elapsed time per iteration (s): 0.48 | learning rate: 1.563E-04 | global batch size: 256 | lm loss: 3.237714E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.916 | TFLOPs: 34.59 | +7: iteration 3780/ 11269 | consumed samples: 967680 | consumed tokens: 1981808640 | elapsed time per iteration (s): 0.48 | learning rate: 1.561E-04 | global batch size: 256 | lm loss: 3.231464E+00 | grad norm: 0.388 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 538.369 | TFLOPs: 35.21 | +7: iteration 3790/ 11269 | consumed samples: 970240 | consumed tokens: 1987051520 | elapsed time per iteration (s): 0.48 | learning rate: 1.559E-04 | global batch size: 256 | lm loss: 3.219939E+00 | grad norm: 0.424 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.728 | TFLOPs: 34.64 | +7: iteration 3800/ 11269 | consumed samples: 972800 | consumed tokens: 1992294400 | elapsed time per iteration (s): 0.49 | learning rate: 1.557E-04 | global batch size: 256 | lm loss: 3.254816E+00 | grad norm: 0.647 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.708 | TFLOPs: 34.32 | +7: iteration 3810/ 11269 | consumed samples: 975360 | consumed tokens: 1997537280 | elapsed time per iteration (s): 0.50 | learning rate: 1.555E-04 | global batch size: 256 | lm loss: 3.240480E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 511.544 | TFLOPs: 33.45 | +7: iteration 3820/ 11269 | consumed samples: 977920 | consumed tokens: 2002780160 | elapsed time per iteration (s): 0.48 | learning rate: 1.553E-04 | global batch size: 256 | lm loss: 3.232115E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.032 | TFLOPs: 34.53 | +7: iteration 3830/ 11269 | consumed samples: 980480 | consumed tokens: 2008023040 | elapsed time per iteration (s): 0.49 | learning rate: 1.550E-04 | global batch size: 256 | lm loss: 3.229807E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.105 | TFLOPs: 34.41 | +7: iteration 3840/ 11269 | consumed samples: 983040 | consumed tokens: 2013265920 | elapsed time per iteration (s): 0.48 | learning rate: 1.548E-04 | global batch size: 256 | lm loss: 3.229958E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.424 | TFLOPs: 35.02 | +7: iteration 3850/ 11269 | consumed samples: 985600 | consumed tokens: 2018508800 | elapsed time per iteration (s): 0.48 | learning rate: 1.546E-04 | global batch size: 256 | lm loss: 3.253176E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.057 | TFLOPs: 34.93 | +7: iteration 3860/ 11269 | consumed samples: 988160 | consumed tokens: 2023751680 | elapsed time per iteration (s): 0.49 | learning rate: 1.544E-04 | global batch size: 256 | lm loss: 3.211185E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.983 | TFLOPs: 34.14 | +7: iteration 3870/ 11269 | consumed samples: 990720 | consumed tokens: 2028994560 | elapsed time per iteration (s): 0.47 | learning rate: 1.542E-04 | global batch size: 256 | lm loss: 3.215765E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 541.006 | TFLOPs: 35.38 | +7: iteration 3880/ 11269 | consumed samples: 993280 | consumed tokens: 2034237440 | elapsed time per iteration (s): 0.48 | learning rate: 1.539E-04 | global batch size: 256 | lm loss: 3.202934E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.545 | TFLOPs: 35.09 | +7: iteration 3890/ 11269 | consumed samples: 995840 | consumed tokens: 2039480320 | elapsed time per iteration (s): 0.51 | learning rate: 1.537E-04 | global batch size: 256 | lm loss: 3.204744E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 502.505 | TFLOPs: 32.86 | +7: iteration 3900/ 11269 | consumed samples: 998400 | consumed tokens: 2044723200 | elapsed time per iteration (s): 0.48 | learning rate: 1.535E-04 | global batch size: 256 | lm loss: 3.202953E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.557 | TFLOPs: 35.16 | +7: iteration 3910/ 11269 | consumed samples: 1000960 | consumed tokens: 2049966080 | elapsed time per iteration (s): 0.48 | learning rate: 1.533E-04 | global batch size: 256 | lm loss: 3.191960E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 538.330 | TFLOPs: 35.21 | +7: iteration 3920/ 11269 | consumed samples: 1003520 | consumed tokens: 2055208960 | elapsed time per iteration (s): 0.48 | learning rate: 1.530E-04 | global batch size: 256 | lm loss: 3.196174E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.222 | TFLOPs: 34.55 | +7: iteration 3930/ 11269 | consumed samples: 1006080 | consumed tokens: 2060451840 | elapsed time per iteration (s): 0.49 | learning rate: 1.528E-04 | global batch size: 256 | lm loss: 3.202548E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.217 | TFLOPs: 34.41 | +7: iteration 3940/ 11269 | consumed samples: 1008640 | consumed tokens: 2065694720 | elapsed time per iteration (s): 0.48 | learning rate: 1.526E-04 | global batch size: 256 | lm loss: 3.204599E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.286 | TFLOPs: 34.62 | +7: iteration 3950/ 11269 | consumed samples: 1011200 | consumed tokens: 2070937600 | elapsed time per iteration (s): 0.49 | learning rate: 1.524E-04 | global batch size: 256 | lm loss: 3.213648E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.211 | TFLOPs: 34.41 | +7: iteration 3960/ 11269 | consumed samples: 1013760 | consumed tokens: 2076180480 | elapsed time per iteration (s): 0.48 | learning rate: 1.522E-04 | global batch size: 256 | lm loss: 3.183068E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.235 | TFLOPs: 34.68 | +7: iteration 3970/ 11269 | consumed samples: 1016320 | consumed tokens: 2081423360 | elapsed time per iteration (s): 0.49 | learning rate: 1.519E-04 | global batch size: 256 | lm loss: 3.213995E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.380 | TFLOPs: 34.03 | +7: iteration 3980/ 11269 | consumed samples: 1018880 | consumed tokens: 2086666240 | elapsed time per iteration (s): 0.48 | learning rate: 1.517E-04 | global batch size: 256 | lm loss: 3.200967E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.116 | TFLOPs: 35.06 | +7: iteration 3990/ 11269 | consumed samples: 1021440 | consumed tokens: 2091909120 | elapsed time per iteration (s): 0.49 | learning rate: 1.515E-04 | global batch size: 256 | lm loss: 3.205708E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.013 | TFLOPs: 34.20 | +0: [2022-11-29 17:25:27,307] [INFO] [logging.py:68:log_dist] [Rank 0] step=4000, skipped=0, lr=[0.00015125198701273666, 0.00015125198701273666, 0.00015125198701273666], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 4000/ 11269 | consumed samples: 1024000 | consumed tokens: 2097152000 | elapsed time per iteration (s): 0.51 | learning rate: 1.513E-04 | global batch size: 256 | lm loss: 3.197967E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 500.832 | TFLOPs: 32.75 | +0: steps: 4000 loss: 3.1917 iter time (s): 0.486 samples/sec: 526.944 +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 4000 | lm loss value: 3.067122E+00 | lm loss PPL: 2.148000E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 4000 to checkpoints_280moscar +0: [2022-11-29 17:25:27,497] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step4000 is begin to save! +0: [2022-11-29 17:25:27,503] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:25:27,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:25:27,618] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:25:27,642] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:25:27,643] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:25:27,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:25:27,667] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:25:27,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:25:27,691] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:25:27,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:25:27,716] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:25:27,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:25:27,741] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:25:27,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:25:27,766] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:25:27,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:25:27,790] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:25:27,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:25:27,815] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:25:27,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:25:27,839] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:25:27,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:25:27,864] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:25:27,889] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:25:27,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:25:27,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:25:27,916] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:25:27,941] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:25:27,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:25:27,965] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:25:27,965] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:25:27,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:25:27,990] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/layer_18-model_00-model_states.pt... +0: [2022-11-29 17:25:28,014] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/layer_18-model_00-model_states.pt. +0: [2022-11-29 17:25:28,015] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:25:28,039] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:25:28,039] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/layer_20-model_00-model_states.pt... +0: [2022-11-29 17:25:28,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/layer_20-model_00-model_states.pt. +0: [2022-11-29 17:25:28,063] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/layer_22-model_00-model_states.pt... +0: [2022-11-29 17:25:28,064] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/layer_22-model_00-model_states.pt. +0: [2022-11-29 17:25:28,065] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_280moscar/global_step4000/mp_rank_00_model_states.pt +0: [2022-11-29 17:25:28,065] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:25:28,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:25:28,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:25:28,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:25:28,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:25:28,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:25:28,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:25:28,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:25:28,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:25:28,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:25:28,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:25:28,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:25:28,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:25:28,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:25:28,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:25:28,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:25:28,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:25:28,150] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:25:28,150] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:25:28,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:25:28,150] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +5: [2022-11-29 17:25:28,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:25:28,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:25:28,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:25:28,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:25:28,150] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:25:28,150] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:25:28,150] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:25:28,150] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +4: [2022-11-29 17:25:28,150] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:25:28,150] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:25:28,150] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:25:28,150] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:25:28,150] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:25:28,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:25:28,151] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:25:28,151] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:25:28,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:25:28,152] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:25:28,152] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:25:28,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:25:28,152] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:25:28,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:25:28,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:25:28,152] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +2: [2022-11-29 17:25:28,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:25:28,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:25:28,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:25:28,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:25:28,152] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:25:28,150] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:25:28,150] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:25:28,152] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:25:28,152] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:25:28,152] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:25:28,152] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:25:28,152] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:25:28,152] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:25:28,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:25:28,154] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +4: [2022-11-29 17:25:28,155] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:25:28,155] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:25:28,155] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:25:28,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:25:28,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:25:28,156] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:25:28,156] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:25:28,156] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:25:28,156] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:25:28,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:25:28,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:25:28,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:25:28,157] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:25:28,157] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:25:28,157] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:25:28,157] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:25:28,157] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:25:28,157] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:25:28,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:25:28,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:25:28,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:25:28,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:25:28,157] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:25:28,157] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:25:28,157] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:25:28,157] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:25:28,157] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:25:28,157] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:25:28,157] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:25:28,157] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:25:28,158] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:25:28,158] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:25:28,158] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:25:28,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:25:28,160] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:25:28,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:25:28,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:25:28,160] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:25:28,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:25:28,145] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:25:28,145] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:25:28,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:25:28,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:25:28,152] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:25:28,152] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:25:28,152] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:25:28,152] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:25:28,152] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:25:28,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:25:28,162] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:25:28,162] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:25:28,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:25:28,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:25:28,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:25:28,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:25:28,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:25:28,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:25:28,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:25:28,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:25:28,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:25:28,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:25:28,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:25:28,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:25:28,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:25:28,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:25:28,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:25:28,174] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:25:28,174] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:25:28,174] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:25:28,174] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:25:28,174] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +3: [2022-11-29 17:25:28,152] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:25:28,152] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:25:28,174] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:25:28,153] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:25:28,153] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:25:28,153] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:25:28,153] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:25:28,153] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:25:28,153] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:25:28,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:25:28,157] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:25:28,157] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:25:28,158] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:25:28,158] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:25:28,158] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:25:28,183] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:25:28,183] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:25:28,183] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:25:28,183] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:25:28,183] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:25:28,183] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:25:28,183] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:25:28,183] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:25:28,183] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:25:28,183] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:25:28,183] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:25:28,183] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:25:28,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:25:28,184] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:25:28,184] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:25:28,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:25:28,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:25:28,184] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:25:28,184] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:25:28,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:25:28,184] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:25:28,184] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:25:28,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:25:28,185] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:25:28,185] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:25:28,154] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:25:28,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:25:28,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:25:28,154] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:25:28,154] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:25:28,154] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:25:28,154] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:25:28,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:25:28,156] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:25:28,156] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:25:28,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:25:28,173] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:25:28,173] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:25:28,236] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:25:28,237] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:25:28,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:25:28,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:25:28,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:25:28,240] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:25:28,240] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:25:28,240] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:25:28,240] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:25:28,240] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:25:28,240] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: successfully saved checkpoint at iteration 4000 to checkpoints_280moscar +7: time (ms) | save-checkpoint: 752.49 +7: iteration 4010/ 11269 | consumed samples: 1026560 | consumed tokens: 2102394880 | elapsed time per iteration (s): 0.59 | learning rate: 1.510E-04 | global batch size: 256 | lm loss: 3.204708E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.229 | TFLOPs: 28.59 | +7: iteration 4020/ 11269 | consumed samples: 1029120 | consumed tokens: 2107637760 | elapsed time per iteration (s): 0.49 | learning rate: 1.508E-04 | global batch size: 256 | lm loss: 3.217372E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.810 | TFLOPs: 34.13 | +7: iteration 4030/ 11269 | consumed samples: 1031680 | consumed tokens: 2112880640 | elapsed time per iteration (s): 0.48 | learning rate: 1.506E-04 | global batch size: 256 | lm loss: 3.208146E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.212 | TFLOPs: 34.94 | +7: iteration 4040/ 11269 | consumed samples: 1034240 | consumed tokens: 2118123520 | elapsed time per iteration (s): 0.49 | learning rate: 1.503E-04 | global batch size: 256 | lm loss: 3.213557E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.216 | TFLOPs: 34.09 | +7: iteration 4050/ 11269 | consumed samples: 1036800 | consumed tokens: 2123366400 | elapsed time per iteration (s): 0.48 | learning rate: 1.501E-04 | global batch size: 256 | lm loss: 3.201057E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.262 | TFLOPs: 34.55 | +7: iteration 4060/ 11269 | consumed samples: 1039360 | consumed tokens: 2128609280 | elapsed time per iteration (s): 0.48 | learning rate: 1.499E-04 | global batch size: 256 | lm loss: 3.206929E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.482 | TFLOPs: 34.56 | +7: iteration 4070/ 11269 | consumed samples: 1041920 | consumed tokens: 2133852160 | elapsed time per iteration (s): 0.49 | learning rate: 1.497E-04 | global batch size: 256 | lm loss: 3.178758E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.106 | TFLOPs: 34.34 | +7: iteration 4080/ 11269 | consumed samples: 1044480 | consumed tokens: 2139095040 | elapsed time per iteration (s): 0.48 | learning rate: 1.494E-04 | global batch size: 256 | lm loss: 3.205444E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.268 | TFLOPs: 35.01 | +7: iteration 4090/ 11269 | consumed samples: 1047040 | consumed tokens: 2144337920 | elapsed time per iteration (s): 0.48 | learning rate: 1.492E-04 | global batch size: 256 | lm loss: 3.223802E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.309 | TFLOPs: 34.55 | +7: iteration 4100/ 11269 | consumed samples: 1049600 | consumed tokens: 2149580800 | elapsed time per iteration (s): 0.48 | learning rate: 1.490E-04 | global batch size: 256 | lm loss: 3.197293E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.089 | TFLOPs: 34.54 | +7: iteration 4110/ 11269 | consumed samples: 1052160 | consumed tokens: 2154823680 | elapsed time per iteration (s): 0.48 | learning rate: 1.488E-04 | global batch size: 256 | lm loss: 3.188232E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.663 | TFLOPs: 34.64 | +7: iteration 4120/ 11269 | consumed samples: 1054720 | consumed tokens: 2160066560 | elapsed time per iteration (s): 0.49 | learning rate: 1.485E-04 | global batch size: 256 | lm loss: 3.173922E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.680 | TFLOPs: 34.05 | +7: iteration 4130/ 11269 | consumed samples: 1057280 | consumed tokens: 2165309440 | elapsed time per iteration (s): 0.50 | learning rate: 1.483E-04 | global batch size: 256 | lm loss: 3.205990E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 511.580 | TFLOPs: 33.46 | +7: iteration 4140/ 11269 | consumed samples: 1059840 | consumed tokens: 2170552320 | elapsed time per iteration (s): 0.49 | learning rate: 1.481E-04 | global batch size: 256 | lm loss: 3.181448E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.584 | TFLOPs: 34.18 | +7: iteration 4150/ 11269 | consumed samples: 1062400 | consumed tokens: 2175795200 | elapsed time per iteration (s): 0.48 | learning rate: 1.478E-04 | global batch size: 256 | lm loss: 3.193245E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.522 | TFLOPs: 34.63 | +7: iteration 4160/ 11269 | consumed samples: 1064960 | consumed tokens: 2181038080 | elapsed time per iteration (s): 0.51 | learning rate: 1.476E-04 | global batch size: 256 | lm loss: 3.193359E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 505.288 | TFLOPs: 33.05 | +7: iteration 4170/ 11269 | consumed samples: 1067520 | consumed tokens: 2186280960 | elapsed time per iteration (s): 0.48 | learning rate: 1.474E-04 | global batch size: 256 | lm loss: 3.175042E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.223 | TFLOPs: 34.61 | +7: iteration 4180/ 11269 | consumed samples: 1070080 | consumed tokens: 2191523840 | elapsed time per iteration (s): 0.48 | learning rate: 1.471E-04 | global batch size: 256 | lm loss: 3.160396E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.897 | TFLOPs: 34.85 | +7: iteration 4190/ 11269 | consumed samples: 1072640 | consumed tokens: 2196766720 | elapsed time per iteration (s): 0.47 | learning rate: 1.469E-04 | global batch size: 256 | lm loss: 3.181924E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 541.209 | TFLOPs: 35.39 | +7: iteration 4200/ 11269 | consumed samples: 1075200 | consumed tokens: 2202009600 | elapsed time per iteration (s): 0.49 | learning rate: 1.467E-04 | global batch size: 256 | lm loss: 3.182685E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.436 | TFLOPs: 34.49 | +7: iteration 4210/ 11269 | consumed samples: 1077760 | consumed tokens: 2207252480 | elapsed time per iteration (s): 0.49 | learning rate: 1.465E-04 | global batch size: 256 | lm loss: 3.201620E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.453 | TFLOPs: 34.04 | +7: iteration 4220/ 11269 | consumed samples: 1080320 | consumed tokens: 2212495360 | elapsed time per iteration (s): 0.48 | learning rate: 1.462E-04 | global batch size: 256 | lm loss: 3.205148E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.883 | TFLOPs: 34.72 | +7: iteration 4230/ 11269 | consumed samples: 1082880 | consumed tokens: 2217738240 | elapsed time per iteration (s): 0.49 | learning rate: 1.460E-04 | global batch size: 256 | lm loss: 3.181755E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.913 | TFLOPs: 34.33 | +7: iteration 4240/ 11269 | consumed samples: 1085440 | consumed tokens: 2222981120 | elapsed time per iteration (s): 0.48 | learning rate: 1.458E-04 | global batch size: 256 | lm loss: 3.219645E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.642 | TFLOPs: 34.90 | +7: iteration 4250/ 11269 | consumed samples: 1088000 | consumed tokens: 2228224000 | elapsed time per iteration (s): 0.48 | learning rate: 1.455E-04 | global batch size: 256 | lm loss: 3.143963E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.467 | TFLOPs: 34.56 | +7: iteration 4260/ 11269 | consumed samples: 1090560 | consumed tokens: 2233466880 | elapsed time per iteration (s): 0.48 | learning rate: 1.453E-04 | global batch size: 256 | lm loss: 3.220148E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.135 | TFLOPs: 35.00 | +7: iteration 4270/ 11269 | consumed samples: 1093120 | consumed tokens: 2238709760 | elapsed time per iteration (s): 0.48 | learning rate: 1.451E-04 | global batch size: 256 | lm loss: 3.190829E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.336 | TFLOPs: 34.75 | +7: iteration 4280/ 11269 | consumed samples: 1095680 | consumed tokens: 2243952640 | elapsed time per iteration (s): 0.48 | learning rate: 1.448E-04 | global batch size: 256 | lm loss: 3.194734E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.595 | TFLOPs: 34.64 | +7: iteration 4290/ 11269 | consumed samples: 1098240 | consumed tokens: 2249195520 | elapsed time per iteration (s): 0.50 | learning rate: 1.446E-04 | global batch size: 256 | lm loss: 3.190852E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 513.241 | TFLOPs: 33.57 | +7: iteration 4300/ 11269 | consumed samples: 1100800 | consumed tokens: 2254438400 | elapsed time per iteration (s): 0.49 | learning rate: 1.444E-04 | global batch size: 256 | lm loss: 3.137502E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.246 | TFLOPs: 34.42 | +7: iteration 4310/ 11269 | consumed samples: 1103360 | consumed tokens: 2259681280 | elapsed time per iteration (s): 0.52 | learning rate: 1.441E-04 | global batch size: 256 | lm loss: 3.171609E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 492.319 | TFLOPs: 32.20 | +7: iteration 4320/ 11269 | consumed samples: 1105920 | consumed tokens: 2264924160 | elapsed time per iteration (s): 0.49 | learning rate: 1.439E-04 | global batch size: 256 | lm loss: 3.159054E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.138 | TFLOPs: 34.21 | +7: iteration 4330/ 11269 | consumed samples: 1108480 | consumed tokens: 2270167040 | elapsed time per iteration (s): 0.49 | learning rate: 1.437E-04 | global batch size: 256 | lm loss: 3.167524E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.796 | TFLOPs: 34.13 | +7: iteration 4340/ 11269 | consumed samples: 1111040 | consumed tokens: 2275409920 | elapsed time per iteration (s): 0.48 | learning rate: 1.434E-04 | global batch size: 256 | lm loss: 3.207053E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.751 | TFLOPs: 34.65 | +7: iteration 4350/ 11269 | consumed samples: 1113600 | consumed tokens: 2280652800 | elapsed time per iteration (s): 0.49 | learning rate: 1.432E-04 | global batch size: 256 | lm loss: 3.151580E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.081 | TFLOPs: 34.21 | +7: iteration 4360/ 11269 | consumed samples: 1116160 | consumed tokens: 2285895680 | elapsed time per iteration (s): 0.48 | learning rate: 1.429E-04 | global batch size: 256 | lm loss: 3.145603E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.598 | TFLOPs: 34.57 | +7: iteration 4370/ 11269 | consumed samples: 1118720 | consumed tokens: 2291138560 | elapsed time per iteration (s): 0.49 | learning rate: 1.427E-04 | global batch size: 256 | lm loss: 3.173687E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.890 | TFLOPs: 34.26 | +7: iteration 4380/ 11269 | consumed samples: 1121280 | consumed tokens: 2296381440 | elapsed time per iteration (s): 0.49 | learning rate: 1.425E-04 | global batch size: 256 | lm loss: 3.177135E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.648 | TFLOPs: 33.85 | +7: iteration 4390/ 11269 | consumed samples: 1123840 | consumed tokens: 2301624320 | elapsed time per iteration (s): 0.48 | learning rate: 1.422E-04 | global batch size: 256 | lm loss: 3.164020E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.432 | TFLOPs: 35.08 | +7: iteration 4400/ 11269 | consumed samples: 1126400 | consumed tokens: 2306867200 | elapsed time per iteration (s): 0.48 | learning rate: 1.420E-04 | global batch size: 256 | lm loss: 3.162332E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.358 | TFLOPs: 34.62 | +7: iteration 4410/ 11269 | consumed samples: 1128960 | consumed tokens: 2312110080 | elapsed time per iteration (s): 0.49 | learning rate: 1.418E-04 | global batch size: 256 | lm loss: 3.167559E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.862 | TFLOPs: 34.20 | +7: iteration 4420/ 11269 | consumed samples: 1131520 | consumed tokens: 2317352960 | elapsed time per iteration (s): 0.49 | learning rate: 1.415E-04 | global batch size: 256 | lm loss: 3.163002E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.970 | TFLOPs: 33.88 | +7: iteration 4430/ 11269 | consumed samples: 1134080 | consumed tokens: 2322595840 | elapsed time per iteration (s): 0.48 | learning rate: 1.413E-04 | global batch size: 256 | lm loss: 3.167165E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.378 | TFLOPs: 34.75 | +7: iteration 4440/ 11269 | consumed samples: 1136640 | consumed tokens: 2327838720 | elapsed time per iteration (s): 0.51 | learning rate: 1.411E-04 | global batch size: 256 | lm loss: 3.149237E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 504.699 | TFLOPs: 33.01 | +7: iteration 4450/ 11269 | consumed samples: 1139200 | consumed tokens: 2333081600 | elapsed time per iteration (s): 0.48 | learning rate: 1.408E-04 | global batch size: 256 | lm loss: 3.161631E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.121 | TFLOPs: 34.80 | +7: iteration 4460/ 11269 | consumed samples: 1141760 | consumed tokens: 2338324480 | elapsed time per iteration (s): 0.47 | learning rate: 1.406E-04 | global batch size: 256 | lm loss: 3.164098E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 541.148 | TFLOPs: 35.39 | +7: iteration 4470/ 11269 | consumed samples: 1144320 | consumed tokens: 2343567360 | elapsed time per iteration (s): 0.49 | learning rate: 1.403E-04 | global batch size: 256 | lm loss: 3.140189E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.439 | TFLOPs: 34.04 | +7: iteration 4480/ 11269 | consumed samples: 1146880 | consumed tokens: 2348810240 | elapsed time per iteration (s): 0.48 | learning rate: 1.401E-04 | global batch size: 256 | lm loss: 3.165246E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.311 | TFLOPs: 35.01 | +7: iteration 4490/ 11269 | consumed samples: 1149440 | consumed tokens: 2354053120 | elapsed time per iteration (s): 0.49 | learning rate: 1.399E-04 | global batch size: 256 | lm loss: 3.167266E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.136 | TFLOPs: 34.15 | +7: iteration 4500/ 11269 | consumed samples: 1152000 | consumed tokens: 2359296000 | elapsed time per iteration (s): 0.49 | learning rate: 1.396E-04 | global batch size: 256 | lm loss: 3.154243E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.115 | TFLOPs: 34.08 | +7: iteration 4510/ 11269 | consumed samples: 1154560 | consumed tokens: 2364538880 | elapsed time per iteration (s): 0.50 | learning rate: 1.394E-04 | global batch size: 256 | lm loss: 3.181034E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 507.316 | TFLOPs: 33.18 | +7: iteration 4520/ 11269 | consumed samples: 1157120 | consumed tokens: 2369781760 | elapsed time per iteration (s): 0.50 | learning rate: 1.391E-04 | global batch size: 256 | lm loss: 3.148374E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 515.241 | TFLOPs: 33.70 | +7: iteration 4530/ 11269 | consumed samples: 1159680 | consumed tokens: 2375024640 | elapsed time per iteration (s): 0.48 | learning rate: 1.389E-04 | global batch size: 256 | lm loss: 3.153963E+00 | grad norm: 0.473 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.545 | TFLOPs: 34.57 | +7: iteration 4540/ 11269 | consumed samples: 1162240 | consumed tokens: 2380267520 | elapsed time per iteration (s): 0.48 | learning rate: 1.387E-04 | global batch size: 256 | lm loss: 3.159493E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.751 | TFLOPs: 34.58 | +7: iteration 4550/ 11269 | consumed samples: 1164800 | consumed tokens: 2385510400 | elapsed time per iteration (s): 0.49 | learning rate: 1.384E-04 | global batch size: 256 | lm loss: 3.157259E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 519.148 | TFLOPs: 33.95 | +7: iteration 4560/ 11269 | consumed samples: 1167360 | consumed tokens: 2390753280 | elapsed time per iteration (s): 0.49 | learning rate: 1.382E-04 | global batch size: 256 | lm loss: 3.144427E+00 | grad norm: 0.373 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.070 | TFLOPs: 34.14 | +7: iteration 4570/ 11269 | consumed samples: 1169920 | consumed tokens: 2395996160 | elapsed time per iteration (s): 0.48 | learning rate: 1.379E-04 | global batch size: 256 | lm loss: 3.157361E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.073 | TFLOPs: 34.60 | +7: iteration 4580/ 11269 | consumed samples: 1172480 | consumed tokens: 2401239040 | elapsed time per iteration (s): 0.49 | learning rate: 1.377E-04 | global batch size: 256 | lm loss: 3.144600E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.947 | TFLOPs: 34.33 | +7: iteration 4590/ 11269 | consumed samples: 1175040 | consumed tokens: 2406481920 | elapsed time per iteration (s): 0.49 | learning rate: 1.375E-04 | global batch size: 256 | lm loss: 3.144612E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.499 | TFLOPs: 34.11 | +7: iteration 4600/ 11269 | consumed samples: 1177600 | consumed tokens: 2411724800 | elapsed time per iteration (s): 0.49 | learning rate: 1.372E-04 | global batch size: 256 | lm loss: 3.154229E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.988 | TFLOPs: 34.40 | +7: iteration 4610/ 11269 | consumed samples: 1180160 | consumed tokens: 2416967680 | elapsed time per iteration (s): 0.50 | learning rate: 1.370E-04 | global batch size: 256 | lm loss: 3.149665E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 514.243 | TFLOPs: 33.63 | +7: iteration 4620/ 11269 | consumed samples: 1182720 | consumed tokens: 2422210560 | elapsed time per iteration (s): 0.49 | learning rate: 1.367E-04 | global batch size: 256 | lm loss: 3.136519E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 519.820 | TFLOPs: 34.00 | +7: iteration 4630/ 11269 | consumed samples: 1185280 | consumed tokens: 2427453440 | elapsed time per iteration (s): 0.48 | learning rate: 1.365E-04 | global batch size: 256 | lm loss: 3.159681E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.306 | TFLOPs: 34.68 | +7: iteration 4640/ 11269 | consumed samples: 1187840 | consumed tokens: 2432696320 | elapsed time per iteration (s): 0.50 | learning rate: 1.362E-04 | global batch size: 256 | lm loss: 3.163074E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 512.726 | TFLOPs: 33.53 | +7: iteration 4650/ 11269 | consumed samples: 1190400 | consumed tokens: 2437939200 | elapsed time per iteration (s): 0.49 | learning rate: 1.360E-04 | global batch size: 256 | lm loss: 3.139187E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.559 | TFLOPs: 34.44 | +7: iteration 4660/ 11269 | consumed samples: 1192960 | consumed tokens: 2443182080 | elapsed time per iteration (s): 0.49 | learning rate: 1.358E-04 | global batch size: 256 | lm loss: 3.141833E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.120 | TFLOPs: 34.34 | +7: iteration 4670/ 11269 | consumed samples: 1195520 | consumed tokens: 2448424960 | elapsed time per iteration (s): 0.50 | learning rate: 1.355E-04 | global batch size: 256 | lm loss: 3.142156E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.152 | TFLOPs: 33.82 | +7: iteration 4680/ 11269 | consumed samples: 1198080 | consumed tokens: 2453667840 | elapsed time per iteration (s): 0.49 | learning rate: 1.353E-04 | global batch size: 256 | lm loss: 3.150235E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.991 | TFLOPs: 34.07 | +7: iteration 4690/ 11269 | consumed samples: 1200640 | consumed tokens: 2458910720 | elapsed time per iteration (s): 0.50 | learning rate: 1.350E-04 | global batch size: 256 | lm loss: 3.160802E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 514.629 | TFLOPs: 33.66 | +7: iteration 4700/ 11269 | consumed samples: 1203200 | consumed tokens: 2464153600 | elapsed time per iteration (s): 0.50 | learning rate: 1.348E-04 | global batch size: 256 | lm loss: 3.141085E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 512.089 | TFLOPs: 33.49 | +7: iteration 4710/ 11269 | consumed samples: 1205760 | consumed tokens: 2469396480 | elapsed time per iteration (s): 0.48 | learning rate: 1.345E-04 | global batch size: 256 | lm loss: 3.151021E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.498 | TFLOPs: 34.76 | +7: iteration 4720/ 11269 | consumed samples: 1208320 | consumed tokens: 2474639360 | elapsed time per iteration (s): 0.48 | learning rate: 1.343E-04 | global batch size: 256 | lm loss: 3.148089E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.538 | TFLOPs: 34.96 | +7: iteration 4730/ 11269 | consumed samples: 1210880 | consumed tokens: 2479882240 | elapsed time per iteration (s): 0.48 | learning rate: 1.341E-04 | global batch size: 256 | lm loss: 3.169354E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.347 | TFLOPs: 34.95 | +7: iteration 4740/ 11269 | consumed samples: 1213440 | consumed tokens: 2485125120 | elapsed time per iteration (s): 0.50 | learning rate: 1.338E-04 | global batch size: 256 | lm loss: 3.143807E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 508.662 | TFLOPs: 33.27 | +7: iteration 4750/ 11269 | consumed samples: 1216000 | consumed tokens: 2490368000 | elapsed time per iteration (s): 0.48 | learning rate: 1.336E-04 | global batch size: 256 | lm loss: 3.138082E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.034 | TFLOPs: 35.06 | +7: iteration 4760/ 11269 | consumed samples: 1218560 | consumed tokens: 2495610880 | elapsed time per iteration (s): 0.52 | learning rate: 1.333E-04 | global batch size: 256 | lm loss: 3.139678E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 488.750 | TFLOPs: 31.96 | +7: iteration 4770/ 11269 | consumed samples: 1221120 | consumed tokens: 2500853760 | elapsed time per iteration (s): 0.49 | learning rate: 1.331E-04 | global batch size: 256 | lm loss: 3.133711E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.390 | TFLOPs: 34.03 | +7: iteration 4780/ 11269 | consumed samples: 1223680 | consumed tokens: 2506096640 | elapsed time per iteration (s): 0.49 | learning rate: 1.328E-04 | global batch size: 256 | lm loss: 3.147760E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.136 | TFLOPs: 34.08 | +7: iteration 4790/ 11269 | consumed samples: 1226240 | consumed tokens: 2511339520 | elapsed time per iteration (s): 0.49 | learning rate: 1.326E-04 | global batch size: 256 | lm loss: 3.148574E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.286 | TFLOPs: 34.22 | +7: iteration 4800/ 11269 | consumed samples: 1228800 | consumed tokens: 2516582400 | elapsed time per iteration (s): 0.48 | learning rate: 1.323E-04 | global batch size: 256 | lm loss: 3.103058E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.530 | TFLOPs: 34.76 | +7: iteration 4810/ 11269 | consumed samples: 1231360 | consumed tokens: 2521825280 | elapsed time per iteration (s): 0.48 | learning rate: 1.321E-04 | global batch size: 256 | lm loss: 3.130402E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.149 | TFLOPs: 34.93 | +7: iteration 4820/ 11269 | consumed samples: 1233920 | consumed tokens: 2527068160 | elapsed time per iteration (s): 0.48 | learning rate: 1.319E-04 | global batch size: 256 | lm loss: 3.157230E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.522 | TFLOPs: 34.83 | +7: iteration 4830/ 11269 | consumed samples: 1236480 | consumed tokens: 2532311040 | elapsed time per iteration (s): 0.49 | learning rate: 1.316E-04 | global batch size: 256 | lm loss: 3.116362E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.624 | TFLOPs: 34.24 | +7: iteration 4840/ 11269 | consumed samples: 1239040 | consumed tokens: 2537553920 | elapsed time per iteration (s): 0.48 | learning rate: 1.314E-04 | global batch size: 256 | lm loss: 3.147972E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.477 | TFLOPs: 34.76 | +7: iteration 4850/ 11269 | consumed samples: 1241600 | consumed tokens: 2542796800 | elapsed time per iteration (s): 0.48 | learning rate: 1.311E-04 | global batch size: 256 | lm loss: 3.141303E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.180 | TFLOPs: 34.80 | +7: iteration 4860/ 11269 | consumed samples: 1244160 | consumed tokens: 2548039680 | elapsed time per iteration (s): 0.49 | learning rate: 1.309E-04 | global batch size: 256 | lm loss: 3.116443E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 519.031 | TFLOPs: 33.94 | +7: iteration 4870/ 11269 | consumed samples: 1246720 | consumed tokens: 2553282560 | elapsed time per iteration (s): 0.48 | learning rate: 1.306E-04 | global batch size: 256 | lm loss: 3.121532E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.224 | TFLOPs: 35.07 | +7: iteration 4880/ 11269 | consumed samples: 1249280 | consumed tokens: 2558525440 | elapsed time per iteration (s): 0.49 | learning rate: 1.304E-04 | global batch size: 256 | lm loss: 3.133436E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.390 | TFLOPs: 34.23 | +7: iteration 4890/ 11269 | consumed samples: 1251840 | consumed tokens: 2563768320 | elapsed time per iteration (s): 0.49 | learning rate: 1.301E-04 | global batch size: 256 | lm loss: 3.129926E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 519.319 | TFLOPs: 33.96 | +7: iteration 4900/ 11269 | consumed samples: 1254400 | consumed tokens: 2569011200 | elapsed time per iteration (s): 0.48 | learning rate: 1.299E-04 | global batch size: 256 | lm loss: 3.122818E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.117 | TFLOPs: 34.54 | +7: iteration 4910/ 11269 | consumed samples: 1256960 | consumed tokens: 2574254080 | elapsed time per iteration (s): 0.47 | learning rate: 1.296E-04 | global batch size: 256 | lm loss: 3.122899E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 538.997 | TFLOPs: 35.25 | +7: iteration 4920/ 11269 | consumed samples: 1259520 | consumed tokens: 2579496960 | elapsed time per iteration (s): 0.49 | learning rate: 1.294E-04 | global batch size: 256 | lm loss: 3.145403E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.198 | TFLOPs: 34.35 | +7: iteration 4930/ 11269 | consumed samples: 1262080 | consumed tokens: 2584739840 | elapsed time per iteration (s): 0.50 | learning rate: 1.291E-04 | global batch size: 256 | lm loss: 3.105073E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 507.624 | TFLOPs: 33.20 | +7: iteration 4940/ 11269 | consumed samples: 1264640 | consumed tokens: 2589982720 | elapsed time per iteration (s): 0.49 | learning rate: 1.289E-04 | global batch size: 256 | lm loss: 3.152787E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.325 | TFLOPs: 33.83 | +7: iteration 4950/ 11269 | consumed samples: 1267200 | consumed tokens: 2595225600 | elapsed time per iteration (s): 0.49 | learning rate: 1.286E-04 | global batch size: 256 | lm loss: 3.117798E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.547 | TFLOPs: 34.24 | +7: iteration 4960/ 11269 | consumed samples: 1269760 | consumed tokens: 2600468480 | elapsed time per iteration (s): 0.48 | learning rate: 1.284E-04 | global batch size: 256 | lm loss: 3.152262E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.612 | TFLOPs: 35.16 | +7: iteration 4970/ 11269 | consumed samples: 1272320 | consumed tokens: 2605711360 | elapsed time per iteration (s): 0.49 | learning rate: 1.281E-04 | global batch size: 256 | lm loss: 3.141135E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.600 | TFLOPs: 34.24 | +7: iteration 4980/ 11269 | consumed samples: 1274880 | consumed tokens: 2610954240 | elapsed time per iteration (s): 0.47 | learning rate: 1.279E-04 | global batch size: 256 | lm loss: 3.112229E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 539.540 | TFLOPs: 35.29 | +7: iteration 4990/ 11269 | consumed samples: 1277440 | consumed tokens: 2616197120 | elapsed time per iteration (s): 0.48 | learning rate: 1.276E-04 | global batch size: 256 | lm loss: 3.129363E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.417 | TFLOPs: 34.69 | +7: iteration 5000/ 11269 | consumed samples: 1280000 | consumed tokens: 2621440000 | elapsed time per iteration (s): 0.49 | learning rate: 1.274E-04 | global batch size: 256 | lm loss: 3.121534E+00 | grad norm: 0.676 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.470 | TFLOPs: 33.91 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 5000 | lm loss value: 3.098590E+00 | lm loss PPL: 2.216667E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 5000 to checkpoints_280moscar +0: [2022-11-29 17:33:36,581] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step5000 is begin to save! +0: [2022-11-29 17:33:36,585] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:33:36,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:33:36,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:33:36,725] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:33:36,725] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:33:36,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:33:36,749] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:33:36,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:33:36,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:33:36,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:33:36,799] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:33:36,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:33:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:33:36,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:33:36,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:33:36,874] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:33:36,875] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:33:36,900] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:33:36,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:33:36,925] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:33:36,925] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:33:36,950] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:33:36,950] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:33:36,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:33:36,975] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:33:36,999] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:33:37,000] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:33:37,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:33:37,025] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:33:37,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:33:37,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:33:37,074] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:33:37,074] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/layer_18-model_00-model_states.pt... +0: [2022-11-29 17:33:37,099] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/layer_18-model_00-model_states.pt. +0: [2022-11-29 17:33:37,099] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:33:37,124] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:33:37,124] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/layer_20-model_00-model_states.pt... +0: [2022-11-29 17:33:37,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/layer_20-model_00-model_states.pt. +0: [2022-11-29 17:33:37,149] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/layer_22-model_00-model_states.pt... +0: [2022-11-29 17:33:37,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/layer_22-model_00-model_states.pt. +0: [2022-11-29 17:33:37,151] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_280moscar/global_step5000/mp_rank_00_model_states.pt +0: [2022-11-29 17:33:37,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:33:37,153] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:37,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:37,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:37,229] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:37,229] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:33:37,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:37,230] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:33:37,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:33:37,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:37,232] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:37,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:33:37,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:33:37,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:37,235] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:33:37,235] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:33:37,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:37,235] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:37,235] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:37,235] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:37,235] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:33:37,235] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:37,235] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:33:37,235] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:33:37,236] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:37,236] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:33:37,236] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:37,236] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:33:37,236] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:33:37,236] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:37,236] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:33:37,236] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:33:37,236] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:37,236] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:33:37,236] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:33:37,237] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:37,237] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:37,237] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:37,237] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:37,237] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:33:37,237] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:33:37,237] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:37,237] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:37,230] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:37,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:33:37,237] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:33:37,237] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:33:37,237] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:37,237] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:33:37,237] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:33:37,237] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:37,238] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:37,238] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +4: [2022-11-29 17:33:37,238] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:33:37,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:37,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:33:37,238] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:33:37,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:37,238] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:33:37,238] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:37,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:37,238] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:33:37,238] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +7: [2022-11-29 17:33:37,238] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:33:37,238] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:37,238] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:33:37,238] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:33:37,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:33:37,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:33:37,238] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:37,238] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:37,238] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:33:37,238] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:33:37,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:37,238] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:33:37,238] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:33:37,239] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:37,239] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:37,239] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:33:37,239] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:37,239] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:33:37,239] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:33:37,239] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:37,239] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:33:37,239] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:33:37,239] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:37,240] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +6: [2022-11-29 17:33:37,239] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:37,240] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:33:37,240] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:33:37,240] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:33:37,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:37,241] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:33:37,241] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:33:37,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:37,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:37,241] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:37,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:37,241] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:33:37,241] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:37,241] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:37,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:37,241] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:33:37,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:37,241] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:37,241] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:33:37,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:37,241] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:33:37,241] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:37,241] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:37,242] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:33:37,242] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:33:37,242] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:33:37,242] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:37,242] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:33:37,243] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:37,243] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:37,243] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:33:37,243] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:33:37,243] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:33:37,243] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:33:37,244] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:37,244] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:37,244] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:37,244] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:33:37,244] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:37,244] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:33:37,245] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:33:37,245] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:37,245] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:33:37,245] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:37,245] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:33:37,245] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:33:37,245] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:37,245] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:37,245] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:33:37,246] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:37,246] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:37,246] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:33:37,249] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:37,249] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:33:37,249] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:33:37,249] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:37,249] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:33:37,249] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:33:37,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:37,251] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:37,251] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:33:37,252] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:33:37,252] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:37,252] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:33:37,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:33:37,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:33:37,253] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:37,253] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:37,253] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:33:37,254] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:33:37,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:33:37,254] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:37,254] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:33:37,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:37,261] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:37,261] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:37,261] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:33:37,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:33:37,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:33:37,239] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:33:37,239] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:33:37,239] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:33:37,239] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:33:37,239] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:33:37,239] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:33:37,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:33:37,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:33:37,240] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:33:37,240] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:33:37,240] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:33:37,240] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:33:37,244] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:33:37,245] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:33:37,245] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:33:37,245] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:33:37,245] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:33:37,245] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:33:37,245] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:33:37,245] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:33:37,245] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:33:37,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:33:37,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:37,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:33:37,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:33:37,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:37,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:33:37,324] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:37,324] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: successfully saved checkpoint at iteration 5000 to checkpoints_280moscar +7: time (ms) | save-checkpoint: 752.86 +7: iteration 5010/ 11269 | consumed samples: 1282560 | consumed tokens: 2626682880 | elapsed time per iteration (s): 0.59 | learning rate: 1.272E-04 | global batch size: 256 | lm loss: 3.136636E+00 | grad norm: 0.377 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.276 | TFLOPs: 28.40 | +7: iteration 5020/ 11269 | consumed samples: 1285120 | consumed tokens: 2631925760 | elapsed time per iteration (s): 0.48 | learning rate: 1.269E-04 | global batch size: 256 | lm loss: 3.135511E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.678 | TFLOPs: 34.64 | +7: iteration 5030/ 11269 | consumed samples: 1287680 | consumed tokens: 2637168640 | elapsed time per iteration (s): 0.49 | learning rate: 1.267E-04 | global batch size: 256 | lm loss: 3.104427E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.234 | TFLOPs: 34.35 | +7: iteration 5040/ 11269 | consumed samples: 1290240 | consumed tokens: 2642411520 | elapsed time per iteration (s): 0.48 | learning rate: 1.264E-04 | global batch size: 256 | lm loss: 3.141943E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.995 | TFLOPs: 35.05 | +7: iteration 5050/ 11269 | consumed samples: 1292800 | consumed tokens: 2647654400 | elapsed time per iteration (s): 0.48 | learning rate: 1.262E-04 | global batch size: 256 | lm loss: 3.118844E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.254 | TFLOPs: 34.55 | +7: iteration 5060/ 11269 | consumed samples: 1295360 | consumed tokens: 2652897280 | elapsed time per iteration (s): 0.48 | learning rate: 1.259E-04 | global batch size: 256 | lm loss: 3.125171E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.271 | TFLOPs: 34.68 | +7: iteration 5070/ 11269 | consumed samples: 1297920 | consumed tokens: 2658140160 | elapsed time per iteration (s): 0.49 | learning rate: 1.257E-04 | global batch size: 256 | lm loss: 3.120889E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.336 | TFLOPs: 34.29 | +7: iteration 5080/ 11269 | consumed samples: 1300480 | consumed tokens: 2663383040 | elapsed time per iteration (s): 0.48 | learning rate: 1.254E-04 | global batch size: 256 | lm loss: 3.139838E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.913 | TFLOPs: 34.92 | +7: iteration 5090/ 11269 | consumed samples: 1303040 | consumed tokens: 2668625920 | elapsed time per iteration (s): 0.48 | learning rate: 1.252E-04 | global batch size: 256 | lm loss: 3.142016E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.585 | TFLOPs: 34.57 | +7: iteration 5100/ 11269 | consumed samples: 1305600 | consumed tokens: 2673868800 | elapsed time per iteration (s): 0.49 | learning rate: 1.249E-04 | global batch size: 256 | lm loss: 3.142689E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.900 | TFLOPs: 34.20 | +7: iteration 5110/ 11269 | consumed samples: 1308160 | consumed tokens: 2679111680 | elapsed time per iteration (s): 0.48 | learning rate: 1.247E-04 | global batch size: 256 | lm loss: 3.134387E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.099 | TFLOPs: 34.73 | +7: iteration 5120/ 11269 | consumed samples: 1310720 | consumed tokens: 2684354560 | elapsed time per iteration (s): 0.48 | learning rate: 1.244E-04 | global batch size: 256 | lm loss: 3.109246E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.582 | TFLOPs: 34.77 | +7: iteration 5130/ 11269 | consumed samples: 1313280 | consumed tokens: 2689597440 | elapsed time per iteration (s): 0.48 | learning rate: 1.242E-04 | global batch size: 256 | lm loss: 3.135127E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.623 | TFLOPs: 34.70 | +7: iteration 5140/ 11269 | consumed samples: 1315840 | consumed tokens: 2694840320 | elapsed time per iteration (s): 0.48 | learning rate: 1.239E-04 | global batch size: 256 | lm loss: 3.134586E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.721 | TFLOPs: 34.71 | +7: iteration 5150/ 11269 | consumed samples: 1318400 | consumed tokens: 2700083200 | elapsed time per iteration (s): 0.49 | learning rate: 1.237E-04 | global batch size: 256 | lm loss: 3.129356E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.515 | TFLOPs: 34.24 | +7: iteration 5160/ 11269 | consumed samples: 1320960 | consumed tokens: 2705326080 | elapsed time per iteration (s): 0.48 | learning rate: 1.234E-04 | global batch size: 256 | lm loss: 3.123814E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.924 | TFLOPs: 34.59 | +7: iteration 5170/ 11269 | consumed samples: 1323520 | consumed tokens: 2710568960 | elapsed time per iteration (s): 0.49 | learning rate: 1.232E-04 | global batch size: 256 | lm loss: 3.135324E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.800 | TFLOPs: 34.26 | +7: iteration 5180/ 11269 | consumed samples: 1326080 | consumed tokens: 2715811840 | elapsed time per iteration (s): 0.48 | learning rate: 1.229E-04 | global batch size: 256 | lm loss: 3.113697E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.548 | TFLOPs: 35.02 | +7: iteration 5190/ 11269 | consumed samples: 1328640 | consumed tokens: 2721054720 | elapsed time per iteration (s): 0.47 | learning rate: 1.227E-04 | global batch size: 256 | lm loss: 3.115358E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 538.977 | TFLOPs: 35.25 | +7: iteration 5200/ 11269 | consumed samples: 1331200 | consumed tokens: 2726297600 | elapsed time per iteration (s): 0.48 | learning rate: 1.224E-04 | global batch size: 256 | lm loss: 3.121964E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.276 | TFLOPs: 35.07 | +7: iteration 5210/ 11269 | consumed samples: 1333760 | consumed tokens: 2731540480 | elapsed time per iteration (s): 0.55 | learning rate: 1.221E-04 | global batch size: 256 | lm loss: 3.112877E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.390 | TFLOPs: 30.17 | +7: iteration 5220/ 11269 | consumed samples: 1336320 | consumed tokens: 2736783360 | elapsed time per iteration (s): 0.48 | learning rate: 1.219E-04 | global batch size: 256 | lm loss: 3.112120E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.821 | TFLOPs: 34.98 | +7: iteration 5230/ 11269 | consumed samples: 1338880 | consumed tokens: 2742026240 | elapsed time per iteration (s): 0.48 | learning rate: 1.216E-04 | global batch size: 256 | lm loss: 3.076105E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.719 | TFLOPs: 34.84 | +7: iteration 5240/ 11269 | consumed samples: 1341440 | consumed tokens: 2747269120 | elapsed time per iteration (s): 0.49 | learning rate: 1.214E-04 | global batch size: 256 | lm loss: 3.092333E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.962 | TFLOPs: 34.46 | +7: iteration 5250/ 11269 | consumed samples: 1344000 | consumed tokens: 2752512000 | elapsed time per iteration (s): 0.48 | learning rate: 1.211E-04 | global batch size: 256 | lm loss: 3.114621E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.642 | TFLOPs: 35.10 | +7: iteration 5260/ 11269 | consumed samples: 1346560 | consumed tokens: 2757754880 | elapsed time per iteration (s): 0.49 | learning rate: 1.209E-04 | global batch size: 256 | lm loss: 3.098986E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.483 | TFLOPs: 34.50 | +7: iteration 5270/ 11269 | consumed samples: 1349120 | consumed tokens: 2762997760 | elapsed time per iteration (s): 0.55 | learning rate: 1.206E-04 | global batch size: 256 | lm loss: 3.100653E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 466.738 | TFLOPs: 30.52 | +7: iteration 5280/ 11269 | consumed samples: 1351680 | consumed tokens: 2768240640 | elapsed time per iteration (s): 0.48 | learning rate: 1.204E-04 | global batch size: 256 | lm loss: 3.095035E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.202 | TFLOPs: 34.87 | +7: iteration 5290/ 11269 | consumed samples: 1354240 | consumed tokens: 2773483520 | elapsed time per iteration (s): 0.48 | learning rate: 1.201E-04 | global batch size: 256 | lm loss: 3.119621E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.006 | TFLOPs: 34.60 | +7: iteration 5300/ 11269 | consumed samples: 1356800 | consumed tokens: 2778726400 | elapsed time per iteration (s): 0.48 | learning rate: 1.199E-04 | global batch size: 256 | lm loss: 3.099569E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.228 | TFLOPs: 34.94 | +7: iteration 5310/ 11269 | consumed samples: 1359360 | consumed tokens: 2783969280 | elapsed time per iteration (s): 0.48 | learning rate: 1.196E-04 | global batch size: 256 | lm loss: 3.077674E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.935 | TFLOPs: 35.05 | +7: iteration 5320/ 11269 | consumed samples: 1361920 | consumed tokens: 2789212160 | elapsed time per iteration (s): 0.48 | learning rate: 1.194E-04 | global batch size: 256 | lm loss: 3.133804E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.662 | TFLOPs: 34.90 | +7: iteration 5330/ 11269 | consumed samples: 1364480 | consumed tokens: 2794455040 | elapsed time per iteration (s): 0.47 | learning rate: 1.191E-04 | global batch size: 256 | lm loss: 3.100406E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 539.366 | TFLOPs: 35.27 | +7: iteration 5340/ 11269 | consumed samples: 1367040 | consumed tokens: 2799697920 | elapsed time per iteration (s): 0.49 | learning rate: 1.189E-04 | global batch size: 256 | lm loss: 3.106160E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.898 | TFLOPs: 34.39 | +7: iteration 5350/ 11269 | consumed samples: 1369600 | consumed tokens: 2804940800 | elapsed time per iteration (s): 0.49 | learning rate: 1.186E-04 | global batch size: 256 | lm loss: 3.114830E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.766 | TFLOPs: 33.86 | +7: iteration 5360/ 11269 | consumed samples: 1372160 | consumed tokens: 2810183680 | elapsed time per iteration (s): 0.50 | learning rate: 1.184E-04 | global batch size: 256 | lm loss: 3.084948E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 510.677 | TFLOPs: 33.40 | +7: iteration 5370/ 11269 | consumed samples: 1374720 | consumed tokens: 2815426560 | elapsed time per iteration (s): 0.49 | learning rate: 1.181E-04 | global batch size: 256 | lm loss: 3.097579E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.310 | TFLOPs: 34.16 | +7: iteration 5380/ 11269 | consumed samples: 1377280 | consumed tokens: 2820669440 | elapsed time per iteration (s): 0.48 | learning rate: 1.179E-04 | global batch size: 256 | lm loss: 3.123086E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.607 | TFLOPs: 34.96 | +7: iteration 5390/ 11269 | consumed samples: 1379840 | consumed tokens: 2825912320 | elapsed time per iteration (s): 0.49 | learning rate: 1.176E-04 | global batch size: 256 | lm loss: 3.099529E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.399 | TFLOPs: 34.36 | +7: iteration 5400/ 11269 | consumed samples: 1382400 | consumed tokens: 2831155200 | elapsed time per iteration (s): 0.48 | learning rate: 1.174E-04 | global batch size: 256 | lm loss: 3.061372E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.867 | TFLOPs: 34.85 | +7: iteration 5410/ 11269 | consumed samples: 1384960 | consumed tokens: 2836398080 | elapsed time per iteration (s): 0.48 | learning rate: 1.171E-04 | global batch size: 256 | lm loss: 3.099939E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.194 | TFLOPs: 35.07 | +7: iteration 5420/ 11269 | consumed samples: 1387520 | consumed tokens: 2841640960 | elapsed time per iteration (s): 0.47 | learning rate: 1.169E-04 | global batch size: 256 | lm loss: 3.132364E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 540.853 | TFLOPs: 35.37 | +7: iteration 5430/ 11269 | consumed samples: 1390080 | consumed tokens: 2846883840 | elapsed time per iteration (s): 0.49 | learning rate: 1.166E-04 | global batch size: 256 | lm loss: 3.105640E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.519 | TFLOPs: 34.30 | +7: iteration 5440/ 11269 | consumed samples: 1392640 | consumed tokens: 2852126720 | elapsed time per iteration (s): 0.48 | learning rate: 1.164E-04 | global batch size: 256 | lm loss: 3.111472E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.844 | TFLOPs: 35.04 | +7: iteration 5450/ 11269 | consumed samples: 1395200 | consumed tokens: 2857369600 | elapsed time per iteration (s): 0.48 | learning rate: 1.161E-04 | global batch size: 256 | lm loss: 3.067811E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.487 | TFLOPs: 34.69 | +7: iteration 5460/ 11269 | consumed samples: 1397760 | consumed tokens: 2862612480 | elapsed time per iteration (s): 0.51 | learning rate: 1.158E-04 | global batch size: 256 | lm loss: 3.093767E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 498.474 | TFLOPs: 32.60 | +7: iteration 5470/ 11269 | consumed samples: 1400320 | consumed tokens: 2867855360 | elapsed time per iteration (s): 0.49 | learning rate: 1.156E-04 | global batch size: 256 | lm loss: 3.094585E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.104 | TFLOPs: 34.47 | +7: iteration 5480/ 11269 | consumed samples: 1402880 | consumed tokens: 2873098240 | elapsed time per iteration (s): 0.47 | learning rate: 1.153E-04 | global batch size: 256 | lm loss: 3.109892E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 539.049 | TFLOPs: 35.25 | +7: iteration 5490/ 11269 | consumed samples: 1405440 | consumed tokens: 2878341120 | elapsed time per iteration (s): 0.47 | learning rate: 1.151E-04 | global batch size: 256 | lm loss: 3.089760E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 540.500 | TFLOPs: 35.35 | +7: iteration 5500/ 11269 | consumed samples: 1408000 | consumed tokens: 2883584000 | elapsed time per iteration (s): 0.49 | learning rate: 1.148E-04 | global batch size: 256 | lm loss: 3.121438E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.708 | TFLOPs: 34.45 | +7: iteration 5510/ 11269 | consumed samples: 1410560 | consumed tokens: 2888826880 | elapsed time per iteration (s): 0.48 | learning rate: 1.146E-04 | global batch size: 256 | lm loss: 3.069639E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.114 | TFLOPs: 34.87 | +7: iteration 5520/ 11269 | consumed samples: 1413120 | consumed tokens: 2894069760 | elapsed time per iteration (s): 0.48 | learning rate: 1.143E-04 | global batch size: 256 | lm loss: 3.074761E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.812 | TFLOPs: 34.91 | +7: iteration 5530/ 11269 | consumed samples: 1415680 | consumed tokens: 2899312640 | elapsed time per iteration (s): 0.48 | learning rate: 1.141E-04 | global batch size: 256 | lm loss: 3.075307E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.671 | TFLOPs: 34.64 | +7: iteration 5540/ 11269 | consumed samples: 1418240 | consumed tokens: 2904555520 | elapsed time per iteration (s): 0.48 | learning rate: 1.138E-04 | global batch size: 256 | lm loss: 3.100433E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.088 | TFLOPs: 34.99 | +7: iteration 5550/ 11269 | consumed samples: 1420800 | consumed tokens: 2909798400 | elapsed time per iteration (s): 0.49 | learning rate: 1.136E-04 | global batch size: 256 | lm loss: 3.090164E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.089 | TFLOPs: 34.08 | +7: iteration 5560/ 11269 | consumed samples: 1423360 | consumed tokens: 2915041280 | elapsed time per iteration (s): 0.48 | learning rate: 1.133E-04 | global batch size: 256 | lm loss: 3.076575E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.285 | TFLOPs: 34.88 | +7: iteration 5570/ 11269 | consumed samples: 1425920 | consumed tokens: 2920284160 | elapsed time per iteration (s): 0.47 | learning rate: 1.131E-04 | global batch size: 256 | lm loss: 3.079079E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 540.002 | TFLOPs: 35.32 | +7: iteration 5580/ 11269 | consumed samples: 1428480 | consumed tokens: 2925527040 | elapsed time per iteration (s): 0.48 | learning rate: 1.128E-04 | global batch size: 256 | lm loss: 3.095694E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.663 | TFLOPs: 35.03 | +7: iteration 5590/ 11269 | consumed samples: 1431040 | consumed tokens: 2930769920 | elapsed time per iteration (s): 0.48 | learning rate: 1.126E-04 | global batch size: 256 | lm loss: 3.053952E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.846 | TFLOPs: 34.98 | +7: iteration 5600/ 11269 | consumed samples: 1433600 | consumed tokens: 2936012800 | elapsed time per iteration (s): 0.49 | learning rate: 1.123E-04 | global batch size: 256 | lm loss: 3.087182E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.865 | TFLOPs: 34.13 | +7: iteration 5610/ 11269 | consumed samples: 1436160 | consumed tokens: 2941255680 | elapsed time per iteration (s): 0.48 | learning rate: 1.120E-04 | global batch size: 256 | lm loss: 3.074302E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.712 | TFLOPs: 34.64 | +7: iteration 5620/ 11269 | consumed samples: 1438720 | consumed tokens: 2946498560 | elapsed time per iteration (s): 0.49 | learning rate: 1.118E-04 | global batch size: 256 | lm loss: 3.085210E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.724 | TFLOPs: 34.51 | +7: iteration 5630/ 11269 | consumed samples: 1441280 | consumed tokens: 2951741440 | elapsed time per iteration (s): 0.48 | learning rate: 1.115E-04 | global batch size: 256 | lm loss: 3.072972E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.886 | TFLOPs: 35.11 | +7: iteration 5640/ 11269 | consumed samples: 1443840 | consumed tokens: 2956984320 | elapsed time per iteration (s): 0.48 | learning rate: 1.113E-04 | global batch size: 256 | lm loss: 3.086461E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 538.552 | TFLOPs: 35.22 | +7: iteration 5650/ 11269 | consumed samples: 1446400 | consumed tokens: 2962227200 | elapsed time per iteration (s): 0.49 | learning rate: 1.110E-04 | global batch size: 256 | lm loss: 3.106919E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.960 | TFLOPs: 34.40 | +7: iteration 5660/ 11269 | consumed samples: 1448960 | consumed tokens: 2967470080 | elapsed time per iteration (s): 0.51 | learning rate: 1.108E-04 | global batch size: 256 | lm loss: 3.104283E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 501.397 | TFLOPs: 32.79 | +7: iteration 5670/ 11269 | consumed samples: 1451520 | consumed tokens: 2972712960 | elapsed time per iteration (s): 0.50 | learning rate: 1.105E-04 | global batch size: 256 | lm loss: 3.076432E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 516.883 | TFLOPs: 33.80 | +7: iteration 5680/ 11269 | consumed samples: 1454080 | consumed tokens: 2977955840 | elapsed time per iteration (s): 0.48 | learning rate: 1.103E-04 | global batch size: 256 | lm loss: 3.086386E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.138 | TFLOPs: 34.74 | +7: iteration 5690/ 11269 | consumed samples: 1456640 | consumed tokens: 2983198720 | elapsed time per iteration (s): 0.48 | learning rate: 1.100E-04 | global batch size: 256 | lm loss: 3.067182E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.347 | TFLOPs: 34.88 | +7: iteration 5700/ 11269 | consumed samples: 1459200 | consumed tokens: 2988441600 | elapsed time per iteration (s): 0.48 | learning rate: 1.098E-04 | global batch size: 256 | lm loss: 3.090037E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.169 | TFLOPs: 34.74 | +7: iteration 5710/ 11269 | consumed samples: 1461760 | consumed tokens: 2993684480 | elapsed time per iteration (s): 0.48 | learning rate: 1.095E-04 | global batch size: 256 | lm loss: 3.088234E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.200 | TFLOPs: 34.61 | +7: iteration 5720/ 11269 | consumed samples: 1464320 | consumed tokens: 2998927360 | elapsed time per iteration (s): 0.48 | learning rate: 1.093E-04 | global batch size: 256 | lm loss: 3.067057E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.780 | TFLOPs: 35.11 | +7: iteration 5730/ 11269 | consumed samples: 1466880 | consumed tokens: 3004170240 | elapsed time per iteration (s): 0.48 | learning rate: 1.090E-04 | global batch size: 256 | lm loss: 3.055091E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.789 | TFLOPs: 34.58 | +7: iteration 5740/ 11269 | consumed samples: 1469440 | consumed tokens: 3009413120 | elapsed time per iteration (s): 0.49 | learning rate: 1.088E-04 | global batch size: 256 | lm loss: 3.086383E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 519.642 | TFLOPs: 33.98 | +7: iteration 5750/ 11269 | consumed samples: 1472000 | consumed tokens: 3014656000 | elapsed time per iteration (s): 0.48 | learning rate: 1.085E-04 | global batch size: 256 | lm loss: 3.073791E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.423 | TFLOPs: 35.15 | +7: iteration 5760/ 11269 | consumed samples: 1474560 | consumed tokens: 3019898880 | elapsed time per iteration (s): 0.49 | learning rate: 1.082E-04 | global batch size: 256 | lm loss: 3.052653E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.895 | TFLOPs: 34.26 | +7: iteration 5770/ 11269 | consumed samples: 1477120 | consumed tokens: 3025141760 | elapsed time per iteration (s): 0.48 | learning rate: 1.080E-04 | global batch size: 256 | lm loss: 3.086959E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.731 | TFLOPs: 35.10 | +7: iteration 5780/ 11269 | consumed samples: 1479680 | consumed tokens: 3030384640 | elapsed time per iteration (s): 0.48 | learning rate: 1.077E-04 | global batch size: 256 | lm loss: 3.069123E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.415 | TFLOPs: 34.75 | +7: iteration 5790/ 11269 | consumed samples: 1482240 | consumed tokens: 3035627520 | elapsed time per iteration (s): 0.48 | learning rate: 1.075E-04 | global batch size: 256 | lm loss: 3.094396E+00 | grad norm: 0.424 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.363 | TFLOPs: 34.82 | +7: iteration 5800/ 11269 | consumed samples: 1484800 | consumed tokens: 3040870400 | elapsed time per iteration (s): 0.48 | learning rate: 1.072E-04 | global batch size: 256 | lm loss: 3.074201E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 538.533 | TFLOPs: 35.22 | +7: iteration 5810/ 11269 | consumed samples: 1487360 | consumed tokens: 3046113280 | elapsed time per iteration (s): 0.48 | learning rate: 1.070E-04 | global batch size: 256 | lm loss: 3.094241E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.746 | TFLOPs: 34.58 | +7: iteration 5820/ 11269 | consumed samples: 1489920 | consumed tokens: 3051356160 | elapsed time per iteration (s): 0.48 | learning rate: 1.067E-04 | global batch size: 256 | lm loss: 3.082017E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.424 | TFLOPs: 34.82 | +7: iteration 5830/ 11269 | consumed samples: 1492480 | consumed tokens: 3056599040 | elapsed time per iteration (s): 0.50 | learning rate: 1.065E-04 | global batch size: 256 | lm loss: 3.059198E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 510.285 | TFLOPs: 33.37 | +7: iteration 5840/ 11269 | consumed samples: 1495040 | consumed tokens: 3061841920 | elapsed time per iteration (s): 0.48 | learning rate: 1.062E-04 | global batch size: 256 | lm loss: 3.071318E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.371 | TFLOPs: 35.14 | +7: iteration 5850/ 11269 | consumed samples: 1497600 | consumed tokens: 3067084800 | elapsed time per iteration (s): 0.50 | learning rate: 1.060E-04 | global batch size: 256 | lm loss: 3.098994E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 509.414 | TFLOPs: 33.32 | +7: iteration 5860/ 11269 | consumed samples: 1500160 | consumed tokens: 3072327680 | elapsed time per iteration (s): 0.49 | learning rate: 1.057E-04 | global batch size: 256 | lm loss: 3.055338E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.411 | TFLOPs: 33.90 | +7: iteration 5870/ 11269 | consumed samples: 1502720 | consumed tokens: 3077570560 | elapsed time per iteration (s): 0.48 | learning rate: 1.055E-04 | global batch size: 256 | lm loss: 3.077762E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.883 | TFLOPs: 35.11 | +7: iteration 5880/ 11269 | consumed samples: 1505280 | consumed tokens: 3082813440 | elapsed time per iteration (s): 0.48 | learning rate: 1.052E-04 | global batch size: 256 | lm loss: 3.066060E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.827 | TFLOPs: 34.65 | +7: iteration 5890/ 11269 | consumed samples: 1507840 | consumed tokens: 3088056320 | elapsed time per iteration (s): 0.48 | learning rate: 1.050E-04 | global batch size: 256 | lm loss: 3.047990E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.529 | TFLOPs: 34.96 | +7: iteration 5900/ 11269 | consumed samples: 1510400 | consumed tokens: 3093299200 | elapsed time per iteration (s): 0.48 | learning rate: 1.047E-04 | global batch size: 256 | lm loss: 3.041354E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.965 | TFLOPs: 34.86 | +7: iteration 5910/ 11269 | consumed samples: 1512960 | consumed tokens: 3098542080 | elapsed time per iteration (s): 0.48 | learning rate: 1.045E-04 | global batch size: 256 | lm loss: 3.086613E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.388 | TFLOPs: 34.75 | +7: iteration 5920/ 11269 | consumed samples: 1515520 | consumed tokens: 3103784960 | elapsed time per iteration (s): 0.49 | learning rate: 1.042E-04 | global batch size: 256 | lm loss: 3.066828E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.128 | TFLOPs: 34.47 | +7: iteration 5930/ 11269 | consumed samples: 1518080 | consumed tokens: 3109027840 | elapsed time per iteration (s): 0.49 | learning rate: 1.039E-04 | global batch size: 256 | lm loss: 3.083417E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.353 | TFLOPs: 34.36 | +7: iteration 5940/ 11269 | consumed samples: 1520640 | consumed tokens: 3114270720 | elapsed time per iteration (s): 0.48 | learning rate: 1.037E-04 | global batch size: 256 | lm loss: 3.080331E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.982 | TFLOPs: 34.53 | +7: iteration 5950/ 11269 | consumed samples: 1523200 | consumed tokens: 3119513600 | elapsed time per iteration (s): 0.48 | learning rate: 1.034E-04 | global batch size: 256 | lm loss: 3.076603E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.798 | TFLOPs: 35.04 | +7: iteration 5960/ 11269 | consumed samples: 1525760 | consumed tokens: 3124756480 | elapsed time per iteration (s): 0.49 | learning rate: 1.032E-04 | global batch size: 256 | lm loss: 3.074554E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.792 | TFLOPs: 34.26 | +7: iteration 5970/ 11269 | consumed samples: 1528320 | consumed tokens: 3129999360 | elapsed time per iteration (s): 0.49 | learning rate: 1.029E-04 | global batch size: 256 | lm loss: 3.071013E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.987 | TFLOPs: 34.14 | +7: iteration 5980/ 11269 | consumed samples: 1530880 | consumed tokens: 3135242240 | elapsed time per iteration (s): 0.49 | learning rate: 1.027E-04 | global batch size: 256 | lm loss: 3.052682E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.146 | TFLOPs: 34.15 | +7: iteration 5990/ 11269 | consumed samples: 1533440 | consumed tokens: 3140485120 | elapsed time per iteration (s): 0.48 | learning rate: 1.024E-04 | global batch size: 256 | lm loss: 3.088480E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.469 | TFLOPs: 34.69 | +0: [2022-11-29 17:41:42,406] [INFO] [logging.py:68:log_dist] [Rank 0] step=6000, skipped=0, lr=[0.00010217547488893524, 0.00010217547488893524, 0.00010217547488893524], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +0: steps: 6000 loss: 3.0177 iter time (s): 0.484 samples/sec: 529.059 +7: iteration 6000/ 11269 | consumed samples: 1536000 | consumed tokens: 3145728000 | elapsed time per iteration (s): 0.48 | learning rate: 1.022E-04 | global batch size: 256 | lm loss: 3.058696E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.520 | TFLOPs: 34.89 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 6000 | lm loss value: 2.953916E+00 | lm loss PPL: 1.918093E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 6000 to checkpoints_280moscar +0: [2022-11-29 17:41:42,602] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step6000 is begin to save! +0: [2022-11-29 17:41:42,606] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:41:42,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:41:42,719] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:41:42,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:41:42,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:41:42,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:41:42,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:41:42,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:41:42,794] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:41:42,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:41:42,819] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:41:42,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:41:42,843] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:41:42,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:41:42,868] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:41:42,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:41:42,892] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:41:42,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:41:42,917] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:41:42,941] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:41:42,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:41:42,965] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:41:42,966] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:41:42,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:41:42,990] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:41:43,015] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:41:43,015] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:41:43,039] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:41:43,040] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:41:43,066] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:41:43,066] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:41:43,091] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:41:43,091] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/layer_18-model_00-model_states.pt... +0: [2022-11-29 17:41:43,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/layer_18-model_00-model_states.pt. +0: [2022-11-29 17:41:43,115] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:41:43,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:41:43,140] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/layer_20-model_00-model_states.pt... +0: [2022-11-29 17:41:43,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/layer_20-model_00-model_states.pt. +0: [2022-11-29 17:41:43,164] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/layer_22-model_00-model_states.pt... +0: [2022-11-29 17:41:43,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/layer_22-model_00-model_states.pt. +0: [2022-11-29 17:41:43,166] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_280moscar/global_step6000/mp_rank_00_model_states.pt +0: [2022-11-29 17:41:43,166] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:41:43,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:41:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:41:43,250] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:41:43,250] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:41:43,250] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:41:43,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:41:43,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:41:43,253] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:41:43,253] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:41:43,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:41:43,251] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:41:43,251] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:41:43,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:41:43,251] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +7: [2022-11-29 17:41:43,254] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:41:43,251] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:41:43,254] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:41:43,254] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:41:43,254] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:41:43,254] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:41:43,254] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:41:43,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:41:43,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:41:43,256] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:41:43,256] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:41:43,256] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:41:43,256] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:41:43,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:41:43,257] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:41:43,257] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:41:43,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:41:43,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:41:43,257] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:41:43,257] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:41:43,257] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:41:43,257] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:41:43,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:41:43,257] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:41:43,257] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:41:43,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:41:43,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:41:43,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:41:43,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:41:43,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:41:43,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:41:43,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:41:43,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:41:43,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:41:43,259] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:41:43,259] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:41:43,259] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:41:43,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:41:43,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:41:43,260] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:41:43,260] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:41:43,260] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:41:43,260] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:41:43,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:41:43,262] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:41:43,262] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:41:43,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:41:43,262] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:41:43,262] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:41:43,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:41:43,262] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:41:43,262] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:41:43,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:41:43,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:41:43,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:41:43,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:41:43,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:41:43,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:41:43,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:41:43,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:41:43,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:41:43,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:41:43,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:41:43,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:41:43,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:41:43,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:41:43,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:41:43,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:41:43,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:41:43,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:41:43,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:41:43,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:41:43,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:41:43,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:41:43,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:41:43,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:41:43,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:41:43,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:41:43,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:41:43,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:41:43,266] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:41:43,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:41:43,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:41:43,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:41:43,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:41:43,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:41:43,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:41:43,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:41:43,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:41:43,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:41:43,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:41:43,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:41:43,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:41:43,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:41:43,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:41:43,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:41:43,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:41:43,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:41:43,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:41:43,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:41:43,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:41:43,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:41:43,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:41:43,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:41:43,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:41:43,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:41:43,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:41:43,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:41:43,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:41:43,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:41:43,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:41:43,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:41:43,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:41:43,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:41:43,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:41:43,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:41:43,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:41:43,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:41:43,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:41:43,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:41:43,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:41:43,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:41:43,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:41:43,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:41:43,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:41:43,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:41:43,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:41:43,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:41:43,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:41:43,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:41:43,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:41:43,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:41:43,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:41:43,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:41:43,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:41:43,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:41:43,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:41:43,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:41:43,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:41:43,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:41:43,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:41:43,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:41:43,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:41:43,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:41:43,285] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:41:43,285] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:41:43,251] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:41:43,252] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:41:43,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:41:43,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:41:43,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:41:43,260] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:41:43,260] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:41:43,260] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:41:43,260] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:41:43,260] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:41:43,260] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:41:43,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:41:43,260] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:41:43,260] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:41:43,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:41:43,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:41:43,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:41:43,261] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:41:43,261] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:41:43,261] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:41:43,261] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:41:43,261] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:41:43,261] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:41:43,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:41:43,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:41:43,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:41:43,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:41:43,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:41:43,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:41:43,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:41:43,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:41:43,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step6000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:41:43,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:41:43,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: successfully saved checkpoint at iteration 6000 to checkpoints_280moscar +7: time (ms) | save-checkpoint: 721.95 +7: iteration 6010/ 11269 | consumed samples: 1538560 | consumed tokens: 3150970880 | elapsed time per iteration (s): 0.58 | learning rate: 1.019E-04 | global batch size: 256 | lm loss: 3.074790E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.896 | TFLOPs: 29.10 | +7: iteration 6020/ 11269 | consumed samples: 1541120 | consumed tokens: 3156213760 | elapsed time per iteration (s): 0.48 | learning rate: 1.017E-04 | global batch size: 256 | lm loss: 3.082388E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.769 | TFLOPs: 34.91 | +7: iteration 6030/ 11269 | consumed samples: 1543680 | consumed tokens: 3161456640 | elapsed time per iteration (s): 0.47 | learning rate: 1.014E-04 | global batch size: 256 | lm loss: 3.092185E+00 | grad norm: 0.622 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 541.395 | TFLOPs: 35.41 | +7: iteration 6040/ 11269 | consumed samples: 1546240 | consumed tokens: 3166699520 | elapsed time per iteration (s): 0.48 | learning rate: 1.012E-04 | global batch size: 256 | lm loss: 3.041357E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.031 | TFLOPs: 34.73 | +7: iteration 6050/ 11269 | consumed samples: 1548800 | consumed tokens: 3171942400 | elapsed time per iteration (s): 0.48 | learning rate: 1.009E-04 | global batch size: 256 | lm loss: 3.042415E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.752 | TFLOPs: 34.91 | +7: iteration 6060/ 11269 | consumed samples: 1551360 | consumed tokens: 3177185280 | elapsed time per iteration (s): 0.49 | learning rate: 1.007E-04 | global batch size: 256 | lm loss: 3.058877E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.301 | TFLOPs: 34.29 | +7: iteration 6070/ 11269 | consumed samples: 1553920 | consumed tokens: 3182428160 | elapsed time per iteration (s): 0.48 | learning rate: 1.004E-04 | global batch size: 256 | lm loss: 3.087601E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.978 | TFLOPs: 35.05 | +7: iteration 6080/ 11269 | consumed samples: 1556480 | consumed tokens: 3187671040 | elapsed time per iteration (s): 0.48 | learning rate: 1.002E-04 | global batch size: 256 | lm loss: 3.043071E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.187 | TFLOPs: 35.13 | +7: iteration 6090/ 11269 | consumed samples: 1559040 | consumed tokens: 3192913920 | elapsed time per iteration (s): 0.49 | learning rate: 9.991E-05 | global batch size: 256 | lm loss: 3.107035E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.755 | TFLOPs: 34.19 | +7: iteration 6100/ 11269 | consumed samples: 1561600 | consumed tokens: 3198156800 | elapsed time per iteration (s): 0.48 | learning rate: 9.965E-05 | global batch size: 256 | lm loss: 3.067079E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.337 | TFLOPs: 34.75 | +7: iteration 6110/ 11269 | consumed samples: 1564160 | consumed tokens: 3203399680 | elapsed time per iteration (s): 0.48 | learning rate: 9.940E-05 | global batch size: 256 | lm loss: 3.078067E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.060 | TFLOPs: 34.60 | +7: iteration 6120/ 11269 | consumed samples: 1566720 | consumed tokens: 3208642560 | elapsed time per iteration (s): 0.48 | learning rate: 9.915E-05 | global batch size: 256 | lm loss: 3.059985E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.227 | TFLOPs: 34.68 | +7: iteration 6130/ 11269 | consumed samples: 1569280 | consumed tokens: 3213885440 | elapsed time per iteration (s): 0.48 | learning rate: 9.890E-05 | global batch size: 256 | lm loss: 3.055671E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.670 | TFLOPs: 34.97 | +7: iteration 6140/ 11269 | consumed samples: 1571840 | consumed tokens: 3219128320 | elapsed time per iteration (s): 0.48 | learning rate: 9.865E-05 | global batch size: 256 | lm loss: 3.032620E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.950 | TFLOPs: 34.59 | +7: iteration 6150/ 11269 | consumed samples: 1574400 | consumed tokens: 3224371200 | elapsed time per iteration (s): 0.48 | learning rate: 9.840E-05 | global batch size: 256 | lm loss: 3.056570E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.599 | TFLOPs: 34.64 | +7: iteration 6160/ 11269 | consumed samples: 1576960 | consumed tokens: 3229614080 | elapsed time per iteration (s): 0.48 | learning rate: 9.815E-05 | global batch size: 256 | lm loss: 3.059776E+00 | grad norm: 0.380 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.386 | TFLOPs: 34.75 | +7: iteration 6170/ 11269 | consumed samples: 1579520 | consumed tokens: 3234856960 | elapsed time per iteration (s): 0.49 | learning rate: 9.789E-05 | global batch size: 256 | lm loss: 3.066242E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.399 | TFLOPs: 34.30 | +7: iteration 6180/ 11269 | consumed samples: 1582080 | consumed tokens: 3240099840 | elapsed time per iteration (s): 0.48 | learning rate: 9.764E-05 | global batch size: 256 | lm loss: 3.065916E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.771 | TFLOPs: 34.84 | +7: iteration 6190/ 11269 | consumed samples: 1584640 | consumed tokens: 3245342720 | elapsed time per iteration (s): 0.48 | learning rate: 9.739E-05 | global batch size: 256 | lm loss: 3.043438E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.530 | TFLOPs: 34.63 | +7: iteration 6200/ 11269 | consumed samples: 1587200 | consumed tokens: 3250585600 | elapsed time per iteration (s): 0.47 | learning rate: 9.714E-05 | global batch size: 256 | lm loss: 3.056389E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 541.452 | TFLOPs: 35.41 | +7: iteration 6210/ 11269 | consumed samples: 1589760 | consumed tokens: 3255828480 | elapsed time per iteration (s): 0.49 | learning rate: 9.689E-05 | global batch size: 256 | lm loss: 3.029701E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.964 | TFLOPs: 34.20 | +7: iteration 6220/ 11269 | consumed samples: 1592320 | consumed tokens: 3261071360 | elapsed time per iteration (s): 0.47 | learning rate: 9.664E-05 | global batch size: 256 | lm loss: 3.071566E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 539.893 | TFLOPs: 35.31 | +7: iteration 6230/ 11269 | consumed samples: 1594880 | consumed tokens: 3266314240 | elapsed time per iteration (s): 0.48 | learning rate: 9.639E-05 | global batch size: 256 | lm loss: 3.052189E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.511 | TFLOPs: 35.09 | +7: iteration 6240/ 11269 | consumed samples: 1597440 | consumed tokens: 3271557120 | elapsed time per iteration (s): 0.54 | learning rate: 9.614E-05 | global batch size: 256 | lm loss: 3.049375E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 473.361 | TFLOPs: 30.96 | +7: iteration 6250/ 11269 | consumed samples: 1600000 | consumed tokens: 3276800000 | elapsed time per iteration (s): 0.48 | learning rate: 9.589E-05 | global batch size: 256 | lm loss: 3.052546E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.089 | TFLOPs: 34.54 | +7: iteration 6260/ 11269 | consumed samples: 1602560 | consumed tokens: 3282042880 | elapsed time per iteration (s): 0.48 | learning rate: 9.564E-05 | global batch size: 256 | lm loss: 3.064846E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.974 | TFLOPs: 34.99 | +7: iteration 6270/ 11269 | consumed samples: 1605120 | consumed tokens: 3287285760 | elapsed time per iteration (s): 0.48 | learning rate: 9.539E-05 | global batch size: 256 | lm loss: 3.075937E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.620 | TFLOPs: 34.64 | +7: iteration 6280/ 11269 | consumed samples: 1607680 | consumed tokens: 3292528640 | elapsed time per iteration (s): 0.51 | learning rate: 9.514E-05 | global batch size: 256 | lm loss: 3.042408E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 506.916 | TFLOPs: 33.15 | +7: iteration 6290/ 11269 | consumed samples: 1610240 | consumed tokens: 3297771520 | elapsed time per iteration (s): 0.49 | learning rate: 9.489E-05 | global batch size: 256 | lm loss: 3.046255E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.544 | TFLOPs: 34.31 | +7: iteration 6300/ 11269 | consumed samples: 1612800 | consumed tokens: 3303014400 | elapsed time per iteration (s): 0.49 | learning rate: 9.464E-05 | global batch size: 256 | lm loss: 3.058287E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.871 | TFLOPs: 34.33 | +7: iteration 6310/ 11269 | consumed samples: 1615360 | consumed tokens: 3308257280 | elapsed time per iteration (s): 0.48 | learning rate: 9.439E-05 | global batch size: 256 | lm loss: 3.032653E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.782 | TFLOPs: 34.65 | +7: iteration 6320/ 11269 | consumed samples: 1617920 | consumed tokens: 3313500160 | elapsed time per iteration (s): 0.48 | learning rate: 9.414E-05 | global batch size: 256 | lm loss: 3.035754E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.252 | TFLOPs: 35.07 | +7: iteration 6330/ 11269 | consumed samples: 1620480 | consumed tokens: 3318743040 | elapsed time per iteration (s): 0.50 | learning rate: 9.389E-05 | global batch size: 256 | lm loss: 3.034783E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 516.545 | TFLOPs: 33.78 | +7: iteration 6340/ 11269 | consumed samples: 1623040 | consumed tokens: 3323985920 | elapsed time per iteration (s): 0.48 | learning rate: 9.364E-05 | global batch size: 256 | lm loss: 3.043350E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.750 | TFLOPs: 34.84 | +7: iteration 6350/ 11269 | consumed samples: 1625600 | consumed tokens: 3329228800 | elapsed time per iteration (s): 0.48 | learning rate: 9.339E-05 | global batch size: 256 | lm loss: 3.072782E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.976 | TFLOPs: 34.86 | +7: iteration 6360/ 11269 | consumed samples: 1628160 | consumed tokens: 3334471680 | elapsed time per iteration (s): 0.48 | learning rate: 9.314E-05 | global batch size: 256 | lm loss: 3.025561E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.896 | TFLOPs: 34.98 | +7: iteration 6370/ 11269 | consumed samples: 1630720 | consumed tokens: 3339714560 | elapsed time per iteration (s): 0.48 | learning rate: 9.289E-05 | global batch size: 256 | lm loss: 3.047623E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.161 | TFLOPs: 35.13 | +7: iteration 6380/ 11269 | consumed samples: 1633280 | consumed tokens: 3344957440 | elapsed time per iteration (s): 0.48 | learning rate: 9.264E-05 | global batch size: 256 | lm loss: 3.042932E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.054 | TFLOPs: 34.93 | +7: iteration 6390/ 11269 | consumed samples: 1635840 | consumed tokens: 3350200320 | elapsed time per iteration (s): 0.49 | learning rate: 9.240E-05 | global batch size: 256 | lm loss: 3.048637E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.717 | TFLOPs: 33.86 | +7: iteration 6400/ 11269 | consumed samples: 1638400 | consumed tokens: 3355443200 | elapsed time per iteration (s): 0.49 | learning rate: 9.215E-05 | global batch size: 256 | lm loss: 3.070885E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.909 | TFLOPs: 33.87 | +7: iteration 6410/ 11269 | consumed samples: 1640960 | consumed tokens: 3360686080 | elapsed time per iteration (s): 0.49 | learning rate: 9.190E-05 | global batch size: 256 | lm loss: 3.048225E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.984 | TFLOPs: 34.40 | +7: iteration 6420/ 11269 | consumed samples: 1643520 | consumed tokens: 3365928960 | elapsed time per iteration (s): 0.48 | learning rate: 9.165E-05 | global batch size: 256 | lm loss: 3.055878E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.479 | TFLOPs: 35.09 | +7: iteration 6430/ 11269 | consumed samples: 1646080 | consumed tokens: 3371171840 | elapsed time per iteration (s): 0.55 | learning rate: 9.140E-05 | global batch size: 256 | lm loss: 3.055202E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 469.104 | TFLOPs: 30.68 | +7: iteration 6440/ 11269 | consumed samples: 1648640 | consumed tokens: 3376414720 | elapsed time per iteration (s): 0.50 | learning rate: 9.115E-05 | global batch size: 256 | lm loss: 3.047850E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 510.801 | TFLOPs: 33.41 | +7: iteration 6450/ 11269 | consumed samples: 1651200 | consumed tokens: 3381657600 | elapsed time per iteration (s): 0.48 | learning rate: 9.091E-05 | global batch size: 256 | lm loss: 3.056570E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.101 | TFLOPs: 35.00 | +7: iteration 6460/ 11269 | consumed samples: 1653760 | consumed tokens: 3386900480 | elapsed time per iteration (s): 0.48 | learning rate: 9.066E-05 | global batch size: 256 | lm loss: 3.045737E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.547 | TFLOPs: 34.76 | +7: iteration 6470/ 11269 | consumed samples: 1656320 | consumed tokens: 3392143360 | elapsed time per iteration (s): 0.48 | learning rate: 9.041E-05 | global batch size: 256 | lm loss: 3.070866E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.293 | TFLOPs: 34.62 | +7: iteration 6480/ 11269 | consumed samples: 1658880 | consumed tokens: 3397386240 | elapsed time per iteration (s): 0.49 | learning rate: 9.016E-05 | global batch size: 256 | lm loss: 3.042868E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.679 | TFLOPs: 34.31 | +7: iteration 6490/ 11269 | consumed samples: 1661440 | consumed tokens: 3402629120 | elapsed time per iteration (s): 0.52 | learning rate: 8.992E-05 | global batch size: 256 | lm loss: 3.049438E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 494.894 | TFLOPs: 32.37 | +7: iteration 6500/ 11269 | consumed samples: 1664000 | consumed tokens: 3407872000 | elapsed time per iteration (s): 0.48 | learning rate: 8.967E-05 | global batch size: 256 | lm loss: 3.045595E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.874 | TFLOPs: 34.65 | +7: iteration 6510/ 11269 | consumed samples: 1666560 | consumed tokens: 3413114880 | elapsed time per iteration (s): 0.49 | learning rate: 8.942E-05 | global batch size: 256 | lm loss: 3.029402E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.600 | TFLOPs: 34.31 | +7: iteration 6520/ 11269 | consumed samples: 1669120 | consumed tokens: 3418357760 | elapsed time per iteration (s): 0.48 | learning rate: 8.918E-05 | global batch size: 256 | lm loss: 3.033430E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 538.929 | TFLOPs: 35.25 | +7: iteration 6530/ 11269 | consumed samples: 1671680 | consumed tokens: 3423600640 | elapsed time per iteration (s): 0.49 | learning rate: 8.893E-05 | global batch size: 256 | lm loss: 3.011537E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.388 | TFLOPs: 34.49 | +7: iteration 6540/ 11269 | consumed samples: 1674240 | consumed tokens: 3428843520 | elapsed time per iteration (s): 0.48 | learning rate: 8.868E-05 | global batch size: 256 | lm loss: 3.026364E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.804 | TFLOPs: 34.58 | +7: iteration 6550/ 11269 | consumed samples: 1676800 | consumed tokens: 3434086400 | elapsed time per iteration (s): 0.48 | learning rate: 8.844E-05 | global batch size: 256 | lm loss: 3.048631E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.823 | TFLOPs: 34.98 | +7: iteration 6560/ 11269 | consumed samples: 1679360 | consumed tokens: 3439329280 | elapsed time per iteration (s): 0.49 | learning rate: 8.819E-05 | global batch size: 256 | lm loss: 3.024204E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.696 | TFLOPs: 34.05 | +7: iteration 6570/ 11269 | consumed samples: 1681920 | consumed tokens: 3444572160 | elapsed time per iteration (s): 0.48 | learning rate: 8.795E-05 | global batch size: 256 | lm loss: 3.029959E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.101 | TFLOPs: 35.13 | +7: iteration 6580/ 11269 | consumed samples: 1684480 | consumed tokens: 3449815040 | elapsed time per iteration (s): 0.48 | learning rate: 8.770E-05 | global batch size: 256 | lm loss: 3.055942E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.890 | TFLOPs: 34.79 | +7: iteration 6590/ 11269 | consumed samples: 1687040 | consumed tokens: 3455057920 | elapsed time per iteration (s): 0.49 | learning rate: 8.746E-05 | global batch size: 256 | lm loss: 3.045466E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.669 | TFLOPs: 33.92 | +7: iteration 6600/ 11269 | consumed samples: 1689600 | consumed tokens: 3460300800 | elapsed time per iteration (s): 0.48 | learning rate: 8.721E-05 | global batch size: 256 | lm loss: 3.074398E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.740 | TFLOPs: 34.64 | +7: iteration 6610/ 11269 | consumed samples: 1692160 | consumed tokens: 3465543680 | elapsed time per iteration (s): 0.48 | learning rate: 8.697E-05 | global batch size: 256 | lm loss: 3.049190E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.646 | TFLOPs: 34.90 | +7: iteration 6620/ 11269 | consumed samples: 1694720 | consumed tokens: 3470786560 | elapsed time per iteration (s): 0.48 | learning rate: 8.672E-05 | global batch size: 256 | lm loss: 3.017346E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.124 | TFLOPs: 35.00 | +7: iteration 6630/ 11269 | consumed samples: 1697280 | consumed tokens: 3476029440 | elapsed time per iteration (s): 0.48 | learning rate: 8.648E-05 | global batch size: 256 | lm loss: 3.043756E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.961 | TFLOPs: 35.12 | +7: iteration 6640/ 11269 | consumed samples: 1699840 | consumed tokens: 3481272320 | elapsed time per iteration (s): 0.49 | learning rate: 8.623E-05 | global batch size: 256 | lm loss: 3.025374E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.633 | TFLOPs: 34.31 | +7: iteration 6650/ 11269 | consumed samples: 1702400 | consumed tokens: 3486515200 | elapsed time per iteration (s): 0.48 | learning rate: 8.599E-05 | global batch size: 256 | lm loss: 3.031068E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.101 | TFLOPs: 34.86 | +7: iteration 6660/ 11269 | consumed samples: 1704960 | consumed tokens: 3491758080 | elapsed time per iteration (s): 0.48 | learning rate: 8.574E-05 | global batch size: 256 | lm loss: 3.050808E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.512 | TFLOPs: 34.83 | +7: iteration 6670/ 11269 | consumed samples: 1707520 | consumed tokens: 3497000960 | elapsed time per iteration (s): 0.47 | learning rate: 8.550E-05 | global batch size: 256 | lm loss: 3.031379E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 540.095 | TFLOPs: 35.32 | +7: iteration 6680/ 11269 | consumed samples: 1710080 | consumed tokens: 3502243840 | elapsed time per iteration (s): 0.48 | learning rate: 8.525E-05 | global batch size: 256 | lm loss: 3.041650E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.812 | TFLOPs: 35.17 | +7: iteration 6690/ 11269 | consumed samples: 1712640 | consumed tokens: 3507486720 | elapsed time per iteration (s): 0.48 | learning rate: 8.501E-05 | global batch size: 256 | lm loss: 3.041671E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.380 | TFLOPs: 34.88 | +7: iteration 6700/ 11269 | consumed samples: 1715200 | consumed tokens: 3512729600 | elapsed time per iteration (s): 0.48 | learning rate: 8.477E-05 | global batch size: 256 | lm loss: 3.019928E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 538.263 | TFLOPs: 35.20 | +7: iteration 6710/ 11269 | consumed samples: 1717760 | consumed tokens: 3517972480 | elapsed time per iteration (s): 0.48 | learning rate: 8.452E-05 | global batch size: 256 | lm loss: 3.045275E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.290 | TFLOPs: 34.55 | +7: iteration 6720/ 11269 | consumed samples: 1720320 | consumed tokens: 3523215360 | elapsed time per iteration (s): 0.50 | learning rate: 8.428E-05 | global batch size: 256 | lm loss: 3.019716E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 516.041 | TFLOPs: 33.75 | +7: iteration 6730/ 11269 | consumed samples: 1722880 | consumed tokens: 3528458240 | elapsed time per iteration (s): 0.49 | learning rate: 8.404E-05 | global batch size: 256 | lm loss: 3.036318E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.921 | TFLOPs: 34.46 | +7: iteration 6740/ 11269 | consumed samples: 1725440 | consumed tokens: 3533701120 | elapsed time per iteration (s): 0.48 | learning rate: 8.380E-05 | global batch size: 256 | lm loss: 3.050341E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.053 | TFLOPs: 34.99 | +7: iteration 6750/ 11269 | consumed samples: 1728000 | consumed tokens: 3538944000 | elapsed time per iteration (s): 0.48 | learning rate: 8.355E-05 | global batch size: 256 | lm loss: 3.048076E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.539 | TFLOPs: 34.89 | +7: iteration 6760/ 11269 | consumed samples: 1730560 | consumed tokens: 3544186880 | elapsed time per iteration (s): 0.48 | learning rate: 8.331E-05 | global batch size: 256 | lm loss: 3.029926E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.607 | TFLOPs: 35.16 | +7: iteration 6770/ 11269 | consumed samples: 1733120 | consumed tokens: 3549429760 | elapsed time per iteration (s): 0.47 | learning rate: 8.307E-05 | global batch size: 256 | lm loss: 3.063436E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 540.076 | TFLOPs: 35.32 | +7: iteration 6780/ 11269 | consumed samples: 1735680 | consumed tokens: 3554672640 | elapsed time per iteration (s): 0.48 | learning rate: 8.283E-05 | global batch size: 256 | lm loss: 3.010662E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.563 | TFLOPs: 34.89 | +7: iteration 6790/ 11269 | consumed samples: 1738240 | consumed tokens: 3559915520 | elapsed time per iteration (s): 0.48 | learning rate: 8.259E-05 | global batch size: 256 | lm loss: 3.024159E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.698 | TFLOPs: 34.97 | +7: iteration 6800/ 11269 | consumed samples: 1740800 | consumed tokens: 3565158400 | elapsed time per iteration (s): 0.49 | learning rate: 8.235E-05 | global batch size: 256 | lm loss: 3.077055E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.482 | TFLOPs: 34.30 | +7: iteration 6810/ 11269 | consumed samples: 1743360 | consumed tokens: 3570401280 | elapsed time per iteration (s): 0.48 | learning rate: 8.210E-05 | global batch size: 256 | lm loss: 3.006493E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.842 | TFLOPs: 34.91 | +7: iteration 6820/ 11269 | consumed samples: 1745920 | consumed tokens: 3575644160 | elapsed time per iteration (s): 0.48 | learning rate: 8.186E-05 | global batch size: 256 | lm loss: 3.041565E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.352 | TFLOPs: 34.82 | +7: iteration 6830/ 11269 | consumed samples: 1748480 | consumed tokens: 3580887040 | elapsed time per iteration (s): 0.47 | learning rate: 8.162E-05 | global batch size: 256 | lm loss: 3.034169E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 539.896 | TFLOPs: 35.31 | +7: iteration 6840/ 11269 | consumed samples: 1751040 | consumed tokens: 3586129920 | elapsed time per iteration (s): 0.47 | learning rate: 8.138E-05 | global batch size: 256 | lm loss: 3.040675E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 540.918 | TFLOPs: 35.38 | +7: iteration 6850/ 11269 | consumed samples: 1753600 | consumed tokens: 3591372800 | elapsed time per iteration (s): 0.48 | learning rate: 8.114E-05 | global batch size: 256 | lm loss: 3.020071E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.099 | TFLOPs: 34.93 | +7: iteration 6860/ 11269 | consumed samples: 1756160 | consumed tokens: 3596615680 | elapsed time per iteration (s): 0.48 | learning rate: 8.090E-05 | global batch size: 256 | lm loss: 3.002618E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.377 | TFLOPs: 35.14 | +7: iteration 6870/ 11269 | consumed samples: 1758720 | consumed tokens: 3601858560 | elapsed time per iteration (s): 0.48 | learning rate: 8.066E-05 | global batch size: 256 | lm loss: 3.013862E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.881 | TFLOPs: 34.78 | +7: iteration 6880/ 11269 | consumed samples: 1761280 | consumed tokens: 3607101440 | elapsed time per iteration (s): 0.48 | learning rate: 8.042E-05 | global batch size: 256 | lm loss: 3.010849E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.545 | TFLOPs: 34.89 | +7: iteration 6890/ 11269 | consumed samples: 1763840 | consumed tokens: 3612344320 | elapsed time per iteration (s): 0.49 | learning rate: 8.018E-05 | global batch size: 256 | lm loss: 3.034126E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.028 | TFLOPs: 34.14 | +7: iteration 6900/ 11269 | consumed samples: 1766400 | consumed tokens: 3617587200 | elapsed time per iteration (s): 0.49 | learning rate: 7.994E-05 | global batch size: 256 | lm loss: 3.036066E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.014 | TFLOPs: 34.47 | +7: iteration 6910/ 11269 | consumed samples: 1768960 | consumed tokens: 3622830080 | elapsed time per iteration (s): 0.50 | learning rate: 7.971E-05 | global batch size: 256 | lm loss: 3.021942E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 512.090 | TFLOPs: 33.49 | +7: iteration 6920/ 11269 | consumed samples: 1771520 | consumed tokens: 3628072960 | elapsed time per iteration (s): 0.48 | learning rate: 7.947E-05 | global batch size: 256 | lm loss: 3.032337E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.505 | TFLOPs: 34.69 | +7: iteration 6930/ 11269 | consumed samples: 1774080 | consumed tokens: 3633315840 | elapsed time per iteration (s): 0.48 | learning rate: 7.923E-05 | global batch size: 256 | lm loss: 3.017269E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.608 | TFLOPs: 34.77 | +7: iteration 6940/ 11269 | consumed samples: 1776640 | consumed tokens: 3638558720 | elapsed time per iteration (s): 0.48 | learning rate: 7.899E-05 | global batch size: 256 | lm loss: 3.011263E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.061 | TFLOPs: 34.86 | +7: iteration 6950/ 11269 | consumed samples: 1779200 | consumed tokens: 3643801600 | elapsed time per iteration (s): 0.49 | learning rate: 7.875E-05 | global batch size: 256 | lm loss: 3.031565E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.422 | TFLOPs: 34.43 | +7: iteration 6960/ 11269 | consumed samples: 1781760 | consumed tokens: 3649044480 | elapsed time per iteration (s): 0.47 | learning rate: 7.852E-05 | global batch size: 256 | lm loss: 3.002994E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 539.752 | TFLOPs: 35.30 | +7: iteration 6970/ 11269 | consumed samples: 1784320 | consumed tokens: 3654287360 | elapsed time per iteration (s): 0.48 | learning rate: 7.828E-05 | global batch size: 256 | lm loss: 3.019741E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.954 | TFLOPs: 34.79 | +7: iteration 6980/ 11269 | consumed samples: 1786880 | consumed tokens: 3659530240 | elapsed time per iteration (s): 0.48 | learning rate: 7.804E-05 | global batch size: 256 | lm loss: 2.980466E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.176 | TFLOPs: 34.80 | +7: iteration 6990/ 11269 | consumed samples: 1789440 | consumed tokens: 3664773120 | elapsed time per iteration (s): 0.48 | learning rate: 7.780E-05 | global batch size: 256 | lm loss: 3.009328E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.760 | TFLOPs: 34.65 | +7: iteration 7000/ 11269 | consumed samples: 1792000 | consumed tokens: 3670016000 | elapsed time per iteration (s): 0.48 | learning rate: 7.757E-05 | global batch size: 256 | lm loss: 3.025553E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 538.046 | TFLOPs: 35.19 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 7000 | lm loss value: 2.911196E+00 | lm loss PPL: 1.837876E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 7000 to checkpoints_280moscar +0: [2022-11-29 17:49:47,525] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step7000 is begin to save! +0: [2022-11-29 17:49:47,529] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:49:47,642] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:49:47,642] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:49:47,668] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:49:47,669] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:49:47,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:49:47,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:49:47,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:49:47,718] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:49:47,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:49:47,743] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:49:47,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:49:47,769] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:49:47,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:49:47,794] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:49:47,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:49:47,819] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:49:47,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:49:47,844] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:49:47,869] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:49:47,869] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:49:47,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:49:47,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:49:47,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:49:47,919] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:49:47,944] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:49:47,944] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:49:47,968] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:49:47,968] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:49:47,993] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:49:47,993] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:49:48,018] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:49:48,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/layer_18-model_00-model_states.pt... +0: [2022-11-29 17:49:48,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/layer_18-model_00-model_states.pt. +0: [2022-11-29 17:49:48,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:49:48,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:49:48,068] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/layer_20-model_00-model_states.pt... +0: [2022-11-29 17:49:48,093] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/layer_20-model_00-model_states.pt. +0: [2022-11-29 17:49:48,093] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/layer_22-model_00-model_states.pt... +0: [2022-11-29 17:49:48,094] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/layer_22-model_00-model_states.pt. +0: [2022-11-29 17:49:48,095] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_280moscar/global_step7000/mp_rank_00_model_states.pt +0: [2022-11-29 17:49:48,095] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:49:48,097] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:49:48,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:49:48,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:49:48,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:49:48,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 17:49:48,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:49:48,179] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:49:48,179] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 17:49:48,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:49:48,180] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:49:48,180] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 17:49:48,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:49:48,180] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:49:48,180] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:49:48,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:49:48,181] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:49:48,181] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 17:49:48,182] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:49:48,183] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:49:48,183] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:49:48,183] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:49:48,183] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:49:48,183] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:49:48,183] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:49:48,183] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:49:48,183] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:49:48,187] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:49:48,187] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:49:48,187] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:49:48,188] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:49:48,188] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:49:48,188] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:49:48,188] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:49:48,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:49:48,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:49:48,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:49:48,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:49:48,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:49:48,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:49:48,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:49:48,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:49:48,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:49:48,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:49:48,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:49:48,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:49:48,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:49:48,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:49:48,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:49:48,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:49:48,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +5: [2022-11-29 17:49:48,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:49:48,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:49:48,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:49:48,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:49:48,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:49:48,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:49:48,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:49:48,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:49:48,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:49:48,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:49:48,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:49:48,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:49:48,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:49:48,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:49:48,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:49:48,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:49:48,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:49:48,197] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:49:48,189] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:49:48,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 17:49:48,197] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +2: [2022-11-29 17:49:48,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:49:48,189] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:49:48,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:49:48,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:49:48,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:49:48,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:49:48,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:49:48,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:49:48,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:49:48,196] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:49:48,196] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:49:48,196] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:49:48,196] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:49:48,196] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:49:48,196] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:49:48,196] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:49:48,197] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:49:48,197] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:49:48,197] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:49:48,197] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 17:49:48,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:49:48,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:49:48,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 17:49:48,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:49:48,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:49:48,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 17:49:48,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:49:48,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:49:48,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 17:49:48,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:49:48,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:49:48,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:49:48,202] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:49:48,202] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:49:48,202] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:49:48,202] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 17:49:48,202] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 17:49:48,202] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 17:49:48,204] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:49:48,204] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:49:48,204] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:49:48,204] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:49:48,204] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 17:49:48,204] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:49:48,204] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:49:48,204] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 17:49:48,204] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:49:48,197] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:49:48,197] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:49:48,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:49:48,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:49:48,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:49:48,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:49:48,207] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:49:48,207] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:49:48,207] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:49:48,207] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:49:48,207] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:49:48,207] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 17:49:48,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:49:48,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:49:48,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:49:48,184] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:49:48,184] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:49:48,185] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:49:48,185] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 17:49:48,185] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 17:49:48,185] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 17:49:48,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:49:48,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:49:48,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 17:49:48,210] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:49:48,210] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:49:48,210] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 17:49:48,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:49:48,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:49:48,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:49:48,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:49:48,212] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:49:48,212] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:49:48,212] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:49:48,212] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:49:48,212] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 17:49:48,212] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 17:49:48,212] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 17:49:48,212] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:49:48,187] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:49:48,187] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:49:48,187] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:49:48,187] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:49:48,187] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:49:48,187] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:49:48,187] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:49:48,187] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:49:48,188] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:49:48,188] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:49:48,188] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:49:48,188] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:49:48,188] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:49:48,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:49:48,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:49:48,189] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:49:48,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:49:48,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:49:48,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:49:48,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:49:48,201] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:49:48,201] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:49:48,201] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:49:48,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:49:48,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:49:48,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:49:48,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:49:48,234] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:49:48,234] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:49:48,234] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:49:48,234] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:49:48,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:49:48,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:49:48,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:49:48,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:49:48,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step7000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:49:48,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: successfully saved checkpoint at iteration 7000 to checkpoints_280moscar +7: time (ms) | save-checkpoint: 749.29 +7: iteration 7010/ 11269 | consumed samples: 1794560 | consumed tokens: 3675258880 | elapsed time per iteration (s): 0.57 | learning rate: 7.733E-05 | global batch size: 256 | lm loss: 3.038550E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.587 | TFLOPs: 29.14 | +7: iteration 7020/ 11269 | consumed samples: 1797120 | consumed tokens: 3680501760 | elapsed time per iteration (s): 0.48 | learning rate: 7.710E-05 | global batch size: 256 | lm loss: 3.017143E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.596 | TFLOPs: 34.83 | +7: iteration 7030/ 11269 | consumed samples: 1799680 | consumed tokens: 3685744640 | elapsed time per iteration (s): 0.48 | learning rate: 7.686E-05 | global batch size: 256 | lm loss: 3.023853E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.661 | TFLOPs: 34.90 | +7: iteration 7040/ 11269 | consumed samples: 1802240 | consumed tokens: 3690987520 | elapsed time per iteration (s): 0.48 | learning rate: 7.662E-05 | global batch size: 256 | lm loss: 3.025972E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.484 | TFLOPs: 34.69 | +7: iteration 7050/ 11269 | consumed samples: 1804800 | consumed tokens: 3696230400 | elapsed time per iteration (s): 0.48 | learning rate: 7.639E-05 | global batch size: 256 | lm loss: 3.032664E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.368 | TFLOPs: 35.14 | +7: iteration 7060/ 11269 | consumed samples: 1807360 | consumed tokens: 3701473280 | elapsed time per iteration (s): 0.47 | learning rate: 7.615E-05 | global batch size: 256 | lm loss: 3.040195E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 540.455 | TFLOPs: 35.35 | +7: iteration 7070/ 11269 | consumed samples: 1809920 | consumed tokens: 3706716160 | elapsed time per iteration (s): 0.48 | learning rate: 7.592E-05 | global batch size: 256 | lm loss: 2.997417E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.420 | TFLOPs: 34.95 | +7: iteration 7080/ 11269 | consumed samples: 1812480 | consumed tokens: 3711959040 | elapsed time per iteration (s): 0.48 | learning rate: 7.569E-05 | global batch size: 256 | lm loss: 3.018037E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.068 | TFLOPs: 35.06 | +7: iteration 7090/ 11269 | consumed samples: 1815040 | consumed tokens: 3717201920 | elapsed time per iteration (s): 0.48 | learning rate: 7.545E-05 | global batch size: 256 | lm loss: 3.017728E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.153 | TFLOPs: 34.87 | +7: iteration 7100/ 11269 | consumed samples: 1817600 | consumed tokens: 3722444800 | elapsed time per iteration (s): 0.49 | learning rate: 7.522E-05 | global batch size: 256 | lm loss: 3.016155E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.333 | TFLOPs: 34.29 | +7: iteration 7110/ 11269 | consumed samples: 1820160 | consumed tokens: 3727687680 | elapsed time per iteration (s): 0.48 | learning rate: 7.498E-05 | global batch size: 256 | lm loss: 3.032949E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.765 | TFLOPs: 35.17 | +7: iteration 7120/ 11269 | consumed samples: 1822720 | consumed tokens: 3732930560 | elapsed time per iteration (s): 0.48 | learning rate: 7.475E-05 | global batch size: 256 | lm loss: 3.036119E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.521 | TFLOPs: 34.89 | +7: iteration 7130/ 11269 | consumed samples: 1825280 | consumed tokens: 3738173440 | elapsed time per iteration (s): 0.49 | learning rate: 7.452E-05 | global batch size: 256 | lm loss: 3.038700E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.930 | TFLOPs: 34.20 | +7: iteration 7140/ 11269 | consumed samples: 1827840 | consumed tokens: 3743416320 | elapsed time per iteration (s): 0.48 | learning rate: 7.428E-05 | global batch size: 256 | lm loss: 3.026126E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.900 | TFLOPs: 34.59 | +7: iteration 7150/ 11269 | consumed samples: 1830400 | consumed tokens: 3748659200 | elapsed time per iteration (s): 0.48 | learning rate: 7.405E-05 | global batch size: 256 | lm loss: 3.034135E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.884 | TFLOPs: 34.72 | +7: iteration 7160/ 11269 | consumed samples: 1832960 | consumed tokens: 3753902080 | elapsed time per iteration (s): 0.48 | learning rate: 7.382E-05 | global batch size: 256 | lm loss: 3.011906E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.149 | TFLOPs: 34.61 | +7: iteration 7170/ 11269 | consumed samples: 1835520 | consumed tokens: 3759144960 | elapsed time per iteration (s): 0.49 | learning rate: 7.359E-05 | global batch size: 256 | lm loss: 3.004256E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.374 | TFLOPs: 34.29 | +7: iteration 7180/ 11269 | consumed samples: 1838080 | consumed tokens: 3764387840 | elapsed time per iteration (s): 0.48 | learning rate: 7.336E-05 | global batch size: 256 | lm loss: 3.013455E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.328 | TFLOPs: 34.68 | +7: iteration 7190/ 11269 | consumed samples: 1840640 | consumed tokens: 3769630720 | elapsed time per iteration (s): 0.48 | learning rate: 7.313E-05 | global batch size: 256 | lm loss: 3.038618E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.726 | TFLOPs: 34.84 | +7: iteration 7200/ 11269 | consumed samples: 1843200 | consumed tokens: 3774873600 | elapsed time per iteration (s): 0.48 | learning rate: 7.289E-05 | global batch size: 256 | lm loss: 2.975939E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.092 | TFLOPs: 34.54 | +7: iteration 7210/ 11269 | consumed samples: 1845760 | consumed tokens: 3780116480 | elapsed time per iteration (s): 0.50 | learning rate: 7.266E-05 | global batch size: 256 | lm loss: 3.041520E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 508.225 | TFLOPs: 33.24 | +7: iteration 7220/ 11269 | consumed samples: 1848320 | consumed tokens: 3785359360 | elapsed time per iteration (s): 0.49 | learning rate: 7.243E-05 | global batch size: 256 | lm loss: 3.018927E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.789 | TFLOPs: 34.19 | +7: iteration 7230/ 11269 | consumed samples: 1850880 | consumed tokens: 3790602240 | elapsed time per iteration (s): 0.48 | learning rate: 7.220E-05 | global batch size: 256 | lm loss: 3.012043E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.623 | TFLOPs: 34.83 | +7: iteration 7240/ 11269 | consumed samples: 1853440 | consumed tokens: 3795845120 | elapsed time per iteration (s): 0.48 | learning rate: 7.197E-05 | global batch size: 256 | lm loss: 2.997097E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.423 | TFLOPs: 35.08 | +7: iteration 7250/ 11269 | consumed samples: 1856000 | consumed tokens: 3801088000 | elapsed time per iteration (s): 0.49 | learning rate: 7.174E-05 | global batch size: 256 | lm loss: 3.024489E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.954 | TFLOPs: 34.40 | +7: iteration 7260/ 11269 | consumed samples: 1858560 | consumed tokens: 3806330880 | elapsed time per iteration (s): 0.55 | learning rate: 7.151E-05 | global batch size: 256 | lm loss: 3.005846E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 464.050 | TFLOPs: 30.35 | +7: iteration 7270/ 11269 | consumed samples: 1861120 | consumed tokens: 3811573760 | elapsed time per iteration (s): 0.48 | learning rate: 7.129E-05 | global batch size: 256 | lm loss: 3.030543E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.248 | TFLOPs: 35.07 | +7: iteration 7280/ 11269 | consumed samples: 1863680 | consumed tokens: 3816816640 | elapsed time per iteration (s): 0.48 | learning rate: 7.106E-05 | global batch size: 256 | lm loss: 2.995080E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.321 | TFLOPs: 34.68 | +7: iteration 7290/ 11269 | consumed samples: 1866240 | consumed tokens: 3822059520 | elapsed time per iteration (s): 0.47 | learning rate: 7.083E-05 | global batch size: 256 | lm loss: 3.009303E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 540.816 | TFLOPs: 35.37 | +7: iteration 7300/ 11269 | consumed samples: 1868800 | consumed tokens: 3827302400 | elapsed time per iteration (s): 0.48 | learning rate: 7.060E-05 | global batch size: 256 | lm loss: 3.028093E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.570 | TFLOPs: 34.76 | +7: iteration 7310/ 11269 | consumed samples: 1871360 | consumed tokens: 3832545280 | elapsed time per iteration (s): 0.48 | learning rate: 7.037E-05 | global batch size: 256 | lm loss: 3.016205E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.442 | TFLOPs: 34.63 | +7: iteration 7320/ 11269 | consumed samples: 1873920 | consumed tokens: 3837788160 | elapsed time per iteration (s): 0.48 | learning rate: 7.014E-05 | global batch size: 256 | lm loss: 3.015342E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.214 | TFLOPs: 35.00 | +7: iteration 7330/ 11269 | consumed samples: 1876480 | consumed tokens: 3843031040 | elapsed time per iteration (s): 0.48 | learning rate: 6.992E-05 | global batch size: 256 | lm loss: 3.002710E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.224 | TFLOPs: 35.13 | +7: iteration 7340/ 11269 | consumed samples: 1879040 | consumed tokens: 3848273920 | elapsed time per iteration (s): 0.48 | learning rate: 6.969E-05 | global batch size: 256 | lm loss: 2.992717E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.619 | TFLOPs: 34.83 | +7: iteration 7350/ 11269 | consumed samples: 1881600 | consumed tokens: 3853516800 | elapsed time per iteration (s): 0.48 | learning rate: 6.946E-05 | global batch size: 256 | lm loss: 3.041384E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.672 | TFLOPs: 34.77 | +7: iteration 7360/ 11269 | consumed samples: 1884160 | consumed tokens: 3858759680 | elapsed time per iteration (s): 0.48 | learning rate: 6.924E-05 | global batch size: 256 | lm loss: 3.032174E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.020 | TFLOPs: 35.12 | +7: iteration 7370/ 11269 | consumed samples: 1886720 | consumed tokens: 3864002560 | elapsed time per iteration (s): 0.48 | learning rate: 6.901E-05 | global batch size: 256 | lm loss: 2.999604E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.197 | TFLOPs: 35.13 | +7: iteration 7380/ 11269 | consumed samples: 1889280 | consumed tokens: 3869245440 | elapsed time per iteration (s): 0.47 | learning rate: 6.879E-05 | global batch size: 256 | lm loss: 3.003503E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 540.130 | TFLOPs: 35.32 | +7: iteration 7390/ 11269 | consumed samples: 1891840 | consumed tokens: 3874488320 | elapsed time per iteration (s): 0.48 | learning rate: 6.856E-05 | global batch size: 256 | lm loss: 2.987897E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.588 | TFLOPs: 34.90 | +7: iteration 7400/ 11269 | consumed samples: 1894400 | consumed tokens: 3879731200 | elapsed time per iteration (s): 0.48 | learning rate: 6.834E-05 | global batch size: 256 | lm loss: 3.004783E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.540 | TFLOPs: 35.02 | +7: iteration 7410/ 11269 | consumed samples: 1896960 | consumed tokens: 3884974080 | elapsed time per iteration (s): 0.48 | learning rate: 6.811E-05 | global batch size: 256 | lm loss: 2.994323E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.341 | TFLOPs: 35.08 | +7: iteration 7420/ 11269 | consumed samples: 1899520 | consumed tokens: 3890216960 | elapsed time per iteration (s): 0.48 | learning rate: 6.789E-05 | global batch size: 256 | lm loss: 3.005012E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.262 | TFLOPs: 34.61 | +7: iteration 7430/ 11269 | consumed samples: 1902080 | consumed tokens: 3895459840 | elapsed time per iteration (s): 0.48 | learning rate: 6.766E-05 | global batch size: 256 | lm loss: 3.008517E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.483 | TFLOPs: 35.09 | +7: iteration 7440/ 11269 | consumed samples: 1904640 | consumed tokens: 3900702720 | elapsed time per iteration (s): 0.48 | learning rate: 6.744E-05 | global batch size: 256 | lm loss: 3.006135E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.205 | TFLOPs: 34.87 | +7: iteration 7450/ 11269 | consumed samples: 1907200 | consumed tokens: 3905945600 | elapsed time per iteration (s): 0.48 | learning rate: 6.722E-05 | global batch size: 256 | lm loss: 3.016244E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.129 | TFLOPs: 35.00 | +7: iteration 7460/ 11269 | consumed samples: 1909760 | consumed tokens: 3911188480 | elapsed time per iteration (s): 0.48 | learning rate: 6.700E-05 | global batch size: 256 | lm loss: 3.021980E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.720 | TFLOPs: 35.17 | +7: iteration 7470/ 11269 | consumed samples: 1912320 | consumed tokens: 3916431360 | elapsed time per iteration (s): 0.47 | learning rate: 6.677E-05 | global batch size: 256 | lm loss: 3.001615E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 542.264 | TFLOPs: 35.46 | +7: iteration 7480/ 11269 | consumed samples: 1914880 | consumed tokens: 3921674240 | elapsed time per iteration (s): 0.47 | learning rate: 6.655E-05 | global batch size: 256 | lm loss: 2.979653E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 540.797 | TFLOPs: 35.37 | +7: iteration 7490/ 11269 | consumed samples: 1917440 | consumed tokens: 3926917120 | elapsed time per iteration (s): 0.48 | learning rate: 6.633E-05 | global batch size: 256 | lm loss: 2.998870E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.523 | TFLOPs: 34.96 | +7: iteration 7500/ 11269 | consumed samples: 1920000 | consumed tokens: 3932160000 | elapsed time per iteration (s): 0.48 | learning rate: 6.611E-05 | global batch size: 256 | lm loss: 3.013471E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.908 | TFLOPs: 35.18 | +7: iteration 7510/ 11269 | consumed samples: 1922560 | consumed tokens: 3937402880 | elapsed time per iteration (s): 0.48 | learning rate: 6.589E-05 | global batch size: 256 | lm loss: 2.999314E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.688 | TFLOPs: 35.10 | +7: iteration 7520/ 11269 | consumed samples: 1925120 | consumed tokens: 3942645760 | elapsed time per iteration (s): 0.48 | learning rate: 6.567E-05 | global batch size: 256 | lm loss: 3.009971E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.373 | TFLOPs: 34.95 | +7: iteration 7530/ 11269 | consumed samples: 1927680 | consumed tokens: 3947888640 | elapsed time per iteration (s): 0.49 | learning rate: 6.545E-05 | global batch size: 256 | lm loss: 3.002436E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.992 | TFLOPs: 34.47 | +7: iteration 7540/ 11269 | consumed samples: 1930240 | consumed tokens: 3953131520 | elapsed time per iteration (s): 0.48 | learning rate: 6.523E-05 | global batch size: 256 | lm loss: 3.017666E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.074 | TFLOPs: 34.86 | +7: iteration 7550/ 11269 | consumed samples: 1932800 | consumed tokens: 3958374400 | elapsed time per iteration (s): 0.48 | learning rate: 6.501E-05 | global batch size: 256 | lm loss: 3.007270E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.557 | TFLOPs: 35.09 | +7: iteration 7560/ 11269 | consumed samples: 1935360 | consumed tokens: 3963617280 | elapsed time per iteration (s): 0.48 | learning rate: 6.479E-05 | global batch size: 256 | lm loss: 2.994733E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.845 | TFLOPs: 34.78 | +7: iteration 7570/ 11269 | consumed samples: 1937920 | consumed tokens: 3968860160 | elapsed time per iteration (s): 0.49 | learning rate: 6.457E-05 | global batch size: 256 | lm loss: 3.009362E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.918 | TFLOPs: 34.33 | +7: iteration 7580/ 11269 | consumed samples: 1940480 | consumed tokens: 3974103040 | elapsed time per iteration (s): 0.47 | learning rate: 6.435E-05 | global batch size: 256 | lm loss: 3.004095E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 539.737 | TFLOPs: 35.30 | +7: iteration 7590/ 11269 | consumed samples: 1943040 | consumed tokens: 3979345920 | elapsed time per iteration (s): 0.48 | learning rate: 6.413E-05 | global batch size: 256 | lm loss: 2.991517E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.802 | TFLOPs: 35.04 | +7: iteration 7600/ 11269 | consumed samples: 1945600 | consumed tokens: 3984588800 | elapsed time per iteration (s): 0.49 | learning rate: 6.391E-05 | global batch size: 256 | lm loss: 2.977418E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.909 | TFLOPs: 34.26 | +7: iteration 7610/ 11269 | consumed samples: 1948160 | consumed tokens: 3989831680 | elapsed time per iteration (s): 0.48 | learning rate: 6.370E-05 | global batch size: 256 | lm loss: 3.012438E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.687 | TFLOPs: 35.10 | +7: iteration 7620/ 11269 | consumed samples: 1950720 | consumed tokens: 3995074560 | elapsed time per iteration (s): 0.48 | learning rate: 6.348E-05 | global batch size: 256 | lm loss: 2.994912E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.573 | TFLOPs: 35.03 | +7: iteration 7630/ 11269 | consumed samples: 1953280 | consumed tokens: 4000317440 | elapsed time per iteration (s): 0.48 | learning rate: 6.326E-05 | global batch size: 256 | lm loss: 3.001226E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.327 | TFLOPs: 34.81 | +7: iteration 7640/ 11269 | consumed samples: 1955840 | consumed tokens: 4005560320 | elapsed time per iteration (s): 0.47 | learning rate: 6.305E-05 | global batch size: 256 | lm loss: 2.999415E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 539.954 | TFLOPs: 35.31 | +7: iteration 7650/ 11269 | consumed samples: 1958400 | consumed tokens: 4010803200 | elapsed time per iteration (s): 0.48 | learning rate: 6.283E-05 | global batch size: 256 | lm loss: 3.013126E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.520 | TFLOPs: 34.83 | +7: iteration 7660/ 11269 | consumed samples: 1960960 | consumed tokens: 4016046080 | elapsed time per iteration (s): 0.48 | learning rate: 6.261E-05 | global batch size: 256 | lm loss: 3.021244E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.001 | TFLOPs: 34.66 | +7: iteration 7670/ 11269 | consumed samples: 1963520 | consumed tokens: 4021288960 | elapsed time per iteration (s): 0.48 | learning rate: 6.240E-05 | global batch size: 256 | lm loss: 3.017241E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.257 | TFLOPs: 35.07 | +7: iteration 7680/ 11269 | consumed samples: 1966080 | consumed tokens: 4026531840 | elapsed time per iteration (s): 0.50 | learning rate: 6.218E-05 | global batch size: 256 | lm loss: 2.987546E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 515.096 | TFLOPs: 33.69 | +7: iteration 7690/ 11269 | consumed samples: 1968640 | consumed tokens: 4031774720 | elapsed time per iteration (s): 0.53 | learning rate: 6.197E-05 | global batch size: 256 | lm loss: 2.970198E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 485.038 | TFLOPs: 31.72 | +7: iteration 7700/ 11269 | consumed samples: 1971200 | consumed tokens: 4037017600 | elapsed time per iteration (s): 0.48 | learning rate: 6.175E-05 | global batch size: 256 | lm loss: 2.995350E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.020 | TFLOPs: 34.66 | +7: iteration 7710/ 11269 | consumed samples: 1973760 | consumed tokens: 4042260480 | elapsed time per iteration (s): 0.49 | learning rate: 6.154E-05 | global batch size: 256 | lm loss: 2.991755E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.038 | TFLOPs: 33.88 | +7: iteration 7720/ 11269 | consumed samples: 1976320 | consumed tokens: 4047503360 | elapsed time per iteration (s): 0.50 | learning rate: 6.133E-05 | global batch size: 256 | lm loss: 2.983722E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 513.639 | TFLOPs: 33.59 | +7: iteration 7730/ 11269 | consumed samples: 1978880 | consumed tokens: 4052746240 | elapsed time per iteration (s): 0.55 | learning rate: 6.111E-05 | global batch size: 256 | lm loss: 3.001809E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 467.888 | TFLOPs: 30.60 | +7: iteration 7740/ 11269 | consumed samples: 1981440 | consumed tokens: 4057989120 | elapsed time per iteration (s): 0.48 | learning rate: 6.090E-05 | global batch size: 256 | lm loss: 3.004176E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.209 | TFLOPs: 34.61 | +7: iteration 7750/ 11269 | consumed samples: 1984000 | consumed tokens: 4063232000 | elapsed time per iteration (s): 0.62 | learning rate: 6.069E-05 | global batch size: 256 | lm loss: 2.990205E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 409.989 | TFLOPs: 26.81 | +7: iteration 7760/ 11269 | consumed samples: 1986560 | consumed tokens: 4068474880 | elapsed time per iteration (s): 0.50 | learning rate: 6.048E-05 | global batch size: 256 | lm loss: 2.990937E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 508.862 | TFLOPs: 33.28 | +7: iteration 7770/ 11269 | consumed samples: 1989120 | consumed tokens: 4073717760 | elapsed time per iteration (s): 0.63 | learning rate: 6.027E-05 | global batch size: 256 | lm loss: 2.964997E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 407.022 | TFLOPs: 26.62 | +7: iteration 7780/ 11269 | consumed samples: 1991680 | consumed tokens: 4078960640 | elapsed time per iteration (s): 0.48 | learning rate: 6.006E-05 | global batch size: 256 | lm loss: 2.979988E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.854 | TFLOPs: 34.72 | +7: iteration 7790/ 11269 | consumed samples: 1994240 | consumed tokens: 4084203520 | elapsed time per iteration (s): 0.48 | learning rate: 5.984E-05 | global batch size: 256 | lm loss: 2.985297E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.408 | TFLOPs: 34.62 | +7: iteration 7800/ 11269 | consumed samples: 1996800 | consumed tokens: 4089446400 | elapsed time per iteration (s): 0.48 | learning rate: 5.963E-05 | global batch size: 256 | lm loss: 3.001847E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.827 | TFLOPs: 34.85 | +7: iteration 7810/ 11269 | consumed samples: 1999360 | consumed tokens: 4094689280 | elapsed time per iteration (s): 0.48 | learning rate: 5.942E-05 | global batch size: 256 | lm loss: 2.959864E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.357 | TFLOPs: 34.88 | +7: iteration 7820/ 11269 | consumed samples: 2001920 | consumed tokens: 4099932160 | elapsed time per iteration (s): 0.48 | learning rate: 5.922E-05 | global batch size: 256 | lm loss: 3.006787E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.495 | TFLOPs: 34.56 | +7: iteration 7830/ 11269 | consumed samples: 2004480 | consumed tokens: 4105175040 | elapsed time per iteration (s): 0.49 | learning rate: 5.901E-05 | global batch size: 256 | lm loss: 2.989177E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.784 | TFLOPs: 34.45 | +7: iteration 7840/ 11269 | consumed samples: 2007040 | consumed tokens: 4110417920 | elapsed time per iteration (s): 0.50 | learning rate: 5.880E-05 | global batch size: 256 | lm loss: 2.994634E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 516.663 | TFLOPs: 33.79 | +7: iteration 7850/ 11269 | consumed samples: 2009600 | consumed tokens: 4115660800 | elapsed time per iteration (s): 0.48 | learning rate: 5.859E-05 | global batch size: 256 | lm loss: 3.016131E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.194 | TFLOPs: 34.81 | +7: iteration 7860/ 11269 | consumed samples: 2012160 | consumed tokens: 4120903680 | elapsed time per iteration (s): 0.49 | learning rate: 5.838E-05 | global batch size: 256 | lm loss: 2.997942E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.147 | TFLOPs: 34.34 | +7: iteration 7870/ 11269 | consumed samples: 2014720 | consumed tokens: 4126146560 | elapsed time per iteration (s): 0.48 | learning rate: 5.817E-05 | global batch size: 256 | lm loss: 2.961773E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.288 | TFLOPs: 34.55 | +7: iteration 7880/ 11269 | consumed samples: 2017280 | consumed tokens: 4131389440 | elapsed time per iteration (s): 0.49 | learning rate: 5.797E-05 | global batch size: 256 | lm loss: 2.994559E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.063 | TFLOPs: 34.34 | +7: iteration 7890/ 11269 | consumed samples: 2019840 | consumed tokens: 4136632320 | elapsed time per iteration (s): 0.48 | learning rate: 5.776E-05 | global batch size: 256 | lm loss: 3.005396E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.824 | TFLOPs: 34.58 | +7: iteration 7900/ 11269 | consumed samples: 2022400 | consumed tokens: 4141875200 | elapsed time per iteration (s): 0.52 | learning rate: 5.755E-05 | global batch size: 256 | lm loss: 2.962813E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 489.020 | TFLOPs: 31.98 | +7: iteration 7910/ 11269 | consumed samples: 2024960 | consumed tokens: 4147118080 | elapsed time per iteration (s): 0.48 | learning rate: 5.735E-05 | global batch size: 256 | lm loss: 3.018574E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.161 | TFLOPs: 34.80 | +7: iteration 7920/ 11269 | consumed samples: 2027520 | consumed tokens: 4152360960 | elapsed time per iteration (s): 0.48 | learning rate: 5.714E-05 | global batch size: 256 | lm loss: 2.957793E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.663 | TFLOPs: 34.57 | +7: iteration 7930/ 11269 | consumed samples: 2030080 | consumed tokens: 4157603840 | elapsed time per iteration (s): 0.49 | learning rate: 5.694E-05 | global batch size: 256 | lm loss: 2.976242E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.919 | TFLOPs: 34.07 | +7: iteration 7940/ 11269 | consumed samples: 2032640 | consumed tokens: 4162846720 | elapsed time per iteration (s): 0.48 | learning rate: 5.673E-05 | global batch size: 256 | lm loss: 2.984461E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.687 | TFLOPs: 35.10 | +7: iteration 7950/ 11269 | consumed samples: 2035200 | consumed tokens: 4168089600 | elapsed time per iteration (s): 0.48 | learning rate: 5.653E-05 | global batch size: 256 | lm loss: 2.994479E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.812 | TFLOPs: 34.58 | +7: iteration 7960/ 11269 | consumed samples: 2037760 | consumed tokens: 4173332480 | elapsed time per iteration (s): 0.50 | learning rate: 5.633E-05 | global batch size: 256 | lm loss: 2.992779E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 511.535 | TFLOPs: 33.45 | +7: iteration 7970/ 11269 | consumed samples: 2040320 | consumed tokens: 4178575360 | elapsed time per iteration (s): 0.48 | learning rate: 5.612E-05 | global batch size: 256 | lm loss: 3.004975E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.351 | TFLOPs: 34.62 | +7: iteration 7980/ 11269 | consumed samples: 2042880 | consumed tokens: 4183818240 | elapsed time per iteration (s): 0.49 | learning rate: 5.592E-05 | global batch size: 256 | lm loss: 2.985022E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.011 | TFLOPs: 34.20 | +7: iteration 7990/ 11269 | consumed samples: 2045440 | consumed tokens: 4189061120 | elapsed time per iteration (s): 0.50 | learning rate: 5.572E-05 | global batch size: 256 | lm loss: 2.992132E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 514.035 | TFLOPs: 33.62 | +0: [2022-11-29 17:57:55,865] [INFO] [logging.py:68:log_dist] [Rank 0] step=8000, skipped=0, lr=[5.551588445114958e-05, 5.551588445114958e-05, 5.551588445114958e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +0: steps: 8000 loss: 2.9897 iter time (s): 0.482 samples/sec: 530.622 +7: iteration 8000/ 11269 | consumed samples: 2048000 | consumed tokens: 4194304000 | elapsed time per iteration (s): 0.49 | learning rate: 5.552E-05 | global batch size: 256 | lm loss: 2.966776E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.276 | TFLOPs: 34.16 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 8000 | lm loss value: 3.019589E+00 | lm loss PPL: 2.048288E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 8000 to checkpoints_280moscar +0: [2022-11-29 17:57:56,142] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step8000 is begin to save! +0: [2022-11-29 17:57:56,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:57:56,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:57:56,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:57:56,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:57:56,612] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:57:56,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:57:56,638] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:57:56,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:57:56,663] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:57:56,688] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:57:56,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:57:56,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:57:56,714] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:57:56,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:57:56,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:57:56,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:57:56,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:57:56,875] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:57:56,875] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:57:56,900] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:57:56,901] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:57:56,926] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:57:56,926] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:57:56,951] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:57:56,951] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:57:56,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:57:56,977] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:57:57,002] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:57:57,002] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:57:57,027] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:57:57,028] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:57:57,053] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:57:57,053] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/layer_18-model_00-model_states.pt... +0: [2022-11-29 17:57:57,078] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/layer_18-model_00-model_states.pt. +0: [2022-11-29 17:57:57,078] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:57:57,103] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:57:57,103] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/layer_20-model_00-model_states.pt... +0: [2022-11-29 17:57:57,128] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/layer_20-model_00-model_states.pt. +0: [2022-11-29 17:57:57,128] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/layer_22-model_00-model_states.pt... +0: [2022-11-29 17:57:57,129] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/layer_22-model_00-model_states.pt. +0: [2022-11-29 17:57:57,130] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_280moscar/global_step8000/mp_rank_00_model_states.pt +0: [2022-11-29 17:57:57,130] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:57:57,152] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:57:57,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:57:57,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:57:57,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:57:57,234] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:57:57,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 17:57:57,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:57:57,238] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:57:57,238] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:57:57,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:57:57,238] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:57:57,238] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 17:57:57,239] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:57:57,239] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:57:57,239] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 17:57:57,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:57:57,241] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:57:57,241] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 17:57:57,243] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:57:57,243] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:57:57,243] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 17:57:57,243] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:57:57,243] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:57:57,243] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:57:57,243] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:57:57,243] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:57:57,243] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:57:57,243] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:57:57,244] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:57:57,244] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:57:57,244] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:57:57,244] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:57:57,244] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 17:57:57,245] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:57:57,245] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:57:57,245] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:57:57,247] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:57:57,247] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:57:57,247] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:57:57,246] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:57:57,246] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:57:57,246] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:57:57,246] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:57:57,246] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:57:57,246] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:57:57,246] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:57:57,246] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:57:57,246] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +5: [2022-11-29 17:57:57,247] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:57:57,246] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:57:57,246] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:57:57,246] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:57:57,247] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:57:57,247] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +3: [2022-11-29 17:57:57,247] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:57:57,247] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:57:57,247] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:57:57,247] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:57:57,247] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:57:57,247] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +5: [2022-11-29 17:57:57,247] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:57:57,247] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:57:57,247] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:57:57,247] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:57:57,247] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:57:57,247] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 17:57:57,247] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:57:57,247] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:57:57,247] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:57:57,248] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:57:57,248] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 17:57:57,248] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:57:57,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:57:57,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:57:57,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:57:57,251] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:57:57,251] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:57:57,251] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:57:57,251] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:57:57,251] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:57:57,251] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:57:57,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:57:57,251] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:57:57,251] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 17:57:57,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:57:57,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:57:57,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:57:57,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:57:57,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:57:57,253] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:57:57,253] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:57:57,253] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:57:57,253] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:57:57,253] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:57:57,253] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 17:57:57,253] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 17:57:57,253] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 17:57:57,253] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 17:57:57,253] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:57:57,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:57:57,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:57:57,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:57:57,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:57:57,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:57:57,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:57:57,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:57:57,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +5: [2022-11-29 17:57:57,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:57:57,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:57:57,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:57:57,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:57:57,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:57:57,241] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:57:57,241] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:57:57,244] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:57:57,244] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:57:57,244] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:57:57,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:57:57,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:57:57,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:57:57,257] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:57:57,257] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:57:57,257] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:57:57,257] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:57:57,257] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:57:57,257] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:57:57,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:57:57,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:57:57,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:57:57,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:57:57,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:57:57,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:57:57,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:57:57,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:57:57,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:57:57,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:57:57,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:57:57,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:57:57,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +2: [2022-11-29 17:57:57,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +1: [2022-11-29 17:57:57,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:57:57,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:57:57,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:57:57,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:57:57,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +2: [2022-11-29 17:57:57,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:57:57,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:57:57,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +2: [2022-11-29 17:57:57,259] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:57:57,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:57:57,259] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +1: [2022-11-29 17:57:57,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:57:57,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:57:57,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:57:57,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:57:57,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:57:57,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:57:57,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:57:57,259] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:57:57,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:57:57,280] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:57:57,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:57:57,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:57:57,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:57:57,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:57:57,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:57:57,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:57:57,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:57:57,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:57:57,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 17:57:57,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:57:57,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:57:57,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:57:57,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:57:57,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:57:57,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:57:57,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:57:57,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:57:57,368] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:57:57,368] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:57:57,368] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:57:57,368] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:57:57,368] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:57:57,368] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:57:57,368] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:57:57,368] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step8000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:57:57,368] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 17:57:57,368] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 17:57:57,368] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 17:57:57,368] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 17:57:57,368] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 17:57:57,368] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 17:57:57,368] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 17:57:57,368] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: successfully saved checkpoint at iteration 8000 to checkpoints_280moscar +7: time (ms) | save-checkpoint: 1289.80 +7: iteration 8010/ 11269 | consumed samples: 2050560 | consumed tokens: 4199546880 | elapsed time per iteration (s): 0.63 | learning rate: 5.531E-05 | global batch size: 256 | lm loss: 2.981132E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 407.941 | TFLOPs: 26.68 | +7: iteration 8020/ 11269 | consumed samples: 2053120 | consumed tokens: 4204789760 | elapsed time per iteration (s): 0.49 | learning rate: 5.511E-05 | global batch size: 256 | lm loss: 2.976128E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.443 | TFLOPs: 34.23 | +7: iteration 8030/ 11269 | consumed samples: 2055680 | consumed tokens: 4210032640 | elapsed time per iteration (s): 0.48 | learning rate: 5.491E-05 | global batch size: 256 | lm loss: 2.974393E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.545 | TFLOPs: 35.16 | +7: iteration 8040/ 11269 | consumed samples: 2058240 | consumed tokens: 4215275520 | elapsed time per iteration (s): 0.49 | learning rate: 5.471E-05 | global batch size: 256 | lm loss: 2.986502E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.131 | TFLOPs: 34.47 | +7: iteration 8050/ 11269 | consumed samples: 2060800 | consumed tokens: 4220518400 | elapsed time per iteration (s): 0.48 | learning rate: 5.451E-05 | global batch size: 256 | lm loss: 2.992224E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.791 | TFLOPs: 34.91 | +7: iteration 8060/ 11269 | consumed samples: 2063360 | consumed tokens: 4225761280 | elapsed time per iteration (s): 0.48 | learning rate: 5.431E-05 | global batch size: 256 | lm loss: 2.986158E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.014 | TFLOPs: 34.73 | +7: iteration 8070/ 11269 | consumed samples: 2065920 | consumed tokens: 4231004160 | elapsed time per iteration (s): 0.48 | learning rate: 5.411E-05 | global batch size: 256 | lm loss: 3.023498E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.660 | TFLOPs: 34.57 | +7: iteration 8080/ 11269 | consumed samples: 2068480 | consumed tokens: 4236247040 | elapsed time per iteration (s): 0.48 | learning rate: 5.392E-05 | global batch size: 256 | lm loss: 2.968235E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 538.110 | TFLOPs: 35.19 | +7: iteration 8090/ 11269 | consumed samples: 2071040 | consumed tokens: 4241489920 | elapsed time per iteration (s): 0.49 | learning rate: 5.372E-05 | global batch size: 256 | lm loss: 2.960740E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.438 | TFLOPs: 34.43 | +7: iteration 8100/ 11269 | consumed samples: 2073600 | consumed tokens: 4246732800 | elapsed time per iteration (s): 0.49 | learning rate: 5.352E-05 | global batch size: 256 | lm loss: 2.981493E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.968 | TFLOPs: 34.27 | +7: iteration 8110/ 11269 | consumed samples: 2076160 | consumed tokens: 4251975680 | elapsed time per iteration (s): 0.48 | learning rate: 5.332E-05 | global batch size: 256 | lm loss: 2.980529E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.812 | TFLOPs: 34.71 | +7: iteration 8120/ 11269 | consumed samples: 2078720 | consumed tokens: 4257218560 | elapsed time per iteration (s): 0.48 | learning rate: 5.313E-05 | global batch size: 256 | lm loss: 3.000121E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.298 | TFLOPs: 34.75 | +7: iteration 8130/ 11269 | consumed samples: 2081280 | consumed tokens: 4262461440 | elapsed time per iteration (s): 0.48 | learning rate: 5.293E-05 | global batch size: 256 | lm loss: 2.966172E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.109 | TFLOPs: 34.67 | +7: iteration 8140/ 11269 | consumed samples: 2083840 | consumed tokens: 4267704320 | elapsed time per iteration (s): 0.52 | learning rate: 5.273E-05 | global batch size: 256 | lm loss: 2.953363E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 495.636 | TFLOPs: 32.41 | +7: iteration 8150/ 11269 | consumed samples: 2086400 | consumed tokens: 4272947200 | elapsed time per iteration (s): 0.49 | learning rate: 5.254E-05 | global batch size: 256 | lm loss: 3.007117E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.812 | TFLOPs: 33.93 | +7: iteration 8160/ 11269 | consumed samples: 2088960 | consumed tokens: 4278190080 | elapsed time per iteration (s): 0.48 | learning rate: 5.234E-05 | global batch size: 256 | lm loss: 2.980535E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.769 | TFLOPs: 34.71 | +7: iteration 8170/ 11269 | consumed samples: 2091520 | consumed tokens: 4283432960 | elapsed time per iteration (s): 0.48 | learning rate: 5.215E-05 | global batch size: 256 | lm loss: 2.962632E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.361 | TFLOPs: 34.95 | +7: iteration 8180/ 11269 | consumed samples: 2094080 | consumed tokens: 4288675840 | elapsed time per iteration (s): 0.49 | learning rate: 5.196E-05 | global batch size: 256 | lm loss: 2.976201E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.383 | TFLOPs: 34.49 | +7: iteration 8190/ 11269 | consumed samples: 2096640 | consumed tokens: 4293918720 | elapsed time per iteration (s): 0.48 | learning rate: 5.176E-05 | global batch size: 256 | lm loss: 2.988081E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.642 | TFLOPs: 34.70 | +7: iteration 8200/ 11269 | consumed samples: 2099200 | consumed tokens: 4299161600 | elapsed time per iteration (s): 0.49 | learning rate: 5.157E-05 | global batch size: 256 | lm loss: 2.986716E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.399 | TFLOPs: 34.49 | +7: iteration 8210/ 11269 | consumed samples: 2101760 | consumed tokens: 4304404480 | elapsed time per iteration (s): 0.49 | learning rate: 5.138E-05 | global batch size: 256 | lm loss: 3.018667E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.395 | TFLOPs: 34.30 | +7: iteration 8220/ 11269 | consumed samples: 2104320 | consumed tokens: 4309647360 | elapsed time per iteration (s): 0.48 | learning rate: 5.119E-05 | global batch size: 256 | lm loss: 2.985399E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 538.153 | TFLOPs: 35.20 | +7: iteration 8230/ 11269 | consumed samples: 2106880 | consumed tokens: 4314890240 | elapsed time per iteration (s): 0.47 | learning rate: 5.099E-05 | global batch size: 256 | lm loss: 2.996389E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 541.029 | TFLOPs: 35.38 | +7: iteration 8240/ 11269 | consumed samples: 2109440 | consumed tokens: 4320133120 | elapsed time per iteration (s): 0.48 | learning rate: 5.080E-05 | global batch size: 256 | lm loss: 3.007089E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.828 | TFLOPs: 34.59 | +7: iteration 8250/ 11269 | consumed samples: 2112000 | consumed tokens: 4325376000 | elapsed time per iteration (s): 0.48 | learning rate: 5.061E-05 | global batch size: 256 | lm loss: 2.979893E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.779 | TFLOPs: 35.11 | +7: iteration 8260/ 11269 | consumed samples: 2114560 | consumed tokens: 4330618880 | elapsed time per iteration (s): 0.49 | learning rate: 5.042E-05 | global batch size: 256 | lm loss: 2.988453E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.517 | TFLOPs: 34.37 | +7: iteration 8270/ 11269 | consumed samples: 2117120 | consumed tokens: 4335861760 | elapsed time per iteration (s): 0.49 | learning rate: 5.023E-05 | global batch size: 256 | lm loss: 2.989503E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.670 | TFLOPs: 34.31 | +7: iteration 8280/ 11269 | consumed samples: 2119680 | consumed tokens: 4341104640 | elapsed time per iteration (s): 0.50 | learning rate: 5.004E-05 | global batch size: 256 | lm loss: 3.008477E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 511.910 | TFLOPs: 33.48 | +7: iteration 8290/ 11269 | consumed samples: 2122240 | consumed tokens: 4346347520 | elapsed time per iteration (s): 0.52 | learning rate: 4.985E-05 | global batch size: 256 | lm loss: 3.002016E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 491.227 | TFLOPs: 32.13 | +7: iteration 8300/ 11269 | consumed samples: 2124800 | consumed tokens: 4351590400 | elapsed time per iteration (s): 0.50 | learning rate: 4.967E-05 | global batch size: 256 | lm loss: 2.953207E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 511.850 | TFLOPs: 33.47 | +7: iteration 8310/ 11269 | consumed samples: 2127360 | consumed tokens: 4356833280 | elapsed time per iteration (s): 0.51 | learning rate: 4.948E-05 | global batch size: 256 | lm loss: 2.968270E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 502.459 | TFLOPs: 32.86 | +7: iteration 8320/ 11269 | consumed samples: 2129920 | consumed tokens: 4362076160 | elapsed time per iteration (s): 0.48 | learning rate: 4.929E-05 | global batch size: 256 | lm loss: 2.981281E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.384 | TFLOPs: 35.14 | +7: iteration 8330/ 11269 | consumed samples: 2132480 | consumed tokens: 4367319040 | elapsed time per iteration (s): 0.48 | learning rate: 4.910E-05 | global batch size: 256 | lm loss: 2.970050E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.308 | TFLOPs: 34.68 | +7: iteration 8340/ 11269 | consumed samples: 2135040 | consumed tokens: 4372561920 | elapsed time per iteration (s): 0.47 | learning rate: 4.892E-05 | global batch size: 256 | lm loss: 2.977054E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 541.561 | TFLOPs: 35.42 | +7: iteration 8350/ 11269 | consumed samples: 2137600 | consumed tokens: 4377804800 | elapsed time per iteration (s): 0.48 | learning rate: 4.873E-05 | global batch size: 256 | lm loss: 2.977229E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.289 | TFLOPs: 34.88 | +7: iteration 8360/ 11269 | consumed samples: 2140160 | consumed tokens: 4383047680 | elapsed time per iteration (s): 0.48 | learning rate: 4.855E-05 | global batch size: 256 | lm loss: 2.994799E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.669 | TFLOPs: 35.10 | +7: iteration 8370/ 11269 | consumed samples: 2142720 | consumed tokens: 4388290560 | elapsed time per iteration (s): 0.47 | learning rate: 4.836E-05 | global batch size: 256 | lm loss: 2.976890E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 539.597 | TFLOPs: 35.29 | +7: iteration 8380/ 11269 | consumed samples: 2145280 | consumed tokens: 4393533440 | elapsed time per iteration (s): 0.48 | learning rate: 4.818E-05 | global batch size: 256 | lm loss: 2.969186E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.207 | TFLOPs: 34.94 | +7: iteration 8390/ 11269 | consumed samples: 2147840 | consumed tokens: 4398776320 | elapsed time per iteration (s): 0.47 | learning rate: 4.799E-05 | global batch size: 256 | lm loss: 2.995726E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 539.617 | TFLOPs: 35.29 | +7: iteration 8400/ 11269 | consumed samples: 2150400 | consumed tokens: 4404019200 | elapsed time per iteration (s): 1.00 | learning rate: 4.781E-05 | global batch size: 256 | lm loss: 2.956376E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 256.693 | TFLOPs: 16.79 | +7: iteration 8410/ 11269 | consumed samples: 2152960 | consumed tokens: 4409262080 | elapsed time per iteration (s): 0.49 | learning rate: 4.763E-05 | global batch size: 256 | lm loss: 2.972665E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.367 | TFLOPs: 34.36 | +7: iteration 8420/ 11269 | consumed samples: 2155520 | consumed tokens: 4414504960 | elapsed time per iteration (s): 0.49 | learning rate: 4.744E-05 | global batch size: 256 | lm loss: 2.980226E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.549 | TFLOPs: 34.50 | +7: iteration 8430/ 11269 | consumed samples: 2158080 | consumed tokens: 4419747840 | elapsed time per iteration (s): 0.48 | learning rate: 4.726E-05 | global batch size: 256 | lm loss: 2.966893E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 538.385 | TFLOPs: 35.21 | +7: iteration 8440/ 11269 | consumed samples: 2160640 | consumed tokens: 4424990720 | elapsed time per iteration (s): 0.48 | learning rate: 4.708E-05 | global batch size: 256 | lm loss: 2.967156E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.773 | TFLOPs: 34.78 | +7: iteration 8450/ 11269 | consumed samples: 2163200 | consumed tokens: 4430233600 | elapsed time per iteration (s): 0.48 | learning rate: 4.690E-05 | global batch size: 256 | lm loss: 2.970160E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.381 | TFLOPs: 35.14 | +7: iteration 8460/ 11269 | consumed samples: 2165760 | consumed tokens: 4435476480 | elapsed time per iteration (s): 0.48 | learning rate: 4.672E-05 | global batch size: 256 | lm loss: 2.986608E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.883 | TFLOPs: 34.65 | +7: iteration 8470/ 11269 | consumed samples: 2168320 | consumed tokens: 4440719360 | elapsed time per iteration (s): 0.48 | learning rate: 4.654E-05 | global batch size: 256 | lm loss: 2.982518E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.195 | TFLOPs: 34.61 | +7: iteration 8480/ 11269 | consumed samples: 2170880 | consumed tokens: 4445962240 | elapsed time per iteration (s): 0.50 | learning rate: 4.636E-05 | global batch size: 256 | lm loss: 2.968833E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 507.626 | TFLOPs: 33.20 | +7: iteration 8490/ 11269 | consumed samples: 2173440 | consumed tokens: 4451205120 | elapsed time per iteration (s): 0.49 | learning rate: 4.618E-05 | global batch size: 256 | lm loss: 2.990524E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.711 | TFLOPs: 34.12 | +7: iteration 8500/ 11269 | consumed samples: 2176000 | consumed tokens: 4456448000 | elapsed time per iteration (s): 0.50 | learning rate: 4.600E-05 | global batch size: 256 | lm loss: 3.017323E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 515.429 | TFLOPs: 33.71 | +7: iteration 8510/ 11269 | consumed samples: 2178560 | consumed tokens: 4461690880 | elapsed time per iteration (s): 0.49 | learning rate: 4.582E-05 | global batch size: 256 | lm loss: 2.984216E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.028 | TFLOPs: 34.27 | +7: iteration 8520/ 11269 | consumed samples: 2181120 | consumed tokens: 4466933760 | elapsed time per iteration (s): 0.48 | learning rate: 4.565E-05 | global batch size: 256 | lm loss: 2.975901E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.953 | TFLOPs: 35.12 | +7: iteration 8530/ 11269 | consumed samples: 2183680 | consumed tokens: 4472176640 | elapsed time per iteration (s): 0.48 | learning rate: 4.547E-05 | global batch size: 256 | lm loss: 2.990956E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.741 | TFLOPs: 35.04 | +7: iteration 8540/ 11269 | consumed samples: 2186240 | consumed tokens: 4477419520 | elapsed time per iteration (s): 0.47 | learning rate: 4.529E-05 | global batch size: 256 | lm loss: 2.974085E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 541.397 | TFLOPs: 35.41 | +7: iteration 8550/ 11269 | consumed samples: 2188800 | consumed tokens: 4482662400 | elapsed time per iteration (s): 0.48 | learning rate: 4.512E-05 | global batch size: 256 | lm loss: 2.982958E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.228 | TFLOPs: 34.61 | +7: iteration 8560/ 11269 | consumed samples: 2191360 | consumed tokens: 4487905280 | elapsed time per iteration (s): 0.48 | learning rate: 4.494E-05 | global batch size: 256 | lm loss: 2.953322E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.931 | TFLOPs: 35.18 | +7: iteration 8570/ 11269 | consumed samples: 2193920 | consumed tokens: 4493148160 | elapsed time per iteration (s): 0.52 | learning rate: 4.477E-05 | global batch size: 256 | lm loss: 2.981657E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 495.187 | TFLOPs: 32.39 | +7: iteration 8580/ 11269 | consumed samples: 2196480 | consumed tokens: 4498391040 | elapsed time per iteration (s): 0.49 | learning rate: 4.459E-05 | global batch size: 256 | lm loss: 2.946248E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.555 | TFLOPs: 34.11 | +7: iteration 8590/ 11269 | consumed samples: 2199040 | consumed tokens: 4503633920 | elapsed time per iteration (s): 0.60 | learning rate: 4.442E-05 | global batch size: 256 | lm loss: 2.985984E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 425.145 | TFLOPs: 27.80 | +7: iteration 8600/ 11269 | consumed samples: 2201600 | consumed tokens: 4508876800 | elapsed time per iteration (s): 0.53 | learning rate: 4.425E-05 | global batch size: 256 | lm loss: 2.950692E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 482.012 | TFLOPs: 31.52 | +7: iteration 8610/ 11269 | consumed samples: 2204160 | consumed tokens: 4514119680 | elapsed time per iteration (s): 0.51 | learning rate: 4.407E-05 | global batch size: 256 | lm loss: 2.964858E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 505.083 | TFLOPs: 33.03 | +7: iteration 8620/ 11269 | consumed samples: 2206720 | consumed tokens: 4519362560 | elapsed time per iteration (s): 0.48 | learning rate: 4.390E-05 | global batch size: 256 | lm loss: 2.948545E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.319 | TFLOPs: 35.08 | +7: iteration 8630/ 11269 | consumed samples: 2209280 | consumed tokens: 4524605440 | elapsed time per iteration (s): 0.48 | learning rate: 4.373E-05 | global batch size: 256 | lm loss: 3.008340E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.800 | TFLOPs: 35.04 | +7: iteration 8640/ 11269 | consumed samples: 2211840 | consumed tokens: 4529848320 | elapsed time per iteration (s): 0.48 | learning rate: 4.356E-05 | global batch size: 256 | lm loss: 3.015373E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.600 | TFLOPs: 34.96 | +7: iteration 8650/ 11269 | consumed samples: 2214400 | consumed tokens: 4535091200 | elapsed time per iteration (s): 0.49 | learning rate: 4.339E-05 | global batch size: 256 | lm loss: 2.961931E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.433 | TFLOPs: 34.36 | +7: iteration 8660/ 11269 | consumed samples: 2216960 | consumed tokens: 4540334080 | elapsed time per iteration (s): 0.48 | learning rate: 4.322E-05 | global batch size: 256 | lm loss: 2.960880E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.706 | TFLOPs: 35.03 | +7: iteration 8670/ 11269 | consumed samples: 2219520 | consumed tokens: 4545576960 | elapsed time per iteration (s): 0.49 | learning rate: 4.305E-05 | global batch size: 256 | lm loss: 2.980735E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.090 | TFLOPs: 34.28 | +7: iteration 8680/ 11269 | consumed samples: 2222080 | consumed tokens: 4550819840 | elapsed time per iteration (s): 0.49 | learning rate: 4.288E-05 | global batch size: 256 | lm loss: 2.948911E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.619 | TFLOPs: 34.18 | +7: iteration 8690/ 11269 | consumed samples: 2224640 | consumed tokens: 4556062720 | elapsed time per iteration (s): 0.50 | learning rate: 4.271E-05 | global batch size: 256 | lm loss: 2.942383E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 515.355 | TFLOPs: 33.70 | +7: iteration 8700/ 11269 | consumed samples: 2227200 | consumed tokens: 4561305600 | elapsed time per iteration (s): 0.49 | learning rate: 4.254E-05 | global batch size: 256 | lm loss: 2.989683E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.768 | TFLOPs: 33.86 | +7: iteration 8710/ 11269 | consumed samples: 2229760 | consumed tokens: 4566548480 | elapsed time per iteration (s): 0.49 | learning rate: 4.237E-05 | global batch size: 256 | lm loss: 2.985198E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.616 | TFLOPs: 34.38 | +7: iteration 8720/ 11269 | consumed samples: 2232320 | consumed tokens: 4571791360 | elapsed time per iteration (s): 0.48 | learning rate: 4.221E-05 | global batch size: 256 | lm loss: 2.957963E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.637 | TFLOPs: 34.77 | +7: iteration 8730/ 11269 | consumed samples: 2234880 | consumed tokens: 4577034240 | elapsed time per iteration (s): 0.48 | learning rate: 4.204E-05 | global batch size: 256 | lm loss: 2.976958E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.420 | TFLOPs: 34.62 | +7: iteration 8740/ 11269 | consumed samples: 2237440 | consumed tokens: 4582277120 | elapsed time per iteration (s): 0.48 | learning rate: 4.188E-05 | global batch size: 256 | lm loss: 2.973350E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.100 | TFLOPs: 35.06 | +7: iteration 8750/ 11269 | consumed samples: 2240000 | consumed tokens: 4587520000 | elapsed time per iteration (s): 0.48 | learning rate: 4.171E-05 | global batch size: 256 | lm loss: 2.954576E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.324 | TFLOPs: 34.75 | +7: iteration 8760/ 11269 | consumed samples: 2242560 | consumed tokens: 4592762880 | elapsed time per iteration (s): 0.48 | learning rate: 4.154E-05 | global batch size: 256 | lm loss: 2.959223E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.636 | TFLOPs: 35.03 | +7: iteration 8770/ 11269 | consumed samples: 2245120 | consumed tokens: 4598005760 | elapsed time per iteration (s): 0.59 | learning rate: 4.138E-05 | global batch size: 256 | lm loss: 2.968824E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.375 | TFLOPs: 28.28 | +7: iteration 8780/ 11269 | consumed samples: 2247680 | consumed tokens: 4603248640 | elapsed time per iteration (s): 0.54 | learning rate: 4.122E-05 | global batch size: 256 | lm loss: 2.985784E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 472.269 | TFLOPs: 30.89 | +7: iteration 8790/ 11269 | consumed samples: 2250240 | consumed tokens: 4608491520 | elapsed time per iteration (s): 0.53 | learning rate: 4.105E-05 | global batch size: 256 | lm loss: 2.983135E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 485.119 | TFLOPs: 31.73 | +7: iteration 8800/ 11269 | consumed samples: 2252800 | consumed tokens: 4613734400 | elapsed time per iteration (s): 0.48 | learning rate: 4.089E-05 | global batch size: 256 | lm loss: 2.967547E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.969 | TFLOPs: 34.79 | +7: iteration 8810/ 11269 | consumed samples: 2255360 | consumed tokens: 4618977280 | elapsed time per iteration (s): 0.48 | learning rate: 4.073E-05 | global batch size: 256 | lm loss: 2.969740E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.457 | TFLOPs: 34.89 | +7: iteration 8820/ 11269 | consumed samples: 2257920 | consumed tokens: 4624220160 | elapsed time per iteration (s): 0.48 | learning rate: 4.057E-05 | global batch size: 256 | lm loss: 2.961281E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.601 | TFLOPs: 34.70 | +7: iteration 8830/ 11269 | consumed samples: 2260480 | consumed tokens: 4629463040 | elapsed time per iteration (s): 0.49 | learning rate: 4.041E-05 | global batch size: 256 | lm loss: 2.974414E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.435 | TFLOPs: 34.49 | +7: iteration 8840/ 11269 | consumed samples: 2263040 | consumed tokens: 4634705920 | elapsed time per iteration (s): 0.49 | learning rate: 4.025E-05 | global batch size: 256 | lm loss: 2.966874E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.124 | TFLOPs: 34.47 | +7: iteration 8850/ 11269 | consumed samples: 2265600 | consumed tokens: 4639948800 | elapsed time per iteration (s): 0.53 | learning rate: 4.009E-05 | global batch size: 256 | lm loss: 2.991764E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 484.892 | TFLOPs: 31.71 | +7: iteration 8860/ 11269 | consumed samples: 2268160 | consumed tokens: 4645191680 | elapsed time per iteration (s): 0.48 | learning rate: 3.993E-05 | global batch size: 256 | lm loss: 2.965109E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.882 | TFLOPs: 34.59 | +7: iteration 8870/ 11269 | consumed samples: 2270720 | consumed tokens: 4650434560 | elapsed time per iteration (s): 0.49 | learning rate: 3.977E-05 | global batch size: 256 | lm loss: 2.984915E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.872 | TFLOPs: 34.46 | +7: iteration 8880/ 11269 | consumed samples: 2273280 | consumed tokens: 4655677440 | elapsed time per iteration (s): 0.49 | learning rate: 3.961E-05 | global batch size: 256 | lm loss: 2.968619E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.043 | TFLOPs: 34.27 | +7: iteration 8890/ 11269 | consumed samples: 2275840 | consumed tokens: 4660920320 | elapsed time per iteration (s): 0.49 | learning rate: 3.945E-05 | global batch size: 256 | lm loss: 2.980545E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.839 | TFLOPs: 34.39 | +7: iteration 8900/ 11269 | consumed samples: 2278400 | consumed tokens: 4666163200 | elapsed time per iteration (s): 0.48 | learning rate: 3.930E-05 | global batch size: 256 | lm loss: 2.967694E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.511 | TFLOPs: 34.56 | +7: iteration 8910/ 11269 | consumed samples: 2280960 | consumed tokens: 4671406080 | elapsed time per iteration (s): 0.49 | learning rate: 3.914E-05 | global batch size: 256 | lm loss: 2.986803E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.129 | TFLOPs: 34.15 | +7: iteration 8920/ 11269 | consumed samples: 2283520 | consumed tokens: 4676648960 | elapsed time per iteration (s): 0.49 | learning rate: 3.898E-05 | global batch size: 256 | lm loss: 2.964342E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.789 | TFLOPs: 34.39 | +7: iteration 8930/ 11269 | consumed samples: 2286080 | consumed tokens: 4681891840 | elapsed time per iteration (s): 0.49 | learning rate: 3.883E-05 | global batch size: 256 | lm loss: 2.977954E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.248 | TFLOPs: 34.15 | +7: iteration 8940/ 11269 | consumed samples: 2288640 | consumed tokens: 4687134720 | elapsed time per iteration (s): 0.48 | learning rate: 3.867E-05 | global batch size: 256 | lm loss: 2.976213E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.576 | TFLOPs: 34.57 | +7: iteration 8950/ 11269 | consumed samples: 2291200 | consumed tokens: 4692377600 | elapsed time per iteration (s): 0.48 | learning rate: 3.852E-05 | global batch size: 256 | lm loss: 2.962411E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.666 | TFLOPs: 34.84 | +7: iteration 8960/ 11269 | consumed samples: 2293760 | consumed tokens: 4697620480 | elapsed time per iteration (s): 0.48 | learning rate: 3.836E-05 | global batch size: 256 | lm loss: 2.972074E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.447 | TFLOPs: 35.02 | +7: iteration 8970/ 11269 | consumed samples: 2296320 | consumed tokens: 4702863360 | elapsed time per iteration (s): 0.48 | learning rate: 3.821E-05 | global batch size: 256 | lm loss: 2.976127E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.336 | TFLOPs: 34.68 | +7: iteration 8980/ 11269 | consumed samples: 2298880 | consumed tokens: 4708106240 | elapsed time per iteration (s): 0.84 | learning rate: 3.806E-05 | global batch size: 256 | lm loss: 2.941481E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 303.125 | TFLOPs: 19.82 | +7: iteration 8990/ 11269 | consumed samples: 2301440 | consumed tokens: 4713349120 | elapsed time per iteration (s): 0.48 | learning rate: 3.791E-05 | global batch size: 256 | lm loss: 2.971447E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.406 | TFLOPs: 34.69 | +7: iteration 9000/ 11269 | consumed samples: 2304000 | consumed tokens: 4718592000 | elapsed time per iteration (s): 0.49 | learning rate: 3.776E-05 | global batch size: 256 | lm loss: 2.987918E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.293 | TFLOPs: 34.16 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 9000 | lm loss value: 2.805341E+00 | lm loss PPL: 1.653272E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 9000 to checkpoints_280moscar +0: [2022-11-29 18:06:15,663] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step9000 is begin to save! +0: [2022-11-29 18:06:15,681] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:06:15,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:06:15,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:06:15,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:06:15,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:06:15,926] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:06:15,926] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:06:15,962] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:06:15,962] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:06:15,999] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:06:15,999] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:06:16,036] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:06:16,037] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:06:16,073] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:06:16,073] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:06:16,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:06:16,112] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:06:16,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:06:16,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:06:16,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:06:16,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:06:16,226] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:06:16,226] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/layer_13-model_00-model_states.pt... +0: [2022-11-29 18:06:16,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/layer_13-model_00-model_states.pt. +0: [2022-11-29 18:06:16,263] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:06:16,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:06:16,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/layer_15-model_00-model_states.pt... +0: [2022-11-29 18:06:16,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/layer_15-model_00-model_states.pt. +0: [2022-11-29 18:06:16,338] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/layer_16-model_00-model_states.pt... +0: [2022-11-29 18:06:16,377] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/layer_16-model_00-model_states.pt. +0: [2022-11-29 18:06:16,377] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/layer_17-model_00-model_states.pt... +0: [2022-11-29 18:06:16,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/layer_17-model_00-model_states.pt. +0: [2022-11-29 18:06:16,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/layer_18-model_00-model_states.pt... +0: [2022-11-29 18:06:16,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/layer_18-model_00-model_states.pt. +0: [2022-11-29 18:06:16,453] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/layer_19-model_00-model_states.pt... +0: [2022-11-29 18:06:16,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/layer_19-model_00-model_states.pt. +0: [2022-11-29 18:06:16,490] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/layer_20-model_00-model_states.pt... +0: [2022-11-29 18:06:16,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/layer_20-model_00-model_states.pt. +0: [2022-11-29 18:06:16,528] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/layer_22-model_00-model_states.pt... +0: [2022-11-29 18:06:16,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/layer_22-model_00-model_states.pt. +0: [2022-11-29 18:06:16,530] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_280moscar/global_step9000/mp_rank_00_model_states.pt +0: [2022-11-29 18:06:16,530] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:06:16,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:06:16,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:06:16,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:06:16,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:06:16,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 18:06:16,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:06:16,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:06:16,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:06:16,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 18:06:16,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:06:16,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 18:06:16,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:06:16,622] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:06:16,622] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 18:06:16,622] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:06:16,622] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:06:16,622] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:06:16,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 18:06:16,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:06:16,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:06:16,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 18:06:16,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:06:16,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 18:06:16,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:06:16,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:06:16,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:06:16,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:06:16,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:06:16,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:06:16,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:06:16,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:06:16,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:06:16,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 18:06:16,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 18:06:16,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 18:06:16,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 18:06:16,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:06:16,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:06:16,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 18:06:16,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:06:16,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:06:16,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 18:06:16,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:06:16,635] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:06:16,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 18:06:16,648] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:06:16,648] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:06:16,648] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 18:06:16,692] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:06:16,692] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 18:06:16,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:06:16,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:06:16,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 18:06:16,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:06:16,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:06:16,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 18:06:16,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:06:16,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:06:16,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:06:16,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:06:16,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:06:16,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 18:06:16,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 18:06:16,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:06:16,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 18:06:16,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:06:16,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:06:16,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:06:16,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 18:06:16,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:06:16,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 18:06:16,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:06:16,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:06:16,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:06:16,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:06:16,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:06:16,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 18:06:16,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:06:16,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:06:16,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:06:16,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 18:06:16,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:06:16,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:06:16,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:06:16,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:06:16,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:06:16,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:06:16,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:06:16,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:06:16,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 18:06:16,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 18:06:16,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:06:16,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:06:16,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:06:16,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:06:16,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:06:16,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:06:16,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:06:16,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:06:16,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:06:16,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:06:16,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:06:16,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:06:16,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:06:16,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 18:06:16,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:06:16,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 18:06:16,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:06:16,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 18:06:16,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 18:06:16,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:06:16,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 18:06:16,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 18:06:16,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 18:06:16,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 18:06:16,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:06:16,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:06:16,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:06:16,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:06:16,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:06:16,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:06:16,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:06:16,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:06:16,911] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:06:16,911] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:06:16,911] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:06:16,911] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:06:16,911] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:06:16,911] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:06:16,911] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:06:16,911] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 18:06:16,911] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 18:06:16,911] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 18:06:16,911] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 18:06:16,911] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 18:06:16,911] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:06:16,911] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 18:06:16,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 18:06:16,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 18:06:16,935] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:06:16,935] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:06:16,935] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:06:16,935] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:06:16,935] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:06:16,935] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:06:16,935] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:06:16,935] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:06:16,935] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:06:16,935] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:06:16,935] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:06:16,935] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:06:16,935] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:06:16,935] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:06:16,935] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:06:16,935] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step9000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:06:16,935] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 18:06:16,935] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 18:06:16,935] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 18:06:16,935] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 18:06:16,935] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 18:06:16,935] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 18:06:16,935] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 18:06:16,935] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: successfully saved checkpoint at iteration 9000 to checkpoints_280moscar +7: time (ms) | save-checkpoint: 1312.17 +7: iteration 9010/ 11269 | consumed samples: 2306560 | consumed tokens: 4723834880 | elapsed time per iteration (s): 0.63 | learning rate: 3.760E-05 | global batch size: 256 | lm loss: 2.965768E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 406.863 | TFLOPs: 26.61 | +7: iteration 9020/ 11269 | consumed samples: 2309120 | consumed tokens: 4729077760 | elapsed time per iteration (s): 0.48 | learning rate: 3.745E-05 | global batch size: 256 | lm loss: 2.955235E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.798 | TFLOPs: 34.78 | +7: iteration 9030/ 11269 | consumed samples: 2311680 | consumed tokens: 4734320640 | elapsed time per iteration (s): 0.49 | learning rate: 3.730E-05 | global batch size: 256 | lm loss: 2.960055E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.867 | TFLOPs: 34.33 | +7: iteration 9040/ 11269 | consumed samples: 2314240 | consumed tokens: 4739563520 | elapsed time per iteration (s): 0.50 | learning rate: 3.716E-05 | global batch size: 256 | lm loss: 2.943272E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 515.130 | TFLOPs: 33.69 | +7: iteration 9050/ 11269 | consumed samples: 2316800 | consumed tokens: 4744806400 | elapsed time per iteration (s): 0.48 | learning rate: 3.701E-05 | global batch size: 256 | lm loss: 2.955539E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.093 | TFLOPs: 35.06 | +7: iteration 9060/ 11269 | consumed samples: 2319360 | consumed tokens: 4750049280 | elapsed time per iteration (s): 0.49 | learning rate: 3.686E-05 | global batch size: 256 | lm loss: 2.936133E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 519.069 | TFLOPs: 33.95 | +7: iteration 9070/ 11269 | consumed samples: 2321920 | consumed tokens: 4755292160 | elapsed time per iteration (s): 0.48 | learning rate: 3.671E-05 | global batch size: 256 | lm loss: 2.965899E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.680 | TFLOPs: 34.71 | +7: iteration 9080/ 11269 | consumed samples: 2324480 | consumed tokens: 4760535040 | elapsed time per iteration (s): 0.49 | learning rate: 3.656E-05 | global batch size: 256 | lm loss: 2.980352E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.588 | TFLOPs: 34.44 | +7: iteration 9090/ 11269 | consumed samples: 2327040 | consumed tokens: 4765777920 | elapsed time per iteration (s): 0.48 | learning rate: 3.642E-05 | global batch size: 256 | lm loss: 2.985004E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.711 | TFLOPs: 34.90 | +7: iteration 9100/ 11269 | consumed samples: 2329600 | consumed tokens: 4771020800 | elapsed time per iteration (s): 0.48 | learning rate: 3.627E-05 | global batch size: 256 | lm loss: 2.946349E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.420 | TFLOPs: 34.62 | +7: iteration 9110/ 11269 | consumed samples: 2332160 | consumed tokens: 4776263680 | elapsed time per iteration (s): 0.49 | learning rate: 3.613E-05 | global batch size: 256 | lm loss: 2.953293E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.222 | TFLOPs: 34.35 | +7: iteration 9120/ 11269 | consumed samples: 2334720 | consumed tokens: 4781506560 | elapsed time per iteration (s): 0.48 | learning rate: 3.598E-05 | global batch size: 256 | lm loss: 2.949181E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.739 | TFLOPs: 34.71 | +7: iteration 9130/ 11269 | consumed samples: 2337280 | consumed tokens: 4786749440 | elapsed time per iteration (s): 0.48 | learning rate: 3.584E-05 | global batch size: 256 | lm loss: 2.957528E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.337 | TFLOPs: 34.81 | +7: iteration 9140/ 11269 | consumed samples: 2339840 | consumed tokens: 4791992320 | elapsed time per iteration (s): 0.49 | learning rate: 3.570E-05 | global batch size: 256 | lm loss: 2.955737E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.952 | TFLOPs: 33.94 | +7: iteration 9150/ 11269 | consumed samples: 2342400 | consumed tokens: 4797235200 | elapsed time per iteration (s): 0.48 | learning rate: 3.555E-05 | global batch size: 256 | lm loss: 2.928420E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.201 | TFLOPs: 35.00 | +7: iteration 9160/ 11269 | consumed samples: 2344960 | consumed tokens: 4802478080 | elapsed time per iteration (s): 0.47 | learning rate: 3.541E-05 | global batch size: 256 | lm loss: 2.965880E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 539.380 | TFLOPs: 35.28 | +7: iteration 9170/ 11269 | consumed samples: 2347520 | consumed tokens: 4807720960 | elapsed time per iteration (s): 0.48 | learning rate: 3.527E-05 | global batch size: 256 | lm loss: 2.959750E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.492 | TFLOPs: 34.82 | +7: iteration 9180/ 11269 | consumed samples: 2350080 | consumed tokens: 4812963840 | elapsed time per iteration (s): 0.48 | learning rate: 3.513E-05 | global batch size: 256 | lm loss: 2.948067E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.623 | TFLOPs: 34.90 | +7: iteration 9190/ 11269 | consumed samples: 2352640 | consumed tokens: 4818206720 | elapsed time per iteration (s): 0.48 | learning rate: 3.499E-05 | global batch size: 256 | lm loss: 2.951501E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.340 | TFLOPs: 34.55 | +7: iteration 9200/ 11269 | consumed samples: 2355200 | consumed tokens: 4823449600 | elapsed time per iteration (s): 0.48 | learning rate: 3.485E-05 | global batch size: 256 | lm loss: 2.983529E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.246 | TFLOPs: 34.94 | +7: iteration 9210/ 11269 | consumed samples: 2357760 | consumed tokens: 4828692480 | elapsed time per iteration (s): 0.48 | learning rate: 3.471E-05 | global batch size: 256 | lm loss: 2.979089E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.959 | TFLOPs: 35.12 | +7: iteration 9220/ 11269 | consumed samples: 2360320 | consumed tokens: 4833935360 | elapsed time per iteration (s): 0.49 | learning rate: 3.457E-05 | global batch size: 256 | lm loss: 2.976541E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.502 | TFLOPs: 34.50 | +7: iteration 9230/ 11269 | consumed samples: 2362880 | consumed tokens: 4839178240 | elapsed time per iteration (s): 0.48 | learning rate: 3.443E-05 | global batch size: 256 | lm loss: 2.964111E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.709 | TFLOPs: 34.71 | +7: iteration 9240/ 11269 | consumed samples: 2365440 | consumed tokens: 4844421120 | elapsed time per iteration (s): 0.49 | learning rate: 3.430E-05 | global batch size: 256 | lm loss: 2.993029E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 519.747 | TFLOPs: 33.99 | +7: iteration 9250/ 11269 | consumed samples: 2368000 | consumed tokens: 4849664000 | elapsed time per iteration (s): 0.49 | learning rate: 3.416E-05 | global batch size: 256 | lm loss: 2.984913E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.709 | TFLOPs: 33.92 | +7: iteration 9260/ 11269 | consumed samples: 2370560 | consumed tokens: 4854906880 | elapsed time per iteration (s): 0.49 | learning rate: 3.402E-05 | global batch size: 256 | lm loss: 2.939316E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.898 | TFLOPs: 34.33 | +7: iteration 9270/ 11269 | consumed samples: 2373120 | consumed tokens: 4860149760 | elapsed time per iteration (s): 0.48 | learning rate: 3.389E-05 | global batch size: 256 | lm loss: 2.927187E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.092 | TFLOPs: 34.54 | +7: iteration 9280/ 11269 | consumed samples: 2375680 | consumed tokens: 4865392640 | elapsed time per iteration (s): 0.48 | learning rate: 3.375E-05 | global batch size: 256 | lm loss: 2.974104E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.348 | TFLOPs: 34.95 | +7: iteration 9290/ 11269 | consumed samples: 2378240 | consumed tokens: 4870635520 | elapsed time per iteration (s): 0.48 | learning rate: 3.362E-05 | global batch size: 256 | lm loss: 2.953234E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.241 | TFLOPs: 34.87 | +7: iteration 9300/ 11269 | consumed samples: 2380800 | consumed tokens: 4875878400 | elapsed time per iteration (s): 0.48 | learning rate: 3.348E-05 | global batch size: 256 | lm loss: 2.942837E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.072 | TFLOPs: 34.99 | +7: iteration 9310/ 11269 | consumed samples: 2383360 | consumed tokens: 4881121280 | elapsed time per iteration (s): 0.47 | learning rate: 3.335E-05 | global batch size: 256 | lm loss: 2.963445E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 539.413 | TFLOPs: 35.28 | +7: iteration 9320/ 11269 | consumed samples: 2385920 | consumed tokens: 4886364160 | elapsed time per iteration (s): 0.48 | learning rate: 3.322E-05 | global batch size: 256 | lm loss: 2.935279E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.430 | TFLOPs: 34.95 | +7: iteration 9330/ 11269 | consumed samples: 2388480 | consumed tokens: 4891607040 | elapsed time per iteration (s): 0.48 | learning rate: 3.309E-05 | global batch size: 256 | lm loss: 2.941747E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.534 | TFLOPs: 34.57 | +7: iteration 9340/ 11269 | consumed samples: 2391040 | consumed tokens: 4896849920 | elapsed time per iteration (s): 0.48 | learning rate: 3.296E-05 | global batch size: 256 | lm loss: 2.955027E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.066 | TFLOPs: 34.99 | +7: iteration 9350/ 11269 | consumed samples: 2393600 | consumed tokens: 4902092800 | elapsed time per iteration (s): 0.48 | learning rate: 3.282E-05 | global batch size: 256 | lm loss: 2.964594E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.234 | TFLOPs: 34.55 | +7: iteration 9360/ 11269 | consumed samples: 2396160 | consumed tokens: 4907335680 | elapsed time per iteration (s): 0.49 | learning rate: 3.269E-05 | global batch size: 256 | lm loss: 2.950163E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.296 | TFLOPs: 34.35 | +7: iteration 9370/ 11269 | consumed samples: 2398720 | consumed tokens: 4912578560 | elapsed time per iteration (s): 0.49 | learning rate: 3.257E-05 | global batch size: 256 | lm loss: 2.951284E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.708 | TFLOPs: 34.05 | +7: iteration 9380/ 11269 | consumed samples: 2401280 | consumed tokens: 4917821440 | elapsed time per iteration (s): 0.48 | learning rate: 3.244E-05 | global batch size: 256 | lm loss: 2.958136E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.662 | TFLOPs: 35.16 | +7: iteration 9390/ 11269 | consumed samples: 2403840 | consumed tokens: 4923064320 | elapsed time per iteration (s): 0.48 | learning rate: 3.231E-05 | global batch size: 256 | lm loss: 2.945325E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.021 | TFLOPs: 34.79 | +7: iteration 9400/ 11269 | consumed samples: 2406400 | consumed tokens: 4928307200 | elapsed time per iteration (s): 0.48 | learning rate: 3.218E-05 | global batch size: 256 | lm loss: 2.954827E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.394 | TFLOPs: 34.75 | +7: iteration 9410/ 11269 | consumed samples: 2408960 | consumed tokens: 4933550080 | elapsed time per iteration (s): 0.48 | learning rate: 3.205E-05 | global batch size: 256 | lm loss: 2.967720E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.035 | TFLOPs: 34.86 | +7: iteration 9420/ 11269 | consumed samples: 2411520 | consumed tokens: 4938792960 | elapsed time per iteration (s): 0.49 | learning rate: 3.193E-05 | global batch size: 256 | lm loss: 2.953071E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.177 | TFLOPs: 34.35 | +7: iteration 9430/ 11269 | consumed samples: 2414080 | consumed tokens: 4944035840 | elapsed time per iteration (s): 0.48 | learning rate: 3.180E-05 | global batch size: 256 | lm loss: 2.978694E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.886 | TFLOPs: 34.92 | +7: iteration 9440/ 11269 | consumed samples: 2416640 | consumed tokens: 4949278720 | elapsed time per iteration (s): 0.48 | learning rate: 3.168E-05 | global batch size: 256 | lm loss: 2.985368E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.577 | TFLOPs: 34.63 | +7: iteration 9450/ 11269 | consumed samples: 2419200 | consumed tokens: 4954521600 | elapsed time per iteration (s): 0.48 | learning rate: 3.155E-05 | global batch size: 256 | lm loss: 2.934842E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.163 | TFLOPs: 34.93 | +7: iteration 9460/ 11269 | consumed samples: 2421760 | consumed tokens: 4959764480 | elapsed time per iteration (s): 0.49 | learning rate: 3.143E-05 | global batch size: 256 | lm loss: 2.949098E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.512 | TFLOPs: 34.37 | +7: iteration 9470/ 11269 | consumed samples: 2424320 | consumed tokens: 4965007360 | elapsed time per iteration (s): 0.48 | learning rate: 3.130E-05 | global batch size: 256 | lm loss: 2.980833E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.097 | TFLOPs: 34.60 | +7: iteration 9480/ 11269 | consumed samples: 2426880 | consumed tokens: 4970250240 | elapsed time per iteration (s): 0.50 | learning rate: 3.118E-05 | global batch size: 256 | lm loss: 2.940388E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 516.711 | TFLOPs: 33.79 | +7: iteration 9490/ 11269 | consumed samples: 2429440 | consumed tokens: 4975493120 | elapsed time per iteration (s): 0.48 | learning rate: 3.106E-05 | global batch size: 256 | lm loss: 2.922714E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.919 | TFLOPs: 34.92 | +7: iteration 9500/ 11269 | consumed samples: 2432000 | consumed tokens: 4980736000 | elapsed time per iteration (s): 0.49 | learning rate: 3.094E-05 | global batch size: 256 | lm loss: 2.960623E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.563 | TFLOPs: 34.50 | +7: iteration 9510/ 11269 | consumed samples: 2434560 | consumed tokens: 4985978880 | elapsed time per iteration (s): 0.48 | learning rate: 3.082E-05 | global batch size: 256 | lm loss: 2.960914E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.840 | TFLOPs: 34.98 | +7: iteration 9520/ 11269 | consumed samples: 2437120 | consumed tokens: 4991221760 | elapsed time per iteration (s): 0.49 | learning rate: 3.070E-05 | global batch size: 256 | lm loss: 2.978851E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.748 | TFLOPs: 34.45 | +7: iteration 9530/ 11269 | consumed samples: 2439680 | consumed tokens: 4996464640 | elapsed time per iteration (s): 0.48 | learning rate: 3.058E-05 | global batch size: 256 | lm loss: 2.943972E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.429 | TFLOPs: 34.89 | +7: iteration 9540/ 11269 | consumed samples: 2442240 | consumed tokens: 5001707520 | elapsed time per iteration (s): 0.48 | learning rate: 3.046E-05 | global batch size: 256 | lm loss: 2.965546E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.070 | TFLOPs: 34.86 | +7: iteration 9550/ 11269 | consumed samples: 2444800 | consumed tokens: 5006950400 | elapsed time per iteration (s): 0.49 | learning rate: 3.034E-05 | global batch size: 256 | lm loss: 2.958671E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.484 | TFLOPs: 34.43 | +7: iteration 9560/ 11269 | consumed samples: 2447360 | consumed tokens: 5012193280 | elapsed time per iteration (s): 0.48 | learning rate: 3.022E-05 | global batch size: 256 | lm loss: 2.945181E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.862 | TFLOPs: 35.05 | +7: iteration 9570/ 11269 | consumed samples: 2449920 | consumed tokens: 5017436160 | elapsed time per iteration (s): 0.48 | learning rate: 3.011E-05 | global batch size: 256 | lm loss: 2.932230E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.387 | TFLOPs: 35.01 | +7: iteration 9580/ 11269 | consumed samples: 2452480 | consumed tokens: 5022679040 | elapsed time per iteration (s): 0.48 | learning rate: 2.999E-05 | global batch size: 256 | lm loss: 2.957807E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.408 | TFLOPs: 34.69 | +7: iteration 9590/ 11269 | consumed samples: 2455040 | consumed tokens: 5027921920 | elapsed time per iteration (s): 0.48 | learning rate: 2.987E-05 | global batch size: 256 | lm loss: 2.968377E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.958 | TFLOPs: 34.92 | +7: iteration 9600/ 11269 | consumed samples: 2457600 | consumed tokens: 5033164800 | elapsed time per iteration (s): 0.48 | learning rate: 2.976E-05 | global batch size: 256 | lm loss: 2.949443E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.053 | TFLOPs: 35.06 | +7: iteration 9610/ 11269 | consumed samples: 2460160 | consumed tokens: 5038407680 | elapsed time per iteration (s): 0.48 | learning rate: 2.964E-05 | global batch size: 256 | lm loss: 2.915225E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.858 | TFLOPs: 34.59 | +7: iteration 9620/ 11269 | consumed samples: 2462720 | consumed tokens: 5043650560 | elapsed time per iteration (s): 0.48 | learning rate: 2.953E-05 | global batch size: 256 | lm loss: 2.964422E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.910 | TFLOPs: 34.66 | +7: iteration 9630/ 11269 | consumed samples: 2465280 | consumed tokens: 5048893440 | elapsed time per iteration (s): 0.48 | learning rate: 2.942E-05 | global batch size: 256 | lm loss: 2.950091E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.715 | TFLOPs: 34.64 | +7: iteration 9640/ 11269 | consumed samples: 2467840 | consumed tokens: 5054136320 | elapsed time per iteration (s): 0.48 | learning rate: 2.930E-05 | global batch size: 256 | lm loss: 2.952169E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.637 | TFLOPs: 34.57 | +7: iteration 9650/ 11269 | consumed samples: 2470400 | consumed tokens: 5059379200 | elapsed time per iteration (s): 0.49 | learning rate: 2.919E-05 | global batch size: 256 | lm loss: 2.953157E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.896 | TFLOPs: 33.94 | +7: iteration 9660/ 11269 | consumed samples: 2472960 | consumed tokens: 5064622080 | elapsed time per iteration (s): 0.50 | learning rate: 2.908E-05 | global batch size: 256 | lm loss: 2.945417E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 511.307 | TFLOPs: 33.44 | +7: iteration 9670/ 11269 | consumed samples: 2475520 | consumed tokens: 5069864960 | elapsed time per iteration (s): 0.49 | learning rate: 2.897E-05 | global batch size: 256 | lm loss: 2.947362E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 519.966 | TFLOPs: 34.01 | +7: iteration 9680/ 11269 | consumed samples: 2478080 | consumed tokens: 5075107840 | elapsed time per iteration (s): 0.50 | learning rate: 2.886E-05 | global batch size: 256 | lm loss: 2.911422E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 510.342 | TFLOPs: 33.38 | +7: iteration 9690/ 11269 | consumed samples: 2480640 | consumed tokens: 5080350720 | elapsed time per iteration (s): 0.48 | learning rate: 2.875E-05 | global batch size: 256 | lm loss: 2.960410E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.411 | TFLOPs: 34.56 | +7: iteration 9700/ 11269 | consumed samples: 2483200 | consumed tokens: 5085593600 | elapsed time per iteration (s): 0.48 | learning rate: 2.864E-05 | global batch size: 256 | lm loss: 2.934860E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.306 | TFLOPs: 34.88 | +7: iteration 9710/ 11269 | consumed samples: 2485760 | consumed tokens: 5090836480 | elapsed time per iteration (s): 0.48 | learning rate: 2.853E-05 | global batch size: 256 | lm loss: 2.968908E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 538.070 | TFLOPs: 35.19 | +7: iteration 9720/ 11269 | consumed samples: 2488320 | consumed tokens: 5096079360 | elapsed time per iteration (s): 0.47 | learning rate: 2.843E-05 | global batch size: 256 | lm loss: 2.934406E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 540.550 | TFLOPs: 35.35 | +7: iteration 9730/ 11269 | consumed samples: 2490880 | consumed tokens: 5101322240 | elapsed time per iteration (s): 0.48 | learning rate: 2.832E-05 | global batch size: 256 | lm loss: 2.953772E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.483 | TFLOPs: 34.76 | +7: iteration 9740/ 11269 | consumed samples: 2493440 | consumed tokens: 5106565120 | elapsed time per iteration (s): 0.48 | learning rate: 2.821E-05 | global batch size: 256 | lm loss: 2.916823E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.735 | TFLOPs: 35.17 | +7: iteration 9750/ 11269 | consumed samples: 2496000 | consumed tokens: 5111808000 | elapsed time per iteration (s): 0.49 | learning rate: 2.811E-05 | global batch size: 256 | lm loss: 2.968411E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.359 | TFLOPs: 34.29 | +7: iteration 9760/ 11269 | consumed samples: 2498560 | consumed tokens: 5117050880 | elapsed time per iteration (s): 0.49 | learning rate: 2.800E-05 | global batch size: 256 | lm loss: 2.973595E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.823 | TFLOPs: 34.26 | +7: iteration 9770/ 11269 | consumed samples: 2501120 | consumed tokens: 5122293760 | elapsed time per iteration (s): 0.49 | learning rate: 2.790E-05 | global batch size: 256 | lm loss: 2.943527E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.188 | TFLOPs: 34.35 | +7: iteration 9780/ 11269 | consumed samples: 2503680 | consumed tokens: 5127536640 | elapsed time per iteration (s): 0.49 | learning rate: 2.780E-05 | global batch size: 256 | lm loss: 2.937275E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.566 | TFLOPs: 34.04 | +7: iteration 9790/ 11269 | consumed samples: 2506240 | consumed tokens: 5132779520 | elapsed time per iteration (s): 0.48 | learning rate: 2.769E-05 | global batch size: 256 | lm loss: 2.953485E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.714 | TFLOPs: 35.04 | +7: iteration 9800/ 11269 | consumed samples: 2508800 | consumed tokens: 5138022400 | elapsed time per iteration (s): 0.49 | learning rate: 2.759E-05 | global batch size: 256 | lm loss: 2.963880E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.197 | TFLOPs: 34.48 | +7: iteration 9810/ 11269 | consumed samples: 2511360 | consumed tokens: 5143265280 | elapsed time per iteration (s): 0.48 | learning rate: 2.749E-05 | global batch size: 256 | lm loss: 2.931374E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.968 | TFLOPs: 34.73 | +7: iteration 9820/ 11269 | consumed samples: 2513920 | consumed tokens: 5148508160 | elapsed time per iteration (s): 0.52 | learning rate: 2.739E-05 | global batch size: 256 | lm loss: 2.930736E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 494.944 | TFLOPs: 32.37 | +7: iteration 9830/ 11269 | consumed samples: 2516480 | consumed tokens: 5153751040 | elapsed time per iteration (s): 0.48 | learning rate: 2.729E-05 | global batch size: 256 | lm loss: 2.938315E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.265 | TFLOPs: 34.61 | +7: iteration 9840/ 11269 | consumed samples: 2519040 | consumed tokens: 5158993920 | elapsed time per iteration (s): 0.48 | learning rate: 2.719E-05 | global batch size: 256 | lm loss: 2.963375E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.790 | TFLOPs: 34.98 | +7: iteration 9850/ 11269 | consumed samples: 2521600 | consumed tokens: 5164236800 | elapsed time per iteration (s): 0.48 | learning rate: 2.709E-05 | global batch size: 256 | lm loss: 2.933547E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.943 | TFLOPs: 34.85 | +7: iteration 9860/ 11269 | consumed samples: 2524160 | consumed tokens: 5169479680 | elapsed time per iteration (s): 0.49 | learning rate: 2.699E-05 | global batch size: 256 | lm loss: 2.913055E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.176 | TFLOPs: 34.48 | +7: iteration 9870/ 11269 | consumed samples: 2526720 | consumed tokens: 5174722560 | elapsed time per iteration (s): 0.48 | learning rate: 2.689E-05 | global batch size: 256 | lm loss: 2.936841E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.432 | TFLOPs: 34.69 | +7: iteration 9880/ 11269 | consumed samples: 2529280 | consumed tokens: 5179965440 | elapsed time per iteration (s): 0.48 | learning rate: 2.680E-05 | global batch size: 256 | lm loss: 2.957700E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.659 | TFLOPs: 34.64 | +7: iteration 9890/ 11269 | consumed samples: 2531840 | consumed tokens: 5185208320 | elapsed time per iteration (s): 0.48 | learning rate: 2.670E-05 | global batch size: 256 | lm loss: 2.960428E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.885 | TFLOPs: 34.92 | +7: iteration 9900/ 11269 | consumed samples: 2534400 | consumed tokens: 5190451200 | elapsed time per iteration (s): 0.48 | learning rate: 2.661E-05 | global batch size: 256 | lm loss: 2.965465E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.204 | TFLOPs: 34.61 | +7: iteration 9910/ 11269 | consumed samples: 2536960 | consumed tokens: 5195694080 | elapsed time per iteration (s): 0.48 | learning rate: 2.651E-05 | global batch size: 256 | lm loss: 2.971680E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 538.836 | TFLOPs: 35.24 | +7: iteration 9920/ 11269 | consumed samples: 2539520 | consumed tokens: 5200936960 | elapsed time per iteration (s): 0.48 | learning rate: 2.642E-05 | global batch size: 256 | lm loss: 2.942171E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.407 | TFLOPs: 34.82 | +7: iteration 9930/ 11269 | consumed samples: 2542080 | consumed tokens: 5206179840 | elapsed time per iteration (s): 0.48 | learning rate: 2.632E-05 | global batch size: 256 | lm loss: 2.950120E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.282 | TFLOPs: 34.68 | +7: iteration 9940/ 11269 | consumed samples: 2544640 | consumed tokens: 5211422720 | elapsed time per iteration (s): 0.54 | learning rate: 2.623E-05 | global batch size: 256 | lm loss: 2.955668E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 474.512 | TFLOPs: 31.03 | +7: iteration 9950/ 11269 | consumed samples: 2547200 | consumed tokens: 5216665600 | elapsed time per iteration (s): 0.48 | learning rate: 2.614E-05 | global batch size: 256 | lm loss: 2.965146E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 538.131 | TFLOPs: 35.19 | +7: iteration 9960/ 11269 | consumed samples: 2549760 | consumed tokens: 5221908480 | elapsed time per iteration (s): 0.48 | learning rate: 2.605E-05 | global batch size: 256 | lm loss: 2.953116E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.897 | TFLOPs: 35.18 | +7: iteration 9970/ 11269 | consumed samples: 2552320 | consumed tokens: 5227151360 | elapsed time per iteration (s): 0.49 | learning rate: 2.595E-05 | global batch size: 256 | lm loss: 2.942319E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.372 | TFLOPs: 33.90 | +7: iteration 9980/ 11269 | consumed samples: 2554880 | consumed tokens: 5232394240 | elapsed time per iteration (s): 0.48 | learning rate: 2.586E-05 | global batch size: 256 | lm loss: 2.920641E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.043 | TFLOPs: 34.53 | +7: iteration 9990/ 11269 | consumed samples: 2557440 | consumed tokens: 5237637120 | elapsed time per iteration (s): 0.50 | learning rate: 2.577E-05 | global batch size: 256 | lm loss: 2.955049E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 514.192 | TFLOPs: 33.63 | +0: [2022-11-29 18:14:21,275] [INFO] [logging.py:68:log_dist] [Rank 0] step=10000, skipped=0, lr=[2.568592118488235e-05, 2.568592118488235e-05, 2.568592118488235e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 10000/ 11269 | consumed samples: 2560000 | consumed tokens: 5242880000 | elapsed time per iteration (s): 0.48 | learning rate: 2.569E-05 | global batch size: 256 | lm loss: 2.959277E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.023 | TFLOPs: 34.92 | +0: steps: 10000 loss: 2.9621 iter time (s): 0.489 samples/sec: 523.039 +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 10000 | lm loss value: 2.856580E+00 | lm loss PPL: 1.740191E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 10000 to checkpoints_280moscar +0: [2022-11-29 18:14:21,454] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step10000 is begin to save! +0: [2022-11-29 18:14:21,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:14:21,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:14:21,572] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:14:21,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:14:21,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:14:21,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:14:21,624] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:14:21,648] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:14:21,649] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:14:21,672] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:14:21,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:14:21,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:14:21,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:14:21,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:14:21,723] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:14:21,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:14:21,748] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:14:21,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:14:21,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:14:21,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:14:21,797] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:14:21,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:14:21,822] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/layer_13-model_00-model_states.pt... +0: [2022-11-29 18:14:21,846] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/layer_13-model_00-model_states.pt. +0: [2022-11-29 18:14:21,846] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:14:21,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:14:21,871] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/layer_15-model_00-model_states.pt... +0: [2022-11-29 18:14:21,895] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/layer_15-model_00-model_states.pt. +0: [2022-11-29 18:14:21,896] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/layer_16-model_00-model_states.pt... +0: [2022-11-29 18:14:21,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/layer_16-model_00-model_states.pt. +0: [2022-11-29 18:14:21,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/layer_17-model_00-model_states.pt... +0: [2022-11-29 18:14:21,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/layer_17-model_00-model_states.pt. +0: [2022-11-29 18:14:21,945] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/layer_18-model_00-model_states.pt... +0: [2022-11-29 18:14:21,970] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/layer_18-model_00-model_states.pt. +0: [2022-11-29 18:14:21,970] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/layer_19-model_00-model_states.pt... +0: [2022-11-29 18:14:21,994] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/layer_19-model_00-model_states.pt. +0: [2022-11-29 18:14:21,994] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/layer_20-model_00-model_states.pt... +0: [2022-11-29 18:14:22,019] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/layer_20-model_00-model_states.pt. +0: [2022-11-29 18:14:22,019] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/layer_22-model_00-model_states.pt... +0: [2022-11-29 18:14:22,021] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/layer_22-model_00-model_states.pt. +0: [2022-11-29 18:14:22,021] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_280moscar/global_step10000/mp_rank_00_model_states.pt +0: [2022-11-29 18:14:22,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:14:22,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:14:22,044] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:14:22,044] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:14:22,044] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:14:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:14:22,103] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:14:22,102] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:14:22,103] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:14:22,103] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 18:14:22,102] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:14:22,102] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 18:14:22,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:14:22,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:14:22,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 18:14:22,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:14:22,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:14:22,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 18:14:22,107] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:14:22,107] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:14:22,107] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:14:22,107] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +6: [2022-11-29 18:14:22,107] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:14:22,107] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:14:22,107] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +1: [2022-11-29 18:14:22,107] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 18:14:22,107] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +0: [2022-11-29 18:14:22,107] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 18:14:22,107] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 18:14:22,107] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 18:14:22,107] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:14:22,107] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:14:22,107] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 18:14:22,107] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:14:22,107] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:14:22,107] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 18:14:22,108] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:14:22,108] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:14:22,108] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 18:14:22,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:14:22,110] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:14:22,110] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 18:14:22,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:14:22,111] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:14:22,111] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 18:14:22,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:14:22,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:14:22,111] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:14:22,111] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +0: [2022-11-29 18:14:22,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:14:22,111] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 18:14:22,111] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 18:14:22,111] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:14:22,111] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 18:14:22,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:14:22,112] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:14:22,112] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 18:14:22,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:14:22,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:14:22,112] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +1: [2022-11-29 18:14:22,112] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:14:22,112] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 18:14:22,112] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 18:14:22,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:14:22,112] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:14:22,113] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 18:14:22,114] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:14:22,114] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:14:22,114] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 18:14:22,114] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:14:22,114] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:14:22,114] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:14:22,114] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:14:22,115] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:14:22,115] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:14:22,115] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 18:14:22,115] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 18:14:22,115] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 18:14:22,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:14:22,115] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:14:22,115] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 18:14:22,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:14:22,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:14:22,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +2: [2022-11-29 18:14:22,112] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +1: [2022-11-29 18:14:22,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 18:14:22,112] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 18:14:22,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:14:22,112] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:14:22,112] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 18:14:22,113] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:14:22,113] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:14:22,113] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 18:14:22,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:14:22,115] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:14:22,115] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 18:14:22,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:14:22,115] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:14:22,115] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 18:14:22,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:14:22,118] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:14:22,118] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 18:14:22,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:14:22,118] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:14:22,118] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 18:14:22,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:14:22,118] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:14:22,118] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 18:14:22,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:14:22,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:14:22,120] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 18:14:22,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:14:22,120] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:14:22,120] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 18:14:22,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:14:22,120] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:14:22,120] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 18:14:22,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:14:22,120] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:14:22,120] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 18:14:22,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:14:22,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:14:22,121] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:14:22,121] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:14:22,121] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 18:14:22,121] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 18:14:22,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:14:22,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:14:22,121] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:14:22,121] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:14:22,121] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 18:14:22,121] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 18:14:22,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:14:22,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:14:22,123] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:14:22,123] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:14:22,123] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:14:22,123] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:14:22,123] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 18:14:22,123] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 18:14:22,124] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:14:22,124] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:14:22,124] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:14:22,124] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:14:22,124] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:14:22,124] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:14:22,124] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:14:22,124] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 18:14:22,124] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:14:22,124] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 18:14:22,124] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:14:22,124] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 18:14:22,124] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +4: [2022-11-29 18:14:22,124] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 18:14:22,124] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 18:14:22,124] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:14:22,124] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:14:22,124] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 18:14:22,126] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:14:22,125] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:14:22,126] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +2: [2022-11-29 18:14:22,125] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:14:22,125] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 18:14:22,126] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 18:14:22,131] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:14:22,131] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:14:22,131] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 18:14:22,110] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:14:22,110] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:14:22,110] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 18:14:22,111] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 18:14:22,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:14:22,111] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:14:22,111] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 18:14:22,116] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:14:22,116] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:14:22,116] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:14:22,116] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:14:22,116] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 18:14:22,116] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 18:14:22,122] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:14:22,122] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:14:22,122] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:14:22,122] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:14:22,122] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 18:14:22,122] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 18:14:22,124] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:14:22,124] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:14:22,124] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 18:14:22,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:14:22,163] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:14:22,163] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 18:14:22,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:14:22,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:14:22,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:14:22,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 18:14:22,197] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:14:22,197] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: successfully saved checkpoint at iteration 10000 to checkpoints_280moscar +7: time (ms) | save-checkpoint: 747.86 +7: iteration 10010/ 11269 | consumed samples: 2562560 | consumed tokens: 5248122880 | elapsed time per iteration (s): 0.57 | learning rate: 2.560E-05 | global batch size: 256 | lm loss: 2.972881E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.468 | TFLOPs: 29.53 | +7: iteration 10020/ 11269 | consumed samples: 2565120 | consumed tokens: 5253365760 | elapsed time per iteration (s): 0.48 | learning rate: 2.551E-05 | global batch size: 256 | lm loss: 2.924081E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.666 | TFLOPs: 34.77 | +7: iteration 10030/ 11269 | consumed samples: 2567680 | consumed tokens: 5258608640 | elapsed time per iteration (s): 0.48 | learning rate: 2.542E-05 | global batch size: 256 | lm loss: 2.958115E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.227 | TFLOPs: 34.55 | +7: iteration 10040/ 11269 | consumed samples: 2570240 | consumed tokens: 5263851520 | elapsed time per iteration (s): 0.49 | learning rate: 2.534E-05 | global batch size: 256 | lm loss: 2.971580E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.190 | TFLOPs: 34.15 | +7: iteration 10050/ 11269 | consumed samples: 2572800 | consumed tokens: 5269094400 | elapsed time per iteration (s): 0.48 | learning rate: 2.525E-05 | global batch size: 256 | lm loss: 2.935071E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.630 | TFLOPs: 34.90 | +7: iteration 10060/ 11269 | consumed samples: 2575360 | consumed tokens: 5274337280 | elapsed time per iteration (s): 0.49 | learning rate: 2.517E-05 | global batch size: 256 | lm loss: 2.964279E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.889 | TFLOPs: 34.46 | +7: iteration 10070/ 11269 | consumed samples: 2577920 | consumed tokens: 5279580160 | elapsed time per iteration (s): 0.49 | learning rate: 2.508E-05 | global batch size: 256 | lm loss: 2.952264E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.800 | TFLOPs: 34.19 | +7: iteration 10080/ 11269 | consumed samples: 2580480 | consumed tokens: 5284823040 | elapsed time per iteration (s): 0.49 | learning rate: 2.500E-05 | global batch size: 256 | lm loss: 2.936727E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.865 | TFLOPs: 34.20 | +7: iteration 10090/ 11269 | consumed samples: 2583040 | consumed tokens: 5290065920 | elapsed time per iteration (s): 0.49 | learning rate: 2.492E-05 | global batch size: 256 | lm loss: 2.938185E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.111 | TFLOPs: 34.28 | +7: iteration 10100/ 11269 | consumed samples: 2585600 | consumed tokens: 5295308800 | elapsed time per iteration (s): 0.49 | learning rate: 2.483E-05 | global batch size: 256 | lm loss: 2.914658E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.685 | TFLOPs: 33.92 | +7: iteration 10110/ 11269 | consumed samples: 2588160 | consumed tokens: 5300551680 | elapsed time per iteration (s): 0.48 | learning rate: 2.475E-05 | global batch size: 256 | lm loss: 2.950852E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.129 | TFLOPs: 34.93 | +7: iteration 10120/ 11269 | consumed samples: 2590720 | consumed tokens: 5305794560 | elapsed time per iteration (s): 0.48 | learning rate: 2.467E-05 | global batch size: 256 | lm loss: 2.947028E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.989 | TFLOPs: 34.86 | +7: iteration 10130/ 11269 | consumed samples: 2593280 | consumed tokens: 5311037440 | elapsed time per iteration (s): 0.49 | learning rate: 2.459E-05 | global batch size: 256 | lm loss: 2.936901E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.632 | TFLOPs: 34.11 | +7: iteration 10140/ 11269 | consumed samples: 2595840 | consumed tokens: 5316280320 | elapsed time per iteration (s): 0.48 | learning rate: 2.451E-05 | global batch size: 256 | lm loss: 2.956045E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.424 | TFLOPs: 34.82 | +7: iteration 10150/ 11269 | consumed samples: 2598400 | consumed tokens: 5321523200 | elapsed time per iteration (s): 0.48 | learning rate: 2.443E-05 | global batch size: 256 | lm loss: 2.961201E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.104 | TFLOPs: 34.54 | +7: iteration 10160/ 11269 | consumed samples: 2600960 | consumed tokens: 5326766080 | elapsed time per iteration (s): 0.49 | learning rate: 2.435E-05 | global batch size: 256 | lm loss: 2.987570E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.979 | TFLOPs: 34.40 | +7: iteration 10170/ 11269 | consumed samples: 2603520 | consumed tokens: 5332008960 | elapsed time per iteration (s): 0.48 | learning rate: 2.428E-05 | global batch size: 256 | lm loss: 2.970314E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.565 | TFLOPs: 34.76 | +7: iteration 10180/ 11269 | consumed samples: 2606080 | consumed tokens: 5337251840 | elapsed time per iteration (s): 0.48 | learning rate: 2.420E-05 | global batch size: 256 | lm loss: 2.933841E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.682 | TFLOPs: 35.10 | +7: iteration 10190/ 11269 | consumed samples: 2608640 | consumed tokens: 5342494720 | elapsed time per iteration (s): 0.48 | learning rate: 2.412E-05 | global batch size: 256 | lm loss: 2.947474E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.187 | TFLOPs: 34.67 | +7: iteration 10200/ 11269 | consumed samples: 2611200 | consumed tokens: 5347737600 | elapsed time per iteration (s): 0.48 | learning rate: 2.405E-05 | global batch size: 256 | lm loss: 2.947267E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.175 | TFLOPs: 34.67 | +7: iteration 10210/ 11269 | consumed samples: 2613760 | consumed tokens: 5352980480 | elapsed time per iteration (s): 0.48 | learning rate: 2.397E-05 | global batch size: 256 | lm loss: 2.922620E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 537.522 | TFLOPs: 35.15 | +7: iteration 10220/ 11269 | consumed samples: 2616320 | consumed tokens: 5358223360 | elapsed time per iteration (s): 0.49 | learning rate: 2.390E-05 | global batch size: 256 | lm loss: 2.942453E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.738 | TFLOPs: 34.45 | +7: iteration 10230/ 11269 | consumed samples: 2618880 | consumed tokens: 5363466240 | elapsed time per iteration (s): 0.48 | learning rate: 2.383E-05 | global batch size: 256 | lm loss: 2.958689E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.977 | TFLOPs: 34.53 | +7: iteration 10240/ 11269 | consumed samples: 2621440 | consumed tokens: 5368709120 | elapsed time per iteration (s): 0.50 | learning rate: 2.375E-05 | global batch size: 256 | lm loss: 2.949984E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.062 | TFLOPs: 33.82 | +7: iteration 10250/ 11269 | consumed samples: 2624000 | consumed tokens: 5373952000 | elapsed time per iteration (s): 0.48 | learning rate: 2.368E-05 | global batch size: 256 | lm loss: 2.942538E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.888 | TFLOPs: 34.59 | +7: iteration 10260/ 11269 | consumed samples: 2626560 | consumed tokens: 5379194880 | elapsed time per iteration (s): 0.50 | learning rate: 2.361E-05 | global batch size: 256 | lm loss: 2.935217E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 516.785 | TFLOPs: 33.80 | +7: iteration 10270/ 11269 | consumed samples: 2629120 | consumed tokens: 5384437760 | elapsed time per iteration (s): 0.48 | learning rate: 2.354E-05 | global batch size: 256 | lm loss: 2.944214E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.281 | TFLOPs: 34.75 | +7: iteration 10280/ 11269 | consumed samples: 2631680 | consumed tokens: 5389680640 | elapsed time per iteration (s): 0.48 | learning rate: 2.347E-05 | global batch size: 256 | lm loss: 2.922641E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.804 | TFLOPs: 35.11 | +7: iteration 10290/ 11269 | consumed samples: 2634240 | consumed tokens: 5394923520 | elapsed time per iteration (s): 0.47 | learning rate: 2.340E-05 | global batch size: 256 | lm loss: 2.927140E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 539.583 | TFLOPs: 35.29 | +7: iteration 10300/ 11269 | consumed samples: 2636800 | consumed tokens: 5400166400 | elapsed time per iteration (s): 0.48 | learning rate: 2.333E-05 | global batch size: 256 | lm loss: 2.934487E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.697 | TFLOPs: 34.97 | +7: iteration 10310/ 11269 | consumed samples: 2639360 | consumed tokens: 5405409280 | elapsed time per iteration (s): 0.49 | learning rate: 2.326E-05 | global batch size: 256 | lm loss: 2.945398E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.938 | TFLOPs: 34.46 | +7: iteration 10320/ 11269 | consumed samples: 2641920 | consumed tokens: 5410652160 | elapsed time per iteration (s): 0.51 | learning rate: 2.319E-05 | global batch size: 256 | lm loss: 2.979256E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 501.064 | TFLOPs: 32.77 | +7: iteration 10330/ 11269 | consumed samples: 2644480 | consumed tokens: 5415895040 | elapsed time per iteration (s): 0.48 | learning rate: 2.313E-05 | global batch size: 256 | lm loss: 2.951371E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.242 | TFLOPs: 35.00 | +7: iteration 10340/ 11269 | consumed samples: 2647040 | consumed tokens: 5421137920 | elapsed time per iteration (s): 0.48 | learning rate: 2.306E-05 | global batch size: 256 | lm loss: 2.955462E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.496 | TFLOPs: 35.02 | +7: iteration 10350/ 11269 | consumed samples: 2649600 | consumed tokens: 5426380800 | elapsed time per iteration (s): 0.48 | learning rate: 2.300E-05 | global batch size: 256 | lm loss: 2.962001E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.743 | TFLOPs: 34.78 | +7: iteration 10360/ 11269 | consumed samples: 2652160 | consumed tokens: 5431623680 | elapsed time per iteration (s): 0.49 | learning rate: 2.293E-05 | global batch size: 256 | lm loss: 2.959449E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.581 | TFLOPs: 34.44 | +7: iteration 10370/ 11269 | consumed samples: 2654720 | consumed tokens: 5436866560 | elapsed time per iteration (s): 0.48 | learning rate: 2.287E-05 | global batch size: 256 | lm loss: 2.945506E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.004 | TFLOPs: 34.86 | +7: iteration 10380/ 11269 | consumed samples: 2657280 | consumed tokens: 5442109440 | elapsed time per iteration (s): 0.48 | learning rate: 2.281E-05 | global batch size: 256 | lm loss: 2.931514E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.335 | TFLOPs: 34.81 | +7: iteration 10390/ 11269 | consumed samples: 2659840 | consumed tokens: 5447352320 | elapsed time per iteration (s): 0.48 | learning rate: 2.274E-05 | global batch size: 256 | lm loss: 2.970775E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.713 | TFLOPs: 34.97 | +7: iteration 10400/ 11269 | consumed samples: 2662400 | consumed tokens: 5452595200 | elapsed time per iteration (s): 0.48 | learning rate: 2.268E-05 | global batch size: 256 | lm loss: 2.941205E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.581 | TFLOPs: 34.77 | +7: iteration 10410/ 11269 | consumed samples: 2664960 | consumed tokens: 5457838080 | elapsed time per iteration (s): 0.48 | learning rate: 2.262E-05 | global batch size: 256 | lm loss: 2.957727E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.209 | TFLOPs: 34.68 | +7: iteration 10420/ 11269 | consumed samples: 2667520 | consumed tokens: 5463080960 | elapsed time per iteration (s): 0.48 | learning rate: 2.256E-05 | global batch size: 256 | lm loss: 2.941789E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.800 | TFLOPs: 34.58 | +7: iteration 10430/ 11269 | consumed samples: 2670080 | consumed tokens: 5468323840 | elapsed time per iteration (s): 0.48 | learning rate: 2.250E-05 | global batch size: 256 | lm loss: 2.921336E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.001 | TFLOPs: 34.66 | +7: iteration 10440/ 11269 | consumed samples: 2672640 | consumed tokens: 5473566720 | elapsed time per iteration (s): 0.49 | learning rate: 2.244E-05 | global batch size: 256 | lm loss: 2.957564E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.065 | TFLOPs: 34.21 | +7: iteration 10450/ 11269 | consumed samples: 2675200 | consumed tokens: 5478809600 | elapsed time per iteration (s): 0.48 | learning rate: 2.238E-05 | global batch size: 256 | lm loss: 2.923932E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.421 | TFLOPs: 34.62 | +7: iteration 10460/ 11269 | consumed samples: 2677760 | consumed tokens: 5484052480 | elapsed time per iteration (s): 0.48 | learning rate: 2.233E-05 | global batch size: 256 | lm loss: 2.953266E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.616 | TFLOPs: 34.96 | +7: iteration 10470/ 11269 | consumed samples: 2680320 | consumed tokens: 5489295360 | elapsed time per iteration (s): 0.50 | learning rate: 2.227E-05 | global batch size: 256 | lm loss: 2.920202E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 515.083 | TFLOPs: 33.69 | +7: iteration 10480/ 11269 | consumed samples: 2682880 | consumed tokens: 5494538240 | elapsed time per iteration (s): 0.49 | learning rate: 2.221E-05 | global batch size: 256 | lm loss: 2.924229E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.191 | TFLOPs: 34.28 | +7: iteration 10490/ 11269 | consumed samples: 2685440 | consumed tokens: 5499781120 | elapsed time per iteration (s): 0.48 | learning rate: 2.216E-05 | global batch size: 256 | lm loss: 2.965581E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.149 | TFLOPs: 34.67 | +7: iteration 10500/ 11269 | consumed samples: 2688000 | consumed tokens: 5505024000 | elapsed time per iteration (s): 0.49 | learning rate: 2.210E-05 | global batch size: 256 | lm loss: 2.947656E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.571 | TFLOPs: 34.37 | +7: iteration 10510/ 11269 | consumed samples: 2690560 | consumed tokens: 5510266880 | elapsed time per iteration (s): 0.49 | learning rate: 2.205E-05 | global batch size: 256 | lm loss: 2.950228E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.705 | TFLOPs: 33.92 | +7: iteration 10520/ 11269 | consumed samples: 2693120 | consumed tokens: 5515509760 | elapsed time per iteration (s): 0.48 | learning rate: 2.199E-05 | global batch size: 256 | lm loss: 2.936923E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.899 | TFLOPs: 34.98 | +7: iteration 10530/ 11269 | consumed samples: 2695680 | consumed tokens: 5520752640 | elapsed time per iteration (s): 0.48 | learning rate: 2.194E-05 | global batch size: 256 | lm loss: 2.925665E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.985 | TFLOPs: 34.53 | +7: iteration 10540/ 11269 | consumed samples: 2698240 | consumed tokens: 5525995520 | elapsed time per iteration (s): 0.48 | learning rate: 2.189E-05 | global batch size: 256 | lm loss: 2.906148E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.846 | TFLOPs: 34.98 | +7: iteration 10550/ 11269 | consumed samples: 2700800 | consumed tokens: 5531238400 | elapsed time per iteration (s): 0.49 | learning rate: 2.184E-05 | global batch size: 256 | lm loss: 2.940064E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.155 | TFLOPs: 34.48 | +7: iteration 10560/ 11269 | consumed samples: 2703360 | consumed tokens: 5536481280 | elapsed time per iteration (s): 0.48 | learning rate: 2.179E-05 | global batch size: 256 | lm loss: 2.888948E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.323 | TFLOPs: 35.08 | +7: iteration 10570/ 11269 | consumed samples: 2705920 | consumed tokens: 5541724160 | elapsed time per iteration (s): 0.48 | learning rate: 2.174E-05 | global batch size: 256 | lm loss: 2.959572E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.511 | TFLOPs: 34.83 | +7: iteration 10580/ 11269 | consumed samples: 2708480 | consumed tokens: 5546967040 | elapsed time per iteration (s): 0.48 | learning rate: 2.169E-05 | global batch size: 256 | lm loss: 2.974988E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.899 | TFLOPs: 34.72 | +7: iteration 10590/ 11269 | consumed samples: 2711040 | consumed tokens: 5552209920 | elapsed time per iteration (s): 0.48 | learning rate: 2.164E-05 | global batch size: 256 | lm loss: 2.922430E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.726 | TFLOPs: 35.10 | +7: iteration 10600/ 11269 | consumed samples: 2713600 | consumed tokens: 5557452800 | elapsed time per iteration (s): 0.49 | learning rate: 2.159E-05 | global batch size: 256 | lm loss: 2.972191E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.758 | TFLOPs: 33.86 | +7: iteration 10610/ 11269 | consumed samples: 2716160 | consumed tokens: 5562695680 | elapsed time per iteration (s): 0.48 | learning rate: 2.155E-05 | global batch size: 256 | lm loss: 2.955290E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.167 | TFLOPs: 34.67 | +7: iteration 10620/ 11269 | consumed samples: 2718720 | consumed tokens: 5567938560 | elapsed time per iteration (s): 0.49 | learning rate: 2.150E-05 | global batch size: 256 | lm loss: 2.917628E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 519.861 | TFLOPs: 34.00 | +7: iteration 10630/ 11269 | consumed samples: 2721280 | consumed tokens: 5573181440 | elapsed time per iteration (s): 0.49 | learning rate: 2.145E-05 | global batch size: 256 | lm loss: 2.925992E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.685 | TFLOPs: 34.51 | +7: iteration 10640/ 11269 | consumed samples: 2723840 | consumed tokens: 5578424320 | elapsed time per iteration (s): 0.47 | learning rate: 2.141E-05 | global batch size: 256 | lm loss: 2.931488E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 540.507 | TFLOPs: 35.35 | +7: iteration 10650/ 11269 | consumed samples: 2726400 | consumed tokens: 5583667200 | elapsed time per iteration (s): 0.48 | learning rate: 2.136E-05 | global batch size: 256 | lm loss: 2.936049E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.269 | TFLOPs: 35.07 | +7: iteration 10660/ 11269 | consumed samples: 2728960 | consumed tokens: 5588910080 | elapsed time per iteration (s): 0.49 | learning rate: 2.132E-05 | global batch size: 256 | lm loss: 2.958782E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.489 | TFLOPs: 34.37 | +7: iteration 10670/ 11269 | consumed samples: 2731520 | consumed tokens: 5594152960 | elapsed time per iteration (s): 0.48 | learning rate: 2.128E-05 | global batch size: 256 | lm loss: 2.924755E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.777 | TFLOPs: 34.65 | +7: iteration 10680/ 11269 | consumed samples: 2734080 | consumed tokens: 5599395840 | elapsed time per iteration (s): 0.48 | learning rate: 2.124E-05 | global batch size: 256 | lm loss: 2.947948E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 531.643 | TFLOPs: 34.77 | +7: iteration 10690/ 11269 | consumed samples: 2736640 | consumed tokens: 5604638720 | elapsed time per iteration (s): 0.48 | learning rate: 2.119E-05 | global batch size: 256 | lm loss: 2.928103E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.170 | TFLOPs: 35.00 | +7: iteration 10700/ 11269 | consumed samples: 2739200 | consumed tokens: 5609881600 | elapsed time per iteration (s): 0.47 | learning rate: 2.115E-05 | global batch size: 256 | lm loss: 2.960028E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 542.671 | TFLOPs: 35.49 | +7: iteration 10710/ 11269 | consumed samples: 2741760 | consumed tokens: 5615124480 | elapsed time per iteration (s): 0.48 | learning rate: 2.111E-05 | global batch size: 256 | lm loss: 2.947750E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.860 | TFLOPs: 34.91 | +7: iteration 10720/ 11269 | consumed samples: 2744320 | consumed tokens: 5620367360 | elapsed time per iteration (s): 0.48 | learning rate: 2.107E-05 | global batch size: 256 | lm loss: 2.979490E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.327 | TFLOPs: 34.68 | +7: iteration 10730/ 11269 | consumed samples: 2746880 | consumed tokens: 5625610240 | elapsed time per iteration (s): 0.48 | learning rate: 2.103E-05 | global batch size: 256 | lm loss: 2.946428E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.976 | TFLOPs: 35.12 | +7: iteration 10740/ 11269 | consumed samples: 2749440 | consumed tokens: 5630853120 | elapsed time per iteration (s): 0.49 | learning rate: 2.100E-05 | global batch size: 256 | lm loss: 2.915006E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.751 | TFLOPs: 34.25 | +7: iteration 10750/ 11269 | consumed samples: 2752000 | consumed tokens: 5636096000 | elapsed time per iteration (s): 0.49 | learning rate: 2.096E-05 | global batch size: 256 | lm loss: 2.944552E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.672 | TFLOPs: 34.18 | +7: iteration 10760/ 11269 | consumed samples: 2754560 | consumed tokens: 5641338880 | elapsed time per iteration (s): 0.48 | learning rate: 2.092E-05 | global batch size: 256 | lm loss: 2.929896E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.957 | TFLOPs: 34.99 | +7: iteration 10770/ 11269 | consumed samples: 2757120 | consumed tokens: 5646581760 | elapsed time per iteration (s): 0.49 | learning rate: 2.089E-05 | global batch size: 256 | lm loss: 2.938448E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.778 | TFLOPs: 34.52 | +7: iteration 10780/ 11269 | consumed samples: 2759680 | consumed tokens: 5651824640 | elapsed time per iteration (s): 0.48 | learning rate: 2.085E-05 | global batch size: 256 | lm loss: 2.966349E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.847 | TFLOPs: 35.11 | +7: iteration 10790/ 11269 | consumed samples: 2762240 | consumed tokens: 5657067520 | elapsed time per iteration (s): 0.49 | learning rate: 2.082E-05 | global batch size: 256 | lm loss: 2.913998E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.918 | TFLOPs: 34.33 | +7: iteration 10800/ 11269 | consumed samples: 2764800 | consumed tokens: 5662310400 | elapsed time per iteration (s): 0.48 | learning rate: 2.078E-05 | global batch size: 256 | lm loss: 2.957031E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.854 | TFLOPs: 34.98 | +7: iteration 10810/ 11269 | consumed samples: 2767360 | consumed tokens: 5667553280 | elapsed time per iteration (s): 0.47 | learning rate: 2.075E-05 | global batch size: 256 | lm loss: 2.915865E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 543.068 | TFLOPs: 35.52 | +7: iteration 10820/ 11269 | consumed samples: 2769920 | consumed tokens: 5672796160 | elapsed time per iteration (s): 0.49 | learning rate: 2.072E-05 | global batch size: 256 | lm loss: 2.939219E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 518.309 | TFLOPs: 33.90 | +7: iteration 10830/ 11269 | consumed samples: 2772480 | consumed tokens: 5678039040 | elapsed time per iteration (s): 0.50 | learning rate: 2.069E-05 | global batch size: 256 | lm loss: 2.939923E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 514.654 | TFLOPs: 33.66 | +7: iteration 10840/ 11269 | consumed samples: 2775040 | consumed tokens: 5683281920 | elapsed time per iteration (s): 0.54 | learning rate: 2.066E-05 | global batch size: 256 | lm loss: 2.929653E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 477.585 | TFLOPs: 31.23 | +7: iteration 10850/ 11269 | consumed samples: 2777600 | consumed tokens: 5688524800 | elapsed time per iteration (s): 0.51 | learning rate: 2.063E-05 | global batch size: 256 | lm loss: 2.955391E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 497.338 | TFLOPs: 32.53 | +7: iteration 10860/ 11269 | consumed samples: 2780160 | consumed tokens: 5693767680 | elapsed time per iteration (s): 0.53 | learning rate: 2.060E-05 | global batch size: 256 | lm loss: 2.971083E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 479.001 | TFLOPs: 31.33 | +7: iteration 10870/ 11269 | consumed samples: 2782720 | consumed tokens: 5699010560 | elapsed time per iteration (s): 0.49 | learning rate: 2.057E-05 | global batch size: 256 | lm loss: 2.971263E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.791 | TFLOPs: 34.12 | +7: iteration 10880/ 11269 | consumed samples: 2785280 | consumed tokens: 5704253440 | elapsed time per iteration (s): 0.48 | learning rate: 2.054E-05 | global batch size: 256 | lm loss: 2.920686E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.471 | TFLOPs: 35.02 | +7: iteration 10890/ 11269 | consumed samples: 2787840 | consumed tokens: 5709496320 | elapsed time per iteration (s): 0.48 | learning rate: 2.051E-05 | global batch size: 256 | lm loss: 2.916738E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.593 | TFLOPs: 34.96 | +7: iteration 10900/ 11269 | consumed samples: 2790400 | consumed tokens: 5714739200 | elapsed time per iteration (s): 0.48 | learning rate: 2.049E-05 | global batch size: 256 | lm loss: 2.933327E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.862 | TFLOPs: 34.98 | +7: iteration 10910/ 11269 | consumed samples: 2792960 | consumed tokens: 5719982080 | elapsed time per iteration (s): 0.53 | learning rate: 2.046E-05 | global batch size: 256 | lm loss: 2.928835E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 486.999 | TFLOPs: 31.85 | +7: iteration 10920/ 11269 | consumed samples: 2795520 | consumed tokens: 5725224960 | elapsed time per iteration (s): 0.48 | learning rate: 2.043E-05 | global batch size: 256 | lm loss: 2.943738E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 534.457 | TFLOPs: 34.95 | +7: iteration 10930/ 11269 | consumed samples: 2798080 | consumed tokens: 5730467840 | elapsed time per iteration (s): 0.49 | learning rate: 2.041E-05 | global batch size: 256 | lm loss: 2.945975E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.094 | TFLOPs: 34.41 | +7: iteration 10940/ 11269 | consumed samples: 2800640 | consumed tokens: 5735710720 | elapsed time per iteration (s): 0.73 | learning rate: 2.039E-05 | global batch size: 256 | lm loss: 2.905365E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 352.533 | TFLOPs: 23.06 | +7: iteration 10950/ 11269 | consumed samples: 2803200 | consumed tokens: 5740953600 | elapsed time per iteration (s): 0.61 | learning rate: 2.036E-05 | global batch size: 256 | lm loss: 2.946931E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 422.330 | TFLOPs: 27.62 | +7: iteration 10960/ 11269 | consumed samples: 2805760 | consumed tokens: 5746196480 | elapsed time per iteration (s): 0.49 | learning rate: 2.034E-05 | global batch size: 256 | lm loss: 2.923399E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 522.299 | TFLOPs: 34.16 | +7: iteration 10970/ 11269 | consumed samples: 2808320 | consumed tokens: 5751439360 | elapsed time per iteration (s): 0.50 | learning rate: 2.032E-05 | global batch size: 256 | lm loss: 2.951532E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 516.668 | TFLOPs: 33.79 | +7: iteration 10980/ 11269 | consumed samples: 2810880 | consumed tokens: 5756682240 | elapsed time per iteration (s): 0.49 | learning rate: 2.030E-05 | global batch size: 256 | lm loss: 2.947533E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.328 | TFLOPs: 34.09 | +7: iteration 10990/ 11269 | consumed samples: 2813440 | consumed tokens: 5761925120 | elapsed time per iteration (s): 0.48 | learning rate: 2.028E-05 | global batch size: 256 | lm loss: 2.927096E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 529.858 | TFLOPs: 34.65 | +7: iteration 11000/ 11269 | consumed samples: 2816000 | consumed tokens: 5767168000 | elapsed time per iteration (s): 0.48 | learning rate: 2.026E-05 | global batch size: 256 | lm loss: 2.929156E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 532.762 | TFLOPs: 34.84 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 11000 | lm loss value: 2.871375E+00 | lm loss PPL: 1.766128E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 11000 to checkpoints_280moscar +0: [2022-11-29 18:22:31,645] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step11000 is begin to save! +0: [2022-11-29 18:22:31,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:22:31,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:22:31,761] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:22:31,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:22:31,787] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:22:31,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:22:31,811] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:22:31,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:22:31,835] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:22:31,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:22:31,860] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:22:31,885] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:22:31,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:22:31,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:22:31,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:22:31,934] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:22:31,934] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:22:31,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:22:31,959] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:22:31,983] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:22:31,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:22:32,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:22:32,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/layer_13-model_00-model_states.pt... +0: [2022-11-29 18:22:32,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/layer_13-model_00-model_states.pt. +0: [2022-11-29 18:22:32,033] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:22:32,058] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:22:32,058] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/layer_15-model_00-model_states.pt... +0: [2022-11-29 18:22:32,083] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/layer_15-model_00-model_states.pt. +0: [2022-11-29 18:22:32,083] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/layer_16-model_00-model_states.pt... +0: [2022-11-29 18:22:32,107] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/layer_16-model_00-model_states.pt. +0: [2022-11-29 18:22:32,108] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/layer_17-model_00-model_states.pt... +0: [2022-11-29 18:22:32,132] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/layer_17-model_00-model_states.pt. +0: [2022-11-29 18:22:32,132] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/layer_18-model_00-model_states.pt... +0: [2022-11-29 18:22:32,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/layer_18-model_00-model_states.pt. +0: [2022-11-29 18:22:32,157] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/layer_19-model_00-model_states.pt... +0: [2022-11-29 18:22:32,181] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/layer_19-model_00-model_states.pt. +0: [2022-11-29 18:22:32,181] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/layer_20-model_00-model_states.pt... +0: [2022-11-29 18:22:32,206] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/layer_20-model_00-model_states.pt. +0: [2022-11-29 18:22:32,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/layer_22-model_00-model_states.pt... +0: [2022-11-29 18:22:32,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/layer_22-model_00-model_states.pt. +0: [2022-11-29 18:22:32,208] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_280moscar/global_step11000/mp_rank_00_model_states.pt +0: [2022-11-29 18:22:32,208] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:22:32,211] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:22:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:22:32,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:22:32,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:22:32,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:22:32,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 18:22:32,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:22:32,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:22:32,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 18:22:32,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:22:32,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:22:32,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 18:22:32,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:22:32,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:22:32,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +2: [2022-11-29 18:22:32,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +7: [2022-11-29 18:22:32,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 18:22:32,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 18:22:32,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:22:32,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +0: [2022-11-29 18:22:32,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:22:32,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 18:22:32,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:22:32,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 18:22:32,292] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:22:32,292] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:22:32,292] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 18:22:32,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:22:32,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:22:32,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 18:22:32,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:22:32,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:22:32,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 18:22:32,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:22:32,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:22:32,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 18:22:32,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:22:32,298] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:22:32,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 18:22:32,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:22:32,299] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:22:32,299] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 18:22:32,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:22:32,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:22:32,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 18:22:32,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:22:32,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:22:32,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 18:22:32,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:22:32,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:22:32,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 18:22:32,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:22:32,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:22:32,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 18:22:32,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:22:32,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:22:32,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 18:22:32,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:22:32,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:22:32,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 18:22:32,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:22:32,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:22:32,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 18:22:32,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:22:32,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:22:32,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 18:22:32,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:22:32,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:22:32,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:22:32,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 18:22:32,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:22:32,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:22:32,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 18:22:32,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:22:32,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:22:32,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 18:22:32,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:22:32,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:22:32,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:22:32,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:22:32,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 18:22:32,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 18:22:32,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:22:32,311] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:22:32,311] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 18:22:32,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:22:32,311] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:22:32,311] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 18:22:32,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:22:32,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:22:32,311] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:22:32,311] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:22:32,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:22:32,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:22:32,311] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 18:22:32,311] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 18:22:32,311] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:22:32,311] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:22:32,311] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 18:22:32,311] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 18:22:32,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:22:32,311] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:22:32,312] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 18:22:32,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:22:32,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:22:32,312] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +7: [2022-11-29 18:22:32,312] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +6: [2022-11-29 18:22:32,312] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 18:22:32,312] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 18:22:32,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:22:32,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:22:32,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 18:22:32,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:22:32,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:22:32,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 18:22:32,314] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:22:32,314] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:22:32,314] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 18:22:32,314] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:22:32,314] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:22:32,315] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 18:22:32,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:22:32,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:22:32,315] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 18:22:32,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:22:32,316] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:22:32,317] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 18:22:32,317] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:22:32,317] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:22:32,317] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 18:22:32,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:22:32,325] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:22:32,325] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 18:22:32,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:22:32,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:22:32,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 18:22:32,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:22:32,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:22:32,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:22:32,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 18:22:32,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:22:32,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 18:22:32,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:22:32,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:22:32,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 18:22:32,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:22:32,312] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:22:32,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 18:22:32,326] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:22:32,326] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:22:32,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 18:22:32,326] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:22:32,327] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:22:32,327] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 18:22:32,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:22:32,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:22:32,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 18:22:32,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:22:32,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:22:32,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:22:32,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 18:22:32,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 18:22:32,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:22:32,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:22:32,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 18:22:32,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:22:32,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:22:32,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 18:22:32,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:22:32,342] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:22:32,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 18:22:32,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:22:32,342] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:22:32,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:22:32,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 18:22:32,342] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:22:32,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 18:22:32,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:22:32,342] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:22:32,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 18:22:32,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:22:32,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:22:32,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 18:22:32,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:22:32,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:22:32,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:22:32,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 18:22:32,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:22:32,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 18:22:32,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:22:32,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:22:32,350] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 18:22:32,390] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:22:32,390] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: successfully saved checkpoint at iteration 11000 to checkpoints_280moscar +7: time (ms) | save-checkpoint: 749.86 +7: iteration 11010/ 11269 | consumed samples: 2818560 | consumed tokens: 5772410880 | elapsed time per iteration (s): 0.58 | learning rate: 2.024E-05 | global batch size: 256 | lm loss: 2.925740E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.286 | TFLOPs: 28.73 | +7: iteration 11020/ 11269 | consumed samples: 2821120 | consumed tokens: 5777653760 | elapsed time per iteration (s): 0.49 | learning rate: 2.022E-05 | global batch size: 256 | lm loss: 2.920650E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 520.792 | TFLOPs: 34.06 | +7: iteration 11030/ 11269 | consumed samples: 2823680 | consumed tokens: 5782896640 | elapsed time per iteration (s): 0.50 | learning rate: 2.020E-05 | global batch size: 256 | lm loss: 2.946444E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 515.721 | TFLOPs: 33.73 | +7: iteration 11040/ 11269 | consumed samples: 2826240 | consumed tokens: 5788139520 | elapsed time per iteration (s): 0.51 | learning rate: 2.019E-05 | global batch size: 256 | lm loss: 2.956919E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 502.073 | TFLOPs: 32.84 | +7: iteration 11050/ 11269 | consumed samples: 2828800 | consumed tokens: 5793382400 | elapsed time per iteration (s): 0.49 | learning rate: 2.017E-05 | global batch size: 256 | lm loss: 2.929491E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 523.195 | TFLOPs: 34.22 | +7: iteration 11060/ 11269 | consumed samples: 2831360 | consumed tokens: 5798625280 | elapsed time per iteration (s): 0.49 | learning rate: 2.016E-05 | global batch size: 256 | lm loss: 2.951544E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 526.806 | TFLOPs: 34.45 | +7: iteration 11070/ 11269 | consumed samples: 2833920 | consumed tokens: 5803868160 | elapsed time per iteration (s): 0.48 | learning rate: 2.014E-05 | global batch size: 256 | lm loss: 2.950497E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.141 | TFLOPs: 34.67 | +7: iteration 11080/ 11269 | consumed samples: 2836480 | consumed tokens: 5809111040 | elapsed time per iteration (s): 0.50 | learning rate: 2.013E-05 | global batch size: 256 | lm loss: 2.900419E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 509.238 | TFLOPs: 33.30 | +7: iteration 11090/ 11269 | consumed samples: 2839040 | consumed tokens: 5814353920 | elapsed time per iteration (s): 0.48 | learning rate: 2.011E-05 | global batch size: 256 | lm loss: 2.928820E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.174 | TFLOPs: 34.67 | +7: iteration 11100/ 11269 | consumed samples: 2841600 | consumed tokens: 5819596800 | elapsed time per iteration (s): 0.48 | learning rate: 2.010E-05 | global batch size: 256 | lm loss: 2.915639E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 533.726 | TFLOPs: 34.91 | +7: iteration 11110/ 11269 | consumed samples: 2844160 | consumed tokens: 5824839680 | elapsed time per iteration (s): 0.49 | learning rate: 2.009E-05 | global batch size: 256 | lm loss: 2.935809E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 524.015 | TFLOPs: 34.27 | +7: iteration 11120/ 11269 | consumed samples: 2846720 | consumed tokens: 5830082560 | elapsed time per iteration (s): 0.49 | learning rate: 2.008E-05 | global batch size: 256 | lm loss: 2.943433E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 517.701 | TFLOPs: 33.86 | +7: iteration 11130/ 11269 | consumed samples: 2849280 | consumed tokens: 5835325440 | elapsed time per iteration (s): 0.49 | learning rate: 2.007E-05 | global batch size: 256 | lm loss: 2.955413E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 519.774 | TFLOPs: 33.99 | +7: iteration 11140/ 11269 | consumed samples: 2851840 | consumed tokens: 5840568320 | elapsed time per iteration (s): 0.50 | learning rate: 2.006E-05 | global batch size: 256 | lm loss: 2.932379E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 511.027 | TFLOPs: 33.42 | +7: iteration 11150/ 11269 | consumed samples: 2854400 | consumed tokens: 5845811200 | elapsed time per iteration (s): 0.48 | learning rate: 2.005E-05 | global batch size: 256 | lm loss: 2.952201E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 530.339 | TFLOPs: 34.68 | +7: iteration 11160/ 11269 | consumed samples: 2856960 | consumed tokens: 5851054080 | elapsed time per iteration (s): 0.48 | learning rate: 2.004E-05 | global batch size: 256 | lm loss: 2.923342E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.254 | TFLOPs: 35.01 | +7: iteration 11170/ 11269 | consumed samples: 2859520 | consumed tokens: 5856296960 | elapsed time per iteration (s): 0.48 | learning rate: 2.004E-05 | global batch size: 256 | lm loss: 2.928914E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 538.178 | TFLOPs: 35.20 | +7: iteration 11180/ 11269 | consumed samples: 2862080 | consumed tokens: 5861539840 | elapsed time per iteration (s): 0.48 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 2.934577E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 528.872 | TFLOPs: 34.59 | +7: iteration 11190/ 11269 | consumed samples: 2864640 | consumed tokens: 5866782720 | elapsed time per iteration (s): 0.48 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 2.914578E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 535.244 | TFLOPs: 35.00 | +7: iteration 11200/ 11269 | consumed samples: 2867200 | consumed tokens: 5872025600 | elapsed time per iteration (s): 0.48 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 2.953756E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 536.299 | TFLOPs: 35.07 | +7: iteration 11210/ 11269 | consumed samples: 2869760 | consumed tokens: 5877268480 | elapsed time per iteration (s): 0.49 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.938021E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 527.196 | TFLOPs: 34.48 | +7: iteration 11220/ 11269 | consumed samples: 2872320 | consumed tokens: 5882511360 | elapsed time per iteration (s): 0.52 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.920843E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 496.492 | TFLOPs: 32.47 | +7: iteration 11230/ 11269 | consumed samples: 2874880 | consumed tokens: 5887754240 | elapsed time per iteration (s): 0.50 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.943181E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 512.092 | TFLOPs: 33.49 | +7: iteration 11240/ 11269 | consumed samples: 2877440 | consumed tokens: 5892997120 | elapsed time per iteration (s): 0.49 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.940605E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 521.240 | TFLOPs: 34.09 | +7: iteration 11250/ 11269 | consumed samples: 2880000 | consumed tokens: 5898240000 | elapsed time per iteration (s): 0.49 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.916161E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.609 | TFLOPs: 34.37 | +7: iteration 11260/ 11269 | consumed samples: 2882560 | consumed tokens: 5903482880 | elapsed time per iteration (s): 0.48 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.918173E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 538.164 | TFLOPs: 35.20 | +0: [after training is done] datetime: 2022-11-29 18:24:44 +0: saving checkpoint at iteration 11269 to checkpoints_280moscar +7: ------------------------------------------------------------------------------------------------------------ +7: valid loss at the end of training for val data | lm loss value: 2.799337E+00 | lm loss PPL: 1.643375E+01 | +7: ------------------------------------------------------------------------------------------------------------ +0: [2022-11-29 18:24:44,242] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step11269 is begin to save! +0: [2022-11-29 18:24:44,246] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:24:44,358] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:24:44,359] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:24:44,386] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:24:44,386] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:24:44,411] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:24:44,412] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:24:44,435] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:24:44,436] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:24:44,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:24:44,461] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:24:44,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:24:44,486] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:24:44,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:24:44,510] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:24:44,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:24:44,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:24:44,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:24:44,559] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:24:44,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:24:44,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:24:44,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:24:44,609] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/layer_13-model_00-model_states.pt... +0: [2022-11-29 18:24:44,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/layer_13-model_00-model_states.pt. +0: [2022-11-29 18:24:44,633] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:24:44,658] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:24:44,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/layer_15-model_00-model_states.pt... +0: [2022-11-29 18:24:44,682] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/layer_15-model_00-model_states.pt. +0: [2022-11-29 18:24:44,682] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/layer_16-model_00-model_states.pt... +0: [2022-11-29 18:24:44,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/layer_16-model_00-model_states.pt. +0: [2022-11-29 18:24:44,707] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/layer_17-model_00-model_states.pt... +0: [2022-11-29 18:24:44,731] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/layer_17-model_00-model_states.pt. +0: [2022-11-29 18:24:44,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/layer_18-model_00-model_states.pt... +0: [2022-11-29 18:24:44,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/layer_18-model_00-model_states.pt. +0: [2022-11-29 18:24:44,756] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/layer_19-model_00-model_states.pt... +0: [2022-11-29 18:24:44,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/layer_19-model_00-model_states.pt. +0: [2022-11-29 18:24:44,780] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/layer_20-model_00-model_states.pt... +0: [2022-11-29 18:24:44,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/layer_20-model_00-model_states.pt. +0: [2022-11-29 18:24:44,804] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/layer_22-model_00-model_states.pt... +0: [2022-11-29 18:24:44,805] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/layer_22-model_00-model_states.pt. +0: [2022-11-29 18:24:44,806] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_280moscar/global_step11269/mp_rank_00_model_states.pt +0: [2022-11-29 18:24:44,806] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/mp_rank_00_model_states.pt... +0: [2022-11-29 18:24:44,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/mp_rank_00_model_states.pt. +0: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:24:44,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:24:44,884] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:24:44,884] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +1: [2022-11-29 18:24:44,884] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:24:44,884] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +1: [2022-11-29 18:24:44,884] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:24:44,884] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +3: [2022-11-29 18:24:44,885] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:24:44,886] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:24:44,886] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:24:44,887] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:24:44,887] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:24:44,887] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +4: [2022-11-29 18:24:44,887] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +4: [2022-11-29 18:24:44,887] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:24:44,887] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:24:44,887] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +5: [2022-11-29 18:24:44,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:24:44,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:24:44,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:24:44,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +5: [2022-11-29 18:24:44,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:24:44,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +7: [2022-11-29 18:24:44,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:24:44,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:24:44,892] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +1: [2022-11-29 18:24:44,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:24:44,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:24:44,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:24:44,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:24:44,892] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +1: [2022-11-29 18:24:44,892] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +7: [2022-11-29 18:24:44,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:24:44,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:24:44,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +5: [2022-11-29 18:24:44,897] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:24:44,897] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:24:44,897] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:24:44,897] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:24:44,897] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:24:44,897] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:24:44,897] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +5: [2022-11-29 18:24:44,897] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +5: [2022-11-29 18:24:44,897] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +2: [2022-11-29 18:24:44,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:24:44,900] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:24:44,900] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:24:44,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +0: [2022-11-29 18:24:44,900] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +2: [2022-11-29 18:24:44,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +0: [2022-11-29 18:24:44,900] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +2: [2022-11-29 18:24:44,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:24:44,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:24:44,900] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +2: [2022-11-29 18:24:44,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:24:44,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:24:44,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +0: [2022-11-29 18:24:44,900] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +2: [2022-11-29 18:24:44,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +2: [2022-11-29 18:24:44,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:24:44,891] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:24:44,891] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +2: [2022-11-29 18:24:44,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:24:44,891] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:24:44,891] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +2: [2022-11-29 18:24:44,893] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:24:44,893] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:24:44,893] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +2: [2022-11-29 18:24:44,895] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:24:44,895] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:24:44,895] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +2: [2022-11-29 18:24:44,900] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:24:44,900] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:24:44,900] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +6: [2022-11-29 18:24:44,900] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:24:44,900] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:24:44,901] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:24:44,901] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:24:44,901] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +6: [2022-11-29 18:24:44,901] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +0: [2022-11-29 18:24:44,901] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:24:44,901] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:24:44,901] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +0: [2022-11-29 18:24:44,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:24:44,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:24:44,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:24:44,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +0: [2022-11-29 18:24:44,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:24:44,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:24:44,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +0: [2022-11-29 18:24:44,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:24:44,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:24:44,905] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +0: [2022-11-29 18:24:44,905] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:24:44,905] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:24:44,905] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +1: [2022-11-29 18:24:44,905] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:24:44,905] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:24:44,905] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:24:44,905] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:24:44,905] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +1: [2022-11-29 18:24:44,905] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +4: [2022-11-29 18:24:44,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:24:44,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:24:44,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:24:44,907] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:24:44,907] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:24:44,907] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:24:44,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +4: [2022-11-29 18:24:44,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +4: [2022-11-29 18:24:44,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +1: [2022-11-29 18:24:44,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:24:44,907] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:24:44,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +1: [2022-11-29 18:24:44,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:24:44,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:24:44,908] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +1: [2022-11-29 18:24:44,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:24:44,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:24:44,908] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +3: [2022-11-29 18:24:44,885] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:24:44,885] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +3: [2022-11-29 18:24:44,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:24:44,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:24:44,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:24:44,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:24:44,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:24:44,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:24:44,892] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +3: [2022-11-29 18:24:44,892] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +3: [2022-11-29 18:24:44,892] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +3: [2022-11-29 18:24:44,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:24:44,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:24:44,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +3: [2022-11-29 18:24:44,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:24:44,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:24:44,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +3: [2022-11-29 18:24:44,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:24:44,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:24:44,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +3: [2022-11-29 18:24:44,906] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:24:44,906] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:24:44,906] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +6: [2022-11-29 18:24:44,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:24:44,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:24:44,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:24:44,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +6: [2022-11-29 18:24:44,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:24:44,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +4: [2022-11-29 18:24:44,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:24:44,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:24:44,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:24:44,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:24:44,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +4: [2022-11-29 18:24:44,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +5: [2022-11-29 18:24:44,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:24:44,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:24:44,914] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +5: [2022-11-29 18:24:44,914] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:24:44,914] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:24:44,914] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +5: [2022-11-29 18:24:44,914] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:24:44,914] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:24:44,914] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +7: [2022-11-29 18:24:44,895] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:24:44,895] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:24:44,895] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:24:44,895] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +7: [2022-11-29 18:24:44,895] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:24:44,895] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +7: [2022-11-29 18:24:44,898] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:24:44,899] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:24:44,899] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +7: [2022-11-29 18:24:44,905] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:24:44,905] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:24:44,905] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +7: [2022-11-29 18:24:44,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:24:44,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:24:44,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +6: [2022-11-29 18:24:44,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:24:44,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:24:44,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:24:44,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:24:44,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:24:44,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:24:44,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:24:44,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:24:44,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +6: [2022-11-29 18:24:44,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +6: [2022-11-29 18:24:44,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +6: [2022-11-29 18:24:44,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +0: [2022-11-29 18:24:44,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_280moscar/global_step11269/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:24:44,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11269 is ready now! +0: successfully saved checkpoint at iteration 11269 to checkpoints_280moscar +7: ------------------------------------------------------------------------------------------------------------ +7: test loss at the end of training for test data | lm loss value: 2.848732E+00 | lm loss PPL: 1.726588E+01 | +7: ------------------------------------------------------------------------------------------------------------ +END 2085609: Tue Nov 29 18:24:57 EET 2022 diff --git a/280m5b95b9/sbatch_280m_oscar.sh b/280m5b95b9/sbatch_280m_oscar.sh new file mode 100755 index 0000000000000000000000000000000000000000..b3016b5c6db29cf67ed6b07661627cdf219f682e --- /dev/null +++ b/280m5b95b9/sbatch_280m_oscar.sh @@ -0,0 +1,161 @@ +#!/bin/bash +#SBATCH --exclude=nid007571,nid007112,nid006774,nid007502,nid007506,nid007507,nid005145,nid006692,nid007218,nid007123,nid006124,nid006123 +#SBATCH --nodes=8 +#SBATCH --ntasks-per-node=1 +#SBATCH --cpus-per-task=32 +#SBATCH --exclusive=user +#SBATCH --mem=256G +#SBATCH -p eap +#SBATCH -t 48:00:00 +#SBATCH --gpus-per-node=mi250:8 +#SBATCH --hint=nomultithread +#SBATCH --account=project_462000119 +#SBATCH -o logs/%j.out +#SBATCH -e logs/%j.err + +VARIANT=280moscar + +# if run without sbatch, invoke here +if [ -z $SLURM_JOB_ID ]; then + mkdir -p logs + sbatch "$0" + exit +fi + +set -euo pipefail + +# symlink logs/latest.out and logs/latest.err +ln -f -s $SLURM_JOB_ID.out logs/latest.out +ln -f -s $SLURM_JOB_ID.err logs/latest.err + +KILL_SWITCH_PATH=kill-switch-$VARIANT +CHECKPOINT_PATH=checkpoints_$VARIANT +TENSORBOARD_PATH=tensorboard_$VARIANT +# Start from scratch +rm -rf "$CHECKPOINT_PATH" "$TENSORBOARD_PATH" + +# Data +VOCAB_FILE="gpt2/vocab.json" +MERGE_FILE="gpt2/merges.txt" +DATA_PATH="/scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document" + +PP_SIZE=1 +TP_SIZE=1 + +MICRO_BATCH_SIZE=4 +GRADIENT_ACCUMULATION_STEPS=1 +WORLD_SIZE=$((SLURM_GPUS_ON_NODE*SLURM_JOB_NUM_NODES)) +GLOBAL_BATCH_SIZE=$((MICRO_BATCH_SIZE*WORLD_SIZE*GRADIENT_ACCUMULATION_STEPS)) + +# Model parameters +source model_params.sh +MODEL_PARAM=("${PARAM_278M[@]}") +NHIDDEN=${MODEL_PARAM[0]} +FFN_HIDDEN_SIZE=${MODEL_PARAM[1]} +KV_SIZE=${MODEL_PARAM[2]} +NHEADS=${MODEL_PARAM[3]} +NLAYERS=${MODEL_PARAM[4]} +SEQ_LEN=2048 + +echo "Model parameters: d_model $NHIDDEN ffw_size $FFN_HIDDEN_SIZE kv_size $KV_SIZE n_heads $NHEADS n_layers $NLAYERS" + +SAVE_INTERVAL=1000 + +# Tokens: 5908231000 +# -> Samples: 2884878 +TRAIN_SAMPLES=2_884_878 +#2_884_878 +OPTIMIZER_ARGS=" \ + --optimizer adam \ + --adam-beta1 0.9 \ + --adam-beta2 0.999 \ + --adam-eps 1e-8 \ + --lr 2e-4 \ + --min-lr 2e-5 \ + --lr-decay-style cosine \ + --lr-decay-samples $TRAIN_SAMPLES \ + --lr-warmup-samples 28_849 \ + --clip-grad 1.0 \ + --weight-decay 1e-1 \ + " + +GPT_ARGS=" \ + --num-layers $NLAYERS \ + --hidden-size $NHIDDEN \ + --num-attention-heads $NHEADS \ + --kv-channels $KV_SIZE \ + --ffn-hidden-size $FFN_HIDDEN_SIZE \ + --seq-length $SEQ_LEN \ + --max-position-embeddings $SEQ_LEN \ + --micro-batch-size $MICRO_BATCH_SIZE \ + --global-batch-size $GLOBAL_BATCH_SIZE \ + --train-samples $TRAIN_SAMPLES \ + --vocab-file $VOCAB_FILE \ + --merge-file $MERGE_FILE \ + --clip-grad 1.0 \ + --kill-switch-path $KILL_SWITCH_PATH \ + --bf16 \ + $OPTIMIZER_ARGS \ + " + +OUTPUT_ARGS=" \ + --log-interval 10 \ + --save-interval $SAVE_INTERVAL \ + --eval-interval 1000 \ + --eval-iters 1 \ + --tensorboard-dir $TENSORBOARD_PATH \ + --tensorboard-queue-size 5 \ + --log-timers-to-tensorboard \ + --log-batch-size-to-tensorboard \ + --log-validation-ppl-to-tensorboard \ + " + +ZERO_STAGE=0 + +mkdir -p ds_configs +DS_CONFIG_PATH="ds_configs/$SLURM_JOB_ID.json" + +cat < $DS_CONFIG_PATH +{ + "train_micro_batch_size_per_gpu": $MICRO_BATCH_SIZE, + "train_batch_size": $GLOBAL_BATCH_SIZE, + "gradient_clipping": 1.0, + "zero_optimization": { + "stage": $ZERO_STAGE + }, + "bf16": { + "enabled": true + }, + "steps_per_print": 2000, + "wall_clock_breakdown": false +} +EOF + +DEEPSPEED_ARGS=" \ + --deepspeed \ + --deepspeed_config $DS_CONFIG_PATH \ + --zero-stage $ZERO_STAGE \ + " + +CMD=" \ + Megatron-DeepSpeed/pretrain_gpt.py \ + --tensor-model-parallel-size $TP_SIZE \ + --pipeline-model-parallel-size $PP_SIZE \ + $GPT_ARGS \ + $OUTPUT_ARGS \ + --save $CHECKPOINT_PATH \ + --load $CHECKPOINT_PATH \ + --data-path $DATA_PATH \ + --data-impl mmap \ + --split 949,50,1 \ + $DEEPSPEED_ARGS \ + " + +echo $CMD + +echo "START $SLURM_JOBID: $(date)" + +# bash launch_srun.sh $CMD +srun --label launch.sh $CMD + +echo "END $SLURM_JOBID: $(date)" diff --git a/280m5b95b9/tensorboard/events.out.tfevents.1669733429.nid005079.115144.0 b/280m5b95b9/tensorboard/events.out.tfevents.1669733429.nid005079.115144.0 new file mode 100644 index 0000000000000000000000000000000000000000..d58a968912346f02ee665e2f65bcd721cf6563f5 --- /dev/null +++ b/280m5b95b9/tensorboard/events.out.tfevents.1669733429.nid005079.115144.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e5efae4fabd76258a8c4b8add52b72958ed4c3b9c162d89fa3b3cf96efa186e +size 20062409 diff --git a/3b977b77b/evaluation/lm1-3b9-77b-oscar-results_lm-eval_global_step73814_2022-12-03-12-11-41.csv b/3b977b77b/evaluation/lm1-3b9-77b-oscar-results_lm-eval_global_step73814_2022-12-03-12-11-41.csv new file mode 100644 index 0000000000000000000000000000000000000000..179ae573dcd78ccd0d2279bc54973f773f171299 --- /dev/null +++ b/3b977b77b/evaluation/lm1-3b9-77b-oscar-results_lm-eval_global_step73814_2022-12-03-12-11-41.csv @@ -0,0 +1,10 @@ +task,metric,value,err,version +arc_challenge,acc,0.23890784982935154,0.012461071376316612,0 +arc_challenge,acc_norm,0.27986348122866894,0.013119040897725923,0 +arc_easy,acc,0.561026936026936,0.010183076012972067,0 +arc_easy,acc_norm,0.5071548821548821,0.01025873302244637,0 +boolq,acc,0.5431192660550459,0.008712475433089477,1 +hellaswag,acc,0.39543915554670384,0.00487945547466381,0 +hellaswag,acc_norm,0.5036845249950209,0.004989645929811447,0 +sciq,acc,0.815,0.012285191326386693,0 +sciq,acc_norm,0.751,0.013681600278702293,0 diff --git a/3b977b77b/evaluation/lm1-3b9-77b-oscar-results_lm-eval_global_step73814_2022-12-03-12-11-41.json b/3b977b77b/evaluation/lm1-3b9-77b-oscar-results_lm-eval_global_step73814_2022-12-03-12-11-41.json new file mode 100644 index 0000000000000000000000000000000000000000..b09d945c0b508f6b84e5578e2cbeb174231e3569 --- /dev/null +++ b/3b977b77b/evaluation/lm1-3b9-77b-oscar-results_lm-eval_global_step73814_2022-12-03-12-11-41.json @@ -0,0 +1,39 @@ +{ + "results": { + "boolq": { + "acc": 0.5431192660550459, + "acc_stderr": 0.008712475433089477 + }, + "hellaswag": { + "acc": 0.39543915554670384, + "acc_stderr": 0.00487945547466381, + "acc_norm": 0.5036845249950209, + "acc_norm_stderr": 0.004989645929811447 + }, + "arc_challenge": { + "acc": 0.23890784982935154, + "acc_stderr": 0.012461071376316612, + "acc_norm": 0.27986348122866894, + "acc_norm_stderr": 0.013119040897725923 + }, + "arc_easy": { + "acc": 0.561026936026936, + "acc_stderr": 0.010183076012972067, + "acc_norm": 0.5071548821548821, + "acc_norm_stderr": 0.01025873302244637 + }, + "sciq": { + "acc": 0.815, + "acc_stderr": 0.012285191326386693, + "acc_norm": 0.751, + "acc_norm_stderr": 0.013681600278702293 + } + }, + "versions": { + "boolq": 1, + "hellaswag": 0, + "arc_challenge": 0, + "arc_easy": 0, + "sciq": 0 + } +} \ No newline at end of file diff --git a/3b977b77b/evaluation/lm1-3b9-77b-oscar-results_lm-eval_global_step73814_2022-12-03-13-13-55.csv b/3b977b77b/evaluation/lm1-3b9-77b-oscar-results_lm-eval_global_step73814_2022-12-03-13-13-55.csv new file mode 100644 index 0000000000000000000000000000000000000000..f2ca582e01132108ca08c3dacdc56436b417803d --- /dev/null +++ b/3b977b77b/evaluation/lm1-3b9-77b-oscar-results_lm-eval_global_step73814_2022-12-03-13-13-55.csv @@ -0,0 +1,120 @@ +task,metric,value,err,version +copa,acc,0.74,0.04408440022768078,0 +hendrycksTest-abstract_algebra,acc,0.23,0.04229525846816508,0 +hendrycksTest-abstract_algebra,acc_norm,0.23,0.04229525846816506,0 +hendrycksTest-anatomy,acc,0.2074074074074074,0.03502553170678316,0 +hendrycksTest-anatomy,acc_norm,0.2,0.03455473702325436,0 +hendrycksTest-astronomy,acc,0.2565789473684211,0.03554180368025689,0 +hendrycksTest-astronomy,acc_norm,0.3026315789473684,0.0373852067611967,0 +hendrycksTest-business_ethics,acc,0.38,0.04878317312145633,0 +hendrycksTest-business_ethics,acc_norm,0.32,0.046882617226215034,0 +hendrycksTest-clinical_knowledge,acc,0.22641509433962265,0.025757559893106758,0 +hendrycksTest-clinical_knowledge,acc_norm,0.3132075471698113,0.02854479331905533,0 +hendrycksTest-college_biology,acc,0.2361111111111111,0.03551446610810826,0 +hendrycksTest-college_biology,acc_norm,0.2222222222222222,0.03476590104304134,0 +hendrycksTest-college_chemistry,acc,0.28,0.04512608598542128,0 +hendrycksTest-college_chemistry,acc_norm,0.34,0.04760952285695236,0 +hendrycksTest-college_computer_science,acc,0.32,0.046882617226215034,0 +hendrycksTest-college_computer_science,acc_norm,0.3,0.046056618647183814,0 +hendrycksTest-college_mathematics,acc,0.19,0.03942772444036624,0 +hendrycksTest-college_mathematics,acc_norm,0.28,0.045126085985421296,0 +hendrycksTest-college_medicine,acc,0.2254335260115607,0.031862098516411454,0 +hendrycksTest-college_medicine,acc_norm,0.20809248554913296,0.030952890217749895,0 +hendrycksTest-college_physics,acc,0.18627450980392157,0.038739587141493524,0 +hendrycksTest-college_physics,acc_norm,0.24509803921568626,0.04280105837364396,0 +hendrycksTest-computer_security,acc,0.25,0.04351941398892446,0 +hendrycksTest-computer_security,acc_norm,0.33,0.047258156262526045,0 +hendrycksTest-conceptual_physics,acc,0.2553191489361702,0.028504856470514192,0 +hendrycksTest-conceptual_physics,acc_norm,0.2170212765957447,0.02694748312149622,0 +hendrycksTest-econometrics,acc,0.30701754385964913,0.0433913832257986,0 +hendrycksTest-econometrics,acc_norm,0.23684210526315788,0.03999423879281336,0 +hendrycksTest-electrical_engineering,acc,0.2827586206896552,0.037528339580033376,0 +hendrycksTest-electrical_engineering,acc_norm,0.2827586206896552,0.037528339580033376,0 +hendrycksTest-elementary_mathematics,acc,0.2222222222222222,0.021411684393694185,0 +hendrycksTest-elementary_mathematics,acc_norm,0.25132275132275134,0.022340482339643895,0 +hendrycksTest-formal_logic,acc,0.3333333333333333,0.042163702135578345,0 +hendrycksTest-formal_logic,acc_norm,0.30158730158730157,0.04104947269903394,0 +hendrycksTest-global_facts,acc,0.22,0.041633319989322674,0 +hendrycksTest-global_facts,acc_norm,0.2,0.04020151261036846,0 +hendrycksTest-high_school_biology,acc,0.23225806451612904,0.024022256130308235,0 +hendrycksTest-high_school_biology,acc_norm,0.2838709677419355,0.02564938106302926,0 +hendrycksTest-high_school_chemistry,acc,0.2019704433497537,0.028247350122180267,0 +hendrycksTest-high_school_chemistry,acc_norm,0.270935960591133,0.031270907132976984,0 +hendrycksTest-high_school_computer_science,acc,0.2,0.04020151261036843,0 +hendrycksTest-high_school_computer_science,acc_norm,0.24,0.042923469599092816,0 +hendrycksTest-high_school_european_history,acc,0.21212121212121213,0.031922715695482974,0 +hendrycksTest-high_school_european_history,acc_norm,0.2787878787878788,0.03501438706296781,0 +hendrycksTest-high_school_geography,acc,0.23737373737373738,0.0303137105381989,0 +hendrycksTest-high_school_geography,acc_norm,0.30808080808080807,0.032894773300986155,0 +hendrycksTest-high_school_government_and_politics,acc,0.24352331606217617,0.03097543638684543,0 +hendrycksTest-high_school_government_and_politics,acc_norm,0.27461139896373055,0.03221024508041154,0 +hendrycksTest-high_school_macroeconomics,acc,0.26153846153846155,0.022282141204204426,0 +hendrycksTest-high_school_macroeconomics,acc_norm,0.26666666666666666,0.022421273612923707,0 +hendrycksTest-high_school_mathematics,acc,0.2111111111111111,0.02488211685765507,0 +hendrycksTest-high_school_mathematics,acc_norm,0.29259259259259257,0.02773896963217609,0 +hendrycksTest-high_school_microeconomics,acc,0.24789915966386555,0.028047967224176892,0 +hendrycksTest-high_school_microeconomics,acc_norm,0.3277310924369748,0.030489911417673227,0 +hendrycksTest-high_school_physics,acc,0.2185430463576159,0.03374235550425694,0 +hendrycksTest-high_school_physics,acc_norm,0.23178807947019867,0.03445406271987053,0 +hendrycksTest-high_school_psychology,acc,0.21467889908256882,0.01760430414925649,0 +hendrycksTest-high_school_psychology,acc_norm,0.21467889908256882,0.017604304149256483,0 +hendrycksTest-high_school_statistics,acc,0.25925925925925924,0.02988691054762696,0 +hendrycksTest-high_school_statistics,acc_norm,0.3101851851851852,0.0315469628565663,0 +hendrycksTest-high_school_us_history,acc,0.25,0.03039153369274154,0 +hendrycksTest-high_school_us_history,acc_norm,0.2549019607843137,0.030587591351604246,0 +hendrycksTest-high_school_world_history,acc,0.25738396624472576,0.0284588209914603,0 +hendrycksTest-high_school_world_history,acc_norm,0.25316455696202533,0.02830465794303529,0 +hendrycksTest-human_aging,acc,0.3452914798206278,0.031911001928357954,0 +hendrycksTest-human_aging,acc_norm,0.24663677130044842,0.028930413120910874,0 +hendrycksTest-human_sexuality,acc,0.366412213740458,0.04225875451969638,0 +hendrycksTest-human_sexuality,acc_norm,0.3053435114503817,0.04039314978724562,0 +hendrycksTest-international_law,acc,0.2396694214876033,0.03896878985070417,0 +hendrycksTest-international_law,acc_norm,0.48760330578512395,0.04562951548180765,0 +hendrycksTest-jurisprudence,acc,0.25,0.04186091791394607,0 +hendrycksTest-jurisprudence,acc_norm,0.37037037037037035,0.04668408033024931,0 +hendrycksTest-logical_fallacies,acc,0.2147239263803681,0.03226219377286774,0 +hendrycksTest-logical_fallacies,acc_norm,0.294478527607362,0.03581165790474082,0 +hendrycksTest-machine_learning,acc,0.21428571428571427,0.038946411200447915,0 +hendrycksTest-machine_learning,acc_norm,0.23214285714285715,0.040073418097558045,0 +hendrycksTest-management,acc,0.23300970873786409,0.04185832598928315,0 +hendrycksTest-management,acc_norm,0.32038834951456313,0.04620284082280039,0 +hendrycksTest-marketing,acc,0.2905982905982906,0.029745048572674047,0 +hendrycksTest-marketing,acc_norm,0.3076923076923077,0.030236389942173092,0 +hendrycksTest-medical_genetics,acc,0.28,0.045126085985421255,0 +hendrycksTest-medical_genetics,acc_norm,0.36,0.048241815132442176,0 +hendrycksTest-miscellaneous,acc,0.2707535121328225,0.01588988836256049,0 +hendrycksTest-miscellaneous,acc_norm,0.2669220945083014,0.015818450894777562,0 +hendrycksTest-moral_disputes,acc,0.2745664739884393,0.02402774515526502,0 +hendrycksTest-moral_disputes,acc_norm,0.315028901734104,0.025009313790069706,0 +hendrycksTest-moral_scenarios,acc,0.22346368715083798,0.01393206863857977,0 +hendrycksTest-moral_scenarios,acc_norm,0.27150837988826815,0.014874252168095273,0 +hendrycksTest-nutrition,acc,0.3137254901960784,0.026568921015457155,0 +hendrycksTest-nutrition,acc_norm,0.3888888888888889,0.027914055510467998,0 +hendrycksTest-philosophy,acc,0.24437299035369775,0.024406162094668907,0 +hendrycksTest-philosophy,acc_norm,0.3086816720257235,0.026236965881153252,0 +hendrycksTest-prehistory,acc,0.23148148148148148,0.023468429832451152,0 +hendrycksTest-prehistory,acc_norm,0.20987654320987653,0.022658344085981375,0 +hendrycksTest-professional_accounting,acc,0.24113475177304963,0.025518731049537762,0 +hendrycksTest-professional_accounting,acc_norm,0.26595744680851063,0.026358065698880585,0 +hendrycksTest-professional_law,acc,0.25554106910039115,0.011139857833598514,0 +hendrycksTest-professional_law,acc_norm,0.2900912646675359,0.011590375554733095,0 +hendrycksTest-professional_medicine,acc,0.25735294117647056,0.02655651947004151,0 +hendrycksTest-professional_medicine,acc_norm,0.23161764705882354,0.025626533803777565,0 +hendrycksTest-professional_psychology,acc,0.2565359477124183,0.017667841612379002,0 +hendrycksTest-professional_psychology,acc_norm,0.2565359477124183,0.01766784161237899,0 +hendrycksTest-public_relations,acc,0.24545454545454545,0.041220665028782834,0 +hendrycksTest-public_relations,acc_norm,0.2,0.03831305140884603,0 +hendrycksTest-security_studies,acc,0.39183673469387753,0.031251275910891656,0 +hendrycksTest-security_studies,acc_norm,0.2938775510204082,0.029162738410249776,0 +hendrycksTest-sociology,acc,0.263681592039801,0.031157150869355558,0 +hendrycksTest-sociology,acc_norm,0.23880597014925373,0.03014777593540922,0 +hendrycksTest-us_foreign_policy,acc,0.36,0.04824181513244218,0 +hendrycksTest-us_foreign_policy,acc_norm,0.36,0.04824181513244218,0 +hendrycksTest-virology,acc,0.3072289156626506,0.035915667978246635,0 +hendrycksTest-virology,acc_norm,0.2891566265060241,0.035294868015111155,0 +hendrycksTest-world_religions,acc,0.2982456140350877,0.035087719298245654,0 +hendrycksTest-world_religions,acc_norm,0.3684210526315789,0.036996580176568775,0 +piqa,acc,0.7149075081610446,0.010533270588738935,0 +piqa,acc_norm,0.7116430903155604,0.010569190399220661,0 +rte,acc,0.5342960288808665,0.03002557981936643,0 +winogrande,acc,0.531965272296764,0.01402373922116638,0 diff --git a/3b977b77b/evaluation/lm1-3b9-77b-oscar-results_lm-eval_global_step73814_2022-12-03-13-13-55.json b/3b977b77b/evaluation/lm1-3b9-77b-oscar-results_lm-eval_global_step73814_2022-12-03-13-13-55.json new file mode 100644 index 0000000000000000000000000000000000000000..be61d0d824fa7c6bea8ae396567606430e248b86 --- /dev/null +++ b/3b977b77b/evaluation/lm1-3b9-77b-oscar-results_lm-eval_global_step73814_2022-12-03-13-13-55.json @@ -0,0 +1,427 @@ +{ + "results": { + "copa": { + "acc": 0.74, + "acc_stderr": 0.04408440022768078 + }, + "piqa": { + "acc": 0.7149075081610446, + "acc_stderr": 0.010533270588738935, + "acc_norm": 0.7116430903155604, + "acc_norm_stderr": 0.010569190399220661 + }, + "rte": { + "acc": 0.5342960288808665, + "acc_stderr": 0.03002557981936643 + }, + "winogrande": { + "acc": 0.531965272296764, + "acc_stderr": 0.01402373922116638 + }, + "hendrycksTest-abstract_algebra": { + "acc": 0.23, + "acc_stderr": 0.04229525846816508, + "acc_norm": 0.23, + "acc_norm_stderr": 0.04229525846816506 + }, + "hendrycksTest-anatomy": { + "acc": 0.2074074074074074, + "acc_stderr": 0.03502553170678316, + "acc_norm": 0.2, + "acc_norm_stderr": 0.03455473702325436 + }, + "hendrycksTest-astronomy": { + "acc": 0.2565789473684211, + "acc_stderr": 0.03554180368025689, + "acc_norm": 0.3026315789473684, + "acc_norm_stderr": 0.0373852067611967 + }, + "hendrycksTest-business_ethics": { + "acc": 0.38, + "acc_stderr": 0.04878317312145633, + "acc_norm": 0.32, + "acc_norm_stderr": 0.046882617226215034 + }, + "hendrycksTest-clinical_knowledge": { + "acc": 0.22641509433962265, + "acc_stderr": 0.025757559893106758, + "acc_norm": 0.3132075471698113, + "acc_norm_stderr": 0.02854479331905533 + }, + "hendrycksTest-college_biology": { + "acc": 0.2361111111111111, + "acc_stderr": 0.03551446610810826, + "acc_norm": 0.2222222222222222, + "acc_norm_stderr": 0.03476590104304134 + }, + "hendrycksTest-college_chemistry": { + "acc": 0.28, + "acc_stderr": 0.04512608598542128, + "acc_norm": 0.34, + "acc_norm_stderr": 0.04760952285695236 + }, + "hendrycksTest-college_computer_science": { + "acc": 0.32, + "acc_stderr": 0.046882617226215034, + "acc_norm": 0.3, + "acc_norm_stderr": 0.046056618647183814 + }, + "hendrycksTest-college_mathematics": { + "acc": 0.19, + "acc_stderr": 0.03942772444036624, + "acc_norm": 0.28, + "acc_norm_stderr": 0.045126085985421296 + }, + "hendrycksTest-college_medicine": { + "acc": 0.2254335260115607, + "acc_stderr": 0.031862098516411454, + "acc_norm": 0.20809248554913296, + "acc_norm_stderr": 0.030952890217749895 + }, + "hendrycksTest-college_physics": { + "acc": 0.18627450980392157, + "acc_stderr": 0.038739587141493524, + "acc_norm": 0.24509803921568626, + "acc_norm_stderr": 0.04280105837364396 + }, + "hendrycksTest-computer_security": { + "acc": 0.25, + "acc_stderr": 0.04351941398892446, + "acc_norm": 0.33, + "acc_norm_stderr": 0.047258156262526045 + }, + "hendrycksTest-conceptual_physics": { + "acc": 0.2553191489361702, + "acc_stderr": 0.028504856470514192, + "acc_norm": 0.2170212765957447, + "acc_norm_stderr": 0.02694748312149622 + }, + "hendrycksTest-econometrics": { + "acc": 0.30701754385964913, + "acc_stderr": 0.0433913832257986, + "acc_norm": 0.23684210526315788, + "acc_norm_stderr": 0.03999423879281336 + }, + "hendrycksTest-electrical_engineering": { + "acc": 0.2827586206896552, + "acc_stderr": 0.037528339580033376, + "acc_norm": 0.2827586206896552, + "acc_norm_stderr": 0.037528339580033376 + }, + "hendrycksTest-elementary_mathematics": { + "acc": 0.2222222222222222, + "acc_stderr": 0.021411684393694185, + "acc_norm": 0.25132275132275134, + "acc_norm_stderr": 0.022340482339643895 + }, + "hendrycksTest-formal_logic": { + "acc": 0.3333333333333333, + "acc_stderr": 0.042163702135578345, + "acc_norm": 0.30158730158730157, + "acc_norm_stderr": 0.04104947269903394 + }, + "hendrycksTest-global_facts": { + "acc": 0.22, + "acc_stderr": 0.041633319989322674, + "acc_norm": 0.2, + "acc_norm_stderr": 0.04020151261036846 + }, + "hendrycksTest-high_school_biology": { + "acc": 0.23225806451612904, + "acc_stderr": 0.024022256130308235, + "acc_norm": 0.2838709677419355, + "acc_norm_stderr": 0.02564938106302926 + }, + "hendrycksTest-high_school_chemistry": { + "acc": 0.2019704433497537, + "acc_stderr": 0.028247350122180267, + "acc_norm": 0.270935960591133, + "acc_norm_stderr": 0.031270907132976984 + }, + "hendrycksTest-high_school_computer_science": { + "acc": 0.2, + "acc_stderr": 0.04020151261036843, + "acc_norm": 0.24, + "acc_norm_stderr": 0.042923469599092816 + }, + "hendrycksTest-high_school_european_history": { + "acc": 0.21212121212121213, + "acc_stderr": 0.031922715695482974, + "acc_norm": 0.2787878787878788, + "acc_norm_stderr": 0.03501438706296781 + }, + "hendrycksTest-high_school_geography": { + "acc": 0.23737373737373738, + "acc_stderr": 0.0303137105381989, + "acc_norm": 0.30808080808080807, + "acc_norm_stderr": 0.032894773300986155 + }, + "hendrycksTest-high_school_government_and_politics": { + "acc": 0.24352331606217617, + "acc_stderr": 0.03097543638684543, + "acc_norm": 0.27461139896373055, + "acc_norm_stderr": 0.03221024508041154 + }, + "hendrycksTest-high_school_macroeconomics": { + "acc": 0.26153846153846155, + "acc_stderr": 0.022282141204204426, + "acc_norm": 0.26666666666666666, + "acc_norm_stderr": 0.022421273612923707 + }, + "hendrycksTest-high_school_mathematics": { + "acc": 0.2111111111111111, + "acc_stderr": 0.02488211685765507, + "acc_norm": 0.29259259259259257, + "acc_norm_stderr": 0.02773896963217609 + }, + "hendrycksTest-high_school_microeconomics": { + "acc": 0.24789915966386555, + "acc_stderr": 0.028047967224176892, + "acc_norm": 0.3277310924369748, + "acc_norm_stderr": 0.030489911417673227 + }, + "hendrycksTest-high_school_physics": { + "acc": 0.2185430463576159, + "acc_stderr": 0.03374235550425694, + "acc_norm": 0.23178807947019867, + "acc_norm_stderr": 0.03445406271987053 + }, + "hendrycksTest-high_school_psychology": { + "acc": 0.21467889908256882, + "acc_stderr": 0.01760430414925649, + "acc_norm": 0.21467889908256882, + "acc_norm_stderr": 0.017604304149256483 + }, + "hendrycksTest-high_school_statistics": { + "acc": 0.25925925925925924, + "acc_stderr": 0.02988691054762696, + "acc_norm": 0.3101851851851852, + "acc_norm_stderr": 0.0315469628565663 + }, + "hendrycksTest-high_school_us_history": { + "acc": 0.25, + "acc_stderr": 0.03039153369274154, + "acc_norm": 0.2549019607843137, + "acc_norm_stderr": 0.030587591351604246 + }, + "hendrycksTest-high_school_world_history": { + "acc": 0.25738396624472576, + "acc_stderr": 0.0284588209914603, + "acc_norm": 0.25316455696202533, + "acc_norm_stderr": 0.02830465794303529 + }, + "hendrycksTest-human_aging": { + "acc": 0.3452914798206278, + "acc_stderr": 0.031911001928357954, + "acc_norm": 0.24663677130044842, + "acc_norm_stderr": 0.028930413120910874 + }, + "hendrycksTest-human_sexuality": { + "acc": 0.366412213740458, + "acc_stderr": 0.04225875451969638, + "acc_norm": 0.3053435114503817, + "acc_norm_stderr": 0.04039314978724562 + }, + "hendrycksTest-international_law": { + "acc": 0.2396694214876033, + "acc_stderr": 0.03896878985070417, + "acc_norm": 0.48760330578512395, + "acc_norm_stderr": 0.04562951548180765 + }, + "hendrycksTest-jurisprudence": { + "acc": 0.25, + "acc_stderr": 0.04186091791394607, + "acc_norm": 0.37037037037037035, + "acc_norm_stderr": 0.04668408033024931 + }, + "hendrycksTest-logical_fallacies": { + "acc": 0.2147239263803681, + "acc_stderr": 0.03226219377286774, + "acc_norm": 0.294478527607362, + "acc_norm_stderr": 0.03581165790474082 + }, + "hendrycksTest-machine_learning": { + "acc": 0.21428571428571427, + "acc_stderr": 0.038946411200447915, + "acc_norm": 0.23214285714285715, + "acc_norm_stderr": 0.040073418097558045 + }, + "hendrycksTest-management": { + "acc": 0.23300970873786409, + "acc_stderr": 0.04185832598928315, + "acc_norm": 0.32038834951456313, + "acc_norm_stderr": 0.04620284082280039 + }, + "hendrycksTest-marketing": { + "acc": 0.2905982905982906, + "acc_stderr": 0.029745048572674047, + "acc_norm": 0.3076923076923077, + "acc_norm_stderr": 0.030236389942173092 + }, + "hendrycksTest-medical_genetics": { + "acc": 0.28, + "acc_stderr": 0.045126085985421255, + "acc_norm": 0.36, + "acc_norm_stderr": 0.048241815132442176 + }, + "hendrycksTest-miscellaneous": { + "acc": 0.2707535121328225, + "acc_stderr": 0.01588988836256049, + "acc_norm": 0.2669220945083014, + "acc_norm_stderr": 0.015818450894777562 + }, + "hendrycksTest-moral_disputes": { + "acc": 0.2745664739884393, + "acc_stderr": 0.02402774515526502, + "acc_norm": 0.315028901734104, + "acc_norm_stderr": 0.025009313790069706 + }, + "hendrycksTest-moral_scenarios": { + "acc": 0.22346368715083798, + "acc_stderr": 0.01393206863857977, + "acc_norm": 0.27150837988826815, + "acc_norm_stderr": 0.014874252168095273 + }, + "hendrycksTest-nutrition": { + "acc": 0.3137254901960784, + "acc_stderr": 0.026568921015457155, + "acc_norm": 0.3888888888888889, + "acc_norm_stderr": 0.027914055510467998 + }, + "hendrycksTest-philosophy": { + "acc": 0.24437299035369775, + "acc_stderr": 0.024406162094668907, + "acc_norm": 0.3086816720257235, + "acc_norm_stderr": 0.026236965881153252 + }, + "hendrycksTest-prehistory": { + "acc": 0.23148148148148148, + "acc_stderr": 0.023468429832451152, + "acc_norm": 0.20987654320987653, + "acc_norm_stderr": 0.022658344085981375 + }, + "hendrycksTest-professional_accounting": { + "acc": 0.24113475177304963, + "acc_stderr": 0.025518731049537762, + "acc_norm": 0.26595744680851063, + "acc_norm_stderr": 0.026358065698880585 + }, + "hendrycksTest-professional_law": { + "acc": 0.25554106910039115, + "acc_stderr": 0.011139857833598514, + "acc_norm": 0.2900912646675359, + "acc_norm_stderr": 0.011590375554733095 + }, + "hendrycksTest-professional_medicine": { + "acc": 0.25735294117647056, + "acc_stderr": 0.02655651947004151, + "acc_norm": 0.23161764705882354, + "acc_norm_stderr": 0.025626533803777565 + }, + "hendrycksTest-professional_psychology": { + "acc": 0.2565359477124183, + "acc_stderr": 0.017667841612379002, + "acc_norm": 0.2565359477124183, + "acc_norm_stderr": 0.01766784161237899 + }, + "hendrycksTest-public_relations": { + "acc": 0.24545454545454545, + "acc_stderr": 0.041220665028782834, + "acc_norm": 0.2, + "acc_norm_stderr": 0.03831305140884603 + }, + "hendrycksTest-security_studies": { + "acc": 0.39183673469387753, + "acc_stderr": 0.031251275910891656, + "acc_norm": 0.2938775510204082, + "acc_norm_stderr": 0.029162738410249776 + }, + "hendrycksTest-sociology": { + "acc": 0.263681592039801, + "acc_stderr": 0.031157150869355558, + "acc_norm": 0.23880597014925373, + "acc_norm_stderr": 0.03014777593540922 + }, + "hendrycksTest-us_foreign_policy": { + "acc": 0.36, + "acc_stderr": 0.04824181513244218, + "acc_norm": 0.36, + "acc_norm_stderr": 0.04824181513244218 + }, + "hendrycksTest-virology": { + "acc": 0.3072289156626506, + "acc_stderr": 0.035915667978246635, + "acc_norm": 0.2891566265060241, + "acc_norm_stderr": 0.035294868015111155 + }, + "hendrycksTest-world_religions": { + "acc": 0.2982456140350877, + "acc_stderr": 0.035087719298245654, + "acc_norm": 0.3684210526315789, + "acc_norm_stderr": 0.036996580176568775 + } + }, + "versions": { + "copa": 0, + "piqa": 0, + "rte": 0, + "winogrande": 0, + "hendrycksTest-abstract_algebra": 0, + "hendrycksTest-anatomy": 0, + "hendrycksTest-astronomy": 0, + "hendrycksTest-business_ethics": 0, + "hendrycksTest-clinical_knowledge": 0, + "hendrycksTest-college_biology": 0, + "hendrycksTest-college_chemistry": 0, + "hendrycksTest-college_computer_science": 0, + "hendrycksTest-college_mathematics": 0, + "hendrycksTest-college_medicine": 0, + "hendrycksTest-college_physics": 0, + "hendrycksTest-computer_security": 0, + "hendrycksTest-conceptual_physics": 0, + "hendrycksTest-econometrics": 0, + "hendrycksTest-electrical_engineering": 0, + "hendrycksTest-elementary_mathematics": 0, + "hendrycksTest-formal_logic": 0, + "hendrycksTest-global_facts": 0, + "hendrycksTest-high_school_biology": 0, + "hendrycksTest-high_school_chemistry": 0, + "hendrycksTest-high_school_computer_science": 0, + "hendrycksTest-high_school_european_history": 0, + "hendrycksTest-high_school_geography": 0, + "hendrycksTest-high_school_government_and_politics": 0, + "hendrycksTest-high_school_macroeconomics": 0, + "hendrycksTest-high_school_mathematics": 0, + "hendrycksTest-high_school_microeconomics": 0, + "hendrycksTest-high_school_physics": 0, + "hendrycksTest-high_school_psychology": 0, + "hendrycksTest-high_school_statistics": 0, + "hendrycksTest-high_school_us_history": 0, + "hendrycksTest-high_school_world_history": 0, + "hendrycksTest-human_aging": 0, + "hendrycksTest-human_sexuality": 0, + "hendrycksTest-international_law": 0, + "hendrycksTest-jurisprudence": 0, + "hendrycksTest-logical_fallacies": 0, + "hendrycksTest-machine_learning": 0, + "hendrycksTest-management": 0, + "hendrycksTest-marketing": 0, + "hendrycksTest-medical_genetics": 0, + "hendrycksTest-miscellaneous": 0, + "hendrycksTest-moral_disputes": 0, + "hendrycksTest-moral_scenarios": 0, + "hendrycksTest-nutrition": 0, + "hendrycksTest-philosophy": 0, + "hendrycksTest-prehistory": 0, + "hendrycksTest-professional_accounting": 0, + "hendrycksTest-professional_law": 0, + "hendrycksTest-professional_medicine": 0, + "hendrycksTest-professional_psychology": 0, + "hendrycksTest-public_relations": 0, + "hendrycksTest-security_studies": 0, + "hendrycksTest-sociology": 0, + "hendrycksTest-us_foreign_policy": 0, + "hendrycksTest-virology": 0, + "hendrycksTest-world_religions": 0 + } +} \ No newline at end of file diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..24b0543fd97823854ae0c6fa3a2d5b52d3f55027 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6ca24048f8e910000a01059cbfd12e06a051781a1f9ee6416d6aece39de00f1 +size 95016023 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..308d62e9d7fa6fba6a0b38280295d81ab3707887 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3952b9ae4da9049614f2be494b16c73877f68d159efaab3c1c106ced919dbbe +size 95016407 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5f380c6202976b9b977f83e363867e8e3065a634 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:132452ee32ec3eda64a2526238f9df34e9dd1570e602c35a3dbf2fc3dfe80103 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..275d9f67d9480ab43f1c8ab167b709d817d6529b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1d8cbac5edf6aec03c5cea31638fa60f8212681c5578b676d89917ab00d03f6 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f25eaea973c847f2e448c7e3c4e5cc6a207e2f9c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f223a06aab31030487400c9deeccf8ff2afe6dbd1a087030757c79c4676ef354 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d09172694ae4804a707e050182576d1f76e0a693 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7370c0eb2c0e2029f663bdfa4fdb0281b6bcf6cc2581a82e20fb5ec89e639e22 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..159b2a1ffb8357a2a549350627203d3e5b233424 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e9184cd72d574b3d99cac3f4c431907d2215d9454a6a739a4682cc8f95a5bdf +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c440e2c34f1f574547973c24222828ab483eacc6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0ad98fb10b826f2965b13137aec1177031e8793c9e3f35c63ccdcaaf16affe0 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1243951808efcd5aa1357e3f6269d2959df91b68 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4153aa603d8dd8b6f558fbf99c32f6ab67720d6a1b0901af52692b82a246ec41 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d3293edd36aaec6d8e19da8792e4385d56617c10 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68676a65846f6bc880cf990cb6bf779815678d309d7b128986557ee27ddc2da0 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..93deab705d48d126a4a81ec6df292058e1fb0536 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:957df2707cdd1078e441ad86ef04a9fea1e6d90c7fba1ace90ff743b03c0196c +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1e34bab217b616d5b9ba87da6fa82fc5fc84e60c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db183f3cb7d716df32f8b4bcfd0dd41306d391751aa104e4a92aeb79a33626fd +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dd37e79424b1d8c1fe56d51d055504ca4b955fa4 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea8e64c9123f71207b9793abf55d7041d7902a433de8d6280070f0ae6e113f9a +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..46919bfd777b20912c44b4c929d544fbc6c28371 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaec11a8a6b79fc2c437c6b1ee4e9fe36511d6043349ced1e8e0f21f95a70573 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cebe4c549bb550ca02592ef9cf823b7ff0546ecf --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9b3796a9dcaab444a8bc57e8f07a851a174116b3d46ab8472e813e843c34755 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0fadf3ca02b7dbe778281b55a9d2069ea7915fbc --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32d55bb7e4ab9ce06b831ba9e4896b5a398018ef13468524f7a060b2adb5529e +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4a3021d6113edd16c251e6dbf1f1f5f3f90a4544 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:234f2e49b48156beaae66be7a151c2fe9675643892743ff962116a85eeff356b +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..094e6c5831479ebd941cb59c673b131a39ae090a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1cd5dff596a923a71dbdcc76d7a4ad1c77fc1c90859e24a0c4f6e90155c643a +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d579a52ee149ffe2b233fa1b3c41d4157bb656a8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:558f01356edf4fac79f069995c9e98a42d6a1a002ee360263ddd775b28415cfc +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c1be0ed086593978f4e07c6069fbec5f029683df --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:725aa2f2ed55856208830c0f02ae9c5e4fa3a92633c9a31cf84c44e7651a5293 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3362dc2a3b90ae7b414ee8db1f65f28b843652d7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a541c28b4d8427931276fe7817830783272b19609d51bbe3c6e9fc1165971e3c +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a44c90ceaf4367c71af74e677ae9b3badb266a75 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0278b6c6b992cf1bdde816d21f89473beae119b595dd89274c2ac615d9a8e826 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e99f086f7c6e7e2f78dbea03b53af5deac724f47 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d22a8e41be33db2087c4b940f6cfa5927f205d006dacab0a633073fdfb35cab +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b9a2de476cb64a15172d6d72b4ab5785b450484e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e696ceba34628d7a6d1844303a5710e6ecf3e126012b45e627a03d0736608f1 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..89e08d7b44f822af94be6f02938a1ab1d7fb8128 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af109695145e9f63cf5c57e71ce8dc1348efcef68e92f0a26716b98c78dbcbba +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..44c541fd5696899b0bb6ec5bee2e0e0429f2c9ec --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:124898b7b4172d6b661245582deada9908dc128c75d5b24f6f390901cf0d0514 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..569a2797b4a0f9e14b7ed64f25aa06cf1cdff0d5 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4807cdc016dc3ec1e7f5880dfea7700b06d594c96e43d58777697d4da3fb5bca +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e5c7c4f71a886e73ce908bd2ce38fb0b81b7a871 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:019c44a7a491143375dd7b61cfb12ee5e73244accfac18e312d40d5a316b331e +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a76ad1466854bd6b2d82ec853885fd6b93afddda --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebd207d6bd14cbd8d012a904fd6bbf46f543c2bf8d946c2e3c50a527f4e33886 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6ac60a2de447f942abe2fb5b7709867cec3f1525 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27c43fef4dd0ca3a4d320d8abff7403283b3df19028840a49ba0593f8a3ffe6b +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..67995ee0eb2f26a703d660e895d1d4115896baba --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4105c2ed1a5da64807373d2dad58908ba57e5eb2842dd4cddb71327d59c9967d +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4a64f204e4f35c8233a6fd881dd3f602eef5eb22 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87875c753393a35433d47236fef87dbb5317bc039250fafcb217affb7f7c654c +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d02816eacc383cc5a09363dcc49ac146b045a081 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed73f45e4706dd133663b3beb4defd648d89eb42e62446e6e8ce81acd83feb61 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..174bfde788becea447681a71e0fe04602ed94c9a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ff779a798b3880b7712270a08a1f2f1566ddd87747216a7b78664cfd3072171 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..26b7ec5237770ab2ffbaaba9218648901f7c5156 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af454329e4b264bfddcfa3884ea7eb687dec399959bce6c5a7d7a1629d7a9a23 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c2a9e5229a1a823d5325ae2960e69964dfc88d8e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53377458d9b166343c4cb9144ccac8fb935b9f430b510582650e4162102c049c +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9654e1a3d4ce8c5a4d46c7ce84627c6c18f267d8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6364693b3e95284211ac02c6ebb384822e0849d9b618ceff45a4f10d9462b8b9 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ec56ca80e87568f1adf90015e182e3367e2d80b9 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6c2dcad7cd55bdff410545602e4ad0dd226ecccacca34fbc4de354294506660 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..292bd5dc32d9f2c76cb5a0a7cec0fef8c6024606 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deddf97c1b1d3a3cbe3f92b37b5833dbf92559595c4e5cfd04e2c093344835ad +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..91e7743d3532a907899d3ee13be1eef9d97b78ae --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef927d5db92a32de9fd7bb54c0a1abbd25869218b6a3f986939f0da151d50715 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1fd5eb85f1c837d86e740248c1f3e3d15c87e00d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7bbc0fcf6c87c22216c12ee23f83b0438731dcba42e8832ba0a04e2e7369dbe +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e4b548f9c1b8ad76ff8714a35f991639890def30 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fab231ccc00920c26ba3c69c510187520dbbd44627ccf5c297cd249f9cbd8c5 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c1936366913094255c826a0910cc6c8cf8940496 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a6fa4a64eaf25607f53a555d146f2822f758c296ec45eea66993da410bc135c +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..90f567b7aa0b42af8171d7aa851fb31c66285e2e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e621ef7379bbe27d5c6a19a6956839f3dde60d58caebb0ed31334094e593efd6 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0fefbf5fb4f6cce9342b0bbe9ac37da078e231a0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a746e68ecaea21af8aef29e4538dc55bce98f9b019d7f11b1e043fc8d3ceefe9 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3fe0fdad5ab246e793d95adc9e380c620e1a7d54 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:284c50c3ab7d158e1a7ed872868d9424cc38eadaf00cc615389d6129924a694b +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..654ff230877ab0abe93c82c93a60f26c4b689435 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:308d2da63e230555398c2b6cd0bc3a592c47b12d7d56e5360c9857d0a5d4baee +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..182ba1dff1ed74c99e0d0fba9ac3c5aa93c75580 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b952cf09f0b4efd515d7c2be10cb9a6482bbabef8126c2432fde4781a5f3a49 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ee54427399394963901f9739419b28389ee40e59 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cd827baa1c1d50ba5486f4be6489b4cd56c9d5f3a9400833e21a28ebdd13a90 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2ab6af568376b7b9bb4009ab892c36c798932b29 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad0604f03cd5776a21a63e6275d564355cdeeced481797f2092f4caa1032ba4a +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ebd26d22e3ab4a0543f10f7752ccd5b2e4d22b74 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1babac71e2c4d76a69c28a2152c0839f0d8220833ea58e8a770c9e2f814c0404 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8345cb3857a8794adf4b4749ce9607c3305b368f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:859ae98cbd03af84a024b1a878ed264266cb51cfae602e93fc44dc5956e4d7ad +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..370892fc8a5b30b69bade83da7c457e138f09518 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06452bbc3a1121eff59f462ad8288ecd46e60a9d8acbdc595636c938910f4b02 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9ea01596f2062d78c14ea032a210e750eca8d7cb --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6c8fb55f0737ae4872bc38a5715967779f70f21affd78a7b8bf106ebd5bae86 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..39236efbaff7361b44607a4b0359f141db8147ad --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6b88457ca86c489c16cc73958ca5e22b76da6c2727ee9df6d0384ec5c640f07 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6814f227210627e991b773df9711498606d5858a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abfde9e95f140cc8861d99043b871748cf5b18d71dbde3edb89acd2378f0661a +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..49e704e1ced5f8326bd1a99a3de516760f6f250f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f2472c9d591277a0a69777d971979b50586af83326cb897486603d824f7aa28 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f46d659d65ea6c4f1e23b52612bf4b9ed0d33c68 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4b133d01acd13fde3e8a957812b9b4383f7c2579e434b63a69ae8761f08380b +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f22156327f657be1586bad36131efd40153eb158 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8126bb6845246682297fcac5c806a8a7e749026e00c650105e766edb60bf31cd +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1d2e0ff2ed979d02b57a8bb4ef6a047a0fd1be8c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e081f6804d2e218d9693df226a18976f3927cbfe2621ed5146c683d55ab3ca2 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..918f4892d993342d5784b3413cbd9ee38731d82d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbf40451c8ca0a00dda649494ccb5ff355f9842eaeb909818101427cfd15dc40 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5561851ed1e487670a10fd85a17a1e5f508764da --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c3c513e3b4c1f4536ed4d3761ae5b0dcad4647296faf21629960076933af629 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..76f316bcd4aef38290e2c50750a50e65972aedd8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c079666ac8288006176c291acfe293f346186b9c9796ccb9fbb212fed6e78612 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..476ce2d27c2fdbe2be0ee523c4c2231770c0658f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e7cbecf02a4640433aaa42b0b2e199955f4e06f52bbdc70502ad406aca23989 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..583b5e5a1c261b427167b78a602d5280d4d13ddf --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc82b1d18cb89f48c8c723239e129cc48556e0a58d5d385eed7059aaff4e2614 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a667056c32eb1a77b5e4ce4ca1a36247bc77f0be --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:271340195c7996c4eb96b6f7dfc892844c9ea775bd6a527d9a2081c09669568f +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bb8740935f0a22eaaed706ea0ff4c8f7a7573fa4 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b036b970307f4e88d8c8d8034f6bbee214d003d65653c107ec8c6fb72446a86 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5e254d56e073505f9ee19fa7748498fa80d1a6f8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40ce97791fbb9a31638e599d020780fde00ec35ed70b012d54fb17969a093c27 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..decc719a25883893dd58a8d134efa7d5654d78c6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f3dc6220ee96d6d9ee260dcabaeba369952c32bb530e0b44d48a2661230fef8 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..88cb419ecd0fdb5700af36f60de454048bb9118b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a136da57e1d8e09f91f18f7590f8ab546e4c43f3df7fb527bee493fa6edf66d6 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7af8a842db892873d668999189911794cda3b9e8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b49a80d21f1033e692ae3546fad42a19affad77f58f18e929890906cc8a81741 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..62aa1c3cba8e2530f4a36230077489abcaf7558b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76fcb4af6da65296611db8c24e00b8960c1cefb4aeef999f9aa864882a1b179a +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..46ae1ce2db7a6fe075ab791ae9ad13339395ef4e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b64af006378393a18fa68085ee1ab659f4059b7e63c948a40446e98fe357a1f +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d57936af0491549a1aea7a767238a0fba0236033 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8c01bab10d8e4bdce7327664e42bf4375bb9e8d4abcc9702bf1a2aabd081057 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0bb96b34ba967878d46aa461864c56bc3d03541e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21593d08ab593ae7573c9eddcada831ac2b54d1f2116628580441fa6e7f8956e +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4b11593f76c2549548ddbbc815900590146c04a7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7114be03f2aba8f471aea8356c420b09f69fc8d8f6dcc50b1bb8962414e430e2 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3d5f8c7e2f77319c9344bb01574990c07f803f7e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8733feef4b99252df649269962176b41118fb66b368d7befe006eed305890ec1 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..23a01dbdd84172857d77852cf3f4ed04f195cf09 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eaff9fa077d1ad7ec8bcaf3c3ad82e00dbcc2a21df7f71f833532242f059ab9 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9e980c02ddcb88e0ac1293892e4ab30bdc8c36af --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0360bfbcb01461cfe67e95d6e9c225ae5073addc18a86d1004afcaf317b9dbf1 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1ed7ec6f556edc72d6ae01861b146803c10454c7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:072dadb2c66c7dfbfa6979070fe66a51c8e3b1cded270d6f8a25a59e6ffbe1a7 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4d3977efc54587be2b5f0ef9a8582ebd9a280495 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91b036896a47a39bf42f2d5c4a26117da542f85776d6f65ea0298d906f01e3b6 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..16a50f1791c9e27f0d68bf2d63329cc70f818f01 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dc5e0c4906ee65ec068ac1b6b294ff6c6586e944bf62f675c27404a03211a88 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a246a1741b6c429257669783a8b2f7864124a8fa --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f7920b716d0cd9502c4fd791faf7c0ced52a0f8d20b42fc8e569d5159d605fb +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b056eae8a4f487b7edf25f85e1d8183d3a8a80fa --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cc4669a782221a1118491b4de1beed0f3c21bcfb4e2e32c076921aab7717a53 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..87ee471ce24917e7feafd92cd5ad4325f8a5548e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d7d020962ee1dfd508c7a99e578ad77854da5b849a1d607baa50665ea562748 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0407f53a4e0c212e18de37941ff8e814abb911b5 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff07d5999b84b4bd9b230d2c12a1a322e40a3c7f82111dfec4b7ded28d2840e9 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1ea37dfd7ddce53cd47f6a6a9237374e0e05c611 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:109cdad57ff16bf2877b0c0921630291224f90b65d8d06021df770429feaf001 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..585b75a9fdbf45d3f40a560d7447f5b82316c1e0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bafded5bcef165da2bdd0962c4a62eb63ef3f2b2b7ae7a71a8d7adee705cc997 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..885ccdb3d6b134efb9657b37c26772d1185eb849 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:983a75947da054e029bf6293596f131809408c256b0f4cd61713720a68cc4a73 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3808ea2f1a1bd21138153092cebf9313a05274b7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d3c1a8094a0e509098757f4642d1b7c5655f859515f0b1f2e9b98f33a4844dc +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a80ef0b27a7fd98ef39efd3d4a380784fd029974 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c060e2b1ef00458c96f43455de5a44e4424115bccbea4a28a7b7351dd9c7e704 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e40cad91a3a962a530efcb09d7af0a22119b675e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:517ac4d06f1872a1ed522062c1c67e530ae8d24730c726f3840af98c95a7eea1 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..36cbd3887c743f556cd521cd355379cf1e451e2b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b389729eb9ae73e69239adb4a906f26a6d5898f04ebd118bca3b0d790f1245be +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4040a85c918815f79940905b1d5100af105a39fd --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bae259b6db83c379661b430f324a40a93892f3e117da9f28e7bcfd8c2d4e2c30 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4ca2c7b70593286e65008f7cf7738ac289668c7a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11a4ae765164dac3b1e06fda43feb1747c2291f67a2d63c2eee95992b3933af6 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8a484a299e590bdaa83d8b939533315b8e521602 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18b68899d09b1fc625b098361907040730b6957e3ce036c7beebc21178cb4e73 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ebae0cfe42bf330c3eb37eeb97fada01d87919b2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cbc1ab9e21e2b0fd40f9897612558c375f9bc4105c6a04925116ae90d99db7a +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1843a19d34240519e0b662a0a63d10e14369a90c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c29718df37cc1d7d690a861a1ac18be0c3752ff3c9ff02d7741967c653f8e9e +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..eabd462c6ff80934102936cb1465f7b2223c57ef --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f56ca20d8a651dc39f56410f1296261a3caf4a34e70efd8ea3f66646e371f34 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..26d724d0afe7384ae9d400d1bbe03c8a9a300f32 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33ef14fc3be735d962ae75d02d60ba4dc2d6675e7dbdcc992ba55d0ad958bce0 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b6c05209145b2547d3cc7be927e3ca4bf2d69cb8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59f106184ee3f65397435804c2ddf23c89b5c960c22e6837cecddb6c3e999f03 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c278d79dced862de6580e96a8afb6347426866b5 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b4c321b97349941a613333c15c0a0d22072909ac1bdd3ade559da63e79c3865 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..097ae44edf5a3f7b05faa23c61d41e0841f347a6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47f98effafe890240a77d358d59d68e633826d42c93c05aa623431d5da1e184e +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4a12fbf8d9243f94320fd7fe0a6e2818c53b8d46 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5011a50e260d9b55f755150ecb0d48d3759a3c9fc372dc3cb699dee90d5f61d5 +size 95016621 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b3795cc5f9e747926caa77415cf80c3a55e87413 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3402791d543697e2b35a696fc3022001f8b8d7423be2640bffd9d2ec6747769 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..99742f0a78c1fac090c113f2930d0e9cba6af000 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a695a9c6a3fb8d441aa0feb01099ee140f36be82de5f5387685ddec69f09269 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5676977040e947868ee4a6cf1d816c943b186abf --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0175987c48847d08c8a96c42e1560659cb5125200f6bf8017d9a7e1e6e4eb6c6 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1cda207d1c1b4d5c78c30b6bdfce347d73b997ac --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0832e2b1acd209b6f3fc93b2aea955831df1cf0865a0771d828a16816780491 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3f25d30f24fe22ad247a4ad5a8c8d10dad036df2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e77ac1b62b296539c2df3719a814a87b8324e1e1af641af527e5a90da0a82d2 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9e4772360568d539b8459dd32f9ae37c91c6dc93 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b51aeec73ce4500e7713a03c1f97fe523b28d1aa7e3f8d3da8b8422a37cbc497 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6b601f217578660294d643b4d4ffc012f0ecddb2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c97e8ad76681bb49900fcf48a6d86febbc0c393bd9cf14519180c48ec7f61f8 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7e602088489ca4a7ca9c9baeb702818478690277 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d24d4b5a1691684c74d537c5eca78810ff5f805bf19d47148c6c96eea2f81ec +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8ea8e03cc92a764f7c04440cbb94618c6026cb2a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1ec946a6e94ebd66762a1fca52238c75c70c8778b8b4c82c771a9c6f41787ba +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..26ebd80e60cd447c7e1eb67faf0deb35b645423a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9f7e8a728844115e20d89d694a971e9a58e8f63143bb91f6cf1de9ebc6ce553 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cbe902b57c531c85026f44feb2784e8d0a6eadce --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:671c4d77b6c9a3a9860a8da8ff768d9b97f14a5d45885c4b4a25e6cbfcf4b755 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a593bdd80a10a7b598372a8c0cc8279dae014bf7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e72a33ae8645bce5818458aa992b178ed170c6e8b19ab2da35d8cd5b4274390a +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..da3754dae1e4a847abca828be0b798e9e8c83cc8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe4fd67b0efc427b5017c0ffdcf4adcf48934d39b96c91aa48d715e11c2c989c +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fa5948b0c99e8578966d9fc2f873460927d6e2e9 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa09e299947948eac3d2391f6e499ee17be8467050e14c91a8ca9a007b9ebc55 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..431bfe8db8c41b42d1883d7fc5e3ed0c1afab05f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e4c12e07fce1d4363f65082918795cd7b2a11f0f233336c54b32337011c60c6 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f94bc99544f92538ba60b2d9f6f03f07d1c8b742 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91083a731b0ac975c721de95e94d71ad082dc4b154b917856ec19d3c8c01bdb6 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d6532710f45a3525148c80ad008e45c24639f3b2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:090d7d163accec8aac67958bd4e2d046eef4499f3c328abdb1b320efc3ffd3e6 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f4ed8580df5d73eda256dbf56c380adb498ac3b0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c8092f5cc9fb357f050054a87e8c3931088e734d266cc1dc3a6646086cf0158 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..41c4905469be3a631dbcd473ba321c2a75b00d3c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00d65c362ceaa43711735ce04cb1d64c3c90dc1c5ee3bb353147de8522fd699f +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e7ded5c7224ba81d3a9d9e9cd076e6cbebb06ede --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da3eadb67a091f4b6715896a640c359d8b9471ce39e2a659281a0bb21bce53fe +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..80b8975413d82c5aa72ac119db0f609ba4d6ee69 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc0c8d36e863ae456f038091f74b02f32de47a0bee43bac3f3df7e264cee4a89 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..88754fd31b411fb3817e28841827edead4e7c30e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dfe25e8cdf48071d859c6d7d9aade9b7f37da93450841cc7c1d21c6e7a589ff +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7e7ce889eeb1905ed25f767577616342d6b72955 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b23f91e542dc4cfc41fbee72f0785e79655ef49acd025c8dd5fce4573d570746 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..abdaa4b6211bb0ad9df29b0224d5040fc9bc63c8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ce1e76ed115a600bf46aedc5a0b2dfa7addd1d1481d235aef4f7b13b6421629 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c6cdb07f12d6ab565f5984d0094575acd111d84f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e010dfd09af95752362c06a4ad425ad6399fbee6816f3bdf6560e2fa2930177 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7e6d320a62ac53ff0d94c0b9ef57723cd433f3b1 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7bfd0e73c01ad87c788534c195c35d503167c35f4c9eb801d1ae3db53724ac4 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..acbf07cd2a590ac5fbac2cb0b56f0a0f792bf4ed --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66ac695131ec1d0f9d1e29314fcf67c1e93ec84f51cff0daaf689c23d3794111 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7828330c654206a4cb97bcac6ce3af1c40fbadbc --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3d147c67ea298da741b53998c1c4aa161bc7577cfbcbbceafc5a178998b9569 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..301f0b8e7d0c0564aa42c55398c1b132121cf91d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c9f19c006536580ca7ffc29f7ea63f981f42710b31b584d28dc5a047a6f4a22 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a9712c313012fc82ac38e3ec2a25ad52379159d4 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a3d7003bbfa8e185ca3fd9691dcef98e801fe907a7517d17e0887f8075589e8 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..eafc2af87d722919dfbe460103c479d0741f8395 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53d2767bf4110586636b6ad7b4cc6e56be683aca7c573e80f7fe981f6005c4bd +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a957a61e2320d0fc9103cb6bf7eeccc402902330 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9879393f75b7d769b29395c74f1fff2ab0c425508bd79ee331e856a352271449 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..95d517b61a8aeaaa82599481fe3b4018a6b20774 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4af953efcc65012ed85d9f3ba6a37d17544b415c6640bdd38438ba3b20f0342 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e2733ba7502d1c219abdf6ac96e0144136c57609 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e213c0c5e160578efa3199d637e490af3188947ae404f577d4749d3fbbb911a +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..31416971e22d5e4c09ebb91b07e0a3db9940507d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad9a5ab98bb53c890ced66adf0eeb27352ae8f215dc28390d199997c08a49aa0 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..beafa68105f406a63bcc2dc88d58d9e413dff6ad --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c69deb1a0bc168c35959f2cf5a00fc422a122b1c6776e56462316681df520d4b +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f39377a32a3000cddbce682a60b4f32bdc536ba6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45170f4e1cefd2381952d57a3db39e84cd825ffa7c641ab823e9a69e9f3cbd6c +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3248a8e7f3c18a9f1d129d2479201d51759573f1 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3de4b3d89de9d867c26578ede7b5c275ee89c41585afe5c36da2ea1a0a7292e4 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b1d1a98834e54f6986196eac09ffe8419b9fc25f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1377b7211fed4a2f128e5092ea47e9109f5c06ff3b9f220a1e168dfc2724b861 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c10f80dd2aedfbb15f7b0cd4f7afe1f468ccabf4 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc48e9fca0124fbf0ee54d9981da7b51405981266210bc979e530d0de0a8dd69 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0ea7465e0dc6401af56b66a0a3b51f5fcd1a0270 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:840a0bdc4952f67029e76190cc53c4a1622e5399e655a00d512b31bcf562d36e +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..97e8a28eeeb2ce76978ebcfe830ff7a679b9f289 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f533023a2db9226d5d6f037d641042571435a33a0e7dabc4d32b3a4c8027134 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..19a38a798d6ccd8b58514593043b13ff699c5a9b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d01239eaffb90582539107dde61fd152b70e72edc336de3d746baa8ffea7e5c3 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..163a498f48766e31e33dca67e1011d4227f056e7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac800a294fad9ee8995ffaaa80593fc4b9286e36385ba0dfc39fbef71e185846 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..466bd389ca2aabab4347914a0bcb3896d5a16ab6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26519d6f40b174172f95fd3247f5bbf95820e8f4fe5fc31d8f35c4dfe6de5125 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c5cf72e7dffbf89cc6a2e85b17a2cdaeef544da1 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:646dbac21d432931faf19f1fe07ef9cff583a7b8b318e0392469f5724670c526 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ec959572c298e2d5bc036286607081a8e2264e77 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21406815a997de8bcdc7c7e8549d12a0c056baef309bb54ae642add64efa8796 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a167d6684d2b516220bc5c26c11703d3abcb09df --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8e2dd8cb7ba33994b01818a561d9022088cf10f875d9ec8ddbfea6dd5ea4463 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4359c7cd9bbb745be5e133825112f613886ccf2e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0787fb6bae871e44d53e139f755df6c60ef68e4ebaf5feca71156fc915c0d11a +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..901932ad03964a6bdcfeb0e93a8a1dcae6224a9c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47b816d5039bb6c738d0f61bb60a04409591b9fffe38197baffcb2356b5bc907 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..843271e69cb856879d9455da3788c0bf4e20dbbb --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ecd0b7f4379403f2c647c1709e0bb4833db1b124280a6afb61ed633550dd8e2 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..51a9714ad0abeaabdfc37756bb4c589c16a06763 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c69cc3a0574df3776beccb7850966bc67ead7d90633adc596ab9ff6e0aefe64 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3342817a94c19776e98b514695e07dab90335ee2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddd26d1ef290854015ee5a1a142ede4318503c331c34127ae2b2e33620c03fcf +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..eb676598f991581b995c9c31bd8897cd720c90c6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c902071239be0af30a6182b5357e8d57077a933af61626475a7b3159846a29b5 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..40b2576626ee6c0ecc6073c7377d1f9ae4d9c722 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:495b88270258c26e2b23a120efff55b17108d089fdd8bc539314b552cf28e5c7 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..314865a5b647e6f0a4983548591019289f8308cd --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b471adff42353e30b5c6149d6c2f4ad0e7f74806b46e2fa4605290ac3a6dfc0 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..569564de6f1f01de5763c536861876ddbcd5b022 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55b4c87878b621311b367be17990b91a1eaa9313189079307ab08a222f0f6b5f +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4ba8601436a19ca0c6272aa5bb5f4c4fcc4aa29d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c53efcfc375b2674e20d279668d7af376d5602cf962e20947d7accdfbef7426 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d877572e2221af78c4fca5eab7a533a559c539e2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a64d91193a69dbdf0cfbe8e02536c8f30461b09744eef3e7fb1e5953d2992a2 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2cfb9b7795b0b87bdc57fa3d13607907176fbce5 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26a628d982413c96d13138d211ccb17343265067f0d6b0652fec80a2d9470fdf +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..13a2a1097c455df2ec07593ccb14080e8f92d80a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ef31f5afd12441c2bcb639d01ef312d0bcbdc902c910e72997e48c234362644 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ae3dcce155e56884062d892dec47bbe1f4c1ee1a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff08d937b1b9230fbd806c4cd0f4e872e0699f5113323980874c3adf3207f9e5 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2d07570c9e6bec091dd020fc250d0c3d55150c43 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ec21c86150ab93ee7a1f234c6d26dffc4fbbb7590d39a0d6d043dff4b093ac1 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2da85ddd278288f5300c2b02884fe33281fa9017 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a979f26a9a566bf4e48b5b681dc44b3dce9f55cfeeba8a5a39df3661bf1974f +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8e8e011747180ba443a9f62bb1622ca5d4087ab8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa97578c79db7ae23c19780752ec8649b462cdd928f259ee54f1913d6042f64b +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f35e7289758e0fe10f22a9e0837e59b5c887b2bd --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9450b03a37c9ca4b97d7f8b50fd67f37f135a27cee92ce1a0d7d5100423ea377 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f5d6a6aa9f887a33fc24a3a54728fd8cf120e5cd --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf61edf7db4d0d168b88a7e64ecb19546a3b42b169d502299499b3f8e9f8f4d4 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9d32c81e9c86a1caeebbde6d8423caef1d97e014 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6a63badfd30cf574564a3a4dd82823c0fc930bf7b79861a027a074ae4190399 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3a6791182c20b0c4813a3850d88f43b9f79c148e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87e355678fa6f1b895c2659d22566da871e498167e6d918d46c3870192c89131 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d362429a1e278e3d5c8499b873f25030c19b97b9 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd5a719656cbfb7856b97a34419b7039e349d82e09c6e224887487c0f99d186e +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..860068912f83198296d3f99a83b9ca74ecc03c67 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c49a1979a3d135aeccbe4a9cd5951c0de36b6d8b23174d38dc5ffd2ee50cdf9 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..57ca990bbe5ef35622f6db204bc807e6ae3207a1 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2b9580598406720e4b64ff68b0532f0aed556dc35a6149feff6ca794d3db8ca +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0a8370b48fb1e1972f2bae7b820d339668b04229 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a405e3ce0e6f4eb167d96b36904732336fb6c734670fbe72c97cdddcc8950a48 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ef3c6a8e16571d9547f7c01b03910f7dc1519919 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:609f3dd666d6389b73d9ab1348ac2c32c554915b8bebb5f0658696bcc2215bcf +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bd972cc0a2c7e7839f10b6a273bfe755cedde1c4 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e9abe4d57d8b2c2bf1282a71e58e16caa76547a5ffd94f45ee8a3b492590f64 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b9ace56a16a11dd36cb3dad1f6ed893f7e60736a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4bd3d7ef534591e06f54662065939c0e098aa151549b3a04d2dafdfd367024d +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..302daf159b72e2f1b59cfea78ce5d756e5620168 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b8b4659ffdface7e2cf27751158a80e62273711f5b0388059de07ab6abb262e +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ab3366011939489f05edfdac0c84878f5ff5b880 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac55e07fd963563f68a37be1d96dca5245f7220e3d0e4facc36b6b62c2725f9f +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..edbebfc2bc4c26a535f603ad619977fb015a4c66 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:295cf740a27f1636e6362b20593a196808995579a6056328e7f3a9bf5aa53498 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4f2fd8eb34aa5c8e14f927fdb68e99934ecb43c7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9c5362265e0aa9db79ff801ebcabea1de22431113b3f2798a0d0450ca322901 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7f7e6d7febe68eaa95b6d9302beba06c1b3d6524 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03cebcc0e02088afa079b535f7bc4c6094172575674abe8e0250d014fa99870f +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e589684b58569e712b876b44c72a2ab6a5c2b324 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94faddfc7aba8165260443a01d22271ad4e7c00c4e078bbb361f8673463f27e5 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..31ac2fbd76a408c33e5a5e4e7291e5e80e4157c2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07200a524c557fd9cc42b66f39414b82c1f39fc02fca0a889aa1c19b42d59ddb +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fdf73e1aa0a3e4d07950bbb69ce4e40a2b622d25 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ff430eea8ae79a3b62f3d7182483707249df4b5943dad5ebbd1be0374ac28d7 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dab44ad107cd15be758a2a5f2af7db59c69b9e1f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9692cb01870efc188b3e8e68a57cd4c46db1167cd4737b3cfb370fbabd8a2053 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bff49ce3972ea58a1775698c27e7aeb3e1bbbaf4 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6b316eee03a8de7b6580ef5ac432137212f5b5b2f0472b474c4436cf698578d +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..433e25eaeed68dbff3648efba0373ad48783d1c1 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8f5b77555dbf25396e612d80719f858c3dbc891c3e3e2e227334c42f97aa321 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c5c7048252725747ebd36144d537bdd322b63ad5 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d9997ecb393b5e5fad71ad7f4c4b7f44553a89f06ce894ae41123e03abcee8a +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6b0581bd0aa3c60495eaa8a8be5be3f37a336e07 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30bcae2f816be7dcb4f39c49bc7e2d543bd7d0057c32cd46eac07c151a4c8312 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7c4db7215b4ea88be4be32c7359857d67ab1c289 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3c63ba6c73577f3a0d7629f7cc9e6458fbc7f25178cd31de4913fa136a2b0ba +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..41dd2210e77cb73514d0bd8baf271041563047cb --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffdd330b2f6e033507055e68a4a4a5bb34d13fb7833e36080bdd3659b1e50064 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8d56074903c11e23beffcd7063f22e76d8ff604a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a3183014ca61cea10a46df453bf66fc63be7b4ecef0866067adafeef966c609 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5e1d31514b57b097dfc5c898ac4b710d0b5aadd6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd23b683bf24e69a4ce24a7e12fe041aa2ee186efef041a923715c091f4843fa +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..86b33f778a7d7ed6fd63cf057ed66b24a2854550 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:599b731b03756a19f6dbb4eb2d5d5273738e4774da41254a539e2bacd13629b1 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9809800915444e22d1ab9ee306daccf91427a08a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b5ab75bdf9cc2483320c5b3076e721ebc91cb8dc77d192f85a1bf642e1bd094 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b9e68ae4ae8336e9a5eb0a723eba22aaa76d450a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61341d4488b4b0b41c7c2901487c8ce4ff279279de40f11c8b28b6b4551cc653 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7f0ad97fc116cbd98684b2254ddea9d212658388 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9088f5000b6e00ff2e7f7d5d06e4bb491d1310f606fcc62c6aad0861588bb0f +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4d57f08d27c19e5926a85e22228d10ecc110c465 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:659f81649acd08a01bcfecafd79e8b66a8ad81ac41f5e58c1e20a11ffb73d084 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..00923c2d896eff4f60702ebb1a6d35bbad9741d4 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71dd216b6887afb4b31338c275d249cc4d8057da2f13d4e3088c915caa382cee +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..34d4d96801b74b2f3270ff824e1a22b46c742f58 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdd0105fd9a624924def4cd69e394c6b2f1915fc7e69c57eda2cb8ba6412953a +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c1a1acc7fc0998c16cfe6845b1186e2e57f355eb --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00800ebd9a755674c32ef4ba03afceb68fc29f9886afdd9d02990b9fbb5c5729 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..57ff33a1cc7dce55a2bd8d16ed868085c614b775 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0ccabe0dee4f86daae5f3a28937a9dbc1cdf53a4c1167cebbe9d6e5533c21f0 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..15039abbc81e77e71077e25d46aad9e548f285aa --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37d5d5e321bee67cb0cf8078a10fee44467a89c14873fae96e1f5931fd3bd3fd +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..34a3d892249c76935ca7cde6048516cad1fa5281 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab399e66efa3d5613ca8c6eb7e0fe29b6721daf1d1ece39c4d62f9074b8a7f2b +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2ede44f59fdfde2d877a7258b1f0b7c2318c8842 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:def03f963862c7474b5d7973d8a8b2d737d023d0b099559e32533bfd3d05e158 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5f871f5f3ab27f773e179be430e2ed70611dbcc6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc2f224eeace17b12a6125fce49815afebc50ec8a5aae3196688ab4fb53f6e39 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2a17af53a8f3a66f2cc5e6bc78fca829434b532f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a7284c9a5ab59c6288d480bc187bd7ce1bc160120a8b6970dcdd923cc7a1a18 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..27337d0b96a5a69120af13d2d57643d69f56399b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:349af38022182c4a6d288a878c09ccdf750004e9e8e017a869b2e3611f6cffe7 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ca8bb0b31fbdd5dfc006dbef84681bf302b0c908 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08f021654a895105c5afc70724bbf6c1c9fc357b51e80811bb07fbc1e840cbfa +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6b61d509df65c2ea45530425bae64e6fda99514f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ebbc7264563b9bae7f42e2bf7ec85b03ffbb51a6d2d31ff197081fb8d04a65b +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a5175178a062c200de0a70a2a8c847736709a256 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:709f84d4ede0fd40666227ca911474b29855f4483cd860f2935a545b55f1c19f +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4b04fb0d1d2b31bbfd4ca44523f66e554d59c44b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:036c340d14ffa09b2c71853b7aa33136d0447914c6a029d6d70e1f26934d5cb4 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2b426b18af021afeb452361461ed07e629c7cb90 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fef8c143c440ff8bdfd9b8bc6c59f4dcefb553602468302a49300e433acd06ed +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6fb877e68fb55ebe45701ac993332d3a2d00ca6b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:764cd218d78839958cb99aac65a6c7d1ed295963e8933364184d4e01e2864ebd +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7b226e805b0065a0097ee4049c0546cc05aa8ff7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be896be142cb453347608a594303a5bba5402f5d5a3e6cf3e2be646c03897dc0 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ceadbc48e434e0e63e377610519980e46a2c5473 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:941da99ce5a0611c75125a22cfffc8064389cc63fbdd17607db90ba23ce6f969 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..68bfb9c3045950856536cb31d606304f0a244153 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be7e06a9665f23678ad4e28cbd55a340d4aac2a0f8617966941e6330d6a526c3 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..da89a116d2fdba7a7984df219e94de53c97281a6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:010661973aa1c4ce911cbfe841f09e6f3acfdcf94088a7a81df06b34cbd8b21b +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..99b851a3f9b08f1587d02be908f96c317aa0ff1f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d975e46f9afaa1c4fc607d5288ebb5e8555498921c49d902823e6cfdc679ab46 +size 95016087 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..912a1f71d6685fff43d37d3f21841009551d2680 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26f41edaee8c4174fbff05d48885f413557aea441ee5b45c6d9076f35a8598bc +size 95016471 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4263bf23eb13f6836be519f38716dfb15a82cd70 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:927109d23832469f14c13bdf07fe65f60147bae6030b7fc75f482cac7ac59911 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..094c636b7608dd18ed3e866c47521f7767fb015f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9577c6abf2978b5762355e5173f6809d7c6610519f7b7274c31371358d5313a4 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2e82fb6b5bda3eb0f45da15a7e3cfb7fd1f29dbf --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ed6788bb61fb8135fd970bb296789a8b9320ffd63a4d8b0eb94c6818467fb50 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..da2006adc8c40899cdebfc5d65f19595694f4897 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b150493829a898e57921c45380a2bce5f266a4e23639f9296b968d52a64beca +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6ac1bed4f6c0c31aedd896b7054cf660ef720c0b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f64ce63e141b2ba3de51c29e1767302a8370cfe5d2ea88f9d635b26c2d009c5e +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..785bd2729ba5d87d04fb68c3643064e91e9ffc7d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68f3bfa0d27ec50c32b723a3add7964ab4b2657a50e5c652cde58974a292e2e7 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4ab21691976f2bcf5fe156b96ed63c4efd188132 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10c7f2744732759a07409a519aae87716aa0a80f2122386b73cd989310379f3c +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f40c63d9ab35762f423cff00ca13cf2e49afa52e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3b4550e3e3791cae7e1cf0fb5d5312a9691b74ba6255d4fd38bd19c0a9c0ba1 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8a907477fe058bea24bac488cf8a0376199b8ef2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8902029e474edd0b68b8e5bbf59f73f580b4e133893f2231fbd9a4d0ceae42eb +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..107370f1c18ec16aa843da52932ba923411c07da --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d65356d9b2b0273e47f89ba48d7fe2a4623de9661003b383bcc44389cb47b589 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dd35a303313f9b72454eb787abc86547a4753e55 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5043b48f2cb1b17383d3bbf55e2d02c0808f1031149dbaadba938bf7acfa1e0d +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..316c03c3d0365060b8c427488010972cfcea0d96 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:426db374382c3d426ccb596584aa193b57ce96de8af39bd8653e40dfb97a79f0 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a771e7dbdbe27735bd493dff248d93e6057a5537 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bf94f0a424bc4baf3fde43528528209e76bb44aa806a3083529344cde14d9a2 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8820e4214ea070a8110dc4c99d1968950623e085 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f06c2bb7adc05c81730976ce7437361f0a6e41abea11fbbf8b5bc6b8d82c9dfb +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..286c054de0f1d138f4497d8f6c168c274f6dcd78 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccc574302267aeaef4c66783d0b66a9bd38a7b44597bfd3377b6c71f5ba6c5ff +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b8a1464a8683de02516994d89776f47a7a2a24d5 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b98573f9d2a3a4f94ecb139e7b0bb0019076166a3242783adf802299a704c761 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1f1687d23cee140b83b8f01a522fec0d222a7134 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:464e2575353cebc4bee22cbd02de6c12364b9c25af99f2413e9cfbf936cfc1b5 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7bdab52f0e79b016d172cd69b9de9028544f1f23 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b5cbbd51802f5977d9071d24877a15e74aad175601e6bd1c3bb02940f5aeb71 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..75d0054774a3aea4a54221161b8b5f0b9b44cf83 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff01816aa2a373fb70aae8952dace3ec79aa0880b797fed77ea0dcb37af311e0 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..77767819dc0911bbb1c25fd1640d034fe916ed79 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73890ee014527b0262012af7b0e93d3084d0886af86685c3466fd8b8f276c682 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..027f14f11235eac5caeef97fb230eb5a4190491e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b50a07636e62e1c92354642046a9e2b51559cfa05586418f6b7f100f85269ebb +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2155e944b9ca422dd50624e96a92f304e2d65cb7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f94bf51542626f3627246d12a21b17c9b9e2be77a5be81b5edde4930fb643452 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a1439ebbc8c28bf6af3feb7bc5ffaa9bbcbbe75b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9015e44ab2d9f9d94e5b27dd8072886bf687832d95d20f19deb30afa19012bf4 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bad649e88f9f5afb180508502f2ca27ca4133ebc --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84cefbfff1524ae26a5c1de0b3b6b0c6da15203386c833286e78ff358f02f14b +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..829962cfde207713a640e8ca4e50b5192b1b617c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7632e36510b7410edd80372e726f210e15f9ac56f4ab84c4dcbbd10aa8c1b8d8 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b8fa8f3e51ec076bf070eaba165008608dce14d9 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01ea33a357f6db68438ce56877457996584be165860607cf2c6dc5687325d23a +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..36c7e1736dcd1b70f711563150c87de5b969635f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d0b6c91560075406ef41c8672277f9e454fee75ac1fc1ec4028e79ff391c271 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..83e74974886ed6e9ca6801b9ed37a8dd104d7c68 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:193d0cc631d057a93d934b15a05987ae3422f761ee0233716e748eb1dfbc0738 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9a19ea835e3fea5fa8d5481b61f4cd40b522e809 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb562d312f70f3b0aed7772fca2e109b3d1d2fbd94cacb200cc2ab7c9db66ad9 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f7f1d64316efa76d58ade151715ac82e807ca4f8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b443f717d4ed35419ca197df1ee06dfa157f20d60323b0cff761f14c1d31a55 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..019ab8ef0e3b4bdcfe162f94606cbb1b4753788d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90d9625ad1fe9fcc1640fbc2286b8599a273d868b8d4626e0ab4049abd42cf66 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d0a9eeec09ba6493cb5d00f508c085a104c8cf55 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2b9ac97f09a524b35e9e5fffce535e1a23df54cefc64621ef8fb5932a0c4146 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d3c3ffce9afe0646deebcae189ef3d311f16ebd2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f6eb0d2df61214dc07e995ab6678a422c3e7ffe5aa296f97dbaeb8bfa9bfb45 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..407da7a5a8d4c0d90f9e23cea58cdfda56379ec2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be6a20be9a5e59beaedc7f79c4bbbafc25e0afd5cb7f0cf35d72821c85ea58e9 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8b8efbb1dfb4d80ac892aedab0322f1b79046ded --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2e7919687be607b350e46cc7a35759202da2dc4b8cb3145cd3addfbc969eee5 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4dfc35141cff5c5b6bd4da8f08eefd9e81066232 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21410f21cc59625d755bbe2ba9de303f8da79d1360dbb16ba2a3e4b39b2ea039 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6b8d56dd22402af9a6c94763c136c6c29d85d32b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a06aca943f4cde973c91d77bda696a064be37963fc2334dac3ee60b2cdcfa75 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..49402c03acc931f097c7a4a107f5930e281ef484 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:699e1c2955a0b92332df342f82ebca8ec0b23620efbdad0f7c97540a663754a5 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6ea649dd87d7b4ff4212ec2e754881f12ed0ce38 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad2b81520c323d3bce227b25c162f49dd86bf2d09689fe609456c8fca7fbc878 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b85d5113f6b4bcbba987c33ac79723311a23c195 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba6203d196207f75d9cd2df1715b0166e831d27f2162b5e6c937bab6449cc57a +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..609e61fe4c6ce046ca88d3b68ddca6a5a3f0eb8f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c66b49f239c9f8612a19613618a3628883a8584b1bc7a4ae6c73b81524da5be1 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..27253e99a5bf550de7d5019186cca837db7ec059 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c327bb61251d54b561c8fa641370916e801897528ea6f4528dc9f45c17368772 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..63019cab73318286789ceab9bb7a03961e058380 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a14c585192d5feb812d590acb8b2ffb52bc2b9d80f9bc3caeb85abe1e9d0d7fe +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a552085a1f2bec0abb7c0776e55a10f15013cbe8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9152c06ff200e0253fc15d396545d2edc5c9476368f1e23b60066304af6832e3 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a5b51edd0fbc4b02df38a480fa43e0df9a634a1d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c70f187d9aad16d6f36a8361134e71e7b7927fab31dd7612def9bbafd2ec0a24 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6eac8cad73bfc7fd998331797a1df784ec2de6c7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5730729b33f1d275f8987fd02f5560ccd34586aa4cb69882dc5fcbcb1c327c7d +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7d7773a826d2882f88bbd3c1cd00135065e763fa --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daae5bce6b15c002d58b13f9e87c6d5cb5d1b561e6ccd231de463542a59b34e7 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f3185cecdd1c7af4a49177f5a1e4edc5c0661dff --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09db4a886500f66a1337ae6132282d7f11e1827767b190104c7895aca18d64f3 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0faa2da62416c076857d2768e18deb11ebcb10ce --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82e735591e47b05abc9051022cd70375666d243d87bb2ebb3b501d6278b7f830 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b812c98891d7b2e28cd2cae80d5ce86fda68458d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69f6396a83afe4e625f9c6abc545db5259bfca85c1d8e355ebeba1d7ad2f2024 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b01ae3eb8fba780b919ae284fa8b2ccbfabaae46 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be376b6553b89f514cbd658d52ee257e2a75849cc4f3d7debae6d5af641766f9 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..afd94715cfeb5972c4d4e6d010713b59aba629e4 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fb28829d0bef90df6c10179bf4772b65c9a8ab6043c4a00090b546b6d1cd7c4 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4f2e15957ab2856336c5764ec7e2f30994815645 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc5ec1bfaddded1f0242129cfe3607dabe1b0629a99b128f59c778fcb650a709 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..66e46b82a744569c9089a612c57bb8003644e8b4 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8789cd5e60623e8cf064a436ee5713ec4f54b9d578dce5876c663b12233a737 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f1b3368b96db94be2a0bbbe1c008bff27184a466 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80595b8b951360478ee6a2e7d379f9ffe1bb38ca1401fd173149ba3d9b9364c6 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0e0b742121bd0b33850374eb96fc8943c07bff2d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:833a74ddbc09d6108082cd158e9f82bce6ee07fdb5102e7e4d34b682b20d18ae +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0c5630f5dddbbb3182bbb9bf3047f2c6876770a9 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa7189fdbfbfce065f6459ecfb8e0259f498e2725d7353d62a970975d0e67c29 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e45bc8fc3daebc7220ca0e4b48dbd8ec8bb74701 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:151bb89e26eab2d5c36d5d4922b4fe3d9b6b23cd86f6c5367d5beefbce99d25e +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..32d3ab8be907503041cb1061e0e205529646a64e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d26e816bf7470bf9c9520a6f1cda42f3906b59cd63de758604870e1793091a5 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b557af97c9a0ba73ae6d9c3c3c61454c27b0771e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddeef15721ae64f5ae0e73d4f0aa11dd7cdc399a486e8e7579d35bf80354bc66 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8add10c83196804aec80bdc109e9614f86ec050e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b0676228e936a783f8c5829d3f6d0c4a8e7d5b2c3468741d3546afc4004df98 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d18d13b503ea1298a43eec40d9c8a0f5c016f0ea --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a6684cc65f58652bb8f288c91d9cf46331983e8e0971dcf53cfa090b1916806 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..247270bc869bd94beb449d872494aff4a561c6bd --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6f84f553dc6fa7d76fdae41f4f096babefc1793248008128638e178e5bb16fe +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..31f8ae3711d7dc0f526a599e8e9bbe38af9d1d6f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5304442f46ff60cf7205ad1de4c5a70b4d79f672cf10ff355989b3a10e88b99 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b2b9d2389120ce4be9a8fd2bd8cfe55f3eb86512 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5fbdd7a967f80950f1a3023a7ee529da83dc80f0d1a411e8f861012f7b6a9dd +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d475effdb9ca622236eebb824a31980097bbd06a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b966e193e06f043e616562185307502bf7a39fab3b2d402184f7d7cfb0335635 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3d2513a583cf5eb39403f87acdb8fa710aa44b87 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebf4d53a157395aaa340c397fc908b58a0601efe527f000d230252d9c3c2aadc +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..777f9a6b77ea8ef45f273fa3e2d921b22eb39129 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54936008fdcbf695f4a5ccf6ef35b4a074982368a51b6fbe39aec7dbd7aa85f5 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..df9417e9e486c0b4920767303bdf7fece3b6586d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f508a5e7fa991f47e780e7b78c478890bf4847ff67458dc6a5d4410373de21b +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..319163286b90b2e15defbe808e02ccea40a8fa80 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b10f06f61112920fb3985c6c5fadb095b1dfe0c32045300dc8bceedce0be1023 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c17e5e301ceabff3f3dd09d95cc737bd2f30b7d8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a21272b82311b9b8da3a77ab031e68d23a751e657029f55d24c12405fb925f23 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9b995cf5e08c62cb60095f137f8d71a47b33c7f7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:659004abd1765e19a8d228c4bd58e19d6ab998d3b449db439ab766f968e96e40 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..020223ebc824a76e863ba5bc1a1141270297e57e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b80d28b0607b65d091e096b951083aaaf89bb3724b50b1c38019026ca19206b0 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..89dbbbefe1f3d894464383e08e78805840c2bed8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f22954bbca323f73fdbf4f1dc92f44f5959f1b2374e581285fdf1e7b6709d47 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a5491f9e9e327e2009bde79123b9f914b25b1343 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0f3bfbab43edc477b101cdd568ea86dbdfc6fc997aa67decd73daf9b6f41aaf +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cefb547889318389692ea2bc135909918d9826cf --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2f5d8ef979ca19f315506181fd8b9927b6ecef719f63078d6b99cdd817c5b23 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..57d5f595b57b5ddd9a1818c4c99b1b8b2f78a0fb --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d30e248fe879da13c85e50617a362bd150ecfa72b86fb527e9f9e7a81894511 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cda40d20467ad6295d4e21cee3389f971a778ab8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e1117201851fbd9539cd32da51bf6f087f552f5c737d634dee5314f5b6a4f4d +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..54d8aca95d43f98da6055890c39f761c83b931c2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b26a275f26847dbbb2f0e4ce44bf492640ba2a1f5e3f328845763c1f2b2c58d0 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..57ad249e50661a4dcb9c6ad209ae386def31e530 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f885e04a95fd454b3ef3e88a1648873f769c10a3066fcce6dcd74faadcaf4863 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..929d5a340599d7b78601b78b93e98a823fcf1cda --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:008c0a06aa7ce50dc0174560028f374143bd21da17e4b1ca72d5529c017d7bef +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c74615752f9216db330b93be0f5fda387b794fe2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9e33e90cdb1e0a34bf332447124292ee0fe099f74e76f3d9fd95617bda027ec +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4654fc948de3b07179d9e9b13ed89584135906cc --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9323adb62718719b8ec2d5f47b58619f5c2fc97a99e71135bfc2ac515389a1e +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..91067b32f70d105cdf16c9cd7c57ad40bfa615ac --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:872b8ebc930f960049ede485d678f0870871ad8c8e3de10e8b7b620c088d5ade +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3ff2cb24240c32c6593f89d8c6964a8e2dc98cb1 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd86e1060b971454b22348b175d981e51aed614bcfb4dca8e4360051dc8a408a +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4992016a779c946c6619560d2f9c988f7d64179d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6be15fa3af25714ae7b18a1233eb26ba29f1de79f6dfb28cd4a20374224bfb27 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..48f1f8a29e7326f53a98b8baf3be0b750cb5a2c3 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16f3440606419fda317c9c4b5faf311f46041769f018075810ab5383c9aee787 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a37c73e1e26502ed5c9730cf2534969a1b6f93fd --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eccb96311bcd9f415b7310664c69533b41fdef98c0a61e0d2912bd8651411151 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..12957ca227dbaaca97ddf0835983a0f3cecee2f2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40bbf087845d544c190c963b8f403fcccf23be2339a062b30426c25cfb5e779e +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3a260ba164f3649d5be1fa0aab16b9645d7738c4 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b832b9fb9aa1c1b267722229ab255290eed884ee15ccbeb1ead4b9f0b7e0c55 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..81149b563fe5b9ac4dac4a2ebfdc0bd91c7a8489 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7c1bc63872309b4d9ee6dbe62a3485f0e22b5b7d17e635f48785b53a9e1f488 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ac75c6ddb0f71e8d95b0dedeb042375de15790fe --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:630ef245403647df3d4582b2eec87304251c38fd080324d090c28deeda3b4de3 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..62e6b0277fbd29e4d65d6818d77c708bdce846e1 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c46adbd41b86354c74289302f4c6c8182c7706949264d5ee487fde5f5c8c5ccc +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e017dc62779a2ecafc2a5f72313687e4f9f965a0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09f3475c7aa4d271742b3c0f65cec88b1cbb483ec8ad343b14d70a9dc5148cf2 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..843336bb7a50933e06734b8eda8c0988237ae364 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc60a2b025795eeb45e1fa7b8976255f8a5eb735d7719e733f8302c1ca9e655e +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..24110659350a88291307b75a5148e0968d49f678 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:228cd7272c5503f601276284798181704cfa9556a1f37edacb519b10c8002b9b +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..de5b6e982819292f4983c5da81f3d1950405b688 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24ae333002fae33d82a282fcc4b1046bf564fdac5d9915d89205882c72fa4cf0 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..50afff8479f6a06f582617a6fb587d78ece7a99c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2904e4e038c3285d20a35d9b88c3d9168f164633902c150b005ac4147f71193 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..953f6f178db98ee81ed4ee9935a9e0b0cc2d0e9e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a91ef33e1363deb87d2a591695bac87cddc0c9c377ada8a1f9ce9d7b5df14587 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..59012585d53694539cfc32802babca7179dedf68 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cda3669d99ab8080310a7dcc65e2de8daf3a701eebafff63cfb0b1da2ddc4577 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3c374b36c18bb9e3e9e2f12c1a2f3228e701a7e8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c6650707fdc2250616f5be74696d41bbf5300caa734c451ac4ec1c195b299e9 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e279b4a147d33aefc4e8a90569087c76da46d3ea --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f4b134a683fe47b9b21efdfeaeead30bed3e639fede3b573c55615a8f4f3796 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..594fe28364a4f2fbe58d37b47e5ac776ef27a0f6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a91d8efdd4b1a35f735d7bd75fc828044689c89c596c6cad891835413b290c27 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c55adf8228299b4bc4a6487d5943adbbe34ad756 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:511b0485048f248ce35893ffadf159784684531525b03a34b31a908864799fb5 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..df6a90ca9107641d2085c84a5e46350788031eb8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c91537fa5e665889ee92d10a32a609809e2a97f4a02bed1a3a1743b5bcfe13fd +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0061793b39f9bf1b4dbccc44c1d6074bd3e86244 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a31640c40e9c2aa5dce4aeafdffdea6eee8aaf758237a38d73932eda27607890 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d4133a31d9180ad0b20faf748f62a0bc7f830924 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19d8626159d03b1d3d1445ee43d908c0cd54a92e45dc2bae6e2e6963b81bbbab +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..44ac3457992a0ec544002913265b74116d27aa03 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85e2fa527696b862bbe4ae6e5432ac09b4cee710bb575f6bd3a66fece545e5cc +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5ae9ffdfcf46398b00df4dd2f3e97fc7e078d9b0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a7d17e39a482865f35f8030cbf6b528d823772e4ef9dbcc01b1c2977aac58c8 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6474ce6413cf143c9a9f19f05191078d0e86a7e7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f7a823a2eaab66e2762aff489f54e7ad7b8f0ccef862048d7a9bc47bb8c9983 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..76fddbbe5a905b8e0ce88d49458864f9da8fa2f6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b5918f43237afc4ac3b04da34913ff77c9dd7b289e72eecea37a9be9292d9d6 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a4860ec166851574865317a669121ba522bd1104 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bebc7e9f6e71b4c720e3e3fa06d4e2c10cd4124fc7bb85591fb9d563b5ce17b0 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f6ea14d44ea3385ff439ca1b71ba7293c4e9d55d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8456be8cc5ad67fc68a63a3e79aec1454192e7ba54040c54b566cf994ac5ddbe +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9ed19e7c42f4dcd233b060f83e65700869d02c77 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f72c5e53061c2f214057a735fb8c164d9fb893c1255e7d69dd0d1b739b2da400 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c221c0a60d586068d82b842e99eac87f33dbdf7e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:292a0f8ef0eb57d2a86d1c85e48931c7bbfd5a9720731afa13f3eed8f79f69b0 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5db4f547f822b90b80ce30944ae74ef91ec0b2ff --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f63f413bdc629a5022feea135bfdf2ec0c614f0bee132fdb99aadd3aed396b9 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0ea1553267816d4c4a1e579bf52666f9ed47b75e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f9a33e209b84531e6d96228a54ef5f98f2d1b34407b6a28a5647157173eaee9 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..223132a2fe90cec292ee88b262a1c2a51258f14d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2659e4bac08cec583ddb63d1b2f1e7283aa883d9cd30e8e716532d17a871f924 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..885c89595a758fadd5a073737a867a9e6a3b8a21 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaafa85f39630e35e2e4b6a88f2f8eba2678df06b7f023f41b2a1128845c6732 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..94f5c4c5e0f65ef26886a74407434d27569b5965 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49acc1facb6265cdac0af07776af4c1c2e3f1ca0e902671f2cf03a2a101cb985 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f79a06922ce098da6c334ce5d614f71ee4f3ae0a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:122bf3c4a70ddb5c696e42cb4c3a71ce4d08fe926eee22e1c7343043bba22b6b +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..43e89bbf2d448b7736b3c5b3f79f67222c3f063d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53c215adb8b8cb0df5a93ea2d5bddef01f68d8484fb0ebf39f6c4c2be0dfebad +size 95016365 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8993951d2f8c6101b3fe669b513fcb815745b24f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d92208007d7c03bf781ea6d64322bb0942993c4513b438ffe287c8c41c6b172 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c6c06fa3ddf6171e4e688f6bb7eb911e52d72d36 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe3cb80020a17fe715b3975a7b0b0ae31aaa7eabe6edf9e88f34b81b57f8239a +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a24fc8f4742ee296b5da147ed51a6568123888fe --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1aa5b0ed2491e5e0efc63ae835fdddb11be0d66ed2b4d77f2ca96a647bf4477a +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..31a454cce7946fa8a32eecf6a8257678c124ed11 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bfd826f3146e47773d190a309144b44cba4834bfa227246fe010354d1217320 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e4bab75b3a01104ecadec9094e312fbeff21f74c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf354bcfdae8d717aa31554f4c7aa8509ed7dd1e5f144cf6a55680ff90c1f038 +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..81a31154ea82ae3a29a4f9b63d9ff8453755dde8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7d200445353595e8954c3e909ac6f047109376d9923e94bbd90cb269e01622b +size 95016546 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..109eb33f6a66efb5af8f0f582db3cd1fc402a50b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f25d20ae128c215c581ea53acff9ea6b6a24e895d73cc9e8fb61da2c3deb340 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6fdea2b292b462844be6ce98c930ccb15e72de75 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c236dff55c9cf7a5fad696d700099d81fdb310d954399773aed4136c99936689 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e9aa67fbd19aa6bbfe6481a89bf3b6673715ed58 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fab89acff91bab0f7bd1cad70603f40997a00695410bbb58f11cd5e34f6bc28 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ee4d65a6487e50c9aabe66c52c94c9465da8030d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:778cfaa4f714a568891c5432eb3d8c540322210a9c658147dee2402869071779 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f85efb2df93488e7658f20a3cc24a4382dc95d7b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94bd25f7df868a18ee7f276f772da314a91ba4787dc0e5ed6a282c224eb379a1 +size 95016087 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f53b072a3592c506bfd0c7ea5104efb7c7b3e82e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaabcea1f2dbcff8e67bbd89413c27e45aa9facb6c69a3701a5cf45bd073df34 +size 95016471 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7508b4d229674d531ee108c71f02628a369e3792 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:416de89f67fe70370cb548a46447649b6ee11a8d782f33ad3c2db366ba23847e +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..91a8d95b9609ac1139f242277bf081ef4dc6c547 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c81068f47387e5fc5ad3408ff1fd33d8fcc71501085a5e03c59010cb7c23e634 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a3578fbd89da7f723cde0157fcbab1436256ef7a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:710101f17fb55a27a304e0da8189674577bcc8d1f798fec7276d68d7458f748e +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..29c69f6411e6fe1c02909eb9fd5cfc76fbed5215 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b40f94612da638d4384313f966020609ad7acdd9291c6e1126af4edcfe49a64 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..01614ad49e6d13ae3545a64a4272c37f0acac867 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cb15b213e9538aa6710b3a61aa66cd39e490695975c0c7b9d1505c7f8834b53 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..59ff3d809b596144fb5ac2d15ad481d66723b9fd --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:363ce8bb466375bc2dcc3110b5be03533bb0381f7cd82dae050c6104eb981855 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1b7695c5252494d1161b790700fb4cbfa934bc11 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a77da2794924884989a0f2f5d1403c187176875aeb3ceb47010ca82c96433123 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b63a8a9faa359b5830e484092c25e9fe5650c76c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d280ffaede4830382d87109cd16b94dbc00fc0d6e8e17993fdf2fbd11b5f0742 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..925357ffe5448270799dac459fd114fce7adb38c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a44049c481ee35a2fad214b35e444ea61782fa7122dee46b2bf50f0b116f2e39 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..90550822ca2fbbbc50e1f7c7abaf92c84ddfd8bd --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aac9634428cc41739bb76fa6c08c68e4bb3d4fdadb36631d3214e6ae316883c9 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1e0fd39dd690580b8b88689c3a522fa254c9e502 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:864e7754d40d99d2f0ddb0a3de72246eb2e3b8f0e906bbe61cea40dcaa719047 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0a1820bd53ddbac934f252cc34b16f6377219f85 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc8329db1e96ccb71bfa251e258d637bcaea3454028e1b89af53a71cf9b3ab54 +size 95016546 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..85510d8e6ddac10f8a80a33844e14df7f2495e3d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83a2264b13ffa9729382f45478d91941fdb87ae1adf8123e19b8a8fc6598e07d +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c3dcf087428fdfcda2efaf517c3b28e2766a2640 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a4c69aa380feaf8d2ac930988dafd905b94111788bfc3f860d1150f588248b9 +size 95016546 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5ce8157e116ec1eaaed782f6b810d0c1080e2544 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0869b2439f8450cf3fd796d268e2c893113585572994bb7cb2b9d4ca709749e7 +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..57657e58cb3be5880c29efb7a3d2ef6cdee7bfee --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b51a45af9951b7a42c3bb2852c2a6838e18f3174a9fee8ca1cf24ab514347b6b +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4ade3e49dfc3e636bfec74c3fd43fc61892f1884 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb3bb2e42b1890a3323eb1059dfb5ff7150c98f2a48932912ada54df7a42b08d +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..90b3ca5d62c4bbf3fb921417ca01345f6fa1a6fe --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e106a02f9a12b78f5cbfba384fda7212a9967f13b53a456bf5a5f8eb55442e6 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a8f6add79d93b4ed821c9ca2bfa73baf3efe8846 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74e0fc8ca2fe0a50cfb43814a2525f3a495d7b167f5defd57e0426d3cbb2ac9f +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f3c553c145dcbca333086a6d674f25956a310dab --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df6cc845036f68666e324a8835e8a504351ba8567fb46b07324926058241b089 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..523a95718c0dc45356559c790a21c4b66b3c2908 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34c1cdf1a6091f65ea142eec214499e4ef5b5a21fd1b3d2c4a83182a190d2f9b +size 95016023 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7aad57a485da93fed1ec1a5c399eb58d69e5809b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:396f6ee48221ad8dc889b42f711665a5d92f16d07e430431fb2a956d14779a65 +size 95016407 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..41883da57a6d60ae702fc566e807d606d2969f99 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c90cbfc62101eaf6f2ced6b1be426325b415899a201a9211c5866c0875024f3b +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7b39eaa54994934812edc0a83352f41a9ab9e2cb --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03db98815375f8a56a0b1bdbd1b67186e6178d2b3ea2b44e4d28a15fe9ed938e +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..07cccc44395abd68b78a3e45ab03bb6340328b64 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b9b2f6b4e38e959bcb7ec7a1bc41350b3a714f24509887de2d2c42d9f6c1432 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..75ff01068769478fcf535e3025d17b7a5a1e7ece --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6100c204fa96d8264395f5ed771fa248b6e3de3bb54254e9e44ddea55bc0545b +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..76d387fd72c62fc8e177e5d9f1f7abb4538e624c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47c22696204406e56543f5fffb6661dd20cda69b5d504f621cb7ffef0a047036 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..efe7a93c67307a9fab667da8cb035b982ab232d0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71a5874c475a4030ed99268ec6a3c97120ae21065a65ad12d706a912a1daec1d +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..66eaf5a788e9c6bc26933cb24c630a43ca5f0196 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b24e6e9728745972c8ecf9af07d7d07c5c77df91c895ea63dbd8aa4590009f61 +size 95016226 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1a1310495a6c3722d86b54ea082d7e0449c56684 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29d06683d4748d2dc2c51d72a87e817021b240b76da890fcc19d4613eba307d9 +size 95016610 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b0c8c1413531ac3ae9f4b1224a1d2a8c04ce9b26 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be793aca982cf47a5d517126798ad6c809488e2b407c6dc8ef2ae9652cd3f8bd +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b0a41b2d7f0b5116359b11e35a0c9fef4a3143ec --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59f19e36db3a2bcec70b7ebcd21b9c74547aea3ccf3ee5b6b168e0b63d408e95 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..61294db4dd57b693e24f255254ee60471f4c8b08 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f613b9efc9bdb9c8567adb8bfe8a8d2e7fcceee9aad0c74d5a12eeb6d951078e +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a06dbe41c3ba310f57634c59c44e006bc6c56020 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed33e7c961f94786f6232cd15f6cf887ddfe218f40fb9f9cb95e6b36a7902574 +size 95016546 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..26237426ee1ffc4cb58d2574513d4feb27fac219 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ddb2dc7044c8080ddfa924f38f4c1d02959fa1dc8746a17b76bd1b6b239fdd6 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e0cafd5b74c7ee092326c4c9701f3f388dcace48 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:434056623b8ef1a061458125ca46477951359dfaa05d531dbb108f90517fec74 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..482fe9b009bb5f5ba42aaaac97bca3bd618aee97 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a94c753aac21e68b15fb85ba744f7a1faebd11d214c6be49ef1a99dd7c1ed0b +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..62a3ad8c7a9ee7ad697f12d51a4eb262a72240f8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:397261bf1aca707ca5bc1007e9dffb0787043a9173c59f0754de47e3a36c0eaa +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..06292a26eef14558f6be069e24bd350f01d03844 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cf494a4aa72fb22f000ee2df7ec446fe9e2e48dfdf97833d211de6db1777544 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5b6887c2962871dfa47e3ab752681b85273736be --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc7aa6009e8ece1654af0b38ce3ef13bea165e24207651f3d6c6cd76dd04be4a +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1acf3d581b847cab7cd31c44cd8f21dfd7f1588c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d66515951be9fb5ee8641cbe13f445ec58448f9d62b66ff0e1ea4fbbb4f834d +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f7a57aad5900144521d18e9b9cb34c6ba9b5a1da --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e3337dc456701b7b3863a1ed8b1f7eb1a93afe4700bb4be78dead0c288fd721 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9e07df81bfa21f93669336d348b47a63b5655814 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:924129a7f47d4b18b1c0f479cbd8ea1a75104345b653cf782b72c3bd331ab17e +size 95016023 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d5af9eb218fe5a7418798af4b62cd6226997f63f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39c7d8ecc7919a0871cf04cd30f9e6294cb9911a63904134a00444d25dfd137a +size 95016407 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b0e099fede189501f15eccb4e1dd15b506f8c798 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b8baf780a319477a3b1287c9e1d879beac02995024ead6964110952711d5c8a +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..85a76c1443320d0dfbb442979933f17d71ca9b70 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:828f28f0abef8feabd75f3e3b0a097c2b150ec5b1f5ce920605c4aca55b852f5 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a603eaa6cd53136f9bbd2dc0675122c9b16e668e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2bb44674da617eee30adf5cbca216655287a853c9eb62a823bd0a575ab03f11 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1f9265236c6b6cec727e6518445292683a59f4df --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14316c9d458eb3354b518c240d850e83b1e8bc924d430281c25baf33efed93da +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..23dc12b3e70f6f80f32b873edf2fc65f9795489a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72b63ef277bb8a410133086d384dccc2e29c0f6dc83ba3420e8cc6981167033b +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6738382b84a5166fef724c9b02e76369b2d6328a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9bb2aeffd7951d2c01e38fafabf3839c4aea1bfce2937d43d666f8916b23cb7 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4c313d81df1a60626dbe522241e36cdb46781897 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3179c6155ade8731c1d74659962faa8390e5f5352ee719debe140b8bcba7cd77 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9c34b254575514a790b307a270c9bb6c6a74bc9f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:864cf723dfb05e4f3dff7336f5f47424d362011e5b4b48e23987c2e116a677bb +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3190fc061d87a02e42826f05c1b305f9cc09a555 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4b260906f867391d05748c00f824b116a9b634cf82cea472157403885452912 +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e4839a4d1d389b5eacafc17c1ad04f3065876414 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d46fcc5ba1b506b9ed75620cf7168224222ee449198aafba0caeef9b199ee774 +size 95016546 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..55d9523c70526cc3125532ffdb6e5ee65e8640ce --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fd3622f50a8bb5ed4716d18de47400ecdeb84af0db4edfdc014442f129a77ce +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a8afdb3ff12512e8825b8ae0f8efb15c75ffa6b9 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88b40d7a527f6f66e479c76fb3589c1e8c69ec9b9cad96febc8119d63af1957f +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f796b15dec15880201b9e7c4166536d8c22a67fb --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bee46bab0cbada8ab075bc45ffd49010ae412b4aa06498d34e9479dcb7fa08e +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2f99f7b4bff08fa1db717092a9d68d39ce6d876e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90477618481803e149682f769ba50ff8aa0d187d4d81415b4249aaf88331f8b3 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b0a23c34f370a55955b2324d3e1008ffec0e44b1 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3294ba29d64de7227ca18d577b0952d4793a8e467c7bd5c781e97c77b96d772e +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3e9f9e401938044cd8b649374527eb644b7d5503 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79e61399821dd536c732daf99fe494a0cb5f2f246748b33d70ed66f09e055aa7 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c89d9c4d8eb8f91b6591e01a6ebfe95dc0518500 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2bebdf649e44a77bdc4f2676c95d152000c2c436bbcefc86d6d6f2a61ac5773 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c5665e1196aa29bc5c1b1f97e7de17e68aa1be07 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c9100d74b6bd508183c5bfccecb2ccd3a0f4727314cf58c6416a4b512aabba4 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e2d78a02817bd9f711889737927733d97bce7c28 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5893d2139cf8d2d7f04cf64083cf9c077b2634dba20e81d538117949611b1b71 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9178a3c09b6466528426d95e3e6d16809f3ee699 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a8e8b8c2cc246e5f81208d65e40d762ef9d5f3f0d72d250501067772f4129cb +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a61edcea2b5ecfc5580452fa5ae8d6bc1401a0c2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4e6ed8aaf73858adc2e70504367feaf2c317cbef173bdfef228b7290ed44c8a +size 95016087 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2c2c442c44138aa76498c60c3a688c769c4cae4a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c91370e9e138c8fd74a15310073bbbb697d99546265492ec27511047bd85acee +size 95016471 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..23bc5de61b3a90b2f0285eee5f0d45c514221171 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e9c07fd06739506ae44170d5998347ff43ecc75dc7a6a9dc3a0b7635e4ef60d +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6ba784442867182d4be35aa890e81f8f9dcb7245 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa64897682b1ed9491100ff2dc9d02ef1a9c1f19ff4a4f873951b71f532f7758 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c04241413785c8976e3260e117e57efeec8a960f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cad16dd06cab503824e56899114cb915f30d7b802312a5d74104e5deb63e0cff +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dadecd27434e454e4de5b43c699b91097e87636d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79b18eb8a9c6e062db678ca1f3c117ac4f413632687949467af8d1f3bfe8e6fd +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1d03ef6a217d6d21dfe1b00b549e1c05b86937c0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0516e29423c0da51de298e6db987bf514e64739aef40a542547b8e782c6ddc4e +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..824bedc4ffefa989dbb45daba4a62f20f2f6945d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6bd6c7b3258c9a0cbaa8c2a225bb8ea9f1c3ba111f54b1bec614831fc2be0c2 +size 95016546 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e7e6c669957c12c9b650446cce669b0a374e3bb0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaca3d665e6f9e4e3ec0540dede4137fe59554830c651eb66d4a3fa9e7badd80 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fcff1bcf2a04f8033055a211bf61117e5212395f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c106aaee47dc762841a826f43596b4726d07e9ecb8fd09959d75638113c0563 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..703ddbe02e641c1bd8c51b2cab1ee24621482b00 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6eb3db0d7801c22ee23a914a1d7d5af0885829bf327ee3c387a4c929089d95b9 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..93b6944561beb6b2e363c366f5149f126c0d1a1e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0683dc281f618d1e757ff1ecb40497ee5b5b8d18723e8a4084cd44566f2fd54c +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..621a83bf09920ea36c74e6023a643e14a71a4c28 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16adafd46cd491f0668f32ad077b0e747f05d31e9f5f01b35baaa36f19d60d97 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..283894f795e921a0ceb709de3c22baf6f2518820 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7ae6ff55b4f970af4775f703cb3f7ca3f99ade27a38bc08f20fcfafb068df02 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a69d93d3db2400c7b9496454c067e2386b3d221e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b36f45bd6447dd65087ae98e792f30be87dc83bda35103109efacfdd91bdc19c +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..721d499e203b621745d1ba855d8a3feb6c604634 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4efa3bbe77f14b748b3d16213df1fc46f9f37e0ce60fe79680430d893e43c5b +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f7894abb4fe8d2cfe2d78a25252ff8a0022aa24f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38d1cd4e11885fece67bb621f34bc82ce339d60f874793cfdfce05dd39930e04 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..66d63d8f6a1131607fed837540cf1c13a5fd67a0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e46caab22fc25e247449135c8e558077e07d9f64cea402c6c635e0cce0288f4 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6ea97a2947c0a401dc5ab61ee2e4e621e7406aa6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93da78a87e611f0a9e2c4e602afc498c8d5ba829f1e2e8017b528e7b5e8b74fe +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f7485bec798f8f5291b0841a9c2edbbe06cbe0ae --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:258dbc8a5133c99116869eb3cf745ca009a99fa8bfb7415d2166196a952f9da9 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c08be3adca7ee167525cafac90454e7ffb960885 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:294245b83a443a493508a24e2dea5990e52b8e5f6def8e57719816321a4db543 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..877e693ebcd1e49667deffdb559525025cd9979a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdede0873c6464a05e370aedab3e57bc29eebf57dbb949d2567931a29a509d80 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b26a56532161040d173122c493c4e2ba6826f39b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8126a7d94a435426ace7b8634e0fb0a2b08951c52f280f8432d4af9f62e0b3ec +size 95016087 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3198d9d99dd08853f1f4a8aea1790a82ca2821f2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c046b0c1d82fa218a409f0ca7143f228596efb15b7e8fd3c47160d8e524c6937 +size 95016471 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2f4e9fdc9ef1dbcd6f9e0e76f83c6d8f5a080e8d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0bc108635555f2c28380b22b163c64fa37eedfe7366284a6bf4ac548db9f3ab +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..953f2fc331ea98b362910ffacc4f55d19fb2e565 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56a8db93c2e3f61a05b1a287785feaac287e05b02b1ab7265e30bf51a8810ba4 +size 95016546 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b97a1dd3c3b79c485b92c247d2627c76abe17513 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a8b81f0cc7d9c4aa6617ab14ec50e277076754b27ae6bb5ac7fe27f6e9f7c34 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d88626639ced09c7d2365f0dba1ef6095bbb4f2d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edce4b73abcb68fd28fb75e4192823ac8c537c955679a3f2c3ae75ea857f05f6 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b8d5226b75cca023aa2289cc85f0ba791b8c0baf --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:552f4caf280b199444d3efa097f9cc9a2249726b6db5597a0b2bbc3660889e3e +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..647b577f73236e8277c42058b51ad82891316aae --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e0d929d2dfe27689c423012ba7ce5fed011ac14d586b33847a4651290893707 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4e011dcc9ae9d5a715511f27b287283b431eff0d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49a86589e35864090c8d7ad8c9b48d9944cc05e83354fcc042e62c9f769952a5 +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9734772240085cc50021f3608451c3e7b13afd18 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7681fbc816d8896b2e2b039326834581bb2121f6af4455c4d18fc3ee47dc24df +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6eef819331cefc0ea49b4c9c8be4bea56a12a97b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d25e52ecd4ad5dbde02adcb0fe2515bc2256d10f5630e88c879e9f89c5a5875e +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3dbf26ea2b6863aa3070707e9c8aa8f1f4831737 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:215acea0552b41094a24eff4a11e4069c916d5f38195f9c753768de86daf6577 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8d49fca43d7b5fe89f14c16477a85edc794ce1f7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7f3f75a933a8746520955f99dc38496032f899b291973d0571417a9fd70cef6 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..67c19010b3031b9808cb81fe17b814bf22843dc2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d40ff8bc6e7020c45d1762405cd4a974e4973ac7ed06fd4512c1eddf11dc0c42 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cb1eda83428440c2807c15c2de072769808e460f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23bd0ffe92f845c911655e4118a715867de2ad310a514cf572aec4d4a39149d9 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9bdb9b3c4f1affbee3ddfab85190a39daae0b693 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aec1a49cfb1a5c94af7f8997afc4ae578fbb311b1a3a7ff2d3fe50a71ad02940 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9f75eb68de6453094741fd4b748891401e8c2849 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d256c01f2359d74cbc0a2959d4e1488b236673fcf889ea8b8e8f594b5c121f1 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..feb9605779f11a93e9846d35dfc92ace28cfa08d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b977088fd145ec690025dbd174e91fe5efd6d7d568388a33c6121e4d69c0c1f4 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..65eaba73c7ba5d534662d411f1fef82771b8d32d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:092502917901a85f068754cf797bc08974d9a4ddec70ae7a2688a9cbd2e628c4 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e905fc7bc340f6284d46f1c5dd503370c7e8ae4e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5dc380fca7b3e95022417e3be806ea20ca155bda1e760dd4fab0843a6e3172d +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0bb5d68b803999c815ca5bdfbc53920796cc96cc --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3eb82dab30270cf730f8a7dba4af50daf1d1d3d97e869965a057da63bc58806 +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1289c0aa46c187d32839e77c398fd47b042ed261 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:535e1c44384737a4326ed8e43b03cb34c784106522bcbc0a0816d00e99c3627f +size 95016546 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ace242299f1a4591d1b96eaf79e452d5208fede6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac3e12244e56540bfee431438d10e6ef12252ef87b45392f2de67ab3d344ab82 +size 95016087 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2442116423685fdd01a19c59d37e32eac0817044 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc3a99e5a9f253a0c91c24346d59ad5fe6d25533f398747eba2050769623193f +size 95016471 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ba114832cfe42bbc209edf0d1ce071547766a3e3 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:801b53501c82c79598f2201cb525d1cd8660fdf3fef3bdb7a1c7bb6820787f2a +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cd0c44db4f83729aac359390685ae0c1350706c6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5d83224cc955946bab1b073319c8b7c16b01e4dc88177bfac7d2ec7675e940f +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bdd9111ac25dd763f4c354dcc3a6db3f8c4ec666 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95bbfbaae5a129c31f20b830819becbfd4e6f1d8e1e7b899f18adc155abd6c2f +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1cf662d26414c328fbdfb9afac7c8cc926e16492 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80345c3e9b17317dc8d5f8ee01f7125a29d49edd259504365907d7b13465abe2 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4d5b9883d41cbe68f1ee9b6444705cf19dd63214 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e62265492d7e82c774e12cd77a82a7331384d7ffd35a14b6e88c96725d549ca7 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ca8b097dca7721e0d9e4772ed80100bef1cd8027 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8d952fb7c2ac25f69c188812623c65d331023ef7252e5ca4d5015823b76ca1d +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..185c490ca0d7e137f98224b269fcd7a1b55577e0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:939528011118c5b14faafafd5e9f39f3b37f95cc3a173f81b288f1e3cfb3b5bc +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a399a3e539702c6b6c089df8184db2bcb647d079 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:782984d10ef25aa6e1ea6e10859f3844dd6f643e0c108dd170082439a7d00030 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f9a9d97c6dc7d8dbefef5353c417306a4cc7a999 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7357b378f5eaee77fbd3661b867c63621e78efb9001b8d4b59c5f3a3a79b72c2 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6439a07080e2e52e75cd2525941da57ca227e106 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe0e4a638c5db3b192437d936473df9ddc52acbf41a72b432eb37c35ab235787 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ec7a688ce1f3ba8b34f844c9206a744e7aedc6e0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9da40fe4ff71dd0c6dae314c5826413b8453f685dc734446dbc23d598449559a +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6622250d798327ee4850f19a706690716632bcd5 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7603e35aeecb611f5aa8e4071a072982b0cd2ff1732a567a3b3f01f8b5165f82 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5fb6c94d0583581f8d7e32faa8011aac8ce85784 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dad9e31701310ba738e845dcaaeb372d1e115804649b952e4fb3cdea13379b69 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..297124562a7afa7e92aba95432c3a5f5a2fd7d67 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2260a66f31f1b69f5097d441aea94a5c475cf840c8ff2d2dedec52e52c32f937 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bbe261fa4edff2d35db18198757c1d632b3d94fa --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddd439353f36ef6f1237d9a92f9ddbb590db7543ced7cae656e92f51f251f154 +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..04090f10f8ce2db23a6f81e1e1dc00298df40be1 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:220a02138833570e126bed8ef3228864a6672ee5ade0f60131bb58d437114e56 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c579a3f1700252eece86b6b746ed6df2578f4cd9 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1388f6b93bbd72fdef1fbceb0a77e433b8e3d3205e09622bf42e21802d65479 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0086102064ddd95fbdf60c16284d2e59f4d69033 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:049d4485d661495f2b8c2a3498176840349c767a77d4b19657dda3c3ea78f43d +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..054f199c3ce8ffaa37efa34090b2c0bd2d8d78b0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bc3820d8de425aa55042c7ccb53931d2cb4e14ddfc06961f0ac37c9a394c7fe +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..13254e72ff88588831bf5c3a3a3021781ad210ca --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:969b37f5e2ace31bd3b28e5b71adb17800004f3d1bf634b3135dbe211c275384 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9b1b34e54db22a6dc9d8e84eb3da27446aeb2656 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba4172791e7c515c118be7712a44094e47e06d2d7757e78660f26c05e53b651e +size 95016087 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2591ffe0af3b8e314452aa80e66af95355dfd3fb --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd93468c527d578f3c8c83fcaab0300c42ebf1d21756d819a469e0d8daf0d6af +size 95016471 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..294e2e65c1bc0b9654438ab4bee3f6c028e1285d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3adfec2517495540f6238f852798e74d5a6b6cfee5e894c1066d9d9ea38ac72 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c36559241a9a3ceda073f1fdf4de23c397c513cb --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6eff8bdba61ce14b41a53edf21457e678d3f7709018d3a90b4ba8448cef22014 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dd75453d80be366cecc3904ebeb393a79926d110 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebabbd91c2492e4d4b259ee2f4fbf8769dece61da2234ec89c001e96cb330d3a +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5a642bae8dc2b9fcfd4b9e65fc2cc74f5681f958 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca261157cf9a168562592813a9d683cfee56bfef8eb3adfba233d6d700e73b16 +size 95016546 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e46b18733ab051a8a07969c5a6a3fdb2502155c8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b774d22740b4bc9bbeaca7300d981d590abbe2947dc6e4865718d21c029c85bb +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..061814f6669263d69fcf14b21de82c84d92c08eb --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fb50fc4d1ccd708de0026900c999df9c4a24ee610628e3e956fab62cc5b7fcf +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5e226a0952b8d000ed090fd60ca1b93f86e01f25 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:487b37d68fbd74b7cce8c2340f5f4608ecdde3751f7e7e1b72959772d6092472 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2e342c1ea094cef8d0b75ed54ea3bc4988d924c2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69d88ef40276d43b95b80364a0d48a9e84c9ae323b60fd0e3209d7a3c854d170 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3728bbfc82eef72913c969c2fb50c88d072408e4 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf74819b8cd5741f559eb8e2fbe2753dee464aae217f146ecbb31e2b96953926 +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7410fc1951df4ce608658d5dfc9e1936c75b7053 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1fc5e0e71f32ab5781345f212e76ac85dc0747926b3ec271580f6b47e642513 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..50d4e5473320f38c46a570b386a9cd1b11b9a803 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8993912135c244b3abd410b2ea5f1417f41ada6021dec3a0099d1a91eb85d59e +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9134979c164de10539e368d0cd0f1ee9789c1c6e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bf079dd4f42ee692b8d82757f895e9494179a77f7ab77b8bf453be1c74f772c +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..42b08142dc47436474bc3a5d021d94c9ad848520 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3d7465651e337af986aea4bda6dcab95af245ba78a2ffbd5f5efa01f6937422 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2f7fd08f80c5b09f28b6ca0cf58f9d14de3e17de --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:141b56f26748197408d516820eba90ab76a1851fa411bf6b5d238135904c2ac3 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a7f9629b38c82c4557c79b93dac7fb40de2436d7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a0e0625810c90338d91a138b3db63266db60e4e6eace1af0b66bade4d8bf4ab +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..037300e3f2937df60a2ef83056365a5902b21d72 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fcfe280db6760e480b2cc0093721ba52176a342d161fce548f9347ee312e4a3 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..86b45a345977ca478205cb14b79575a399efe769 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9daeed7be39ebc7e6ac4dde02104db81bcb023112f303fd17896bc16d8456b5f +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..618d5cb15b5200b889aa041984c53e7b9d9232d3 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06bc0a5cbc497a331c80991c76e4e36b6dc41705b596fa2d72305c16abaaa509 +size 95016546 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fbf4459f397f9b1b85e12e1eefe6d012cb29ebdb --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1df4f961e6906f9a064d2c54379c9af6714b5491ea466ee40f4c897ac5f04215 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f94f972f80622b50ef3e625370dc2df7fb46d1de --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df002ad0dc2e12a820c729104508773223901bf512717b56886fff65f1d77553 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7f75c80731d1546d972c96e6b6f8aa3fc33a2424 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:478aad8fad6f9fde6442ff5bf11de8a67bce788b317dd5ca758d7ea04b230af5 +size 95016087 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..82d36d87d338d4bc85fb1ca5947ff6375f7df961 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d77fd9cdf22e9e5a754a22ae081fdb0a936d3b5222aa45efcc57af8e4068376b +size 95016471 diff --git a/3b977b77b/global_step73814/layer_01-model_00-model_states.pt b/3b977b77b/global_step73814/layer_01-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..470b4ca974c77305595565336cd8b68961cd6481 --- /dev/null +++ b/3b977b77b/global_step73814/layer_01-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a01c3159a2fd5ca21e3b27a07877aa195c9e9640c48a5bc08b3f76b3e2a4e21 +size 308249859 diff --git a/3b977b77b/global_step73814/layer_03-model_00-model_states.pt b/3b977b77b/global_step73814/layer_03-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..65921f48ddf53dea4d670165f84fcaf15349b161 --- /dev/null +++ b/3b977b77b/global_step73814/layer_03-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d9725c6aa4b691ca9ec4e24de215ffa39c9e0f3c90f369f9009e2597b508d2a +size 208092163 diff --git a/3b977b77b/global_step73814/layer_04-model_00-model_states.pt b/3b977b77b/global_step73814/layer_04-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8f971daa18d82ea7da1a9a0d0830ef75c1479e26 --- /dev/null +++ b/3b977b77b/global_step73814/layer_04-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:301a1343bc1a9b6d778109b78af78c29beb51277fd1fa422f179cf2091bbc310 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_05-model_00-model_states.pt b/3b977b77b/global_step73814/layer_05-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3c21b21d5a2aedb91c916f0eabb1f013f932d82e --- /dev/null +++ b/3b977b77b/global_step73814/layer_05-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bab0ea0fe3fc8b3d8bf99ee5f9e263a4af2ca6832be4bb0a160f8f71a5cde124 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_06-model_00-model_states.pt b/3b977b77b/global_step73814/layer_06-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..11e8af1849f26561b8a55be2139a516fab214235 --- /dev/null +++ b/3b977b77b/global_step73814/layer_06-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7094440104263b86ba3f34d2edc77c5f8f4aa0f3a4b95f803eaf87ddc043079 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_07-model_00-model_states.pt b/3b977b77b/global_step73814/layer_07-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..29a988063ba58ffa1763999d6e04b7db72728520 --- /dev/null +++ b/3b977b77b/global_step73814/layer_07-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:416b6cb860f43fd3d867fd97010ec3d762dfc1bee5b11f9d2ad808f9dd954c93 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_08-model_00-model_states.pt b/3b977b77b/global_step73814/layer_08-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9a0f25ff43b28e7859365e2f7e65877f9698ec7f --- /dev/null +++ b/3b977b77b/global_step73814/layer_08-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6412a5d90abe92727a339a365e854863c029f9edaf8e9aad50bc39c71c6e4da +size 208092163 diff --git a/3b977b77b/global_step73814/layer_09-model_00-model_states.pt b/3b977b77b/global_step73814/layer_09-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9e49616e9984aa7b93336b48fbc3f170db306fa5 --- /dev/null +++ b/3b977b77b/global_step73814/layer_09-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:574385e99dfcc100339b2842c76773b9ff96db46cfe08f5ca1a0296aad5d060c +size 208092163 diff --git a/3b977b77b/global_step73814/layer_10-model_00-model_states.pt b/3b977b77b/global_step73814/layer_10-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ef7d32a0e4189642a750184fa7b3c3f444f59241 --- /dev/null +++ b/3b977b77b/global_step73814/layer_10-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25ed78a59a17e6c26c2ffc15993bb864c122a2fe7e0248271ec122489519dc1e +size 208092163 diff --git a/3b977b77b/global_step73814/layer_11-model_00-model_states.pt b/3b977b77b/global_step73814/layer_11-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ff5e280526629095d1103c2d3d696bb0ed90986e --- /dev/null +++ b/3b977b77b/global_step73814/layer_11-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3826060108e2e54bcbff271657a32b25311002aa71b197d99496c0779767f9a +size 208092163 diff --git a/3b977b77b/global_step73814/layer_12-model_00-model_states.pt b/3b977b77b/global_step73814/layer_12-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..50303a82d0ce8bc82981b707a766c110e99d5930 --- /dev/null +++ b/3b977b77b/global_step73814/layer_12-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2753c8933478ae76b12adfcbc406d58bb2548d4e61ff79c4e07ba38538545f4 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_13-model_00-model_states.pt b/3b977b77b/global_step73814/layer_13-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..60a93eb66af75553a758b8e46d893d6defa781de --- /dev/null +++ b/3b977b77b/global_step73814/layer_13-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3757c7c5afd6f9f317efafd6316c1d03ffaff9fdde0f9ffba6c5b304a0b4083 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_14-model_00-model_states.pt b/3b977b77b/global_step73814/layer_14-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a1fc20375087463d0b289c6093279b71dcfe63be --- /dev/null +++ b/3b977b77b/global_step73814/layer_14-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a8d4ca763f9580d6f62ea51b728d4b6eba1629b436369bc647c72154d259067 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_15-model_00-model_states.pt b/3b977b77b/global_step73814/layer_15-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9758bcca0524329bea8d464631017de728682dd2 --- /dev/null +++ b/3b977b77b/global_step73814/layer_15-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1236f204df709e8bebd34ccc2857e90e5992474080335ef7ef7cbd506437614 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_16-model_00-model_states.pt b/3b977b77b/global_step73814/layer_16-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c48e77b26a2332cb4cbf2867c57fc0fe4f5a28d6 --- /dev/null +++ b/3b977b77b/global_step73814/layer_16-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44548d10a5a36e9eb07220682c4aa690d8351c864c46615d7380568e99ec6290 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_17-model_00-model_states.pt b/3b977b77b/global_step73814/layer_17-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7c659a668948a29fd372530403eae756de8fbae9 --- /dev/null +++ b/3b977b77b/global_step73814/layer_17-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f41100fc1cebafe9d252b943bebd45f0294ec2bd764d3f1891fb9ed97991f1de +size 208092163 diff --git a/3b977b77b/global_step73814/layer_18-model_00-model_states.pt b/3b977b77b/global_step73814/layer_18-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3542eb068b9a23ef366b410abb230b5b5e6680b7 --- /dev/null +++ b/3b977b77b/global_step73814/layer_18-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c75ea8ddfe9c71c8bfb1774ce0910e756ee479c6ac54b86ad724c890236a18ab +size 208092163 diff --git a/3b977b77b/global_step73814/layer_19-model_00-model_states.pt b/3b977b77b/global_step73814/layer_19-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0c6c1788a7190afc258463ca09af10840ca860b9 --- /dev/null +++ b/3b977b77b/global_step73814/layer_19-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09c575049df1b5f344455fe47dcb4365334045b02bd343b0d047d27e8749eeef +size 208092163 diff --git a/3b977b77b/global_step73814/layer_20-model_00-model_states.pt b/3b977b77b/global_step73814/layer_20-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a23ee83c1afa565fb7702ccbc1a81386a33af0fd --- /dev/null +++ b/3b977b77b/global_step73814/layer_20-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20c099abc896b32a99efef55499e625ae31185e40e9af754b427b8ac5cb7afaf +size 208092163 diff --git a/3b977b77b/global_step73814/layer_21-model_00-model_states.pt b/3b977b77b/global_step73814/layer_21-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..20e6e207cc2428039d5826b2838e765191326b30 --- /dev/null +++ b/3b977b77b/global_step73814/layer_21-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ba2c647df0f0a9fd8a1e9b4740e263351e2ce8d385f34610d9893b6b480f455 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_22-model_00-model_states.pt b/3b977b77b/global_step73814/layer_22-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f8174fc113732356f376b26ea3a35033b5b972c8 --- /dev/null +++ b/3b977b77b/global_step73814/layer_22-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dbcdc74102e6390ff9538ed3a95e2f6c92a5064177cd18e89cc8f65ee0d12cc +size 208092163 diff --git a/3b977b77b/global_step73814/layer_23-model_00-model_states.pt b/3b977b77b/global_step73814/layer_23-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2acf95e8d49a687ee5dba2916cd61e63cbe16d13 --- /dev/null +++ b/3b977b77b/global_step73814/layer_23-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:335a5d72ef0b14701817030416accdafd5811ae4aba30b051cf54540397db09e +size 208092163 diff --git a/3b977b77b/global_step73814/layer_24-model_00-model_states.pt b/3b977b77b/global_step73814/layer_24-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a954ba60c9c3299bb7472dcef971d7e76191a1c6 --- /dev/null +++ b/3b977b77b/global_step73814/layer_24-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f4cc5b962b14ecbf7e888fb3024a455314d75dfed9b7414abc763c03cca06f4 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_25-model_00-model_states.pt b/3b977b77b/global_step73814/layer_25-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0717678f14d7265b18b6148a924ccd2d99c5cc36 --- /dev/null +++ b/3b977b77b/global_step73814/layer_25-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24d3965f8744152d3c696810af7aab9a6709349f86960536ad0c8b47a77dd038 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_26-model_00-model_states.pt b/3b977b77b/global_step73814/layer_26-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..457f6bc236775e2ecce0f65eeff77fce463ea934 --- /dev/null +++ b/3b977b77b/global_step73814/layer_26-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99371beb42eeaa6d754a26b459d7142c97bddd92b3fc0e09af45a7ce985aaa49 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_27-model_00-model_states.pt b/3b977b77b/global_step73814/layer_27-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c7cfe9524d5d69600b88da8d9d0d0f6fe795a6fe --- /dev/null +++ b/3b977b77b/global_step73814/layer_27-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40866425a8996b23fbeac9e8f049463356ba21af9347433e0a1f5c8c6d8d1272 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_28-model_00-model_states.pt b/3b977b77b/global_step73814/layer_28-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e45a43f51d4a9ec1edfc4567f83718f9263f5955 --- /dev/null +++ b/3b977b77b/global_step73814/layer_28-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1e6530d52c61ac585a4780d09a9c9758eeec606b766fcfb4f1bc008de3c97a0 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_29-model_00-model_states.pt b/3b977b77b/global_step73814/layer_29-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3dee0a19d9c1a582f6c2abeb7a47890479a35722 --- /dev/null +++ b/3b977b77b/global_step73814/layer_29-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a2d18fb0ec9c37eeebc614eaf1b4b14ede1d886004f5c6f958e896b001943ea +size 208092163 diff --git a/3b977b77b/global_step73814/layer_30-model_00-model_states.pt b/3b977b77b/global_step73814/layer_30-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0eff5fdba5bbf2ab1a1992e6cad317837eb45710 --- /dev/null +++ b/3b977b77b/global_step73814/layer_30-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cc93ac498e71bd26bab3b2c495f2f13b9bbd25d2ee90646d20cbc5ca8295b76 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_31-model_00-model_states.pt b/3b977b77b/global_step73814/layer_31-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..12e3d1bede01a5ffe759f3798691332e7ecdf61b --- /dev/null +++ b/3b977b77b/global_step73814/layer_31-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:465ebeced9dfbe90ff945b10173305110658d0e10029dc999f41241e00425982 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_32-model_00-model_states.pt b/3b977b77b/global_step73814/layer_32-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c6ed1d6c7755d1226d6310c9a243fda80930e7ec --- /dev/null +++ b/3b977b77b/global_step73814/layer_32-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ea3de7114cc63a9b0ab868803591435ba4c5a6f27c8398b397847073a967227 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_33-model_00-model_states.pt b/3b977b77b/global_step73814/layer_33-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..74aa6a7b2ee743b33664e1a5d5b2268c06b9e865 --- /dev/null +++ b/3b977b77b/global_step73814/layer_33-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:457dd1f534b07715ca3804103167e4677eeb9857b9014e22193e8afd45c99797 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_34-model_00-model_states.pt b/3b977b77b/global_step73814/layer_34-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7f22eacf733837b55fff330f5d42b3f4c9fa48aa --- /dev/null +++ b/3b977b77b/global_step73814/layer_34-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f9d30f17ea5a4a66090eb3a4ba1a5c62b0da6ac3ebb5e0496813be389f985e9 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_35-model_00-model_states.pt b/3b977b77b/global_step73814/layer_35-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5fc88865ad3286723d45db20b2ccd0facadc5371 --- /dev/null +++ b/3b977b77b/global_step73814/layer_35-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75a4ec8172cea3eea9d41f4be1ff0183d4abe9a1e92f1026dc4f2e66d4ea849d +size 208092163 diff --git a/3b977b77b/global_step73814/layer_36-model_00-model_states.pt b/3b977b77b/global_step73814/layer_36-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2d821a8cf4975138568c51ae40cbf422200bbd26 --- /dev/null +++ b/3b977b77b/global_step73814/layer_36-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4919524b51ef537dc571de4b0b6471767f1737dca152fbaa4cfab52df61bba4f +size 208092163 diff --git a/3b977b77b/global_step73814/layer_37-model_00-model_states.pt b/3b977b77b/global_step73814/layer_37-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7e7c5717f53b106276c1d053b922184a9ccd1456 --- /dev/null +++ b/3b977b77b/global_step73814/layer_37-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3bb5ed8a6061b1bee6ed6bad3b0b5a34416051353b44f79466f932687d4c222 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_38-model_00-model_states.pt b/3b977b77b/global_step73814/layer_38-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..60035cf79c4c909a105e364c5eaf1de49536fb50 --- /dev/null +++ b/3b977b77b/global_step73814/layer_38-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1820d8659cc1cdbc6e1e444d991d440c1c004a0053e37ae1bcc36f92fdc48e3e +size 208092163 diff --git a/3b977b77b/global_step73814/layer_40-model_00-model_states.pt b/3b977b77b/global_step73814/layer_40-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b26ed909688943baa1068cce9fe6f5043a2c8243 --- /dev/null +++ b/3b977b77b/global_step73814/layer_40-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1159e9bdfc16836ab8284f367316c2e7cd55d30b6dd8e4be55090463107603ec +size 12995 diff --git a/3b977b77b/global_step73814/mp_rank_00_model_states.pt b/3b977b77b/global_step73814/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d19addddd7e62f9ccd9555b80d4d7eec4b09a0de --- /dev/null +++ b/3b977b77b/global_step73814/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:724f6f30b3e53947296fb1b4adeefc32f874b5f3228646a331adab0ff617d5b4 +size 37363 diff --git a/3b977b77b/global_step73814/mp_rank_01_model_states.pt b/3b977b77b/global_step73814/mp_rank_01_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4dbe956b036ad3221fd5c24d3909529ec210d99e --- /dev/null +++ b/3b977b77b/global_step73814/mp_rank_01_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02c79d376f8ca08d4681c4256da458159bf6982ad9b8d2c58fd460b8743b9c8e +size 37491 diff --git a/3b977b77b/launch.sh b/3b977b77b/launch.sh new file mode 100755 index 0000000000000000000000000000000000000000..6c3445845a5dae614feb4b8a1206322cd7bd9050 --- /dev/null +++ b/3b977b77b/launch.sh @@ -0,0 +1,53 @@ +#!/bin/bash + +# Launch script using torch.distributed.run(). Used by slurm +# scripts, don't invoke directly. + +# Samuel's fix for apparent error in SLURM initialization +if [ $SLURM_LOCALID -eq 0 ]; then + rm -rf /dev/shm/* + rocm-smi || true +else + sleep 2 +fi + +export NCCL_SOCKET_IFNAME=hsn0,hsn1,hsn2,hsn3 +export OMP_NUM_THREADS=$SLURM_CPUS_PER_TASK +export FI_CXI_DEFAULT_CQ_SIZE=131072 + +# debugging (noisy) +#export NCCL_DEBUG=INFO +#export RCCL_KERNEL_COLL_TRACE_ENABLE=1 +#export NCCL_DEBUG_SUBSYS=INIT,COLL + +module --quiet purge +module load cray-python + +module load CrayEnv +module load PrgEnv-cray/8.3.3 +module load craype-accel-amd-gfx90a +module load cray-python + +module use /pfs/lustrep2/projappl/project_462000125/samantao-public/mymodules +module load suse-repo-deps/sam-default +module load rocm/sam-5.2.3.lua +module load rccl/sam-develop.lua +module load aws-ofi-rccl/sam-default.lua + +source venv/bin/activate + +MASTER_NODE=$(scontrol show hostnames "$SLURM_JOB_NODELIST" | head -n 1) +MASTER_PORT=9999 + +echo "Launching on $SLURMD_NODENAME ($SLURM_PROCID/$SLURM_JOB_NUM_NODES)," \ + "master $MASTER_NODE port $MASTER_PORT," \ + "GPUs $SLURM_GPUS_ON_NODE," \ + "CUDA: $(python -c 'import torch; print(torch.cuda.is_available())')" + +python -u -m torch.distributed.run \ + --nnodes $SLURM_JOB_NUM_NODES \ + --nproc_per_node $SLURM_GPUS_ON_NODE \ + --node_rank=$SLURM_PROCID \ + --master_addr $MASTER_NODE \ + --master_port $MASTER_PORT \ + "$@" diff --git a/3b977b77b/logs/2096637.err b/3b977b77b/logs/2096637.err new file mode 100644 index 0000000000000000000000000000000000000000..226628d8430870a0e89446e0ee9fea50ff1608ab --- /dev/null +++ b/3b977b77b/logs/2096637.err @@ -0,0 +1,4156 @@ + 7: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted + 7: rm: cannot remove '/dev/shm/rocm_smi_card0': Operation not permitted + 7: rm: cannot remove '/dev/shm/rocm_smi_card1': Operation not permitted + 7: rm: cannot remove '/dev/shm/rocm_smi_card2': Operation not permitted + 7: rm: cannot remove '/dev/shm/rocm_smi_card3': Operation not permitted + 7: rm: cannot remove '/dev/shm/rocm_smi_card4': Operation not permitted + 7: rm: cannot remove '/dev/shm/rocm_smi_card5': Operation not permitted + 7: rm: cannot remove '/dev/shm/rocm_smi_card6': Operation not permitted +19: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +19: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +20: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted + 7: rm: cannot remove '/dev/shm/rocm_smi_card7': Operation not permitted + 7: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +20: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted + 0: Successfully preprocessed all matching files. + 0: Detected CUDA files, patching ldflags + 0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... + 0: Building extension module scaled_upper_triang_masked_softmax_cuda... + 0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) + 0: Loading extension module scaled_upper_triang_masked_softmax_cuda... + 0: Successfully preprocessed all matching files. + 0: Detected CUDA files, patching ldflags + 0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... + 0: Building extension module scaled_masked_softmax_cuda... + 0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) + 0: Loading extension module scaled_masked_softmax_cuda... + 0: Successfully preprocessed all matching files. + 0: Detected CUDA files, patching ldflags + 0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... + 0: Building extension module fused_mix_prec_layer_norm_cuda... + 0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) + 0: Loading extension module fused_mix_prec_layer_norm_cuda... + 0: Successfully preprocessed all matching files. + 0: Successfully preprocessed all matching files. +47: Successfully preprocessed all matching files. +60: Successfully preprocessed all matching files. +12: Successfully preprocessed all matching files. + 0: Successfully preprocessed all matching files. +39: Successfully preprocessed all matching files. +37: Successfully preprocessed all matching files. +19: Successfully preprocessed all matching files. +58: Successfully preprocessed all matching files. + 8: Successfully preprocessed all matching files. +55: Successfully preprocessed all matching files. +53: Successfully preprocessed all matching files. +26: Successfully preprocessed all matching files. +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +34: warnings.warn( +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +34: warnings.warn( +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +34: warnings.warn( +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +34: warnings.warn( +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +34: warnings.warn( +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +34: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +38: warnings.warn( +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +38: warnings.warn( +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +38: warnings.warn( +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +38: warnings.warn( +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +38: warnings.warn( +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +38: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +43: warnings.warn( +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +43: warnings.warn( +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +43: warnings.warn( +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +43: warnings.warn( +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +43: warnings.warn( +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +40: warnings.warn( +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +40: warnings.warn( +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +40: warnings.warn( +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +40: warnings.warn( +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +40: warnings.warn( +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +40: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +51: warnings.warn( +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +51: warnings.warn( +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +51: warnings.warn( +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +51: warnings.warn( +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +51: warnings.warn( +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +51: warnings.warn( +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +39: warnings.warn( +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +39: warnings.warn( +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +39: warnings.warn( +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +39: warnings.warn( +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +39: warnings.warn( +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +39: warnings.warn( +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +33: warnings.warn( +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +33: warnings.warn( +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +33: warnings.warn( +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +33: warnings.warn( +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +33: warnings.warn( +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +53: warnings.warn( +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +53: warnings.warn( +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +53: warnings.warn( +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +53: warnings.warn( +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +53: warnings.warn( +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +33: warnings.warn( +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +53: warnings.warn( +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +57: warnings.warn( +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +57: warnings.warn( +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +57: warnings.warn( +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +57: warnings.warn( +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +57: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +57: warnings.warn( +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +46: warnings.warn( +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +46: warnings.warn( +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +46: warnings.warn( +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +46: warnings.warn( +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +46: warnings.warn( +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +46: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +50: warnings.warn( +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +50: warnings.warn( +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +50: warnings.warn( +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +50: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +50: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +50: warnings.warn( +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +49: warnings.warn( +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +49: warnings.warn( +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +49: warnings.warn( +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +49: warnings.warn( +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +49: warnings.warn( +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +49: warnings.warn( +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +41: warnings.warn( +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +41: warnings.warn( +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +41: warnings.warn( +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +41: warnings.warn( +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +41: warnings.warn( +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +41: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +36: warnings.warn( +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +36: warnings.warn( +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +36: warnings.warn( +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +36: warnings.warn( +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +36: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +59: warnings.warn( +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +59: warnings.warn( +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +59: warnings.warn( +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +59: warnings.warn( +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +59: warnings.warn( +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +59: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +63: warnings.warn( +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +63: warnings.warn( +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +63: warnings.warn( +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +63: warnings.warn( +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +63: warnings.warn( +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +63: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +52: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +62: warnings.warn( +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +62: warnings.warn( +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +44: warnings.warn( +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +44: warnings.warn( +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +44: warnings.warn( +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +48: warnings.warn( +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +48: warnings.warn( +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +48: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +52: warnings.warn( +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +62: warnings.warn( +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +62: warnings.warn( +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +44: warnings.warn( +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +44: warnings.warn( +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +48: warnings.warn( +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +48: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +52: warnings.warn( +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +62: warnings.warn( +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +44: warnings.warn( +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +48: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +52: warnings.warn( +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +62: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +52: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +52: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +56: warnings.warn( +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +56: warnings.warn( +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +56: warnings.warn( +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +56: warnings.warn( +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +37: warnings.warn( +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +37: warnings.warn( +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +37: warnings.warn( +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +37: warnings.warn( +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +37: warnings.warn( +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +54: warnings.warn( +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +54: warnings.warn( +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +54: warnings.warn( +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +37: warnings.warn( +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +54: warnings.warn( +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +54: warnings.warn( +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +56: warnings.warn( +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +54: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +35: warnings.warn( +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +35: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +35: warnings.warn( +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +35: warnings.warn( +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +35: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +35: warnings.warn( +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +32: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +61: warnings.warn( +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +32: warnings.warn( +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +32: warnings.warn( +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +32: warnings.warn( +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +32: warnings.warn( +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +61: warnings.warn( +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +55: warnings.warn( +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +55: warnings.warn( +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +55: warnings.warn( +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +60: warnings.warn( +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +61: warnings.warn( +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +61: warnings.warn( +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +55: warnings.warn( +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +60: warnings.warn( +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +55: warnings.warn( +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +61: warnings.warn( +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +55: warnings.warn( +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +61: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +60: warnings.warn( +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +60: warnings.warn( +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +60: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +60: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +47: warnings.warn( +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +42: warnings.warn( +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +42: warnings.warn( +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +42: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +42: warnings.warn( +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +42: warnings.warn( +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +47: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +47: warnings.warn( +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +42: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +47: warnings.warn( +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +47: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +45: warnings.warn( +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +45: warnings.warn( +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +45: warnings.warn( +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +45: warnings.warn( +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +45: warnings.warn( +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +47: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +45: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +58: warnings.warn( +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +58: warnings.warn( +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +58: warnings.warn( +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +58: warnings.warn( +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +58: warnings.warn( +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +58: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +36: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +43: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +32: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +56: warnings.warn( +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +57: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +59: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +32: warnings.warn( +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +57: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +32: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +51: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +47: warnings.warn( +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +48: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +51: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +47: warnings.warn( +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +54: warnings.warn( +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +54: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +59: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +60: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +50: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +50: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +42: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +62: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +63: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +63: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +58: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +60: warnings.warn( +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +41: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +56: warnings.warn( +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +62: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +41: warnings.warn( +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +46: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +42: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +55: warnings.warn( +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +55: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +52: warnings.warn( +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +58: warnings.warn( +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +37: warnings.warn( +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +56: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +46: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +34: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +61: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +40: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +40: warnings.warn( +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +61: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +39: warnings.warn( +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +39: warnings.warn( +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +49: warnings.warn( +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +49: warnings.warn( +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +33: warnings.warn( +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +33: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +44: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +48: warnings.warn( +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +34: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +53: warnings.warn( +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +53: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +38: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +45: warnings.warn( +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +45: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +44: warnings.warn( +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +38: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +35: warnings.warn( +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +35: warnings.warn( +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +37: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +36: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +36: warnings.warn( +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +43: warnings.warn( +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +52: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +43: warnings.warn( + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja... + 8: Building extension module utils... + 8: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Loading extension module utils... + 0: Loading extension module utils... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: + 3: + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: + 1: + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: + 1: + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: + 6: + 6: + 6: + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: + 9: + 9: + 9: +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: +10: +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: +10: +10: +10: +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: +11: +11: +11: +11: +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: +13: +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: +14: +14: +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: +15: +15: +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: +17: +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: +17: +17: +17: +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: +16: +16: +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: +16: +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: +18: +18: +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +21: +21: +21: +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +21: +21: +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: +22: +22: +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: +23: +23: +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: +24: +24: +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: +25: +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: +25: +25: +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: +28: +28: +28: +28: +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: +29: +29: +29: +29: +29: +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: +30: +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: +30: +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: +31: +31: +31: +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja... + 0: Building extension module utils... + 0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) + 0: Loading extension module utils... +20: Loading extension module utils... +17: Loading extension module utils... +17: Loading extension module utils... +17: Loading extension module utils... +16: Loading extension module utils... +17: Loading extension module utils... +16: Loading extension module utils... +17: Loading extension module utils... +16: Loading extension module utils... +17: Loading extension module utils... +17: Loading extension module utils... +16: Loading extension module utils... +17: Loading extension module utils... +18: Loading extension module utils... +16: Loading extension module utils... +18: Loading extension module utils... +16: Loading extension module utils... +18: Loading extension module utils... +16: Loading extension module utils... +18: Loading extension module utils... +16: Loading extension module utils... +18: Loading extension module utils... +18: Loading extension module utils... +18: Loading extension module utils... +18: Loading extension module utils... +21: Loading extension module utils... +21: Loading extension module utils... +21: Loading extension module utils... +22: Loading extension module utils... +22: Loading extension module utils... +21: Loading extension module utils... +22: Loading extension module utils... +21: Loading extension module utils... +22: Loading extension module utils... +21: Loading extension module utils... +22: Loading extension module utils... +21: Loading extension module utils... +22: Loading extension module utils... +21: Loading extension module utils... +22: Loading extension module utils... +22: Loading extension module utils... +26: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +26: Loading extension module utils... +27: Loading extension module utils... +26: Loading extension module utils... +27: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +27: Loading extension module utils... +26: Loading extension module utils... +27: Loading extension module utils... +23: Loading extension module utils... +26: Loading extension module utils... +23: Loading extension module utils... +27: Loading extension module utils... +23: Loading extension module utils... +26: Loading extension module utils... +27: Loading extension module utils... +23: Loading extension module utils... +23: Loading extension module utils... +23: Loading extension module utils... +23: Loading extension module utils... +23: Loading extension module utils... +24: Loading extension module utils... +24: Loading extension module utils... +24: Loading extension module utils... +24: Loading extension module utils... +24: Loading extension module utils... +24: Loading extension module utils... +24: Loading extension module utils... +24: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +28: Loading extension module utils... +28: Loading extension module utils... +28: Loading extension module utils... +28: Loading extension module utils... +28: Loading extension module utils... +28: Loading extension module utils... +28: Loading extension module utils... +28: Loading extension module utils... +29: Loading extension module utils... +29: Loading extension module utils... +29: Loading extension module utils... +29: Loading extension module utils... +29: Loading extension module utils... +29: Loading extension module utils... +30: Loading extension module utils... +30: Loading extension module utils... +29: Loading extension module utils... +30: Loading extension module utils... +29: Loading extension module utils... +30: Loading extension module utils... +30: Loading extension module utils... +30: Loading extension module utils... +30: Loading extension module utils... +30: Loading extension module utils... +31: Loading extension module utils... +31: Loading extension module utils... +31: Loading extension module utils... +31: Loading extension module utils... +31: Loading extension module utils... +31: Loading extension module utils... +31: Loading extension module utils... +31: Loading extension module utils... + 0: Loading extension module utils... + 0: Loading extension module utils... + 0: Loading extension module utils... + 0: Loading extension module utils... + 0: Loading extension module utils... + 0: Loading extension module utils... + 2: Loading extension module utils... + 3: Loading extension module utils... + 2: Loading extension module utils... + 2: Loading extension module utils... + 3: Loading extension module utils... + 2: Loading extension module utils... + 2: Loading extension module utils... + 3: Loading extension module utils... + 2: Loading extension module utils... + 3: Loading extension module utils... + 2: Loading extension module utils... + 3: Loading extension module utils... + 3: Loading extension module utils... + 4: Loading extension module utils... + 3: Loading extension module utils... + 4: Loading extension module utils... + 4: Loading extension module utils... + 4: Loading extension module utils... + 5: Loading extension module utils... + 4: Loading extension module utils... + 4: Loading extension module utils... + 4: Loading extension module utils... + 5: Loading extension module utils... + 5: Loading extension module utils... + 5: Loading extension module utils... + 5: Loading extension module utils... + 5: Loading extension module utils... + 5: Loading extension module utils... + 7: Loading extension module utils... + 7: Loading extension module utils... + 7: Loading extension module utils... + 7: Loading extension module utils... + 7: Loading extension module utils... + 7: Loading extension module utils... + 8: Loading extension module utils... + 7: Loading extension module utils... + 8: Loading extension module utils... + 8: Loading extension module utils... + 8: Loading extension module utils... + 8: Loading extension module utils... + 1: Loading extension module utils... + 8: Loading extension module utils... + 1: Loading extension module utils... + 8: Loading extension module utils... + 1: Loading extension module utils... + 1: Loading extension module utils... + 1: Loading extension module utils... + 1: Loading extension module utils... + 1: Loading extension module utils... + 1: Loading extension module utils... + 6: Loading extension module utils... +12: Loading extension module utils... + 6: Loading extension module utils... + 6: Loading extension module utils... + 6: Loading extension module utils... + 6: Loading extension module utils... + 2: Loading extension module utils... + 6: Loading extension module utils... + 6: Loading extension module utils... + 6: Loading extension module utils... +12: Loading extension module utils... + 3: Loading extension module utils... + 5: Loading extension module utils... +12: Loading extension module utils... + 4: Loading extension module utils... + 7: Loading extension module utils... +12: Loading extension module utils... +12: Loading extension module utils... +12: Loading extension module utils... +12: Loading extension module utils... +12: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... +11: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... +11: Loading extension module utils... +10: Loading extension module utils... + 0: No modifications detected for re-loaded extension module utils, skipping build step... + 0: Loading extension module utils... +11: Loading extension module utils... +10: Loading extension module utils... +11: Loading extension module utils... +10: Loading extension module utils... +19: Loading extension module utils... +11: Loading extension module utils... +10: Loading extension module utils... +11: Loading extension module utils... +10: Loading extension module utils... +10: Loading extension module utils... +11: Loading extension module utils... +11: Loading extension module utils... +10: Loading extension module utils... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: No modifications detected for re-loaded extension module utils, skipping build step... + 0: Loading extension module utils... + 0: No modifications detected for re-loaded extension module utils, skipping build step... + 0: Loading extension module utils... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: No modifications detected for re-loaded extension module utils, skipping build step... + 0: Loading extension module utils... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: No modifications detected for re-loaded extension module utils, skipping build step... + 0: Loading extension module utils... +19: Loading extension module utils... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Loading extension module utils... + 0: No modifications detected for re-loaded extension module utils, skipping build step... + 0: Loading extension module utils... +19: Loading extension module utils... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Loading extension module utils... +19: Loading extension module utils... + 0: No modifications detected for re-loaded extension module utils, skipping build step... + 0: Loading extension module utils... +19: Loading extension module utils... +19: Loading extension module utils... +13: Loading extension module utils... +13: Loading extension module utils... +13: Loading extension module utils... +14: Loading extension module utils... +13: Loading extension module utils... +13: Loading extension module utils... +14: Loading extension module utils... +13: Loading extension module utils... +14: Loading extension module utils... +14: Loading extension module utils... +13: Loading extension module utils... +13: Loading extension module utils... +14: Loading extension module utils... +14: Loading extension module utils... +14: Loading extension module utils... +14: Loading extension module utils... +20: Loading extension module utils... +20: Loading extension module utils... +20: Loading extension module utils... +20: Loading extension module utils... +20: Loading extension module utils... +15: Loading extension module utils... +20: Loading extension module utils... +15: Loading extension module utils... +20: Loading extension module utils... +15: Loading extension module utils... +15: Loading extension module utils... +15: Loading extension module utils... +15: Loading extension module utils... +15: Loading extension module utils... +15: Loading extension module utils... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: + 8: + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... + 8: + 8: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... + 8: + 8: Loading extension module utils... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils... +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: +27: +27: +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +27: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +27: +27: Loading extension module utils...Loading extension module utils... +27: +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: +16: +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: +18: +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: No modifications detected for re-loaded extension module utils, skipping build step... +16: Loading extension module utils... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... +16: No modifications detected for re-loaded extension module utils, skipping build step... +16: Loading extension module utils... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... +17: No modifications detected for re-loaded extension module utils, skipping build step... +16: No modifications detected for re-loaded extension module utils, skipping build step... +17: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +17: +16: Loading extension module utils... +17: Loading extension module utils... +16: No modifications detected for re-loaded extension module utils, skipping build step... +16: Loading extension module utils... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... +16: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +16: +16: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils...Loading extension module utils... +16: +16: +16: Loading extension module utils... +16: No modifications detected for re-loaded extension module utils, skipping build step... +16: Loading extension module utils... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +18: +18: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +18: +18: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +18: +18: Loading extension module utils... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: +26: No modifications detected for re-loaded extension module utils, skipping build step... +26: Loading extension module utils... +26: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +26: +26: Loading extension module utils...Loading extension module utils... +26: +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +26: +26: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils...Loading extension module utils... +26: +26: +26: Loading extension module utils... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: No modifications detected for re-loaded extension module utils, skipping build step... +26: Loading extension module utils... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: +23: +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: No modifications detected for re-loaded extension module utils, skipping build step... +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: +30: +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Loading extension module utils... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils... +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: +29: +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +21: +21: +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +31: +31: Loading extension module utils...Loading extension module utils... +31: +23: No modifications detected for re-loaded extension module utils, skipping build step... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Loading extension module utils... +23: No modifications detected for re-loaded extension module utils, skipping build step... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Loading extension module utils... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: +22: +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: +23: No modifications detected for re-loaded extension module utils, skipping build step... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: +25: +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +30: +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +21: No modifications detected for re-loaded extension module utils, skipping build step... +21: Loading extension module utils... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: +31: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +31: +31: Loading extension module utils... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: +28: +31: No modifications detected for re-loaded extension module utils, skipping build step... +30: No modifications detected for re-loaded extension module utils, skipping build step... +31: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +31: +31: Loading extension module utils... +30: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +30: +30: Loading extension module utils... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +30: No modifications detected for re-loaded extension module utils, skipping build step... +31: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils... +21: No modifications detected for re-loaded extension module utils, skipping build step... +21: Loading extension module utils... +31: Loading extension module utils... +21: No modifications detected for re-loaded extension module utils, skipping build step... +21: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +21: +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +21: Loading extension module utils... +21: No modifications detected for re-loaded extension module utils, skipping build step... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +21: Loading extension module utils... +21: No modifications detected for re-loaded extension module utils, skipping build step... +21: Loading extension module utils... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +21: No modifications detected for re-loaded extension module utils, skipping build step... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +29: +29: Loading extension module utils... +21: Loading extension module utils... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +24: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +24: +24: Loading extension module utils...Loading extension module utils... +24: +24: No modifications detected for re-loaded extension module utils, skipping build step... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: Loading extension module utils... +25: No modifications detected for re-loaded extension module utils, skipping build step... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +28: +24: Loading extension module utils... +21: No modifications detected for re-loaded extension module utils, skipping build step... +25: Loading extension module utils... +28: Loading extension module utils... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +21: Loading extension module utils... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... +22: +22: Loading extension module utils... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: Loading extension module utils... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... +25: No modifications detected for re-loaded extension module utils, skipping build step... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... +25: Loading extension module utils... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: Loading extension module utils... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: Loading extension module utils... +25: No modifications detected for re-loaded extension module utils, skipping build step... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... +25: Loading extension module utils... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: Loading extension module utils... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: +19: +19: +19: No modifications detected for re-loaded extension module utils, skipping build step... +19: Loading extension module utils... +19: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +19: +19: +19: Loading extension module utils...Loading extension module utils... +19: Loading extension module utils... +19: +19: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +19: +19: +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Loading extension module utils...Loading extension module utils...Loading extension module utils... +19: +19: +19: No modifications detected for re-loaded extension module utils, skipping build step... +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Loading extension module utils... +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: +15: +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... + 7: No modifications detected for re-loaded extension module utils, skipping build step... + 7: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... + 7: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... + 7: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... + 7: + 7: + 7: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... + 7: Loading extension module utils... + 7: + 7: + 7: + 7: Loading extension module utils...Loading extension module utils...Loading extension module utils... + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: + 7: + 7: No modifications detected for re-loaded extension module utils, skipping build step... + 7: Loading extension module utils... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +15: + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: Loading extension module utils... + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +15: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +15: +15: Loading extension module utils...Loading extension module utils... + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: No modifications detected for re-loaded extension module utils, skipping build step... +13: Loading extension module utils... +13: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +13: +13: Loading extension module utils... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +13: Loading extension module utils... + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: +11: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: Loading extension module utils... +11: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +11: + 5: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: No modifications detected for re-loaded extension module utils, skipping build step... +13: Loading extension module utils... +11: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +11: +11: Loading extension module utils... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: No modifications detected for re-loaded extension module utils, skipping build step... + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... + 5: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Loading extension module utils... +13: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Loading extension module utils... + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: + 3: +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... + 5: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: + 6: + 6: +13: No modifications detected for re-loaded extension module utils, skipping build step... +13: Loading extension module utils... + 5: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: + 3: + 3: + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: No modifications detected for re-loaded extension module utils, skipping build step... +13: Loading extension module utils... + 3: No modifications detected for re-loaded extension module utils, skipping build step... + 3: Loading extension module utils... + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Loading extension module utils... + 2: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Loading extension module utils... + 2: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... + 2: + 2: Loading extension module utils...Loading extension module utils... + 2: + 5: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils... + 5: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils... + 3: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... + 3: + 3: + 3: Loading extension module utils...Loading extension module utils... + 3: Loading extension module utils... + 3: + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Loading extension module utils... + 3: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... + 3: + 3: + 3: + 3: Loading extension module utils...Loading extension module utils...Loading extension module utils...Loading extension module utils... + 3: + 3: + 3: + 5: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... + 5: + 5: Loading extension module utils... + 2: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Loading extension module utils... + 2: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Loading extension module utils... + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Loading extension module utils... + 2: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Loading extension module utils... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Loading extension module utils... + 2: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Loading extension module utils... + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Loading extension module utils... + 2: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Loading extension module utils... + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 1: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... + 1: + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 6: Loading extension module utils... + 1: Loading extension module utils... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Loading extension module utils... + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 6: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... + 6: + 6: Loading extension module utils... + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 6: Loading extension module utils... + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 6: Loading extension module utils... + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 6: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... + 6: + 6: Loading extension module utils... + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 6: Loading extension module utils... + 4: No modifications detected for re-loaded extension module utils, skipping build step... + 4: Loading extension module utils... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: No modifications detected for re-loaded extension module utils, skipping build step... + 4: Loading extension module utils... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: No modifications detected for re-loaded extension module utils, skipping build step... + 4: Loading extension module utils... + 4: No modifications detected for re-loaded extension module utils, skipping build step... + 4: Loading extension module utils... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: No modifications detected for re-loaded extension module utils, skipping build step... + 4: Loading extension module utils... + 4: No modifications detected for re-loaded extension module utils, skipping build step... + 4: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... + 4: + 4: Loading extension module utils... + 4: No modifications detected for re-loaded extension module utils, skipping build step... + 4: Loading extension module utils... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils... +14: No modifications detected for re-loaded extension module utils, skipping build step... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: Loading extension module utils... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: +10: +10: +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: + 9: + 9: +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: No modifications detected for re-loaded extension module utils, skipping build step... + 9: Loading extension module utils... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: No modifications detected for re-loaded extension module utils, skipping build step... + 9: Loading extension module utils... + 9: No modifications detected for re-loaded extension module utils, skipping build step... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... + 9: Loading extension module utils... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... + 9: No modifications detected for re-loaded extension module utils, skipping build step... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... + 9: Loading extension module utils... + 9: No modifications detected for re-loaded extension module utils, skipping build step... + 9: Loading extension module utils... + 9: No modifications detected for re-loaded extension module utils, skipping build step... + 9: Loading extension module utils... + 9: No modifications detected for re-loaded extension module utils, skipping build step... + 9: Loading extension module utils... +12: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: +12: Loading extension module utils...Loading extension module utils... +12: +12: Loading extension module utils... + 9: No modifications detected for re-loaded extension module utils, skipping build step... + 9: Loading extension module utils... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: No modifications detected for re-loaded extension module utils, skipping build step... + 0: Loading extension module utils... +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +40: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +42: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +50: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +56: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja... +33: Building extension module utils... +33: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +33: Loading extension module utils... +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: +32: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +37: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +37: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +37: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +37: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +37: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +37: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +37: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +37: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +35: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +35: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +35: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +35: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +35: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +35: +35: +35: +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: +36: +36: +40: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +40: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +40: +40: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +40: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +40: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +40: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: +41: +38: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +38: +38: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +38: +38: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +38: +38: +38: +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +42: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +42: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +42: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +42: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +42: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +42: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +42: +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +47: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +47: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +47: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +47: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +47: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +47: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +47: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +47: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +43: +43: +43: +43: +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +43: +43: +45: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +45: +45: +45: +45: +45: +45: +45: +46: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +46: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +46: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +46: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +46: +46: +46: +46: +50: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +50: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +50: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +50: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +50: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +50: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +50: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +48: +48: +48: +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +49: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +49: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +49: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +49: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +49: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +49: +49: +49: +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +51: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +51: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +51: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +51: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +51: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +51: +51: +51: +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +55: +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +56: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +56: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +56: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +56: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +56: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +56: +56: +54: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +54: +54: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +54: +54: +54: +54: +54: +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: +60: +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +57: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +57: +57: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +57: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +57: +57: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +57: +57: +59: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +59: +59: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +59: +59: +59: +59: +59: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: +61: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: +61: +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +62: +62: +62: +62: +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +62: +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +63: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +63: +63: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +63: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +63: +63: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +63: +63: +33: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja... +33: Building extension module utils... +33: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +33: Loading extension module utils... +44: Loading extension module utils... +44: Loading extension module utils... +44: Loading extension module utils... +44: Loading extension module utils... +44: Loading extension module utils... +44: Loading extension module utils... +44: Loading extension module utils... +47: Loading extension module utils... +47: Loading extension module utils... +47: Loading extension module utils... +47: Loading extension module utils... +47: Loading extension module utils... +47: Loading extension module utils... +40: Loading extension module utils... +47: Loading extension module utils... +47: Loading extension module utils... +43: Loading extension module utils... +43: Loading extension module utils... +43: Loading extension module utils... +43: Loading extension module utils... +43: Loading extension module utils... +43: Loading extension module utils... +43: Loading extension module utils... +43: Loading extension module utils... +41: Loading extension module utils... +50: Loading extension module utils... +50: Loading extension module utils... +45: Loading extension module utils... +50: Loading extension module utils... +45: Loading extension module utils... +45: Loading extension module utils... +50: Loading extension module utils... +50: Loading extension module utils... +45: Loading extension module utils... +46: Loading extension module utils... +45: Loading extension module utils... +50: Loading extension module utils... +46: Loading extension module utils... +45: Loading extension module utils... +46: Loading extension module utils... +50: Loading extension module utils... +45: Loading extension module utils... +46: Loading extension module utils... +45: Loading extension module utils... +42: Loading extension module utils... +46: Loading extension module utils... +46: Loading extension module utils... +46: Loading extension module utils... +46: Loading extension module utils... +53: Loading extension module utils... +44: Loading extension module utils... +53: Loading extension module utils... +53: Loading extension module utils... +53: Loading extension module utils... +53: Loading extension module utils... +53: Loading extension module utils... +53: Loading extension module utils... +52: Loading extension module utils... +48: Loading extension module utils... +48: Loading extension module utils... +48: Loading extension module utils... +52: Loading extension module utils... +52: Loading extension module utils... +52: Loading extension module utils... +48: Loading extension module utils... +52: Loading extension module utils... +48: Loading extension module utils... +48: Loading extension module utils... +52: Loading extension module utils... +48: Loading extension module utils... +52: Loading extension module utils... +48: Loading extension module utils... +49: Loading extension module utils... +49: Loading extension module utils... +49: Loading extension module utils... +49: Loading extension module utils... +49: Loading extension module utils... +49: Loading extension module utils... +49: Loading extension module utils... +49: Loading extension module utils... +56: Loading extension module utils... +56: Loading extension module utils... +56: Loading extension module utils... +56: Loading extension module utils... +51: Loading extension module utils... +56: Loading extension module utils... +56: Loading extension module utils... +56: Loading extension module utils... +51: Loading extension module utils... +51: Loading extension module utils... +51: Loading extension module utils... +51: Loading extension module utils... +55: Loading extension module utils... +51: Loading extension module utils... +51: Loading extension module utils... +55: Loading extension module utils... +51: Loading extension module utils... +55: Loading extension module utils... +55: Loading extension module utils... +55: Loading extension module utils... +55: Loading extension module utils... +53: Loading extension module utils... +55: Loading extension module utils... +50: Loading extension module utils... +55: Loading extension module utils... +58: Loading extension module utils... +58: Loading extension module utils... +58: Loading extension module utils... +58: Loading extension module utils... +54: Loading extension module utils... +58: Loading extension module utils... +54: Loading extension module utils... +54: Loading extension module utils... +58: Loading extension module utils... +58: Loading extension module utils... +54: Loading extension module utils... +54: Loading extension module utils... +54: Loading extension module utils... +54: Loading extension module utils... +54: Loading extension module utils... +52: Loading extension module utils... +57: Loading extension module utils... +57: Loading extension module utils... +57: Loading extension module utils... +57: Loading extension module utils... +57: Loading extension module utils... +60: Loading extension module utils... +57: Loading extension module utils... +60: Loading extension module utils... +57: Loading extension module utils... +60: Loading extension module utils... +57: Loading extension module utils... +60: Loading extension module utils... +60: Loading extension module utils... +60: Loading extension module utils... +60: Loading extension module utils... +60: Loading extension module utils... +59: Loading extension module utils... +59: Loading extension module utils... +56: Loading extension module utils... +59: Loading extension module utils... +59: Loading extension module utils... +59: Loading extension module utils... +59: Loading extension module utils... +59: Loading extension module utils... +59: Loading extension module utils... +58: Loading extension module utils... +61: Loading extension module utils... +61: Loading extension module utils... +61: Loading extension module utils... +61: Loading extension module utils... +61: Loading extension module utils... +61: Loading extension module utils... +61: Loading extension module utils... +61: Loading extension module utils... +62: Loading extension module utils... +62: Loading extension module utils... +62: Loading extension module utils... +62: Loading extension module utils... +62: Loading extension module utils... +62: Loading extension module utils... +63: Loading extension module utils... +62: Loading extension module utils... +63: Loading extension module utils... +62: Loading extension module utils... +63: Loading extension module utils... +63: Loading extension module utils... +63: Loading extension module utils... +63: Loading extension module utils... +63: Loading extension module utils... +63: Loading extension module utils... +32: Loading extension module utils... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: +44: +44: +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: No modifications detected for re-loaded extension module utils, skipping build step... +44: Loading extension module utils... +44: No modifications detected for re-loaded extension module utils, skipping build step... +44: Loading extension module utils... +44: No modifications detected for re-loaded extension module utils, skipping build step... +44: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +44: +44: Loading extension module utils... +44: No modifications detected for re-loaded extension module utils, skipping build step... +44: Loading extension module utils... +44: No modifications detected for re-loaded extension module utils, skipping build step... +44: Loading extension module utils... +44: No modifications detected for re-loaded extension module utils, skipping build step... +44: Loading extension module utils... +44: No modifications detected for re-loaded extension module utils, skipping build step... +44: Loading extension module utils... +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: No modifications detected for re-loaded extension module utils, skipping build step... +33: Loading extension module utils... +33: No modifications detected for re-loaded extension module utils, skipping build step... +33: Loading extension module utils... +33: Loading extension module utils... +33: Loading extension module utils...Loading extension module utils... +33: +33: Loading extension module utils... +33: Loading extension module utils... +33: Loading extension module utils... +32: Loading extension module utils... +32: Loading extension module utils... +32: Loading extension module utils... +32: Loading extension module utils... +32: Loading extension module utils... +32: Loading extension module utils... +32: Loading extension module utils... +39: Loading extension module utils... +39: Loading extension module utils... +39: Loading extension module utils... +39: Loading extension module utils... +37: Loading extension module utils... +39: Loading extension module utils... +39: Loading extension module utils... +37: Loading extension module utils... +39: Loading extension module utils... +37: Loading extension module utils... +37: Loading extension module utils... +37: Loading extension module utils... +37: Loading extension module utils... +37: Loading extension module utils... +37: Loading extension module utils... +40: Loading extension module utils... +40: Loading extension module utils... +40: Loading extension module utils... +40: Loading extension module utils... +40: Loading extension module utils... +40: Loading extension module utils... +34: Loading extension module utils... +40: Loading extension module utils... +34: Loading extension module utils... +34: Loading extension module utils... +35: Loading extension module utils... +35: Loading extension module utils... +34: Loading extension module utils... +34: Loading extension module utils... +35: Loading extension module utils... +34: Loading extension module utils... +35: Loading extension module utils... +34: Loading extension module utils... +35: Loading extension module utils... +34: Loading extension module utils... +35: Loading extension module utils... +35: Loading extension module utils... +35: Loading extension module utils... +42: Loading extension module utils... +36: Loading extension module utils... +36: Loading extension module utils... +36: Loading extension module utils... +41: Loading extension module utils... +42: Loading extension module utils... +36: Loading extension module utils... +38: Loading extension module utils... +42: Loading extension module utils... +36: Loading extension module utils... +42: Loading extension module utils... +41: Loading extension module utils... +36: Loading extension module utils... +41: Loading extension module utils... +42: Loading extension module utils... +42: Loading extension module utils... +36: Loading extension module utils... +41: Loading extension module utils... +42: Loading extension module utils... +36: Loading extension module utils... +41: Loading extension module utils... +41: Loading extension module utils... +39: Loading extension module utils... +41: Loading extension module utils... +38: Loading extension module utils... +38: Loading extension module utils... +38: Loading extension module utils... +38: Loading extension module utils... +38: Loading extension module utils... +38: Loading extension module utils... +38: Loading extension module utils... +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: No modifications detected for re-loaded extension module utils, skipping build step... +33: Loading extension module utils... +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +62: +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: No modifications detected for re-loaded extension module utils, skipping build step... +33: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +33: +33: Loading extension module utils... +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: No modifications detected for re-loaded extension module utils, skipping build step... +33: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +33: +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: +33: Loading extension module utils... +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: No modifications detected for re-loaded extension module utils, skipping build step... +33: Loading extension module utils... +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +48: +48: +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +62: No modifications detected for re-loaded extension module utils, skipping build step... +62: Loading extension module utils... +52: No modifications detected for re-loaded extension module utils, skipping build step... +52: Loading extension module utils... +48: No modifications detected for re-loaded extension module utils, skipping build step... +48: Loading extension module utils... +48: No modifications detected for re-loaded extension module utils, skipping build step... +48: Loading extension module utils... +52: No modifications detected for re-loaded extension module utils, skipping build step... +52: Loading extension module utils... +62: No modifications detected for re-loaded extension module utils, skipping build step... +62: Loading extension module utils... +62: No modifications detected for re-loaded extension module utils, skipping build step... +62: Loading extension module utils... +62: No modifications detected for re-loaded extension module utils, skipping build step... +62: Loading extension module utils... +62: No modifications detected for re-loaded extension module utils, skipping build step... +62: Loading extension module utils... +62: No modifications detected for re-loaded extension module utils, skipping build step... +62: Loading extension module utils... +48: No modifications detected for re-loaded extension module utils, skipping build step... +48: Loading extension module utils... +62: No modifications detected for re-loaded extension module utils, skipping build step... +62: Loading extension module utils... +48: No modifications detected for re-loaded extension module utils, skipping build step... +48: Loading extension module utils... +48: No modifications detected for re-loaded extension module utils, skipping build step... +52: No modifications detected for re-loaded extension module utils, skipping build step... +52: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +52: +62: No modifications detected for re-loaded extension module utils, skipping build step... +62: Loading extension module utils... +48: Loading extension module utils... +48: No modifications detected for re-loaded extension module utils, skipping build step... +48: Loading extension module utils... +48: No modifications detected for re-loaded extension module utils, skipping build step... +48: Loading extension module utils... +52: Loading extension module utils... +52: No modifications detected for re-loaded extension module utils, skipping build step... +52: Loading extension module utils... +52: No modifications detected for re-loaded extension module utils, skipping build step... +52: Loading extension module utils... +52: No modifications detected for re-loaded extension module utils, skipping build step... +52: Loading extension module utils... +48: No modifications detected for re-loaded extension module utils, skipping build step... +48: Loading extension module utils... +52: No modifications detected for re-loaded extension module utils, skipping build step... +52: Loading extension module utils... +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: No modifications detected for re-loaded extension module utils, skipping build step... +53: Loading extension module utils... +53: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +53: +53: Loading extension module utils...Loading extension module utils... +53: +53: No modifications detected for re-loaded extension module utils, skipping build step... +53: Loading extension module utils... +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: +53: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +53: +53: +53: +53: Loading extension module utils...Loading extension module utils...Loading extension module utils...Loading extension module utils... +53: +53: +53: +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: +59: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +59: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +59: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +59: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +59: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +59: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +42: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +42: +42: +42: +59: +41: No modifications detected for re-loaded extension module utils, skipping build step... +41: Loading extension module utils... +41: No modifications detected for re-loaded extension module utils, skipping build step... +41: Loading extension module utils... +42: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +42: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +42: +59: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +41: +41: +41: Loading extension module utils...Loading extension module utils...Loading extension module utils... +41: +41: +41: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +41: +41: Loading extension module utils... +41: Loading extension module utils... +42: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +59: No modifications detected for re-loaded extension module utils, skipping build step... +59: Loading extension module utils... +42: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +42: +42: Loading extension module utils...Loading extension module utils... +42: +41: No modifications detected for re-loaded extension module utils, skipping build step... +41: Loading extension module utils... +42: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +42: +42: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +42: Loading extension module utils... +42: No modifications detected for re-loaded extension module utils, skipping build step... +42: Loading extension module utils... +42: +42: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +42: +42: Loading extension module utils... +42: No modifications detected for re-loaded extension module utils, skipping build step... +42: Loading extension module utils... +59: No modifications detected for re-loaded extension module utils, skipping build step... +59: Loading extension module utils... +59: No modifications detected for re-loaded extension module utils, skipping build step... +59: Loading extension module utils... +59: No modifications detected for re-loaded extension module utils, skipping build step... +59: Loading extension module utils... +45: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +45: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +59: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +59: +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +59: Loading extension module utils... +59: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +59: +59: Loading extension module utils... +45: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: +60: +45: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +45: +45: +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +59: No modifications detected for re-loaded extension module utils, skipping build step... +59: Loading extension module utils... +45: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +45: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: +32: +32: +32: +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: +32: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +32: +32: Loading extension module utils...Loading extension module utils... +32: +58: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +58: +58: Loading extension module utils...Loading extension module utils... +58: +58: No modifications detected for re-loaded extension module utils, skipping build step... +32: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +32: +32: +32: +32: +32: +32: Loading extension module utils...Loading extension module utils...Loading extension module utils... +32: Loading extension module utils... +58: Loading extension module utils... +32: Loading extension module utils... +32: Loading extension module utils... +32: +32: +60: No modifications detected for re-loaded extension module utils, skipping build step... +60: Loading extension module utils... +58: No modifications detected for re-loaded extension module utils, skipping build step... +58: Loading extension module utils... +58: No modifications detected for re-loaded extension module utils, skipping build step... +49: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: Loading extension module utils... +60: No modifications detected for re-loaded extension module utils, skipping build step... +60: Loading extension module utils... +49: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: No modifications detected for re-loaded extension module utils, skipping build step... +58: Loading extension module utils... +49: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +45: No modifications detected for re-loaded extension module utils, skipping build step... +45: Loading extension module utils... +49: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: No modifications detected for re-loaded extension module utils, skipping build step... +60: Loading extension module utils... +49: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: No modifications detected for re-loaded extension module utils, skipping build step... +58: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +58: +58: Loading extension module utils... +49: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +49: +49: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +45: No modifications detected for re-loaded extension module utils, skipping build step... +45: Loading extension module utils... +60: No modifications detected for re-loaded extension module utils, skipping build step... +60: Loading extension module utils... +60: No modifications detected for re-loaded extension module utils, skipping build step... +60: Loading extension module utils... +56: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +56: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: No modifications detected for re-loaded extension module utils, skipping build step... +60: Loading extension module utils... +60: No modifications detected for re-loaded extension module utils, skipping build step... +60: Loading extension module utils... +45: No modifications detected for re-loaded extension module utils, skipping build step... +45: Loading extension module utils... +40: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +56: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +56: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +40: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +56: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +56: +56: +56: +45: No modifications detected for re-loaded extension module utils, skipping build step... +45: Loading extension module utils... +45: No modifications detected for re-loaded extension module utils, skipping build step... +40: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +40: +60: No modifications detected for re-loaded extension module utils, skipping build step... +60: Loading extension module utils... +46: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +45: Loading extension module utils... +45: No modifications detected for re-loaded extension module utils, skipping build step... +45: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +40: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +40: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +45: +45: Loading extension module utils... +46: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +46: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +40: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +56: No modifications detected for re-loaded extension module utils, skipping build step... +56: Loading extension module utils... +40: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +46: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +46: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +45: No modifications detected for re-loaded extension module utils, skipping build step... +45: Loading extension module utils... +51: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +46: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +40: No modifications detected for re-loaded extension module utils, skipping build step... +40: Loading extension module utils... +56: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +56: +56: +56: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +56: Loading extension module utils... +56: +56: +56: +56: Loading extension module utils...Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +56: +56: +61: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +51: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +51: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +46: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +40: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +40: +40: Loading extension module utils...Loading extension module utils... +40: +56: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +56: +56: Loading extension module utils... +46: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: +51: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +51: +51: +51: +51: +49: No modifications detected for re-loaded extension module utils, skipping build step... +49: Loading extension module utils... +40: No modifications detected for re-loaded extension module utils, skipping build step... +40: Loading extension module utils... +61: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: +61: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +40: No modifications detected for re-loaded extension module utils, skipping build step... +40: Loading extension module utils... +40: No modifications detected for re-loaded extension module utils, skipping build step... +40: Loading extension module utils... +40: No modifications detected for re-loaded extension module utils, skipping build step... +40: Loading extension module utils... +49: No modifications detected for re-loaded extension module utils, skipping build step... +49: Loading extension module utils... +40: No modifications detected for re-loaded extension module utils, skipping build step... +40: Loading extension module utils... +49: No modifications detected for re-loaded extension module utils, skipping build step... +49: Loading extension module utils... +49: No modifications detected for re-loaded extension module utils, skipping build step... +49: Loading extension module utils... +49: No modifications detected for re-loaded extension module utils, skipping build step... +49: Loading extension module utils... +49: No modifications detected for re-loaded extension module utils, skipping build step... +49: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +49: +49: Loading extension module utils... +46: No modifications detected for re-loaded extension module utils, skipping build step... +46: Loading extension module utils... +49: No modifications detected for re-loaded extension module utils, skipping build step... +49: Loading extension module utils... +46: No modifications detected for re-loaded extension module utils, skipping build step... +46: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +46: +46: Loading extension module utils... +51: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +51: +51: Loading extension module utils...Loading extension module utils... +51: +63: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +63: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +63: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +63: +46: No modifications detected for re-loaded extension module utils, skipping build step... +46: Loading extension module utils... +63: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +63: +46: No modifications detected for re-loaded extension module utils, skipping build step... +46: Loading extension module utils... +61: No modifications detected for re-loaded extension module utils, skipping build step... +61: Loading extension module utils... +63: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +51: No modifications detected for re-loaded extension module utils, skipping build step... +46: No modifications detected for re-loaded extension module utils, skipping build step... +46: Loading extension module utils... +51: Loading extension module utils... +51: No modifications detected for re-loaded extension module utils, skipping build step... +51: Loading extension module utils... +46: No modifications detected for re-loaded extension module utils, skipping build step... +46: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +46: +51: No modifications detected for re-loaded extension module utils, skipping build step... +51: Loading extension module utils... +46: Loading extension module utils... +61: No modifications detected for re-loaded extension module utils, skipping build step... +61: Loading extension module utils... +61: No modifications detected for re-loaded extension module utils, skipping build step... +51: No modifications detected for re-loaded extension module utils, skipping build step... +51: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +51: +51: Loading extension module utils... +61: Loading extension module utils... +51: No modifications detected for re-loaded extension module utils, skipping build step... +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +51: Loading extension module utils... +63: No modifications detected for re-loaded extension module utils, skipping build step... +63: Loading extension module utils... +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: No modifications detected for re-loaded extension module utils, skipping build step... +61: Loading extension module utils... +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: No modifications detected for re-loaded extension module utils, skipping build step... +63: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +55: +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: Loading extension module utils... +61: No modifications detected for re-loaded extension module utils, skipping build step... +61: Loading extension module utils... +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: No modifications detected for re-loaded extension module utils, skipping build step... +61: Loading extension module utils... +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: No modifications detected for re-loaded extension module utils, skipping build step... +61: Loading extension module utils... +63: No modifications detected for re-loaded extension module utils, skipping build step... +63: Loading extension module utils... +63: No modifications detected for re-loaded extension module utils, skipping build step... +63: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +63: +63: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +63: +63: Loading extension module utils... +63: No modifications detected for re-loaded extension module utils, skipping build step... +63: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +63: +63: Loading extension module utils... +55: No modifications detected for re-loaded extension module utils, skipping build step... +55: Loading extension module utils... +63: No modifications detected for re-loaded extension module utils, skipping build step... +63: Loading extension module utils... +55: No modifications detected for re-loaded extension module utils, skipping build step... +55: Loading extension module utils... +55: No modifications detected for re-loaded extension module utils, skipping build step... +55: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +55: +55: Loading extension module utils... +55: No modifications detected for re-loaded extension module utils, skipping build step... +55: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +55: +55: Loading extension module utils... +55: No modifications detected for re-loaded extension module utils, skipping build step... +55: Loading extension module utils... +55: No modifications detected for re-loaded extension module utils, skipping build step... +55: Loading extension module utils... +50: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +50: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +50: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +50: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +50: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +50: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +50: +50: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +50: No modifications detected for re-loaded extension module utils, skipping build step... +50: Loading extension module utils... +50: No modifications detected for re-loaded extension module utils, skipping build step... +50: Loading extension module utils... +50: No modifications detected for re-loaded extension module utils, skipping build step... +50: Loading extension module utils... +50: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +50: +50: +50: Loading extension module utils...Loading extension module utils...Loading extension module utils... +50: +50: +50: No modifications detected for re-loaded extension module utils, skipping build step... +50: Loading extension module utils... +50: No modifications detected for re-loaded extension module utils, skipping build step... +50: Loading extension module utils... +57: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +57: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +57: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +57: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +57: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +57: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +57: +57: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +57: No modifications detected for re-loaded extension module utils, skipping build step... +57: Loading extension module utils... +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +43: +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +57: No modifications detected for re-loaded extension module utils, skipping build step... +57: Loading extension module utils... +47: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +47: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +57: No modifications detected for re-loaded extension module utils, skipping build step... +57: Loading extension module utils... +57: No modifications detected for re-loaded extension module utils, skipping build step... +57: Loading extension module utils... +57: No modifications detected for re-loaded extension module utils, skipping build step... +57: Loading extension module utils... +57: No modifications detected for re-loaded extension module utils, skipping build step... +57: Loading extension module utils... +57: No modifications detected for re-loaded extension module utils, skipping build step... +57: Loading extension module utils... +47: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +47: +47: +47: +47: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +47: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +57: No modifications detected for re-loaded extension module utils, skipping build step... +57: Loading extension module utils... +43: No modifications detected for re-loaded extension module utils, skipping build step... +43: Loading extension module utils... +43: No modifications detected for re-loaded extension module utils, skipping build step... +43: Loading extension module utils... +47: No modifications detected for re-loaded extension module utils, skipping build step... +47: Loading extension module utils... +47: No modifications detected for re-loaded extension module utils, skipping build step... +43: No modifications detected for re-loaded extension module utils, skipping build step... +43: Loading extension module utils... +43: No modifications detected for re-loaded extension module utils, skipping build step... +43: Loading extension module utils... +47: Loading extension module utils... +43: No modifications detected for re-loaded extension module utils, skipping build step... +43: Loading extension module utils... +43: No modifications detected for re-loaded extension module utils, skipping build step... +43: Loading extension module utils... +43: No modifications detected for re-loaded extension module utils, skipping build step... +43: Loading extension module utils... +43: No modifications detected for re-loaded extension module utils, skipping build step... +43: Loading extension module utils... +47: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +47: +47: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils...Loading extension module utils... +47: +47: +47: Loading extension module utils... +47: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +47: +47: Loading extension module utils... +47: Loading extension module utils... +47: No modifications detected for re-loaded extension module utils, skipping build step... +47: Loading extension module utils... +54: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +54: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +54: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +54: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +54: +54: +54: +54: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +54: No modifications detected for re-loaded extension module utils, skipping build step... +54: Loading extension module utils... +54: No modifications detected for re-loaded extension module utils, skipping build step... +54: Loading extension module utils... +54: No modifications detected for re-loaded extension module utils, skipping build step... +54: Loading extension module utils... +54: No modifications detected for re-loaded extension module utils, skipping build step... +54: Loading extension module utils... +54: No modifications detected for re-loaded extension module utils, skipping build step... +54: Loading extension module utils... +54: No modifications detected for re-loaded extension module utils, skipping build step... +54: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +54: +54: Loading extension module utils... +54: No modifications detected for re-loaded extension module utils, skipping build step... +54: Loading extension module utils... +38: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +38: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +38: +38: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +38: +38: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +38: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +38: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +38: No modifications detected for re-loaded extension module utils, skipping build step... +38: Loading extension module utils... +38: No modifications detected for re-loaded extension module utils, skipping build step... +38: Loading extension module utils... +38: No modifications detected for re-loaded extension module utils, skipping build step... +38: Loading extension module utils... +38: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +38: +38: Loading extension module utils...Loading extension module utils... +38: +38: No modifications detected for re-loaded extension module utils, skipping build step... +38: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +38: +38: Loading extension module utils... +38: No modifications detected for re-loaded extension module utils, skipping build step... +38: Loading extension module utils... +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: +34: +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: No modifications detected for re-loaded extension module utils, skipping build step... +34: Loading extension module utils... +34: No modifications detected for re-loaded extension module utils, skipping build step... +34: Loading extension module utils... +34: No modifications detected for re-loaded extension module utils, skipping build step... +34: Loading extension module utils... +34: No modifications detected for re-loaded extension module utils, skipping build step... +34: Loading extension module utils... +34: No modifications detected for re-loaded extension module utils, skipping build step... +34: Loading extension module utils... +34: No modifications detected for re-loaded extension module utils, skipping build step... +34: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +34: +34: Loading extension module utils... +34: No modifications detected for re-loaded extension module utils, skipping build step... +34: Loading extension module utils... +36: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: +36: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: +36: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: No modifications detected for re-loaded extension module utils, skipping build step... +36: Loading extension module utils... +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +39: +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +39: +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: No modifications detected for re-loaded extension module utils, skipping build step... +36: Loading extension module utils... +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: No modifications detected for re-loaded extension module utils, skipping build step... +36: Loading extension module utils... +36: No modifications detected for re-loaded extension module utils, skipping build step... +36: Loading extension module utils... +39: No modifications detected for re-loaded extension module utils, skipping build step... +39: Loading extension module utils... +36: No modifications detected for re-loaded extension module utils, skipping build step... +36: Loading extension module utils... +39: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +39: +39: +39: Loading extension module utils...Loading extension module utils... +39: Loading extension module utils... +39: +39: No modifications detected for re-loaded extension module utils, skipping build step... +39: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +39: +36: No modifications detected for re-loaded extension module utils, skipping build step... +36: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +36: +36: Loading extension module utils... +39: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +39: +39: Loading extension module utils... +36: No modifications detected for re-loaded extension module utils, skipping build step... +36: Loading extension module utils... +39: No modifications detected for re-loaded extension module utils, skipping build step... +39: Loading extension module utils... +37: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +37: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +37: +37: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +37: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +37: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +37: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +35: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +37: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +35: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +35: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +35: +35: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +35: +35: +35: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +37: No modifications detected for re-loaded extension module utils, skipping build step... +37: Loading extension module utils... +35: No modifications detected for re-loaded extension module utils, skipping build step... +35: Loading extension module utils... +35: No modifications detected for re-loaded extension module utils, skipping build step... +35: Loading extension module utils... +37: No modifications detected for re-loaded extension module utils, skipping build step... +37: Loading extension module utils... +35: No modifications detected for re-loaded extension module utils, skipping build step... +35: Loading extension module utils... +35: No modifications detected for re-loaded extension module utils, skipping build step... +35: Loading extension module utils... +37: No modifications detected for re-loaded extension module utils, skipping build step... +37: Loading extension module utils... +37: No modifications detected for re-loaded extension module utils, skipping build step... +37: Loading extension module utils... +37: No modifications detected for re-loaded extension module utils, skipping build step... +35: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +35: +35: Loading extension module utils...Loading extension module utils... +35: No modifications detected for re-loaded extension module utils, skipping build step... +35: +35: Loading extension module utils... +37: Loading extension module utils... +37: No modifications detected for re-loaded extension module utils, skipping build step... +37: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +37: +37: Loading extension module utils... +35: No modifications detected for re-loaded extension module utils, skipping build step... +35: Loading extension module utils... +37: No modifications detected for re-loaded extension module utils, skipping build step... +37: Loading extension module utils... + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/utils.py:349: UserWarning: Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings + 0: warnings.warn("Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings") +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +41: if inputs.grad is not None: +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +41: if inputs.grad is not None: +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +41: if inputs.grad is not None: +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +41: if inputs.grad is not None: +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +41: if inputs.grad is not None: +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +41: if inputs.grad is not None: +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +39: if inputs.grad is not None: +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +62: if inputs.grad is not None: +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +38: if inputs.grad is not None: +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +62: if inputs.grad is not None: +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +38: if inputs.grad is not None: +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +62: if inputs.grad is not None: +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +38: if inputs.grad is not None: +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +39: if inputs.grad is not None: +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +61: if inputs.grad is not None: +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +38: if inputs.grad is not None: +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +39: if inputs.grad is not None: +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +61: if inputs.grad is not None: +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +38: if inputs.grad is not None: +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +39: if inputs.grad is not None: +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +61: if inputs.grad is not None: +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +38: if inputs.grad is not None: +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +39: if inputs.grad is not None: +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +61: if inputs.grad is not None: +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +61: if inputs.grad is not None: +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +61: if inputs.grad is not None: +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +39: if inputs.grad is not None: +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +53: if inputs.grad is not None: +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +59: if inputs.grad is not None: +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +59: if inputs.grad is not None: +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +59: if inputs.grad is not None: +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +59: if inputs.grad is not None: +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +59: if inputs.grad is not None: +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +59: if inputs.grad is not None: +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +57: if inputs.grad is not None: +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +57: if inputs.grad is not None: +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +57: if inputs.grad is not None: +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +57: if inputs.grad is not None: +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +57: if inputs.grad is not None: +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +57: if inputs.grad is not None: +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +35: if inputs.grad is not None: +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +35: if inputs.grad is not None: +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +35: if inputs.grad is not None: +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +35: if inputs.grad is not None: +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +35: if inputs.grad is not None: +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +58: if inputs.grad is not None: +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +58: if inputs.grad is not None: +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +58: if inputs.grad is not None: +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +58: if inputs.grad is not None: +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +58: if inputs.grad is not None: +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +58: if inputs.grad is not None: +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +63: if inputs.grad is not None: +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +63: if inputs.grad is not None: +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +63: if inputs.grad is not None: +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +63: if inputs.grad is not None: +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +48: if inputs.grad is not None: +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +48: if inputs.grad is not None: +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +53: if inputs.grad is not None: +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +53: if inputs.grad is not None: +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +48: if inputs.grad is not None: +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +37: if inputs.grad is not None: +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +37: if inputs.grad is not None: +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +37: if inputs.grad is not None: +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +37: if inputs.grad is not None: +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +37: if inputs.grad is not None: +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +37: if inputs.grad is not None: +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +46: if inputs.grad is not None: +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +46: if inputs.grad is not None: +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +60: if inputs.grad is not None: +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +60: if inputs.grad is not None: +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +60: if inputs.grad is not None: +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +60: if inputs.grad is not None: +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +60: if inputs.grad is not None: +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +60: if inputs.grad is not None: +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +46: if inputs.grad is not None: +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +56: if inputs.grad is not None: +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +56: if inputs.grad is not None: +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +56: if inputs.grad is not None: +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +56: if inputs.grad is not None: +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +56: if inputs.grad is not None: +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +42: if inputs.grad is not None: +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +42: if inputs.grad is not None: +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +42: if inputs.grad is not None: +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +42: if inputs.grad is not None: +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +42: if inputs.grad is not None: +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +42: if inputs.grad is not None: +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +52: if inputs.grad is not None: +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +52: if inputs.grad is not None: +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +52: if inputs.grad is not None: +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +52: if inputs.grad is not None: +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +52: if inputs.grad is not None: +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +36: if inputs.grad is not None: +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +36: if inputs.grad is not None: +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +36: if inputs.grad is not None: +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +36: if inputs.grad is not None: +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +36: if inputs.grad is not None: +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +36: if inputs.grad is not None: +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +62: if inputs.grad is not None: +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +62: if inputs.grad is not None: +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +62: if inputs.grad is not None: +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +63: if inputs.grad is not None: +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +63: if inputs.grad is not None: +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +53: if inputs.grad is not None: +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +53: if inputs.grad is not None: +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +48: if inputs.grad is not None: +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +53: if inputs.grad is not None: +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +48: if inputs.grad is not None: +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +35: if inputs.grad is not None: +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +56: if inputs.grad is not None: +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +46: if inputs.grad is not None: +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +46: if inputs.grad is not None: +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +46: if inputs.grad is not None: +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +52: if inputs.grad is not None: +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +40: if inputs.grad is not None: +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +40: if inputs.grad is not None: +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +40: if inputs.grad is not None: +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +40: if inputs.grad is not None: +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +40: if inputs.grad is not None: +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +40: if inputs.grad is not None: +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +44: if inputs.grad is not None: +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +44: if inputs.grad is not None: +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +44: if inputs.grad is not None: +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +48: if inputs.grad is not None: +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +35: if inputs.grad is not None: +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +55: if inputs.grad is not None: +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +55: if inputs.grad is not None: +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +55: if inputs.grad is not None: +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +55: if inputs.grad is not None: +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +55: if inputs.grad is not None: +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +62: if inputs.grad is not None: +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +55: if inputs.grad is not None: +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +62: if inputs.grad is not None: +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +63: if inputs.grad is not None: +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +58: if inputs.grad is not None: +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +63: if inputs.grad is not None: +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +41: if inputs.grad is not None: +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +32: if inputs.grad is not None: +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +32: if inputs.grad is not None: +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +32: if inputs.grad is not None: +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +32: if inputs.grad is not None: +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +32: if inputs.grad is not None: +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +32: if inputs.grad is not None: +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +54: if inputs.grad is not None: +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +54: if inputs.grad is not None: +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +54: if inputs.grad is not None: +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +54: if inputs.grad is not None: +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +54: if inputs.grad is not None: +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +61: if inputs.grad is not None: +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +44: if inputs.grad is not None: +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +44: if inputs.grad is not None: +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +44: if inputs.grad is not None: +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +47: if inputs.grad is not None: +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +47: if inputs.grad is not None: +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +47: if inputs.grad is not None: +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +47: if inputs.grad is not None: +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +47: if inputs.grad is not None: +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +47: if inputs.grad is not None: +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +38: if inputs.grad is not None: +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +42: if inputs.grad is not None: +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +49: if inputs.grad is not None: +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +49: if inputs.grad is not None: +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +49: if inputs.grad is not None: +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +49: if inputs.grad is not None: +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +49: if inputs.grad is not None: +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +49: if inputs.grad is not None: +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +41: if inputs.grad is not None: +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +57: if inputs.grad is not None: +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +50: if inputs.grad is not None: +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +50: if inputs.grad is not None: +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +50: if inputs.grad is not None: +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +50: if inputs.grad is not None: +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +50: if inputs.grad is not None: +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +50: if inputs.grad is not None: +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +45: if inputs.grad is not None: +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +45: if inputs.grad is not None: +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +45: if inputs.grad is not None: +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +45: if inputs.grad is not None: +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +45: if inputs.grad is not None: +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +45: if inputs.grad is not None: +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +34: if inputs.grad is not None: +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +34: if inputs.grad is not None: +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +51: if inputs.grad is not None: +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +34: if inputs.grad is not None: +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +51: if inputs.grad is not None: +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +34: if inputs.grad is not None: +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +51: if inputs.grad is not None: +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +34: if inputs.grad is not None: +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +51: if inputs.grad is not None: +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +34: if inputs.grad is not None: +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +51: if inputs.grad is not None: +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +51: if inputs.grad is not None: +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +61: if inputs.grad is not None: +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +54: if inputs.grad is not None: +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +59: if inputs.grad is not None: +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +33: if inputs.grad is not None: +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +33: if inputs.grad is not None: +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +33: if inputs.grad is not None: +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +33: if inputs.grad is not None: +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +33: if inputs.grad is not None: +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +33: if inputs.grad is not None: +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +43: if inputs.grad is not None: +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +43: if inputs.grad is not None: +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +43: if inputs.grad is not None: +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +60: if inputs.grad is not None: +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +56: if inputs.grad is not None: +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +58: if inputs.grad is not None: +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +36: if inputs.grad is not None: +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +35: if inputs.grad is not None: +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +36: if inputs.grad is not None: +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +37: if inputs.grad is not None: +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +42: if inputs.grad is not None: +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +38: if inputs.grad is not None: +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +39: if inputs.grad is not None: +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +39: if inputs.grad is not None: +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +57: if inputs.grad is not None: +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +59: if inputs.grad is not None: +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +44: if inputs.grad is not None: +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +44: if inputs.grad is not None: +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +49: if inputs.grad is not None: +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +55: if inputs.grad is not None: +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +56: if inputs.grad is not None: +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +43: if inputs.grad is not None: +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +60: if inputs.grad is not None: +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +43: if inputs.grad is not None: +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +43: if inputs.grad is not None: +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +47: if inputs.grad is not None: +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +33: if inputs.grad is not None: +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +53: if inputs.grad is not None: +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +53: if inputs.grad is not None: +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +47: if inputs.grad is not None: +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +37: if inputs.grad is not None: +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +54: if inputs.grad is not None: +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +32: if inputs.grad is not None: +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +51: if inputs.grad is not None: +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +55: if inputs.grad is not None: +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +52: if inputs.grad is not None: +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +43: if inputs.grad is not None: +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +43: if inputs.grad is not None: +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +46: if inputs.grad is not None: +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +46: if inputs.grad is not None: +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +32: if inputs.grad is not None: +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +48: if inputs.grad is not None: +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +33: if inputs.grad is not None: +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +54: if inputs.grad is not None: +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +52: if inputs.grad is not None: +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +51: if inputs.grad is not None: +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +50: if inputs.grad is not None: +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +48: if inputs.grad is not None: +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +49: if inputs.grad is not None: +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +50: if inputs.grad is not None: +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +45: if inputs.grad is not None: +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +45: if inputs.grad is not None: +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +34: if inputs.grad is not None: +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +34: if inputs.grad is not None: +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +40: if inputs.grad is not None: +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +40: if inputs.grad is not None: diff --git a/3b977b77b/logs/2096637.out b/3b977b77b/logs/2096637.out new file mode 100644 index 0000000000000000000000000000000000000000..cb2f66a225d1fae50ac2d63dadd30557c12d1762 --- /dev/null +++ b/3b977b77b/logs/2096637.out @@ -0,0 +1,27898 @@ +Model parameters: d_model 2944 ffw_size 11776 kv_size 128 n_heads 23 n_layers 36 +Megatron-DeepSpeed/pretrain_gpt.py --tensor-model-parallel-size 1 --pipeline-model-parallel-size 2 --num-layers 36 --hidden-size 2944 --num-attention-heads 23 --kv-channels 128 --ffn-hidden-size 11776 --seq-length 2048 --max-position-embeddings 2048 --micro-batch-size 1 --global-batch-size 512 --train-samples 37_792_969 --vocab-file gpt2/vocab.json --merge-file gpt2/merges.txt --clip-grad 1.0 --kill-switch-path kill-switch-3b977boscar --bf16 --optimizer adam --adam-beta1 0.9 --adam-beta2 0.999 --adam-eps 1e-8 --lr 2e-4 --min-lr 2e-5 --lr-decay-style cosine --lr-decay-samples 37_792_969 --lr-warmup-samples 377_930 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 10000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_3b977boscar --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_3b977boscar --load checkpoints_3b977boscar --data-path /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2096637.json --zero-stage 0 +START 2096637: Thu Dec 1 11:37:00 EET 2022 + 0: + 0: + 0: ======================= ROCm System Management Interface ======================= + 0: ================================= Concise Info ================================= + 0: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 0: 0 44.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: 2 44.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: 4 39.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: 6 36.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: ================================================================================ + 0: ============================= End of ROCm SMI Log ============================== +19: +19: +19: ======================= ROCm System Management Interface ======================= +19: ================================= Concise Info ================================= +19: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +19: 0 42.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: 2 41.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 3 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: 4 42.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 5 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: 6 39.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: ================================================================================ +19: ============================= End of ROCm SMI Log ============================== +20: +20: +20: ======================= ROCm System Management Interface ======================= +20: ================================= Concise Info ================================= +20: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +20: 0 39.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: 2 43.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 3 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: 4 40.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: 6 45.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: ================================================================================ +20: ============================= End of ROCm SMI Log ============================== +52: +52: +52: ======================= ROCm System Management Interface ======================= +52: ================================= Concise Info ================================= +52: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +52: 0 41.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +52: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +52: 2 39.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +52: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +52: 4 39.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +52: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +52: 6 42.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +52: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +52: ================================================================================ +52: ============================= End of ROCm SMI Log ============================== +61: +61: +61: ======================= ROCm System Management Interface ======================= +61: ================================= Concise Info ================================= +61: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +61: 0 48.0c 98.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +61: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +61: 2 41.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +61: 3 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +61: 4 45.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +61: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +61: 6 43.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +61: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +61: ================================================================================ +61: ============================= End of ROCm SMI Log ============================== +63: +63: +63: ======================= ROCm System Management Interface ======================= +63: ================================= Concise Info ================================= +63: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +63: 0 47.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +63: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +63: 2 45.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +63: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +63: 4 36.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +63: 5 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +63: 6 43.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +63: 7 37.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +63: ================================================================================ +63: ============================= End of ROCm SMI Log ============================== +53: +53: +53: ======================= ROCm System Management Interface ======================= +53: ================================= Concise Info ================================= +53: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +53: 0 44.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +53: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +53: 2 46.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +53: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +53: 4 40.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +53: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +53: 6 43.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +53: 7 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +53: ================================================================================ +53: ============================= End of ROCm SMI Log ============================== +10: +10: +10: ======================= ROCm System Management Interface ======================= +10: ================================= Concise Info ================================= +10: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +10: 0 47.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: 2 36.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 3 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: 4 44.0c 81.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: 6 38.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: ================================================================================ +10: ============================= End of ROCm SMI Log ============================== +62: +62: +62: ======================= ROCm System Management Interface ======================= +62: ================================= Concise Info ================================= +62: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +62: 0 46.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +62: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +62: 2 42.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +62: 3 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +62: 4 41.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +62: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +62: 6 44.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +62: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +62: ================================================================================ +62: ============================= End of ROCm SMI Log ============================== +28: +28: +28: ======================= ROCm System Management Interface ======================= +28: ================================= Concise Info ================================= +28: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +28: 0 40.0c 99.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: 2 40.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 3 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: 4 40.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: 6 39.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: ================================================================================ +28: ============================= End of ROCm SMI Log ============================== +33: +33: +33: ======================= ROCm System Management Interface ======================= +33: ================================= Concise Info ================================= +33: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +33: 0 46.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +33: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +33: 2 42.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +33: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +33: 4 39.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +33: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +33: 6 41.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +33: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +33: ================================================================================ +33: ============================= End of ROCm SMI Log ============================== +22: +22: +22: ======================= ROCm System Management Interface ======================= +22: ================================= Concise Info ================================= +22: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +22: 0 42.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: 2 40.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: 4 39.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: 6 42.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: ================================================================================ +22: ============================= End of ROCm SMI Log ============================== +18: +18: +18: ======================= ROCm System Management Interface ======================= +18: ================================= Concise Info ================================= +18: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +18: 0 48.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: 2 40.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: 4 42.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: 6 34.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: ================================================================================ +18: ============================= End of ROCm SMI Log ============================== +38: +38: +38: ======================= ROCm System Management Interface ======================= +38: ================================= Concise Info ================================= +38: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +38: 0 47.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +38: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +38: 2 38.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +38: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +38: 4 41.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +38: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +38: 6 35.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +38: 7 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +38: ================================================================================ +38: ============================= End of ROCm SMI Log ============================== +59: +59: +59: ======================= ROCm System Management Interface ======================= +59: ================================= Concise Info ================================= +59: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +59: 0 45.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +59: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +59: 2 45.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +59: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +59: 4 40.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +59: 5 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +59: 6 44.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +59: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +59: ================================================================================ +59: ============================= End of ROCm SMI Log ============================== + 5: + 5: + 5: ======================= ROCm System Management Interface ======================= + 5: ================================= Concise Info ================================= + 5: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 5: 0 44.0c 98.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: 2 40.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 3 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: 4 38.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: 6 35.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 7 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: ================================================================================ + 5: ============================= End of ROCm SMI Log ============================== +34: +34: +34: ======================= ROCm System Management Interface ======================= +34: ================================= Concise Info ================================= +34: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +34: 0 46.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +34: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +34: 2 41.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +34: 3 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +34: 4 49.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +34: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +34: 6 38.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +34: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +34: ================================================================================ +34: ============================= End of ROCm SMI Log ============================== +54: +54: +54: ======================= ROCm System Management Interface ======================= +54: ================================= Concise Info ================================= +54: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +54: 0 41.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +54: 1 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +54: 2 39.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +54: 3 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +54: 4 38.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +54: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +54: 6 41.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +54: 7 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +54: ================================================================================ +54: ============================= End of ROCm SMI Log ============================== +44: +44: +44: ======================= ROCm System Management Interface ======================= +44: ================================= Concise Info ================================= +44: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +44: 0 47.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +44: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +44: 2 44.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +44: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +44: 4 39.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +44: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +44: 6 45.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +44: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +44: ================================================================================ +44: ============================= End of ROCm SMI Log ============================== +43: +43: +43: ======================= ROCm System Management Interface ======================= +43: ================================= Concise Info ================================= +43: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +43: 0 42.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +43: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +43: 2 43.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +43: 3 39.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +43: 4 41.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +43: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +43: 6 37.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +43: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +43: ================================================================================ +43: ============================= End of ROCm SMI Log ============================== +56: +56: +56: ======================= ROCm System Management Interface ======================= +56: ================================= Concise Info ================================= +56: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +56: 0 42.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +56: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +56: 2 42.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +56: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +56: 4 43.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +56: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +56: 6 41.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +56: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +56: ================================================================================ +56: ============================= End of ROCm SMI Log ============================== + 7: + 7: + 7: ======================= ROCm System Management Interface ======================= + 7: ================================= Concise Info ================================= + 7: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 7: 0 43.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: 2 44.0c 80.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: 4 44.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: 6 39.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: ================================================================================ + 7: ============================= End of ROCm SMI Log ============================== +58: +58: +58: ======================= ROCm System Management Interface ======================= +58: ================================= Concise Info ================================= +58: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +58: 0 47.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +58: 1 53.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +58: 2 43.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +58: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +58: 4 42.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +58: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +58: 6 42.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +58: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +58: ================================================================================ +58: ============================= End of ROCm SMI Log ============================== +15: +15: +15: ======================= ROCm System Management Interface ======================= +15: ================================= Concise Info ================================= +15: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +15: 0 41.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: 2 42.0c 98.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: 4 46.0c 80.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: 6 36.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: ================================================================================ +15: ============================= End of ROCm SMI Log ============================== + 1: + 1: + 1: ======================= ROCm System Management Interface ======================= + 1: ================================= Concise Info ================================= + 1: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 1: 0 44.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 1: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 1: 2 41.0c 81.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 1: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 1: 4 48.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 1: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 1: 6 38.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 1: 7 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 1: ================================================================================ + 1: ============================= End of ROCm SMI Log ============================== +11: +11: +11: ======================= ROCm System Management Interface ======================= +11: ================================= Concise Info ================================= +11: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +11: 0 44.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: 2 41.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: 4 41.0c 169.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: 6 38.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 7 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: ================================================================================ +11: ============================= End of ROCm SMI Log ============================== +48: +48: +48: ======================= ROCm System Management Interface ======================= +48: ================================= Concise Info ================================= +48: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +48: 0 46.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +48: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +48: 2 42.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +48: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +48: 4 45.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +48: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +48: 6 42.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +48: 7 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +48: ================================================================================ +48: ============================= End of ROCm SMI Log ============================== +26: +26: +26: ======================= ROCm System Management Interface ======================= +26: ================================= Concise Info ================================= +26: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +26: 0 44.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: 2 36.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: 4 39.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: 6 42.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: ================================================================================ +26: ============================= End of ROCm SMI Log ============================== + 2: + 2: + 2: ======================= ROCm System Management Interface ======================= + 2: ================================= Concise Info ================================= + 2: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 2: 0 46.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: 2 43.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: 4 43.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 5 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: 6 46.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: ================================================================================ + 2: ============================= End of ROCm SMI Log ============================== +32: +32: +32: ======================= ROCm System Management Interface ======================= +32: ================================= Concise Info ================================= +32: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +32: 0 45.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +32: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +32: 2 42.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +32: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +32: 4 42.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +32: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +32: 6 39.0c 81.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +32: 7 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +32: ================================================================================ +32: ============================= End of ROCm SMI Log ============================== +51: +51: +51: ======================= ROCm System Management Interface ======================= +51: ================================= Concise Info ================================= +51: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +51: 0 43.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +51: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +51: 2 39.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +51: 3 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +51: 4 45.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +51: 5 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +51: 6 41.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +51: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +51: ================================================================================ +51: ============================= End of ROCm SMI Log ============================== +60: +60: +60: ======================= ROCm System Management Interface ======================= +60: ================================= Concise Info ================================= +60: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +60: 0 42.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +60: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +60: 2 42.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +60: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +60: 4 45.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +60: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +60: 6 43.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +60: 7 53.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +60: ================================================================================ +60: ============================= End of ROCm SMI Log ============================== +36: +36: +36: ======================= ROCm System Management Interface ======================= +36: ================================= Concise Info ================================= +36: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +36: 0 47.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +36: 1 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +36: 2 46.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +36: 3 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +36: 4 39.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +36: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +36: 6 39.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +36: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +36: ================================================================================ +36: ============================= End of ROCm SMI Log ============================== +12: +12: +12: ======================= ROCm System Management Interface ======================= +12: ================================= Concise Info ================================= +12: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +12: 0 49.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: 2 37.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 3 39.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: 4 39.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: 6 43.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 7 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: ================================================================================ +12: ============================= End of ROCm SMI Log ============================== +49: +49: +49: ======================= ROCm System Management Interface ======================= +49: ================================= Concise Info ================================= +49: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +49: 0 42.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +49: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +49: 2 42.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +49: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +49: 4 42.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +49: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +49: 6 40.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +49: 7 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +49: ================================================================================ +49: ============================= End of ROCm SMI Log ============================== +39: +39: +39: ======================= ROCm System Management Interface ======================= +39: ================================= Concise Info ================================= +39: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +39: 0 40.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +39: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +39: 2 38.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +39: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +39: 4 39.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +39: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +39: 6 47.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +39: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +39: ================================================================================ +39: ============================= End of ROCm SMI Log ============================== +55: +55: +55: ======================= ROCm System Management Interface ======================= +55: ================================= Concise Info ================================= +55: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +55: 0 45.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +55: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +55: 2 49.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +55: 3 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +55: 4 41.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +55: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +55: 6 41.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +55: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +55: ================================================================================ +55: ============================= End of ROCm SMI Log ============================== +47: +47: +47: ======================= ROCm System Management Interface ======================= +47: ================================= Concise Info ================================= +47: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +47: 0 44.0c 99.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +47: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +47: 2 44.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +47: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +47: 4 41.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +47: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +47: 6 44.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +47: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +47: ================================================================================ +47: ============================= End of ROCm SMI Log ============================== + 3: + 3: + 3: ======================= ROCm System Management Interface ======================= + 3: ================================= Concise Info ================================= + 3: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 3: 0 43.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: 2 44.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: 4 42.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: 6 38.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: ================================================================================ + 3: ============================= End of ROCm SMI Log ============================== +13: +13: +13: ======================= ROCm System Management Interface ======================= +13: ================================= Concise Info ================================= +13: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +13: 0 48.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 1 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: 2 39.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: 4 43.0c 78.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: 6 38.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: ================================================================================ +13: ============================= End of ROCm SMI Log ============================== +31: +31: +31: ======================= ROCm System Management Interface ======================= +31: ================================= Concise Info ================================= +31: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +31: 0 50.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: 2 41.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 3 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: 4 42.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 5 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: 6 41.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 7 39.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: ================================================================================ +31: ============================= End of ROCm SMI Log ============================== +46: +46: +46: ======================= ROCm System Management Interface ======================= +46: ================================= Concise Info ================================= +46: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +46: 0 43.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +46: 1 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +46: 2 41.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +46: 3 39.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +46: 4 43.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +46: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +46: 6 38.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +46: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +46: ================================================================================ +46: ============================= End of ROCm SMI Log ============================== +30: +30: +30: ======================= ROCm System Management Interface ======================= +30: ================================= Concise Info ================================= +30: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +30: 0 44.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: 2 37.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: 4 46.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: 6 38.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: ================================================================================ +30: ============================= End of ROCm SMI Log ============================== +50: +50: +50: ======================= ROCm System Management Interface ======================= +50: ================================= Concise Info ================================= +50: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +50: 0 48.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +50: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +50: 2 40.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +50: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +50: 4 42.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +50: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +50: 6 34.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +50: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +50: ================================================================================ +50: ============================= End of ROCm SMI Log ============================== +35: +35: +35: ======================= ROCm System Management Interface ======================= +35: ================================= Concise Info ================================= +35: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +35: 0 46.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +35: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +35: 2 45.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +35: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +35: 4 41.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +35: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +35: 6 37.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +35: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +35: ================================================================================ +35: ============================= End of ROCm SMI Log ============================== +42: +42: +42: ======================= ROCm System Management Interface ======================= +42: ================================= Concise Info ================================= +42: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +42: 0 43.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +42: 1 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +42: 2 44.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +42: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +42: 4 41.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +42: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +42: 6 48.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +42: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +42: ================================================================================ +42: ============================= End of ROCm SMI Log ============================== +25: +25: +25: ======================= ROCm System Management Interface ======================= +25: ================================= Concise Info ================================= +25: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +25: 0 44.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: 2 39.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: 4 40.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: 6 38.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: ================================================================================ +25: ============================= End of ROCm SMI Log ============================== + 6: + 6: + 6: ======================= ROCm System Management Interface ======================= + 6: ================================= Concise Info ================================= + 6: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 6: 0 45.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: 2 41.0c 98.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: 4 43.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: 6 44.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: ================================================================================ + 6: ============================= End of ROCm SMI Log ============================== +21: +21: +21: ======================= ROCm System Management Interface ======================= +21: ================================= Concise Info ================================= +21: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +21: 0 46.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: 2 42.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: 4 43.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: 6 43.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: ================================================================================ +21: ============================= End of ROCm SMI Log ============================== + 9: + 9: + 9: ======================= ROCm System Management Interface ======================= + 9: ================================= Concise Info ================================= + 9: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 9: 0 46.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: 2 42.0c 82.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: 4 42.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: 6 43.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: ================================================================================ + 9: ============================= End of ROCm SMI Log ============================== +37: +37: +37: ======================= ROCm System Management Interface ======================= +37: ================================= Concise Info ================================= +37: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +37: 0 42.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +37: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +37: 2 40.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +37: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +37: 4 36.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +37: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +37: 6 38.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +37: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +37: ================================================================================ +37: ============================= End of ROCm SMI Log ============================== +16: +16: +16: ======================= ROCm System Management Interface ======================= +16: ================================= Concise Info ================================= +16: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +16: 0 46.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: 2 41.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: 4 38.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: 6 42.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: ================================================================================ +16: ============================= End of ROCm SMI Log ============================== +14: +14: +14: ======================= ROCm System Management Interface ======================= +14: ================================= Concise Info ================================= +14: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +14: 0 45.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: 2 42.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 3 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: 4 43.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 5 55.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: 6 41.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: ================================================================================ +14: ============================= End of ROCm SMI Log ============================== +45: +45: +45: ======================= ROCm System Management Interface ======================= +45: ================================= Concise Info ================================= +45: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +45: 0 43.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +45: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +45: 2 43.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +45: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +45: 4 43.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +45: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +45: 6 37.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +45: 7 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +45: ================================================================================ +45: ============================= End of ROCm SMI Log ============================== +23: +23: +23: ======================= ROCm System Management Interface ======================= +23: ================================= Concise Info ================================= +23: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +23: 0 49.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: 2 41.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: 4 41.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: 6 40.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: ================================================================================ +23: ============================= End of ROCm SMI Log ============================== +40: +40: +40: ======================= ROCm System Management Interface ======================= +40: ================================= Concise Info ================================= +40: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +40: 0 45.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +40: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +40: 2 43.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +40: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +40: 4 46.0c 82.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +40: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +40: 6 40.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +40: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +40: ================================================================================ +40: ============================= End of ROCm SMI Log ============================== +41: +41: +41: ======================= ROCm System Management Interface ======================= +41: ================================= Concise Info ================================= +41: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +41: 0 43.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +41: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +41: 2 47.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +41: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +41: 4 40.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +41: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +41: 6 40.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +41: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +41: ================================================================================ +41: ============================= End of ROCm SMI Log ============================== +57: +57: +57: ======================= ROCm System Management Interface ======================= +57: ================================= Concise Info ================================= +57: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +57: 0 44.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +57: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +57: 2 43.0c 82.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +57: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +57: 4 41.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +57: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +57: 6 38.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +57: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +57: ================================================================================ +57: ============================= End of ROCm SMI Log ============================== + 4: + 4: + 4: ======================= ROCm System Management Interface ======================= + 4: ================================= Concise Info ================================= + 4: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 4: 0 43.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: 2 44.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: 4 40.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: 6 41.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: ================================================================================ + 4: ============================= End of ROCm SMI Log ============================== + 8: + 8: + 8: ======================= ROCm System Management Interface ======================= + 8: ================================= Concise Info ================================= + 8: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 8: 0 48.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: 2 42.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: 4 42.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 5 39.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: 6 38.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: ================================================================================ + 8: ============================= End of ROCm SMI Log ============================== +27: +27: +27: ======================= ROCm System Management Interface ======================= +27: ================================= Concise Info ================================= +27: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +27: 0 45.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: 2 44.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: 4 41.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: 6 37.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: ================================================================================ +27: ============================= End of ROCm SMI Log ============================== +29: +29: +29: ======================= ROCm System Management Interface ======================= +29: ================================= Concise Info ================================= +29: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +29: 0 43.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: 2 44.0c 80.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: 4 40.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: 6 36.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: ================================================================================ +29: ============================= End of ROCm SMI Log ============================== +24: +24: +24: ======================= ROCm System Management Interface ======================= +24: ================================= Concise Info ================================= +24: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +24: 0 41.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: 2 39.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: 4 38.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 5 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: 6 38.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 7 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: ================================================================================ +24: ============================= End of ROCm SMI Log ============================== +17: +17: +17: ======================= ROCm System Management Interface ======================= +17: ================================= Concise Info ================================= +17: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +17: 0 43.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: 2 38.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 3 38.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: 4 43.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: 6 36.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: ================================================================================ +17: ============================= End of ROCm SMI Log ============================== + 0: Launching on nid005196 (0/64), master nid005196 port 9999, GPUs 8, CUDA: True +15: Launching on nid005910 (15/64), master nid005196 port 9999, GPUs 8, CUDA: True +20: Launching on nid006162 (20/64), master nid005196 port 9999, GPUs 8, CUDA: True +12: Launching on nid005907 (12/64), master nid005196 port 9999, GPUs 8, CUDA: True +11: Launching on nid005906 (11/64), master nid005196 port 9999, GPUs 8, CUDA: True +38: Launching on nid006752 (38/64), master nid005196 port 9999, GPUs 8, CUDA: True +27: Launching on nid006169 (27/64), master nid005196 port 9999, GPUs 8, CUDA: True + 1: Launching on nid005197 (1/64), master nid005196 port 9999, GPUs 8, CUDA: True +52: Launching on nid007154 (52/64), master nid005196 port 9999, GPUs 8, CUDA: True +61: Launching on nid007232 (61/64), master nid005196 port 9999, GPUs 8, CUDA: True +39: Launching on nid006753 (39/64), master nid005196 port 9999, GPUs 8, CUDA: True +60: Launching on nid007231 (60/64), master nid005196 port 9999, GPUs 8, CUDA: True +57: Launching on nid007228 (57/64), master nid005196 port 9999, GPUs 8, CUDA: True +17: Launching on nid005912 (17/64), master nid005196 port 9999, GPUs 8, CUDA: True +56: Launching on nid007227 (56/64), master nid005196 port 9999, GPUs 8, CUDA: True +46: Launching on nid007148 (46/64), master nid005196 port 9999, GPUs 8, CUDA: True +30: Launching on nid006744 (30/64), master nid005196 port 9999, GPUs 8, CUDA: True +58: Launching on nid007229 (58/64), master nid005196 port 9999, GPUs 8, CUDA: True +41: Launching on nid007143 (41/64), master nid005196 port 9999, GPUs 8, CUDA: True +62: Launching on nid007233 (62/64), master nid005196 port 9999, GPUs 8, CUDA: True +51: Launching on nid007153 (51/64), master nid005196 port 9999, GPUs 8, CUDA: True + 2: Launching on nid005198 (2/64), master nid005196 port 9999, GPUs 8, CUDA: True +48: Launching on nid007150 (48/64), master nid005196 port 9999, GPUs 8, CUDA: True +43: Launching on nid007145 (43/64), master nid005196 port 9999, GPUs 8, CUDA: True +59: Launching on nid007230 (59/64), master nid005196 port 9999, GPUs 8, CUDA: True +14: Launching on nid005909 (14/64), master nid005196 port 9999, GPUs 8, CUDA: True +32: Launching on nid006746 (32/64), master nid005196 port 9999, GPUs 8, CUDA: True +23: Launching on nid006165 (23/64), master nid005196 port 9999, GPUs 8, CUDA: True +10: Launching on nid005905 (10/64), master nid005196 port 9999, GPUs 8, CUDA: True +35: Launching on nid006749 (35/64), master nid005196 port 9999, GPUs 8, CUDA: True +33: Launching on nid006747 (33/64), master nid005196 port 9999, GPUs 8, CUDA: True +18: Launching on nid005913 (18/64), master nid005196 port 9999, GPUs 8, CUDA: True +34: Launching on nid006748 (34/64), master nid005196 port 9999, GPUs 8, CUDA: True + 5: Launching on nid005201 (5/64), master nid005196 port 9999, GPUs 8, CUDA: True +24: Launching on nid006166 (24/64), master nid005196 port 9999, GPUs 8, CUDA: True +16: Launching on nid005911 (16/64), master nid005196 port 9999, GPUs 8, CUDA: True + 9: Launching on nid005904 (9/64), master nid005196 port 9999, GPUs 8, CUDA: True +45: Launching on nid007147 (45/64), master nid005196 port 9999, GPUs 8, CUDA: True + 6: Launching on nid005202 (6/64), master nid005196 port 9999, GPUs 8, CUDA: True +31: Launching on nid006745 (31/64), master nid005196 port 9999, GPUs 8, CUDA: True +44: Launching on nid007146 (44/64), master nid005196 port 9999, GPUs 8, CUDA: True +63: Launching on nid007234 (63/64), master nid005196 port 9999, GPUs 8, CUDA: True +19: Launching on nid006161 (19/64), master nid005196 port 9999, GPUs 8, CUDA: True +28: Launching on nid006170 (28/64), master nid005196 port 9999, GPUs 8, CUDA: True +40: Launching on nid007142 (40/64), master nid005196 port 9999, GPUs 8, CUDA: True +49: Launching on nid007151 (49/64), master nid005196 port 9999, GPUs 8, CUDA: True +25: Launching on nid006167 (25/64), master nid005196 port 9999, GPUs 8, CUDA: True +50: Launching on nid007152 (50/64), master nid005196 port 9999, GPUs 8, CUDA: True + 8: Launching on nid005903 (8/64), master nid005196 port 9999, GPUs 8, CUDA: True + 3: Launching on nid005199 (3/64), master nid005196 port 9999, GPUs 8, CUDA: True +42: Launching on nid007144 (42/64), master nid005196 port 9999, GPUs 8, CUDA: True +36: Launching on nid006750 (36/64), master nid005196 port 9999, GPUs 8, CUDA: True +21: Launching on nid006163 (21/64), master nid005196 port 9999, GPUs 8, CUDA: True +26: Launching on nid006168 (26/64), master nid005196 port 9999, GPUs 8, CUDA: True + 7: Launching on nid005344 (7/64), master nid005196 port 9999, GPUs 8, CUDA: True +53: Launching on nid007224 (53/64), master nid005196 port 9999, GPUs 8, CUDA: True +22: Launching on nid006164 (22/64), master nid005196 port 9999, GPUs 8, CUDA: True +55: Launching on nid007226 (55/64), master nid005196 port 9999, GPUs 8, CUDA: True +37: Launching on nid006751 (37/64), master nid005196 port 9999, GPUs 8, CUDA: True +47: Launching on nid007149 (47/64), master nid005196 port 9999, GPUs 8, CUDA: True +54: Launching on nid007225 (54/64), master nid005196 port 9999, GPUs 8, CUDA: True +13: Launching on nid005908 (13/64), master nid005196 port 9999, GPUs 8, CUDA: True +29: Launching on nid006171 (29/64), master nid005196 port 9999, GPUs 8, CUDA: True + 4: Launching on nid005200 (4/64), master nid005196 port 9999, GPUs 8, CUDA: True + 0: using world size: 512, data-parallel-size: 256, tensor-model-parallel size: 1, pipeline-model-parallel size: 2 + 0: accumulate and all-reduce gradients in fp32 for bfloat16 data type. + 0: using torch.bfloat16 for parameters ... + 0: ------------------------ arguments ------------------------ + 0: abort_on_unmet_fused_kernel_constraints ......... False + 0: accumulate_allreduce_grads_in_fp32 .............. True + 0: adam_beta1 ...................................... 0.9 + 0: adam_beta2 ...................................... 0.999 + 0: adam_eps ........................................ 1e-08 + 0: adlr_autoresume ................................. False + 0: adlr_autoresume_interval ........................ 1000 + 0: apply_query_key_layer_scaling ................... True + 0: apply_residual_connection_post_layernorm ........ False + 0: attention_dropout ............................... 0.1 + 0: attention_softmax_in_fp32 ....................... False + 0: bert_binary_head ................................ True + 0: bert_load ....................................... None + 0: bf16 ............................................ True + 0: bias_dropout_fusion ............................. True + 0: bias_gelu_fusion ................................ True + 0: biencoder_projection_dim ........................ 0 + 0: biencoder_shared_query_context_model ............ False + 0: block_data_path ................................. None + 0: checkpoint_activations .......................... False + 0: checkpoint_in_cpu ............................... False + 0: checkpoint_num_layers ........................... 1 + 0: clip_grad ....................................... 1.0 + 0: codecarbon_dir .................................. None + 0: consumed_train_samples .......................... 0 + 0: consumed_train_tokens ........................... 0 + 0: consumed_valid_samples .......................... 0 + 0: contigious_checkpointing ........................ False + 0: cpu_optimizer ................................... False + 0: cpu_torch_adam .................................. False + 0: curriculum_learning ............................. False + 0: data_impl ....................................... mmap + 0: data_parallel_size .............................. 256 + 0: data_path ....................................... ['/scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document'] + 0: dataloader_type ................................. single + 0: DDP_impl ........................................ local + 0: decoder_seq_length .............................. None + 0: deepscale ....................................... False + 0: deepscale_config ................................ None + 0: deepspeed ....................................... True + 0: deepspeed_activation_checkpointing .............. False + 0: deepspeed_config ................................ ds_configs/2096637.json + 0: deepspeed_mpi ................................... False + 0: distribute_checkpointed_activations ............. False + 0: distributed_backend ............................. nccl + 0: embed_layernorm ................................. False + 0: embedding_path .................................. None + 0: encoder_seq_length .............................. 2048 + 0: eod_mask_loss ................................... False + 0: eval_interval ................................... 1000 + 0: eval_iters ...................................... 1 + 0: eval_only ....................................... None + 0: evidence_data_path .............................. None + 0: exit_duration_in_mins ........................... None + 0: exit_interval ................................... None + 0: ffn_hidden_size ................................. 11776 + 0: finetune ........................................ False + 0: fp16 ............................................ False + 0: fp16_lm_cross_entropy ........................... False + 0: fp32_residual_connection ........................ False + 0: gigaflos_no_embeds .............................. 0 + 0: global_batch_size ............................... 512 + 0: glu_activation .................................. None + 0: hidden_dropout .................................. 0.1 + 0: hidden_size ..................................... 2944 + 0: hysteresis ...................................... 2 + 0: ict_head_size ................................... None + 0: ict_load ........................................ None + 0: img_dim ......................................... 224 + 0: indexer_batch_size .............................. 128 + 0: indexer_log_interval ............................ 1000 + 0: inference ....................................... False + 0: init_method_std ................................. 0.02 + 0: init_method_xavier_uniform ...................... False + 0: initial_loss_scale .............................. 4294967296 + 0: kill_switch_path ................................ kill-switch-3b977boscar + 0: kv_channels ..................................... 128 + 0: layer_norm_fusion ............................... True + 0: layernorm_epsilon ............................... 1e-05 + 0: lazy_mpu_init ................................... None + 0: load ............................................ checkpoints_3b977boscar + 0: local_rank ...................................... None + 0: log_batch_size_to_tensorboard ................... True + 0: log_interval .................................... 10 + 0: log_learning_rate_to_tensorboard ................ True + 0: log_level ....................................... None + 0: log_level_replica ............................... None + 0: log_loss_scale_to_tensorboard ................... True + 0: log_num_zeros_in_grad ........................... False + 0: log_params_norm ................................. False + 0: log_path ........................................ None + 0: log_timers_to_tensorboard ....................... True + 0: log_validation_ppl_to_tensorboard ............... True + 0: loss_on_targets_only ............................ False + 0: loss_scale ...................................... None + 0: loss_scale_window ............................... 1000 + 0: lr .............................................. 0.0002 + 0: lr_decay_iters .................................. None + 0: lr_decay_samples ................................ 37792969 + 0: lr_decay_style .................................. cosine + 0: lr_decay_tokens ................................. None + 0: lr_warmup_fraction .............................. None + 0: lr_warmup_iters ................................. 0 + 0: lr_warmup_samples ............................... 377930 + 0: make_vocab_size_divisible_by .................... 128 + 0: mask_prob ....................................... 0.15 + 0: masked_softmax_fusion ........................... True + 0: max_position_embeddings ......................... 2048 + 0: mean_noise_span_length .......................... None + 0: memory_centric_tiled_linear ..................... False + 0: merge_file ...................................... gpt2/merges.txt + 0: micro_batch_size ................................ 1 + 0: min_loss_scale .................................. 1.0 + 0: min_lr .......................................... 2e-05 + 0: mmap_warmup ..................................... False + 0: no_load_optim ................................... None + 0: no_load_rng ..................................... None + 0: no_save_optim ................................... None + 0: no_save_rng ..................................... None + 0: noise_density ................................... None + 0: num_attention_heads ............................. 23 + 0: num_channels .................................... 3 + 0: num_classes ..................................... 1000 + 0: num_layers ...................................... 36 + 0: num_layers_per_virtual_pipeline_stage ........... None + 0: num_workers ..................................... 2 + 0: onnx_safe ....................................... None + 0: openai_gelu ..................................... False + 0: optimizer ....................................... adam + 0: optimizer_fusion ................................ True + 0: override_lr_scheduler ........................... False + 0: pad_vocab_size_to ............................... None + 0: params_dtype .................................... torch.bfloat16 + 0: partition_activations ........................... False + 0: patch_dim ....................................... 16 + 0: pipeline_model_parallel_size .................... 2 + 0: position_embedding_type ......................... PositionEmbeddingType.absolute + 0: pp_partition_method ............................. None + 0: profile_backward ................................ False + 0: query_in_block_prob ............................. 0.1 + 0: rampup_batch_size ............................... None + 0: rank ............................................ 0 + 0: remote_device ................................... none + 0: reset_attention_mask ............................ False + 0: reset_position_ids .............................. False + 0: retriever_report_topk_accuracies ................ [] + 0: retriever_score_scaling ......................... False + 0: retriever_seq_length ............................ 256 + 0: reweight_loss_based_on_position_frequency ....... False + 0: sample_rate ..................................... 1.0 + 0: save ............................................ checkpoints_3b977boscar + 0: save_interval ................................... 10000 + 0: scatter_gather_tensors_in_pipeline .............. True + 0: scattered_embeddings ............................ False + 0: seed ............................................ 1234 + 0: seq_length ...................................... 2048 + 0: sgd_momentum .................................... 0.9 + 0: short_seq_prob .................................. 0.1 + 0: skip_train_iteration_range ...................... None + 0: split ........................................... 949,50,1 + 0: split_transformers .............................. False + 0: sync_tp_duplicated_parameters ................... False + 0: synchronize_each_layer .......................... False + 0: tensor_model_parallel_size ...................... 1 + 0: tensorboard_dir ................................. tensorboard_3b977boscar + 0: tensorboard_log_interval ........................ 1 + 0: tensorboard_queue_size .......................... 5 + 0: test_weighted_split_names ....................... None + 0: test_weighted_split_paths ....................... None + 0: test_weighted_split_paths_path .................. None + 0: test_weighted_split_splits ...................... None + 0: test_weighted_split_weights ..................... None + 0: tile_factor ..................................... 1 + 0: titles_data_path ................................ None + 0: tokenizer_name_or_path .......................... None + 0: tokenizer_type .................................. GPT2BPETokenizer + 0: train_iters ..................................... None + 0: train_samples ................................... 37792969 + 0: train_tokens .................................... None + 0: train_weighted_split_paths ...................... None + 0: train_weighted_split_paths_path ................. None + 0: universal_checkpoint ............................ False + 0: use_bnb_optimizer ............................... False + 0: use_checkpoint_lr_scheduler ..................... False + 0: use_contiguous_buffers_in_ddp ................... True + 0: use_cpu_initialization .......................... None + 0: use_one_sent_docs ............................... False + 0: use_pin_memory .................................. False + 0: valid_num_workers ............................... 2 + 0: valid_weighted_split_names ...................... None + 0: valid_weighted_split_paths ...................... None + 0: valid_weighted_split_paths_path ................. None + 0: valid_weighted_split_splits ..................... None + 0: valid_weighted_split_weights .................... None + 0: virtual_pipeline_model_parallel_size ............ None + 0: vocab_extra_ids ................................. 0 + 0: vocab_file ...................................... gpt2/vocab.json + 0: weight_decay .................................... 0.1 + 0: world_size ...................................... 512 + 0: zero_allgather_bucket_size ...................... 0.0 + 0: zero_contigious_gradients ....................... False + 0: zero_reduce_bucket_size ......................... 0.0 + 0: zero_reduce_scatter ............................. False + 0: zero_stage ...................................... 0 + 0: -------------------- end of arguments --------------------- + 0: setting number of micro-batches to constant 2 + 0: > building GPT2BPETokenizer tokenizer ... + 0: > padded vocab (size: 50257) with 47 dummy tokens (new size: 50304) + 0: DeepSpeed general environment info: + 0: torch install path ............... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch'] + 0: torch version .................... 1.13.0+rocm5.2 + 0: torch cuda version ............... None + 0: torch hip version ................ 5.2.21151-afdc89f8 + 0: nvcc version ..................... None + 0: deepspeed install path ........... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed'] + 0: deepspeed info ................... 0.7.5, unknown, unknown + 0: deepspeed wheel compiled w. ...... torch 1.13, hip 5.1 + 0: **** Git info for Megatron: git_hash=unknown git_branch=unknown **** + 0: > initializing torch distributed ... + 0: [2022-12-01 11:38:33,635] [INFO] [comm.py:633:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +63: > setting tensorboard ... + 0: > initializing tensor model parallel with size 1 + 0: > initializing pipeline model parallel with size 2 + 0: > setting random seeds to 1234 ... + 0: > initializing model parallel cuda seeds on global rank 0, model parallel rank 0, and data parallel rank 0 with model parallel seed: 3952 and data parallel seed: 1234 + 0: > compiling dataset index builder ... + 0: make: Entering directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' + 0: make: Nothing to be done for 'default'. + 0: make: Leaving directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' + 0: >>> done with dataset index builder. Compilation time: 0.086 seconds + 0: WARNING: constraints for invoking optimized fused softmax kernel are not met. We default back to unfused kernel invocations. + 0: > compiling and loading fused kernels ... + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.cpp [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.hip [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] + 0: Total number of unsupported CUDA function calls: 0 + 0: + 0: + 0: Total number of replaced kernel launches: 87 + 0: [1/1] c++ scaled_upper_triang_masked_softmax_hip.o scaled_upper_triang_masked_softmax_hip.cuda.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib -lamdhip64 -o scaled_upper_triang_masked_softmax_cuda.so + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.cpp [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.hip [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] + 0: Total number of unsupported CUDA function calls: 0 + 0: + 0: + 0: Total number of replaced kernel launches: 63 + 0: ninja: no work to do. + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda_kernel.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_hip_kernel.hip [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] + 0: Total number of unsupported CUDA function calls: 0 + 0: + 0: + 0: Total number of replaced kernel launches: 67 + 0: [1/1] c++ layer_norm_cuda.o layer_norm_hip_kernel.cuda.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib -lamdhip64 -o fused_mix_prec_layer_norm_cuda.so + 0: >>> done with compiling and loading fused kernels. Compilation time: 29.160 seconds + 0: time to initialize megatron (seconds): 82.205 + 0: [after megatron is initialized] datetime: 2022-12-01 11:39:30 + 0: building GPT model ... + 0: [2022-12-01 11:39:30,267] [INFO] [utils.py:827:see_memory_usage] Before Building Model + 0: [2022-12-01 11:39:30,267] [INFO] [utils.py:828:see_memory_usage] MA 0.0 GB Max_MA 0.0 GB CA 0.0 GB Max_CA 0 GB + 0: [2022-12-01 11:39:30,268] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 43.95 GB, percent = 8.7% + 0: SEED_LAYERS=False BASE_SEED=1234 SEED_FN=None + 0: Using topology: {ProcessCoord(pipe=0, data=0, model=0): 0, ProcessCoord(pipe=0, data=1, model=0): 1, ProcessCoord(pipe=0, data=2, model=0): 2, ProcessCoord(pipe=0, data=3, model=0): 3, ProcessCoord(pipe=0, data=4, model=0): 4, ProcessCoord(pipe=0, data=5, model=0): 5, ProcessCoord(pipe=0, data=6, model=0): 6, ProcessCoord(pipe=0, data=7, model=0): 7, ProcessCoord(pipe=0, data=8, model=0): 8, ProcessCoord(pipe=0, data=9, model=0): 9, ProcessCoord(pipe=0, data=10, model=0): 10, ProcessCoord(pipe=0, data=11, model=0): 11, ProcessCoord(pipe=0, data=12, model=0): 12, ProcessCoord(pipe=0, data=13, model=0): 13, ProcessCoord(pipe=0, data=14, model=0): 14, ProcessCoord(pipe=0, data=15, model=0): 15, ProcessCoord(pipe=0, data=16, model=0): 16, ProcessCoord(pipe=0, data=17, model=0): 17, ProcessCoord(pipe=0, data=18, model=0): 18, ProcessCoord(pipe=0, data=19, model=0): 19, ProcessCoord(pipe=0, data=20, model=0): 20, ProcessCoord(pipe=0, data=21, model=0): 21, ProcessCoord(pipe=0, data=22, model=0): 22, ProcessCoord(pi + 0: pe=0, data=23, model=0): 23, ProcessCoord(pipe=0, data=24, model=0): 24, ProcessCoord(pipe=0, data=25, model=0): 25, ProcessCoord(pipe=0, data=26, model=0): 26, ProcessCoord(pipe=0, data=27, model=0): 27, ProcessCoord(pipe=0, data=28, model=0): 28, ProcessCoord(pipe=0, data=29, model=0): 29, ProcessCoord(pipe=0, data=30, model=0): 30, ProcessCoord(pipe=0, data=31, model=0): 31, ProcessCoord(pipe=0, data=32, model=0): 32, ProcessCoord(pipe=0, data=33, model=0): 33, ProcessCoord(pipe=0, data=34, model=0): 34, ProcessCoord(pipe=0, data=35, model=0): 35, ProcessCoord(pipe=0, data=36, model=0): 36, ProcessCoord(pipe=0, data=37, model=0): 37, ProcessCoord(pipe=0, data=38, model=0): 38, ProcessCoord(pipe=0, data=39, model=0): 39, ProcessCoord(pipe=0, data=40, model=0): 40, ProcessCoord(pipe=0, data=41, model=0): 41, ProcessCoord(pipe=0, data=42, model=0): 42, ProcessCoord(pipe=0, data=43, model=0): 43, ProcessCoord(pipe=0, data=44, model=0): 44, ProcessCoord(pipe=0, data=45, model=0): 45, ProcessCoord(pipe=0, data=4 + 0: 6, model=0): 46, ProcessCoord(pipe=0, data=47, model=0): 47, ProcessCoord(pipe=0, data=48, model=0): 48, ProcessCoord(pipe=0, data=49, model=0): 49, ProcessCoord(pipe=0, data=50, model=0): 50, ProcessCoord(pipe=0, data=51, model=0): 51, ProcessCoord(pipe=0, data=52, model=0): 52, ProcessCoord(pipe=0, data=53, model=0): 53, ProcessCoord(pipe=0, data=54, model=0): 54, ProcessCoord(pipe=0, data=55, model=0): 55, ProcessCoord(pipe=0, data=56, model=0): 56, ProcessCoord(pipe=0, data=57, model=0): 57, ProcessCoord(pipe=0, data=58, model=0): 58, ProcessCoord(pipe=0, data=59, model=0): 59, ProcessCoord(pipe=0, data=60, model=0): 60, ProcessCoord(pipe=0, data=61, model=0): 61, ProcessCoord(pipe=0, data=62, model=0): 62, ProcessCoord(pipe=0, data=63, model=0): 63, ProcessCoord(pipe=0, data=64, model=0): 64, ProcessCoord(pipe=0, data=65, model=0): 65, ProcessCoord(pipe=0, data=66, model=0): 66, ProcessCoord(pipe=0, data=67, model=0): 67, ProcessCoord(pipe=0, data=68, model=0): 68, ProcessCoord(pipe=0, data=69, model=0): + 0: 69, ProcessCoord(pipe=0, data=70, model=0): 70, ProcessCoord(pipe=0, data=71, model=0): 71, ProcessCoord(pipe=0, data=72, model=0): 72, ProcessCoord(pipe=0, data=73, model=0): 73, ProcessCoord(pipe=0, data=74, model=0): 74, ProcessCoord(pipe=0, data=75, model=0): 75, ProcessCoord(pipe=0, data=76, model=0): 76, ProcessCoord(pipe=0, data=77, model=0): 77, ProcessCoord(pipe=0, data=78, model=0): 78, ProcessCoord(pipe=0, data=79, model=0): 79, ProcessCoord(pipe=0, data=80, model=0): 80, ProcessCoord(pipe=0, data=81, model=0): 81, ProcessCoord(pipe=0, data=82, model=0): 82, ProcessCoord(pipe=0, data=83, model=0): 83, ProcessCoord(pipe=0, data=84, model=0): 84, ProcessCoord(pipe=0, data=85, model=0): 85, ProcessCoord(pipe=0, data=86, model=0): 86, ProcessCoord(pipe=0, data=87, model=0): 87, ProcessCoord(pipe=0, data=88, model=0): 88, ProcessCoord(pipe=0, data=89, model=0): 89, ProcessCoord(pipe=0, data=90, model=0): 90, ProcessCoord(pipe=0, data=91, model=0): 91, ProcessCoord(pipe=0, data=92, model=0): 92, Process + 0: Coord(pipe=0, data=93, model=0): 93, ProcessCoord(pipe=0, data=94, model=0): 94, ProcessCoord(pipe=0, data=95, model=0): 95, ProcessCoord(pipe=0, data=96, model=0): 96, ProcessCoord(pipe=0, data=97, model=0): 97, ProcessCoord(pipe=0, data=98, model=0): 98, ProcessCoord(pipe=0, data=99, model=0): 99, ProcessCoord(pipe=0, data=100, model=0): 100, ProcessCoord(pipe=0, data=101, model=0): 101, ProcessCoord(pipe=0, data=102, model=0): 102, ProcessCoord(pipe=0, data=103, model=0): 103, ProcessCoord(pipe=0, data=104, model=0): 104, ProcessCoord(pipe=0, data=105, model=0): 105, ProcessCoord(pipe=0, data=106, model=0): 106, ProcessCoord(pipe=0, data=107, model=0): 107, ProcessCoord(pipe=0, data=108, model=0): 108, ProcessCoord(pipe=0, data=109, model=0): 109, ProcessCoord(pipe=0, data=110, model=0): 110, ProcessCoord(pipe=0, data=111, model=0): 111, ProcessCoord(pipe=0, data=112, model=0): 112, ProcessCoord(pipe=0, data=113, model=0): 113, ProcessCoord(pipe=0, data=114, model=0): 114, ProcessCoord(pipe=0, data=115, mo + 0: del=0): 115, ProcessCoord(pipe=0, data=116, model=0): 116, ProcessCoord(pipe=0, data=117, model=0): 117, ProcessCoord(pipe=0, data=118, model=0): 118, ProcessCoord(pipe=0, data=119, model=0): 119, ProcessCoord(pipe=0, data=120, model=0): 120, ProcessCoord(pipe=0, data=121, model=0): 121, ProcessCoord(pipe=0, data=122, model=0): 122, ProcessCoord(pipe=0, data=123, model=0): 123, ProcessCoord(pipe=0, data=124, model=0): 124, ProcessCoord(pipe=0, data=125, model=0): 125, ProcessCoord(pipe=0, data=126, model=0): 126, ProcessCoord(pipe=0, data=127, model=0): 127, ProcessCoord(pipe=0, data=128, model=0): 128, ProcessCoord(pipe=0, data=129, model=0): 129, ProcessCoord(pipe=0, data=130, model=0): 130, ProcessCoord(pipe=0, data=131, model=0): 131, ProcessCoord(pipe=0, data=132, model=0): 132, ProcessCoord(pipe=0, data=133, model=0): 133, ProcessCoord(pipe=0, data=134, model=0): 134, ProcessCoord(pipe=0, data=135, model=0): 135, ProcessCoord(pipe=0, data=136, model=0): 136, ProcessCoord(pipe=0, data=137, model=0): 137, + 0: ProcessCoord(pipe=0, data=138, model=0): 138, ProcessCoord(pipe=0, data=139, model=0): 139, ProcessCoord(pipe=0, data=140, model=0): 140, ProcessCoord(pipe=0, data=141, model=0): 141, ProcessCoord(pipe=0, data=142, model=0): 142, ProcessCoord(pipe=0, data=143, model=0): 143, ProcessCoord(pipe=0, data=144, model=0): 144, ProcessCoord(pipe=0, data=145, model=0): 145, ProcessCoord(pipe=0, data=146, model=0): 146, ProcessCoord(pipe=0, data=147, model=0): 147, ProcessCoord(pipe=0, data=148, model=0): 148, ProcessCoord(pipe=0, data=149, model=0): 149, ProcessCoord(pipe=0, data=150, model=0): 150, ProcessCoord(pipe=0, data=151, model=0): 151, ProcessCoord(pipe=0, data=152, model=0): 152, ProcessCoord(pipe=0, data=153, model=0): 153, ProcessCoord(pipe=0, data=154, model=0): 154, ProcessCoord(pipe=0, data=155, model=0): 155, ProcessCoord(pipe=0, data=156, model=0): 156, ProcessCoord(pipe=0, data=157, model=0): 157, ProcessCoord(pipe=0, data=158, model=0): 158, ProcessCoord(pipe=0, data=159, model=0): 159, ProcessCoor + 0: d(pipe=0, data=160, model=0): 160, ProcessCoord(pipe=0, data=161, model=0): 161, ProcessCoord(pipe=0, data=162, model=0): 162, ProcessCoord(pipe=0, data=163, model=0): 163, ProcessCoord(pipe=0, data=164, model=0): 164, ProcessCoord(pipe=0, data=165, model=0): 165, ProcessCoord(pipe=0, data=166, model=0): 166, ProcessCoord(pipe=0, data=167, model=0): 167, ProcessCoord(pipe=0, data=168, model=0): 168, ProcessCoord(pipe=0, data=169, model=0): 169, ProcessCoord(pipe=0, data=170, model=0): 170, ProcessCoord(pipe=0, data=171, model=0): 171, ProcessCoord(pipe=0, data=172, model=0): 172, ProcessCoord(pipe=0, data=173, model=0): 173, ProcessCoord(pipe=0, data=174, model=0): 174, ProcessCoord(pipe=0, data=175, model=0): 175, ProcessCoord(pipe=0, data=176, model=0): 176, ProcessCoord(pipe=0, data=177, model=0): 177, ProcessCoord(pipe=0, data=178, model=0): 178, ProcessCoord(pipe=0, data=179, model=0): 179, ProcessCoord(pipe=0, data=180, model=0): 180, ProcessCoord(pipe=0, data=181, model=0): 181, ProcessCoord(pipe=0, da + 0: ta=182, model=0): 182, ProcessCoord(pipe=0, data=183, model=0): 183, ProcessCoord(pipe=0, data=184, model=0): 184, ProcessCoord(pipe=0, data=185, model=0): 185, ProcessCoord(pipe=0, data=186, model=0): 186, ProcessCoord(pipe=0, data=187, model=0): 187, ProcessCoord(pipe=0, data=188, model=0): 188, ProcessCoord(pipe=0, data=189, model=0): 189, ProcessCoord(pipe=0, data=190, model=0): 190, ProcessCoord(pipe=0, data=191, model=0): 191, ProcessCoord(pipe=0, data=192, model=0): 192, ProcessCoord(pipe=0, data=193, model=0): 193, ProcessCoord(pipe=0, data=194, model=0): 194, ProcessCoord(pipe=0, data=195, model=0): 195, ProcessCoord(pipe=0, data=196, model=0): 196, ProcessCoord(pipe=0, data=197, model=0): 197, ProcessCoord(pipe=0, data=198, model=0): 198, ProcessCoord(pipe=0, data=199, model=0): 199, ProcessCoord(pipe=0, data=200, model=0): 200, ProcessCoord(pipe=0, data=201, model=0): 201, ProcessCoord(pipe=0, data=202, model=0): 202, ProcessCoord(pipe=0, data=203, model=0): 203, ProcessCoord(pipe=0, data=204, mode + 0: l=0): 204, ProcessCoord(pipe=0, data=205, model=0): 205, ProcessCoord(pipe=0, data=206, model=0): 206, ProcessCoord(pipe=0, data=207, model=0): 207, ProcessCoord(pipe=0, data=208, model=0): 208, ProcessCoord(pipe=0, data=209, model=0): 209, ProcessCoord(pipe=0, data=210, model=0): 210, ProcessCoord(pipe=0, data=211, model=0): 211, ProcessCoord(pipe=0, data=212, model=0): 212, ProcessCoord(pipe=0, data=213, model=0): 213, ProcessCoord(pipe=0, data=214, model=0): 214, ProcessCoord(pipe=0, data=215, model=0): 215, ProcessCoord(pipe=0, data=216, model=0): 216, ProcessCoord(pipe=0, data=217, model=0): 217, ProcessCoord(pipe=0, data=218, model=0): 218, ProcessCoord(pipe=0, data=219, model=0): 219, ProcessCoord(pipe=0, data=220, model=0): 220, ProcessCoord(pipe=0, data=221, model=0): 221, ProcessCoord(pipe=0, data=222, model=0): 222, ProcessCoord(pipe=0, data=223, model=0): 223, ProcessCoord(pipe=0, data=224, model=0): 224, ProcessCoord(pipe=0, data=225, model=0): 225, ProcessCoord(pipe=0, data=226, model=0): 226, P + 0: rocessCoord(pipe=0, data=227, model=0): 227, ProcessCoord(pipe=0, data=228, model=0): 228, ProcessCoord(pipe=0, data=229, model=0): 229, ProcessCoord(pipe=0, data=230, model=0): 230, ProcessCoord(pipe=0, data=231, model=0): 231, ProcessCoord(pipe=0, data=232, model=0): 232, ProcessCoord(pipe=0, data=233, model=0): 233, ProcessCoord(pipe=0, data=234, model=0): 234, ProcessCoord(pipe=0, data=235, model=0): 235, ProcessCoord(pipe=0, data=236, model=0): 236, ProcessCoord(pipe=0, data=237, model=0): 237, ProcessCoord(pipe=0, data=238, model=0): 238, ProcessCoord(pipe=0, data=239, model=0): 239, ProcessCoord(pipe=0, data=240, model=0): 240, ProcessCoord(pipe=0, data=241, model=0): 241, ProcessCoord(pipe=0, data=242, model=0): 242, ProcessCoord(pipe=0, data=243, model=0): 243, ProcessCoord(pipe=0, data=244, model=0): 244, ProcessCoord(pipe=0, data=245, model=0): 245, ProcessCoord(pipe=0, data=246, model=0): 246, ProcessCoord(pipe=0, data=247, model=0): 247, ProcessCoord(pipe=0, data=248, model=0): 248, ProcessCoord( + 0: pipe=0, data=249, model=0): 249, ProcessCoord(pipe=0, data=250, model=0): 250, ProcessCoord(pipe=0, data=251, model=0): 251, ProcessCoord(pipe=0, data=252, model=0): 252, ProcessCoord(pipe=0, data=253, model=0): 253, ProcessCoord(pipe=0, data=254, model=0): 254, ProcessCoord(pipe=0, data=255, model=0): 255, ProcessCoord(pipe=1, data=0, model=0): 256, ProcessCoord(pipe=1, data=1, model=0): 257, ProcessCoord(pipe=1, data=2, model=0): 258, ProcessCoord(pipe=1, data=3, model=0): 259, ProcessCoord(pipe=1, data=4, model=0): 260, ProcessCoord(pipe=1, data=5, model=0): 261, ProcessCoord(pipe=1, data=6, model=0): 262, ProcessCoord(pipe=1, data=7, model=0): 263, ProcessCoord(pipe=1, data=8, model=0): 264, ProcessCoord(pipe=1, data=9, model=0): 265, ProcessCoord(pipe=1, data=10, model=0): 266, ProcessCoord(pipe=1, data=11, model=0): 267, ProcessCoord(pipe=1, data=12, model=0): 268, ProcessCoord(pipe=1, data=13, model=0): 269, ProcessCoord(pipe=1, data=14, model=0): 270, ProcessCoord(pipe=1, data=15, model=0): 271, Proce + 0: ssCoord(pipe=1, data=16, model=0): 272, ProcessCoord(pipe=1, data=17, model=0): 273, ProcessCoord(pipe=1, data=18, model=0): 274, ProcessCoord(pipe=1, data=19, model=0): 275, ProcessCoord(pipe=1, data=20, model=0): 276, ProcessCoord(pipe=1, data=21, model=0): 277, ProcessCoord(pipe=1, data=22, model=0): 278, ProcessCoord(pipe=1, data=23, model=0): 279, ProcessCoord(pipe=1, data=24, model=0): 280, ProcessCoord(pipe=1, data=25, model=0): 281, ProcessCoord(pipe=1, data=26, model=0): 282, ProcessCoord(pipe=1, data=27, model=0): 283, ProcessCoord(pipe=1, data=28, model=0): 284, ProcessCoord(pipe=1, data=29, model=0): 285, ProcessCoord(pipe=1, data=30, model=0): 286, ProcessCoord(pipe=1, data=31, model=0): 287, ProcessCoord(pipe=1, data=32, model=0): 288, ProcessCoord(pipe=1, data=33, model=0): 289, ProcessCoord(pipe=1, data=34, model=0): 290, ProcessCoord(pipe=1, data=35, model=0): 291, ProcessCoord(pipe=1, data=36, model=0): 292, ProcessCoord(pipe=1, data=37, model=0): 293, ProcessCoord(pipe=1, data=38, model=0): + 0: 294, ProcessCoord(pipe=1, data=39, model=0): 295, ProcessCoord(pipe=1, data=40, model=0): 296, ProcessCoord(pipe=1, data=41, model=0): 297, ProcessCoord(pipe=1, data=42, model=0): 298, ProcessCoord(pipe=1, data=43, model=0): 299, ProcessCoord(pipe=1, data=44, model=0): 300, ProcessCoord(pipe=1, data=45, model=0): 301, ProcessCoord(pipe=1, data=46, model=0): 302, ProcessCoord(pipe=1, data=47, model=0): 303, ProcessCoord(pipe=1, data=48, model=0): 304, ProcessCoord(pipe=1, data=49, model=0): 305, ProcessCoord(pipe=1, data=50, model=0): 306, ProcessCoord(pipe=1, data=51, model=0): 307, ProcessCoord(pipe=1, data=52, model=0): 308, ProcessCoord(pipe=1, data=53, model=0): 309, ProcessCoord(pipe=1, data=54, model=0): 310, ProcessCoord(pipe=1, data=55, model=0): 311, ProcessCoord(pipe=1, data=56, model=0): 312, ProcessCoord(pipe=1, data=57, model=0): 313, ProcessCoord(pipe=1, data=58, model=0): 314, ProcessCoord(pipe=1, data=59, model=0): 315, ProcessCoord(pipe=1, data=60, model=0): 316, ProcessCoord(pipe=1, data=61 + 0: , model=0): 317, ProcessCoord(pipe=1, data=62, model=0): 318, ProcessCoord(pipe=1, data=63, model=0): 319, ProcessCoord(pipe=1, data=64, model=0): 320, ProcessCoord(pipe=1, data=65, model=0): 321, ProcessCoord(pipe=1, data=66, model=0): 322, ProcessCoord(pipe=1, data=67, model=0): 323, ProcessCoord(pipe=1, data=68, model=0): 324, ProcessCoord(pipe=1, data=69, model=0): 325, ProcessCoord(pipe=1, data=70, model=0): 326, ProcessCoord(pipe=1, data=71, model=0): 327, ProcessCoord(pipe=1, data=72, model=0): 328, ProcessCoord(pipe=1, data=73, model=0): 329, ProcessCoord(pipe=1, data=74, model=0): 330, ProcessCoord(pipe=1, data=75, model=0): 331, ProcessCoord(pipe=1, data=76, model=0): 332, ProcessCoord(pipe=1, data=77, model=0): 333, ProcessCoord(pipe=1, data=78, model=0): 334, ProcessCoord(pipe=1, data=79, model=0): 335, ProcessCoord(pipe=1, data=80, model=0): 336, ProcessCoord(pipe=1, data=81, model=0): 337, ProcessCoord(pipe=1, data=82, model=0): 338, ProcessCoord(pipe=1, data=83, model=0): 339, ProcessCoord(pipe + 0: =1, data=84, model=0): 340, ProcessCoord(pipe=1, data=85, model=0): 341, ProcessCoord(pipe=1, data=86, model=0): 342, ProcessCoord(pipe=1, data=87, model=0): 343, ProcessCoord(pipe=1, data=88, model=0): 344, ProcessCoord(pipe=1, data=89, model=0): 345, ProcessCoord(pipe=1, data=90, model=0): 346, ProcessCoord(pipe=1, data=91, model=0): 347, ProcessCoord(pipe=1, data=92, model=0): 348, ProcessCoord(pipe=1, data=93, model=0): 349, ProcessCoord(pipe=1, data=94, model=0): 350, ProcessCoord(pipe=1, data=95, model=0): 351, ProcessCoord(pipe=1, data=96, model=0): 352, ProcessCoord(pipe=1, data=97, model=0): 353, ProcessCoord(pipe=1, data=98, model=0): 354, ProcessCoord(pipe=1, data=99, model=0): 355, ProcessCoord(pipe=1, data=100, model=0): 356, ProcessCoord(pipe=1, data=101, model=0): 357, ProcessCoord(pipe=1, data=102, model=0): 358, ProcessCoord(pipe=1, data=103, model=0): 359, ProcessCoord(pipe=1, data=104, model=0): 360, ProcessCoord(pipe=1, data=105, model=0): 361, ProcessCoord(pipe=1, data=106, model=0): 362, + 0: ProcessCoord(pipe=1, data=107, model=0): 363, ProcessCoord(pipe=1, data=108, model=0): 364, ProcessCoord(pipe=1, data=109, model=0): 365, ProcessCoord(pipe=1, data=110, model=0): 366, ProcessCoord(pipe=1, data=111, model=0): 367, ProcessCoord(pipe=1, data=112, model=0): 368, ProcessCoord(pipe=1, data=113, model=0): 369, ProcessCoord(pipe=1, data=114, model=0): 370, ProcessCoord(pipe=1, data=115, model=0): 371, ProcessCoord(pipe=1, data=116, model=0): 372, ProcessCoord(pipe=1, data=117, model=0): 373, ProcessCoord(pipe=1, data=118, model=0): 374, ProcessCoord(pipe=1, data=119, model=0): 375, ProcessCoord(pipe=1, data=120, model=0): 376, ProcessCoord(pipe=1, data=121, model=0): 377, ProcessCoord(pipe=1, data=122, model=0): 378, ProcessCoord(pipe=1, data=123, model=0): 379, ProcessCoord(pipe=1, data=124, model=0): 380, ProcessCoord(pipe=1, data=125, model=0): 381, ProcessCoord(pipe=1, data=126, model=0): 382, ProcessCoord(pipe=1, data=127, model=0): 383, ProcessCoord(pipe=1, data=128, model=0): 384, ProcessCoor + 0: d(pipe=1, data=129, model=0): 385, ProcessCoord(pipe=1, data=130, model=0): 386, ProcessCoord(pipe=1, data=131, model=0): 387, ProcessCoord(pipe=1, data=132, model=0): 388, ProcessCoord(pipe=1, data=133, model=0): 389, ProcessCoord(pipe=1, data=134, model=0): 390, ProcessCoord(pipe=1, data=135, model=0): 391, ProcessCoord(pipe=1, data=136, model=0): 392, ProcessCoord(pipe=1, data=137, model=0): 393, ProcessCoord(pipe=1, data=138, model=0): 394, ProcessCoord(pipe=1, data=139, model=0): 395, ProcessCoord(pipe=1, data=140, model=0): 396, ProcessCoord(pipe=1, data=141, model=0): 397, ProcessCoord(pipe=1, data=142, model=0): 398, ProcessCoord(pipe=1, data=143, model=0): 399, ProcessCoord(pipe=1, data=144, model=0): 400, ProcessCoord(pipe=1, data=145, model=0): 401, ProcessCoord(pipe=1, data=146, model=0): 402, ProcessCoord(pipe=1, data=147, model=0): 403, ProcessCoord(pipe=1, data=148, model=0): 404, ProcessCoord(pipe=1, data=149, model=0): 405, ProcessCoord(pipe=1, data=150, model=0): 406, ProcessCoord(pipe=1, da + 0: ta=151, model=0): 407, ProcessCoord(pipe=1, data=152, model=0): 408, ProcessCoord(pipe=1, data=153, model=0): 409, ProcessCoord(pipe=1, data=154, model=0): 410, ProcessCoord(pipe=1, data=155, model=0): 411, ProcessCoord(pipe=1, data=156, model=0): 412, ProcessCoord(pipe=1, data=157, model=0): 413, ProcessCoord(pipe=1, data=158, model=0): 414, ProcessCoord(pipe=1, data=159, model=0): 415, ProcessCoord(pipe=1, data=160, model=0): 416, ProcessCoord(pipe=1, data=161, model=0): 417, ProcessCoord(pipe=1, data=162, model=0): 418, ProcessCoord(pipe=1, data=163, model=0): 419, ProcessCoord(pipe=1, data=164, model=0): 420, ProcessCoord(pipe=1, data=165, model=0): 421, ProcessCoord(pipe=1, data=166, model=0): 422, ProcessCoord(pipe=1, data=167, model=0): 423, ProcessCoord(pipe=1, data=168, model=0): 424, ProcessCoord(pipe=1, data=169, model=0): 425, ProcessCoord(pipe=1, data=170, model=0): 426, ProcessCoord(pipe=1, data=171, model=0): 427, ProcessCoord(pipe=1, data=172, model=0): 428, ProcessCoord(pipe=1, data=173, mode + 0: l=0): 429, ProcessCoord(pipe=1, data=174, model=0): 430, ProcessCoord(pipe=1, data=175, model=0): 431, ProcessCoord(pipe=1, data=176, model=0): 432, ProcessCoord(pipe=1, data=177, model=0): 433, ProcessCoord(pipe=1, data=178, model=0): 434, ProcessCoord(pipe=1, data=179, model=0): 435, ProcessCoord(pipe=1, data=180, model=0): 436, ProcessCoord(pipe=1, data=181, model=0): 437, ProcessCoord(pipe=1, data=182, model=0): 438, ProcessCoord(pipe=1, data=183, model=0): 439, ProcessCoord(pipe=1, data=184, model=0): 440, ProcessCoord(pipe=1, data=185, model=0): 441, ProcessCoord(pipe=1, data=186, model=0): 442, ProcessCoord(pipe=1, data=187, model=0): 443, ProcessCoord(pipe=1, data=188, model=0): 444, ProcessCoord(pipe=1, data=189, model=0): 445, ProcessCoord(pipe=1, data=190, model=0): 446, ProcessCoord(pipe=1, data=191, model=0): 447, ProcessCoord(pipe=1, data=192, model=0): 448, ProcessCoord(pipe=1, data=193, model=0): 449, ProcessCoord(pipe=1, data=194, model=0): 450, ProcessCoord(pipe=1, data=195, model=0): 451, P + 0: rocessCoord(pipe=1, data=196, model=0): 452, ProcessCoord(pipe=1, data=197, model=0): 453, ProcessCoord(pipe=1, data=198, model=0): 454, ProcessCoord(pipe=1, data=199, model=0): 455, ProcessCoord(pipe=1, data=200, model=0): 456, ProcessCoord(pipe=1, data=201, model=0): 457, ProcessCoord(pipe=1, data=202, model=0): 458, ProcessCoord(pipe=1, data=203, model=0): 459, ProcessCoord(pipe=1, data=204, model=0): 460, ProcessCoord(pipe=1, data=205, model=0): 461, ProcessCoord(pipe=1, data=206, model=0): 462, ProcessCoord(pipe=1, data=207, model=0): 463, ProcessCoord(pipe=1, data=208, model=0): 464, ProcessCoord(pipe=1, data=209, model=0): 465, ProcessCoord(pipe=1, data=210, model=0): 466, ProcessCoord(pipe=1, data=211, model=0): 467, ProcessCoord(pipe=1, data=212, model=0): 468, ProcessCoord(pipe=1, data=213, model=0): 469, ProcessCoord(pipe=1, data=214, model=0): 470, ProcessCoord(pipe=1, data=215, model=0): 471, ProcessCoord(pipe=1, data=216, model=0): 472, ProcessCoord(pipe=1, data=217, model=0): 473, ProcessCoord( + 0: pipe=1, data=218, model=0): 474, ProcessCoord(pipe=1, data=219, model=0): 475, ProcessCoord(pipe=1, data=220, model=0): 476, ProcessCoord(pipe=1, data=221, model=0): 477, ProcessCoord(pipe=1, data=222, model=0): 478, ProcessCoord(pipe=1, data=223, model=0): 479, ProcessCoord(pipe=1, data=224, model=0): 480, ProcessCoord(pipe=1, data=225, model=0): 481, ProcessCoord(pipe=1, data=226, model=0): 482, ProcessCoord(pipe=1, data=227, model=0): 483, ProcessCoord(pipe=1, data=228, model=0): 484, ProcessCoord(pipe=1, data=229, model=0): 485, ProcessCoord(pipe=1, data=230, model=0): 486, ProcessCoord(pipe=1, data=231, model=0): 487, ProcessCoord(pipe=1, data=232, model=0): 488, ProcessCoord(pipe=1, data=233, model=0): 489, ProcessCoord(pipe=1, data=234, model=0): 490, ProcessCoord(pipe=1, data=235, model=0): 491, ProcessCoord(pipe=1, data=236, model=0): 492, ProcessCoord(pipe=1, data=237, model=0): 493, ProcessCoord(pipe=1, data=238, model=0): 494, ProcessCoord(pipe=1, data=239, model=0): 495, ProcessCoord(pipe=1, data + 0: =240, model=0): 496, ProcessCoord(pipe=1, data=241, model=0): 497, ProcessCoord(pipe=1, data=242, model=0): 498, ProcessCoord(pipe=1, data=243, model=0): 499, ProcessCoord(pipe=1, data=244, model=0): 500, ProcessCoord(pipe=1, data=245, model=0): 501, ProcessCoord(pipe=1, data=246, model=0): 502, ProcessCoord(pipe=1, data=247, model=0): 503, ProcessCoord(pipe=1, data=248, model=0): 504, ProcessCoord(pipe=1, data=249, model=0): 505, ProcessCoord(pipe=1, data=250, model=0): 506, ProcessCoord(pipe=1, data=251, model=0): 507, ProcessCoord(pipe=1, data=252, model=0): 508, ProcessCoord(pipe=1, data=253, model=0): 509, ProcessCoord(pipe=1, data=254, model=0): 510, ProcessCoord(pipe=1, data=255, model=0): 511} + 0: [2022-12-01 11:39:49,720] [INFO] [module.py:366:_partition_layers] Partitioning pipeline stages with method type:transformer + 0: stage=0 layers=21 + 0: 0: _to_float16 + 0: 1: EmbeddingPipe + 0: 2: + 0: 3: ParallelTransformerLayerPipe + 0: 4: ParallelTransformerLayerPipe + 0: 5: ParallelTransformerLayerPipe + 0: 6: ParallelTransformerLayerPipe + 0: 7: ParallelTransformerLayerPipe + 0: 8: ParallelTransformerLayerPipe + 0: 9: ParallelTransformerLayerPipe + 0: 10: ParallelTransformerLayerPipe + 0: 11: ParallelTransformerLayerPipe + 0: 12: ParallelTransformerLayerPipe + 0: 13: ParallelTransformerLayerPipe + 0: 14: ParallelTransformerLayerPipe + 0: 15: ParallelTransformerLayerPipe + 0: 16: ParallelTransformerLayerPipe + 0: 17: ParallelTransformerLayerPipe + 0: 18: ParallelTransformerLayerPipe + 0: 19: ParallelTransformerLayerPipe + 0: 20: ParallelTransformerLayerPipe + 0: stage=1 layers=22 + 0: 21: ParallelTransformerLayerPipe + 0: 22: ParallelTransformerLayerPipe + 0: 23: ParallelTransformerLayerPipe + 0: 24: ParallelTransformerLayerPipe + 0: 25: ParallelTransformerLayerPipe + 0: 26: ParallelTransformerLayerPipe + 0: 27: ParallelTransformerLayerPipe + 0: 28: ParallelTransformerLayerPipe + 0: 29: ParallelTransformerLayerPipe + 0: 30: ParallelTransformerLayerPipe + 0: 31: ParallelTransformerLayerPipe + 0: 32: ParallelTransformerLayerPipe + 0: 33: ParallelTransformerLayerPipe + 0: 34: ParallelTransformerLayerPipe + 0: 35: ParallelTransformerLayerPipe + 0: 36: ParallelTransformerLayerPipe + 0: 37: ParallelTransformerLayerPipe + 0: 38: ParallelTransformerLayerPipe + 0: 39: undo + 0: 40: MixedFusedLayerNorm + 0: 41: EmbeddingPipe + 0: 42: float16_to_fp32 + 0: loss: CrossEntropy + 0: [2022-12-01 11:39:55,364] [INFO] [utils.py:827:see_memory_usage] After Building Model + 0: [2022-12-01 11:39:55,365] [INFO] [utils.py:828:see_memory_usage] MA 3.8 GB Max_MA 3.8 GB CA 3.89 GB Max_CA 4 GB + 0: [2022-12-01 11:39:55,365] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 44.42 GB, percent = 8.8% + 0: setting training iterations to 73814 + 0: > learning rate decay style: cosine + 0: DeepSpeed is enabled. + 0: [2022-12-01 11:39:55,367] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed info: version=0.7.5, git-hash=unknown, git-branch=unknown + 0: [2022-12-01 11:40:13,875] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False + 0: [2022-12-01 11:40:13,876] [INFO] [logging.py:68:log_dist] [Rank 0] Removing param_group that has no 'params' in the client Optimizer + 0: [2022-12-01 11:40:13,876] [INFO] [logging.py:68:log_dist] [Rank 0] Using client Optimizer as basic optimizer + 0: [2022-12-01 11:40:13,882] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Basic Optimizer = FusedAdam + 0: [2022-12-01 11:40:13,882] [INFO] [logging.py:68:log_dist] [Rank 0] Creating BF16 optimizer + 0: [2022-12-01 11:40:13,922] [INFO] [utils.py:827:see_memory_usage] begin bf16_optimizer + 0: [2022-12-01 11:40:13,922] [INFO] [utils.py:828:see_memory_usage] MA 3.78 GB Max_MA 3.81 GB CA 3.9 GB Max_CA 4 GB + 0: [2022-12-01 11:40:13,923] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 45.31 GB, percent = 9.0% + 8: ninja: no work to do. + 8: Time to load utils op: 0.14458608627319336 seconds + 0: Time to load utils op: 0.11079645156860352 seconds + 0: [2022-12-01 11:40:14,067] [INFO] [utils.py:827:see_memory_usage] before initializing group 0 + 0: [2022-12-01 11:40:14,067] [INFO] [utils.py:828:see_memory_usage] MA 3.78 GB Max_MA 3.78 GB CA 3.9 GB Max_CA 4 GB + 0: [2022-12-01 11:40:14,067] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 45.31 GB, percent = 9.0% + 0: ninja: no work to do. + 0: Time to load utils op: 0.1303102970123291 seconds +20: Time to load utils op: 0.31070590019226074 seconds +16: Time to load utils op: 0.11193132400512695 seconds +16: Time to load utils op: 0.11191511154174805 seconds +16: Time to load utils op: 0.1119084358215332 seconds +16: Time to load utils op: 0.11194944381713867 secondsTime to load utils op: 0.1119697093963623 seconds +16: +16: Time to load utils op: 0.11194705963134766 secondsTime to load utils op: 0.11195588111877441 seconds +16: +16: Time to load utils op: 0.11194634437561035 seconds +17: Time to load utils op: 0.11294150352478027 secondsTime to load utils op: 0.11293625831604004 seconds +17: +17: Time to load utils op: 0.112945556640625 seconds +17: Time to load utils op: 0.11295318603515625 secondsTime to load utils op: 0.11297011375427246 seconds +17: +17: Time to load utils op: 0.11296772956848145 seconds +17: Time to load utils op: 0.11298012733459473 secondsTime to load utils op: 0.11298966407775879 seconds +17: +18: Time to load utils op: 0.11158204078674316 secondsTime to load utils op: 0.11157488822937012 secondsTime to load utils op: 0.11154985427856445 seconds +18: +18: +18: Time to load utils op: 0.11159873008728027 secondsTime to load utils op: 0.11157655715942383 seconds +18: +18: Time to load utils op: 0.11157369613647461 seconds +18: Time to load utils op: 0.11160731315612793 seconds +18: Time to load utils op: 0.11158061027526855 seconds +21: Time to load utils op: 0.11204838752746582 secondsTime to load utils op: 0.11207079887390137 secondsTime to load utils op: 0.11204099655151367 seconds +21: +21: +21: Time to load utils op: 0.11205029487609863 seconds +21: Time to load utils op: 0.11205005645751953 secondsTime to load utils op: 0.1120603084564209 seconds +21: +21: Time to load utils op: 0.11208987236022949 secondsTime to load utils op: 0.11208724975585938 seconds +21: +22: Time to load utils op: 0.11125755310058594 secondsTime to load utils op: 0.11123776435852051 seconds +22: +22: Time to load utils op: 0.11127877235412598 secondsTime to load utils op: 0.11124181747436523 seconds +22: Time to load utils op: 0.11127758026123047 seconds +22: +22: Time to load utils op: 0.11125993728637695 seconds +22: Time to load utils op: 0.11129379272460938 seconds +22: Time to load utils op: 0.11126136779785156 seconds +27: Time to load utils op: 0.10919046401977539 seconds +27: Time to load utils op: 0.10881757736206055 seconds +27: Time to load utils op: 0.10887002944946289 seconds +27: Time to load utils op: 0.10934257507324219 seconds +27: Time to load utils op: 0.3104555606842041 seconds +27: Time to load utils op: 0.10888266563415527 seconds +27: Time to load utils op: 0.10887503623962402 seconds +27: Time to load utils op: 0.10887765884399414 seconds +23: Time to load utils op: 0.11215448379516602 secondsTime to load utils op: 0.11213016510009766 seconds +23: +23: Time to load utils op: 0.11213111877441406 seconds +23: Time to load utils op: 0.11218380928039551 secondsTime to load utils op: 0.11220932006835938 secondsTime to load utils op: 0.11217308044433594 seconds +23: +23: +23: Time to load utils op: 0.11221432685852051 seconds +23: Time to load utils op: 0.11219573020935059 seconds +26: Time to load utils op: 0.11270976066589355 seconds +26: Time to load utils op: 0.11266803741455078 seconds +26: Time to load utils op: 0.11381125450134277 seconds +26: Time to load utils op: 0.11338138580322266 secondsTime to load utils op: 0.11418318748474121 seconds +26: +26: Time to load utils op: 0.11366057395935059 seconds +26: Time to load utils op: 0.11309647560119629 seconds +26: Time to load utils op: 0.11319708824157715 seconds +25: Time to load utils op: 0.11006355285644531 secondsTime to load utils op: 0.11004376411437988 seconds +25: +25: Time to load utils op: 0.11005139350891113 seconds +25: Time to load utils op: 0.11006999015808105 secondsTime to load utils op: 0.11008381843566895 secondsTime to load utils op: 0.11010003089904785 seconds +25: +25: +25: Time to load utils op: 0.11007046699523926 seconds +25: Time to load utils op: 0.11008453369140625 seconds +24: Time to load utils op: 0.11142110824584961 seconds +24: Time to load utils op: 0.11145424842834473 seconds +24: Time to load utils op: 0.1114494800567627 seconds +24: Time to load utils op: 0.11145758628845215 secondsTime to load utils op: 0.1114656925201416 secondsTime to load utils op: 0.11145710945129395 seconds +24: Time to load utils op: 0.11146378517150879 seconds +24: +24: +24: Time to load utils op: 0.11150693893432617 seconds +28: Time to load utils op: 0.10959196090698242 seconds +28: Time to load utils op: 0.10960936546325684 seconds +28: Time to load utils op: 0.10956668853759766 seconds +28: Time to load utils op: 0.10964131355285645 secondsTime to load utils op: 0.10960960388183594 seconds +28: +28: Time to load utils op: 0.10961580276489258 secondsTime to load utils op: 0.10964846611022949 seconds +28: +28: Time to load utils op: 0.10958433151245117 seconds +29: Time to load utils op: 0.10991597175598145 seconds +29: Time to load utils op: 0.10992431640625 secondsTime to load utils op: 0.10992240905761719 seconds +29: +29: Time to load utils op: 0.10992908477783203 seconds +29: Time to load utils op: 0.10991120338439941 seconds +29: Time to load utils op: 0.10994291305541992 seconds +29: Time to load utils op: 0.10994482040405273 seconds +29: Time to load utils op: 0.10993742942810059 seconds +30: Time to load utils op: 0.11067438125610352 seconds +30: Time to load utils op: 0.11071634292602539 seconds +30: Time to load utils op: 0.1107325553894043 seconds +30: Time to load utils op: 0.11074042320251465 secondsTime to load utils op: 0.11075639724731445 seconds +30: +30: Time to load utils op: 0.11075496673583984 secondsTime to load utils op: 0.11075520515441895 seconds +30: +30: Time to load utils op: 0.11078524589538574 seconds +31: Time to load utils op: 0.11094284057617188 seconds +31: Time to load utils op: 0.11096620559692383 seconds +31: Time to load utils op: 0.11097526550292969 secondsTime to load utils op: 0.11094427108764648 seconds +31: Time to load utils op: 0.11094522476196289 seconds +31: +31: Time to load utils op: 0.1109771728515625 seconds +31: Time to load utils op: 0.11099123954772949 seconds +31: Time to load utils op: 0.11101651191711426 seconds + 0: [2022-12-01 11:40:14,244] [INFO] [utils.py:827:see_memory_usage] after initializing group 0 + 0: [2022-12-01 11:40:14,244] [INFO] [utils.py:828:see_memory_usage] MA 7.73 GB Max_MA 7.73 GB CA 9.8 GB Max_CA 10 GB + 0: [2022-12-01 11:40:14,245] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 45.31 GB, percent = 9.0% + 0: Time to load utils op: 0.20286178588867188 seconds + 0: Time to load utils op: 0.20263099670410156 seconds + 0: Time to load utils op: 0.20299983024597168 seconds + 0: Time to load utils op: 0.20310592651367188 seconds + 0: Time to load utils op: 0.20297694206237793 seconds + 0: Time to load utils op: 0.20315074920654297 seconds + 8: Time to load utils op: 0.20278596878051758 seconds + 8: Time to load utils op: 0.20381593704223633 secondsTime to load utils op: 0.20381522178649902 seconds + 8: + 8: Time to load utils op: 0.20438766479492188 seconds + 8: Time to load utils op: 0.2034471035003662 seconds + 8: Time to load utils op: 0.20411920547485352 seconds + 8: Time to load utils op: 0.20470190048217773 seconds + 0: Time to load utils op: 0.0006165504455566406 seconds + 0: Time to load utils op: 0.00042629241943359375 seconds + 0: Time to load utils op: 0.000392913818359375 seconds + 0: Time to load utils op: 0.00034356117248535156 seconds + 0: Time to load utils op: 0.00038909912109375 seconds + 0: Time to load utils op: 0.0003921985626220703 seconds + 0: Time to load utils op: 0.0003752708435058594 seconds +20: Time to load utils op: 0.20336341857910156 seconds +20: Time to load utils op: 0.20354533195495605 seconds +20: Time to load utils op: 0.20367026329040527 seconds +20: Time to load utils op: 0.20365428924560547 seconds +20: Time to load utils op: 0.2036879062652588 seconds +20: Time to load utils op: 0.20426106452941895 secondsTime to load utils op: 0.20427298545837402 seconds +20: + 0: [2022-12-01 11:40:14,276] [INFO] [utils.py:827:see_memory_usage] before initializing group 1 + 0: [2022-12-01 11:40:14,276] [INFO] [utils.py:828:see_memory_usage] MA 7.73 GB Max_MA 7.73 GB CA 9.8 GB Max_CA 10 GB + 0: [2022-12-01 11:40:14,276] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 45.33 GB, percent = 9.0% + 8: Time to load utils op: 0.0004928112030029297 seconds + 8: Time to load utils op: 0.000461578369140625 seconds + 8: Time to load utils op: 0.0005171298980712891 seconds +20: Time to load utils op: 0.00048065185546875 seconds + 8: Time to load utils op: 0.0006005764007568359 seconds + 8: Time to load utils op: 0.0005953311920166016 seconds + 8: Time to load utils op: 0.0006051063537597656 seconds + 8: Time to load utils op: 0.000579833984375 seconds + 8: Time to load utils op: 0.0004918575286865234 seconds +20: Time to load utils op: 0.00037789344787597656 seconds +20: Time to load utils op: 0.0003044605255126953 seconds +20: Time to load utils op: 0.00036215782165527344 seconds + 3: Time to load utils op: 0.24559330940246582 seconds + 3: Time to load utils op: 0.2456073760986328 seconds + 3: Time to load utils op: 0.24532508850097656 seconds + 3: Time to load utils op: 0.24562668800354004 seconds + 3: Time to load utils op: 0.4350090026855469 seconds + 3: Time to load utils op: 0.2456662654876709 seconds + 3: Time to load utils op: 0.24551033973693848 seconds +20: Time to load utils op: 0.00032210350036621094 seconds + 3: Time to load utils op: 0.2456827163696289 seconds +20: Time to load utils op: 0.00035190582275390625 seconds +20: Time to load utils op: 0.00040411949157714844 seconds +20: Time to load utils op: 0.0003323554992675781 seconds +27: Time to load utils op: 0.0004985332489013672 seconds +27: Time to load utils op: 0.0004940032958984375 seconds +27: Time to load utils op: 0.0005056858062744141 seconds +27: Time to load utils op: 0.0005185604095458984 seconds +27: Time to load utils op: 0.0005838871002197266 seconds +27: Time to load utils op: 0.0005733966827392578 seconds +27: Time to load utils op: 0.0006346702575683594 seconds +27: Time to load utils op: 0.0006361007690429688 seconds + 2: Time to load utils op: 0.254425048828125 seconds + 2: Time to load utils op: 0.44409608840942383 seconds + 2: Time to load utils op: 0.25443601608276367 seconds + 2: Time to load utils op: 0.2544260025024414 seconds + 2: Time to load utils op: 0.25446105003356934 seconds + 2: Time to load utils op: 0.2551612854003906 seconds + 2: Time to load utils op: 0.2544870376586914 seconds + 2: Time to load utils op: 0.25448107719421387 seconds + 5: Time to load utils op: 0.25116658210754395 seconds + 5: Time to load utils op: 0.2512376308441162 secondsTime to load utils op: 0.2512538433074951 seconds + 5: + 5: Time to load utils op: 0.2512378692626953 secondsTime to load utils op: 0.2519819736480713 seconds + 5: + 5: Time to load utils op: 0.44420289993286133 secondsTime to load utils op: 0.2514827251434326 seconds + 5: Time to load utils op: 0.25122666358947754 seconds + 5: + 7: Time to load utils op: 0.24993586540222168 seconds + 7: Time to load utils op: 0.24998116493225098 seconds + 7: Time to load utils op: 0.2507028579711914 seconds + 7: Time to load utils op: 0.25060534477233887 seconds + 7: Time to load utils op: 0.4441983699798584 seconds + 7: Time to load utils op: 0.25006866455078125 seconds + 7: Time to load utils op: 0.2500317096710205 secondsTime to load utils op: 0.2504241466522217 seconds + 7: +17: Time to load utils op: 0.0008215904235839844 seconds +16: Time to load utils op: 0.0006246566772460938 seconds +17: Time to load utils op: 0.0011336803436279297 seconds +16: Time to load utils op: 0.0008246898651123047 seconds +16: Time to load utils op: 0.0009114742279052734 seconds +16: Time to load utils op: 0.0009565353393554688 seconds +17: Time to load utils op: 0.0012595653533935547 seconds +18: Time to load utils op: 0.0009915828704833984 seconds +17: Time to load utils op: 0.0012390613555908203 secondsTime to load utils op: 0.0012884140014648438 seconds +17: +17: Time to load utils op: 0.0012612342834472656 seconds +17: Time to load utils op: 0.0012965202331542969 seconds +17: Time to load utils op: 0.0013461112976074219 seconds +16: Time to load utils op: 0.0013251304626464844 seconds +16: Time to load utils op: 0.0011856555938720703 seconds +16: Time to load utils op: 0.001238107681274414 seconds +16: Time to load utils op: 0.0013537406921386719 seconds +18: Time to load utils op: 0.0013124942779541016 secondsTime to load utils op: 0.0012128353118896484 seconds +18: +18: Time to load utils op: 0.0011873245239257812 seconds +18: Time to load utils op: 0.0012514591217041016 seconds +18: Time to load utils op: 0.0012400150299072266 secondsTime to load utils op: 0.0013012886047363281 seconds +18: +18: Time to load utils op: 0.0012836456298828125 seconds + 0: [2022-12-01 11:40:14,310] [INFO] [utils.py:827:see_memory_usage] after initializing group 1 + 0: [2022-12-01 11:40:14,311] [INFO] [utils.py:828:see_memory_usage] MA 11.36 GB Max_MA 11.36 GB CA 15.23 GB Max_CA 15 GB + 0: [2022-12-01 11:40:14,311] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 45.34 GB, percent = 9.0% + 1: Time to load utils op: 0.27794694900512695 seconds + 1: Time to load utils op: 0.2779996395111084 seconds + 1: Time to load utils op: 0.2780158519744873 secondsTime to load utils op: 0.2780158519744873 seconds + 1: + 1: Time to load utils op: 0.27843189239501953 seconds + 1: Time to load utils op: 0.2784276008605957 seconds + 1: Time to load utils op: 0.27841854095458984 secondsTime to load utils op: 0.2784693241119385 seconds + 1: +12: Time to load utils op: 0.2699244022369385 seconds +12: Time to load utils op: 0.2698655128479004 seconds +12: Time to load utils op: 0.26990509033203125 seconds +12: Time to load utils op: 0.47428178787231445 seconds +12: Time to load utils op: 0.26995277404785156 secondsTime to load utils op: 0.26996493339538574 secondsTime to load utils op: 0.2703871726989746 secondsTime to load utils op: 0.2699873447418213 seconds +12: +12: +12: + 4: Time to load utils op: 0.2809758186340332 seconds +11: Time to load utils op: 0.26860713958740234 seconds + 6: Time to load utils op: 0.2748110294342041 seconds + 4: Time to load utils op: 0.2812368869781494 seconds + 4: Time to load utils op: 0.28108763694763184 seconds + 6: Time to load utils op: 0.2748298645019531 seconds + 4: Time to load utils op: 0.2814290523529053 seconds + 6: Time to load utils op: 0.2747788429260254 seconds +11: Time to load utils op: 0.26865100860595703 seconds + 4: Time to load utils op: 0.2811317443847656 seconds +11: Time to load utils op: 0.26872992515563965 seconds + 4: Time to load utils op: 0.4715547561645508 seconds + 9: Time to load utils op: 0.2706105709075928 seconds + 9: Time to load utils op: 0.27063655853271484 seconds + 4: Time to load utils op: 0.28165125846862793 secondsTime to load utils op: 0.2815272808074951 seconds + 6: Time to load utils op: 0.2748885154724121 seconds +11: Time to load utils op: 0.26875758171081543 secondsTime to load utils op: 0.2687828540802002 seconds +11: Time to load utils op: 0.2687821388244629 seconds +11: + 4: + 6: Time to load utils op: 0.27489447593688965 seconds +11: Time to load utils op: 0.2687849998474121 seconds + 6: Time to load utils op: 0.274904727935791 seconds + 6: Time to load utils op: 0.2748854160308838 seconds + 6: Time to load utils op: 0.27492618560791016 seconds +11: Time to load utils op: 0.26880621910095215 seconds + 9: Time to load utils op: 0.27068352699279785 seconds + 9: Time to load utils op: 0.2706918716430664 seconds + 9: Time to load utils op: 0.2707695960998535 secondsTime to load utils op: 0.27074623107910156 seconds + 9: + 9: Time to load utils op: 0.27079296112060547 seconds + 9: Time to load utils op: 0.27075886726379395 seconds +10: Time to load utils op: 0.2694258689880371 seconds +10: Time to load utils op: 0.26944875717163086 seconds +10: Time to load utils op: 0.2694554328918457 seconds +10: Time to load utils op: 0.26946330070495605 seconds +10: Time to load utils op: 0.26947927474975586 seconds +10: Time to load utils op: 0.26947832107543945 seconds +10: Time to load utils op: 0.2694885730743408 seconds +10: Time to load utils op: 0.26952624320983887 seconds +19: Time to load utils op: 0.2635617256164551 seconds +19: Time to load utils op: 0.2634897232055664 seconds +13: Time to load utils op: 0.2658424377441406 seconds +19: Time to load utils op: 0.2646312713623047 seconds +19: Time to load utils op: 0.26401376724243164 secondsTime to load utils op: 0.2644970417022705 seconds +19: +19: Time to load utils op: 0.46828365325927734 secondsTime to load utils op: 0.2645988464355469 seconds +19: +13: Time to load utils op: 0.2658829689025879 seconds +19: Time to load utils op: 0.26346755027770996 seconds +13: Time to load utils op: 0.2659299373626709 secondsTime to load utils op: 0.2659027576446533 seconds +13: +13: Time to load utils op: 0.2659416198730469 seconds +13: Time to load utils op: 0.26592278480529785 seconds +13: Time to load utils op: 0.26594996452331543 seconds +15: Time to load utils op: 0.2637004852294922 seconds +15: Time to load utils op: 0.26371169090270996 seconds +13: Time to load utils op: 0.26593947410583496 seconds +15: Time to load utils op: 0.2637472152709961 seconds +15: Time to load utils op: 0.26377129554748535 seconds +15: Time to load utils op: 0.2637629508972168 secondsTime to load utils op: 0.2637972831726074 seconds +15: +15: Time to load utils op: 0.2637970447540283 seconds +15: Time to load utils op: 0.2637763023376465 seconds +14: Time to load utils op: 0.2658247947692871 seconds +14: Time to load utils op: 0.2658412456512451 seconds +14: Time to load utils op: 0.26584792137145996 seconds +14: Time to load utils op: 0.26586389541625977 seconds +14: Time to load utils op: 0.2658979892730713 secondsTime to load utils op: 0.2658708095550537 seconds +14: +14: Time to load utils op: 0.26587390899658203 seconds +14: Time to load utils op: 0.265883207321167 seconds +26: Time to load utils op: 0.0008957386016845703 seconds +26: Time to load utils op: 0.0009686946868896484 secondsTime to load utils op: 0.0009508132934570312 seconds +26: +26: Time to load utils op: 0.0011949539184570312 seconds +26: Time to load utils op: 0.0011322498321533203 seconds +26: Time to load utils op: 0.0011210441589355469 seconds +26: Time to load utils op: 0.0011434555053710938 seconds +26: Time to load utils op: 0.001245737075805664 seconds +30: Time to load utils op: 0.0009696483612060547 seconds +23: Time to load utils op: 0.0009999275207519531 seconds +23: Time to load utils op: 0.001009225845336914 seconds +31: Time to load utils op: 0.0010197162628173828 seconds +31: Time to load utils op: 0.0009484291076660156 seconds +23: Time to load utils op: 0.0011372566223144531 seconds +23: Time to load utils op: 0.0011470317840576172 seconds +23: Time to load utils op: 0.0011415481567382812 seconds +23: Time to load utils op: 0.0011408329010009766 seconds +23: Time to load utils op: 0.001161336898803711 seconds +23: Time to load utils op: 0.0011942386627197266 seconds +21: Time to load utils op: 0.0009489059448242188 seconds +31: Time to load utils op: 0.0013737678527832031 seconds +30: Time to load utils op: 0.0016400814056396484 seconds +30: Time to load utils op: 0.001622915267944336 seconds +31: Time to load utils op: 0.0013954639434814453 seconds +22: Time to load utils op: 0.0007987022399902344 seconds +31: Time to load utils op: 0.0013742446899414062 seconds +30: Time to load utils op: 0.0016286373138427734 seconds +30: Time to load utils op: 0.0016338825225830078 seconds +29: Time to load utils op: 0.0012204647064208984 seconds +30: Time to load utils op: 0.0016336441040039062 secondsTime to load utils op: 0.0016188621520996094 seconds +30: +31: Time to load utils op: 0.001341104507446289 secondsTime to load utils op: 0.0013747215270996094 seconds +31: +30: Time to load utils op: 0.0016896724700927734 seconds +21: Time to load utils op: 0.0011839866638183594 seconds +31: Time to load utils op: 0.0013844966888427734 seconds +22: Time to load utils op: 0.0011072158813476562 seconds +21: Time to load utils op: 0.0013308525085449219 seconds +21: Time to load utils op: 0.0013179779052734375 seconds +21: Time to load utils op: 0.0013785362243652344 secondsTime to load utils op: 0.0013425350189208984 seconds +21: +22: Time to load utils op: 0.001176595687866211 seconds +29: Time to load utils op: 0.0015473365783691406 seconds +29: Time to load utils op: 0.0015664100646972656 seconds +24: Time to load utils op: 0.0011153221130371094 seconds +24: Time to load utils op: 0.0010819435119628906 seconds +21: Time to load utils op: 0.001321554183959961 seconds +25: Time to load utils op: 0.0011892318725585938 seconds +25: Time to load utils op: 0.0012054443359375 seconds +24: Time to load utils op: 0.001100778579711914 seconds +28: Time to load utils op: 0.0010247230529785156 seconds +28: Time to load utils op: 0.0009691715240478516 seconds +29: Time to load utils op: 0.0015006065368652344 secondsTime to load utils op: 0.0015380382537841797 seconds +29: +29: Time to load utils op: 0.0015292167663574219 seconds +21: Time to load utils op: 0.0013539791107177734 seconds +29: Time to load utils op: 0.0015599727630615234 seconds +29: Time to load utils op: 0.0015621185302734375 seconds +24: Time to load utils op: 0.0012836456298828125 seconds +22: Time to load utils op: 0.0013628005981445312 seconds +22: Time to load utils op: 0.0014045238494873047 seconds +28: Time to load utils op: 0.0012607574462890625 seconds +22: Time to load utils op: 0.0013804435729980469 seconds +24: Time to load utils op: 0.0014522075653076172 seconds +24: Time to load utils op: 0.0013661384582519531 secondsTime to load utils op: 0.0013689994812011719 seconds +24: +25: Time to load utils op: 0.0014827251434326172 secondsTime to load utils op: 0.0015633106231689453 seconds +25: +25: Time to load utils op: 0.0015611648559570312 seconds +24: Time to load utils op: 0.0014710426330566406 seconds +28: Time to load utils op: 0.0014200210571289062 seconds +25: Time to load utils op: 0.0015497207641601562 seconds +28: Time to load utils op: 0.0014274120330810547 seconds +28: Time to load utils op: 0.0014200210571289062 seconds +25: Time to load utils op: 0.001508951187133789 seconds +28: Time to load utils op: 0.0014073848724365234 seconds +25: Time to load utils op: 0.001543283462524414 seconds +28: Time to load utils op: 0.0014362335205078125 seconds + 0: [2022-12-01 11:40:14,342] [INFO] [utils.py:827:see_memory_usage] before initializing group 2 + 0: [2022-12-01 11:40:14,342] [INFO] [utils.py:828:see_memory_usage] MA 11.36 GB Max_MA 11.36 GB CA 15.23 GB Max_CA 15 GB + 0: [2022-12-01 11:40:14,343] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 45.34 GB, percent = 9.0% +22: Time to load utils op: 0.001340627670288086 seconds +22: Time to load utils op: 0.0013837814331054688 seconds + 0: [2022-12-01 11:40:14,377] [INFO] [utils.py:827:see_memory_usage] after initializing group 2 + 0: [2022-12-01 11:40:14,378] [INFO] [utils.py:828:see_memory_usage] MA 11.36 GB Max_MA 11.36 GB CA 15.23 GB Max_CA 15 GB + 0: [2022-12-01 11:40:14,378] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 45.34 GB, percent = 9.0% +19: Time to load utils op: 0.000514984130859375 seconds +19: Time to load utils op: 0.000576019287109375 seconds +19: Time to load utils op: 0.0005483627319335938 secondsTime to load utils op: 0.0006093978881835938 seconds +19: +19: Time to load utils op: 0.0005986690521240234 secondsTime to load utils op: 0.0005998611450195312 seconds +19: +19: Time to load utils op: 0.0006005764007568359 seconds +19: Time to load utils op: 0.00063323974609375 seconds +15: Time to load utils op: 0.0008392333984375 seconds +15: Time to load utils op: 0.0009138584136962891 seconds +15: Time to load utils op: 0.0008761882781982422 seconds +11: Time to load utils op: 0.0007903575897216797 seconds + 7: Time to load utils op: 0.0005507469177246094 seconds + 7: Time to load utils op: 0.0005450248718261719 secondsTime to load utils op: 0.0005440711975097656 seconds + 7: + 7: Time to load utils op: 0.00045609474182128906 seconds +11: Time to load utils op: 0.0008165836334228516 seconds + 7: Time to load utils op: 0.00046181678771972656 secondsTime to load utils op: 0.0004317760467529297 secondsTime to load utils op: 0.00046706199645996094 seconds + 7: + 7: + 7: Time to load utils op: 0.0004894733428955078 seconds +15: Time to load utils op: 0.0010900497436523438 seconds +15: Time to load utils op: 0.0011000633239746094 seconds +15: Time to load utils op: 0.0011053085327148438 seconds +15: Time to load utils op: 0.0011110305786132812 seconds +13: Time to load utils op: 0.0009505748748779297 seconds +13: Time to load utils op: 0.0009844303131103516 seconds +13: Time to load utils op: 0.0009214878082275391 seconds +15: Time to load utils op: 0.0011780261993408203 seconds +11: Time to load utils op: 0.0011796951293945312 seconds + 5: Time to load utils op: 0.0005145072937011719 seconds +11: Time to load utils op: 0.0009915828704833984 seconds +13: Time to load utils op: 0.0011684894561767578 seconds +11: Time to load utils op: 0.0011813640594482422 secondsTime to load utils op: 0.0011036396026611328 seconds +11: + 5: Time to load utils op: 0.0005474090576171875 seconds +13: Time to load utils op: 0.0011358261108398438 seconds +13: Time to load utils op: 0.0011396408081054688 seconds +11: Time to load utils op: 0.0011022090911865234 seconds +13: Time to load utils op: 0.001148223876953125 seconds +11: Time to load utils op: 0.0011909008026123047 seconds + 5: Time to load utils op: 0.0005686283111572266 seconds + 3: Time to load utils op: 0.00045371055603027344 seconds + 1: Time to load utils op: 0.0010595321655273438 seconds + 2: Time to load utils op: 0.0004999637603759766 seconds +13: Time to load utils op: 0.0011594295501708984 seconds + 5: Time to load utils op: 0.0005774497985839844 seconds + 2: Time to load utils op: 0.0005059242248535156 seconds + 5: Time to load utils op: 0.0006291866302490234 seconds + 1: Time to load utils op: 0.001117706298828125 seconds + 5: Time to load utils op: 0.0006334781646728516 seconds + 5: Time to load utils op: 0.0005974769592285156 seconds + 2: Time to load utils op: 0.00042510032653808594 seconds + 5: Time to load utils op: 0.0006461143493652344 seconds + 2: Time to load utils op: 0.0005195140838623047 seconds + 1: Time to load utils op: 0.0012607574462890625 seconds + 2: Time to load utils op: 0.0005347728729248047 seconds + 2: Time to load utils op: 0.0005557537078857422 seconds + 2: Time to load utils op: 0.0005843639373779297 seconds + 2: Time to load utils op: 0.00061798095703125 seconds + 1: Time to load utils op: 0.0014507770538330078 seconds + 6: Time to load utils op: 0.0011394023895263672 seconds + 1: Time to load utils op: 0.0013561248779296875 seconds + 1: Time to load utils op: 0.0014271736145019531 seconds + 1: Time to load utils op: 0.001455545425415039 seconds + 1: Time to load utils op: 0.0014293193817138672 seconds + 6: Time to load utils op: 0.0012927055358886719 secondsTime to load utils op: 0.0013458728790283203 seconds + 6: + 6: Time to load utils op: 0.0012047290802001953 seconds + 6: Time to load utils op: 0.001321554183959961 seconds + 6: Time to load utils op: 0.0012350082397460938 secondsTime to load utils op: 0.0012230873107910156 seconds + 6: + 6: Time to load utils op: 0.001262664794921875 seconds + 4: Time to load utils op: 0.0009682178497314453 seconds + 4: Time to load utils op: 0.001074075698852539 seconds + 4: Time to load utils op: 0.0010886192321777344 seconds + 4: Time to load utils op: 0.0011255741119384766 seconds + 4: Time to load utils op: 0.0011870861053466797 seconds + 4: Time to load utils op: 0.0012116432189941406 seconds + 4: Time to load utils op: 0.0012214183807373047 seconds + 4: Time to load utils op: 0.0012764930725097656 seconds +14: Time to load utils op: 0.0011403560638427734 seconds +14: Time to load utils op: 0.0011250972747802734 seconds +14: Time to load utils op: 0.0012807846069335938 seconds +14: Time to load utils op: 0.0014352798461914062 seconds +14: Time to load utils op: 0.0014607906341552734 seconds +14: Time to load utils op: 0.0014352798461914062 seconds +14: Time to load utils op: 0.0013730525970458984 seconds +14: Time to load utils op: 0.0014774799346923828 seconds +10: Time to load utils op: 0.0008442401885986328 seconds +10: Time to load utils op: 0.0010902881622314453 seconds +10: Time to load utils op: 0.0010983943939208984 seconds +10: Time to load utils op: 0.0012133121490478516 seconds +10: Time to load utils op: 0.0012042522430419922 seconds +10: Time to load utils op: 0.0012004375457763672 secondsTime to load utils op: 0.001191854476928711 seconds +10: +10: Time to load utils op: 0.0012557506561279297 seconds + 0: [2022-12-01 11:40:14,407] [INFO] [utils.py:827:see_memory_usage] before initialize_optimizer + 0: [2022-12-01 11:40:14,408] [INFO] [utils.py:828:see_memory_usage] MA 11.36 GB Max_MA 11.36 GB CA 15.23 GB Max_CA 15 GB + 0: [2022-12-01 11:40:14,408] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 45.34 GB, percent = 9.0% + 9: Time to load utils op: 0.0009946823120117188 seconds + 9: Time to load utils op: 0.0011098384857177734 seconds +12: Time to load utils op: 0.0005104541778564453 seconds +12: Time to load utils op: 0.0005276203155517578 seconds + 9: Time to load utils op: 0.0011990070343017578 seconds +12: Time to load utils op: 0.0005352497100830078 seconds + 9: Time to load utils op: 0.0012822151184082031 seconds + 9: Time to load utils op: 0.0012176036834716797 seconds +12: Time to load utils op: 0.0005893707275390625 secondsTime to load utils op: 0.0004978179931640625 seconds +12: +12: Time to load utils op: 0.00054168701171875 seconds + 9: Time to load utils op: 0.0012359619140625 seconds + 9: Time to load utils op: 0.001344919204711914 seconds + 9: Time to load utils op: 0.0012977123260498047 seconds +12: Time to load utils op: 0.0006766319274902344 seconds +12: Time to load utils op: 0.0007336139678955078 seconds + 3: Time to load utils op: 0.00042700767517089844 secondsTime to load utils op: 0.0004343986511230469 secondsTime to load utils op: 0.0004336833953857422 seconds + 3: + 3: + 3: Time to load utils op: 0.0004413127899169922 secondsTime to load utils op: 0.0004444122314453125 secondsTime to load utils op: 0.0004417896270751953 seconds + 3: + 3: Time to load utils op: 0.0004417896270751953 seconds + 3: + 0: [2022-12-01 11:40:14,444] [INFO] [utils.py:827:see_memory_usage] end initialize_optimizer + 0: [2022-12-01 11:40:14,444] [INFO] [utils.py:828:see_memory_usage] MA 11.42 GB Max_MA 11.42 GB CA 15.23 GB Max_CA 15 GB + 0: [2022-12-01 11:40:14,444] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 45.34 GB, percent = 9.0% + 0: [2022-12-01 11:40:14,474] [INFO] [utils.py:827:see_memory_usage] end bf16_optimizer + 0: [2022-12-01 11:40:14,475] [INFO] [utils.py:828:see_memory_usage] MA 11.42 GB Max_MA 11.42 GB CA 15.23 GB Max_CA 15 GB + 0: [2022-12-01 11:40:14,475] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 45.34 GB, percent = 9.0% + 0: [2022-12-01 11:40:14,475] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Final Optimizer = FusedAdam + 0: [2022-12-01 11:40:14,475] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed using client LR scheduler + 0: [2022-12-01 11:40:14,475] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed LR Scheduler = + 0: [2022-12-01 11:40:14,475] [INFO] [logging.py:68:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0, 0.0, 0.0], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] + 0: [2022-12-01 11:40:14,475] [INFO] [config.py:1007:print] DeepSpeedEngine configuration: + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] activation_checkpointing_config { + 0: "partition_activations": false, + 0: "contiguous_memory_optimization": false, + 0: "cpu_checkpointing": false, + 0: "number_checkpoints": null, + 0: "synchronize_checkpoint_boundary": false, + 0: "profile": false + 0: } + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True} + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] amp_enabled .................. False + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] amp_params ................... False + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] autotuning_config ............ { + 0: "enabled": false, + 0: "start_step": null, + 0: "end_step": null, + 0: "metric_path": null, + 0: "arg_mappings": null, + 0: "metric": "throughput", + 0: "model_info": null, + 0: "results_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_results", + 0: "exps_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_exps", + 0: "overwrite": true, + 0: "fast": true, + 0: "start_profile_step": 3, + 0: "end_profile_step": 5, + 0: "tuner_type": "gridsearch", + 0: "tuner_early_stopping": 5, + 0: "tuner_num_trials": 50, + 0: "model_info_path": null, + 0: "mp_size": 1, + 0: "max_train_batch_size": null, + 0: "min_train_batch_size": 1, + 0: "max_train_micro_batch_size_per_gpu": 1.024000e+03, + 0: "min_train_micro_batch_size_per_gpu": 1, + 0: "num_tuning_micro_batch_sizes": 3 + 0: } + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] bfloat16_enabled ............. True + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] checkpoint_parallel_write_pipeline False + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] checkpoint_tag_validation_enabled True + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] checkpoint_tag_validation_fail False + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] comms_config ................. + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] communication_data_type ...... None + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] compression_config ........... {'weight_quantization': {'shared_parameters': {'enabled': False, 'quantizer_kernel': False, 'schedule_offset': 0, 'quantize_groups': 1, 'quantize_verbose': False, 'quantization_type': 'symmetric', 'quantize_weight_in_forward': False, 'rounding': 'nearest', 'fp16_mixed_quantize': False, 'quantize_change_ratio': 0.001}, 'different_groups': {}}, 'activation_quantization': {'shared_parameters': {'enabled': False, 'quantization_type': 'symmetric', 'range_calibration': 'dynamic', 'schedule_offset': 1000}, 'different_groups': {}}, 'sparse_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'row_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'head_pruning': {'shared_parameters': {'enabled': False, 'method': 'topk', 'schedule_offset': 1000}, 'different_groups': {}}, 'channel_pruning': {'shared_pa + 0: rameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'layer_reduction': {'enabled': False}} + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] curriculum_enabled ........... False + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] curriculum_params ............ False + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] dataloader_drop_last ......... False + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] disable_allgather ............ False + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] dump_state ................... False + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] dynamic_loss_scale_args ...... None + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] eigenvalue_enabled ........... False + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] eigenvalue_gas_boundary_resolution 1 + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] eigenvalue_layer_name ........ bert.encoder.layer + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] eigenvalue_layer_num ......... 0 + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] eigenvalue_max_iter .......... 100 + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] eigenvalue_stability ......... 1e-06 + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] eigenvalue_tol ............... 0.01 + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] eigenvalue_verbose ........... False + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] elasticity_enabled ........... False + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] flops_profiler_config ........ { + 0: "enabled": false, + 0: "profile_step": 1, + 0: "module_depth": -1, + 0: "top_modules": 1, + 0: "detailed": true, + 0: "output_file": null + 0: } + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] fp16_auto_cast ............... None + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] fp16_enabled ................. False + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] fp16_master_weights_and_gradients False + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] global_rank .................. 0 + 0: [2022-12-01 11:40:14,476] [INFO] [config.py:1011:print] gradient_accumulation_steps .. 2 + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] gradient_clipping ............ 1.0 + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] gradient_predivide_factor .... 1.0 + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] initial_dynamic_scale ........ 1 + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] load_universal_checkpoint .... False + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] loss_scale ................... 1.0 + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] memory_breakdown ............. False + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] monitor_config ............... + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] nebula_config ................ { + 0: "enabled": false, + 0: "persistent_storage_path": null, + 0: "persistent_time_interval": 100, + 0: "num_of_version_in_retention": 2, + 0: "enable_nebula_load": true, + 0: "load_path": null + 0: } + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] optimizer_legacy_fusion ...... False + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] optimizer_name ............... None + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] optimizer_params ............. None + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0} + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] pld_enabled .................. False + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] pld_params ................... False + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] prescale_gradients ........... False + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] scheduler_name ............... None + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] scheduler_params ............. None + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] sparse_attention ............. None + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] sparse_gradients_enabled ..... False + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] steps_per_print .............. 2000 + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] train_batch_size ............. 512 + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] train_micro_batch_size_per_gpu 1 + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] use_node_local_storage ....... False + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] wall_clock_breakdown ......... False + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] world_size ................... 256 + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] zero_allow_untested_optimizer False + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] zero_config .................. stage=0 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=500000000 allgather_partitions=True allgather_bucket_size=500000000 overlap_comm=False load_from_fp32_weights=True elastic_checkpoint=False offload_param=None offload_optimizer=None sub_group_size=1000000000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=50000000 param_persistence_threshold=100000 model_persistence_threshold=9223372036854775807 max_live_parameters=1000000000 max_reuse_distance=1000000000 gather_16bit_weights_on_model_save=False stage3_gather_fp16_weights_on_model_save=False ignore_unused_parameters=True legacy_stage1=False round_robin_gradients=False + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] zero_enabled ................. False + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:1011:print] zero_optimization_stage ...... 0 + 0: [2022-12-01 11:40:14,477] [INFO] [config.py:996:print_user_config] json = { + 0: "train_micro_batch_size_per_gpu": 1, + 0: "train_batch_size": 512, + 0: "gradient_clipping": 1.0, + 0: "zero_optimization": { + 0: "stage": 0 + 0: }, + 0: "bf16": { + 0: "enabled": true + 0: }, + 0: "steps_per_print": 2.000000e+03, + 0: "wall_clock_breakdown": false + 0: } + 0: Time to load utils op: 0.00037598609924316406 seconds + 0: [2022-12-01 11:40:14,478] [INFO] [engine.py:87:__init__] CONFIG: micro_batches=2 micro_batch_size=1 +33: ninja: no work to do. +33: Time to load utils op: 0.2868318557739258 seconds +33: ninja: no work to do. +33: Time to load utils op: 0.11793661117553711 seconds +44: Time to load utils op: 0.10904788970947266 secondsTime to load utils op: 0.10960578918457031 seconds +44: Time to load utils op: 0.10946822166442871 seconds +44: +44: Time to load utils op: 0.10960793495178223 secondsTime to load utils op: 0.10899662971496582 secondsTime to load utils op: 0.10970616340637207 seconds +44: +44: +44: Time to load utils op: 0.10900163650512695 seconds +44: Time to load utils op: 0.40371131896972656 seconds +40: Time to load utils op: 0.43702268600463867 seconds +47: Time to load utils op: 0.13931918144226074 secondsTime to load utils op: 0.13885879516601562 seconds +47: +47: Time to load utils op: 0.1388416290283203 seconds +47: Time to load utils op: 0.13837528228759766 seconds +47: Time to load utils op: 0.13802051544189453 seconds +47: Time to load utils op: 0.1385037899017334 seconds +47: Time to load utils op: 0.13785195350646973 secondsTime to load utils op: 0.1384432315826416 seconds +47: +41: Time to load utils op: 0.43697404861450195 seconds +42: Time to load utils op: 0.43491530418395996 seconds +45: Time to load utils op: 0.1372060775756836 secondsTime to load utils op: 0.1371629238128662 seconds +45: +45: Time to load utils op: 0.1372067928314209 seconds +45: Time to load utils op: 0.1371934413909912 seconds +45: Time to load utils op: 0.1371910572052002 seconds +45: Time to load utils op: 0.13718891143798828 secondsTime to load utils op: 0.13724327087402344 seconds +45: +45: Time to load utils op: 0.13729500770568848 seconds +43: Time to load utils op: 0.13975262641906738 seconds +53: Time to load utils op: 0.13326644897460938 seconds +43: Time to load utils op: 0.13973641395568848 seconds +43: Time to load utils op: 0.13975214958190918 seconds +43: Time to load utils op: 0.13975119590759277 seconds +53: Time to load utils op: 0.13368868827819824 seconds +53: Time to load utils op: 0.1323106288909912 seconds +53: Time to load utils op: 0.13247323036193848 secondsTime to load utils op: 0.13275909423828125 seconds +43: Time to load utils op: 0.1398015022277832 secondsTime to load utils op: 0.139817476272583 secondsTime to load utils op: 0.13979005813598633 secondsTime to load utils op: 0.13979721069335938 seconds +43: +43: +43: +53: +53: Time to load utils op: 0.13316679000854492 seconds +53: Time to load utils op: 0.42817234992980957 secondsTime to load utils op: 0.13297343254089355 seconds +53: +50: Time to load utils op: 0.42714405059814453 seconds +50: Time to load utils op: 0.13604736328125 seconds +50: Time to load utils op: 0.13615942001342773 seconds +50: Time to load utils op: 0.1355760097503662 seconds +50: Time to load utils op: 0.13557863235473633 secondsTime to load utils op: 0.13553357124328613 seconds +50: +50: Time to load utils op: 0.13553547859191895 seconds +50: Time to load utils op: 0.13561344146728516 seconds +52: Time to load utils op: 0.1341557502746582 seconds +48: Time to load utils op: 0.1352231502532959 secondsTime to load utils op: 0.1351916790008545 seconds +48: +52: Time to load utils op: 0.13446617126464844 seconds +48: Time to load utils op: 0.13524842262268066 seconds +52: Time to load utils op: 0.13463735580444336 seconds +48: Time to load utils op: 0.13532447814941406 seconds +52: Time to load utils op: 0.13431215286254883 seconds +48: Time to load utils op: 0.13528180122375488 secondsTime to load utils op: 0.13531494140625 seconds +48: +48: Time to load utils op: 0.1352841854095459 seconds +52: Time to load utils op: 0.13441014289855957 seconds +52: Time to load utils op: 0.13420891761779785 seconds +59: Time to load utils op: 0.12096571922302246 secondsTime to load utils op: 0.12095832824707031 seconds +59: +48: Time to load utils op: 0.13530898094177246 seconds +52: Time to load utils op: 0.13454246520996094 seconds +52: Time to load utils op: 0.42532920837402344 seconds +59: Time to load utils op: 0.12098288536071777 seconds +59: Time to load utils op: 0.12104606628417969 seconds +59: Time to load utils op: 0.12102913856506348 secondsTime to load utils op: 0.12100505828857422 seconds +59: +59: Time to load utils op: 0.1210026741027832 seconds +59: Time to load utils op: 0.12102818489074707 seconds +55: Time to load utils op: 0.13164830207824707 seconds +55: Time to load utils op: 0.1308901309967041 seconds +55: Time to load utils op: 0.13145971298217773 seconds +55: Time to load utils op: 0.1310427188873291 seconds +55: Time to load utils op: 0.13230276107788086 secondsTime to load utils op: 0.13169431686401367 secondsTime to load utils op: 0.1318378448486328 seconds +55: +55: +55: Time to load utils op: 0.13124656677246094 seconds +63: Time to load utils op: 0.11678743362426758 seconds +58: Time to load utils op: 0.12807750701904297 secondsTime to load utils op: 0.12728357315063477 seconds +58: +46: Time to load utils op: 0.13867831230163574 seconds +46: Time to load utils op: 0.13866543769836426 seconds +56: Time to load utils op: 0.1304013729095459 seconds +56: Time to load utils op: 0.13011407852172852 seconds +51: Time to load utils op: 0.13232874870300293 seconds +63: Time to load utils op: 0.1167745590209961 seconds +58: Time to load utils op: 0.42293262481689453 seconds +46: Time to load utils op: 0.13863682746887207 seconds +46: Time to load utils op: 0.1386885643005371 seconds +56: Time to load utils op: 0.12969064712524414 secondsTime to load utils op: 0.12971925735473633 seconds +56: +63: Time to load utils op: 0.11678481101989746 seconds +58: Time to load utils op: 0.12833619117736816 seconds +51: Time to load utils op: 0.13233375549316406 seconds +46: Time to load utils op: 0.1386561393737793 secondsTime to load utils op: 0.13869976997375488 secondsTime to load utils op: 0.13866782188415527 seconds +46: +46: +56: Time to load utils op: 0.12971997261047363 seconds +56: Time to load utils op: 0.12972211837768555 seconds +63: Time to load utils op: 0.11679768562316895 secondsTime to load utils op: 0.11680197715759277 seconds +63: +58: Time to load utils op: 0.12827277183532715 secondsTime to load utils op: 0.127882719039917 seconds +58: +51: Time to load utils op: 0.13236355781555176 seconds +49: Time to load utils op: 0.1345529556274414 seconds +49: Time to load utils op: 0.13460993766784668 secondsTime to load utils op: 0.13456392288208008 seconds +49: +46: Time to load utils op: 0.13867855072021484 seconds +56: Time to load utils op: 0.12972283363342285 seconds +63: Time to load utils op: 0.11685371398925781 seconds +58: Time to load utils op: 0.12754344940185547 seconds +51: Time to load utils op: 0.13237667083740234 seconds +56: Time to load utils op: 0.42143964767456055 seconds +63: Time to load utils op: 0.11682271957397461 seconds +58: Time to load utils op: 0.1282486915588379 seconds +51: Time to load utils op: 0.13236689567565918 seconds +51: Time to load utils op: 0.1323847770690918 secondsTime to load utils op: 0.1323719024658203 seconds +51: +63: Time to load utils op: 0.11691093444824219 seconds +51: Time to load utils op: 0.13242268562316895 seconds +49: Time to load utils op: 0.13457703590393066 seconds +49: Time to load utils op: 0.13461637496948242 secondsTime to load utils op: 0.13464736938476562 seconds +49: +49: Time to load utils op: 0.13465595245361328 secondsTime to load utils op: 0.13465309143066406 seconds +49: +54: Time to load utils op: 0.12901997566223145 seconds +54: Time to load utils op: 0.1290137767791748 seconds +54: Time to load utils op: 0.12903213500976562 secondsTime to load utils op: 0.12905287742614746 seconds +54: Time to load utils op: 0.12899017333984375 seconds +54: +54: Time to load utils op: 0.12893176078796387 secondsTime to load utils op: 0.12900066375732422 seconds +54: +54: Time to load utils op: 0.1289975643157959 seconds +61: Time to load utils op: 0.1202857494354248 seconds +61: Time to load utils op: 0.1202993392944336 seconds +61: Time to load utils op: 0.1203010082244873 seconds +61: Time to load utils op: 0.12030792236328125 seconds +61: Time to load utils op: 0.1203620433807373 seconds +61: Time to load utils op: 0.1203606128692627 secondsTime to load utils op: 0.12034344673156738 seconds +61: +61: Time to load utils op: 0.12032723426818848 seconds +62: Time to load utils op: 0.11821269989013672 secondsTime to load utils op: 0.11824631690979004 seconds +62: +62: Time to load utils op: 0.11828207969665527 seconds +62: Time to load utils op: 0.11830925941467285 seconds +62: Time to load utils op: 0.1183474063873291 secondsTime to load utils op: 0.11831498146057129 seconds +62: Time to load utils op: 0.11829352378845215 seconds +62: +62: Time to load utils op: 0.11836624145507812 seconds +57: Time to load utils op: 0.12591934204101562 secondsTime to load utils op: 0.12587738037109375 seconds +57: +57: Time to load utils op: 0.12588858604431152 seconds +57: Time to load utils op: 0.12591052055358887 seconds +57: Time to load utils op: 0.1259777545928955 seconds +57: Time to load utils op: 0.12597036361694336 seconds +57: Time to load utils op: 0.12599515914916992 seconds +57: Time to load utils op: 0.12596368789672852 seconds +60: Time to load utils op: 0.1263728141784668 secondsTime to load utils op: 0.12696576118469238 seconds +60: +60: Time to load utils op: 0.12635397911071777 seconds +60: Time to load utils op: 0.1264348030090332 seconds +60: Time to load utils op: 0.12710309028625488 secondsTime to load utils op: 0.12704706192016602 secondsTime to load utils op: 0.1269993782043457 secondsTime to load utils op: 0.1271505355834961 seconds +60: +60: +60: +32: Time to load utils op: 0.4099690914154053 seconds +44: Time to load utils op: 0.0005044937133789062 seconds +44: Time to load utils op: 0.0005233287811279297 secondsTime to load utils op: 0.0005192756652832031 seconds +44: +44: Time to load utils op: 0.00044035911560058594 seconds +44: Time to load utils op: 0.0006706714630126953 seconds +44: Time to load utils op: 0.0006680488586425781 secondsTime to load utils op: 0.0006725788116455078 seconds +44: +44: Time to load utils op: 0.0007240772247314453 seconds +33: Time to load utils op: 0.0006260871887207031 seconds +33: Time to load utils op: 0.0006089210510253906 seconds +33: Time to load utils op: 0.20255708694458008 seconds +33: Time to load utils op: 0.20210671424865723 seconds +33: Time to load utils op: 0.20173072814941406 seconds +33: Time to load utils op: 0.20175719261169434 seconds +33: Time to load utils op: 0.20257878303527832 seconds +33: Time to load utils op: 0.20187163352966309 seconds +32: Time to load utils op: 0.20231866836547852 seconds +32: Time to load utils op: 0.20236825942993164 secondsTime to load utils op: 0.20294904708862305 seconds +32: +32: Time to load utils op: 0.2023923397064209 seconds +32: Time to load utils op: 0.20341110229492188 seconds +32: Time to load utils op: 0.20342087745666504 seconds +32: Time to load utils op: 0.2027723789215088 seconds +40: Time to load utils op: 0.20284080505371094 seconds +40: Time to load utils op: 0.20228314399719238 seconds +40: Time to load utils op: 0.20236587524414062 seconds +40: Time to load utils op: 0.2030167579650879 seconds +40: Time to load utils op: 0.2035367488861084 seconds +40: Time to load utils op: 0.20294761657714844 seconds +40: Time to load utils op: 0.20316290855407715 seconds +42: Time to load utils op: 0.20291399955749512 seconds +42: Time to load utils op: 0.20318222045898438 seconds +41: Time to load utils op: 0.20523905754089355 seconds +42: Time to load utils op: 0.20353031158447266 seconds +41: Time to load utils op: 0.20495247840881348 seconds +42: Time to load utils op: 0.20373892784118652 secondsTime to load utils op: 0.2037339210510254 seconds +42: +41: Time to load utils op: 0.20526599884033203 seconds +42: Time to load utils op: 0.20403432846069336 seconds +41: Time to load utils op: 0.2050797939300537 seconds +42: Time to load utils op: 0.20406556129455566 seconds +41: Time to load utils op: 0.20563864707946777 secondsTime to load utils op: 0.2056417465209961 seconds +41: +41: Time to load utils op: 0.20583105087280273 seconds +39: Time to load utils op: 0.20948362350463867 secondsTime to load utils op: 0.209946870803833 secondsTime to load utils op: 0.5055770874023438 secondsTime to load utils op: 0.2093653678894043 secondsTime to load utils op: 0.20934557914733887 seconds +39: +39: +39: +39: +37: Time to load utils op: 0.21255064010620117 secondsTime to load utils op: 0.2122492790222168 seconds +37: +39: Time to load utils op: 0.2108614444732666 secondsTime to load utils op: 0.21045231819152832 seconds +39: +39: Time to load utils op: 0.20966482162475586 seconds +37: Time to load utils op: 0.21180200576782227 seconds +37: Time to load utils op: 0.2120833396911621 seconds +37: Time to load utils op: 0.21351218223571777 seconds +37: Time to load utils op: 0.21269750595092773 seconds +37: Time to load utils op: 0.21254777908325195 secondsTime to load utils op: 0.21267056465148926 seconds +37: +34: Time to load utils op: 0.21294522285461426 secondsTime to load utils op: 0.21297955513000488 seconds +34: +34: Time to load utils op: 0.21296906471252441 secondsTime to load utils op: 0.21298694610595703 seconds +34: +34: Time to load utils op: 0.21297025680541992 seconds +34: Time to load utils op: 0.21302056312561035 secondsTime to load utils op: 0.21303033828735352 seconds +35: Time to load utils op: 0.21289348602294922 seconds +35: Time to load utils op: 0.21290302276611328 seconds +34: +34: Time to load utils op: 0.21300005912780762 seconds +35: Time to load utils op: 0.2129344940185547 seconds +35: Time to load utils op: 0.21293425559997559 secondsTime to load utils op: 0.21295547485351562 seconds +35: +35: Time to load utils op: 0.21299314498901367 seconds +35: Time to load utils op: 0.21300172805786133 secondsTime to load utils op: 0.21297240257263184 seconds +35: +36: Time to load utils op: 0.2120661735534668 seconds +36: Time to load utils op: 0.21206879615783691 seconds +36: Time to load utils op: 0.21210479736328125 seconds +36: Time to load utils op: 0.2120976448059082 seconds +36: Time to load utils op: 0.21210265159606934 secondsTime to load utils op: 0.21214985847473145 seconds +36: Time to load utils op: 0.21216726303100586 seconds +36: +36: Time to load utils op: 0.21211576461791992 seconds +33: Time to load utils op: 0.00038695335388183594 seconds +33: Time to load utils op: 0.0003898143768310547 secondsTime to load utils op: 0.00040149688720703125 seconds +33: +33: Time to load utils op: 0.0003619194030761719 seconds +33: Time to load utils op: 0.00039768218994140625 seconds +33: Time to load utils op: 0.00036525726318359375 seconds +62: Time to load utils op: 0.0010502338409423828 seconds +52: Time to load utils op: 0.0009930133819580078 seconds +48: Time to load utils op: 0.0008666515350341797 seconds +38: Time to load utils op: 0.21187448501586914 secondsTime to load utils op: 0.21191000938415527 seconds +38: +48: Time to load utils op: 0.0008172988891601562 seconds +52: Time to load utils op: 0.0011355876922607422 seconds +38: Time to load utils op: 0.21191048622131348 seconds +38: Time to load utils op: 0.21189665794372559 seconds +38: Time to load utils op: 0.2118816375732422 seconds +38: Time to load utils op: 0.21190452575683594 secondsTime to load utils op: 0.21193480491638184 seconds +38: +38: Time to load utils op: 0.21190714836120605 seconds +48: Time to load utils op: 0.0009915828704833984 seconds +62: Time to load utils op: 0.0013873577117919922 seconds +62: Time to load utils op: 0.001355886459350586 seconds +62: Time to load utils op: 0.0013942718505859375 seconds +62: Time to load utils op: 0.001348257064819336 seconds +62: Time to load utils op: 0.001317739486694336 seconds +62: Time to load utils op: 0.0013213157653808594 seconds +62: Time to load utils op: 0.0013713836669921875 seconds +48: Time to load utils op: 0.0011072158813476562 seconds +52: Time to load utils op: 0.0014243125915527344 secondsTime to load utils op: 0.0014002323150634766 seconds +52: +48: Time to load utils op: 0.001194000244140625 seconds +48: Time to load utils op: 0.0012373924255371094 seconds +48: Time to load utils op: 0.0011744499206542969 seconds +52: Time to load utils op: 0.0014460086822509766 seconds +52: Time to load utils op: 0.0014472007751464844 seconds +48: Time to load utils op: 0.0011675357818603516 seconds +52: Time to load utils op: 0.001390695571899414 seconds +52: Time to load utils op: 0.0015227794647216797 seconds +53: Time to load utils op: 0.0005242824554443359 seconds +53: Time to load utils op: 0.0005655288696289062 seconds +53: Time to load utils op: 0.0005543231964111328 seconds +53: Time to load utils op: 0.0005636215209960938 seconds +53: Time to load utils op: 0.0006287097930908203 secondsTime to load utils op: 0.0005733966827392578 secondsTime to load utils op: 0.0006358623504638672 secondsTime to load utils op: 0.0006039142608642578 seconds +53: +53: +53: +41: Time to load utils op: 0.00047850608825683594 seconds +41: Time to load utils op: 0.0004978179931640625 seconds +41: Time to load utils op: 0.0003724098205566406 seconds +41: Time to load utils op: 0.0005164146423339844 seconds +41: Time to load utils op: 0.00044035911560058594 seconds +41: Time to load utils op: 0.0005552768707275391 secondsTime to load utils op: 0.0005300045013427734 seconds +41: +59: Time to load utils op: 0.0006525516510009766 seconds +41: Time to load utils op: 0.000606536865234375 seconds +42: Time to load utils op: 0.0006034374237060547 secondsTime to load utils op: 0.0005810260772705078 seconds +42: +42: Time to load utils op: 0.0005986690521240234 secondsTime to load utils op: 0.0006155967712402344 secondsTime to load utils op: 0.0006234645843505859 seconds +42: +42: +42: Time to load utils op: 0.0006012916564941406 secondsTime to load utils op: 0.0006194114685058594 seconds +42: +59: Time to load utils op: 0.0008234977722167969 seconds +42: Time to load utils op: 0.00042748451232910156 seconds +59: Time to load utils op: 0.001001596450805664 seconds +59: Time to load utils op: 0.0011870861053466797 secondsTime to load utils op: 0.0010192394256591797 seconds +59: +59: Time to load utils op: 0.0011818408966064453 seconds +59: Time to load utils op: 0.0011746883392333984 seconds +59: Time to load utils op: 0.0012154579162597656 seconds +32: Time to load utils op: 0.0004930496215820312 secondsTime to load utils op: 0.0004897117614746094 seconds +32: +60: Time to load utils op: 0.0010175704956054688 seconds +58: Time to load utils op: 0.0005466938018798828 secondsTime to load utils op: 0.0005323886871337891 seconds +58: +58: Time to load utils op: 0.0005421638488769531 seconds +60: Time to load utils op: 0.0011601448059082031 seconds +58: Time to load utils op: 0.0005035400390625 seconds +58: Time to load utils op: 0.0005800724029541016 seconds +45: Time to load utils op: 0.0011093616485595703 seconds +58: Time to load utils op: 0.0005145072937011719 seconds +60: Time to load utils op: 0.0012547969818115234 seconds +58: Time to load utils op: 0.0005805492401123047 seconds +58: Time to load utils op: 0.0005624294281005859 seconds +60: Time to load utils op: 0.0013227462768554688 seconds +45: Time to load utils op: 0.001226663589477539 seconds +60: Time to load utils op: 0.0014185905456542969 seconds +60: Time to load utils op: 0.0014390945434570312 seconds +60: Time to load utils op: 0.0014274120330810547 seconds +60: Time to load utils op: 0.0014181137084960938 seconds +45: Time to load utils op: 0.001445770263671875 seconds +45: Time to load utils op: 0.0014696121215820312 seconds +45: Time to load utils op: 0.001405477523803711 seconds +56: Time to load utils op: 0.0005061626434326172 seconds +45: Time to load utils op: 0.0014069080352783203 secondsTime to load utils op: 0.0014023780822753906 seconds +45: +45: Time to load utils op: 0.0013773441314697266 seconds +40: Time to load utils op: 0.0004620552062988281 seconds +56: Time to load utils op: 0.0005748271942138672 secondsTime to load utils op: 0.0005447864532470703 secondsTime to load utils op: 0.0005695819854736328 seconds +56: +56: +56: Time to load utils op: 0.0004582405090332031 secondsTime to load utils op: 0.00047898292541503906 seconds +56: +56: Time to load utils op: 0.00047135353088378906 seconds +40: Time to load utils op: 0.00040912628173828125 seconds +56: Time to load utils op: 0.0004904270172119141 seconds +49: Time to load utils op: 0.001020193099975586 seconds +40: Time to load utils op: 0.00039458274841308594 seconds +40: Time to load utils op: 0.0003921985626220703 seconds +40: Time to load utils op: 0.00048470497131347656 seconds +40: Time to load utils op: 0.0003960132598876953 seconds +40: Time to load utils op: 0.00048422813415527344 seconds +40: Time to load utils op: 0.0005311965942382812 seconds +49: Time to load utils op: 0.00133514404296875 seconds +49: Time to load utils op: 0.0012259483337402344 seconds +49: Time to load utils op: 0.0012712478637695312 seconds +46: Time to load utils op: 0.000820159912109375 seconds +49: Time to load utils op: 0.0012884140014648438 seconds +49: Time to load utils op: 0.0012865066528320312 seconds +49: Time to load utils op: 0.001262664794921875 seconds +46: Time to load utils op: 0.0010118484497070312 seconds +49: Time to load utils op: 0.0012810230255126953 seconds +46: Time to load utils op: 0.0009677410125732422 seconds +51: Time to load utils op: 0.0008959770202636719 seconds +51: Time to load utils op: 0.0008409023284912109 seconds +51: Time to load utils op: 0.0009059906005859375 seconds +46: Time to load utils op: 0.001161813735961914 seconds +61: Time to load utils op: 0.001055002212524414 seconds +46: Time to load utils op: 0.0011975765228271484 seconds +46: Time to load utils op: 0.001142740249633789 seconds +51: Time to load utils op: 0.0009937286376953125 seconds +46: Time to load utils op: 0.0011484622955322266 secondsTime to load utils op: 0.0012102127075195312 seconds +46: +51: Time to load utils op: 0.0010845661163330078 seconds +51: Time to load utils op: 0.0012805461883544922 seconds +51: Time to load utils op: 0.0012595653533935547 seconds +61: Time to load utils op: 0.0013172626495361328 seconds +61: Time to load utils op: 0.0012197494506835938 seconds +51: Time to load utils op: 0.0012454986572265625 seconds +63: Time to load utils op: 0.0008172988891601562 seconds +61: Time to load utils op: 0.0014538764953613281 seconds +61: Time to load utils op: 0.0013875961303710938 seconds +61: Time to load utils op: 0.0014603137969970703 seconds +61: Time to load utils op: 0.001384735107421875 seconds +61: Time to load utils op: 0.0014505386352539062 seconds +63: Time to load utils op: 0.0011036396026611328 seconds +63: Time to load utils op: 0.0012979507446289062 seconds +63: Time to load utils op: 0.0012631416320800781 seconds +63: Time to load utils op: 0.0007081031799316406 secondsTime to load utils op: 0.0013287067413330078 seconds +63: +63: Time to load utils op: 0.0012590885162353516 seconds +55: Time to load utils op: 0.0009179115295410156 seconds +63: Time to load utils op: 0.0013353824615478516 seconds +55: Time to load utils op: 0.0012099742889404297 seconds +55: Time to load utils op: 0.0014081001281738281 seconds +55: Time to load utils op: 0.0014243125915527344 seconds +55: Time to load utils op: 0.0014240741729736328 secondsTime to load utils op: 0.0013823509216308594 seconds +55: +55: Time to load utils op: 0.0014350414276123047 seconds +55: Time to load utils op: 0.0014913082122802734 seconds +50: Time to load utils op: 0.0004975795745849609 seconds +50: Time to load utils op: 0.0004673004150390625 secondsTime to load utils op: 0.0005118846893310547 seconds +50: +50: Time to load utils op: 0.0005426406860351562 secondsTime to load utils op: 0.0005543231964111328 seconds +50: Time to load utils op: 0.0005252361297607422 seconds +50: +50: Time to load utils op: 0.000545501708984375 seconds +50: Time to load utils op: 0.0005447864532470703 seconds +57: Time to load utils op: 0.0011723041534423828 seconds +57: Time to load utils op: 0.0013892650604248047 seconds +57: Time to load utils op: 0.0013077259063720703 seconds +57: Time to load utils op: 0.0012974739074707031 seconds +57: Time to load utils op: 0.0013761520385742188 seconds +57: Time to load utils op: 0.0013027191162109375 seconds +57: Time to load utils op: 0.001333475112915039 seconds +57: Time to load utils op: 0.0013971328735351562 seconds +43: Time to load utils op: 0.0011012554168701172 seconds +47: Time to load utils op: 0.0010819435119628906 seconds +47: Time to load utils op: 0.0009851455688476562 seconds +43: Time to load utils op: 0.0015087127685546875 seconds +43: Time to load utils op: 0.0015006065368652344 secondsTime to load utils op: 0.0015342235565185547 seconds +43: +43: Time to load utils op: 0.0015223026275634766 secondsTime to load utils op: 0.0015239715576171875 secondsTime to load utils op: 0.0015287399291992188 seconds +43: +43: +43: Time to load utils op: 0.0015752315521240234 seconds +47: Time to load utils op: 0.0013077259063720703 seconds +47: Time to load utils op: 0.0012171268463134766 seconds +47: Time to load utils op: 0.001237630844116211 seconds +47: Time to load utils op: 0.0012230873107910156 secondsTime to load utils op: 0.0012123584747314453 seconds +47: +47: Time to load utils op: 0.0012552738189697266 seconds +54: Time to load utils op: 0.0011663436889648438 seconds +54: Time to load utils op: 0.001074075698852539 seconds +54: Time to load utils op: 0.001172780990600586 seconds +54: Time to load utils op: 0.001306772232055664 seconds +54: Time to load utils op: 0.00128936767578125 seconds +54: Time to load utils op: 0.0012712478637695312 seconds +54: Time to load utils op: 0.001253366470336914 seconds +54: Time to load utils op: 0.0013759136199951172 seconds +32: Time to load utils op: 0.0004799365997314453 secondsTime to load utils op: 0.0004820823669433594 seconds +32: Time to load utils op: 0.00046324729919433594 seconds +32: Time to load utils op: 0.00048232078552246094 seconds +32: +32: Time to load utils op: 0.0004951953887939453 secondsTime to load utils op: 0.00047016143798828125 seconds +32: +38: Time to load utils op: 0.0011336803436279297 seconds +38: Time to load utils op: 0.0011248588562011719 seconds +38: Time to load utils op: 0.001226663589477539 seconds +38: Time to load utils op: 0.0012640953063964844 seconds +38: Time to load utils op: 0.0012688636779785156 seconds +38: Time to load utils op: 0.001318216323852539 seconds +38: Time to load utils op: 0.001302480697631836 seconds +38: Time to load utils op: 0.0013079643249511719 seconds +34: Time to load utils op: 0.0009796619415283203 seconds +34: Time to load utils op: 0.0010809898376464844 seconds +34: Time to load utils op: 0.0013921260833740234 seconds +34: Time to load utils op: 0.0013315677642822266 seconds +34: Time to load utils op: 0.0013415813446044922 seconds +34: Time to load utils op: 0.0013499259948730469 seconds +34: Time to load utils op: 0.0013549327850341797 seconds +34: Time to load utils op: 0.001382589340209961 seconds +36: Time to load utils op: 0.0007212162017822266 seconds +36: Time to load utils op: 0.0009589195251464844 seconds +36: Time to load utils op: 0.0009031295776367188 seconds +36: Time to load utils op: 0.0010762214660644531 seconds +39: Time to load utils op: 0.0005707740783691406 seconds +36: Time to load utils op: 0.0011188983917236328 seconds +36: Time to load utils op: 0.001140594482421875 secondsTime to load utils op: 0.0011448860168457031 seconds +39: Time to load utils op: 0.0005996227264404297 secondsTime to load utils op: 0.0006172657012939453 seconds +39: +39: Time to load utils op: 0.0005960464477539062 seconds +39: Time to load utils op: 0.0005753040313720703 seconds +36: +39: Time to load utils op: 0.0006299018859863281 seconds +39: Time to load utils op: 0.0006084442138671875 seconds +39: Time to load utils op: 0.0006694793701171875 seconds +36: Time to load utils op: 0.0011439323425292969 seconds + 0: [2022-12-01 11:40:15,122] [INFO] [engine.py:145:__init__] RANK=0 STAGE=0 LAYERS=21 [0, 21) STAGE_PARAMS=2026914560 (2026.915M) TOTAL_PARAMS=4053835008 (4053.835M) UNIQUE_PARAMS=3899710720 (3899.711M) +32: [2022-12-01 11:40:15,123] [INFO] [engine.py:145:__init__] RANK=256 STAGE=1 LAYERS=22 [21, 43) STAGE_PARAMS=2026920448 (2026.920M) TOTAL_PARAMS=4053835008 (4053.835M) UNIQUE_PARAMS=3899710720 (3899.711M) +37: Time to load utils op: 0.0009222030639648438 seconds +35: Time to load utils op: 0.000713348388671875 seconds +35: Time to load utils op: 0.0008418560028076172 seconds +37: Time to load utils op: 0.001081228256225586 seconds +35: Time to load utils op: 0.0009047985076904297 seconds +35: Time to load utils op: 0.000888824462890625 seconds +35: Time to load utils op: 0.0010306835174560547 seconds +35: Time to load utils op: 0.0009999275207519531 seconds +35: Time to load utils op: 0.0009875297546386719 seconds +37: Time to load utils op: 0.0012073516845703125 secondsTime to load utils op: 0.0011761188507080078 seconds +37: +35: Time to load utils op: 0.0010535717010498047 seconds +37: Time to load utils op: 0.0011975765228271484 seconds +37: Time to load utils op: 0.0012407302856445312 secondsTime to load utils op: 0.0012197494506835938 seconds +37: +37: Time to load utils op: 0.001222372055053711 seconds + 0: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: WARNING: could not find the metadata file checkpoints_3b977boscar + 0: will not load any checkpoints and will start from random + 0: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +48: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +56: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +32: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +60: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +63: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +62: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +32: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +32: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +40: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +32: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +16: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +24: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +48: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +56: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +61: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +63: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +59: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +28: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +62: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +60: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +46: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +54: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +52: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +58: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +44: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +32: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +55: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +47: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +32: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +43: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +40: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +36: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +39: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +53: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +29: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +38: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +57: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +57: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +57: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +59: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +28: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +48: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +50: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +60: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +42: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +57: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +56: [2022-12-01 11:40:17,507] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +63: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +36: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +32: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +32: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +16: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +24: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +62: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +34: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +37: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +57: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +35: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +46: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +40: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +54: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +44: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +51: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +57: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +61: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +58: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +60: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +47: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +41: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +55: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +45: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +16: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +52: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +63: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +56: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +28: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +53: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +50: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +29: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +42: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +33: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +33: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +33: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +49: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +37: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +57: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +57: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +33: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +59: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +62: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +44: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +48: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +34: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +43: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +35: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +39: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +60: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +46: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +55: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +54: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +61: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +33: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +58: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +38: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +36: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +41: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +45: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +47: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +33: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +33: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +24: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +63: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +51: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +16: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +52: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +53: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +59: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +37: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +40: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +56: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +48: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +34: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +35: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +60: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +29: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +42: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +50: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +36: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +63: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +33: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +58: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +43: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +39: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +49: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +46: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +55: [2022-12-01 11:40:17,508] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +38: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +44: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +45: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +61: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +59: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +28: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +62: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +60: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +40: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +56: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +48: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +54: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +51: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +34: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +41: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +16: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +24: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +37: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +29: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +58: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +40: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +42: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +35: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +59: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +43: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +46: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +62: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +44: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +60: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +52: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +53: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +38: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +49: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +63: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +39: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +55: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +56: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +34: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +51: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +24: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +54: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +61: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +28: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +48: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +50: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +41: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +45: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +35: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +40: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +59: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +16: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +37: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +58: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +36: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +47: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +52: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +53: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +62: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +38: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +43: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +46: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +44: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +34: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +39: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +50: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +29: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +61: [2022-12-01 11:40:17,509] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +28: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +48: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +35: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +45: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +42: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +63: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +59: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +16: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +54: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +49: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +55: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +40: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +52: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +41: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +62: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +51: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +47: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +24: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +37: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +38: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +36: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +53: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +58: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +35: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +56: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +34: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +44: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +39: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +61: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +43: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +46: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +16: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +45: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +42: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +54: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +52: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +28: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +50: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +49: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +55: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +29: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +37: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +53: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +38: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +35: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +47: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +34: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +41: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +44: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +36: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +39: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +51: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +24: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +58: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +42: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +37: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +38: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +54: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +49: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +46: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +55: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +47: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +52: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +53: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +28: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +43: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +36: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +41: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +29: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +45: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +24: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +61: [2022-12-01 11:40:17,510] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +39: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +50: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +51: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +42: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +43: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +49: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +41: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +47: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +51: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +29: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +45: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +50: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +49: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-12-01 11:40:17,511] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_3b977boscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +63: time (ms) | load-checkpoint: 15.15 + 0: estimated model parameters: 4.05382912 + 0: estimated model parameters without embeddings: 3.745580544 + 0: [after model, optimizer, and learning rate scheduler are built] datetime: 2022-12-01 11:40:18 + 0: > building train, validation, and test datasets ... + 0: > datasets target sizes (minimum size): + 0: train: 37792969 + 0: validation: 37888 + 0: test: 512 + 0: > building train, validation, and test datasets for GPT ... + 0: > building dataset index ... + 0: reading sizes... + 0: reading pointers... + 0: reading document index... + 0: creating numpy buffer of mmap... + 0: creating memory view of numpy buffer... + 0: > finished creating indexed dataset in 0.028187 seconds + 0: number of documents: 431992659 + 0: > dataset split: + 0: train: + 0: document indices in [0, 409961033) total of 409961033 documents + 0: validation: + 0: document indices in [409961033, 431560666) total of 21599633 documents + 0: test: + 0: document indices in [431560666, 431992659) total of 431993 documents + 0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_37792969ns_2048sl_1234s_doc_idx.npy + 0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_37792969ns_2048sl_1234s_sample_idx.npy + 0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_37792969ns_2048sl_1234s_shuffle_idx.npy + 0: loaded indexed file in 0.070 seconds + 0: total number of samples: 262636458 + 0: total number of epochs: 1 + 0: > WARNING: could not find index map files, building the indices on rank 0 ... + 0: > only one epoch required, setting separate_last_epoch to False + 0: > elasped time to build and save doc-idx mapping (seconds): 1.454449 + 0: using: + 0: number of documents: 21599633 + 0: number of epochs: 1 + 0: sequence length: 2048 + 0: total number of samples: 13852049 + 0: > elasped time to build and save sample-idx mapping (seconds): 0.481189 + 0: > building shuffle index with split [0, 13852049) and [13852049, 13852049) ... + 0: > elasped time to build and save shuffle-idx mapping (seconds): 0.482960 + 0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_37888ns_2048sl_1234s_doc_idx.npy + 0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_37888ns_2048sl_1234s_sample_idx.npy + 0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_37888ns_2048sl_1234s_shuffle_idx.npy + 0: loaded indexed file in 0.025 seconds + 0: total number of samples: 13852050 + 0: total number of epochs: 1 + 0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_512ns_2048sl_1234s_doc_idx.npy + 0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_512ns_2048sl_1234s_sample_idx.npy + 0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_512ns_2048sl_1234s_shuffle_idx.npy + 0: loaded indexed file in 0.080 seconds + 0: total number of samples: 276852 + 0: total number of epochs: 1 + 0: > finished creating GPT datasets ... + 0: [after dataloaders are built] datetime: 2022-12-01 11:40:54 + 0: done with setup ... + 0: training ... + 0: Number of parameters: [tensor rank - pipeline rank] w/ and w/o embeddings: +63: time (ms) | model-and-optimizer-setup: 47761.45 | train/valid/test-data-iterators-setup: 36095.13 +32: [000-001] 4.0538B / 3.7456B + 0: [000-000] 4.0538B / 3.7456B + 0: [before the start of training step] datetime: 2022-12-01 11:40:54 + 0: [Rank 0] (after 10 iterations) memory (MB) | allocated: 15589.80810546875 | max allocated: 46167.35498046875 | reserved: 49744.0 | max reserved: 49744.0 +63: iteration 10/ 73814 | consumed samples: 5120 | consumed tokens: 10485760 | elapsed time per iteration (s): 6.38 | learning rate: 2.709E-06 | global batch size: 512 | lm loss: 1.082458E+01 | grad norm: 106.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 80.273 | TFLOPs: 8.26 | +32: [Rank 256] (after 10 iterations) memory (MB) | allocated: 16405.80615234375 | max allocated: 32144.1962890625 | reserved: 38584.0 | max reserved: 38584.0 +63: iteration 20/ 73814 | consumed samples: 10240 | consumed tokens: 20971520 | elapsed time per iteration (s): 2.29 | learning rate: 5.419E-06 | global batch size: 512 | lm loss: 9.376541E+00 | grad norm: 11.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.485 | TFLOPs: 23.01 | +63: iteration 30/ 73814 | consumed samples: 15360 | consumed tokens: 31457280 | elapsed time per iteration (s): 2.24 | learning rate: 8.128E-06 | global batch size: 512 | lm loss: 8.822540E+00 | grad norm: 6.502 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.832 | TFLOPs: 23.56 | +63: iteration 40/ 73814 | consumed samples: 20480 | consumed tokens: 41943040 | elapsed time per iteration (s): 2.23 | learning rate: 1.084E-05 | global batch size: 512 | lm loss: 8.542800E+00 | grad norm: 7.887 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.102 | TFLOPs: 23.58 | +63: iteration 50/ 73814 | consumed samples: 25600 | consumed tokens: 52428800 | elapsed time per iteration (s): 2.25 | learning rate: 1.355E-05 | global batch size: 512 | lm loss: 8.213834E+00 | grad norm: 2.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.471 | TFLOPs: 23.42 | +63: iteration 60/ 73814 | consumed samples: 30720 | consumed tokens: 62914560 | elapsed time per iteration (s): 2.26 | learning rate: 1.626E-05 | global batch size: 512 | lm loss: 7.911785E+00 | grad norm: 3.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.560 | TFLOPs: 23.32 | +63: iteration 70/ 73814 | consumed samples: 35840 | consumed tokens: 73400320 | elapsed time per iteration (s): 2.25 | learning rate: 1.897E-05 | global batch size: 512 | lm loss: 7.651092E+00 | grad norm: 4.924 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.337 | TFLOPs: 23.40 | +63: iteration 80/ 73814 | consumed samples: 40960 | consumed tokens: 83886080 | elapsed time per iteration (s): 2.27 | learning rate: 2.168E-05 | global batch size: 512 | lm loss: 7.457419E+00 | grad norm: 3.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.847 | TFLOPs: 23.25 | +63: iteration 90/ 73814 | consumed samples: 46080 | consumed tokens: 94371840 | elapsed time per iteration (s): 2.29 | learning rate: 2.439E-05 | global batch size: 512 | lm loss: 7.305508E+00 | grad norm: 3.015 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.638 | TFLOPs: 23.02 | +63: iteration 100/ 73814 | consumed samples: 51200 | consumed tokens: 104857600 | elapsed time per iteration (s): 2.25 | learning rate: 2.709E-05 | global batch size: 512 | lm loss: 7.210305E+00 | grad norm: 4.666 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.243 | TFLOPs: 23.39 | +63: iteration 110/ 73814 | consumed samples: 56320 | consumed tokens: 115343360 | elapsed time per iteration (s): 2.26 | learning rate: 2.980E-05 | global batch size: 512 | lm loss: 7.097086E+00 | grad norm: 4.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.704 | TFLOPs: 23.34 | +63: iteration 120/ 73814 | consumed samples: 61440 | consumed tokens: 125829120 | elapsed time per iteration (s): 2.25 | learning rate: 3.251E-05 | global batch size: 512 | lm loss: 6.959027E+00 | grad norm: 3.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.336 | TFLOPs: 23.40 | +63: iteration 130/ 73814 | consumed samples: 66560 | consumed tokens: 136314880 | elapsed time per iteration (s): 2.27 | learning rate: 3.522E-05 | global batch size: 512 | lm loss: 6.899335E+00 | grad norm: 1.849 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.204 | TFLOPs: 23.18 | +63: iteration 140/ 73814 | consumed samples: 71680 | consumed tokens: 146800640 | elapsed time per iteration (s): 2.24 | learning rate: 3.793E-05 | global batch size: 512 | lm loss: 6.817669E+00 | grad norm: 3.628 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.492 | TFLOPs: 23.52 | +63: iteration 150/ 73814 | consumed samples: 76800 | consumed tokens: 157286400 | elapsed time per iteration (s): 2.32 | learning rate: 4.064E-05 | global batch size: 512 | lm loss: 6.735748E+00 | grad norm: 2.540 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.567 | TFLOPs: 22.71 | +63: iteration 160/ 73814 | consumed samples: 81920 | consumed tokens: 167772160 | elapsed time per iteration (s): 2.29 | learning rate: 4.335E-05 | global batch size: 512 | lm loss: 6.651645E+00 | grad norm: 1.551 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.554 | TFLOPs: 23.01 | +63: iteration 170/ 73814 | consumed samples: 87040 | consumed tokens: 178257920 | elapsed time per iteration (s): 2.24 | learning rate: 4.606E-05 | global batch size: 512 | lm loss: 6.594221E+00 | grad norm: 1.831 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.317 | TFLOPs: 23.50 | +63: iteration 180/ 73814 | consumed samples: 92160 | consumed tokens: 188743680 | elapsed time per iteration (s): 2.28 | learning rate: 4.877E-05 | global batch size: 512 | lm loss: 6.544823E+00 | grad norm: 1.473 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.938 | TFLOPs: 23.16 | +63: iteration 190/ 73814 | consumed samples: 97280 | consumed tokens: 199229440 | elapsed time per iteration (s): 2.26 | learning rate: 5.148E-05 | global batch size: 512 | lm loss: 6.466557E+00 | grad norm: 2.007 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.658 | TFLOPs: 23.33 | +63: iteration 200/ 73814 | consumed samples: 102400 | consumed tokens: 209715200 | elapsed time per iteration (s): 2.26 | learning rate: 5.419E-05 | global batch size: 512 | lm loss: 6.407451E+00 | grad norm: 2.601 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.754 | TFLOPs: 23.34 | +63: iteration 210/ 73814 | consumed samples: 107520 | consumed tokens: 220200960 | elapsed time per iteration (s): 2.24 | learning rate: 5.690E-05 | global batch size: 512 | lm loss: 6.355247E+00 | grad norm: 1.368 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.430 | TFLOPs: 23.52 | +63: iteration 220/ 73814 | consumed samples: 112640 | consumed tokens: 230686720 | elapsed time per iteration (s): 2.27 | learning rate: 5.961E-05 | global batch size: 512 | lm loss: 6.305715E+00 | grad norm: 2.423 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.715 | TFLOPs: 23.24 | +63: iteration 230/ 73814 | consumed samples: 117760 | consumed tokens: 241172480 | elapsed time per iteration (s): 2.27 | learning rate: 6.232E-05 | global batch size: 512 | lm loss: 6.277489E+00 | grad norm: 1.734 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.894 | TFLOPs: 23.25 | +63: iteration 240/ 73814 | consumed samples: 122880 | consumed tokens: 251658240 | elapsed time per iteration (s): 2.26 | learning rate: 6.503E-05 | global batch size: 512 | lm loss: 6.223585E+00 | grad norm: 1.742 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.896 | TFLOPs: 23.36 | +63: iteration 250/ 73814 | consumed samples: 128000 | consumed tokens: 262144000 | elapsed time per iteration (s): 2.26 | learning rate: 6.774E-05 | global batch size: 512 | lm loss: 6.184647E+00 | grad norm: 1.433 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.232 | TFLOPs: 23.29 | +63: iteration 260/ 73814 | consumed samples: 133120 | consumed tokens: 272629760 | elapsed time per iteration (s): 2.26 | learning rate: 7.045E-05 | global batch size: 512 | lm loss: 6.162161E+00 | grad norm: 1.880 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.699 | TFLOPs: 23.34 | +63: iteration 270/ 73814 | consumed samples: 138240 | consumed tokens: 283115520 | elapsed time per iteration (s): 2.24 | learning rate: 7.316E-05 | global batch size: 512 | lm loss: 6.121986E+00 | grad norm: 1.392 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.826 | TFLOPs: 23.56 | +63: iteration 280/ 73814 | consumed samples: 143360 | consumed tokens: 293601280 | elapsed time per iteration (s): 2.32 | learning rate: 7.587E-05 | global batch size: 512 | lm loss: 6.107367E+00 | grad norm: 1.518 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.918 | TFLOPs: 22.74 | +63: iteration 290/ 73814 | consumed samples: 148480 | consumed tokens: 304087040 | elapsed time per iteration (s): 2.24 | learning rate: 7.858E-05 | global batch size: 512 | lm loss: 6.065410E+00 | grad norm: 1.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.080 | TFLOPs: 23.48 | +63: iteration 300/ 73814 | consumed samples: 153600 | consumed tokens: 314572800 | elapsed time per iteration (s): 2.24 | learning rate: 8.128E-05 | global batch size: 512 | lm loss: 6.041515E+00 | grad norm: 1.463 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.729 | TFLOPs: 23.55 | +63: iteration 310/ 73814 | consumed samples: 158720 | consumed tokens: 325058560 | elapsed time per iteration (s): 2.24 | learning rate: 8.399E-05 | global batch size: 512 | lm loss: 5.987265E+00 | grad norm: 1.437 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.356 | TFLOPs: 23.51 | +63: iteration 320/ 73814 | consumed samples: 163840 | consumed tokens: 335544320 | elapsed time per iteration (s): 2.25 | learning rate: 8.670E-05 | global batch size: 512 | lm loss: 5.954240E+00 | grad norm: 1.071 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.186 | TFLOPs: 23.39 | +63: iteration 330/ 73814 | consumed samples: 168960 | consumed tokens: 346030080 | elapsed time per iteration (s): 2.24 | learning rate: 8.941E-05 | global batch size: 512 | lm loss: 5.922803E+00 | grad norm: 1.672 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.527 | TFLOPs: 23.53 | +63: iteration 340/ 73814 | consumed samples: 174080 | consumed tokens: 356515840 | elapsed time per iteration (s): 2.25 | learning rate: 9.212E-05 | global batch size: 512 | lm loss: 5.881100E+00 | grad norm: 1.745 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.079 | TFLOPs: 23.38 | +63: iteration 350/ 73814 | consumed samples: 179200 | consumed tokens: 367001600 | elapsed time per iteration (s): 2.23 | learning rate: 9.483E-05 | global batch size: 512 | lm loss: 5.858498E+00 | grad norm: 1.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.234 | TFLOPs: 23.60 | +63: iteration 360/ 73814 | consumed samples: 184320 | consumed tokens: 377487360 | elapsed time per iteration (s): 2.26 | learning rate: 9.754E-05 | global batch size: 512 | lm loss: 5.821947E+00 | grad norm: 1.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.660 | TFLOPs: 23.33 | +63: iteration 370/ 73814 | consumed samples: 189440 | consumed tokens: 387973120 | elapsed time per iteration (s): 2.24 | learning rate: 1.003E-04 | global batch size: 512 | lm loss: 5.798786E+00 | grad norm: 1.746 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.487 | TFLOPs: 23.52 | +63: iteration 380/ 73814 | consumed samples: 194560 | consumed tokens: 398458880 | elapsed time per iteration (s): 2.24 | learning rate: 1.030E-04 | global batch size: 512 | lm loss: 5.749462E+00 | grad norm: 0.933 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.492 | TFLOPs: 23.52 | +63: iteration 390/ 73814 | consumed samples: 199680 | consumed tokens: 408944640 | elapsed time per iteration (s): 2.27 | learning rate: 1.057E-04 | global batch size: 512 | lm loss: 5.713268E+00 | grad norm: 1.488 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.915 | TFLOPs: 23.26 | +63: iteration 400/ 73814 | consumed samples: 204800 | consumed tokens: 419430400 | elapsed time per iteration (s): 2.25 | learning rate: 1.084E-04 | global batch size: 512 | lm loss: 5.709724E+00 | grad norm: 1.520 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.037 | TFLOPs: 23.48 | +63: iteration 410/ 73814 | consumed samples: 209920 | consumed tokens: 429916160 | elapsed time per iteration (s): 2.23 | learning rate: 1.111E-04 | global batch size: 512 | lm loss: 5.651255E+00 | grad norm: 0.894 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.515 | TFLOPs: 23.63 | +63: iteration 420/ 73814 | consumed samples: 215040 | consumed tokens: 440401920 | elapsed time per iteration (s): 2.26 | learning rate: 1.138E-04 | global batch size: 512 | lm loss: 5.621982E+00 | grad norm: 1.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.528 | TFLOPs: 23.32 | +63: iteration 430/ 73814 | consumed samples: 220160 | consumed tokens: 450887680 | elapsed time per iteration (s): 2.66 | learning rate: 1.165E-04 | global batch size: 512 | lm loss: 5.554871E+00 | grad norm: 1.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 192.137 | TFLOPs: 19.78 | +63: iteration 440/ 73814 | consumed samples: 225280 | consumed tokens: 461373440 | elapsed time per iteration (s): 2.25 | learning rate: 1.192E-04 | global batch size: 512 | lm loss: 5.541079E+00 | grad norm: 1.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.966 | TFLOPs: 23.47 | +63: iteration 450/ 73814 | consumed samples: 230400 | consumed tokens: 471859200 | elapsed time per iteration (s): 2.25 | learning rate: 1.219E-04 | global batch size: 512 | lm loss: 5.514816E+00 | grad norm: 1.053 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.085 | TFLOPs: 23.38 | +63: iteration 460/ 73814 | consumed samples: 235520 | consumed tokens: 482344960 | elapsed time per iteration (s): 2.23 | learning rate: 1.246E-04 | global batch size: 512 | lm loss: 5.472031E+00 | grad norm: 1.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.191 | TFLOPs: 23.59 | +63: iteration 470/ 73814 | consumed samples: 240640 | consumed tokens: 492830720 | elapsed time per iteration (s): 2.26 | learning rate: 1.273E-04 | global batch size: 512 | lm loss: 5.430584E+00 | grad norm: 1.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.966 | TFLOPs: 23.37 | +63: iteration 480/ 73814 | consumed samples: 245760 | consumed tokens: 503316480 | elapsed time per iteration (s): 2.24 | learning rate: 1.301E-04 | global batch size: 512 | lm loss: 5.398465E+00 | grad norm: 0.925 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.128 | TFLOPs: 23.48 | +63: iteration 490/ 73814 | consumed samples: 250880 | consumed tokens: 513802240 | elapsed time per iteration (s): 2.23 | learning rate: 1.328E-04 | global batch size: 512 | lm loss: 5.346005E+00 | grad norm: 0.941 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.433 | TFLOPs: 23.62 | +63: iteration 500/ 73814 | consumed samples: 256000 | consumed tokens: 524288000 | elapsed time per iteration (s): 2.26 | learning rate: 1.355E-04 | global batch size: 512 | lm loss: 5.319405E+00 | grad norm: 1.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.258 | TFLOPs: 23.29 | +63: iteration 510/ 73814 | consumed samples: 261120 | consumed tokens: 534773760 | elapsed time per iteration (s): 2.25 | learning rate: 1.382E-04 | global batch size: 512 | lm loss: 5.290100E+00 | grad norm: 1.662 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.154 | TFLOPs: 23.38 | +63: iteration 520/ 73814 | consumed samples: 266240 | consumed tokens: 545259520 | elapsed time per iteration (s): 2.23 | learning rate: 1.409E-04 | global batch size: 512 | lm loss: 5.218536E+00 | grad norm: 0.754 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.118 | TFLOPs: 23.59 | +63: iteration 530/ 73814 | consumed samples: 271360 | consumed tokens: 555745280 | elapsed time per iteration (s): 2.24 | learning rate: 1.436E-04 | global batch size: 512 | lm loss: 5.207651E+00 | grad norm: 1.497 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.664 | TFLOPs: 23.54 | +63: iteration 540/ 73814 | consumed samples: 276480 | consumed tokens: 566231040 | elapsed time per iteration (s): 2.23 | learning rate: 1.463E-04 | global batch size: 512 | lm loss: 5.134875E+00 | grad norm: 1.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.291 | TFLOPs: 23.60 | +63: iteration 550/ 73814 | consumed samples: 281600 | consumed tokens: 576716800 | elapsed time per iteration (s): 2.24 | learning rate: 1.490E-04 | global batch size: 512 | lm loss: 5.111858E+00 | grad norm: 1.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.834 | TFLOPs: 23.56 | +63: iteration 560/ 73814 | consumed samples: 286720 | consumed tokens: 587202560 | elapsed time per iteration (s): 2.26 | learning rate: 1.517E-04 | global batch size: 512 | lm loss: 5.056441E+00 | grad norm: 0.971 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.161 | TFLOPs: 23.28 | +63: iteration 570/ 73814 | consumed samples: 291840 | consumed tokens: 597688320 | elapsed time per iteration (s): 2.26 | learning rate: 1.544E-04 | global batch size: 512 | lm loss: 5.036073E+00 | grad norm: 0.754 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.391 | TFLOPs: 23.31 | +63: iteration 580/ 73814 | consumed samples: 296960 | consumed tokens: 608174080 | elapsed time per iteration (s): 2.28 | learning rate: 1.572E-04 | global batch size: 512 | lm loss: 4.988589E+00 | grad norm: 0.802 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.136 | TFLOPs: 23.07 | +63: iteration 590/ 73814 | consumed samples: 302080 | consumed tokens: 618659840 | elapsed time per iteration (s): 2.33 | learning rate: 1.599E-04 | global batch size: 512 | lm loss: 4.918135E+00 | grad norm: 0.900 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.650 | TFLOPs: 22.61 | +63: iteration 600/ 73814 | consumed samples: 307200 | consumed tokens: 629145600 | elapsed time per iteration (s): 2.32 | learning rate: 1.626E-04 | global batch size: 512 | lm loss: 4.892681E+00 | grad norm: 0.876 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.870 | TFLOPs: 22.74 | +63: iteration 610/ 73814 | consumed samples: 312320 | consumed tokens: 639631360 | elapsed time per iteration (s): 2.31 | learning rate: 1.653E-04 | global batch size: 512 | lm loss: 4.869042E+00 | grad norm: 1.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.623 | TFLOPs: 22.81 | +63: iteration 620/ 73814 | consumed samples: 317440 | consumed tokens: 650117120 | elapsed time per iteration (s): 2.26 | learning rate: 1.680E-04 | global batch size: 512 | lm loss: 4.825233E+00 | grad norm: 0.969 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.808 | TFLOPs: 23.35 | +63: iteration 630/ 73814 | consumed samples: 322560 | consumed tokens: 660602880 | elapsed time per iteration (s): 2.29 | learning rate: 1.707E-04 | global batch size: 512 | lm loss: 4.744333E+00 | grad norm: 0.984 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.014 | TFLOPs: 23.06 | +63: iteration 640/ 73814 | consumed samples: 327680 | consumed tokens: 671088640 | elapsed time per iteration (s): 2.26 | learning rate: 1.734E-04 | global batch size: 512 | lm loss: 4.706239E+00 | grad norm: 1.730 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.481 | TFLOPs: 23.32 | +63: iteration 650/ 73814 | consumed samples: 332800 | consumed tokens: 681574400 | elapsed time per iteration (s): 2.31 | learning rate: 1.761E-04 | global batch size: 512 | lm loss: 4.700868E+00 | grad norm: 1.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.287 | TFLOPs: 22.78 | +63: iteration 660/ 73814 | consumed samples: 337920 | consumed tokens: 692060160 | elapsed time per iteration (s): 2.27 | learning rate: 1.788E-04 | global batch size: 512 | lm loss: 4.613201E+00 | grad norm: 0.984 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.391 | TFLOPs: 23.20 | +63: iteration 670/ 73814 | consumed samples: 343040 | consumed tokens: 702545920 | elapsed time per iteration (s): 2.24 | learning rate: 1.815E-04 | global batch size: 512 | lm loss: 4.506183E+00 | grad norm: 0.975 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.789 | TFLOPs: 23.55 | +63: iteration 680/ 73814 | consumed samples: 348160 | consumed tokens: 713031680 | elapsed time per iteration (s): 2.25 | learning rate: 1.842E-04 | global batch size: 512 | lm loss: 4.425256E+00 | grad norm: 0.774 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.575 | TFLOPs: 23.43 | +63: iteration 690/ 73814 | consumed samples: 353280 | consumed tokens: 723517440 | elapsed time per iteration (s): 2.25 | learning rate: 1.870E-04 | global batch size: 512 | lm loss: 4.320316E+00 | grad norm: 0.649 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.757 | TFLOPs: 23.45 | +63: iteration 700/ 73814 | consumed samples: 358400 | consumed tokens: 734003200 | elapsed time per iteration (s): 2.24 | learning rate: 1.897E-04 | global batch size: 512 | lm loss: 4.273073E+00 | grad norm: 1.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.079 | TFLOPs: 23.58 | +63: iteration 710/ 73814 | consumed samples: 363520 | consumed tokens: 744488960 | elapsed time per iteration (s): 2.23 | learning rate: 1.924E-04 | global batch size: 512 | lm loss: 4.300705E+00 | grad norm: 0.855 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.252 | TFLOPs: 23.60 | +63: iteration 720/ 73814 | consumed samples: 368640 | consumed tokens: 754974720 | elapsed time per iteration (s): 2.23 | learning rate: 1.951E-04 | global batch size: 512 | lm loss: 4.268408E+00 | grad norm: 0.914 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.453 | TFLOPs: 23.62 | +63: iteration 730/ 73814 | consumed samples: 373760 | consumed tokens: 765460480 | elapsed time per iteration (s): 2.25 | learning rate: 1.978E-04 | global batch size: 512 | lm loss: 4.249738E+00 | grad norm: 1.063 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.285 | TFLOPs: 23.40 | +63: iteration 740/ 73814 | consumed samples: 378880 | consumed tokens: 775946240 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 4.224942E+00 | grad norm: 0.643 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.730 | TFLOPs: 23.44 | +63: iteration 750/ 73814 | consumed samples: 384000 | consumed tokens: 786432000 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 4.096097E+00 | grad norm: 0.452 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.294 | TFLOPs: 23.60 | +63: iteration 760/ 73814 | consumed samples: 389120 | consumed tokens: 796917760 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 4.068512E+00 | grad norm: 0.390 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.803 | TFLOPs: 23.66 | +63: iteration 770/ 73814 | consumed samples: 394240 | consumed tokens: 807403520 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 4.009196E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.321 | TFLOPs: 23.61 | +63: iteration 780/ 73814 | consumed samples: 399360 | consumed tokens: 817889280 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.967502E+00 | grad norm: 0.491 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.024 | TFLOPs: 23.47 | +63: iteration 790/ 73814 | consumed samples: 404480 | consumed tokens: 828375040 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 4.087117E+00 | grad norm: 1.749 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.722 | TFLOPs: 23.44 | +63: iteration 800/ 73814 | consumed samples: 409600 | consumed tokens: 838860800 | elapsed time per iteration (s): 2.26 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 4.159515E+00 | grad norm: 1.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.681 | TFLOPs: 23.34 | +63: iteration 810/ 73814 | consumed samples: 414720 | consumed tokens: 849346560 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 4.123320E+00 | grad norm: 0.698 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.065 | TFLOPs: 23.58 | +63: iteration 820/ 73814 | consumed samples: 419840 | consumed tokens: 859832320 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 4.032620E+00 | grad norm: 0.481 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.993 | TFLOPs: 23.47 | +63: iteration 830/ 73814 | consumed samples: 424960 | consumed tokens: 870318080 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.947185E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.553 | TFLOPs: 23.63 | +63: iteration 840/ 73814 | consumed samples: 430080 | consumed tokens: 880803840 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.877919E+00 | grad norm: 0.419 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.910 | TFLOPs: 23.46 | +63: iteration 850/ 73814 | consumed samples: 435200 | consumed tokens: 891289600 | elapsed time per iteration (s): 2.27 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.850576E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.699 | TFLOPs: 23.23 | +63: iteration 860/ 73814 | consumed samples: 440320 | consumed tokens: 901775360 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.810270E+00 | grad norm: 0.439 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.444 | TFLOPs: 23.41 | +63: iteration 870/ 73814 | consumed samples: 445440 | consumed tokens: 912261120 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.805886E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.650 | TFLOPs: 23.64 | +63: iteration 880/ 73814 | consumed samples: 450560 | consumed tokens: 922746880 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.783057E+00 | grad norm: 0.473 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.462 | TFLOPs: 23.62 | +63: iteration 890/ 73814 | consumed samples: 455680 | consumed tokens: 933232640 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.765791E+00 | grad norm: 0.406 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.002 | TFLOPs: 23.68 | +63: iteration 900/ 73814 | consumed samples: 460800 | consumed tokens: 943718400 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.760938E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.705 | TFLOPs: 23.44 | +63: iteration 910/ 73814 | consumed samples: 465920 | consumed tokens: 954204160 | elapsed time per iteration (s): 2.27 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.716785E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.476 | TFLOPs: 23.21 | +63: iteration 920/ 73814 | consumed samples: 471040 | consumed tokens: 964689920 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.732428E+00 | grad norm: 0.386 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.830 | TFLOPs: 23.66 | +63: iteration 930/ 73814 | consumed samples: 476160 | consumed tokens: 975175680 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.695633E+00 | grad norm: 0.427 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.788 | TFLOPs: 23.66 | +63: iteration 940/ 73814 | consumed samples: 481280 | consumed tokens: 985661440 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.652497E+00 | grad norm: 0.380 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.001 | TFLOPs: 23.68 | +63: iteration 950/ 73814 | consumed samples: 486400 | consumed tokens: 996147200 | elapsed time per iteration (s): 2.26 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.660273E+00 | grad norm: 0.449 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.990 | TFLOPs: 23.37 | +63: iteration 960/ 73814 | consumed samples: 491520 | consumed tokens: 1006632960 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.649047E+00 | grad norm: 0.517 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.427 | TFLOPs: 23.62 | +63: iteration 970/ 73814 | consumed samples: 496640 | consumed tokens: 1017118720 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.655902E+00 | grad norm: 0.541 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.636 | TFLOPs: 23.54 | +63: iteration 980/ 73814 | consumed samples: 501760 | consumed tokens: 1027604480 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 4.004233E+00 | grad norm: 4.964 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.786 | TFLOPs: 23.55 | +63: iteration 990/ 73814 | consumed samples: 506880 | consumed tokens: 1038090240 | elapsed time per iteration (s): 2.29 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 4.124567E+00 | grad norm: 1.997 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.766 | TFLOPs: 23.04 | +63: iteration 1000/ 73814 | consumed samples: 512000 | consumed tokens: 1048576000 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 4.096008E+00 | grad norm: 1.589 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.742 | TFLOPs: 23.44 | +63: ------------------------------------------------------------------------------------------ +63: valid loss at iteration 1000 | lm loss value: 3.943520E+00 | lm loss PPL: 5.159990E+01 | +63: ------------------------------------------------------------------------------------------ +63: iteration 1010/ 73814 | consumed samples: 517120 | consumed tokens: 1059061760 | elapsed time per iteration (s): 2.30 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 4.034760E+00 | grad norm: 1.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.524 | TFLOPs: 22.91 | +63: iteration 1020/ 73814 | consumed samples: 522240 | consumed tokens: 1069547520 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.883276E+00 | grad norm: 0.866 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.923 | TFLOPs: 23.46 | +63: iteration 1030/ 73814 | consumed samples: 527360 | consumed tokens: 1080033280 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.740493E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.483 | TFLOPs: 23.62 | +63: iteration 1040/ 73814 | consumed samples: 532480 | consumed tokens: 1090519040 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.652044E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.304 | TFLOPs: 23.61 | +63: iteration 1050/ 73814 | consumed samples: 537600 | consumed tokens: 1101004800 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.611458E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.514 | TFLOPs: 23.52 | +63: iteration 1060/ 73814 | consumed samples: 542720 | consumed tokens: 1111490560 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.598650E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.917 | TFLOPs: 23.57 | +63: iteration 1070/ 73814 | consumed samples: 547840 | consumed tokens: 1121976320 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.570859E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.223 | TFLOPs: 23.60 | +63: iteration 1080/ 73814 | consumed samples: 552960 | consumed tokens: 1132462080 | elapsed time per iteration (s): 2.27 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.568339E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.562 | TFLOPs: 23.22 | +63: iteration 1090/ 73814 | consumed samples: 558080 | consumed tokens: 1142947840 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.542044E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.301 | TFLOPs: 23.50 | +63: iteration 1100/ 73814 | consumed samples: 563200 | consumed tokens: 1153433600 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.530043E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.668 | TFLOPs: 23.44 | +63: iteration 1110/ 73814 | consumed samples: 568320 | consumed tokens: 1163919360 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.608700E+00 | grad norm: 1.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.887 | TFLOPs: 23.46 | +63: iteration 1120/ 73814 | consumed samples: 573440 | consumed tokens: 1174405120 | elapsed time per iteration (s): 2.27 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.743490E+00 | grad norm: 0.764 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.165 | TFLOPs: 23.18 | +63: iteration 1130/ 73814 | consumed samples: 578560 | consumed tokens: 1184890880 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.728024E+00 | grad norm: 0.934 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.738 | TFLOPs: 23.44 | +63: iteration 1140/ 73814 | consumed samples: 583680 | consumed tokens: 1195376640 | elapsed time per iteration (s): 2.26 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.655492E+00 | grad norm: 0.524 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.037 | TFLOPs: 23.37 | +63: iteration 1150/ 73814 | consumed samples: 588800 | consumed tokens: 1205862400 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.572477E+00 | grad norm: 0.437 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.553 | TFLOPs: 23.53 | +63: iteration 1160/ 73814 | consumed samples: 593920 | consumed tokens: 1216348160 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.556502E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.263 | TFLOPs: 23.60 | +63: iteration 1170/ 73814 | consumed samples: 599040 | consumed tokens: 1226833920 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.519315E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.092 | TFLOPs: 23.38 | +63: iteration 1180/ 73814 | consumed samples: 604160 | consumed tokens: 1237319680 | elapsed time per iteration (s): 2.30 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.481354E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.054 | TFLOPs: 22.96 | +63: iteration 1190/ 73814 | consumed samples: 609280 | consumed tokens: 1247805440 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.434579E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.301 | TFLOPs: 23.50 | +63: iteration 1200/ 73814 | consumed samples: 614400 | consumed tokens: 1258291200 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.452773E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.588 | TFLOPs: 23.43 | +63: iteration 1210/ 73814 | consumed samples: 619520 | consumed tokens: 1268776960 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.496745E+00 | grad norm: 1.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.826 | TFLOPs: 23.66 | +63: iteration 1220/ 73814 | consumed samples: 624640 | consumed tokens: 1279262720 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.640980E+00 | grad norm: 0.805 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.767 | TFLOPs: 23.45 | +63: iteration 1230/ 73814 | consumed samples: 629760 | consumed tokens: 1289748480 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.613667E+00 | grad norm: 1.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.095 | TFLOPs: 23.58 | +63: iteration 1240/ 73814 | consumed samples: 634880 | consumed tokens: 1300234240 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.667424E+00 | grad norm: 1.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.878 | TFLOPs: 23.56 | +63: iteration 1250/ 73814 | consumed samples: 640000 | consumed tokens: 1310720000 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.594647E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.316 | TFLOPs: 23.50 | +63: iteration 1260/ 73814 | consumed samples: 645120 | consumed tokens: 1321205760 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.499585E+00 | grad norm: 0.423 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.335 | TFLOPs: 23.51 | +63: iteration 1270/ 73814 | consumed samples: 650240 | consumed tokens: 1331691520 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.453998E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.075 | TFLOPs: 23.48 | +63: iteration 1280/ 73814 | consumed samples: 655360 | consumed tokens: 1342177280 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.429255E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.738 | TFLOPs: 23.65 | +63: iteration 1290/ 73814 | consumed samples: 660480 | consumed tokens: 1352663040 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.412457E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.892 | TFLOPs: 23.56 | +63: iteration 1300/ 73814 | consumed samples: 665600 | consumed tokens: 1363148800 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.382024E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.312 | TFLOPs: 23.50 | +63: iteration 1310/ 73814 | consumed samples: 670720 | consumed tokens: 1373634560 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.381322E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.319 | TFLOPs: 23.50 | +63: iteration 1320/ 73814 | consumed samples: 675840 | consumed tokens: 1384120320 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.375527E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.838 | TFLOPs: 23.66 | +63: iteration 1330/ 73814 | consumed samples: 680960 | consumed tokens: 1394606080 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.372660E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.873 | TFLOPs: 23.66 | +63: iteration 1340/ 73814 | consumed samples: 686080 | consumed tokens: 1405091840 | elapsed time per iteration (s): 2.26 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.347375E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.558 | TFLOPs: 23.32 | +63: iteration 1350/ 73814 | consumed samples: 691200 | consumed tokens: 1415577600 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.330698E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.395 | TFLOPs: 23.51 | +63: iteration 1360/ 73814 | consumed samples: 696320 | consumed tokens: 1426063360 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.327995E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.948 | TFLOPs: 23.47 | +63: iteration 1370/ 73814 | consumed samples: 701440 | consumed tokens: 1436549120 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.317349E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.723 | TFLOPs: 23.55 | +63: iteration 1380/ 73814 | consumed samples: 706560 | consumed tokens: 1447034880 | elapsed time per iteration (s): 2.27 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.470451E+00 | grad norm: 1.040 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.995 | TFLOPs: 23.27 | +63: iteration 1390/ 73814 | consumed samples: 711680 | consumed tokens: 1457520640 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.596442E+00 | grad norm: 1.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.790 | TFLOPs: 23.55 | +63: iteration 1400/ 73814 | consumed samples: 716800 | consumed tokens: 1468006400 | elapsed time per iteration (s): 2.27 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.579095E+00 | grad norm: 0.917 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.841 | TFLOPs: 23.25 | +63: iteration 1410/ 73814 | consumed samples: 721920 | consumed tokens: 1478492160 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.493357E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.503 | TFLOPs: 23.63 | +63: iteration 1420/ 73814 | consumed samples: 727040 | consumed tokens: 1488977920 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.399675E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.881 | TFLOPs: 23.67 | +63: iteration 1430/ 73814 | consumed samples: 732160 | consumed tokens: 1499463680 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.369331E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.237 | TFLOPs: 23.50 | +63: iteration 1440/ 73814 | consumed samples: 737280 | consumed tokens: 1509949440 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.331328E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.585 | TFLOPs: 23.63 | +63: iteration 1450/ 73814 | consumed samples: 742400 | consumed tokens: 1520435200 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.308492E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.808 | TFLOPs: 23.66 | +63: iteration 1460/ 73814 | consumed samples: 747520 | consumed tokens: 1530920960 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.300542E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.619 | TFLOPs: 23.64 | +63: iteration 1470/ 73814 | consumed samples: 752640 | consumed tokens: 1541406720 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.292529E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.719 | TFLOPs: 23.44 | +63: iteration 1480/ 73814 | consumed samples: 757760 | consumed tokens: 1551892480 | elapsed time per iteration (s): 2.27 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.255645E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.135 | TFLOPs: 23.18 | +63: iteration 1490/ 73814 | consumed samples: 762880 | consumed tokens: 1562378240 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.282503E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.514 | TFLOPs: 23.42 | +63: iteration 1500/ 73814 | consumed samples: 768000 | consumed tokens: 1572864000 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.240703E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.769 | TFLOPs: 23.45 | +63: iteration 1510/ 73814 | consumed samples: 773120 | consumed tokens: 1583349760 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-04 | global batch size: 512 | lm loss: 3.261357E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.400 | TFLOPs: 23.51 | +63: iteration 1520/ 73814 | consumed samples: 778240 | consumed tokens: 1593835520 | elapsed time per iteration (s): 2.25 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.251596E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.349 | TFLOPs: 23.40 | +63: iteration 1530/ 73814 | consumed samples: 783360 | consumed tokens: 1604321280 | elapsed time per iteration (s): 2.26 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.238650E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.456 | TFLOPs: 23.31 | +63: iteration 1540/ 73814 | consumed samples: 788480 | consumed tokens: 1614807040 | elapsed time per iteration (s): 2.23 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.248568E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.099 | TFLOPs: 23.58 | +63: iteration 1550/ 73814 | consumed samples: 793600 | consumed tokens: 1625292800 | elapsed time per iteration (s): 2.23 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.233268E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.298 | TFLOPs: 23.61 | +63: iteration 1560/ 73814 | consumed samples: 798720 | consumed tokens: 1635778560 | elapsed time per iteration (s): 2.26 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.229184E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.294 | TFLOPs: 23.30 | +63: iteration 1570/ 73814 | consumed samples: 803840 | consumed tokens: 1646264320 | elapsed time per iteration (s): 2.24 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.222168E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.940 | TFLOPs: 23.57 | +63: iteration 1580/ 73814 | consumed samples: 808960 | consumed tokens: 1656750080 | elapsed time per iteration (s): 2.23 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.196898E+00 | grad norm: 0.368 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.069 | TFLOPs: 23.68 | +63: iteration 1590/ 73814 | consumed samples: 814080 | consumed tokens: 1667235840 | elapsed time per iteration (s): 2.23 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.214748E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.548 | TFLOPs: 23.63 | +63: iteration 1600/ 73814 | consumed samples: 819200 | consumed tokens: 1677721600 | elapsed time per iteration (s): 2.23 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.207629E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.620 | TFLOPs: 23.64 | +63: iteration 1610/ 73814 | consumed samples: 824320 | consumed tokens: 1688207360 | elapsed time per iteration (s): 2.23 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.195828E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.203 | TFLOPs: 23.60 | +63: iteration 1620/ 73814 | consumed samples: 829440 | consumed tokens: 1698693120 | elapsed time per iteration (s): 2.33 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.178151E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.828 | TFLOPs: 22.63 | +63: iteration 1630/ 73814 | consumed samples: 834560 | consumed tokens: 1709178880 | elapsed time per iteration (s): 2.24 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.152920E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.327 | TFLOPs: 23.51 | +63: iteration 1640/ 73814 | consumed samples: 839680 | consumed tokens: 1719664640 | elapsed time per iteration (s): 2.24 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.185193E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.892 | TFLOPs: 23.56 | +63: iteration 1650/ 73814 | consumed samples: 844800 | consumed tokens: 1730150400 | elapsed time per iteration (s): 2.24 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.164393E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.650 | TFLOPs: 23.54 | +63: iteration 1660/ 73814 | consumed samples: 849920 | consumed tokens: 1740636160 | elapsed time per iteration (s): 2.56 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.161442E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.353 | TFLOPs: 20.63 | +63: iteration 1670/ 73814 | consumed samples: 855040 | consumed tokens: 1751121920 | elapsed time per iteration (s): 2.25 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.175636E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.747 | TFLOPs: 23.45 | +63: iteration 1680/ 73814 | consumed samples: 860160 | consumed tokens: 1761607680 | elapsed time per iteration (s): 2.49 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.145090E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.709 | TFLOPs: 21.18 | +63: iteration 1690/ 73814 | consumed samples: 865280 | consumed tokens: 1772093440 | elapsed time per iteration (s): 2.24 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.155805E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.521 | TFLOPs: 23.53 | +63: iteration 1700/ 73814 | consumed samples: 870400 | consumed tokens: 1782579200 | elapsed time per iteration (s): 2.37 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.143147E+00 | grad norm: 0.457 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.084 | TFLOPs: 22.24 | +63: iteration 1710/ 73814 | consumed samples: 875520 | consumed tokens: 1793064960 | elapsed time per iteration (s): 2.24 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.126282E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.416 | TFLOPs: 23.51 | +63: iteration 1720/ 73814 | consumed samples: 880640 | consumed tokens: 1803550720 | elapsed time per iteration (s): 2.53 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.150482E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.169 | TFLOPs: 20.81 | +63: iteration 1730/ 73814 | consumed samples: 885760 | consumed tokens: 1814036480 | elapsed time per iteration (s): 2.27 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.240815E+00 | grad norm: 1.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.013 | TFLOPs: 23.27 | +63: iteration 1740/ 73814 | consumed samples: 890880 | consumed tokens: 1824522240 | elapsed time per iteration (s): 2.34 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.593828E+00 | grad norm: 1.957 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.977 | TFLOPs: 22.54 | +63: iteration 1750/ 73814 | consumed samples: 896000 | consumed tokens: 1835008000 | elapsed time per iteration (s): 2.29 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.709441E+00 | grad norm: 2.010 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.032 | TFLOPs: 23.06 | +63: iteration 1760/ 73814 | consumed samples: 901120 | consumed tokens: 1845493760 | elapsed time per iteration (s): 2.27 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.712485E+00 | grad norm: 1.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.350 | TFLOPs: 23.20 | +63: iteration 1770/ 73814 | consumed samples: 906240 | consumed tokens: 1855979520 | elapsed time per iteration (s): 2.24 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.665218E+00 | grad norm: 1.470 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.644 | TFLOPs: 23.54 | +63: iteration 1780/ 73814 | consumed samples: 911360 | consumed tokens: 1866465280 | elapsed time per iteration (s): 2.24 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.586027E+00 | grad norm: 0.763 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.663 | TFLOPs: 23.54 | +63: iteration 1790/ 73814 | consumed samples: 916480 | consumed tokens: 1876951040 | elapsed time per iteration (s): 2.25 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.505307E+00 | grad norm: 0.875 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.850 | TFLOPs: 23.46 | +63: iteration 1800/ 73814 | consumed samples: 921600 | consumed tokens: 1887436800 | elapsed time per iteration (s): 2.25 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.358867E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.800 | TFLOPs: 23.45 | +63: iteration 1810/ 73814 | consumed samples: 926720 | consumed tokens: 1897922560 | elapsed time per iteration (s): 2.24 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.260201E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.460 | TFLOPs: 23.52 | +63: iteration 1820/ 73814 | consumed samples: 931840 | consumed tokens: 1908408320 | elapsed time per iteration (s): 2.26 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.235712E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.448 | TFLOPs: 23.31 | +63: iteration 1830/ 73814 | consumed samples: 936960 | consumed tokens: 1918894080 | elapsed time per iteration (s): 2.23 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.207601E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.552 | TFLOPs: 23.63 | +63: iteration 1840/ 73814 | consumed samples: 942080 | consumed tokens: 1929379840 | elapsed time per iteration (s): 2.25 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.187841E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.311 | TFLOPs: 23.40 | +63: iteration 1850/ 73814 | consumed samples: 947200 | consumed tokens: 1939865600 | elapsed time per iteration (s): 2.26 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.257230E+00 | grad norm: 0.891 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.405 | TFLOPs: 23.31 | +63: iteration 1860/ 73814 | consumed samples: 952320 | consumed tokens: 1950351360 | elapsed time per iteration (s): 2.23 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.382585E+00 | grad norm: 0.701 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.258 | TFLOPs: 23.60 | +63: iteration 1870/ 73814 | consumed samples: 957440 | consumed tokens: 1960837120 | elapsed time per iteration (s): 2.23 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.352118E+00 | grad norm: 0.394 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.722 | TFLOPs: 23.65 | +63: iteration 1880/ 73814 | consumed samples: 962560 | consumed tokens: 1971322880 | elapsed time per iteration (s): 2.25 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.227935E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.661 | TFLOPs: 23.44 | +63: iteration 1890/ 73814 | consumed samples: 967680 | consumed tokens: 1981808640 | elapsed time per iteration (s): 2.25 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.197809E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.885 | TFLOPs: 23.46 | +63: iteration 1900/ 73814 | consumed samples: 972800 | consumed tokens: 1992294400 | elapsed time per iteration (s): 2.23 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.163480E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.557 | TFLOPs: 23.63 | +63: iteration 1910/ 73814 | consumed samples: 977920 | consumed tokens: 2002780160 | elapsed time per iteration (s): 2.24 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.147366E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.286 | TFLOPs: 23.50 | +63: iteration 1920/ 73814 | consumed samples: 983040 | consumed tokens: 2013265920 | elapsed time per iteration (s): 2.23 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.137253E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.124 | TFLOPs: 23.59 | +63: iteration 1930/ 73814 | consumed samples: 988160 | consumed tokens: 2023751680 | elapsed time per iteration (s): 2.25 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.135254E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.717 | TFLOPs: 23.44 | +63: iteration 1940/ 73814 | consumed samples: 993280 | consumed tokens: 2034237440 | elapsed time per iteration (s): 2.23 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.107404E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.551 | TFLOPs: 23.63 | +63: iteration 1950/ 73814 | consumed samples: 998400 | consumed tokens: 2044723200 | elapsed time per iteration (s): 2.23 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.094640E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.473 | TFLOPs: 23.62 | +63: iteration 1960/ 73814 | consumed samples: 1003520 | consumed tokens: 2055208960 | elapsed time per iteration (s): 2.23 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.080163E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.654 | TFLOPs: 23.64 | +63: iteration 1970/ 73814 | consumed samples: 1008640 | consumed tokens: 2065694720 | elapsed time per iteration (s): 2.24 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.086462E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.165 | TFLOPs: 23.49 | +63: iteration 1980/ 73814 | consumed samples: 1013760 | consumed tokens: 2076180480 | elapsed time per iteration (s): 2.24 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.078637E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.255 | TFLOPs: 23.50 | +63: iteration 1990/ 73814 | consumed samples: 1018880 | consumed tokens: 2086666240 | elapsed time per iteration (s): 2.23 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.081868E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.827 | TFLOPs: 23.66 | + 0: [2022-12-01 12:56:49,484] [INFO] [logging.py:68:log_dist] [Rank 0] step=2000, skipped=0, lr=[0.0001998676047214727, 0.0001998676047214727, 0.0001998676047214727], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 2000/ 73814 | consumed samples: 1024000 | consumed tokens: 2097152000 | elapsed time per iteration (s): 2.23 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.073191E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.590 | TFLOPs: 23.64 | + 0: steps: 2000 loss: 3.0559 iter time (s): 2.276 samples/sec: 224.985 +63: ------------------------------------------------------------------------------------------ +63: valid loss at iteration 2000 | lm loss value: 2.924753E+00 | lm loss PPL: 1.862963E+01 | +63: ------------------------------------------------------------------------------------------ +63: iteration 2010/ 73814 | consumed samples: 1029120 | consumed tokens: 2107637760 | elapsed time per iteration (s): 2.29 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.080121E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.496 | TFLOPs: 23.01 | +63: iteration 2020/ 73814 | consumed samples: 1034240 | consumed tokens: 2118123520 | elapsed time per iteration (s): 2.25 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.076202E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.326 | TFLOPs: 23.40 | +63: iteration 2030/ 73814 | consumed samples: 1039360 | consumed tokens: 2128609280 | elapsed time per iteration (s): 2.25 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.067023E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.003 | TFLOPs: 23.47 | +63: iteration 2040/ 73814 | consumed samples: 1044480 | consumed tokens: 2139095040 | elapsed time per iteration (s): 2.23 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.048252E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.172 | TFLOPs: 23.59 | +63: iteration 2050/ 73814 | consumed samples: 1049600 | consumed tokens: 2149580800 | elapsed time per iteration (s): 2.23 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.069396E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.428 | TFLOPs: 23.62 | +63: iteration 2060/ 73814 | consumed samples: 1054720 | consumed tokens: 2160066560 | elapsed time per iteration (s): 2.24 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.036463E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.891 | TFLOPs: 23.56 | +63: iteration 2070/ 73814 | consumed samples: 1059840 | consumed tokens: 2170552320 | elapsed time per iteration (s): 2.25 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.046141E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.951 | TFLOPs: 23.47 | +63: iteration 2080/ 73814 | consumed samples: 1064960 | consumed tokens: 2181038080 | elapsed time per iteration (s): 2.23 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.045584E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.606 | TFLOPs: 23.64 | +63: iteration 2090/ 73814 | consumed samples: 1070080 | consumed tokens: 2191523840 | elapsed time per iteration (s): 2.23 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 3.016169E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.686 | TFLOPs: 23.65 | +63: iteration 2100/ 73814 | consumed samples: 1075200 | consumed tokens: 2202009600 | elapsed time per iteration (s): 2.24 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 3.028210E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.502 | TFLOPs: 23.52 | +63: iteration 2110/ 73814 | consumed samples: 1080320 | consumed tokens: 2212495360 | elapsed time per iteration (s): 2.22 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 3.052065E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.313 | TFLOPs: 23.71 | +63: iteration 2120/ 73814 | consumed samples: 1085440 | consumed tokens: 2222981120 | elapsed time per iteration (s): 2.23 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 3.046964E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.625 | TFLOPs: 23.64 | +63: iteration 2130/ 73814 | consumed samples: 1090560 | consumed tokens: 2233466880 | elapsed time per iteration (s): 2.23 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 3.017502E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.106 | TFLOPs: 23.59 | +63: iteration 2140/ 73814 | consumed samples: 1095680 | consumed tokens: 2243952640 | elapsed time per iteration (s): 2.22 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 3.030454E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.117 | TFLOPs: 23.69 | +63: iteration 2150/ 73814 | consumed samples: 1100800 | consumed tokens: 2254438400 | elapsed time per iteration (s): 2.25 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 3.000582E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.743 | TFLOPs: 23.45 | +63: iteration 2160/ 73814 | consumed samples: 1105920 | consumed tokens: 2264924160 | elapsed time per iteration (s): 2.23 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 3.003242E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.647 | TFLOPs: 23.64 | +63: iteration 2170/ 73814 | consumed samples: 1111040 | consumed tokens: 2275409920 | elapsed time per iteration (s): 3.06 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 3.019891E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 167.166 | TFLOPs: 17.21 | +63: iteration 2180/ 73814 | consumed samples: 1116160 | consumed tokens: 2285895680 | elapsed time per iteration (s): 2.24 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.983278E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.542 | TFLOPs: 23.53 | +63: iteration 2190/ 73814 | consumed samples: 1121280 | consumed tokens: 2296381440 | elapsed time per iteration (s): 2.23 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 3.002457E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.086 | TFLOPs: 23.69 | +63: iteration 2200/ 73814 | consumed samples: 1126400 | consumed tokens: 2306867200 | elapsed time per iteration (s): 2.23 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.988458E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.953 | TFLOPs: 23.67 | +63: iteration 2210/ 73814 | consumed samples: 1131520 | consumed tokens: 2317352960 | elapsed time per iteration (s): 2.23 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.989782E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.523 | TFLOPs: 23.63 | +63: iteration 2220/ 73814 | consumed samples: 1136640 | consumed tokens: 2327838720 | elapsed time per iteration (s): 5.12 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.982211E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 99.948 | TFLOPs: 10.29 | +63: iteration 2230/ 73814 | consumed samples: 1141760 | consumed tokens: 2338324480 | elapsed time per iteration (s): 2.25 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.986164E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.352 | TFLOPs: 23.40 | +63: iteration 2240/ 73814 | consumed samples: 1146880 | consumed tokens: 2348810240 | elapsed time per iteration (s): 2.25 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.968617E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.824 | TFLOPs: 23.45 | +63: iteration 2250/ 73814 | consumed samples: 1152000 | consumed tokens: 2359296000 | elapsed time per iteration (s): 2.22 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.976582E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.294 | TFLOPs: 23.71 | +63: iteration 2260/ 73814 | consumed samples: 1157120 | consumed tokens: 2369781760 | elapsed time per iteration (s): 2.24 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.980335E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.433 | TFLOPs: 23.52 | +63: iteration 2270/ 73814 | consumed samples: 1162240 | consumed tokens: 2380267520 | elapsed time per iteration (s): 2.23 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.970451E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.319 | TFLOPs: 23.61 | +63: iteration 2280/ 73814 | consumed samples: 1167360 | consumed tokens: 2390753280 | elapsed time per iteration (s): 2.23 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.964942E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.240 | TFLOPs: 23.60 | +63: iteration 2290/ 73814 | consumed samples: 1172480 | consumed tokens: 2401239040 | elapsed time per iteration (s): 2.24 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.962106E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.272 | TFLOPs: 23.50 | +63: iteration 2300/ 73814 | consumed samples: 1177600 | consumed tokens: 2411724800 | elapsed time per iteration (s): 2.23 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.958459E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.148 | TFLOPs: 23.59 | +63: iteration 2310/ 73814 | consumed samples: 1182720 | consumed tokens: 2422210560 | elapsed time per iteration (s): 2.23 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.953629E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.164 | TFLOPs: 23.59 | +63: iteration 2320/ 73814 | consumed samples: 1187840 | consumed tokens: 2432696320 | elapsed time per iteration (s): 2.25 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.971559E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.952 | TFLOPs: 23.47 | +63: iteration 2330/ 73814 | consumed samples: 1192960 | consumed tokens: 2443182080 | elapsed time per iteration (s): 2.23 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.947885E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.032 | TFLOPs: 23.68 | +63: iteration 2340/ 73814 | consumed samples: 1198080 | consumed tokens: 2453667840 | elapsed time per iteration (s): 2.26 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.954559E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.865 | TFLOPs: 23.35 | +63: iteration 2350/ 73814 | consumed samples: 1203200 | consumed tokens: 2464153600 | elapsed time per iteration (s): 2.23 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.958161E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.813 | TFLOPs: 23.66 | +63: iteration 2360/ 73814 | consumed samples: 1208320 | consumed tokens: 2474639360 | elapsed time per iteration (s): 2.24 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.956520E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.130 | TFLOPs: 23.48 | +63: iteration 2370/ 73814 | consumed samples: 1213440 | consumed tokens: 2485125120 | elapsed time per iteration (s): 2.24 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.959934E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.134 | TFLOPs: 23.49 | +63: iteration 2380/ 73814 | consumed samples: 1218560 | consumed tokens: 2495610880 | elapsed time per iteration (s): 2.23 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.938045E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.383 | TFLOPs: 23.61 | +63: iteration 2390/ 73814 | consumed samples: 1223680 | consumed tokens: 2506096640 | elapsed time per iteration (s): 2.23 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.937507E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.666 | TFLOPs: 23.64 | +63: iteration 2400/ 73814 | consumed samples: 1228800 | consumed tokens: 2516582400 | elapsed time per iteration (s): 2.23 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.921236E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.297 | TFLOPs: 23.61 | +63: iteration 2410/ 73814 | consumed samples: 1233920 | consumed tokens: 2527068160 | elapsed time per iteration (s): 2.24 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.939890E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.426 | TFLOPs: 23.52 | +63: iteration 2420/ 73814 | consumed samples: 1239040 | consumed tokens: 2537553920 | elapsed time per iteration (s): 2.25 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.928143E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.549 | TFLOPs: 23.43 | +63: iteration 2430/ 73814 | consumed samples: 1244160 | consumed tokens: 2548039680 | elapsed time per iteration (s): 2.21 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.918579E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 231.218 | TFLOPs: 23.80 | +63: iteration 2440/ 73814 | consumed samples: 1249280 | consumed tokens: 2558525440 | elapsed time per iteration (s): 2.23 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.923197E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.624 | TFLOPs: 23.64 | +63: iteration 2450/ 73814 | consumed samples: 1254400 | consumed tokens: 2569011200 | elapsed time per iteration (s): 2.26 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.915906E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.106 | TFLOPs: 23.28 | +63: iteration 2460/ 73814 | consumed samples: 1259520 | consumed tokens: 2579496960 | elapsed time per iteration (s): 2.25 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.925406E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.508 | TFLOPs: 23.42 | +63: iteration 2470/ 73814 | consumed samples: 1264640 | consumed tokens: 2589982720 | elapsed time per iteration (s): 2.26 | learning rate: 1.998E-04 | global batch size: 512 | lm loss: 2.921716E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.312 | TFLOPs: 23.30 | +63: iteration 2480/ 73814 | consumed samples: 1269760 | consumed tokens: 2600468480 | elapsed time per iteration (s): 2.25 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.928929E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.767 | TFLOPs: 23.45 | +63: iteration 2490/ 73814 | consumed samples: 1274880 | consumed tokens: 2610954240 | elapsed time per iteration (s): 2.28 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.918981E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.681 | TFLOPs: 23.13 | +63: iteration 2500/ 73814 | consumed samples: 1280000 | consumed tokens: 2621440000 | elapsed time per iteration (s): 2.25 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.913911E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.302 | TFLOPs: 23.40 | +63: iteration 2510/ 73814 | consumed samples: 1285120 | consumed tokens: 2631925760 | elapsed time per iteration (s): 2.23 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.928032E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.663 | TFLOPs: 23.64 | +63: iteration 2520/ 73814 | consumed samples: 1290240 | consumed tokens: 2642411520 | elapsed time per iteration (s): 2.23 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.910373E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.769 | TFLOPs: 23.65 | +63: iteration 2530/ 73814 | consumed samples: 1295360 | consumed tokens: 2652897280 | elapsed time per iteration (s): 2.23 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.906717E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.681 | TFLOPs: 23.64 | +63: iteration 2540/ 73814 | consumed samples: 1300480 | consumed tokens: 2663383040 | elapsed time per iteration (s): 2.23 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.910507E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.193 | TFLOPs: 23.59 | +63: iteration 2550/ 73814 | consumed samples: 1305600 | consumed tokens: 2673868800 | elapsed time per iteration (s): 2.24 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.925212E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.150 | TFLOPs: 23.49 | +63: iteration 2560/ 73814 | consumed samples: 1310720 | consumed tokens: 2684354560 | elapsed time per iteration (s): 2.28 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.908291E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.609 | TFLOPs: 23.12 | +63: iteration 2570/ 73814 | consumed samples: 1315840 | consumed tokens: 2694840320 | elapsed time per iteration (s): 2.23 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.918614E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.641 | TFLOPs: 23.64 | +63: iteration 2580/ 73814 | consumed samples: 1320960 | consumed tokens: 2705326080 | elapsed time per iteration (s): 2.24 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.907689E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.054 | TFLOPs: 23.58 | +63: iteration 2590/ 73814 | consumed samples: 1326080 | consumed tokens: 2715811840 | elapsed time per iteration (s): 2.23 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.902796E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.927 | TFLOPs: 23.67 | +63: iteration 2600/ 73814 | consumed samples: 1331200 | consumed tokens: 2726297600 | elapsed time per iteration (s): 2.23 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.898236E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.985 | TFLOPs: 23.68 | +63: iteration 2610/ 73814 | consumed samples: 1336320 | consumed tokens: 2736783360 | elapsed time per iteration (s): 2.24 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.898095E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.041 | TFLOPs: 23.58 | +63: iteration 2620/ 73814 | consumed samples: 1341440 | consumed tokens: 2747269120 | elapsed time per iteration (s): 2.25 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.869612E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.197 | TFLOPs: 23.39 | +63: iteration 2630/ 73814 | consumed samples: 1346560 | consumed tokens: 2757754880 | elapsed time per iteration (s): 2.23 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.886891E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.548 | TFLOPs: 23.63 | +63: iteration 2640/ 73814 | consumed samples: 1351680 | consumed tokens: 2768240640 | elapsed time per iteration (s): 2.25 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.871366E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.712 | TFLOPs: 23.44 | +63: iteration 2650/ 73814 | consumed samples: 1356800 | consumed tokens: 2778726400 | elapsed time per iteration (s): 2.23 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.883750E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.219 | TFLOPs: 23.60 | +63: iteration 2660/ 73814 | consumed samples: 1361920 | consumed tokens: 2789212160 | elapsed time per iteration (s): 2.24 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.879169E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.727 | TFLOPs: 23.55 | +63: iteration 2670/ 73814 | consumed samples: 1367040 | consumed tokens: 2799697920 | elapsed time per iteration (s): 2.26 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.873778E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.756 | TFLOPs: 23.34 | +63: iteration 2680/ 73814 | consumed samples: 1372160 | consumed tokens: 2810183680 | elapsed time per iteration (s): 2.23 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.869572E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.569 | TFLOPs: 23.63 | +63: iteration 2690/ 73814 | consumed samples: 1377280 | consumed tokens: 2820669440 | elapsed time per iteration (s): 2.24 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.875708E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.078 | TFLOPs: 23.48 | +63: iteration 2700/ 73814 | consumed samples: 1382400 | consumed tokens: 2831155200 | elapsed time per iteration (s): 2.23 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.848882E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.499 | TFLOPs: 23.63 | +63: iteration 2710/ 73814 | consumed samples: 1387520 | consumed tokens: 2841640960 | elapsed time per iteration (s): 2.25 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.884268E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.867 | TFLOPs: 23.46 | +63: iteration 2720/ 73814 | consumed samples: 1392640 | consumed tokens: 2852126720 | elapsed time per iteration (s): 2.46 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.871852E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.002 | TFLOPs: 21.41 | +63: iteration 2730/ 73814 | consumed samples: 1397760 | consumed tokens: 2862612480 | elapsed time per iteration (s): 2.24 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.849050E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.294 | TFLOPs: 23.50 | +63: iteration 2740/ 73814 | consumed samples: 1402880 | consumed tokens: 2873098240 | elapsed time per iteration (s): 2.23 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.862021E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.256 | TFLOPs: 23.60 | +63: iteration 2750/ 73814 | consumed samples: 1408000 | consumed tokens: 2883584000 | elapsed time per iteration (s): 2.24 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.867513E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.249 | TFLOPs: 23.50 | +63: iteration 2760/ 73814 | consumed samples: 1413120 | consumed tokens: 2894069760 | elapsed time per iteration (s): 2.23 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.833479E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.865 | TFLOPs: 23.66 | +63: iteration 2770/ 73814 | consumed samples: 1418240 | consumed tokens: 2904555520 | elapsed time per iteration (s): 2.26 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.845196E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.737 | TFLOPs: 23.34 | +63: iteration 2780/ 73814 | consumed samples: 1423360 | consumed tokens: 2915041280 | elapsed time per iteration (s): 2.23 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.840336E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.972 | TFLOPs: 23.67 | +63: iteration 2790/ 73814 | consumed samples: 1428480 | consumed tokens: 2925527040 | elapsed time per iteration (s): 2.23 | learning rate: 1.997E-04 | global batch size: 512 | lm loss: 2.846681E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.339 | TFLOPs: 23.61 | +63: iteration 2800/ 73814 | consumed samples: 1433600 | consumed tokens: 2936012800 | elapsed time per iteration (s): 2.24 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 2.823163E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.753 | TFLOPs: 23.55 | +63: iteration 2810/ 73814 | consumed samples: 1438720 | consumed tokens: 2946498560 | elapsed time per iteration (s): 2.23 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 2.831254E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.762 | TFLOPs: 23.65 | +63: iteration 2820/ 73814 | consumed samples: 1443840 | consumed tokens: 2956984320 | elapsed time per iteration (s): 2.23 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 2.834718E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.566 | TFLOPs: 23.63 | +63: iteration 2830/ 73814 | consumed samples: 1448960 | consumed tokens: 2967470080 | elapsed time per iteration (s): 2.23 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 2.860731E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.492 | TFLOPs: 23.63 | +63: iteration 2840/ 73814 | consumed samples: 1454080 | consumed tokens: 2977955840 | elapsed time per iteration (s): 2.25 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 2.828483E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.910 | TFLOPs: 23.46 | +63: iteration 2850/ 73814 | consumed samples: 1459200 | consumed tokens: 2988441600 | elapsed time per iteration (s): 2.26 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 2.827128E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.529 | TFLOPs: 23.32 | +63: iteration 2860/ 73814 | consumed samples: 1464320 | consumed tokens: 2998927360 | elapsed time per iteration (s): 2.23 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 2.824731E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.918 | TFLOPs: 23.67 | +63: iteration 2870/ 73814 | consumed samples: 1469440 | consumed tokens: 3009413120 | elapsed time per iteration (s): 2.23 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 2.820268E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.828 | TFLOPs: 23.66 | +63: iteration 2880/ 73814 | consumed samples: 1474560 | consumed tokens: 3019898880 | elapsed time per iteration (s): 2.24 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 2.811736E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.153 | TFLOPs: 23.49 | +63: iteration 2890/ 73814 | consumed samples: 1479680 | consumed tokens: 3030384640 | elapsed time per iteration (s): 2.23 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 2.823316E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.811 | TFLOPs: 23.66 | +63: iteration 2900/ 73814 | consumed samples: 1484800 | consumed tokens: 3040870400 | elapsed time per iteration (s): 2.24 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 2.831727E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.824 | TFLOPs: 23.56 | +63: iteration 2910/ 73814 | consumed samples: 1489920 | consumed tokens: 3051356160 | elapsed time per iteration (s): 2.23 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 2.847128E+00 | grad norm: 0.472 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.635 | TFLOPs: 23.64 | +63: iteration 2920/ 73814 | consumed samples: 1495040 | consumed tokens: 3061841920 | elapsed time per iteration (s): 2.27 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 2.904374E+00 | grad norm: 1.756 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.520 | TFLOPs: 23.22 | +63: iteration 2930/ 73814 | consumed samples: 1500160 | consumed tokens: 3072327680 | elapsed time per iteration (s): 2.26 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 3.096631E+00 | grad norm: 2.689 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.794 | TFLOPs: 23.35 | +63: iteration 2940/ 73814 | consumed samples: 1505280 | consumed tokens: 3082813440 | elapsed time per iteration (s): 2.26 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 3.302181E+00 | grad norm: 1.602 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.520 | TFLOPs: 23.32 | +63: iteration 2950/ 73814 | consumed samples: 1510400 | consumed tokens: 3093299200 | elapsed time per iteration (s): 2.25 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 3.399968E+00 | grad norm: 1.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.673 | TFLOPs: 23.44 | +63: iteration 2960/ 73814 | consumed samples: 1515520 | consumed tokens: 3103784960 | elapsed time per iteration (s): 2.25 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 3.435523E+00 | grad norm: 1.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.936 | TFLOPs: 23.46 | +63: iteration 2970/ 73814 | consumed samples: 1520640 | consumed tokens: 3114270720 | elapsed time per iteration (s): 2.24 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 3.487362E+00 | grad norm: 1.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.566 | TFLOPs: 23.53 | +63: iteration 2980/ 73814 | consumed samples: 1525760 | consumed tokens: 3124756480 | elapsed time per iteration (s): 2.25 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 3.437527E+00 | grad norm: 1.027 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.512 | TFLOPs: 23.42 | +63: iteration 2990/ 73814 | consumed samples: 1530880 | consumed tokens: 3135242240 | elapsed time per iteration (s): 2.25 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 3.398412E+00 | grad norm: 0.433 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.633 | TFLOPs: 23.43 | +63: iteration 3000/ 73814 | consumed samples: 1536000 | consumed tokens: 3145728000 | elapsed time per iteration (s): 2.23 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 3.195549E+00 | grad norm: 0.494 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.393 | TFLOPs: 23.61 | +63: ------------------------------------------------------------------------------------------ +63: valid loss at iteration 3000 | lm loss value: 3.055795E+00 | lm loss PPL: 2.123806E+01 | +63: ------------------------------------------------------------------------------------------ +63: iteration 3010/ 73814 | consumed samples: 1541120 | consumed tokens: 3156213760 | elapsed time per iteration (s): 2.30 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 3.078347E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.601 | TFLOPs: 22.92 | +63: iteration 3020/ 73814 | consumed samples: 1546240 | consumed tokens: 3166699520 | elapsed time per iteration (s): 2.23 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 3.029090E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.201 | TFLOPs: 23.60 | +63: iteration 3030/ 73814 | consumed samples: 1551360 | consumed tokens: 3177185280 | elapsed time per iteration (s): 2.23 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 2.966147E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.472 | TFLOPs: 23.62 | +63: iteration 3040/ 73814 | consumed samples: 1556480 | consumed tokens: 3187671040 | elapsed time per iteration (s): 2.23 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 2.938599E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.203 | TFLOPs: 23.60 | +63: iteration 3050/ 73814 | consumed samples: 1561600 | consumed tokens: 3198156800 | elapsed time per iteration (s): 2.24 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 2.944241E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.725 | TFLOPs: 23.55 | +63: iteration 3060/ 73814 | consumed samples: 1566720 | consumed tokens: 3208642560 | elapsed time per iteration (s): 2.24 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 2.912189E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.433 | TFLOPs: 23.52 | +63: iteration 3070/ 73814 | consumed samples: 1571840 | consumed tokens: 3219128320 | elapsed time per iteration (s): 2.25 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.871950E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.051 | TFLOPs: 23.48 | +63: iteration 3080/ 73814 | consumed samples: 1576960 | consumed tokens: 3229614080 | elapsed time per iteration (s): 2.27 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.879201E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.837 | TFLOPs: 23.25 | +63: iteration 3090/ 73814 | consumed samples: 1582080 | consumed tokens: 3240099840 | elapsed time per iteration (s): 2.28 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.875886E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.878 | TFLOPs: 23.15 | +63: iteration 3100/ 73814 | consumed samples: 1587200 | consumed tokens: 3250585600 | elapsed time per iteration (s): 2.25 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.849582E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.427 | TFLOPs: 23.41 | +63: iteration 3110/ 73814 | consumed samples: 1592320 | consumed tokens: 3261071360 | elapsed time per iteration (s): 2.25 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.847703E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.762 | TFLOPs: 23.45 | +63: iteration 3120/ 73814 | consumed samples: 1597440 | consumed tokens: 3271557120 | elapsed time per iteration (s): 2.25 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.838484E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.258 | TFLOPs: 23.40 | +63: iteration 3130/ 73814 | consumed samples: 1602560 | consumed tokens: 3282042880 | elapsed time per iteration (s): 2.23 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.845091E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.875 | TFLOPs: 23.66 | +63: iteration 3140/ 73814 | consumed samples: 1607680 | consumed tokens: 3292528640 | elapsed time per iteration (s): 2.23 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.840293E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.698 | TFLOPs: 23.65 | +63: iteration 3150/ 73814 | consumed samples: 1612800 | consumed tokens: 3303014400 | elapsed time per iteration (s): 2.23 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.831210E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.835 | TFLOPs: 23.66 | +63: iteration 3160/ 73814 | consumed samples: 1617920 | consumed tokens: 3313500160 | elapsed time per iteration (s): 2.25 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.808803E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.853 | TFLOPs: 23.46 | +63: iteration 3170/ 73814 | consumed samples: 1623040 | consumed tokens: 3323985920 | elapsed time per iteration (s): 2.23 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.812595E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.723 | TFLOPs: 23.65 | +63: iteration 3180/ 73814 | consumed samples: 1628160 | consumed tokens: 3334471680 | elapsed time per iteration (s): 2.25 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.822187E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.001 | TFLOPs: 23.47 | +63: iteration 3190/ 73814 | consumed samples: 1633280 | consumed tokens: 3344957440 | elapsed time per iteration (s): 2.24 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.811224E+00 | grad norm: 0.549 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.437 | TFLOPs: 23.52 | +63: iteration 3200/ 73814 | consumed samples: 1638400 | consumed tokens: 3355443200 | elapsed time per iteration (s): 2.25 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.833524E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.723 | TFLOPs: 23.44 | +63: iteration 3210/ 73814 | consumed samples: 1643520 | consumed tokens: 3365928960 | elapsed time per iteration (s): 2.23 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.820510E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.622 | TFLOPs: 23.64 | +63: iteration 3220/ 73814 | consumed samples: 1648640 | consumed tokens: 3376414720 | elapsed time per iteration (s): 2.23 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.811462E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.708 | TFLOPs: 23.65 | +63: iteration 3230/ 73814 | consumed samples: 1653760 | consumed tokens: 3386900480 | elapsed time per iteration (s): 42.57 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.810450E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 12.029 | TFLOPs: 1.24 | +63: iteration 3240/ 73814 | consumed samples: 1658880 | consumed tokens: 3397386240 | elapsed time per iteration (s): 2.27 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.815989E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.485 | TFLOPs: 23.21 | +63: iteration 3250/ 73814 | consumed samples: 1664000 | consumed tokens: 3407872000 | elapsed time per iteration (s): 2.25 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.806744E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.044 | TFLOPs: 23.48 | +63: iteration 3260/ 73814 | consumed samples: 1669120 | consumed tokens: 3418357760 | elapsed time per iteration (s): 2.60 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.788174E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 196.595 | TFLOPs: 20.24 | +63: iteration 3270/ 73814 | consumed samples: 1674240 | consumed tokens: 3428843520 | elapsed time per iteration (s): 2.27 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.778308E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.859 | TFLOPs: 23.25 | +63: iteration 3280/ 73814 | consumed samples: 1679360 | consumed tokens: 3439329280 | elapsed time per iteration (s): 2.30 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.793256E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.681 | TFLOPs: 22.92 | +63: iteration 3290/ 73814 | consumed samples: 1684480 | consumed tokens: 3449815040 | elapsed time per iteration (s): 2.24 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.798283E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.906 | TFLOPs: 23.56 | +63: iteration 3300/ 73814 | consumed samples: 1689600 | consumed tokens: 3460300800 | elapsed time per iteration (s): 2.24 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.814487E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.134 | TFLOPs: 23.49 | +63: iteration 3310/ 73814 | consumed samples: 1694720 | consumed tokens: 3470786560 | elapsed time per iteration (s): 2.23 | learning rate: 1.995E-04 | global batch size: 512 | lm loss: 2.777452E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.771 | TFLOPs: 23.65 | +63: iteration 3320/ 73814 | consumed samples: 1699840 | consumed tokens: 3481272320 | elapsed time per iteration (s): 2.25 | learning rate: 1.994E-04 | global batch size: 512 | lm loss: 2.783912E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.031 | TFLOPs: 23.47 | +63: iteration 3330/ 73814 | consumed samples: 1704960 | consumed tokens: 3491758080 | elapsed time per iteration (s): 2.23 | learning rate: 1.994E-04 | global batch size: 512 | lm loss: 2.782973E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.239 | TFLOPs: 23.60 | +63: iteration 3340/ 73814 | consumed samples: 1710080 | consumed tokens: 3502243840 | elapsed time per iteration (s): 2.24 | learning rate: 1.994E-04 | global batch size: 512 | lm loss: 2.782617E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.645 | TFLOPs: 23.54 | +63: iteration 3350/ 73814 | consumed samples: 1715200 | consumed tokens: 3512729600 | elapsed time per iteration (s): 2.24 | learning rate: 1.994E-04 | global batch size: 512 | lm loss: 2.776588E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.624 | TFLOPs: 23.54 | +63: iteration 3360/ 73814 | consumed samples: 1720320 | consumed tokens: 3523215360 | elapsed time per iteration (s): 2.23 | learning rate: 1.994E-04 | global batch size: 512 | lm loss: 2.772923E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.761 | TFLOPs: 23.65 | +63: iteration 3370/ 73814 | consumed samples: 1725440 | consumed tokens: 3533701120 | elapsed time per iteration (s): 2.25 | learning rate: 1.994E-04 | global batch size: 512 | lm loss: 2.781462E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.800 | TFLOPs: 23.45 | +63: iteration 3380/ 73814 | consumed samples: 1730560 | consumed tokens: 3544186880 | elapsed time per iteration (s): 2.87 | learning rate: 1.994E-04 | global batch size: 512 | lm loss: 2.777232E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 178.106 | TFLOPs: 18.34 | +63: iteration 3390/ 73814 | consumed samples: 1735680 | consumed tokens: 3554672640 | elapsed time per iteration (s): 2.26 | learning rate: 1.994E-04 | global batch size: 512 | lm loss: 2.777434E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.549 | TFLOPs: 23.32 | +63: iteration 3400/ 73814 | consumed samples: 1740800 | consumed tokens: 3565158400 | elapsed time per iteration (s): 2.33 | learning rate: 1.994E-04 | global batch size: 512 | lm loss: 2.781872E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.585 | TFLOPs: 22.61 | +63: iteration 3410/ 73814 | consumed samples: 1745920 | consumed tokens: 3575644160 | elapsed time per iteration (s): 2.25 | learning rate: 1.994E-04 | global batch size: 512 | lm loss: 2.756693E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.460 | TFLOPs: 23.42 | +63: iteration 3420/ 73814 | consumed samples: 1751040 | consumed tokens: 3586129920 | elapsed time per iteration (s): 2.23 | learning rate: 1.994E-04 | global batch size: 512 | lm loss: 2.772000E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.759 | TFLOPs: 23.65 | +63: iteration 3430/ 73814 | consumed samples: 1756160 | consumed tokens: 3596615680 | elapsed time per iteration (s): 2.23 | learning rate: 1.994E-04 | global batch size: 512 | lm loss: 2.740322E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.670 | TFLOPs: 23.64 | +63: iteration 3440/ 73814 | consumed samples: 1761280 | consumed tokens: 3607101440 | elapsed time per iteration (s): 2.23 | learning rate: 1.994E-04 | global batch size: 512 | lm loss: 2.751960E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.643 | TFLOPs: 23.64 | +63: iteration 3450/ 73814 | consumed samples: 1766400 | consumed tokens: 3617587200 | elapsed time per iteration (s): 2.23 | learning rate: 1.994E-04 | global batch size: 512 | lm loss: 2.762852E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.090 | TFLOPs: 23.58 | +63: iteration 3460/ 73814 | consumed samples: 1771520 | consumed tokens: 3628072960 | elapsed time per iteration (s): 2.23 | learning rate: 1.994E-04 | global batch size: 512 | lm loss: 2.761745E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.102 | TFLOPs: 23.58 | +63: iteration 3470/ 73814 | consumed samples: 1776640 | consumed tokens: 3638558720 | elapsed time per iteration (s): 2.24 | learning rate: 1.994E-04 | global batch size: 512 | lm loss: 2.736086E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.975 | TFLOPs: 23.57 | +63: iteration 3480/ 73814 | consumed samples: 1781760 | consumed tokens: 3649044480 | elapsed time per iteration (s): 2.23 | learning rate: 1.994E-04 | global batch size: 512 | lm loss: 2.745948E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.468 | TFLOPs: 23.62 | +63: iteration 3490/ 73814 | consumed samples: 1786880 | consumed tokens: 3659530240 | elapsed time per iteration (s): 2.24 | learning rate: 1.994E-04 | global batch size: 512 | lm loss: 2.724564E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.064 | TFLOPs: 23.48 | +63: iteration 3500/ 73814 | consumed samples: 1792000 | consumed tokens: 3670016000 | elapsed time per iteration (s): 2.23 | learning rate: 1.994E-04 | global batch size: 512 | lm loss: 2.740987E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.731 | TFLOPs: 23.65 | +63: iteration 3510/ 73814 | consumed samples: 1797120 | consumed tokens: 3680501760 | elapsed time per iteration (s): 2.26 | learning rate: 1.994E-04 | global batch size: 512 | lm loss: 2.749612E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.518 | TFLOPs: 23.32 | +63: iteration 3520/ 73814 | consumed samples: 1802240 | consumed tokens: 3690987520 | elapsed time per iteration (s): 2.23 | learning rate: 1.994E-04 | global batch size: 512 | lm loss: 2.747462E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.502 | TFLOPs: 23.63 | +63: iteration 3530/ 73814 | consumed samples: 1807360 | consumed tokens: 3701473280 | elapsed time per iteration (s): 2.24 | learning rate: 1.994E-04 | global batch size: 512 | lm loss: 2.762455E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.646 | TFLOPs: 23.54 | +63: iteration 3540/ 73814 | consumed samples: 1812480 | consumed tokens: 3711959040 | elapsed time per iteration (s): 2.24 | learning rate: 1.993E-04 | global batch size: 512 | lm loss: 2.729912E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.715 | TFLOPs: 23.55 | +63: iteration 3550/ 73814 | consumed samples: 1817600 | consumed tokens: 3722444800 | elapsed time per iteration (s): 2.28 | learning rate: 1.993E-04 | global batch size: 512 | lm loss: 2.736282E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.045 | TFLOPs: 23.17 | +63: iteration 3560/ 73814 | consumed samples: 1822720 | consumed tokens: 3732930560 | elapsed time per iteration (s): 2.25 | learning rate: 1.993E-04 | global batch size: 512 | lm loss: 2.748279E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.535 | TFLOPs: 23.42 | +63: iteration 3570/ 73814 | consumed samples: 1827840 | consumed tokens: 3743416320 | elapsed time per iteration (s): 2.23 | learning rate: 1.993E-04 | global batch size: 512 | lm loss: 2.756140E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.496 | TFLOPs: 23.63 | +63: iteration 3580/ 73814 | consumed samples: 1832960 | consumed tokens: 3753902080 | elapsed time per iteration (s): 2.23 | learning rate: 1.993E-04 | global batch size: 512 | lm loss: 2.751233E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.269 | TFLOPs: 23.60 | +63: iteration 3590/ 73814 | consumed samples: 1838080 | consumed tokens: 3764387840 | elapsed time per iteration (s): 2.24 | learning rate: 1.993E-04 | global batch size: 512 | lm loss: 2.735680E+00 | grad norm: 0.368 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.119 | TFLOPs: 23.48 | +63: iteration 3600/ 73814 | consumed samples: 1843200 | consumed tokens: 3774873600 | elapsed time per iteration (s): 2.25 | learning rate: 1.993E-04 | global batch size: 512 | lm loss: 2.745518E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.166 | TFLOPs: 23.39 | +63: iteration 3610/ 73814 | consumed samples: 1848320 | consumed tokens: 3785359360 | elapsed time per iteration (s): 2.23 | learning rate: 1.993E-04 | global batch size: 512 | lm loss: 2.758997E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.462 | TFLOPs: 23.62 | +63: iteration 3620/ 73814 | consumed samples: 1853440 | consumed tokens: 3795845120 | elapsed time per iteration (s): 2.23 | learning rate: 1.993E-04 | global batch size: 512 | lm loss: 2.725155E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.673 | TFLOPs: 23.64 | +63: iteration 3630/ 73814 | consumed samples: 1858560 | consumed tokens: 3806330880 | elapsed time per iteration (s): 2.25 | learning rate: 1.993E-04 | global batch size: 512 | lm loss: 2.731844E+00 | grad norm: 0.416 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.430 | TFLOPs: 23.41 | +63: iteration 3640/ 73814 | consumed samples: 1863680 | consumed tokens: 3816816640 | elapsed time per iteration (s): 2.24 | learning rate: 1.993E-04 | global batch size: 512 | lm loss: 2.837235E+00 | grad norm: 0.824 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.666 | TFLOPs: 23.54 | +63: iteration 3650/ 73814 | consumed samples: 1868800 | consumed tokens: 3827302400 | elapsed time per iteration (s): 4.44 | learning rate: 1.993E-04 | global batch size: 512 | lm loss: 3.117956E+00 | grad norm: 1.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 115.355 | TFLOPs: 11.88 | +63: iteration 3660/ 73814 | consumed samples: 1873920 | consumed tokens: 3837788160 | elapsed time per iteration (s): 2.25 | learning rate: 1.993E-04 | global batch size: 512 | lm loss: 3.077209E+00 | grad norm: 1.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.642 | TFLOPs: 23.43 | +63: iteration 3670/ 73814 | consumed samples: 1879040 | consumed tokens: 3848273920 | elapsed time per iteration (s): 2.25 | learning rate: 1.993E-04 | global batch size: 512 | lm loss: 3.011936E+00 | grad norm: 0.636 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.053 | TFLOPs: 23.37 | +63: iteration 3680/ 73814 | consumed samples: 1884160 | consumed tokens: 3858759680 | elapsed time per iteration (s): 2.23 | learning rate: 1.993E-04 | global batch size: 512 | lm loss: 2.939231E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.458 | TFLOPs: 23.62 | +63: iteration 3690/ 73814 | consumed samples: 1889280 | consumed tokens: 3869245440 | elapsed time per iteration (s): 2.23 | learning rate: 1.993E-04 | global batch size: 512 | lm loss: 2.819053E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.069 | TFLOPs: 23.68 | +63: iteration 3700/ 73814 | consumed samples: 1894400 | consumed tokens: 3879731200 | elapsed time per iteration (s): 2.25 | learning rate: 1.993E-04 | global batch size: 512 | lm loss: 2.780992E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.537 | TFLOPs: 23.42 | +63: iteration 3710/ 73814 | consumed samples: 1899520 | consumed tokens: 3890216960 | elapsed time per iteration (s): 2.25 | learning rate: 1.993E-04 | global batch size: 512 | lm loss: 2.759444E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.745 | TFLOPs: 23.45 | +63: iteration 3720/ 73814 | consumed samples: 1904640 | consumed tokens: 3900702720 | elapsed time per iteration (s): 2.23 | learning rate: 1.993E-04 | global batch size: 512 | lm loss: 2.763833E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.239 | TFLOPs: 23.60 | +63: iteration 3730/ 73814 | consumed samples: 1909760 | consumed tokens: 3911188480 | elapsed time per iteration (s): 2.23 | learning rate: 1.993E-04 | global batch size: 512 | lm loss: 2.761118E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.785 | TFLOPs: 23.66 | +63: iteration 3740/ 73814 | consumed samples: 1914880 | consumed tokens: 3921674240 | elapsed time per iteration (s): 2.23 | learning rate: 1.993E-04 | global batch size: 512 | lm loss: 2.732571E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.921 | TFLOPs: 23.67 | +63: iteration 3750/ 73814 | consumed samples: 1920000 | consumed tokens: 3932160000 | elapsed time per iteration (s): 2.26 | learning rate: 1.992E-04 | global batch size: 512 | lm loss: 2.751108E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.420 | TFLOPs: 23.31 | +63: iteration 3760/ 73814 | consumed samples: 1925120 | consumed tokens: 3942645760 | elapsed time per iteration (s): 2.26 | learning rate: 1.992E-04 | global batch size: 512 | lm loss: 2.741549E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.188 | TFLOPs: 23.28 | +63: iteration 3770/ 73814 | consumed samples: 1930240 | consumed tokens: 3953131520 | elapsed time per iteration (s): 2.27 | learning rate: 1.992E-04 | global batch size: 512 | lm loss: 2.738339E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.135 | TFLOPs: 23.18 | +63: iteration 3780/ 73814 | consumed samples: 1935360 | consumed tokens: 3963617280 | elapsed time per iteration (s): 2.23 | learning rate: 1.992E-04 | global batch size: 512 | lm loss: 2.735083E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.291 | TFLOPs: 23.60 | +63: iteration 3790/ 73814 | consumed samples: 1940480 | consumed tokens: 3974103040 | elapsed time per iteration (s): 2.24 | learning rate: 1.992E-04 | global batch size: 512 | lm loss: 2.733234E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.076 | TFLOPs: 23.58 | +63: iteration 3800/ 73814 | consumed samples: 1945600 | consumed tokens: 3984588800 | elapsed time per iteration (s): 2.25 | learning rate: 1.992E-04 | global batch size: 512 | lm loss: 2.708771E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.320 | TFLOPs: 23.40 | +63: iteration 3810/ 73814 | consumed samples: 1950720 | consumed tokens: 3995074560 | elapsed time per iteration (s): 2.26 | learning rate: 1.992E-04 | global batch size: 512 | lm loss: 2.721661E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.131 | TFLOPs: 23.28 | +63: iteration 3820/ 73814 | consumed samples: 1955840 | consumed tokens: 4005560320 | elapsed time per iteration (s): 2.25 | learning rate: 1.992E-04 | global batch size: 512 | lm loss: 2.720290E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.871 | TFLOPs: 23.46 | +63: iteration 3830/ 73814 | consumed samples: 1960960 | consumed tokens: 4016046080 | elapsed time per iteration (s): 2.24 | learning rate: 1.992E-04 | global batch size: 512 | lm loss: 2.738391E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.926 | TFLOPs: 23.57 | +63: iteration 3840/ 73814 | consumed samples: 1966080 | consumed tokens: 4026531840 | elapsed time per iteration (s): 2.25 | learning rate: 1.992E-04 | global batch size: 512 | lm loss: 2.720010E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.643 | TFLOPs: 23.43 | +63: iteration 3850/ 73814 | consumed samples: 1971200 | consumed tokens: 4037017600 | elapsed time per iteration (s): 2.24 | learning rate: 1.992E-04 | global batch size: 512 | lm loss: 2.704826E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.855 | TFLOPs: 23.56 | +63: iteration 3860/ 73814 | consumed samples: 1976320 | consumed tokens: 4047503360 | elapsed time per iteration (s): 2.26 | learning rate: 1.992E-04 | global batch size: 512 | lm loss: 2.696754E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.162 | TFLOPs: 23.28 | +63: iteration 3870/ 73814 | consumed samples: 1981440 | consumed tokens: 4057989120 | elapsed time per iteration (s): 2.25 | learning rate: 1.992E-04 | global batch size: 512 | lm loss: 2.715684E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.903 | TFLOPs: 23.46 | +63: iteration 3880/ 73814 | consumed samples: 1986560 | consumed tokens: 4068474880 | elapsed time per iteration (s): 2.25 | learning rate: 1.992E-04 | global batch size: 512 | lm loss: 2.701550E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.784 | TFLOPs: 23.45 | +63: iteration 3890/ 73814 | consumed samples: 1991680 | consumed tokens: 4078960640 | elapsed time per iteration (s): 2.24 | learning rate: 1.992E-04 | global batch size: 512 | lm loss: 2.689731E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.820 | TFLOPs: 23.56 | +63: iteration 3900/ 73814 | consumed samples: 1996800 | consumed tokens: 4089446400 | elapsed time per iteration (s): 2.26 | learning rate: 1.992E-04 | global batch size: 512 | lm loss: 2.699595E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.668 | TFLOPs: 23.33 | +63: iteration 3910/ 73814 | consumed samples: 2001920 | consumed tokens: 4099932160 | elapsed time per iteration (s): 2.23 | learning rate: 1.992E-04 | global batch size: 512 | lm loss: 2.690499E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.648 | TFLOPs: 23.64 | +63: iteration 3920/ 73814 | consumed samples: 2007040 | consumed tokens: 4110417920 | elapsed time per iteration (s): 2.24 | learning rate: 1.992E-04 | global batch size: 512 | lm loss: 2.702595E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.114 | TFLOPs: 23.48 | +63: iteration 3930/ 73814 | consumed samples: 2012160 | consumed tokens: 4120903680 | elapsed time per iteration (s): 2.26 | learning rate: 1.992E-04 | global batch size: 512 | lm loss: 2.716331E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.120 | TFLOPs: 23.28 | +63: iteration 3940/ 73814 | consumed samples: 2017280 | consumed tokens: 4131389440 | elapsed time per iteration (s): 2.25 | learning rate: 1.991E-04 | global batch size: 512 | lm loss: 2.678920E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.505 | TFLOPs: 23.42 | +63: iteration 3950/ 73814 | consumed samples: 2022400 | consumed tokens: 4141875200 | elapsed time per iteration (s): 2.26 | learning rate: 1.991E-04 | global batch size: 512 | lm loss: 2.689314E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.900 | TFLOPs: 23.36 | +63: iteration 3960/ 73814 | consumed samples: 2027520 | consumed tokens: 4152360960 | elapsed time per iteration (s): 2.25 | learning rate: 1.991E-04 | global batch size: 512 | lm loss: 2.685933E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.191 | TFLOPs: 23.39 | +63: iteration 3970/ 73814 | consumed samples: 2032640 | consumed tokens: 4162846720 | elapsed time per iteration (s): 2.25 | learning rate: 1.991E-04 | global batch size: 512 | lm loss: 2.668538E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.148 | TFLOPs: 23.38 | +63: iteration 3980/ 73814 | consumed samples: 2037760 | consumed tokens: 4173332480 | elapsed time per iteration (s): 2.24 | learning rate: 1.991E-04 | global batch size: 512 | lm loss: 2.689762E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.494 | TFLOPs: 23.52 | +63: iteration 3990/ 73814 | consumed samples: 2042880 | consumed tokens: 4183818240 | elapsed time per iteration (s): 2.24 | learning rate: 1.991E-04 | global batch size: 512 | lm loss: 2.697137E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.985 | TFLOPs: 23.57 | + 0: [2022-12-01 14:19:29,831] [INFO] [logging.py:68:log_dist] [Rank 0] step=4000, skipped=0, lr=[0.00019911655927480593, 0.00019911655927480593, 0.00019911655927480593], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 4000/ 73814 | consumed samples: 2048000 | consumed tokens: 4194304000 | elapsed time per iteration (s): 2.29 | learning rate: 1.991E-04 | global batch size: 512 | lm loss: 2.675462E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.677 | TFLOPs: 23.03 | + 0: steps: 4000 loss: 2.6489 iter time (s): 2.478 samples/sec: 206.635 +63: ------------------------------------------------------------------------------------------ +63: valid loss at iteration 4000 | lm loss value: 2.673040E+00 | lm loss PPL: 1.448393E+01 | +63: ------------------------------------------------------------------------------------------ +63: iteration 4010/ 73814 | consumed samples: 2053120 | consumed tokens: 4204789760 | elapsed time per iteration (s): 2.29 | learning rate: 1.991E-04 | global batch size: 512 | lm loss: 2.667576E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.552 | TFLOPs: 23.01 | +63: iteration 4020/ 73814 | consumed samples: 2058240 | consumed tokens: 4215275520 | elapsed time per iteration (s): 2.25 | learning rate: 1.991E-04 | global batch size: 512 | lm loss: 2.680703E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.957 | TFLOPs: 23.47 | +63: iteration 4030/ 73814 | consumed samples: 2063360 | consumed tokens: 4225761280 | elapsed time per iteration (s): 2.23 | learning rate: 1.991E-04 | global batch size: 512 | lm loss: 2.688361E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.922 | TFLOPs: 23.67 | +63: iteration 4040/ 73814 | consumed samples: 2068480 | consumed tokens: 4236247040 | elapsed time per iteration (s): 2.23 | learning rate: 1.991E-04 | global batch size: 512 | lm loss: 2.694706E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.493 | TFLOPs: 23.63 | +63: iteration 4050/ 73814 | consumed samples: 2073600 | consumed tokens: 4246732800 | elapsed time per iteration (s): 2.23 | learning rate: 1.991E-04 | global batch size: 512 | lm loss: 2.663687E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.370 | TFLOPs: 23.61 | +63: iteration 4060/ 73814 | consumed samples: 2078720 | consumed tokens: 4257218560 | elapsed time per iteration (s): 2.23 | learning rate: 1.991E-04 | global batch size: 512 | lm loss: 2.684795E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.611 | TFLOPs: 23.64 | +63: iteration 4070/ 73814 | consumed samples: 2083840 | consumed tokens: 4267704320 | elapsed time per iteration (s): 2.25 | learning rate: 1.991E-04 | global batch size: 512 | lm loss: 2.657665E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.638 | TFLOPs: 23.43 | +63: iteration 4080/ 73814 | consumed samples: 2088960 | consumed tokens: 4278190080 | elapsed time per iteration (s): 2.25 | learning rate: 1.991E-04 | global batch size: 512 | lm loss: 2.682784E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.028 | TFLOPs: 23.47 | +63: iteration 4090/ 73814 | consumed samples: 2094080 | consumed tokens: 4288675840 | elapsed time per iteration (s): 2.23 | learning rate: 1.991E-04 | global batch size: 512 | lm loss: 2.660706E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.382 | TFLOPs: 23.61 | +63: iteration 4100/ 73814 | consumed samples: 2099200 | consumed tokens: 4299161600 | elapsed time per iteration (s): 2.25 | learning rate: 1.991E-04 | global batch size: 512 | lm loss: 2.673016E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.421 | TFLOPs: 23.41 | +63: iteration 4110/ 73814 | consumed samples: 2104320 | consumed tokens: 4309647360 | elapsed time per iteration (s): 2.26 | learning rate: 1.991E-04 | global batch size: 512 | lm loss: 2.690504E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.715 | TFLOPs: 23.34 | +63: iteration 4120/ 73814 | consumed samples: 2109440 | consumed tokens: 4320133120 | elapsed time per iteration (s): 2.24 | learning rate: 1.991E-04 | global batch size: 512 | lm loss: 2.692560E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.100 | TFLOPs: 23.48 | +63: iteration 4130/ 73814 | consumed samples: 2114560 | consumed tokens: 4330618880 | elapsed time per iteration (s): 2.25 | learning rate: 1.990E-04 | global batch size: 512 | lm loss: 2.677247E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.016 | TFLOPs: 23.47 | +63: iteration 4140/ 73814 | consumed samples: 2119680 | consumed tokens: 4341104640 | elapsed time per iteration (s): 2.26 | learning rate: 1.990E-04 | global batch size: 512 | lm loss: 2.686634E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.644 | TFLOPs: 23.33 | +63: iteration 4150/ 73814 | consumed samples: 2124800 | consumed tokens: 4351590400 | elapsed time per iteration (s): 2.24 | learning rate: 1.990E-04 | global batch size: 512 | lm loss: 2.659825E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.056 | TFLOPs: 23.58 | +63: iteration 4160/ 73814 | consumed samples: 2129920 | consumed tokens: 4362076160 | elapsed time per iteration (s): 2.23 | learning rate: 1.990E-04 | global batch size: 512 | lm loss: 2.657611E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.413 | TFLOPs: 23.62 | +63: iteration 4170/ 73814 | consumed samples: 2135040 | consumed tokens: 4372561920 | elapsed time per iteration (s): 2.24 | learning rate: 1.990E-04 | global batch size: 512 | lm loss: 2.657812E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.513 | TFLOPs: 23.52 | +63: iteration 4180/ 73814 | consumed samples: 2140160 | consumed tokens: 4383047680 | elapsed time per iteration (s): 2.24 | learning rate: 1.990E-04 | global batch size: 512 | lm loss: 2.668477E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.529 | TFLOPs: 23.53 | +63: iteration 4190/ 73814 | consumed samples: 2145280 | consumed tokens: 4393533440 | elapsed time per iteration (s): 2.25 | learning rate: 1.990E-04 | global batch size: 512 | lm loss: 2.659212E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.543 | TFLOPs: 23.42 | +63: iteration 4200/ 73814 | consumed samples: 2150400 | consumed tokens: 4404019200 | elapsed time per iteration (s): 2.26 | learning rate: 1.990E-04 | global batch size: 512 | lm loss: 2.663657E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.209 | TFLOPs: 23.29 | +63: iteration 4210/ 73814 | consumed samples: 2155520 | consumed tokens: 4414504960 | elapsed time per iteration (s): 2.23 | learning rate: 1.990E-04 | global batch size: 512 | lm loss: 2.660086E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.248 | TFLOPs: 23.60 | +63: iteration 4220/ 73814 | consumed samples: 2160640 | consumed tokens: 4424990720 | elapsed time per iteration (s): 2.23 | learning rate: 1.990E-04 | global batch size: 512 | lm loss: 2.652522E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.388 | TFLOPs: 23.61 | +63: iteration 4230/ 73814 | consumed samples: 2165760 | consumed tokens: 4435476480 | elapsed time per iteration (s): 2.26 | learning rate: 1.990E-04 | global batch size: 512 | lm loss: 2.661088E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.264 | TFLOPs: 23.29 | +63: iteration 4240/ 73814 | consumed samples: 2170880 | consumed tokens: 4445962240 | elapsed time per iteration (s): 2.23 | learning rate: 1.990E-04 | global batch size: 512 | lm loss: 2.657682E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.434 | TFLOPs: 23.62 | +63: iteration 4250/ 73814 | consumed samples: 2176000 | consumed tokens: 4456448000 | elapsed time per iteration (s): 2.23 | learning rate: 1.990E-04 | global batch size: 512 | lm loss: 2.685961E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.713 | TFLOPs: 23.65 | +63: iteration 4260/ 73814 | consumed samples: 2181120 | consumed tokens: 4466933760 | elapsed time per iteration (s): 2.24 | learning rate: 1.990E-04 | global batch size: 512 | lm loss: 2.661745E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.811 | TFLOPs: 23.56 | +63: iteration 4270/ 73814 | consumed samples: 2186240 | consumed tokens: 4477419520 | elapsed time per iteration (s): 2.30 | learning rate: 1.990E-04 | global batch size: 512 | lm loss: 2.662782E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.055 | TFLOPs: 22.96 | +63: iteration 4280/ 73814 | consumed samples: 2191360 | consumed tokens: 4487905280 | elapsed time per iteration (s): 2.23 | learning rate: 1.990E-04 | global batch size: 512 | lm loss: 2.647074E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.793 | TFLOPs: 23.66 | +63: iteration 4290/ 73814 | consumed samples: 2196480 | consumed tokens: 4498391040 | elapsed time per iteration (s): 2.26 | learning rate: 1.990E-04 | global batch size: 512 | lm loss: 2.642353E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.851 | TFLOPs: 23.35 | +63: iteration 4300/ 73814 | consumed samples: 2201600 | consumed tokens: 4508876800 | elapsed time per iteration (s): 2.25 | learning rate: 1.989E-04 | global batch size: 512 | lm loss: 2.647062E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.331 | TFLOPs: 23.40 | +63: iteration 4310/ 73814 | consumed samples: 2206720 | consumed tokens: 4519362560 | elapsed time per iteration (s): 2.23 | learning rate: 1.989E-04 | global batch size: 512 | lm loss: 2.637076E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.319 | TFLOPs: 23.61 | +63: iteration 4320/ 73814 | consumed samples: 2211840 | consumed tokens: 4529848320 | elapsed time per iteration (s): 2.24 | learning rate: 1.989E-04 | global batch size: 512 | lm loss: 2.700072E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.912 | TFLOPs: 23.57 | +63: iteration 4330/ 73814 | consumed samples: 2216960 | consumed tokens: 4540334080 | elapsed time per iteration (s): 2.24 | learning rate: 1.989E-04 | global batch size: 512 | lm loss: 2.646280E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.493 | TFLOPs: 23.52 | +63: iteration 4340/ 73814 | consumed samples: 2222080 | consumed tokens: 4550819840 | elapsed time per iteration (s): 2.25 | learning rate: 1.989E-04 | global batch size: 512 | lm loss: 2.648345E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.892 | TFLOPs: 23.46 | +63: iteration 4350/ 73814 | consumed samples: 2227200 | consumed tokens: 4561305600 | elapsed time per iteration (s): 2.25 | learning rate: 1.989E-04 | global batch size: 512 | lm loss: 2.647638E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.791 | TFLOPs: 23.45 | +63: iteration 4360/ 73814 | consumed samples: 2232320 | consumed tokens: 4571791360 | elapsed time per iteration (s): 2.24 | learning rate: 1.989E-04 | global batch size: 512 | lm loss: 2.643912E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.537 | TFLOPs: 23.53 | +63: iteration 4370/ 73814 | consumed samples: 2237440 | consumed tokens: 4582277120 | elapsed time per iteration (s): 2.23 | learning rate: 1.989E-04 | global batch size: 512 | lm loss: 2.651846E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.317 | TFLOPs: 23.61 | +63: iteration 4380/ 73814 | consumed samples: 2242560 | consumed tokens: 4592762880 | elapsed time per iteration (s): 2.23 | learning rate: 1.989E-04 | global batch size: 512 | lm loss: 2.633721E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.461 | TFLOPs: 23.62 | +63: iteration 4390/ 73814 | consumed samples: 2247680 | consumed tokens: 4603248640 | elapsed time per iteration (s): 2.25 | learning rate: 1.989E-04 | global batch size: 512 | lm loss: 2.658736E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.101 | TFLOPs: 23.38 | +63: iteration 4400/ 73814 | consumed samples: 2252800 | consumed tokens: 4613734400 | elapsed time per iteration (s): 2.23 | learning rate: 1.989E-04 | global batch size: 512 | lm loss: 2.651070E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.502 | TFLOPs: 23.63 | +63: iteration 4410/ 73814 | consumed samples: 2257920 | consumed tokens: 4624220160 | elapsed time per iteration (s): 2.23 | learning rate: 1.989E-04 | global batch size: 512 | lm loss: 2.646730E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.262 | TFLOPs: 23.60 | +63: iteration 4420/ 73814 | consumed samples: 2263040 | consumed tokens: 4634705920 | elapsed time per iteration (s): 3.96 | learning rate: 1.989E-04 | global batch size: 512 | lm loss: 2.643011E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 129.284 | TFLOPs: 13.31 | +63: iteration 4430/ 73814 | consumed samples: 2268160 | consumed tokens: 4645191680 | elapsed time per iteration (s): 2.23 | learning rate: 1.989E-04 | global batch size: 512 | lm loss: 2.657525E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.266 | TFLOPs: 23.60 | +63: iteration 4440/ 73814 | consumed samples: 2273280 | consumed tokens: 4655677440 | elapsed time per iteration (s): 2.23 | learning rate: 1.989E-04 | global batch size: 512 | lm loss: 2.646273E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.509 | TFLOPs: 23.63 | +63: iteration 4450/ 73814 | consumed samples: 2278400 | consumed tokens: 4666163200 | elapsed time per iteration (s): 2.26 | learning rate: 1.989E-04 | global batch size: 512 | lm loss: 2.646180E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.683 | TFLOPs: 23.34 | +63: iteration 4460/ 73814 | consumed samples: 2283520 | consumed tokens: 4676648960 | elapsed time per iteration (s): 2.23 | learning rate: 1.989E-04 | global batch size: 512 | lm loss: 2.634970E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.487 | TFLOPs: 23.62 | +63: iteration 4470/ 73814 | consumed samples: 2288640 | consumed tokens: 4687134720 | elapsed time per iteration (s): 2.23 | learning rate: 1.988E-04 | global batch size: 512 | lm loss: 2.645978E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.528 | TFLOPs: 23.63 | +63: iteration 4480/ 73814 | consumed samples: 2293760 | consumed tokens: 4697620480 | elapsed time per iteration (s): 2.24 | learning rate: 1.988E-04 | global batch size: 512 | lm loss: 2.635522E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.868 | TFLOPs: 23.56 | +63: iteration 4490/ 73814 | consumed samples: 2298880 | consumed tokens: 4708106240 | elapsed time per iteration (s): 2.32 | learning rate: 1.988E-04 | global batch size: 512 | lm loss: 2.634188E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.601 | TFLOPs: 22.71 | +63: iteration 4500/ 73814 | consumed samples: 2304000 | consumed tokens: 4718592000 | elapsed time per iteration (s): 2.38 | learning rate: 1.988E-04 | global batch size: 512 | lm loss: 2.642269E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.550 | TFLOPs: 22.19 | +63: iteration 4510/ 73814 | consumed samples: 2309120 | consumed tokens: 4729077760 | elapsed time per iteration (s): 2.39 | learning rate: 1.988E-04 | global batch size: 512 | lm loss: 2.632916E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.897 | TFLOPs: 22.02 | +63: iteration 4520/ 73814 | consumed samples: 2314240 | consumed tokens: 4739563520 | elapsed time per iteration (s): 2.39 | learning rate: 1.988E-04 | global batch size: 512 | lm loss: 2.615075E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.405 | TFLOPs: 22.07 | +63: iteration 4530/ 73814 | consumed samples: 2319360 | consumed tokens: 4750049280 | elapsed time per iteration (s): 2.35 | learning rate: 1.988E-04 | global batch size: 512 | lm loss: 2.633936E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.933 | TFLOPs: 22.44 | +63: iteration 4540/ 73814 | consumed samples: 2324480 | consumed tokens: 4760535040 | elapsed time per iteration (s): 2.27 | learning rate: 1.988E-04 | global batch size: 512 | lm loss: 2.642476E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.907 | TFLOPs: 23.26 | +63: iteration 4550/ 73814 | consumed samples: 2329600 | consumed tokens: 4771020800 | elapsed time per iteration (s): 2.24 | learning rate: 1.988E-04 | global batch size: 512 | lm loss: 2.633515E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.033 | TFLOPs: 23.58 | +63: iteration 4560/ 73814 | consumed samples: 2334720 | consumed tokens: 4781506560 | elapsed time per iteration (s): 2.28 | learning rate: 1.988E-04 | global batch size: 512 | lm loss: 2.612657E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.917 | TFLOPs: 23.15 | +63: iteration 4570/ 73814 | consumed samples: 2339840 | consumed tokens: 4791992320 | elapsed time per iteration (s): 2.24 | learning rate: 1.988E-04 | global batch size: 512 | lm loss: 2.625065E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.987 | TFLOPs: 23.57 | +63: iteration 4580/ 73814 | consumed samples: 2344960 | consumed tokens: 4802478080 | elapsed time per iteration (s): 2.25 | learning rate: 1.988E-04 | global batch size: 512 | lm loss: 2.611889E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.359 | TFLOPs: 23.41 | +63: iteration 4590/ 73814 | consumed samples: 2350080 | consumed tokens: 4812963840 | elapsed time per iteration (s): 2.26 | learning rate: 1.988E-04 | global batch size: 512 | lm loss: 2.617122E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.758 | TFLOPs: 23.34 | +63: iteration 4600/ 73814 | consumed samples: 2355200 | consumed tokens: 4823449600 | elapsed time per iteration (s): 2.25 | learning rate: 1.988E-04 | global batch size: 512 | lm loss: 2.631514E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.485 | TFLOPs: 23.42 | +63: iteration 4610/ 73814 | consumed samples: 2360320 | consumed tokens: 4833935360 | elapsed time per iteration (s): 2.23 | learning rate: 1.988E-04 | global batch size: 512 | lm loss: 2.637484E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.525 | TFLOPs: 23.63 | +63: iteration 4620/ 73814 | consumed samples: 2365440 | consumed tokens: 4844421120 | elapsed time per iteration (s): 2.30 | learning rate: 1.987E-04 | global batch size: 512 | lm loss: 2.632369E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.406 | TFLOPs: 22.90 | +63: iteration 4630/ 73814 | consumed samples: 2370560 | consumed tokens: 4854906880 | elapsed time per iteration (s): 2.25 | learning rate: 1.987E-04 | global batch size: 512 | lm loss: 2.657200E+00 | grad norm: 0.387 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.180 | TFLOPs: 23.39 | +63: iteration 4640/ 73814 | consumed samples: 2375680 | consumed tokens: 4865392640 | elapsed time per iteration (s): 2.24 | learning rate: 1.987E-04 | global batch size: 512 | lm loss: 2.638112E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.733 | TFLOPs: 23.55 | +63: iteration 4650/ 73814 | consumed samples: 2380800 | consumed tokens: 4875878400 | elapsed time per iteration (s): 2.26 | learning rate: 1.987E-04 | global batch size: 512 | lm loss: 2.621607E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.310 | TFLOPs: 23.30 | +63: iteration 4660/ 73814 | consumed samples: 2385920 | consumed tokens: 4886364160 | elapsed time per iteration (s): 2.30 | learning rate: 1.987E-04 | global batch size: 512 | lm loss: 2.619420E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.895 | TFLOPs: 22.95 | +63: iteration 4670/ 73814 | consumed samples: 2391040 | consumed tokens: 4896849920 | elapsed time per iteration (s): 2.28 | learning rate: 1.987E-04 | global batch size: 512 | lm loss: 2.616523E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.321 | TFLOPs: 23.09 | +63: iteration 4680/ 73814 | consumed samples: 2396160 | consumed tokens: 4907335680 | elapsed time per iteration (s): 2.24 | learning rate: 1.987E-04 | global batch size: 512 | lm loss: 2.616291E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.128 | TFLOPs: 23.48 | +63: iteration 4690/ 73814 | consumed samples: 2401280 | consumed tokens: 4917821440 | elapsed time per iteration (s): 2.25 | learning rate: 1.987E-04 | global batch size: 512 | lm loss: 2.614884E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.339 | TFLOPs: 23.40 | +63: iteration 4700/ 73814 | consumed samples: 2406400 | consumed tokens: 4928307200 | elapsed time per iteration (s): 2.23 | learning rate: 1.987E-04 | global batch size: 512 | lm loss: 2.604834E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.389 | TFLOPs: 23.61 | +63: iteration 4710/ 73814 | consumed samples: 2411520 | consumed tokens: 4938792960 | elapsed time per iteration (s): 2.25 | learning rate: 1.987E-04 | global batch size: 512 | lm loss: 2.621050E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.275 | TFLOPs: 23.40 | +63: iteration 4720/ 73814 | consumed samples: 2416640 | consumed tokens: 4949278720 | elapsed time per iteration (s): 2.24 | learning rate: 1.987E-04 | global batch size: 512 | lm loss: 2.636504E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.967 | TFLOPs: 23.57 | +63: iteration 4730/ 73814 | consumed samples: 2421760 | consumed tokens: 4959764480 | elapsed time per iteration (s): 2.30 | learning rate: 1.987E-04 | global batch size: 512 | lm loss: 2.602888E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.658 | TFLOPs: 22.92 | +63: iteration 4740/ 73814 | consumed samples: 2426880 | consumed tokens: 4970250240 | elapsed time per iteration (s): 2.25 | learning rate: 1.987E-04 | global batch size: 512 | lm loss: 2.623807E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.717 | TFLOPs: 23.44 | +63: iteration 4750/ 73814 | consumed samples: 2432000 | consumed tokens: 4980736000 | elapsed time per iteration (s): 2.24 | learning rate: 1.987E-04 | global batch size: 512 | lm loss: 2.604889E+00 | grad norm: 0.394 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.172 | TFLOPs: 23.49 | +63: iteration 4760/ 73814 | consumed samples: 2437120 | consumed tokens: 4991221760 | elapsed time per iteration (s): 2.23 | learning rate: 1.987E-04 | global batch size: 512 | lm loss: 2.636404E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.780 | TFLOPs: 23.65 | +63: iteration 4770/ 73814 | consumed samples: 2442240 | consumed tokens: 5001707520 | elapsed time per iteration (s): 2.23 | learning rate: 1.987E-04 | global batch size: 512 | lm loss: 2.629082E+00 | grad norm: 0.622 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.331 | TFLOPs: 23.61 | +63: iteration 4780/ 73814 | consumed samples: 2447360 | consumed tokens: 5012193280 | elapsed time per iteration (s): 2.28 | learning rate: 1.986E-04 | global batch size: 512 | lm loss: 3.050629E+00 | grad norm: 6.800 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.078 | TFLOPs: 23.07 | +63: iteration 4790/ 73814 | consumed samples: 2452480 | consumed tokens: 5022679040 | elapsed time per iteration (s): 2.25 | learning rate: 1.986E-04 | global batch size: 512 | lm loss: 3.367044E+00 | grad norm: 3.529 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.830 | TFLOPs: 23.45 | +63: iteration 4800/ 73814 | consumed samples: 2457600 | consumed tokens: 5033164800 | elapsed time per iteration (s): 2.25 | learning rate: 1.986E-04 | global batch size: 512 | lm loss: 3.550697E+00 | grad norm: 3.552 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.966 | TFLOPs: 23.47 | +63: iteration 4810/ 73814 | consumed samples: 2462720 | consumed tokens: 5043650560 | elapsed time per iteration (s): 2.26 | learning rate: 1.986E-04 | global batch size: 512 | lm loss: 3.457948E+00 | grad norm: 1.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.764 | TFLOPs: 23.34 | +63: iteration 4820/ 73814 | consumed samples: 2467840 | consumed tokens: 5054136320 | elapsed time per iteration (s): 2.27 | learning rate: 1.986E-04 | global batch size: 512 | lm loss: 3.253845E+00 | grad norm: 0.931 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.328 | TFLOPs: 23.20 | +63: iteration 4830/ 73814 | consumed samples: 2472960 | consumed tokens: 5064622080 | elapsed time per iteration (s): 2.24 | learning rate: 1.986E-04 | global batch size: 512 | lm loss: 3.105210E+00 | grad norm: 0.864 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.693 | TFLOPs: 23.54 | +63: iteration 4840/ 73814 | consumed samples: 2478080 | consumed tokens: 5075107840 | elapsed time per iteration (s): 2.24 | learning rate: 1.986E-04 | global batch size: 512 | lm loss: 2.886592E+00 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.434 | TFLOPs: 23.52 | +63: iteration 4850/ 73814 | consumed samples: 2483200 | consumed tokens: 5085593600 | elapsed time per iteration (s): 2.23 | learning rate: 1.986E-04 | global batch size: 512 | lm loss: 2.779702E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.479 | TFLOPs: 23.62 | +63: iteration 4860/ 73814 | consumed samples: 2488320 | consumed tokens: 5096079360 | elapsed time per iteration (s): 2.23 | learning rate: 1.986E-04 | global batch size: 512 | lm loss: 2.729762E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.210 | TFLOPs: 23.60 | +63: iteration 4870/ 73814 | consumed samples: 2493440 | consumed tokens: 5106565120 | elapsed time per iteration (s): 2.31 | learning rate: 1.986E-04 | global batch size: 512 | lm loss: 2.691475E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.832 | TFLOPs: 22.84 | +63: iteration 4880/ 73814 | consumed samples: 2498560 | consumed tokens: 5117050880 | elapsed time per iteration (s): 2.25 | learning rate: 1.986E-04 | global batch size: 512 | lm loss: 2.707273E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.227 | TFLOPs: 23.39 | +63: iteration 4890/ 73814 | consumed samples: 2503680 | consumed tokens: 5127536640 | elapsed time per iteration (s): 2.22 | learning rate: 1.986E-04 | global batch size: 512 | lm loss: 2.671367E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.306 | TFLOPs: 23.71 | +63: iteration 4900/ 73814 | consumed samples: 2508800 | consumed tokens: 5138022400 | elapsed time per iteration (s): 2.23 | learning rate: 1.986E-04 | global batch size: 512 | lm loss: 2.670761E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.256 | TFLOPs: 23.60 | +63: iteration 4910/ 73814 | consumed samples: 2513920 | consumed tokens: 5148508160 | elapsed time per iteration (s): 2.26 | learning rate: 1.986E-04 | global batch size: 512 | lm loss: 2.632487E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.436 | TFLOPs: 23.31 | +63: iteration 4920/ 73814 | consumed samples: 2519040 | consumed tokens: 5158993920 | elapsed time per iteration (s): 2.49 | learning rate: 1.985E-04 | global batch size: 512 | lm loss: 2.639940E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.586 | TFLOPs: 21.16 | +63: iteration 4930/ 73814 | consumed samples: 2524160 | consumed tokens: 5169479680 | elapsed time per iteration (s): 2.36 | learning rate: 1.985E-04 | global batch size: 512 | lm loss: 2.609629E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.879 | TFLOPs: 22.33 | +63: iteration 4940/ 73814 | consumed samples: 2529280 | consumed tokens: 5179965440 | elapsed time per iteration (s): 2.37 | learning rate: 1.985E-04 | global batch size: 512 | lm loss: 2.634189E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.120 | TFLOPs: 22.25 | +63: iteration 4950/ 73814 | consumed samples: 2534400 | consumed tokens: 5190451200 | elapsed time per iteration (s): 2.29 | learning rate: 1.985E-04 | global batch size: 512 | lm loss: 2.648847E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.398 | TFLOPs: 23.00 | +63: iteration 4960/ 73814 | consumed samples: 2539520 | consumed tokens: 5200936960 | elapsed time per iteration (s): 2.26 | learning rate: 1.985E-04 | global batch size: 512 | lm loss: 2.653343E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.076 | TFLOPs: 23.27 | +63: iteration 4970/ 73814 | consumed samples: 2544640 | consumed tokens: 5211422720 | elapsed time per iteration (s): 2.53 | learning rate: 1.985E-04 | global batch size: 512 | lm loss: 2.631595E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.355 | TFLOPs: 20.83 | +63: iteration 4980/ 73814 | consumed samples: 2549760 | consumed tokens: 5221908480 | elapsed time per iteration (s): 2.28 | learning rate: 1.985E-04 | global batch size: 512 | lm loss: 2.643845E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.367 | TFLOPs: 23.10 | +63: iteration 4990/ 73814 | consumed samples: 2554880 | consumed tokens: 5232394240 | elapsed time per iteration (s): 2.30 | learning rate: 1.985E-04 | global batch size: 512 | lm loss: 2.604811E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.500 | TFLOPs: 22.91 | +63: iteration 5000/ 73814 | consumed samples: 2560000 | consumed tokens: 5242880000 | elapsed time per iteration (s): 2.26 | learning rate: 1.985E-04 | global batch size: 512 | lm loss: 2.634410E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.783 | TFLOPs: 23.35 | +63: ------------------------------------------------------------------------------------------ +63: valid loss at iteration 5000 | lm loss value: 2.533657E+00 | lm loss PPL: 1.259950E+01 | +63: ------------------------------------------------------------------------------------------ +63: iteration 5010/ 73814 | consumed samples: 2565120 | consumed tokens: 5253365760 | elapsed time per iteration (s): 2.29 | learning rate: 1.985E-04 | global batch size: 512 | lm loss: 2.629141E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.449 | TFLOPs: 23.00 | +63: iteration 5020/ 73814 | consumed samples: 2570240 | consumed tokens: 5263851520 | elapsed time per iteration (s): 2.25 | learning rate: 1.985E-04 | global batch size: 512 | lm loss: 2.635336E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.929 | TFLOPs: 23.46 | +63: iteration 5030/ 73814 | consumed samples: 2575360 | consumed tokens: 5274337280 | elapsed time per iteration (s): 2.26 | learning rate: 1.985E-04 | global batch size: 512 | lm loss: 2.616809E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.013 | TFLOPs: 23.37 | +63: iteration 5040/ 73814 | consumed samples: 2580480 | consumed tokens: 5284823040 | elapsed time per iteration (s): 2.26 | learning rate: 1.985E-04 | global batch size: 512 | lm loss: 2.606015E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.855 | TFLOPs: 23.35 | +63: iteration 5050/ 73814 | consumed samples: 2585600 | consumed tokens: 5295308800 | elapsed time per iteration (s): 2.24 | learning rate: 1.985E-04 | global batch size: 512 | lm loss: 2.592662E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.323 | TFLOPs: 23.50 | +63: iteration 5060/ 73814 | consumed samples: 2590720 | consumed tokens: 5305794560 | elapsed time per iteration (s): 2.30 | learning rate: 1.985E-04 | global batch size: 512 | lm loss: 2.615521E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.511 | TFLOPs: 22.91 | +63: iteration 5070/ 73814 | consumed samples: 2595840 | consumed tokens: 5316280320 | elapsed time per iteration (s): 2.26 | learning rate: 1.984E-04 | global batch size: 512 | lm loss: 2.604068E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.752 | TFLOPs: 23.34 | +63: iteration 5080/ 73814 | consumed samples: 2600960 | consumed tokens: 5326766080 | elapsed time per iteration (s): 2.25 | learning rate: 1.984E-04 | global batch size: 512 | lm loss: 2.631382E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.050 | TFLOPs: 23.48 | +63: iteration 5090/ 73814 | consumed samples: 2606080 | consumed tokens: 5337251840 | elapsed time per iteration (s): 2.25 | learning rate: 1.984E-04 | global batch size: 512 | lm loss: 2.612720E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.323 | TFLOPs: 23.40 | +63: iteration 5100/ 73814 | consumed samples: 2611200 | consumed tokens: 5347737600 | elapsed time per iteration (s): 2.23 | learning rate: 1.984E-04 | global batch size: 512 | lm loss: 2.599939E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.443 | TFLOPs: 23.62 | +63: iteration 5110/ 73814 | consumed samples: 2616320 | consumed tokens: 5358223360 | elapsed time per iteration (s): 2.23 | learning rate: 1.984E-04 | global batch size: 512 | lm loss: 2.576412E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.605 | TFLOPs: 23.64 | +63: iteration 5120/ 73814 | consumed samples: 2621440 | consumed tokens: 5368709120 | elapsed time per iteration (s): 2.31 | learning rate: 1.984E-04 | global batch size: 512 | lm loss: 2.604162E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.360 | TFLOPs: 22.79 | +63: iteration 5130/ 73814 | consumed samples: 2626560 | consumed tokens: 5379194880 | elapsed time per iteration (s): 2.28 | learning rate: 1.984E-04 | global batch size: 512 | lm loss: 2.587427E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.978 | TFLOPs: 23.16 | +63: iteration 5140/ 73814 | consumed samples: 2631680 | consumed tokens: 5389680640 | elapsed time per iteration (s): 2.54 | learning rate: 1.984E-04 | global batch size: 512 | lm loss: 2.591294E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.450 | TFLOPs: 20.74 | +63: iteration 5150/ 73814 | consumed samples: 2636800 | consumed tokens: 5400166400 | elapsed time per iteration (s): 2.26 | learning rate: 1.984E-04 | global batch size: 512 | lm loss: 2.582208E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.772 | TFLOPs: 23.35 | +63: iteration 5160/ 73814 | consumed samples: 2641920 | consumed tokens: 5410652160 | elapsed time per iteration (s): 2.26 | learning rate: 1.984E-04 | global batch size: 512 | lm loss: 2.610431E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.920 | TFLOPs: 23.36 | +63: iteration 5170/ 73814 | consumed samples: 2647040 | consumed tokens: 5421137920 | elapsed time per iteration (s): 2.24 | learning rate: 1.984E-04 | global batch size: 512 | lm loss: 2.611950E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.860 | TFLOPs: 23.56 | +63: iteration 5180/ 73814 | consumed samples: 2652160 | consumed tokens: 5431623680 | elapsed time per iteration (s): 2.24 | learning rate: 1.984E-04 | global batch size: 512 | lm loss: 2.603170E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.970 | TFLOPs: 23.57 | +63: iteration 5190/ 73814 | consumed samples: 2657280 | consumed tokens: 5442109440 | elapsed time per iteration (s): 2.24 | learning rate: 1.984E-04 | global batch size: 512 | lm loss: 2.585007E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.014 | TFLOPs: 23.58 | +63: iteration 5200/ 73814 | consumed samples: 2662400 | consumed tokens: 5452595200 | elapsed time per iteration (s): 2.24 | learning rate: 1.983E-04 | global batch size: 512 | lm loss: 2.604645E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.677 | TFLOPs: 23.54 | +63: iteration 5210/ 73814 | consumed samples: 2667520 | consumed tokens: 5463080960 | elapsed time per iteration (s): 2.27 | learning rate: 1.983E-04 | global batch size: 512 | lm loss: 2.582846E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.553 | TFLOPs: 23.22 | +63: iteration 5220/ 73814 | consumed samples: 2672640 | consumed tokens: 5473566720 | elapsed time per iteration (s): 2.25 | learning rate: 1.983E-04 | global batch size: 512 | lm loss: 2.579410E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.387 | TFLOPs: 23.41 | +63: iteration 5230/ 73814 | consumed samples: 2677760 | consumed tokens: 5484052480 | elapsed time per iteration (s): 2.23 | learning rate: 1.983E-04 | global batch size: 512 | lm loss: 2.588039E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.500 | TFLOPs: 23.63 | +63: iteration 5240/ 73814 | consumed samples: 2682880 | consumed tokens: 5494538240 | elapsed time per iteration (s): 2.23 | learning rate: 1.983E-04 | global batch size: 512 | lm loss: 2.577716E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.512 | TFLOPs: 23.63 | +63: iteration 5250/ 73814 | consumed samples: 2688000 | consumed tokens: 5505024000 | elapsed time per iteration (s): 2.23 | learning rate: 1.983E-04 | global batch size: 512 | lm loss: 2.601241E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.409 | TFLOPs: 23.62 | +63: iteration 5260/ 73814 | consumed samples: 2693120 | consumed tokens: 5515509760 | elapsed time per iteration (s): 2.23 | learning rate: 1.983E-04 | global batch size: 512 | lm loss: 2.597050E+00 | grad norm: 0.487 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.256 | TFLOPs: 23.60 | +63: iteration 5270/ 73814 | consumed samples: 2698240 | consumed tokens: 5525995520 | elapsed time per iteration (s): 2.23 | learning rate: 1.983E-04 | global batch size: 512 | lm loss: 2.615949E+00 | grad norm: 1.073 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.526 | TFLOPs: 23.63 | +63: iteration 5280/ 73814 | consumed samples: 2703360 | consumed tokens: 5536481280 | elapsed time per iteration (s): 2.24 | learning rate: 1.983E-04 | global batch size: 512 | lm loss: 2.641268E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.091 | TFLOPs: 23.48 | +63: iteration 5290/ 73814 | consumed samples: 2708480 | consumed tokens: 5546967040 | elapsed time per iteration (s): 2.24 | learning rate: 1.983E-04 | global batch size: 512 | lm loss: 2.654468E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.261 | TFLOPs: 23.50 | +63: iteration 5300/ 73814 | consumed samples: 2713600 | consumed tokens: 5557452800 | elapsed time per iteration (s): 2.24 | learning rate: 1.983E-04 | global batch size: 512 | lm loss: 2.607751E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.660 | TFLOPs: 23.54 | +63: iteration 5310/ 73814 | consumed samples: 2718720 | consumed tokens: 5567938560 | elapsed time per iteration (s): 2.24 | learning rate: 1.983E-04 | global batch size: 512 | lm loss: 2.602875E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.968 | TFLOPs: 23.57 | +63: iteration 5320/ 73814 | consumed samples: 2723840 | consumed tokens: 5578424320 | elapsed time per iteration (s): 2.25 | learning rate: 1.983E-04 | global batch size: 512 | lm loss: 2.581283E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.871 | TFLOPs: 23.46 | +63: iteration 5330/ 73814 | consumed samples: 2728960 | consumed tokens: 5588910080 | elapsed time per iteration (s): 2.24 | learning rate: 1.983E-04 | global batch size: 512 | lm loss: 2.594586E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.708 | TFLOPs: 23.54 | +63: iteration 5340/ 73814 | consumed samples: 2734080 | consumed tokens: 5599395840 | elapsed time per iteration (s): 2.23 | learning rate: 1.982E-04 | global batch size: 512 | lm loss: 2.581359E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.725 | TFLOPs: 23.65 | +63: iteration 5350/ 73814 | consumed samples: 2739200 | consumed tokens: 5609881600 | elapsed time per iteration (s): 2.23 | learning rate: 1.982E-04 | global batch size: 512 | lm loss: 2.588956E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.251 | TFLOPs: 23.60 | +63: iteration 5360/ 73814 | consumed samples: 2744320 | consumed tokens: 5620367360 | elapsed time per iteration (s): 2.27 | learning rate: 1.982E-04 | global batch size: 512 | lm loss: 2.596279E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.820 | TFLOPs: 23.25 | +63: iteration 5370/ 73814 | consumed samples: 2749440 | consumed tokens: 5630853120 | elapsed time per iteration (s): 2.23 | learning rate: 1.982E-04 | global batch size: 512 | lm loss: 2.573156E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.718 | TFLOPs: 23.65 | +63: iteration 5380/ 73814 | consumed samples: 2754560 | consumed tokens: 5641338880 | elapsed time per iteration (s): 2.23 | learning rate: 1.982E-04 | global batch size: 512 | lm loss: 2.569034E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.814 | TFLOPs: 23.66 | +63: iteration 5390/ 73814 | consumed samples: 2759680 | consumed tokens: 5651824640 | elapsed time per iteration (s): 2.27 | learning rate: 1.982E-04 | global batch size: 512 | lm loss: 2.589476E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.397 | TFLOPs: 23.20 | +63: iteration 5400/ 73814 | consumed samples: 2764800 | consumed tokens: 5662310400 | elapsed time per iteration (s): 2.25 | learning rate: 1.982E-04 | global batch size: 512 | lm loss: 2.566816E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.289 | TFLOPs: 23.40 | +63: iteration 5410/ 73814 | consumed samples: 2769920 | consumed tokens: 5672796160 | elapsed time per iteration (s): 2.23 | learning rate: 1.982E-04 | global batch size: 512 | lm loss: 2.559188E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.701 | TFLOPs: 23.65 | +63: iteration 5420/ 73814 | consumed samples: 2775040 | consumed tokens: 5683281920 | elapsed time per iteration (s): 2.23 | learning rate: 1.982E-04 | global batch size: 512 | lm loss: 2.570559E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.709 | TFLOPs: 23.65 | +63: iteration 5430/ 73814 | consumed samples: 2780160 | consumed tokens: 5693767680 | elapsed time per iteration (s): 2.23 | learning rate: 1.982E-04 | global batch size: 512 | lm loss: 2.593178E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.516 | TFLOPs: 23.63 | +63: iteration 5440/ 73814 | consumed samples: 2785280 | consumed tokens: 5704253440 | elapsed time per iteration (s): 2.26 | learning rate: 1.982E-04 | global batch size: 512 | lm loss: 2.582387E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.473 | TFLOPs: 23.31 | +63: iteration 5450/ 73814 | consumed samples: 2790400 | consumed tokens: 5714739200 | elapsed time per iteration (s): 2.23 | learning rate: 1.982E-04 | global batch size: 512 | lm loss: 2.556989E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.925 | TFLOPs: 23.67 | +63: iteration 5460/ 73814 | consumed samples: 2795520 | consumed tokens: 5725224960 | elapsed time per iteration (s): 2.26 | learning rate: 1.982E-04 | global batch size: 512 | lm loss: 2.562482E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.027 | TFLOPs: 23.37 | +63: iteration 5470/ 73814 | consumed samples: 2800640 | consumed tokens: 5735710720 | elapsed time per iteration (s): 2.24 | learning rate: 1.981E-04 | global batch size: 512 | lm loss: 2.540894E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.032 | TFLOPs: 23.58 | +63: iteration 5480/ 73814 | consumed samples: 2805760 | consumed tokens: 5746196480 | elapsed time per iteration (s): 2.24 | learning rate: 1.981E-04 | global batch size: 512 | lm loss: 2.555011E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.497 | TFLOPs: 23.52 | +63: iteration 5490/ 73814 | consumed samples: 2810880 | consumed tokens: 5756682240 | elapsed time per iteration (s): 2.25 | learning rate: 1.981E-04 | global batch size: 512 | lm loss: 2.575211E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.383 | TFLOPs: 23.41 | +63: iteration 5500/ 73814 | consumed samples: 2816000 | consumed tokens: 5767168000 | elapsed time per iteration (s): 2.24 | learning rate: 1.981E-04 | global batch size: 512 | lm loss: 2.556662E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.467 | TFLOPs: 23.52 | +63: iteration 5510/ 73814 | consumed samples: 2821120 | consumed tokens: 5777653760 | elapsed time per iteration (s): 2.27 | learning rate: 1.981E-04 | global batch size: 512 | lm loss: 2.562744E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.633 | TFLOPs: 23.23 | +63: iteration 5520/ 73814 | consumed samples: 2826240 | consumed tokens: 5788139520 | elapsed time per iteration (s): 2.24 | learning rate: 1.981E-04 | global batch size: 512 | lm loss: 2.569641E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.733 | TFLOPs: 23.55 | +63: iteration 5530/ 73814 | consumed samples: 2831360 | consumed tokens: 5798625280 | elapsed time per iteration (s): 2.25 | learning rate: 1.981E-04 | global batch size: 512 | lm loss: 2.563688E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.013 | TFLOPs: 23.47 | +63: iteration 5540/ 73814 | consumed samples: 2836480 | consumed tokens: 5809111040 | elapsed time per iteration (s): 2.24 | learning rate: 1.981E-04 | global batch size: 512 | lm loss: 2.546336E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.798 | TFLOPs: 23.55 | +63: iteration 5550/ 73814 | consumed samples: 2841600 | consumed tokens: 5819596800 | elapsed time per iteration (s): 2.24 | learning rate: 1.981E-04 | global batch size: 512 | lm loss: 2.543604E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.094 | TFLOPs: 23.48 | +63: iteration 5560/ 73814 | consumed samples: 2846720 | consumed tokens: 5830082560 | elapsed time per iteration (s): 2.24 | learning rate: 1.981E-04 | global batch size: 512 | lm loss: 2.557886E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.771 | TFLOPs: 23.55 | +63: iteration 5570/ 73814 | consumed samples: 2851840 | consumed tokens: 5840568320 | elapsed time per iteration (s): 2.23 | learning rate: 1.981E-04 | global batch size: 512 | lm loss: 2.564126E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.565 | TFLOPs: 23.63 | +63: iteration 5580/ 73814 | consumed samples: 2856960 | consumed tokens: 5851054080 | elapsed time per iteration (s): 2.24 | learning rate: 1.981E-04 | global batch size: 512 | lm loss: 2.554154E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.805 | TFLOPs: 23.55 | +63: iteration 5590/ 73814 | consumed samples: 2862080 | consumed tokens: 5861539840 | elapsed time per iteration (s): 2.23 | learning rate: 1.980E-04 | global batch size: 512 | lm loss: 2.553399E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.813 | TFLOPs: 23.66 | +63: iteration 5600/ 73814 | consumed samples: 2867200 | consumed tokens: 5872025600 | elapsed time per iteration (s): 2.23 | learning rate: 1.980E-04 | global batch size: 512 | lm loss: 2.552151E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.886 | TFLOPs: 23.67 | +63: iteration 5610/ 73814 | consumed samples: 2872320 | consumed tokens: 5882511360 | elapsed time per iteration (s): 2.24 | learning rate: 1.980E-04 | global batch size: 512 | lm loss: 2.541806E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.949 | TFLOPs: 23.57 | +63: iteration 5620/ 73814 | consumed samples: 2877440 | consumed tokens: 5892997120 | elapsed time per iteration (s): 2.27 | learning rate: 1.980E-04 | global batch size: 512 | lm loss: 2.554930E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.172 | TFLOPs: 23.18 | +63: iteration 5630/ 73814 | consumed samples: 2882560 | consumed tokens: 5903482880 | elapsed time per iteration (s): 2.23 | learning rate: 1.980E-04 | global batch size: 512 | lm loss: 2.530129E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.972 | TFLOPs: 23.67 | +63: iteration 5640/ 73814 | consumed samples: 2887680 | consumed tokens: 5913968640 | elapsed time per iteration (s): 2.26 | learning rate: 1.980E-04 | global batch size: 512 | lm loss: 2.543806E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.469 | TFLOPs: 23.31 | +63: iteration 5650/ 73814 | consumed samples: 2892800 | consumed tokens: 5924454400 | elapsed time per iteration (s): 2.24 | learning rate: 1.980E-04 | global batch size: 512 | lm loss: 2.544576E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.907 | TFLOPs: 23.56 | +63: iteration 5660/ 73814 | consumed samples: 2897920 | consumed tokens: 5934940160 | elapsed time per iteration (s): 2.23 | learning rate: 1.980E-04 | global batch size: 512 | lm loss: 2.546182E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.981 | TFLOPs: 23.68 | +63: iteration 5670/ 73814 | consumed samples: 2903040 | consumed tokens: 5945425920 | elapsed time per iteration (s): 2.24 | learning rate: 1.980E-04 | global batch size: 512 | lm loss: 2.568255E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.004 | TFLOPs: 23.57 | +63: iteration 5680/ 73814 | consumed samples: 2908160 | consumed tokens: 5955911680 | elapsed time per iteration (s): 2.23 | learning rate: 1.980E-04 | global batch size: 512 | lm loss: 2.562455E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.315 | TFLOPs: 23.61 | +63: iteration 5690/ 73814 | consumed samples: 2913280 | consumed tokens: 5966397440 | elapsed time per iteration (s): 2.23 | learning rate: 1.980E-04 | global batch size: 512 | lm loss: 2.533801E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.738 | TFLOPs: 23.65 | +63: iteration 5700/ 73814 | consumed samples: 2918400 | consumed tokens: 5976883200 | elapsed time per iteration (s): 2.24 | learning rate: 1.980E-04 | global batch size: 512 | lm loss: 2.539443E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.709 | TFLOPs: 23.54 | +63: iteration 5710/ 73814 | consumed samples: 2923520 | consumed tokens: 5987368960 | elapsed time per iteration (s): 2.26 | learning rate: 1.980E-04 | global batch size: 512 | lm loss: 2.548202E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.736 | TFLOPs: 23.34 | +63: iteration 5720/ 73814 | consumed samples: 2928640 | consumed tokens: 5997854720 | elapsed time per iteration (s): 2.23 | learning rate: 1.979E-04 | global batch size: 512 | lm loss: 2.555355E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.734 | TFLOPs: 23.65 | +63: iteration 5730/ 73814 | consumed samples: 2933760 | consumed tokens: 6008340480 | elapsed time per iteration (s): 2.33 | learning rate: 1.979E-04 | global batch size: 512 | lm loss: 2.525302E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.780 | TFLOPs: 22.63 | +63: iteration 5740/ 73814 | consumed samples: 2938880 | consumed tokens: 6018826240 | elapsed time per iteration (s): 2.24 | learning rate: 1.979E-04 | global batch size: 512 | lm loss: 2.543958E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.567 | TFLOPs: 23.53 | +63: iteration 5750/ 73814 | consumed samples: 2944000 | consumed tokens: 6029312000 | elapsed time per iteration (s): 2.23 | learning rate: 1.979E-04 | global batch size: 512 | lm loss: 2.539673E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.675 | TFLOPs: 23.64 | +63: iteration 5760/ 73814 | consumed samples: 2949120 | consumed tokens: 6039797760 | elapsed time per iteration (s): 2.25 | learning rate: 1.979E-04 | global batch size: 512 | lm loss: 2.568827E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.921 | TFLOPs: 23.46 | +63: iteration 5770/ 73814 | consumed samples: 2954240 | consumed tokens: 6050283520 | elapsed time per iteration (s): 2.26 | learning rate: 1.979E-04 | global batch size: 512 | lm loss: 2.525762E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.321 | TFLOPs: 23.30 | +63: iteration 5780/ 73814 | consumed samples: 2959360 | consumed tokens: 6060769280 | elapsed time per iteration (s): 2.23 | learning rate: 1.979E-04 | global batch size: 512 | lm loss: 2.566394E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.387 | TFLOPs: 23.61 | +63: iteration 5790/ 73814 | consumed samples: 2964480 | consumed tokens: 6071255040 | elapsed time per iteration (s): 2.23 | learning rate: 1.979E-04 | global batch size: 512 | lm loss: 2.543885E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.254 | TFLOPs: 23.60 | +63: iteration 5800/ 73814 | consumed samples: 2969600 | consumed tokens: 6081740800 | elapsed time per iteration (s): 2.25 | learning rate: 1.979E-04 | global batch size: 512 | lm loss: 2.509260E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.506 | TFLOPs: 23.42 | +63: iteration 5810/ 73814 | consumed samples: 2974720 | consumed tokens: 6092226560 | elapsed time per iteration (s): 2.24 | learning rate: 1.979E-04 | global batch size: 512 | lm loss: 2.555376E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.181 | TFLOPs: 23.49 | +63: iteration 5820/ 73814 | consumed samples: 2979840 | consumed tokens: 6102712320 | elapsed time per iteration (s): 2.25 | learning rate: 1.979E-04 | global batch size: 512 | lm loss: 2.528331E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.031 | TFLOPs: 23.47 | +63: iteration 5830/ 73814 | consumed samples: 2984960 | consumed tokens: 6113198080 | elapsed time per iteration (s): 2.26 | learning rate: 1.979E-04 | global batch size: 512 | lm loss: 2.529542E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.601 | TFLOPs: 23.33 | +63: iteration 5840/ 73814 | consumed samples: 2990080 | consumed tokens: 6123683840 | elapsed time per iteration (s): 2.24 | learning rate: 1.978E-04 | global batch size: 512 | lm loss: 2.523230E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.217 | TFLOPs: 23.49 | +63: iteration 5850/ 73814 | consumed samples: 2995200 | consumed tokens: 6134169600 | elapsed time per iteration (s): 2.25 | learning rate: 1.978E-04 | global batch size: 512 | lm loss: 2.545278E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.168 | TFLOPs: 23.39 | +63: iteration 5860/ 73814 | consumed samples: 3000320 | consumed tokens: 6144655360 | elapsed time per iteration (s): 2.24 | learning rate: 1.978E-04 | global batch size: 512 | lm loss: 2.524007E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.461 | TFLOPs: 23.52 | +63: iteration 5870/ 73814 | consumed samples: 3005440 | consumed tokens: 6155141120 | elapsed time per iteration (s): 2.24 | learning rate: 1.978E-04 | global batch size: 512 | lm loss: 2.507731E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.006 | TFLOPs: 23.58 | +63: iteration 5880/ 73814 | consumed samples: 3010560 | consumed tokens: 6165626880 | elapsed time per iteration (s): 2.23 | learning rate: 1.978E-04 | global batch size: 512 | lm loss: 2.538060E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.030 | TFLOPs: 23.68 | +63: iteration 5890/ 73814 | consumed samples: 3015680 | consumed tokens: 6176112640 | elapsed time per iteration (s): 2.23 | learning rate: 1.978E-04 | global batch size: 512 | lm loss: 2.529690E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.378 | TFLOPs: 23.61 | +63: iteration 5900/ 73814 | consumed samples: 3020800 | consumed tokens: 6186598400 | elapsed time per iteration (s): 2.22 | learning rate: 1.978E-04 | global batch size: 512 | lm loss: 2.518155E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.154 | TFLOPs: 23.69 | +63: iteration 5910/ 73814 | consumed samples: 3025920 | consumed tokens: 6197084160 | elapsed time per iteration (s): 2.23 | learning rate: 1.978E-04 | global batch size: 512 | lm loss: 2.541826E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.183 | TFLOPs: 23.59 | +63: iteration 5920/ 73814 | consumed samples: 3031040 | consumed tokens: 6207569920 | elapsed time per iteration (s): 2.24 | learning rate: 1.978E-04 | global batch size: 512 | lm loss: 2.537207E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.082 | TFLOPs: 23.58 | +63: iteration 5930/ 73814 | consumed samples: 3036160 | consumed tokens: 6218055680 | elapsed time per iteration (s): 2.25 | learning rate: 1.978E-04 | global batch size: 512 | lm loss: 2.538651E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.064 | TFLOPs: 23.38 | +63: iteration 5940/ 73814 | consumed samples: 3041280 | consumed tokens: 6228541440 | elapsed time per iteration (s): 2.23 | learning rate: 1.978E-04 | global batch size: 512 | lm loss: 2.519561E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.114 | TFLOPs: 23.59 | +63: iteration 5950/ 73814 | consumed samples: 3046400 | consumed tokens: 6239027200 | elapsed time per iteration (s): 2.23 | learning rate: 1.978E-04 | global batch size: 512 | lm loss: 2.517517E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.540 | TFLOPs: 23.63 | +63: iteration 5960/ 73814 | consumed samples: 3051520 | consumed tokens: 6249512960 | elapsed time per iteration (s): 2.25 | learning rate: 1.977E-04 | global batch size: 512 | lm loss: 2.508500E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.416 | TFLOPs: 23.41 | +63: iteration 5970/ 73814 | consumed samples: 3056640 | consumed tokens: 6259998720 | elapsed time per iteration (s): 2.25 | learning rate: 1.977E-04 | global batch size: 512 | lm loss: 2.521446E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.921 | TFLOPs: 23.46 | +63: iteration 5980/ 73814 | consumed samples: 3061760 | consumed tokens: 6270484480 | elapsed time per iteration (s): 5.25 | learning rate: 1.977E-04 | global batch size: 512 | lm loss: 2.523444E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 97.540 | TFLOPs: 10.04 | +63: iteration 5990/ 73814 | consumed samples: 3066880 | consumed tokens: 6280970240 | elapsed time per iteration (s): 2.24 | learning rate: 1.977E-04 | global batch size: 512 | lm loss: 2.514099E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.529 | TFLOPs: 23.53 | + 0: [2022-12-01 15:35:27,339] [INFO] [logging.py:68:log_dist] [Rank 0] step=6000, skipped=0, lr=[0.00019770710128667795, 0.00019770710128667795, 0.00019770710128667795], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 6000/ 73814 | consumed samples: 3072000 | consumed tokens: 6291456000 | elapsed time per iteration (s): 2.23 | learning rate: 1.977E-04 | global batch size: 512 | lm loss: 2.491387E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.173 | TFLOPs: 23.59 | + 0: steps: 6000 loss: 2.4872 iter time (s): 2.276 samples/sec: 224.917 +63: ------------------------------------------------------------------------------------------ +63: valid loss at iteration 6000 | lm loss value: 2.433987E+00 | lm loss PPL: 1.140426E+01 | +63: ------------------------------------------------------------------------------------------ +63: iteration 6010/ 73814 | consumed samples: 3077120 | consumed tokens: 6301941760 | elapsed time per iteration (s): 2.28 | learning rate: 1.977E-04 | global batch size: 512 | lm loss: 2.543388E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.187 | TFLOPs: 23.08 | +63: iteration 6020/ 73814 | consumed samples: 3082240 | consumed tokens: 6312427520 | elapsed time per iteration (s): 3.91 | learning rate: 1.977E-04 | global batch size: 512 | lm loss: 2.513571E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 131.095 | TFLOPs: 13.50 | +63: iteration 6030/ 73814 | consumed samples: 3087360 | consumed tokens: 6322913280 | elapsed time per iteration (s): 2.23 | learning rate: 1.977E-04 | global batch size: 512 | lm loss: 2.518499E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.696 | TFLOPs: 23.65 | +63: iteration 6040/ 73814 | consumed samples: 3092480 | consumed tokens: 6333399040 | elapsed time per iteration (s): 2.23 | learning rate: 1.977E-04 | global batch size: 512 | lm loss: 2.523526E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.843 | TFLOPs: 23.66 | +63: iteration 6050/ 73814 | consumed samples: 3097600 | consumed tokens: 6343884800 | elapsed time per iteration (s): 2.23 | learning rate: 1.977E-04 | global batch size: 512 | lm loss: 2.534696E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.203 | TFLOPs: 23.60 | +63: iteration 6060/ 73814 | consumed samples: 3102720 | consumed tokens: 6354370560 | elapsed time per iteration (s): 2.24 | learning rate: 1.977E-04 | global batch size: 512 | lm loss: 2.533454E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.220 | TFLOPs: 23.49 | +63: iteration 6070/ 73814 | consumed samples: 3107840 | consumed tokens: 6364856320 | elapsed time per iteration (s): 2.23 | learning rate: 1.976E-04 | global batch size: 512 | lm loss: 2.485175E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.879 | TFLOPs: 23.66 | +63: iteration 6080/ 73814 | consumed samples: 3112960 | consumed tokens: 6375342080 | elapsed time per iteration (s): 2.24 | learning rate: 1.976E-04 | global batch size: 512 | lm loss: 2.530545E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.957 | TFLOPs: 23.57 | +63: iteration 6090/ 73814 | consumed samples: 3118080 | consumed tokens: 6385827840 | elapsed time per iteration (s): 2.25 | learning rate: 1.976E-04 | global batch size: 512 | lm loss: 2.500787E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.432 | TFLOPs: 23.41 | +63: iteration 6100/ 73814 | consumed samples: 3123200 | consumed tokens: 6396313600 | elapsed time per iteration (s): 2.23 | learning rate: 1.976E-04 | global batch size: 512 | lm loss: 2.526885E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.439 | TFLOPs: 23.62 | +63: iteration 6110/ 73814 | consumed samples: 3128320 | consumed tokens: 6406799360 | elapsed time per iteration (s): 2.24 | learning rate: 1.976E-04 | global batch size: 512 | lm loss: 2.520444E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.982 | TFLOPs: 23.57 | +63: iteration 6120/ 73814 | consumed samples: 3133440 | consumed tokens: 6417285120 | elapsed time per iteration (s): 2.24 | learning rate: 1.976E-04 | global batch size: 512 | lm loss: 2.600578E+00 | grad norm: 0.908 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.236 | TFLOPs: 23.50 | +63: iteration 6130/ 73814 | consumed samples: 3138560 | consumed tokens: 6427770880 | elapsed time per iteration (s): 2.24 | learning rate: 1.976E-04 | global batch size: 512 | lm loss: 2.722997E+00 | grad norm: 2.937 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.362 | TFLOPs: 23.51 | +63: iteration 6140/ 73814 | consumed samples: 3143680 | consumed tokens: 6438256640 | elapsed time per iteration (s): 2.26 | learning rate: 1.976E-04 | global batch size: 512 | lm loss: 3.003637E+00 | grad norm: 1.489 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.748 | TFLOPs: 23.34 | +63: iteration 6150/ 73814 | consumed samples: 3148800 | consumed tokens: 6448742400 | elapsed time per iteration (s): 2.24 | learning rate: 1.976E-04 | global batch size: 512 | lm loss: 3.103631E+00 | grad norm: 0.852 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.192 | TFLOPs: 23.49 | +63: iteration 6160/ 73814 | consumed samples: 3153920 | consumed tokens: 6459228160 | elapsed time per iteration (s): 2.27 | learning rate: 1.976E-04 | global batch size: 512 | lm loss: 3.044794E+00 | grad norm: 1.065 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.480 | TFLOPs: 23.21 | +63: iteration 6170/ 73814 | consumed samples: 3159040 | consumed tokens: 6469713920 | elapsed time per iteration (s): 2.23 | learning rate: 1.976E-04 | global batch size: 512 | lm loss: 2.985154E+00 | grad norm: 0.735 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.452 | TFLOPs: 23.62 | +63: iteration 6180/ 73814 | consumed samples: 3164160 | consumed tokens: 6480199680 | elapsed time per iteration (s): 2.26 | learning rate: 1.975E-04 | global batch size: 512 | lm loss: 2.836742E+00 | grad norm: 0.755 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.066 | TFLOPs: 23.27 | +63: iteration 6190/ 73814 | consumed samples: 3169280 | consumed tokens: 6490685440 | elapsed time per iteration (s): 2.25 | learning rate: 1.975E-04 | global batch size: 512 | lm loss: 2.706582E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.852 | TFLOPs: 23.46 | +63: iteration 6200/ 73814 | consumed samples: 3174400 | consumed tokens: 6501171200 | elapsed time per iteration (s): 2.27 | learning rate: 1.975E-04 | global batch size: 512 | lm loss: 2.651525E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.662 | TFLOPs: 23.23 | +63: iteration 6210/ 73814 | consumed samples: 3179520 | consumed tokens: 6511656960 | elapsed time per iteration (s): 2.23 | learning rate: 1.975E-04 | global batch size: 512 | lm loss: 2.609732E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.295 | TFLOPs: 23.60 | +63: iteration 6220/ 73814 | consumed samples: 3184640 | consumed tokens: 6522142720 | elapsed time per iteration (s): 2.23 | learning rate: 1.975E-04 | global batch size: 512 | lm loss: 2.592513E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.103 | TFLOPs: 23.59 | +63: iteration 6230/ 73814 | consumed samples: 3189760 | consumed tokens: 6532628480 | elapsed time per iteration (s): 2.23 | learning rate: 1.975E-04 | global batch size: 512 | lm loss: 2.570056E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.746 | TFLOPs: 23.65 | +63: iteration 6240/ 73814 | consumed samples: 3194880 | consumed tokens: 6543114240 | elapsed time per iteration (s): 2.24 | learning rate: 1.975E-04 | global batch size: 512 | lm loss: 2.567762E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.794 | TFLOPs: 23.55 | +63: iteration 6250/ 73814 | consumed samples: 3200000 | consumed tokens: 6553600000 | elapsed time per iteration (s): 2.23 | learning rate: 1.975E-04 | global batch size: 512 | lm loss: 2.538248E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.613 | TFLOPs: 23.64 | +63: iteration 6260/ 73814 | consumed samples: 3205120 | consumed tokens: 6564085760 | elapsed time per iteration (s): 2.24 | learning rate: 1.975E-04 | global batch size: 512 | lm loss: 2.551596E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.252 | TFLOPs: 23.50 | +63: iteration 6270/ 73814 | consumed samples: 3210240 | consumed tokens: 6574571520 | elapsed time per iteration (s): 2.24 | learning rate: 1.975E-04 | global batch size: 512 | lm loss: 2.551285E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.147 | TFLOPs: 23.49 | +63: iteration 6280/ 73814 | consumed samples: 3215360 | consumed tokens: 6585057280 | elapsed time per iteration (s): 2.23 | learning rate: 1.975E-04 | global batch size: 512 | lm loss: 2.542493E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.426 | TFLOPs: 23.62 | +63: iteration 6290/ 73814 | consumed samples: 3220480 | consumed tokens: 6595543040 | elapsed time per iteration (s): 2.24 | learning rate: 1.974E-04 | global batch size: 512 | lm loss: 2.552885E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.862 | TFLOPs: 23.56 | +63: iteration 6300/ 73814 | consumed samples: 3225600 | consumed tokens: 6606028800 | elapsed time per iteration (s): 2.23 | learning rate: 1.974E-04 | global batch size: 512 | lm loss: 2.543991E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.978 | TFLOPs: 23.68 | +63: iteration 6310/ 73814 | consumed samples: 3230720 | consumed tokens: 6616514560 | elapsed time per iteration (s): 2.24 | learning rate: 1.974E-04 | global batch size: 512 | lm loss: 2.519634E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.366 | TFLOPs: 23.51 | +63: iteration 6320/ 73814 | consumed samples: 3235840 | consumed tokens: 6627000320 | elapsed time per iteration (s): 2.23 | learning rate: 1.974E-04 | global batch size: 512 | lm loss: 2.517088E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.803 | TFLOPs: 23.66 | +63: iteration 6330/ 73814 | consumed samples: 3240960 | consumed tokens: 6637486080 | elapsed time per iteration (s): 2.22 | learning rate: 1.974E-04 | global batch size: 512 | lm loss: 2.512082E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.271 | TFLOPs: 23.71 | +63: iteration 6340/ 73814 | consumed samples: 3246080 | consumed tokens: 6647971840 | elapsed time per iteration (s): 2.26 | learning rate: 1.974E-04 | global batch size: 512 | lm loss: 2.509737E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.861 | TFLOPs: 23.35 | +63: iteration 6350/ 73814 | consumed samples: 3251200 | consumed tokens: 6658457600 | elapsed time per iteration (s): 2.23 | learning rate: 1.974E-04 | global batch size: 512 | lm loss: 2.519367E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.527 | TFLOPs: 23.63 | +63: iteration 6360/ 73814 | consumed samples: 3256320 | consumed tokens: 6668943360 | elapsed time per iteration (s): 2.23 | learning rate: 1.974E-04 | global batch size: 512 | lm loss: 2.516725E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.115 | TFLOPs: 23.59 | +63: iteration 6370/ 73814 | consumed samples: 3261440 | consumed tokens: 6679429120 | elapsed time per iteration (s): 2.23 | learning rate: 1.974E-04 | global batch size: 512 | lm loss: 2.528484E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.846 | TFLOPs: 23.66 | +63: iteration 6380/ 73814 | consumed samples: 3266560 | consumed tokens: 6689914880 | elapsed time per iteration (s): 2.24 | learning rate: 1.974E-04 | global batch size: 512 | lm loss: 2.510769E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.411 | TFLOPs: 23.51 | +63: iteration 6390/ 73814 | consumed samples: 3271680 | consumed tokens: 6700400640 | elapsed time per iteration (s): 2.23 | learning rate: 1.974E-04 | global batch size: 512 | lm loss: 2.514503E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.353 | TFLOPs: 23.61 | +63: iteration 6400/ 73814 | consumed samples: 3276800 | consumed tokens: 6710886400 | elapsed time per iteration (s): 2.24 | learning rate: 1.973E-04 | global batch size: 512 | lm loss: 2.510017E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.001 | TFLOPs: 23.57 | +63: iteration 6410/ 73814 | consumed samples: 3281920 | consumed tokens: 6721372160 | elapsed time per iteration (s): 2.25 | learning rate: 1.973E-04 | global batch size: 512 | lm loss: 2.489479E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.620 | TFLOPs: 23.43 | +63: iteration 6420/ 73814 | consumed samples: 3287040 | consumed tokens: 6731857920 | elapsed time per iteration (s): 2.25 | learning rate: 1.973E-04 | global batch size: 512 | lm loss: 2.480932E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.747 | TFLOPs: 23.45 | +63: iteration 6430/ 73814 | consumed samples: 3292160 | consumed tokens: 6742343680 | elapsed time per iteration (s): 2.23 | learning rate: 1.973E-04 | global batch size: 512 | lm loss: 2.499143E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.271 | TFLOPs: 23.60 | +63: iteration 6440/ 73814 | consumed samples: 3297280 | consumed tokens: 6752829440 | elapsed time per iteration (s): 2.24 | learning rate: 1.973E-04 | global batch size: 512 | lm loss: 2.499818E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.343 | TFLOPs: 23.51 | +63: iteration 6450/ 73814 | consumed samples: 3302400 | consumed tokens: 6763315200 | elapsed time per iteration (s): 2.25 | learning rate: 1.973E-04 | global batch size: 512 | lm loss: 2.508493E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.866 | TFLOPs: 23.46 | +63: iteration 6460/ 73814 | consumed samples: 3307520 | consumed tokens: 6773800960 | elapsed time per iteration (s): 2.23 | learning rate: 1.973E-04 | global batch size: 512 | lm loss: 2.487057E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.368 | TFLOPs: 23.61 | +63: iteration 6470/ 73814 | consumed samples: 3312640 | consumed tokens: 6784286720 | elapsed time per iteration (s): 2.23 | learning rate: 1.973E-04 | global batch size: 512 | lm loss: 2.506409E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.194 | TFLOPs: 23.59 | +63: iteration 6480/ 73814 | consumed samples: 3317760 | consumed tokens: 6794772480 | elapsed time per iteration (s): 2.24 | learning rate: 1.973E-04 | global batch size: 512 | lm loss: 2.504417E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.741 | TFLOPs: 23.55 | +63: iteration 6490/ 73814 | consumed samples: 3322880 | consumed tokens: 6805258240 | elapsed time per iteration (s): 2.24 | learning rate: 1.973E-04 | global batch size: 512 | lm loss: 2.498154E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.851 | TFLOPs: 23.56 | +63: iteration 6500/ 73814 | consumed samples: 3328000 | consumed tokens: 6815744000 | elapsed time per iteration (s): 2.23 | learning rate: 1.973E-04 | global batch size: 512 | lm loss: 2.494307E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.573 | TFLOPs: 23.63 | +63: iteration 6510/ 73814 | consumed samples: 3333120 | consumed tokens: 6826229760 | elapsed time per iteration (s): 2.23 | learning rate: 1.972E-04 | global batch size: 512 | lm loss: 2.512981E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.713 | TFLOPs: 23.65 | +63: iteration 6520/ 73814 | consumed samples: 3338240 | consumed tokens: 6836715520 | elapsed time per iteration (s): 2.25 | learning rate: 1.972E-04 | global batch size: 512 | lm loss: 2.497361E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.798 | TFLOPs: 23.45 | +63: iteration 6530/ 73814 | consumed samples: 3343360 | consumed tokens: 6847201280 | elapsed time per iteration (s): 2.23 | learning rate: 1.972E-04 | global batch size: 512 | lm loss: 2.500768E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.193 | TFLOPs: 23.59 | +63: iteration 6540/ 73814 | consumed samples: 3348480 | consumed tokens: 6857687040 | elapsed time per iteration (s): 2.23 | learning rate: 1.972E-04 | global batch size: 512 | lm loss: 2.493205E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.949 | TFLOPs: 23.67 | +63: iteration 6550/ 73814 | consumed samples: 3353600 | consumed tokens: 6868172800 | elapsed time per iteration (s): 2.24 | learning rate: 1.972E-04 | global batch size: 512 | lm loss: 2.527373E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.712 | TFLOPs: 23.54 | +63: iteration 6560/ 73814 | consumed samples: 3358720 | consumed tokens: 6878658560 | elapsed time per iteration (s): 2.24 | learning rate: 1.972E-04 | global batch size: 512 | lm loss: 2.461393E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.045 | TFLOPs: 23.58 | +63: iteration 6570/ 73814 | consumed samples: 3363840 | consumed tokens: 6889144320 | elapsed time per iteration (s): 2.23 | learning rate: 1.972E-04 | global batch size: 512 | lm loss: 2.485068E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.976 | TFLOPs: 23.67 | +63: iteration 6580/ 73814 | consumed samples: 3368960 | consumed tokens: 6899630080 | elapsed time per iteration (s): 2.27 | learning rate: 1.972E-04 | global batch size: 512 | lm loss: 2.503359E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.598 | TFLOPs: 23.22 | +63: iteration 6590/ 73814 | consumed samples: 3374080 | consumed tokens: 6910115840 | elapsed time per iteration (s): 2.28 | learning rate: 1.972E-04 | global batch size: 512 | lm loss: 2.508540E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.149 | TFLOPs: 23.08 | +63: iteration 6600/ 73814 | consumed samples: 3379200 | consumed tokens: 6920601600 | elapsed time per iteration (s): 2.24 | learning rate: 1.972E-04 | global batch size: 512 | lm loss: 2.486273E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.444 | TFLOPs: 23.52 | +63: iteration 6610/ 73814 | consumed samples: 3384320 | consumed tokens: 6931087360 | elapsed time per iteration (s): 2.41 | learning rate: 1.971E-04 | global batch size: 512 | lm loss: 2.477601E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.702 | TFLOPs: 21.90 | +63: iteration 6620/ 73814 | consumed samples: 3389440 | consumed tokens: 6941573120 | elapsed time per iteration (s): 2.34 | learning rate: 1.971E-04 | global batch size: 512 | lm loss: 2.470020E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.169 | TFLOPs: 22.56 | +63: iteration 6630/ 73814 | consumed samples: 3394560 | consumed tokens: 6952058880 | elapsed time per iteration (s): 2.38 | learning rate: 1.971E-04 | global batch size: 512 | lm loss: 2.488759E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.862 | TFLOPs: 22.12 | +63: iteration 6640/ 73814 | consumed samples: 3399680 | consumed tokens: 6962544640 | elapsed time per iteration (s): 2.43 | learning rate: 1.971E-04 | global batch size: 512 | lm loss: 2.499476E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.603 | TFLOPs: 21.68 | +63: iteration 6650/ 73814 | consumed samples: 3404800 | consumed tokens: 6973030400 | elapsed time per iteration (s): 2.47 | learning rate: 1.971E-04 | global batch size: 512 | lm loss: 2.483799E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 207.418 | TFLOPs: 21.35 | +63: iteration 6660/ 73814 | consumed samples: 3409920 | consumed tokens: 6983516160 | elapsed time per iteration (s): 2.36 | learning rate: 1.971E-04 | global batch size: 512 | lm loss: 2.477096E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.868 | TFLOPs: 22.33 | +63: iteration 6670/ 73814 | consumed samples: 3415040 | consumed tokens: 6994001920 | elapsed time per iteration (s): 2.25 | learning rate: 1.971E-04 | global batch size: 512 | lm loss: 2.511727E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.217 | TFLOPs: 23.39 | +63: iteration 6680/ 73814 | consumed samples: 3420160 | consumed tokens: 7004487680 | elapsed time per iteration (s): 2.45 | learning rate: 1.971E-04 | global batch size: 512 | lm loss: 2.509423E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.306 | TFLOPs: 21.55 | +63: iteration 6690/ 73814 | consumed samples: 3425280 | consumed tokens: 7014973440 | elapsed time per iteration (s): 2.30 | learning rate: 1.971E-04 | global batch size: 512 | lm loss: 2.508798E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.874 | TFLOPs: 22.94 | +63: iteration 6700/ 73814 | consumed samples: 3430400 | consumed tokens: 7025459200 | elapsed time per iteration (s): 2.25 | learning rate: 1.971E-04 | global batch size: 512 | lm loss: 2.480427E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.172 | TFLOPs: 23.39 | +63: iteration 6710/ 73814 | consumed samples: 3435520 | consumed tokens: 7035944960 | elapsed time per iteration (s): 2.32 | learning rate: 1.971E-04 | global batch size: 512 | lm loss: 2.483061E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.705 | TFLOPs: 22.72 | +63: iteration 6720/ 73814 | consumed samples: 3440640 | consumed tokens: 7046430720 | elapsed time per iteration (s): 2.24 | learning rate: 1.970E-04 | global batch size: 512 | lm loss: 2.485945E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.612 | TFLOPs: 23.53 | +63: iteration 6730/ 73814 | consumed samples: 3445760 | consumed tokens: 7056916480 | elapsed time per iteration (s): 2.39 | learning rate: 1.970E-04 | global batch size: 512 | lm loss: 2.477674E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.634 | TFLOPs: 22.10 | +63: iteration 6740/ 73814 | consumed samples: 3450880 | consumed tokens: 7067402240 | elapsed time per iteration (s): 2.23 | learning rate: 1.970E-04 | global batch size: 512 | lm loss: 2.479819E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.873 | TFLOPs: 23.66 | +63: iteration 6750/ 73814 | consumed samples: 3456000 | consumed tokens: 7077888000 | elapsed time per iteration (s): 2.24 | learning rate: 1.970E-04 | global batch size: 512 | lm loss: 2.482377E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.798 | TFLOPs: 23.55 | +63: iteration 6760/ 73814 | consumed samples: 3461120 | consumed tokens: 7088373760 | elapsed time per iteration (s): 2.22 | learning rate: 1.970E-04 | global batch size: 512 | lm loss: 2.497212E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.193 | TFLOPs: 23.70 | +63: iteration 6770/ 73814 | consumed samples: 3466240 | consumed tokens: 7098859520 | elapsed time per iteration (s): 2.23 | learning rate: 1.970E-04 | global batch size: 512 | lm loss: 2.462679E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.513 | TFLOPs: 23.63 | +63: iteration 6780/ 73814 | consumed samples: 3471360 | consumed tokens: 7109345280 | elapsed time per iteration (s): 2.23 | learning rate: 1.970E-04 | global batch size: 512 | lm loss: 2.499025E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.059 | TFLOPs: 23.68 | +63: iteration 6790/ 73814 | consumed samples: 3476480 | consumed tokens: 7119831040 | elapsed time per iteration (s): 2.27 | learning rate: 1.970E-04 | global batch size: 512 | lm loss: 2.491611E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.221 | TFLOPs: 23.19 | +63: iteration 6800/ 73814 | consumed samples: 3481600 | consumed tokens: 7130316800 | elapsed time per iteration (s): 2.23 | learning rate: 1.970E-04 | global batch size: 512 | lm loss: 2.490741E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.233 | TFLOPs: 23.60 | +63: iteration 6810/ 73814 | consumed samples: 3486720 | consumed tokens: 7140802560 | elapsed time per iteration (s): 2.23 | learning rate: 1.970E-04 | global batch size: 512 | lm loss: 2.461211E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.087 | TFLOPs: 23.58 | +63: iteration 6820/ 73814 | consumed samples: 3491840 | consumed tokens: 7151288320 | elapsed time per iteration (s): 2.23 | learning rate: 1.969E-04 | global batch size: 512 | lm loss: 2.499274E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.698 | TFLOPs: 23.65 | +63: iteration 6830/ 73814 | consumed samples: 3496960 | consumed tokens: 7161774080 | elapsed time per iteration (s): 2.27 | learning rate: 1.969E-04 | global batch size: 512 | lm loss: 2.498090E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.012 | TFLOPs: 23.27 | +63: iteration 6840/ 73814 | consumed samples: 3502080 | consumed tokens: 7172259840 | elapsed time per iteration (s): 2.26 | learning rate: 1.969E-04 | global batch size: 512 | lm loss: 2.476602E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.004 | TFLOPs: 23.37 | +63: iteration 6850/ 73814 | consumed samples: 3507200 | consumed tokens: 7182745600 | elapsed time per iteration (s): 2.40 | learning rate: 1.969E-04 | global batch size: 512 | lm loss: 2.465978E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.629 | TFLOPs: 21.99 | +63: iteration 6860/ 73814 | consumed samples: 3512320 | consumed tokens: 7193231360 | elapsed time per iteration (s): 2.26 | learning rate: 1.969E-04 | global batch size: 512 | lm loss: 2.468393E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.169 | TFLOPs: 23.28 | +63: iteration 6870/ 73814 | consumed samples: 3517440 | consumed tokens: 7203717120 | elapsed time per iteration (s): 2.23 | learning rate: 1.969E-04 | global batch size: 512 | lm loss: 2.472086E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.816 | TFLOPs: 23.66 | +63: iteration 6880/ 73814 | consumed samples: 3522560 | consumed tokens: 7214202880 | elapsed time per iteration (s): 2.23 | learning rate: 1.969E-04 | global batch size: 512 | lm loss: 2.470501E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.760 | TFLOPs: 23.65 | +63: iteration 6890/ 73814 | consumed samples: 3527680 | consumed tokens: 7224688640 | elapsed time per iteration (s): 2.29 | learning rate: 1.969E-04 | global batch size: 512 | lm loss: 2.485982E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.903 | TFLOPs: 23.05 | +63: iteration 6900/ 73814 | consumed samples: 3532800 | consumed tokens: 7235174400 | elapsed time per iteration (s): 2.30 | learning rate: 1.969E-04 | global batch size: 512 | lm loss: 2.475118E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.748 | TFLOPs: 22.93 | +63: iteration 6910/ 73814 | consumed samples: 3537920 | consumed tokens: 7245660160 | elapsed time per iteration (s): 2.23 | learning rate: 1.969E-04 | global batch size: 512 | lm loss: 2.473631E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.687 | TFLOPs: 23.65 | +63: iteration 6920/ 73814 | consumed samples: 3543040 | consumed tokens: 7256145920 | elapsed time per iteration (s): 2.23 | learning rate: 1.968E-04 | global batch size: 512 | lm loss: 2.470344E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.643 | TFLOPs: 23.64 | +63: iteration 6930/ 73814 | consumed samples: 3548160 | consumed tokens: 7266631680 | elapsed time per iteration (s): 2.23 | learning rate: 1.968E-04 | global batch size: 512 | lm loss: 2.457058E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.195 | TFLOPs: 23.59 | +63: iteration 6940/ 73814 | consumed samples: 3553280 | consumed tokens: 7277117440 | elapsed time per iteration (s): 2.24 | learning rate: 1.968E-04 | global batch size: 512 | lm loss: 2.450328E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.849 | TFLOPs: 23.56 | +63: iteration 6950/ 73814 | consumed samples: 3558400 | consumed tokens: 7287603200 | elapsed time per iteration (s): 2.23 | learning rate: 1.968E-04 | global batch size: 512 | lm loss: 2.459011E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.144 | TFLOPs: 23.59 | +63: iteration 6960/ 73814 | consumed samples: 3563520 | consumed tokens: 7298088960 | elapsed time per iteration (s): 2.24 | learning rate: 1.968E-04 | global batch size: 512 | lm loss: 2.457279E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.450 | TFLOPs: 23.52 | +63: iteration 6970/ 73814 | consumed samples: 3568640 | consumed tokens: 7308574720 | elapsed time per iteration (s): 2.24 | learning rate: 1.968E-04 | global batch size: 512 | lm loss: 2.462900E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.729 | TFLOPs: 23.55 | +63: iteration 6980/ 73814 | consumed samples: 3573760 | consumed tokens: 7319060480 | elapsed time per iteration (s): 2.25 | learning rate: 1.968E-04 | global batch size: 512 | lm loss: 2.477754E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.647 | TFLOPs: 23.44 | +63: iteration 6990/ 73814 | consumed samples: 3578880 | consumed tokens: 7329546240 | elapsed time per iteration (s): 2.27 | learning rate: 1.968E-04 | global batch size: 512 | lm loss: 2.474036E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.734 | TFLOPs: 23.24 | +63: iteration 7000/ 73814 | consumed samples: 3584000 | consumed tokens: 7340032000 | elapsed time per iteration (s): 2.25 | learning rate: 1.968E-04 | global batch size: 512 | lm loss: 2.458062E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.389 | TFLOPs: 23.41 | +63: ------------------------------------------------------------------------------------------ +63: valid loss at iteration 7000 | lm loss value: 2.482992E+00 | lm loss PPL: 1.197704E+01 | +63: ------------------------------------------------------------------------------------------ +63: iteration 7010/ 73814 | consumed samples: 3589120 | consumed tokens: 7350517760 | elapsed time per iteration (s): 2.31 | learning rate: 1.967E-04 | global batch size: 512 | lm loss: 2.466183E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.953 | TFLOPs: 22.85 | +63: iteration 7020/ 73814 | consumed samples: 3594240 | consumed tokens: 7361003520 | elapsed time per iteration (s): 2.25 | learning rate: 1.967E-04 | global batch size: 512 | lm loss: 2.457390E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.437 | TFLOPs: 23.41 | +63: iteration 7030/ 73814 | consumed samples: 3599360 | consumed tokens: 7371489280 | elapsed time per iteration (s): 2.24 | learning rate: 1.967E-04 | global batch size: 512 | lm loss: 2.477369E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.661 | TFLOPs: 23.54 | +63: iteration 7040/ 73814 | consumed samples: 3604480 | consumed tokens: 7381975040 | elapsed time per iteration (s): 2.23 | learning rate: 1.967E-04 | global batch size: 512 | lm loss: 2.464390E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.365 | TFLOPs: 23.61 | +63: iteration 7050/ 73814 | consumed samples: 3609600 | consumed tokens: 7392460800 | elapsed time per iteration (s): 2.23 | learning rate: 1.967E-04 | global batch size: 512 | lm loss: 2.456272E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.017 | TFLOPs: 23.68 | +63: iteration 7060/ 73814 | consumed samples: 3614720 | consumed tokens: 7402946560 | elapsed time per iteration (s): 2.23 | learning rate: 1.967E-04 | global batch size: 512 | lm loss: 2.467159E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.189 | TFLOPs: 23.59 | +63: iteration 7070/ 73814 | consumed samples: 3619840 | consumed tokens: 7413432320 | elapsed time per iteration (s): 2.27 | learning rate: 1.967E-04 | global batch size: 512 | lm loss: 2.452339E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.685 | TFLOPs: 23.23 | +63: iteration 7080/ 73814 | consumed samples: 3624960 | consumed tokens: 7423918080 | elapsed time per iteration (s): 2.24 | learning rate: 1.967E-04 | global batch size: 512 | lm loss: 2.450121E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.686 | TFLOPs: 23.54 | +63: iteration 7090/ 73814 | consumed samples: 3630080 | consumed tokens: 7434403840 | elapsed time per iteration (s): 2.26 | learning rate: 1.967E-04 | global batch size: 512 | lm loss: 2.450394E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.287 | TFLOPs: 23.30 | +63: iteration 7100/ 73814 | consumed samples: 3635200 | consumed tokens: 7444889600 | elapsed time per iteration (s): 2.25 | learning rate: 1.967E-04 | global batch size: 512 | lm loss: 2.468248E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.017 | TFLOPs: 23.47 | +63: iteration 7110/ 73814 | consumed samples: 3640320 | consumed tokens: 7455375360 | elapsed time per iteration (s): 2.25 | learning rate: 1.966E-04 | global batch size: 512 | lm loss: 2.451966E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.081 | TFLOPs: 23.38 | +63: iteration 7120/ 73814 | consumed samples: 3645440 | consumed tokens: 7465861120 | elapsed time per iteration (s): 2.23 | learning rate: 1.966E-04 | global batch size: 512 | lm loss: 2.450937E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.315 | TFLOPs: 23.61 | +63: iteration 7130/ 73814 | consumed samples: 3650560 | consumed tokens: 7476346880 | elapsed time per iteration (s): 2.23 | learning rate: 1.966E-04 | global batch size: 512 | lm loss: 2.456493E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.625 | TFLOPs: 23.64 | +63: iteration 7140/ 73814 | consumed samples: 3655680 | consumed tokens: 7486832640 | elapsed time per iteration (s): 2.25 | learning rate: 1.966E-04 | global batch size: 512 | lm loss: 2.475915E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.425 | TFLOPs: 23.41 | +63: iteration 7150/ 73814 | consumed samples: 3660800 | consumed tokens: 7497318400 | elapsed time per iteration (s): 2.23 | learning rate: 1.966E-04 | global batch size: 512 | lm loss: 2.451532E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.697 | TFLOPs: 23.65 | +63: iteration 7160/ 73814 | consumed samples: 3665920 | consumed tokens: 7507804160 | elapsed time per iteration (s): 2.25 | learning rate: 1.966E-04 | global batch size: 512 | lm loss: 2.449672E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.856 | TFLOPs: 23.46 | +63: iteration 7170/ 73814 | consumed samples: 3671040 | consumed tokens: 7518289920 | elapsed time per iteration (s): 2.24 | learning rate: 1.966E-04 | global batch size: 512 | lm loss: 2.468614E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.932 | TFLOPs: 23.57 | +63: iteration 7180/ 73814 | consumed samples: 3676160 | consumed tokens: 7528775680 | elapsed time per iteration (s): 2.24 | learning rate: 1.966E-04 | global batch size: 512 | lm loss: 2.462973E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.356 | TFLOPs: 23.51 | +63: iteration 7190/ 73814 | consumed samples: 3681280 | consumed tokens: 7539261440 | elapsed time per iteration (s): 2.24 | learning rate: 1.966E-04 | global batch size: 512 | lm loss: 2.441952E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.250 | TFLOPs: 23.50 | +63: iteration 7200/ 73814 | consumed samples: 3686400 | consumed tokens: 7549747200 | elapsed time per iteration (s): 2.23 | learning rate: 1.965E-04 | global batch size: 512 | lm loss: 2.475080E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.209 | TFLOPs: 23.60 | +63: iteration 7210/ 73814 | consumed samples: 3691520 | consumed tokens: 7560232960 | elapsed time per iteration (s): 2.25 | learning rate: 1.965E-04 | global batch size: 512 | lm loss: 2.452387E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.155 | TFLOPs: 23.38 | +63: iteration 7220/ 73814 | consumed samples: 3696640 | consumed tokens: 7570718720 | elapsed time per iteration (s): 2.23 | learning rate: 1.965E-04 | global batch size: 512 | lm loss: 2.456851E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.425 | TFLOPs: 23.62 | +63: iteration 7230/ 73814 | consumed samples: 3701760 | consumed tokens: 7581204480 | elapsed time per iteration (s): 2.23 | learning rate: 1.965E-04 | global batch size: 512 | lm loss: 2.460087E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.921 | TFLOPs: 23.67 | +63: iteration 7240/ 73814 | consumed samples: 3706880 | consumed tokens: 7591690240 | elapsed time per iteration (s): 2.25 | learning rate: 1.965E-04 | global batch size: 512 | lm loss: 2.454564E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.949 | TFLOPs: 23.47 | +63: iteration 7250/ 73814 | consumed samples: 3712000 | consumed tokens: 7602176000 | elapsed time per iteration (s): 2.25 | learning rate: 1.965E-04 | global batch size: 512 | lm loss: 2.454043E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.266 | TFLOPs: 23.40 | +63: iteration 7260/ 73814 | consumed samples: 3717120 | consumed tokens: 7612661760 | elapsed time per iteration (s): 2.22 | learning rate: 1.965E-04 | global batch size: 512 | lm loss: 2.444405E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.147 | TFLOPs: 23.69 | +63: iteration 7270/ 73814 | consumed samples: 3722240 | consumed tokens: 7623147520 | elapsed time per iteration (s): 2.23 | learning rate: 1.965E-04 | global batch size: 512 | lm loss: 2.434669E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.771 | TFLOPs: 23.65 | +63: iteration 7280/ 73814 | consumed samples: 3727360 | consumed tokens: 7633633280 | elapsed time per iteration (s): 2.25 | learning rate: 1.965E-04 | global batch size: 512 | lm loss: 2.429241E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.142 | TFLOPs: 23.38 | +63: iteration 7290/ 73814 | consumed samples: 3732480 | consumed tokens: 7644119040 | elapsed time per iteration (s): 2.27 | learning rate: 1.965E-04 | global batch size: 512 | lm loss: 2.438089E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.030 | TFLOPs: 23.27 | +63: iteration 7300/ 73814 | consumed samples: 3737600 | consumed tokens: 7654604800 | elapsed time per iteration (s): 2.23 | learning rate: 1.964E-04 | global batch size: 512 | lm loss: 2.455756E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.188 | TFLOPs: 23.59 | +63: iteration 7310/ 73814 | consumed samples: 3742720 | consumed tokens: 7665090560 | elapsed time per iteration (s): 2.24 | learning rate: 1.964E-04 | global batch size: 512 | lm loss: 2.459639E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.978 | TFLOPs: 23.57 | +63: iteration 7320/ 73814 | consumed samples: 3747840 | consumed tokens: 7675576320 | elapsed time per iteration (s): 2.23 | learning rate: 1.964E-04 | global batch size: 512 | lm loss: 2.451349E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.849 | TFLOPs: 23.66 | +63: iteration 7330/ 73814 | consumed samples: 3752960 | consumed tokens: 7686062080 | elapsed time per iteration (s): 2.24 | learning rate: 1.964E-04 | global batch size: 512 | lm loss: 2.439618E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.776 | TFLOPs: 23.55 | +63: iteration 7340/ 73814 | consumed samples: 3758080 | consumed tokens: 7696547840 | elapsed time per iteration (s): 2.23 | learning rate: 1.964E-04 | global batch size: 512 | lm loss: 2.433037E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.154 | TFLOPs: 23.59 | +63: iteration 7350/ 73814 | consumed samples: 3763200 | consumed tokens: 7707033600 | elapsed time per iteration (s): 2.23 | learning rate: 1.964E-04 | global batch size: 512 | lm loss: 2.447920E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.767 | TFLOPs: 23.65 | +63: iteration 7360/ 73814 | consumed samples: 3768320 | consumed tokens: 7717519360 | elapsed time per iteration (s): 2.25 | learning rate: 1.964E-04 | global batch size: 512 | lm loss: 2.435345E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.829 | TFLOPs: 23.45 | +63: iteration 7370/ 73814 | consumed samples: 3773440 | consumed tokens: 7728005120 | elapsed time per iteration (s): 2.23 | learning rate: 1.964E-04 | global batch size: 512 | lm loss: 2.459286E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.683 | TFLOPs: 23.64 | +63: iteration 7380/ 73814 | consumed samples: 3778560 | consumed tokens: 7738490880 | elapsed time per iteration (s): 2.24 | learning rate: 1.964E-04 | global batch size: 512 | lm loss: 2.448299E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.052 | TFLOPs: 23.58 | +63: iteration 7390/ 73814 | consumed samples: 3783680 | consumed tokens: 7748976640 | elapsed time per iteration (s): 2.23 | learning rate: 1.963E-04 | global batch size: 512 | lm loss: 2.446838E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.979 | TFLOPs: 23.68 | +63: iteration 7400/ 73814 | consumed samples: 3788800 | consumed tokens: 7759462400 | elapsed time per iteration (s): 2.23 | learning rate: 1.963E-04 | global batch size: 512 | lm loss: 2.461871E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.890 | TFLOPs: 23.67 | +63: iteration 7410/ 73814 | consumed samples: 3793920 | consumed tokens: 7769948160 | elapsed time per iteration (s): 2.23 | learning rate: 1.963E-04 | global batch size: 512 | lm loss: 2.432254E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.664 | TFLOPs: 23.64 | +63: iteration 7420/ 73814 | consumed samples: 3799040 | consumed tokens: 7780433920 | elapsed time per iteration (s): 2.23 | learning rate: 1.963E-04 | global batch size: 512 | lm loss: 2.438480E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.241 | TFLOPs: 23.60 | +63: iteration 7430/ 73814 | consumed samples: 3804160 | consumed tokens: 7790919680 | elapsed time per iteration (s): 2.25 | learning rate: 1.963E-04 | global batch size: 512 | lm loss: 2.476788E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.632 | TFLOPs: 23.43 | +63: iteration 7440/ 73814 | consumed samples: 3809280 | consumed tokens: 7801405440 | elapsed time per iteration (s): 2.27 | learning rate: 1.963E-04 | global batch size: 512 | lm loss: 2.435217E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.271 | TFLOPs: 23.19 | +63: iteration 7450/ 73814 | consumed samples: 3814400 | consumed tokens: 7811891200 | elapsed time per iteration (s): 2.23 | learning rate: 1.963E-04 | global batch size: 512 | lm loss: 2.428443E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.866 | TFLOPs: 23.66 | +63: iteration 7460/ 73814 | consumed samples: 3819520 | consumed tokens: 7822376960 | elapsed time per iteration (s): 2.23 | learning rate: 1.963E-04 | global batch size: 512 | lm loss: 2.437001E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.252 | TFLOPs: 23.60 | +63: iteration 7470/ 73814 | consumed samples: 3824640 | consumed tokens: 7832862720 | elapsed time per iteration (s): 2.25 | learning rate: 1.963E-04 | global batch size: 512 | lm loss: 2.444856E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.547 | TFLOPs: 23.42 | +63: iteration 7480/ 73814 | consumed samples: 3829760 | consumed tokens: 7843348480 | elapsed time per iteration (s): 2.23 | learning rate: 1.962E-04 | global batch size: 512 | lm loss: 2.445549E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.991 | TFLOPs: 23.68 | +63: iteration 7490/ 73814 | consumed samples: 3834880 | consumed tokens: 7853834240 | elapsed time per iteration (s): 2.23 | learning rate: 1.962E-04 | global batch size: 512 | lm loss: 2.423195E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.798 | TFLOPs: 23.66 | +63: iteration 7500/ 73814 | consumed samples: 3840000 | consumed tokens: 7864320000 | elapsed time per iteration (s): 2.23 | learning rate: 1.962E-04 | global batch size: 512 | lm loss: 2.460868E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.364 | TFLOPs: 23.61 | +63: iteration 7510/ 73814 | consumed samples: 3845120 | consumed tokens: 7874805760 | elapsed time per iteration (s): 2.26 | learning rate: 1.962E-04 | global batch size: 512 | lm loss: 2.427429E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.929 | TFLOPs: 23.36 | +63: iteration 7520/ 73814 | consumed samples: 3850240 | consumed tokens: 7885291520 | elapsed time per iteration (s): 2.27 | learning rate: 1.962E-04 | global batch size: 512 | lm loss: 2.460946E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.303 | TFLOPs: 23.19 | +63: iteration 7530/ 73814 | consumed samples: 3855360 | consumed tokens: 7895777280 | elapsed time per iteration (s): 2.23 | learning rate: 1.962E-04 | global batch size: 512 | lm loss: 2.458808E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.245 | TFLOPs: 23.60 | +63: iteration 7540/ 73814 | consumed samples: 3860480 | consumed tokens: 7906263040 | elapsed time per iteration (s): 2.23 | learning rate: 1.962E-04 | global batch size: 512 | lm loss: 2.427141E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.431 | TFLOPs: 23.62 | +63: iteration 7550/ 73814 | consumed samples: 3865600 | consumed tokens: 7916748800 | elapsed time per iteration (s): 2.24 | learning rate: 1.962E-04 | global batch size: 512 | lm loss: 2.422009E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.942 | TFLOPs: 23.57 | +63: iteration 7560/ 73814 | consumed samples: 3870720 | consumed tokens: 7927234560 | elapsed time per iteration (s): 2.23 | learning rate: 1.962E-04 | global batch size: 512 | lm loss: 2.445820E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.882 | TFLOPs: 23.67 | +63: iteration 7570/ 73814 | consumed samples: 3875840 | consumed tokens: 7937720320 | elapsed time per iteration (s): 2.23 | learning rate: 1.961E-04 | global batch size: 512 | lm loss: 2.453056E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.684 | TFLOPs: 23.64 | +63: iteration 7580/ 73814 | consumed samples: 3880960 | consumed tokens: 7948206080 | elapsed time per iteration (s): 2.23 | learning rate: 1.961E-04 | global batch size: 512 | lm loss: 2.450884E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.947 | TFLOPs: 23.67 | +63: iteration 7590/ 73814 | consumed samples: 3886080 | consumed tokens: 7958691840 | elapsed time per iteration (s): 2.25 | learning rate: 1.961E-04 | global batch size: 512 | lm loss: 2.425130E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.346 | TFLOPs: 23.40 | +63: iteration 7600/ 73814 | consumed samples: 3891200 | consumed tokens: 7969177600 | elapsed time per iteration (s): 2.26 | learning rate: 1.961E-04 | global batch size: 512 | lm loss: 2.433628E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.868 | TFLOPs: 23.35 | +63: iteration 7610/ 73814 | consumed samples: 3896320 | consumed tokens: 7979663360 | elapsed time per iteration (s): 2.24 | learning rate: 1.961E-04 | global batch size: 512 | lm loss: 2.425487E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.418 | TFLOPs: 23.51 | +63: iteration 7620/ 73814 | consumed samples: 3901440 | consumed tokens: 7990149120 | elapsed time per iteration (s): 2.23 | learning rate: 1.961E-04 | global batch size: 512 | lm loss: 2.426180E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.134 | TFLOPs: 23.59 | +63: iteration 7630/ 73814 | consumed samples: 3906560 | consumed tokens: 8000634880 | elapsed time per iteration (s): 2.24 | learning rate: 1.961E-04 | global batch size: 512 | lm loss: 2.427730E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.166 | TFLOPs: 23.49 | +63: iteration 7640/ 73814 | consumed samples: 3911680 | consumed tokens: 8011120640 | elapsed time per iteration (s): 2.24 | learning rate: 1.961E-04 | global batch size: 512 | lm loss: 2.441497E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.161 | TFLOPs: 23.49 | +63: iteration 7650/ 73814 | consumed samples: 3916800 | consumed tokens: 8021606400 | elapsed time per iteration (s): 2.26 | learning rate: 1.961E-04 | global batch size: 512 | lm loss: 2.453098E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.750 | TFLOPs: 23.34 | +63: iteration 7660/ 73814 | consumed samples: 3921920 | consumed tokens: 8032092160 | elapsed time per iteration (s): 2.25 | learning rate: 1.960E-04 | global batch size: 512 | lm loss: 2.438737E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.014 | TFLOPs: 23.47 | +63: iteration 7670/ 73814 | consumed samples: 3927040 | consumed tokens: 8042577920 | elapsed time per iteration (s): 2.23 | learning rate: 1.960E-04 | global batch size: 512 | lm loss: 2.434202E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.384 | TFLOPs: 23.61 | +63: iteration 7680/ 73814 | consumed samples: 3932160 | consumed tokens: 8053063680 | elapsed time per iteration (s): 2.24 | learning rate: 1.960E-04 | global batch size: 512 | lm loss: 2.445367E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.072 | TFLOPs: 23.48 | +63: iteration 7690/ 73814 | consumed samples: 3937280 | consumed tokens: 8063549440 | elapsed time per iteration (s): 2.24 | learning rate: 1.960E-04 | global batch size: 512 | lm loss: 2.422778E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.694 | TFLOPs: 23.54 | +63: iteration 7700/ 73814 | consumed samples: 3942400 | consumed tokens: 8074035200 | elapsed time per iteration (s): 2.23 | learning rate: 1.960E-04 | global batch size: 512 | lm loss: 2.453149E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.678 | TFLOPs: 23.64 | +63: iteration 7710/ 73814 | consumed samples: 3947520 | consumed tokens: 8084520960 | elapsed time per iteration (s): 2.26 | learning rate: 1.960E-04 | global batch size: 512 | lm loss: 2.432901E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.708 | TFLOPs: 23.34 | +63: iteration 7720/ 73814 | consumed samples: 3952640 | consumed tokens: 8095006720 | elapsed time per iteration (s): 2.23 | learning rate: 1.960E-04 | global batch size: 512 | lm loss: 2.440855E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.795 | TFLOPs: 23.66 | +63: iteration 7730/ 73814 | consumed samples: 3957760 | consumed tokens: 8105492480 | elapsed time per iteration (s): 2.28 | learning rate: 1.960E-04 | global batch size: 512 | lm loss: 2.439097E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.391 | TFLOPs: 23.10 | +63: iteration 7740/ 73814 | consumed samples: 3962880 | consumed tokens: 8115978240 | elapsed time per iteration (s): 2.26 | learning rate: 1.960E-04 | global batch size: 512 | lm loss: 2.418573E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.043 | TFLOPs: 23.37 | +63: iteration 7750/ 73814 | consumed samples: 3968000 | consumed tokens: 8126464000 | elapsed time per iteration (s): 2.25 | learning rate: 1.959E-04 | global batch size: 512 | lm loss: 2.438573E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.989 | TFLOPs: 23.47 | +63: iteration 7760/ 73814 | consumed samples: 3973120 | consumed tokens: 8136949760 | elapsed time per iteration (s): 2.24 | learning rate: 1.959E-04 | global batch size: 512 | lm loss: 2.438736E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.566 | TFLOPs: 23.53 | +63: iteration 7770/ 73814 | consumed samples: 3978240 | consumed tokens: 8147435520 | elapsed time per iteration (s): 2.25 | learning rate: 1.959E-04 | global batch size: 512 | lm loss: 2.439047E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.474 | TFLOPs: 23.42 | +63: iteration 7780/ 73814 | consumed samples: 3983360 | consumed tokens: 8157921280 | elapsed time per iteration (s): 2.25 | learning rate: 1.959E-04 | global batch size: 512 | lm loss: 2.448801E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.379 | TFLOPs: 23.41 | +63: iteration 7790/ 73814 | consumed samples: 3988480 | consumed tokens: 8168407040 | elapsed time per iteration (s): 2.23 | learning rate: 1.959E-04 | global batch size: 512 | lm loss: 2.420356E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.698 | TFLOPs: 23.65 | +63: iteration 7800/ 73814 | consumed samples: 3993600 | consumed tokens: 8178892800 | elapsed time per iteration (s): 2.23 | learning rate: 1.959E-04 | global batch size: 512 | lm loss: 2.444025E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.817 | TFLOPs: 23.66 | +63: iteration 7810/ 73814 | consumed samples: 3998720 | consumed tokens: 8189378560 | elapsed time per iteration (s): 2.23 | learning rate: 1.959E-04 | global batch size: 512 | lm loss: 2.424773E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.280 | TFLOPs: 23.60 | +63: iteration 7820/ 73814 | consumed samples: 4003840 | consumed tokens: 8199864320 | elapsed time per iteration (s): 2.23 | learning rate: 1.959E-04 | global batch size: 512 | lm loss: 2.432079E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.479 | TFLOPs: 23.62 | +63: iteration 7830/ 73814 | consumed samples: 4008960 | consumed tokens: 8210350080 | elapsed time per iteration (s): 2.25 | learning rate: 1.958E-04 | global batch size: 512 | lm loss: 2.430721E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.466 | TFLOPs: 23.42 | +63: iteration 7840/ 73814 | consumed samples: 4014080 | consumed tokens: 8220835840 | elapsed time per iteration (s): 2.23 | learning rate: 1.958E-04 | global batch size: 512 | lm loss: 2.433530E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.477 | TFLOPs: 23.62 | +63: iteration 7850/ 73814 | consumed samples: 4019200 | consumed tokens: 8231321600 | elapsed time per iteration (s): 2.25 | learning rate: 1.958E-04 | global batch size: 512 | lm loss: 2.424845E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.485 | TFLOPs: 23.42 | +63: iteration 7860/ 73814 | consumed samples: 4024320 | consumed tokens: 8241807360 | elapsed time per iteration (s): 2.24 | learning rate: 1.958E-04 | global batch size: 512 | lm loss: 2.421188E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.484 | TFLOPs: 23.52 | +63: iteration 7870/ 73814 | consumed samples: 4029440 | consumed tokens: 8252293120 | elapsed time per iteration (s): 2.25 | learning rate: 1.958E-04 | global batch size: 512 | lm loss: 2.454758E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.401 | TFLOPs: 23.41 | +63: iteration 7880/ 73814 | consumed samples: 4034560 | consumed tokens: 8262778880 | elapsed time per iteration (s): 2.22 | learning rate: 1.958E-04 | global batch size: 512 | lm loss: 2.449493E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.338 | TFLOPs: 23.71 | +63: iteration 7890/ 73814 | consumed samples: 4039680 | consumed tokens: 8273264640 | elapsed time per iteration (s): 2.23 | learning rate: 1.958E-04 | global batch size: 512 | lm loss: 2.411542E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.493 | TFLOPs: 23.63 | +63: iteration 7900/ 73814 | consumed samples: 4044800 | consumed tokens: 8283750400 | elapsed time per iteration (s): 2.24 | learning rate: 1.958E-04 | global batch size: 512 | lm loss: 2.415441E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.508 | TFLOPs: 23.52 | +63: iteration 7910/ 73814 | consumed samples: 4049920 | consumed tokens: 8294236160 | elapsed time per iteration (s): 2.26 | learning rate: 1.958E-04 | global batch size: 512 | lm loss: 2.420460E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.230 | TFLOPs: 23.29 | +63: iteration 7920/ 73814 | consumed samples: 4055040 | consumed tokens: 8304721920 | elapsed time per iteration (s): 2.24 | learning rate: 1.957E-04 | global batch size: 512 | lm loss: 2.437276E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.427 | TFLOPs: 23.52 | +63: iteration 7930/ 73814 | consumed samples: 4060160 | consumed tokens: 8315207680 | elapsed time per iteration (s): 2.23 | learning rate: 1.957E-04 | global batch size: 512 | lm loss: 2.424736E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.685 | TFLOPs: 23.64 | +63: iteration 7940/ 73814 | consumed samples: 4065280 | consumed tokens: 8325693440 | elapsed time per iteration (s): 2.25 | learning rate: 1.957E-04 | global batch size: 512 | lm loss: 2.424364E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.677 | TFLOPs: 23.44 | +63: iteration 7950/ 73814 | consumed samples: 4070400 | consumed tokens: 8336179200 | elapsed time per iteration (s): 9.70 | learning rate: 1.957E-04 | global batch size: 512 | lm loss: 2.428869E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 52.789 | TFLOPs: 5.43 | +63: iteration 7960/ 73814 | consumed samples: 4075520 | consumed tokens: 8346664960 | elapsed time per iteration (s): 2.40 | learning rate: 1.957E-04 | global batch size: 512 | lm loss: 2.442324E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.369 | TFLOPs: 21.97 | +63: iteration 7970/ 73814 | consumed samples: 4080640 | consumed tokens: 8357150720 | elapsed time per iteration (s): 2.24 | learning rate: 1.957E-04 | global batch size: 512 | lm loss: 2.432796E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.325 | TFLOPs: 23.50 | +63: iteration 7980/ 73814 | consumed samples: 4085760 | consumed tokens: 8367636480 | elapsed time per iteration (s): 2.23 | learning rate: 1.957E-04 | global batch size: 512 | lm loss: 2.423143E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.832 | TFLOPs: 23.66 | +63: iteration 7990/ 73814 | consumed samples: 4090880 | consumed tokens: 8378122240 | elapsed time per iteration (s): 2.23 | learning rate: 1.957E-04 | global batch size: 512 | lm loss: 2.406543E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.597 | TFLOPs: 23.64 | + 0: [2022-12-01 16:51:59,097] [INFO] [logging.py:68:log_dist] [Rank 0] step=8000, skipped=0, lr=[0.0001956496441395577, 0.0001956496441395577, 0.0001956496441395577], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 8000/ 73814 | consumed samples: 4096000 | consumed tokens: 8388608000 | elapsed time per iteration (s): 2.24 | learning rate: 1.956E-04 | global batch size: 512 | lm loss: 2.422167E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.568 | TFLOPs: 23.53 | + 0: steps: 8000 loss: 2.4195 iter time (s): 2.293 samples/sec: 223.242 +63: ------------------------------------------------------------------------------------------ +63: valid loss at iteration 8000 | lm loss value: 2.374840E+00 | lm loss PPL: 1.074930E+01 | +63: ------------------------------------------------------------------------------------------ +63: iteration 8010/ 73814 | consumed samples: 4101120 | consumed tokens: 8399093760 | elapsed time per iteration (s): 2.30 | learning rate: 1.956E-04 | global batch size: 512 | lm loss: 2.422395E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.407 | TFLOPs: 22.90 | +63: iteration 8020/ 73814 | consumed samples: 4106240 | consumed tokens: 8409579520 | elapsed time per iteration (s): 2.23 | learning rate: 1.956E-04 | global batch size: 512 | lm loss: 2.395173E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.404 | TFLOPs: 23.62 | +63: iteration 8030/ 73814 | consumed samples: 4111360 | consumed tokens: 8420065280 | elapsed time per iteration (s): 2.23 | learning rate: 1.956E-04 | global batch size: 512 | lm loss: 2.408339E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.923 | TFLOPs: 23.67 | +63: iteration 8040/ 73814 | consumed samples: 4116480 | consumed tokens: 8430551040 | elapsed time per iteration (s): 2.23 | learning rate: 1.956E-04 | global batch size: 512 | lm loss: 2.435896E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.647 | TFLOPs: 23.64 | +63: iteration 8050/ 73814 | consumed samples: 4121600 | consumed tokens: 8441036800 | elapsed time per iteration (s): 26.03 | learning rate: 1.956E-04 | global batch size: 512 | lm loss: 2.393340E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 19.668 | TFLOPs: 2.02 | +63: iteration 8060/ 73814 | consumed samples: 4126720 | consumed tokens: 8451522560 | elapsed time per iteration (s): 2.28 | learning rate: 1.956E-04 | global batch size: 512 | lm loss: 2.416630E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.177 | TFLOPs: 23.08 | +63: iteration 8070/ 73814 | consumed samples: 4131840 | consumed tokens: 8462008320 | elapsed time per iteration (s): 2.23 | learning rate: 1.956E-04 | global batch size: 512 | lm loss: 2.416343E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.621 | TFLOPs: 23.64 | +63: iteration 8080/ 73814 | consumed samples: 4136960 | consumed tokens: 8472494080 | elapsed time per iteration (s): 2.24 | learning rate: 1.956E-04 | global batch size: 512 | lm loss: 2.399039E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.202 | TFLOPs: 23.49 | +63: iteration 8090/ 73814 | consumed samples: 4142080 | consumed tokens: 8482979840 | elapsed time per iteration (s): 2.24 | learning rate: 1.955E-04 | global batch size: 512 | lm loss: 2.396152E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.901 | TFLOPs: 23.56 | +63: iteration 8100/ 73814 | consumed samples: 4147200 | consumed tokens: 8493465600 | elapsed time per iteration (s): 2.26 | learning rate: 1.955E-04 | global batch size: 512 | lm loss: 2.414353E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.231 | TFLOPs: 23.29 | +63: iteration 8110/ 73814 | consumed samples: 4152320 | consumed tokens: 8503951360 | elapsed time per iteration (s): 2.23 | learning rate: 1.955E-04 | global batch size: 512 | lm loss: 2.439734E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.229 | TFLOPs: 23.60 | +63: iteration 8120/ 73814 | consumed samples: 4157440 | consumed tokens: 8514437120 | elapsed time per iteration (s): 2.23 | learning rate: 1.955E-04 | global batch size: 512 | lm loss: 2.415471E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.515 | TFLOPs: 23.63 | +63: iteration 8130/ 73814 | consumed samples: 4162560 | consumed tokens: 8524922880 | elapsed time per iteration (s): 2.24 | learning rate: 1.955E-04 | global batch size: 512 | lm loss: 2.405690E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.564 | TFLOPs: 23.53 | +63: iteration 8140/ 73814 | consumed samples: 4167680 | consumed tokens: 8535408640 | elapsed time per iteration (s): 2.23 | learning rate: 1.955E-04 | global batch size: 512 | lm loss: 2.402453E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.749 | TFLOPs: 23.65 | +63: iteration 8150/ 73814 | consumed samples: 4172800 | consumed tokens: 8545894400 | elapsed time per iteration (s): 2.23 | learning rate: 1.955E-04 | global batch size: 512 | lm loss: 2.429644E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.751 | TFLOPs: 23.65 | +63: iteration 8160/ 73814 | consumed samples: 4177920 | consumed tokens: 8556380160 | elapsed time per iteration (s): 2.23 | learning rate: 1.955E-04 | global batch size: 512 | lm loss: 2.396837E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.415 | TFLOPs: 23.62 | +63: iteration 8170/ 73814 | consumed samples: 4183040 | consumed tokens: 8566865920 | elapsed time per iteration (s): 2.26 | learning rate: 1.954E-04 | global batch size: 512 | lm loss: 2.403761E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.255 | TFLOPs: 23.29 | +63: iteration 8180/ 73814 | consumed samples: 4188160 | consumed tokens: 8577351680 | elapsed time per iteration (s): 2.31 | learning rate: 1.954E-04 | global batch size: 512 | lm loss: 2.440587E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.393 | TFLOPs: 22.79 | +63: iteration 8190/ 73814 | consumed samples: 4193280 | consumed tokens: 8587837440 | elapsed time per iteration (s): 2.23 | learning rate: 1.954E-04 | global batch size: 512 | lm loss: 2.430147E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.319 | TFLOPs: 23.61 | +63: iteration 8200/ 73814 | consumed samples: 4198400 | consumed tokens: 8598323200 | elapsed time per iteration (s): 2.33 | learning rate: 1.954E-04 | global batch size: 512 | lm loss: 2.403038E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.060 | TFLOPs: 22.65 | +63: iteration 8210/ 73814 | consumed samples: 4203520 | consumed tokens: 8608808960 | elapsed time per iteration (s): 2.26 | learning rate: 1.954E-04 | global batch size: 512 | lm loss: 2.430830E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.257 | TFLOPs: 23.29 | +63: iteration 8220/ 73814 | consumed samples: 4208640 | consumed tokens: 8619294720 | elapsed time per iteration (s): 2.45 | learning rate: 1.954E-04 | global batch size: 512 | lm loss: 2.395935E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.271 | TFLOPs: 21.54 | +63: iteration 8230/ 73814 | consumed samples: 4213760 | consumed tokens: 8629780480 | elapsed time per iteration (s): 2.44 | learning rate: 1.954E-04 | global batch size: 512 | lm loss: 2.389027E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.070 | TFLOPs: 21.63 | +63: iteration 8240/ 73814 | consumed samples: 4218880 | consumed tokens: 8640266240 | elapsed time per iteration (s): 2.53 | learning rate: 1.954E-04 | global batch size: 512 | lm loss: 2.407677E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.195 | TFLOPs: 20.82 | +63: iteration 8250/ 73814 | consumed samples: 4224000 | consumed tokens: 8650752000 | elapsed time per iteration (s): 2.35 | learning rate: 1.953E-04 | global batch size: 512 | lm loss: 2.406548E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.058 | TFLOPs: 22.45 | +63: iteration 8260/ 73814 | consumed samples: 4229120 | consumed tokens: 8661237760 | elapsed time per iteration (s): 2.24 | learning rate: 1.953E-04 | global batch size: 512 | lm loss: 2.414126E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.465 | TFLOPs: 23.52 | +63: iteration 8270/ 73814 | consumed samples: 4234240 | consumed tokens: 8671723520 | elapsed time per iteration (s): 2.32 | learning rate: 1.953E-04 | global batch size: 512 | lm loss: 2.396173E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.815 | TFLOPs: 22.73 | +63: iteration 8280/ 73814 | consumed samples: 4239360 | consumed tokens: 8682209280 | elapsed time per iteration (s): 2.45 | learning rate: 1.953E-04 | global batch size: 512 | lm loss: 2.429371E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.798 | TFLOPs: 21.49 | +63: iteration 8290/ 73814 | consumed samples: 4244480 | consumed tokens: 8692695040 | elapsed time per iteration (s): 2.28 | learning rate: 1.953E-04 | global batch size: 512 | lm loss: 2.392494E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.968 | TFLOPs: 23.16 | +63: iteration 8300/ 73814 | consumed samples: 4249600 | consumed tokens: 8703180800 | elapsed time per iteration (s): 2.28 | learning rate: 1.953E-04 | global batch size: 512 | lm loss: 2.404083E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.160 | TFLOPs: 23.08 | +63: iteration 8310/ 73814 | consumed samples: 4254720 | consumed tokens: 8713666560 | elapsed time per iteration (s): 2.23 | learning rate: 1.953E-04 | global batch size: 512 | lm loss: 2.411185E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.224 | TFLOPs: 23.60 | +63: iteration 8320/ 73814 | consumed samples: 4259840 | consumed tokens: 8724152320 | elapsed time per iteration (s): 2.43 | learning rate: 1.953E-04 | global batch size: 512 | lm loss: 2.393746E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.841 | TFLOPs: 21.71 | +63: iteration 8330/ 73814 | consumed samples: 4264960 | consumed tokens: 8734638080 | elapsed time per iteration (s): 2.23 | learning rate: 1.952E-04 | global batch size: 512 | lm loss: 2.400451E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.827 | TFLOPs: 23.66 | +63: iteration 8340/ 73814 | consumed samples: 4270080 | consumed tokens: 8745123840 | elapsed time per iteration (s): 2.27 | learning rate: 1.952E-04 | global batch size: 512 | lm loss: 2.393908E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.296 | TFLOPs: 23.19 | +63: iteration 8350/ 73814 | consumed samples: 4275200 | consumed tokens: 8755609600 | elapsed time per iteration (s): 2.23 | learning rate: 1.952E-04 | global batch size: 512 | lm loss: 2.403899E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.934 | TFLOPs: 23.67 | +63: iteration 8360/ 73814 | consumed samples: 4280320 | consumed tokens: 8766095360 | elapsed time per iteration (s): 2.24 | learning rate: 1.952E-04 | global batch size: 512 | lm loss: 2.397505E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.437 | TFLOPs: 23.52 | +63: iteration 8370/ 73814 | consumed samples: 4285440 | consumed tokens: 8776581120 | elapsed time per iteration (s): 2.33 | learning rate: 1.952E-04 | global batch size: 512 | lm loss: 2.423978E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.832 | TFLOPs: 22.63 | +63: iteration 8380/ 73814 | consumed samples: 4290560 | consumed tokens: 8787066880 | elapsed time per iteration (s): 2.24 | learning rate: 1.952E-04 | global batch size: 512 | lm loss: 2.430225E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.277 | TFLOPs: 23.50 | +63: iteration 8390/ 73814 | consumed samples: 4295680 | consumed tokens: 8797552640 | elapsed time per iteration (s): 2.25 | learning rate: 1.952E-04 | global batch size: 512 | lm loss: 2.417801E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.797 | TFLOPs: 23.45 | +63: iteration 8400/ 73814 | consumed samples: 4300800 | consumed tokens: 8808038400 | elapsed time per iteration (s): 2.39 | learning rate: 1.952E-04 | global batch size: 512 | lm loss: 2.418081E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.322 | TFLOPs: 22.06 | +63: iteration 8410/ 73814 | consumed samples: 4305920 | consumed tokens: 8818524160 | elapsed time per iteration (s): 2.23 | learning rate: 1.951E-04 | global batch size: 512 | lm loss: 2.415348E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.083 | TFLOPs: 23.69 | +63: iteration 8420/ 73814 | consumed samples: 4311040 | consumed tokens: 8829009920 | elapsed time per iteration (s): 2.23 | learning rate: 1.951E-04 | global batch size: 512 | lm loss: 2.387915E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.094 | TFLOPs: 23.58 | +63: iteration 8430/ 73814 | consumed samples: 4316160 | consumed tokens: 8839495680 | elapsed time per iteration (s): 2.30 | learning rate: 1.951E-04 | global batch size: 512 | lm loss: 2.423313E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.373 | TFLOPs: 22.89 | +63: iteration 8440/ 73814 | consumed samples: 4321280 | consumed tokens: 8849981440 | elapsed time per iteration (s): 2.40 | learning rate: 1.951E-04 | global batch size: 512 | lm loss: 2.386839E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.622 | TFLOPs: 21.99 | +63: iteration 8450/ 73814 | consumed samples: 4326400 | consumed tokens: 8860467200 | elapsed time per iteration (s): 2.25 | learning rate: 1.951E-04 | global batch size: 512 | lm loss: 2.400455E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.760 | TFLOPs: 23.45 | +63: iteration 8460/ 73814 | consumed samples: 4331520 | consumed tokens: 8870952960 | elapsed time per iteration (s): 2.24 | learning rate: 1.951E-04 | global batch size: 512 | lm loss: 2.391731E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.805 | TFLOPs: 23.55 | +63: iteration 8470/ 73814 | consumed samples: 4336640 | consumed tokens: 8881438720 | elapsed time per iteration (s): 2.24 | learning rate: 1.951E-04 | global batch size: 512 | lm loss: 2.396984E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.156 | TFLOPs: 23.49 | +63: iteration 8480/ 73814 | consumed samples: 4341760 | consumed tokens: 8891924480 | elapsed time per iteration (s): 2.29 | learning rate: 1.951E-04 | global batch size: 512 | lm loss: 2.415634E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.101 | TFLOPs: 22.97 | +63: iteration 8490/ 73814 | consumed samples: 4346880 | consumed tokens: 8902410240 | elapsed time per iteration (s): 2.33 | learning rate: 1.950E-04 | global batch size: 512 | lm loss: 2.391309E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.942 | TFLOPs: 22.64 | +63: iteration 8500/ 73814 | consumed samples: 4352000 | consumed tokens: 8912896000 | elapsed time per iteration (s): 2.23 | learning rate: 1.950E-04 | global batch size: 512 | lm loss: 2.383400E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.533 | TFLOPs: 23.63 | +63: iteration 8510/ 73814 | consumed samples: 4357120 | consumed tokens: 8923381760 | elapsed time per iteration (s): 2.25 | learning rate: 1.950E-04 | global batch size: 512 | lm loss: 2.403880E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.155 | TFLOPs: 23.38 | +63: iteration 8520/ 73814 | consumed samples: 4362240 | consumed tokens: 8933867520 | elapsed time per iteration (s): 2.26 | learning rate: 1.950E-04 | global batch size: 512 | lm loss: 2.520783E+00 | grad norm: 27.079 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.993 | TFLOPs: 23.37 | +63: iteration 8530/ 73814 | consumed samples: 4367360 | consumed tokens: 8944353280 | elapsed time per iteration (s): 2.25 | learning rate: 1.950E-04 | global batch size: 512 | lm loss: 9.787864E+00 | grad norm: 4.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.553 | TFLOPs: 23.43 | +63: iteration 8540/ 73814 | consumed samples: 4372480 | consumed tokens: 8954839040 | elapsed time per iteration (s): 2.24 | learning rate: 1.950E-04 | global batch size: 512 | lm loss: 8.655133E+00 | grad norm: 2.988 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.233 | TFLOPs: 23.50 | +63: iteration 8550/ 73814 | consumed samples: 4377600 | consumed tokens: 8965324800 | elapsed time per iteration (s): 2.23 | learning rate: 1.950E-04 | global batch size: 512 | lm loss: 7.979011E+00 | grad norm: 1.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.790 | TFLOPs: 23.66 | +63: iteration 8560/ 73814 | consumed samples: 4382720 | consumed tokens: 8975810560 | elapsed time per iteration (s): 2.25 | learning rate: 1.950E-04 | global batch size: 512 | lm loss: 7.623789E+00 | grad norm: 1.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.261 | TFLOPs: 23.40 | +63: iteration 8570/ 73814 | consumed samples: 4387840 | consumed tokens: 8986296320 | elapsed time per iteration (s): 2.24 | learning rate: 1.949E-04 | global batch size: 512 | lm loss: 7.321870E+00 | grad norm: 1.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.506 | TFLOPs: 23.52 | +63: iteration 8580/ 73814 | consumed samples: 4392960 | consumed tokens: 8996782080 | elapsed time per iteration (s): 2.27 | learning rate: 1.949E-04 | global batch size: 512 | lm loss: 6.945401E+00 | grad norm: 0.854 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.310 | TFLOPs: 23.19 | +63: iteration 8590/ 73814 | consumed samples: 4398080 | consumed tokens: 9007267840 | elapsed time per iteration (s): 2.26 | learning rate: 1.949E-04 | global batch size: 512 | lm loss: 6.658221E+00 | grad norm: 0.867 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.467 | TFLOPs: 23.31 | +63: iteration 8600/ 73814 | consumed samples: 4403200 | consumed tokens: 9017753600 | elapsed time per iteration (s): 2.26 | learning rate: 1.949E-04 | global batch size: 512 | lm loss: 6.538675E+00 | grad norm: 1.013 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.680 | TFLOPs: 23.34 | +63: iteration 8610/ 73814 | consumed samples: 4408320 | consumed tokens: 9028239360 | elapsed time per iteration (s): 2.29 | learning rate: 1.949E-04 | global batch size: 512 | lm loss: 6.369421E+00 | grad norm: 0.779 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.322 | TFLOPs: 22.99 | +63: iteration 8620/ 73814 | consumed samples: 4413440 | consumed tokens: 9038725120 | elapsed time per iteration (s): 2.25 | learning rate: 1.949E-04 | global batch size: 512 | lm loss: 6.191006E+00 | grad norm: 0.520 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.981 | TFLOPs: 23.47 | +63: iteration 8630/ 73814 | consumed samples: 4418560 | consumed tokens: 9049210880 | elapsed time per iteration (s): 2.24 | learning rate: 1.949E-04 | global batch size: 512 | lm loss: 5.961716E+00 | grad norm: 0.844 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.691 | TFLOPs: 23.54 | +63: iteration 8640/ 73814 | consumed samples: 4423680 | consumed tokens: 9059696640 | elapsed time per iteration (s): 2.26 | learning rate: 1.949E-04 | global batch size: 512 | lm loss: 5.845874E+00 | grad norm: 0.951 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.876 | TFLOPs: 23.36 | +63: iteration 8650/ 73814 | consumed samples: 4428800 | consumed tokens: 9070182400 | elapsed time per iteration (s): 2.26 | learning rate: 1.948E-04 | global batch size: 512 | lm loss: 5.454401E+00 | grad norm: 1.028 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.018 | TFLOPs: 23.37 | +63: iteration 8660/ 73814 | consumed samples: 4433920 | consumed tokens: 9080668160 | elapsed time per iteration (s): 2.26 | learning rate: 1.948E-04 | global batch size: 512 | lm loss: 4.955354E+00 | grad norm: 1.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.192 | TFLOPs: 23.29 | +63: iteration 8670/ 73814 | consumed samples: 4439040 | consumed tokens: 9091153920 | elapsed time per iteration (s): 2.24 | learning rate: 1.948E-04 | global batch size: 512 | lm loss: 4.094859E+00 | grad norm: 1.530 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.281 | TFLOPs: 23.50 | +63: iteration 8680/ 73814 | consumed samples: 4444160 | consumed tokens: 9101639680 | elapsed time per iteration (s): 2.24 | learning rate: 1.948E-04 | global batch size: 512 | lm loss: 3.646949E+00 | grad norm: 0.839 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.076 | TFLOPs: 23.48 | +63: iteration 8690/ 73814 | consumed samples: 4449280 | consumed tokens: 9112125440 | elapsed time per iteration (s): 2.25 | learning rate: 1.948E-04 | global batch size: 512 | lm loss: 3.257650E+00 | grad norm: 0.809 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.344 | TFLOPs: 23.40 | +63: iteration 8700/ 73814 | consumed samples: 4454400 | consumed tokens: 9122611200 | elapsed time per iteration (s): 2.27 | learning rate: 1.948E-04 | global batch size: 512 | lm loss: 3.039478E+00 | grad norm: 0.728 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.956 | TFLOPs: 23.26 | +63: iteration 8710/ 73814 | consumed samples: 4459520 | consumed tokens: 9133096960 | elapsed time per iteration (s): 2.25 | learning rate: 1.948E-04 | global batch size: 512 | lm loss: 2.863137E+00 | grad norm: 0.623 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.744 | TFLOPs: 23.45 | +63: iteration 8720/ 73814 | consumed samples: 4464640 | consumed tokens: 9143582720 | elapsed time per iteration (s): 2.28 | learning rate: 1.948E-04 | global batch size: 512 | lm loss: 2.712876E+00 | grad norm: 0.639 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.644 | TFLOPs: 23.13 | +63: iteration 8730/ 73814 | consumed samples: 4469760 | consumed tokens: 9154068480 | elapsed time per iteration (s): 2.23 | learning rate: 1.947E-04 | global batch size: 512 | lm loss: 2.633606E+00 | grad norm: 0.403 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.940 | TFLOPs: 23.67 | +63: iteration 8740/ 73814 | consumed samples: 4474880 | consumed tokens: 9164554240 | elapsed time per iteration (s): 2.25 | learning rate: 1.947E-04 | global batch size: 512 | lm loss: 2.559681E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.698 | TFLOPs: 23.44 | +63: iteration 8750/ 73814 | consumed samples: 4480000 | consumed tokens: 9175040000 | elapsed time per iteration (s): 2.23 | learning rate: 1.947E-04 | global batch size: 512 | lm loss: 2.548285E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.064 | TFLOPs: 23.68 | +63: iteration 8760/ 73814 | consumed samples: 4485120 | consumed tokens: 9185525760 | elapsed time per iteration (s): 2.23 | learning rate: 1.947E-04 | global batch size: 512 | lm loss: 2.485567E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.777 | TFLOPs: 23.65 | +63: iteration 8770/ 73814 | consumed samples: 4490240 | consumed tokens: 9196011520 | elapsed time per iteration (s): 2.23 | learning rate: 1.947E-04 | global batch size: 512 | lm loss: 2.518502E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.724 | TFLOPs: 23.65 | +63: iteration 8780/ 73814 | consumed samples: 4495360 | consumed tokens: 9206497280 | elapsed time per iteration (s): 2.23 | learning rate: 1.947E-04 | global batch size: 512 | lm loss: 2.473198E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.317 | TFLOPs: 23.61 | +63: iteration 8790/ 73814 | consumed samples: 4500480 | consumed tokens: 9216983040 | elapsed time per iteration (s): 2.26 | learning rate: 1.947E-04 | global batch size: 512 | lm loss: 2.473234E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.844 | TFLOPs: 23.35 | +63: iteration 8800/ 73814 | consumed samples: 4505600 | consumed tokens: 9227468800 | elapsed time per iteration (s): 2.23 | learning rate: 1.946E-04 | global batch size: 512 | lm loss: 2.476422E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.268 | TFLOPs: 23.60 | +63: iteration 8810/ 73814 | consumed samples: 4510720 | consumed tokens: 9237954560 | elapsed time per iteration (s): 2.23 | learning rate: 1.946E-04 | global batch size: 512 | lm loss: 2.452615E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.847 | TFLOPs: 23.66 | +63: iteration 8820/ 73814 | consumed samples: 4515840 | consumed tokens: 9248440320 | elapsed time per iteration (s): 2.25 | learning rate: 1.946E-04 | global batch size: 512 | lm loss: 2.452073E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.561 | TFLOPs: 23.43 | +63: iteration 8830/ 73814 | consumed samples: 4520960 | consumed tokens: 9258926080 | elapsed time per iteration (s): 2.23 | learning rate: 1.946E-04 | global batch size: 512 | lm loss: 2.451910E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.034 | TFLOPs: 23.68 | +63: iteration 8840/ 73814 | consumed samples: 4526080 | consumed tokens: 9269411840 | elapsed time per iteration (s): 2.23 | learning rate: 1.946E-04 | global batch size: 512 | lm loss: 2.465834E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.965 | TFLOPs: 23.67 | +63: iteration 8850/ 73814 | consumed samples: 4531200 | consumed tokens: 9279897600 | elapsed time per iteration (s): 2.27 | learning rate: 1.946E-04 | global batch size: 512 | lm loss: 2.447618E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.759 | TFLOPs: 23.24 | +63: iteration 8860/ 73814 | consumed samples: 4536320 | consumed tokens: 9290383360 | elapsed time per iteration (s): 2.24 | learning rate: 1.946E-04 | global batch size: 512 | lm loss: 2.437095E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.780 | TFLOPs: 23.55 | +63: iteration 8870/ 73814 | consumed samples: 4541440 | consumed tokens: 9300869120 | elapsed time per iteration (s): 2.25 | learning rate: 1.946E-04 | global batch size: 512 | lm loss: 2.429869E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.351 | TFLOPs: 23.40 | +63: iteration 8880/ 73814 | consumed samples: 4546560 | consumed tokens: 9311354880 | elapsed time per iteration (s): 2.24 | learning rate: 1.945E-04 | global batch size: 512 | lm loss: 2.443349E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.748 | TFLOPs: 23.55 | +63: iteration 8890/ 73814 | consumed samples: 4551680 | consumed tokens: 9321840640 | elapsed time per iteration (s): 2.23 | learning rate: 1.945E-04 | global batch size: 512 | lm loss: 2.441163E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.097 | TFLOPs: 23.58 | +63: iteration 8900/ 73814 | consumed samples: 4556800 | consumed tokens: 9332326400 | elapsed time per iteration (s): 2.25 | learning rate: 1.945E-04 | global batch size: 512 | lm loss: 2.454462E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.645 | TFLOPs: 23.44 | +63: iteration 8910/ 73814 | consumed samples: 4561920 | consumed tokens: 9342812160 | elapsed time per iteration (s): 2.27 | learning rate: 1.945E-04 | global batch size: 512 | lm loss: 2.436789E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.109 | TFLOPs: 23.17 | +63: iteration 8920/ 73814 | consumed samples: 4567040 | consumed tokens: 9353297920 | elapsed time per iteration (s): 2.27 | learning rate: 1.945E-04 | global batch size: 512 | lm loss: 2.428882E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.494 | TFLOPs: 23.21 | +63: iteration 8930/ 73814 | consumed samples: 4572160 | consumed tokens: 9363783680 | elapsed time per iteration (s): 2.29 | learning rate: 1.945E-04 | global batch size: 512 | lm loss: 2.421810E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.469 | TFLOPs: 23.01 | +63: iteration 8940/ 73814 | consumed samples: 4577280 | consumed tokens: 9374269440 | elapsed time per iteration (s): 2.23 | learning rate: 1.945E-04 | global batch size: 512 | lm loss: 2.430126E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.513 | TFLOPs: 23.63 | +63: iteration 8950/ 73814 | consumed samples: 4582400 | consumed tokens: 9384755200 | elapsed time per iteration (s): 2.24 | learning rate: 1.944E-04 | global batch size: 512 | lm loss: 2.445181E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.121 | TFLOPs: 23.48 | +63: iteration 8960/ 73814 | consumed samples: 4587520 | consumed tokens: 9395240960 | elapsed time per iteration (s): 2.27 | learning rate: 1.944E-04 | global batch size: 512 | lm loss: 2.411381E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.891 | TFLOPs: 23.25 | +63: iteration 8970/ 73814 | consumed samples: 4592640 | consumed tokens: 9405726720 | elapsed time per iteration (s): 2.23 | learning rate: 1.944E-04 | global batch size: 512 | lm loss: 2.417101E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.470 | TFLOPs: 23.62 | +63: iteration 8980/ 73814 | consumed samples: 4597760 | consumed tokens: 9416212480 | elapsed time per iteration (s): 2.24 | learning rate: 1.944E-04 | global batch size: 512 | lm loss: 2.427403E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.353 | TFLOPs: 23.51 | +63: iteration 8990/ 73814 | consumed samples: 4602880 | consumed tokens: 9426698240 | elapsed time per iteration (s): 2.24 | learning rate: 1.944E-04 | global batch size: 512 | lm loss: 2.425919E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.580 | TFLOPs: 23.53 | +63: iteration 9000/ 73814 | consumed samples: 4608000 | consumed tokens: 9437184000 | elapsed time per iteration (s): 2.24 | learning rate: 1.944E-04 | global batch size: 512 | lm loss: 2.421972E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.495 | TFLOPs: 23.52 | +63: ------------------------------------------------------------------------------------------ +63: valid loss at iteration 9000 | lm loss value: 2.303467E+00 | lm loss PPL: 1.000883E+01 | +63: ------------------------------------------------------------------------------------------ +63: iteration 9010/ 73814 | consumed samples: 4613120 | consumed tokens: 9447669760 | elapsed time per iteration (s): 2.29 | learning rate: 1.944E-04 | global batch size: 512 | lm loss: 2.424649E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.008 | TFLOPs: 23.06 | +63: iteration 9020/ 73814 | consumed samples: 4618240 | consumed tokens: 9458155520 | elapsed time per iteration (s): 2.23 | learning rate: 1.944E-04 | global batch size: 512 | lm loss: 2.394793E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.760 | TFLOPs: 23.65 | +63: iteration 9030/ 73814 | consumed samples: 4623360 | consumed tokens: 9468641280 | elapsed time per iteration (s): 2.37 | learning rate: 1.943E-04 | global batch size: 512 | lm loss: 2.416308E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.443 | TFLOPs: 22.28 | +63: iteration 9040/ 73814 | consumed samples: 4628480 | consumed tokens: 9479127040 | elapsed time per iteration (s): 2.23 | learning rate: 1.943E-04 | global batch size: 512 | lm loss: 2.399491E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.725 | TFLOPs: 23.65 | +63: iteration 9050/ 73814 | consumed samples: 4633600 | consumed tokens: 9489612800 | elapsed time per iteration (s): 2.23 | learning rate: 1.943E-04 | global batch size: 512 | lm loss: 2.399624E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.629 | TFLOPs: 23.64 | +63: iteration 9060/ 73814 | consumed samples: 4638720 | consumed tokens: 9500098560 | elapsed time per iteration (s): 2.24 | learning rate: 1.943E-04 | global batch size: 512 | lm loss: 2.405876E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.624 | TFLOPs: 23.54 | +63: iteration 9070/ 73814 | consumed samples: 4643840 | consumed tokens: 9510584320 | elapsed time per iteration (s): 2.25 | learning rate: 1.943E-04 | global batch size: 512 | lm loss: 2.403031E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.236 | TFLOPs: 23.39 | +63: iteration 9080/ 73814 | consumed samples: 4648960 | consumed tokens: 9521070080 | elapsed time per iteration (s): 2.25 | learning rate: 1.943E-04 | global batch size: 512 | lm loss: 2.398062E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.921 | TFLOPs: 23.46 | +63: iteration 9090/ 73814 | consumed samples: 4654080 | consumed tokens: 9531555840 | elapsed time per iteration (s): 2.27 | learning rate: 1.943E-04 | global batch size: 512 | lm loss: 2.401464E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.899 | TFLOPs: 23.26 | +63: iteration 9100/ 73814 | consumed samples: 4659200 | consumed tokens: 9542041600 | elapsed time per iteration (s): 2.24 | learning rate: 1.942E-04 | global batch size: 512 | lm loss: 2.400252E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.123 | TFLOPs: 23.48 | +63: iteration 9110/ 73814 | consumed samples: 4664320 | consumed tokens: 9552527360 | elapsed time per iteration (s): 2.23 | learning rate: 1.942E-04 | global batch size: 512 | lm loss: 2.423782E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.789 | TFLOPs: 23.66 | +63: iteration 9120/ 73814 | consumed samples: 4669440 | consumed tokens: 9563013120 | elapsed time per iteration (s): 2.23 | learning rate: 1.942E-04 | global batch size: 512 | lm loss: 2.402776E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.200 | TFLOPs: 23.60 | +63: iteration 9130/ 73814 | consumed samples: 4674560 | consumed tokens: 9573498880 | elapsed time per iteration (s): 2.23 | learning rate: 1.942E-04 | global batch size: 512 | lm loss: 2.407018E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.268 | TFLOPs: 23.60 | +63: iteration 9140/ 73814 | consumed samples: 4679680 | consumed tokens: 9583984640 | elapsed time per iteration (s): 2.23 | learning rate: 1.942E-04 | global batch size: 512 | lm loss: 2.401669E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.559 | TFLOPs: 23.63 | +63: iteration 9150/ 73814 | consumed samples: 4684800 | consumed tokens: 9594470400 | elapsed time per iteration (s): 2.23 | learning rate: 1.942E-04 | global batch size: 512 | lm loss: 2.400464E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.411 | TFLOPs: 23.62 | +63: iteration 9160/ 73814 | consumed samples: 4689920 | consumed tokens: 9604956160 | elapsed time per iteration (s): 2.24 | learning rate: 1.942E-04 | global batch size: 512 | lm loss: 2.379365E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.261 | TFLOPs: 23.50 | +63: iteration 9170/ 73814 | consumed samples: 4695040 | consumed tokens: 9615441920 | elapsed time per iteration (s): 2.26 | learning rate: 1.942E-04 | global batch size: 512 | lm loss: 2.388511E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.038 | TFLOPs: 23.37 | +63: iteration 9180/ 73814 | consumed samples: 4700160 | consumed tokens: 9625927680 | elapsed time per iteration (s): 2.23 | learning rate: 1.941E-04 | global batch size: 512 | lm loss: 2.406482E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.388 | TFLOPs: 23.61 | +63: iteration 9190/ 73814 | consumed samples: 4705280 | consumed tokens: 9636413440 | elapsed time per iteration (s): 2.24 | learning rate: 1.941E-04 | global batch size: 512 | lm loss: 2.396349E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.517 | TFLOPs: 23.52 | +63: iteration 9200/ 73814 | consumed samples: 4710400 | consumed tokens: 9646899200 | elapsed time per iteration (s): 2.24 | learning rate: 1.941E-04 | global batch size: 512 | lm loss: 2.373632E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.638 | TFLOPs: 23.54 | +63: iteration 9210/ 73814 | consumed samples: 4715520 | consumed tokens: 9657384960 | elapsed time per iteration (s): 2.22 | learning rate: 1.941E-04 | global batch size: 512 | lm loss: 2.399238E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.156 | TFLOPs: 23.69 | +63: iteration 9220/ 73814 | consumed samples: 4720640 | consumed tokens: 9667870720 | elapsed time per iteration (s): 2.23 | learning rate: 1.941E-04 | global batch size: 512 | lm loss: 2.395738E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.826 | TFLOPs: 23.66 | +63: iteration 9230/ 73814 | consumed samples: 4725760 | consumed tokens: 9678356480 | elapsed time per iteration (s): 2.23 | learning rate: 1.941E-04 | global batch size: 512 | lm loss: 2.400503E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.422 | TFLOPs: 23.62 | +63: iteration 9240/ 73814 | consumed samples: 4730880 | consumed tokens: 9688842240 | elapsed time per iteration (s): 2.23 | learning rate: 1.941E-04 | global batch size: 512 | lm loss: 2.379662E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.264 | TFLOPs: 23.60 | +63: iteration 9250/ 73814 | consumed samples: 4736000 | consumed tokens: 9699328000 | elapsed time per iteration (s): 2.24 | learning rate: 1.940E-04 | global batch size: 512 | lm loss: 2.402536E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.635 | TFLOPs: 23.54 | +63: iteration 9260/ 73814 | consumed samples: 4741120 | consumed tokens: 9709813760 | elapsed time per iteration (s): 2.23 | learning rate: 1.940E-04 | global batch size: 512 | lm loss: 2.384871E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.077 | TFLOPs: 23.69 | +63: iteration 9270/ 73814 | consumed samples: 4746240 | consumed tokens: 9720299520 | elapsed time per iteration (s): 2.25 | learning rate: 1.940E-04 | global batch size: 512 | lm loss: 2.407445E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.674 | TFLOPs: 23.44 | +63: iteration 9280/ 73814 | consumed samples: 4751360 | consumed tokens: 9730785280 | elapsed time per iteration (s): 2.23 | learning rate: 1.940E-04 | global batch size: 512 | lm loss: 2.378042E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.406 | TFLOPs: 23.62 | +63: iteration 9290/ 73814 | consumed samples: 4756480 | consumed tokens: 9741271040 | elapsed time per iteration (s): 2.24 | learning rate: 1.940E-04 | global batch size: 512 | lm loss: 2.384691E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.691 | TFLOPs: 23.54 | +63: iteration 9300/ 73814 | consumed samples: 4761600 | consumed tokens: 9751756800 | elapsed time per iteration (s): 2.25 | learning rate: 1.940E-04 | global batch size: 512 | lm loss: 2.374803E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.729 | TFLOPs: 23.44 | +63: iteration 9310/ 73814 | consumed samples: 4766720 | consumed tokens: 9762242560 | elapsed time per iteration (s): 2.24 | learning rate: 1.940E-04 | global batch size: 512 | lm loss: 2.397133E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.652 | TFLOPs: 23.54 | +63: iteration 9320/ 73814 | consumed samples: 4771840 | consumed tokens: 9772728320 | elapsed time per iteration (s): 2.31 | learning rate: 1.939E-04 | global batch size: 512 | lm loss: 2.428006E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.427 | TFLOPs: 22.79 | +63: iteration 9330/ 73814 | consumed samples: 4776960 | consumed tokens: 9783214080 | elapsed time per iteration (s): 2.27 | learning rate: 1.939E-04 | global batch size: 512 | lm loss: 2.391077E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.944 | TFLOPs: 23.26 | +63: iteration 9340/ 73814 | consumed samples: 4782080 | consumed tokens: 9793699840 | elapsed time per iteration (s): 2.24 | learning rate: 1.939E-04 | global batch size: 512 | lm loss: 2.371786E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.033 | TFLOPs: 23.58 | +63: iteration 9350/ 73814 | consumed samples: 4787200 | consumed tokens: 9804185600 | elapsed time per iteration (s): 2.23 | learning rate: 1.939E-04 | global batch size: 512 | lm loss: 2.375579E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.421 | TFLOPs: 23.62 | +63: iteration 9360/ 73814 | consumed samples: 4792320 | consumed tokens: 9814671360 | elapsed time per iteration (s): 2.23 | learning rate: 1.939E-04 | global batch size: 512 | lm loss: 2.365385E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.784 | TFLOPs: 23.66 | +63: iteration 9370/ 73814 | consumed samples: 4797440 | consumed tokens: 9825157120 | elapsed time per iteration (s): 2.23 | learning rate: 1.939E-04 | global batch size: 512 | lm loss: 2.377060E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.932 | TFLOPs: 23.67 | +63: iteration 9380/ 73814 | consumed samples: 4802560 | consumed tokens: 9835642880 | elapsed time per iteration (s): 2.23 | learning rate: 1.939E-04 | global batch size: 512 | lm loss: 2.381985E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.801 | TFLOPs: 23.66 | +63: iteration 9390/ 73814 | consumed samples: 4807680 | consumed tokens: 9846128640 | elapsed time per iteration (s): 2.23 | learning rate: 1.938E-04 | global batch size: 512 | lm loss: 2.379611E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.634 | TFLOPs: 23.64 | +63: iteration 9400/ 73814 | consumed samples: 4812800 | consumed tokens: 9856614400 | elapsed time per iteration (s): 2.23 | learning rate: 1.938E-04 | global batch size: 512 | lm loss: 2.385317E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.289 | TFLOPs: 23.60 | +63: iteration 9410/ 73814 | consumed samples: 4817920 | consumed tokens: 9867100160 | elapsed time per iteration (s): 2.25 | learning rate: 1.938E-04 | global batch size: 512 | lm loss: 2.393151E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.845 | TFLOPs: 23.46 | +63: iteration 9420/ 73814 | consumed samples: 4823040 | consumed tokens: 9877585920 | elapsed time per iteration (s): 2.23 | learning rate: 1.938E-04 | global batch size: 512 | lm loss: 2.366261E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.034 | TFLOPs: 23.68 | +63: iteration 9430/ 73814 | consumed samples: 4828160 | consumed tokens: 9888071680 | elapsed time per iteration (s): 2.23 | learning rate: 1.938E-04 | global batch size: 512 | lm loss: 2.369823E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.777 | TFLOPs: 23.65 | +63: iteration 9440/ 73814 | consumed samples: 4833280 | consumed tokens: 9898557440 | elapsed time per iteration (s): 2.27 | learning rate: 1.938E-04 | global batch size: 512 | lm loss: 2.379181E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.448 | TFLOPs: 23.21 | +63: iteration 9450/ 73814 | consumed samples: 4838400 | consumed tokens: 9909043200 | elapsed time per iteration (s): 2.25 | learning rate: 1.938E-04 | global batch size: 512 | lm loss: 2.380524E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.044 | TFLOPs: 23.48 | +63: iteration 9460/ 73814 | consumed samples: 4843520 | consumed tokens: 9919528960 | elapsed time per iteration (s): 2.23 | learning rate: 1.937E-04 | global batch size: 512 | lm loss: 2.371277E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.823 | TFLOPs: 23.66 | +63: iteration 9470/ 73814 | consumed samples: 4848640 | consumed tokens: 9930014720 | elapsed time per iteration (s): 2.23 | learning rate: 1.937E-04 | global batch size: 512 | lm loss: 2.407314E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.953 | TFLOPs: 23.67 | +63: iteration 9480/ 73814 | consumed samples: 4853760 | consumed tokens: 9940500480 | elapsed time per iteration (s): 2.23 | learning rate: 1.937E-04 | global batch size: 512 | lm loss: 2.383792E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.100 | TFLOPs: 23.58 | +63: iteration 9490/ 73814 | consumed samples: 4858880 | consumed tokens: 9950986240 | elapsed time per iteration (s): 2.26 | learning rate: 1.937E-04 | global batch size: 512 | lm loss: 2.417240E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.295 | TFLOPs: 23.30 | +63: iteration 9500/ 73814 | consumed samples: 4864000 | consumed tokens: 9961472000 | elapsed time per iteration (s): 2.23 | learning rate: 1.937E-04 | global batch size: 512 | lm loss: 2.387124E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.897 | TFLOPs: 23.67 | +63: iteration 9510/ 73814 | consumed samples: 4869120 | consumed tokens: 9971957760 | elapsed time per iteration (s): 2.26 | learning rate: 1.937E-04 | global batch size: 512 | lm loss: 2.370097E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.898 | TFLOPs: 23.36 | +63: iteration 9520/ 73814 | consumed samples: 4874240 | consumed tokens: 9982443520 | elapsed time per iteration (s): 2.23 | learning rate: 1.937E-04 | global batch size: 512 | lm loss: 2.392266E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.507 | TFLOPs: 23.63 | +63: iteration 9530/ 73814 | consumed samples: 4879360 | consumed tokens: 9992929280 | elapsed time per iteration (s): 2.25 | learning rate: 1.936E-04 | global batch size: 512 | lm loss: 2.372785E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.057 | TFLOPs: 23.48 | +63: iteration 9540/ 73814 | consumed samples: 4884480 | consumed tokens: 10003415040 | elapsed time per iteration (s): 2.23 | learning rate: 1.936E-04 | global batch size: 512 | lm loss: 2.387394E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.637 | TFLOPs: 23.64 | +63: iteration 9550/ 73814 | consumed samples: 4889600 | consumed tokens: 10013900800 | elapsed time per iteration (s): 2.24 | learning rate: 1.936E-04 | global batch size: 512 | lm loss: 2.378845E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.352 | TFLOPs: 23.51 | +63: iteration 9560/ 73814 | consumed samples: 4894720 | consumed tokens: 10024386560 | elapsed time per iteration (s): 2.23 | learning rate: 1.936E-04 | global batch size: 512 | lm loss: 2.386390E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.949 | TFLOPs: 23.67 | +63: iteration 9570/ 73814 | consumed samples: 4899840 | consumed tokens: 10034872320 | elapsed time per iteration (s): 2.27 | learning rate: 1.936E-04 | global batch size: 512 | lm loss: 2.388671E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.059 | TFLOPs: 23.17 | +63: iteration 9580/ 73814 | consumed samples: 4904960 | consumed tokens: 10045358080 | elapsed time per iteration (s): 2.26 | learning rate: 1.936E-04 | global batch size: 512 | lm loss: 2.358139E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.900 | TFLOPs: 23.36 | +63: iteration 9590/ 73814 | consumed samples: 4910080 | consumed tokens: 10055843840 | elapsed time per iteration (s): 2.25 | learning rate: 1.936E-04 | global batch size: 512 | lm loss: 2.375584E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.063 | TFLOPs: 23.38 | +63: iteration 9600/ 73814 | consumed samples: 4915200 | consumed tokens: 10066329600 | elapsed time per iteration (s): 2.30 | learning rate: 1.935E-04 | global batch size: 512 | lm loss: 2.369136E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.415 | TFLOPs: 22.90 | +63: iteration 9610/ 73814 | consumed samples: 4920320 | consumed tokens: 10076815360 | elapsed time per iteration (s): 2.22 | learning rate: 1.935E-04 | global batch size: 512 | lm loss: 2.378812E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.141 | TFLOPs: 23.69 | +63: iteration 9620/ 73814 | consumed samples: 4925440 | consumed tokens: 10087301120 | elapsed time per iteration (s): 2.25 | learning rate: 1.935E-04 | global batch size: 512 | lm loss: 2.364819E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.648 | TFLOPs: 23.44 | +63: iteration 9630/ 73814 | consumed samples: 4930560 | consumed tokens: 10097786880 | elapsed time per iteration (s): 2.37 | learning rate: 1.935E-04 | global batch size: 512 | lm loss: 2.365882E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.453 | TFLOPs: 22.28 | +63: iteration 9640/ 73814 | consumed samples: 4935680 | consumed tokens: 10108272640 | elapsed time per iteration (s): 2.23 | learning rate: 1.935E-04 | global batch size: 512 | lm loss: 2.381725E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.274 | TFLOPs: 23.60 | +63: iteration 9650/ 73814 | consumed samples: 4940800 | consumed tokens: 10118758400 | elapsed time per iteration (s): 2.23 | learning rate: 1.935E-04 | global batch size: 512 | lm loss: 2.373413E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.883 | TFLOPs: 23.67 | +63: iteration 9660/ 73814 | consumed samples: 4945920 | consumed tokens: 10129244160 | elapsed time per iteration (s): 2.23 | learning rate: 1.935E-04 | global batch size: 512 | lm loss: 2.363930E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.111 | TFLOPs: 23.69 | +63: iteration 9670/ 73814 | consumed samples: 4951040 | consumed tokens: 10139729920 | elapsed time per iteration (s): 2.23 | learning rate: 1.934E-04 | global batch size: 512 | lm loss: 2.359974E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.825 | TFLOPs: 23.66 | +63: iteration 9680/ 73814 | consumed samples: 4956160 | consumed tokens: 10150215680 | elapsed time per iteration (s): 2.25 | learning rate: 1.934E-04 | global batch size: 512 | lm loss: 2.377798E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.042 | TFLOPs: 23.48 | +63: iteration 9690/ 73814 | consumed samples: 4961280 | consumed tokens: 10160701440 | elapsed time per iteration (s): 2.22 | learning rate: 1.934E-04 | global batch size: 512 | lm loss: 2.370824E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.255 | TFLOPs: 23.70 | +63: iteration 9700/ 73814 | consumed samples: 4966400 | consumed tokens: 10171187200 | elapsed time per iteration (s): 2.23 | learning rate: 1.934E-04 | global batch size: 512 | lm loss: 2.368421E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.607 | TFLOPs: 23.64 | +63: iteration 9710/ 73814 | consumed samples: 4971520 | consumed tokens: 10181672960 | elapsed time per iteration (s): 2.26 | learning rate: 1.934E-04 | global batch size: 512 | lm loss: 2.381720E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.239 | TFLOPs: 23.29 | +63: iteration 9720/ 73814 | consumed samples: 4976640 | consumed tokens: 10192158720 | elapsed time per iteration (s): 2.23 | learning rate: 1.934E-04 | global batch size: 512 | lm loss: 2.357260E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.988 | TFLOPs: 23.68 | +63: iteration 9730/ 73814 | consumed samples: 4981760 | consumed tokens: 10202644480 | elapsed time per iteration (s): 2.24 | learning rate: 1.934E-04 | global batch size: 512 | lm loss: 2.357854E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.098 | TFLOPs: 23.48 | +63: iteration 9740/ 73814 | consumed samples: 4986880 | consumed tokens: 10213130240 | elapsed time per iteration (s): 2.23 | learning rate: 1.933E-04 | global batch size: 512 | lm loss: 2.368549E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.339 | TFLOPs: 23.61 | +63: iteration 9750/ 73814 | consumed samples: 4992000 | consumed tokens: 10223616000 | elapsed time per iteration (s): 2.23 | learning rate: 1.933E-04 | global batch size: 512 | lm loss: 2.343844E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.154 | TFLOPs: 23.59 | +63: iteration 9760/ 73814 | consumed samples: 4997120 | consumed tokens: 10234101760 | elapsed time per iteration (s): 2.24 | learning rate: 1.933E-04 | global batch size: 512 | lm loss: 2.352193E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.180 | TFLOPs: 23.49 | +63: iteration 9770/ 73814 | consumed samples: 5002240 | consumed tokens: 10244587520 | elapsed time per iteration (s): 2.25 | learning rate: 1.933E-04 | global batch size: 512 | lm loss: 2.360178E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.973 | TFLOPs: 23.47 | +63: iteration 9780/ 73814 | consumed samples: 5007360 | consumed tokens: 10255073280 | elapsed time per iteration (s): 2.28 | learning rate: 1.933E-04 | global batch size: 512 | lm loss: 2.374884E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.608 | TFLOPs: 23.12 | +63: iteration 9790/ 73814 | consumed samples: 5012480 | consumed tokens: 10265559040 | elapsed time per iteration (s): 2.25 | learning rate: 1.933E-04 | global batch size: 512 | lm loss: 2.354258E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.647 | TFLOPs: 23.44 | +63: iteration 9800/ 73814 | consumed samples: 5017600 | consumed tokens: 10276044800 | elapsed time per iteration (s): 2.26 | learning rate: 1.933E-04 | global batch size: 512 | lm loss: 2.359814E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.744 | TFLOPs: 23.34 | +63: iteration 9810/ 73814 | consumed samples: 5022720 | consumed tokens: 10286530560 | elapsed time per iteration (s): 2.24 | learning rate: 1.932E-04 | global batch size: 512 | lm loss: 2.370597E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.712 | TFLOPs: 23.54 | +63: iteration 9820/ 73814 | consumed samples: 5027840 | consumed tokens: 10297016320 | elapsed time per iteration (s): 2.23 | learning rate: 1.932E-04 | global batch size: 512 | lm loss: 2.389247E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.906 | TFLOPs: 23.67 | +63: iteration 9830/ 73814 | consumed samples: 5032960 | consumed tokens: 10307502080 | elapsed time per iteration (s): 2.25 | learning rate: 1.932E-04 | global batch size: 512 | lm loss: 2.365284E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.932 | TFLOPs: 23.46 | +63: iteration 9840/ 73814 | consumed samples: 5038080 | consumed tokens: 10317987840 | elapsed time per iteration (s): 2.23 | learning rate: 1.932E-04 | global batch size: 512 | lm loss: 2.377288E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.405 | TFLOPs: 23.62 | +63: iteration 9850/ 73814 | consumed samples: 5043200 | consumed tokens: 10328473600 | elapsed time per iteration (s): 4.18 | learning rate: 1.932E-04 | global batch size: 512 | lm loss: 2.359498E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 122.625 | TFLOPs: 12.62 | +63: iteration 9860/ 73814 | consumed samples: 5048320 | consumed tokens: 10338959360 | elapsed time per iteration (s): 2.27 | learning rate: 1.932E-04 | global batch size: 512 | lm loss: 2.357787E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.396 | TFLOPs: 23.20 | +63: iteration 9870/ 73814 | consumed samples: 5053440 | consumed tokens: 10349445120 | elapsed time per iteration (s): 2.26 | learning rate: 1.932E-04 | global batch size: 512 | lm loss: 2.374534E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.742 | TFLOPs: 23.34 | +63: iteration 9880/ 73814 | consumed samples: 5058560 | consumed tokens: 10359930880 | elapsed time per iteration (s): 2.23 | learning rate: 1.931E-04 | global batch size: 512 | lm loss: 2.367044E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.500 | TFLOPs: 23.63 | +63: iteration 9890/ 73814 | consumed samples: 5063680 | consumed tokens: 10370416640 | elapsed time per iteration (s): 2.28 | learning rate: 1.931E-04 | global batch size: 512 | lm loss: 2.372612E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.354 | TFLOPs: 23.10 | +63: iteration 9900/ 73814 | consumed samples: 5068800 | consumed tokens: 10380902400 | elapsed time per iteration (s): 2.29 | learning rate: 1.931E-04 | global batch size: 512 | lm loss: 2.385703E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.492 | TFLOPs: 23.01 | +63: iteration 9910/ 73814 | consumed samples: 5073920 | consumed tokens: 10391388160 | elapsed time per iteration (s): 2.25 | learning rate: 1.931E-04 | global batch size: 512 | lm loss: 2.345786E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.051 | TFLOPs: 23.37 | +63: iteration 9920/ 73814 | consumed samples: 5079040 | consumed tokens: 10401873920 | elapsed time per iteration (s): 2.43 | learning rate: 1.931E-04 | global batch size: 512 | lm loss: 2.368850E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.061 | TFLOPs: 21.73 | +63: iteration 9930/ 73814 | consumed samples: 5084160 | consumed tokens: 10412359680 | elapsed time per iteration (s): 2.25 | learning rate: 1.931E-04 | global batch size: 512 | lm loss: 2.364050E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.888 | TFLOPs: 23.46 | +63: iteration 9940/ 73814 | consumed samples: 5089280 | consumed tokens: 10422845440 | elapsed time per iteration (s): 2.38 | learning rate: 1.930E-04 | global batch size: 512 | lm loss: 2.364725E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.528 | TFLOPs: 22.19 | +63: iteration 9950/ 73814 | consumed samples: 5094400 | consumed tokens: 10433331200 | elapsed time per iteration (s): 2.38 | learning rate: 1.930E-04 | global batch size: 512 | lm loss: 2.333905E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.132 | TFLOPs: 22.15 | +63: iteration 9960/ 73814 | consumed samples: 5099520 | consumed tokens: 10443816960 | elapsed time per iteration (s): 2.67 | learning rate: 1.930E-04 | global batch size: 512 | lm loss: 2.358939E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 191.610 | TFLOPs: 19.73 | +63: iteration 9970/ 73814 | consumed samples: 5104640 | consumed tokens: 10454302720 | elapsed time per iteration (s): 2.36 | learning rate: 1.930E-04 | global batch size: 512 | lm loss: 2.349417E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.927 | TFLOPs: 22.33 | +63: iteration 9980/ 73814 | consumed samples: 5109760 | consumed tokens: 10464788480 | elapsed time per iteration (s): 2.23 | learning rate: 1.930E-04 | global batch size: 512 | lm loss: 2.360347E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.792 | TFLOPs: 23.66 | +63: iteration 9990/ 73814 | consumed samples: 5114880 | consumed tokens: 10475274240 | elapsed time per iteration (s): 2.33 | learning rate: 1.930E-04 | global batch size: 512 | lm loss: 2.340823E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.987 | TFLOPs: 22.65 | + 0: [2022-12-01 18:11:40,911] [INFO] [logging.py:68:log_dist] [Rank 0] step=10000, skipped=0, lr=[0.00019295938877477648, 0.00019295938877477648, 0.00019295938877477648], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] + 0: steps: 10000 loss: 2.3808 iter time (s): 2.388 samples/sec: 214.383 +63: iteration 10000/ 73814 | consumed samples: 5120000 | consumed tokens: 10485760000 | elapsed time per iteration (s): 2.47 | learning rate: 1.930E-04 | global batch size: 512 | lm loss: 2.349165E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 207.624 | TFLOPs: 21.37 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 10000 | lm loss value: 2.343730E+00 | lm loss PPL: 1.042004E+01 | +63: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 10000 to checkpoints_3b977boscar + 0: [2022-12-01 18:11:41,876] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step10000 is begin to save! +32: [2022-12-01 18:11:42,870] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_21-model_00-model_states.pt... + 0: [2022-12-01 18:11:42,873] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_01-model_00-model_states.pt... +32: [2022-12-01 18:11:43,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_21-model_00-model_states.pt. +32: [2022-12-01 18:11:43,266] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_22-model_00-model_states.pt... + 0: [2022-12-01 18:11:43,359] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_01-model_00-model_states.pt. + 0: [2022-12-01 18:11:43,359] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_03-model_00-model_states.pt... +32: [2022-12-01 18:11:43,492] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_22-model_00-model_states.pt. +32: [2022-12-01 18:11:43,492] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_23-model_00-model_states.pt... + 0: [2022-12-01 18:11:43,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_03-model_00-model_states.pt. + 0: [2022-12-01 18:11:43,596] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_04-model_00-model_states.pt... +32: [2022-12-01 18:11:43,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_23-model_00-model_states.pt. +32: [2022-12-01 18:11:43,722] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_24-model_00-model_states.pt... + 0: [2022-12-01 18:11:43,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_04-model_00-model_states.pt. + 0: [2022-12-01 18:11:43,825] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_05-model_00-model_states.pt... +32: [2022-12-01 18:11:43,955] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_24-model_00-model_states.pt. +32: [2022-12-01 18:11:43,956] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_25-model_00-model_states.pt... + 0: [2022-12-01 18:11:44,050] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_05-model_00-model_states.pt. + 0: [2022-12-01 18:11:44,051] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_06-model_00-model_states.pt... +32: [2022-12-01 18:11:44,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_25-model_00-model_states.pt. +32: [2022-12-01 18:11:44,181] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_26-model_00-model_states.pt... + 0: [2022-12-01 18:11:44,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_06-model_00-model_states.pt. + 0: [2022-12-01 18:11:44,274] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_07-model_00-model_states.pt... +32: [2022-12-01 18:11:44,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_26-model_00-model_states.pt. +32: [2022-12-01 18:11:44,411] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_27-model_00-model_states.pt... + 0: [2022-12-01 18:11:44,498] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_07-model_00-model_states.pt. + 0: [2022-12-01 18:11:44,499] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_08-model_00-model_states.pt... +32: [2022-12-01 18:11:44,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_27-model_00-model_states.pt. +32: [2022-12-01 18:11:44,638] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_28-model_00-model_states.pt... + 0: [2022-12-01 18:11:44,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_08-model_00-model_states.pt. + 0: [2022-12-01 18:11:44,722] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_09-model_00-model_states.pt... +32: [2022-12-01 18:11:44,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_28-model_00-model_states.pt. +32: [2022-12-01 18:11:44,863] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_29-model_00-model_states.pt... + 0: [2022-12-01 18:11:44,938] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_09-model_00-model_states.pt. + 0: [2022-12-01 18:11:44,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_10-model_00-model_states.pt... +32: [2022-12-01 18:11:45,088] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_29-model_00-model_states.pt. +32: [2022-12-01 18:11:45,089] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_30-model_00-model_states.pt... + 0: [2022-12-01 18:11:45,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_10-model_00-model_states.pt. + 0: [2022-12-01 18:11:45,160] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_11-model_00-model_states.pt... +32: [2022-12-01 18:11:45,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_30-model_00-model_states.pt. +32: [2022-12-01 18:11:45,317] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_31-model_00-model_states.pt... + 0: [2022-12-01 18:11:45,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_11-model_00-model_states.pt. + 0: [2022-12-01 18:11:45,378] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_12-model_00-model_states.pt... +32: [2022-12-01 18:11:45,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_31-model_00-model_states.pt. +32: [2022-12-01 18:11:45,548] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_32-model_00-model_states.pt... + 0: [2022-12-01 18:11:45,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_12-model_00-model_states.pt. + 0: [2022-12-01 18:11:45,604] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_13-model_00-model_states.pt... +32: [2022-12-01 18:11:45,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_32-model_00-model_states.pt. +32: [2022-12-01 18:11:45,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_33-model_00-model_states.pt... + 0: [2022-12-01 18:11:45,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_13-model_00-model_states.pt. + 0: [2022-12-01 18:11:45,822] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_14-model_00-model_states.pt... +32: [2022-12-01 18:11:46,001] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_33-model_00-model_states.pt. +32: [2022-12-01 18:11:46,001] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_34-model_00-model_states.pt... + 0: [2022-12-01 18:11:46,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_14-model_00-model_states.pt. + 0: [2022-12-01 18:11:46,041] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_15-model_00-model_states.pt... +32: [2022-12-01 18:11:46,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_34-model_00-model_states.pt. +32: [2022-12-01 18:11:46,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_35-model_00-model_states.pt... + 0: [2022-12-01 18:11:46,259] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_15-model_00-model_states.pt. + 0: [2022-12-01 18:11:46,259] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_16-model_00-model_states.pt... +32: [2022-12-01 18:11:46,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_35-model_00-model_states.pt. +32: [2022-12-01 18:11:46,456] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_36-model_00-model_states.pt... + 0: [2022-12-01 18:11:46,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_16-model_00-model_states.pt. + 0: [2022-12-01 18:11:46,476] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_17-model_00-model_states.pt... +32: [2022-12-01 18:11:46,685] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_36-model_00-model_states.pt. +32: [2022-12-01 18:11:46,685] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_37-model_00-model_states.pt... + 0: [2022-12-01 18:11:46,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_17-model_00-model_states.pt. + 0: [2022-12-01 18:11:46,695] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_18-model_00-model_states.pt... +32: [2022-12-01 18:11:46,910] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_37-model_00-model_states.pt. +32: [2022-12-01 18:11:46,911] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_38-model_00-model_states.pt... + 0: [2022-12-01 18:11:46,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_18-model_00-model_states.pt. + 0: [2022-12-01 18:11:46,919] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_19-model_00-model_states.pt... + 0: [2022-12-01 18:11:47,139] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_19-model_00-model_states.pt. + 0: [2022-12-01 18:11:47,139] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_20-model_00-model_states.pt... +32: [2022-12-01 18:11:47,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_38-model_00-model_states.pt. +32: [2022-12-01 18:11:47,146] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/layer_40-model_00-model_states.pt... +32: [2022-12-01 18:11:47,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_40-model_00-model_states.pt. +32: [2022-12-01 18:11:47,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/mp_rank_01_model_states.pt... +32: [2022-12-01 18:11:47,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/mp_rank_01_model_states.pt. + 0: [2022-12-01 18:11:47,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/layer_20-model_00-model_states.pt. + 0: [2022-12-01 18:11:47,363] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_3b977boscar/global_step10000/mp_rank_00_model_states.pt + 0: [2022-12-01 18:11:47,363] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/mp_rank_00_model_states.pt... + 0: [2022-12-01 18:11:47,370] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/mp_rank_00_model_states.pt. +32: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt... + 0: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 0: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 0: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +62: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt... +62: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt... +34: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt... +39: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt... +39: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt... +39: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt... +39: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt... +39: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt... +50: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt... +50: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt... +32: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt... +32: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt... +32: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt... +32: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt... +32: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt... +47: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt... +47: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt... + 0: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +54: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt... +54: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt... +54: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt... +54: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt... +54: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt... +56: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt... +56: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt... +56: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt... +56: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt... +56: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt... +52: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt... +52: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt... +52: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt... +52: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt... +52: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt... +53: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt... +53: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt... +53: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt... +53: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt... +33: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt... +33: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt... +33: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt... +33: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt... +33: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt... +59: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt... +59: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt... +59: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt... +59: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt... +59: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt... +10: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +62: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt... +62: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt... +22: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +58: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt... +58: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt... +38: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt... +38: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt... +38: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt... +38: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt... +38: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt... +44: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt... +44: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt... +44: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt... +44: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt... +44: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt... +48: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt... +48: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt... +48: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt... +48: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt... +48: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt... +43: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt... +43: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt... +43: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt... +43: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt... +36: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt... +36: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt... +36: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt... +35: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt... +35: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt... +35: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt... +35: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt... +39: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt... +39: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt... +39: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt... +50: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt... +50: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt... +50: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt... +50: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt... +32: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt... +51: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt... +51: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt... +51: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt... +51: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt... +60: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt... +60: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt... +60: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt... +60: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt... +60: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt... +46: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt... +46: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt... +46: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt... +46: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt... +46: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt... +41: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt... +41: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt... +41: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt... +41: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt... +41: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt... +55: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt... +55: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt... +55: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt... +55: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt... +47: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt... +47: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt... +27: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +27: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +16: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +45: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt... +45: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt... +45: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt... +45: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt... +45: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt... +23: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +37: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt... +37: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt... +37: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt... +37: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt... +40: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt... +40: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt... +40: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt... +40: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt... +40: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt... +42: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt... +42: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt... + 0: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 7: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +19: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +20: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +54: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt... +54: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt... +54: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt... +56: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt... +52: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt... +52: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt... +52: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt... +61: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt... +61: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt... +61: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt... +61: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt... +61: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt... +63: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt... +63: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt... +63: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt... +63: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt... +63: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt... +15: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +53: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt... + 1: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +11: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +33: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt... +33: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt... +59: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt... +59: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt... + 5: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +10: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +28: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +62: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt... +22: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +12: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +58: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt... +58: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt... +58: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt... +58: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt... +58: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt... +18: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +38: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt... +26: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +26: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +44: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt... +48: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt... +34: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt... +34: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt... +34: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt... +34: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt... +34: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt... +43: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt... + 9: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... +36: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt... +36: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt... +36: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt... +36: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt... +36: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt... +35: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt... +35: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt... +35: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt... +35: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt... + 2: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +25: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +50: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt... +32: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt... +51: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt... +51: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt... +51: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt... +51: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt... + 4: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 6: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +60: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt... +13: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +31: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +49: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt... +49: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt... +49: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt... +49: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt... +49: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt... +46: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt... +46: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt... +46: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt... +41: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt... +41: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt... +47: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt... +47: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt... +47: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt... + 3: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +27: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... + 8: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... +16: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +14: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +17: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +29: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +45: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt... +45: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt... +30: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +24: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +23: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +37: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt... +37: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt... +37: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt... +40: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt... +40: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt... +42: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt... +57: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt... +21: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... + 0: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 7: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +19: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +20: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +56: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt... +56: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt... +61: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt... +63: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt... +63: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt... +63: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt... +15: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +53: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt... + 1: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +11: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +33: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt... +59: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt... + 5: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +10: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +28: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +62: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt... +22: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +12: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +58: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt... +18: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +38: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt... +26: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +44: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt... +48: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt... +48: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt... +34: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt... +43: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt... +43: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt... + 9: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 2: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +25: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +50: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt... + 4: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 6: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +60: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt... +13: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +31: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +49: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt... +49: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt... +49: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt... +41: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt... +55: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt... +55: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt... +55: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt... +47: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt... + 3: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +27: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... + 8: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... +16: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +14: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +17: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +29: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +45: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt... +30: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +24: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +23: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +37: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt... +40: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt... +42: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt... +57: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt... +57: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt... +21: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... + 0: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 7: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +20: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +61: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt... +61: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt... +15: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +53: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt... + 1: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +11: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 5: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +10: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +28: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +62: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt... +62: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt... +22: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +12: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +18: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +38: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt... +26: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +44: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt... +34: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt... +43: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt... + 9: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 2: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +25: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... + 4: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 6: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +60: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt... +13: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +31: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +55: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt... + 3: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 8: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +16: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +14: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +17: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +29: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +24: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +24: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +23: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +42: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt... +57: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt... +57: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt... +21: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... + 7: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +20: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +15: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +53: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt... +11: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... + 5: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +28: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +18: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... + 2: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +13: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... + 3: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 8: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... +16: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +14: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +29: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +23: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +42: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt... +57: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt... +57: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt... +21: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... + 7: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +20: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +15: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +28: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... + 2: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +16: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +42: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt... +57: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt... + 7: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +42: [2022-12-01 18:11:47,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt... +32: [2022-12-01 18:11:47,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt. +32: [2022-12-01 18:11:47,677] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt +32: [2022-12-01 18:11:47,677] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: [2022-12-01 18:11:47,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-12-01 18:11:47,690] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-12-01 18:11:47,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: [2022-12-01 18:11:47,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-12-01 18:11:47,690] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-12-01 18:11:47,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +32: [2022-12-01 18:11:47,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt. +32: [2022-12-01 18:11:47,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt. +32: [2022-12-01 18:11:47,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt. +32: [2022-12-01 18:11:47,691] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt +32: [2022-12-01 18:11:47,691] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt +32: [2022-12-01 18:11:47,691] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt +32: [2022-12-01 18:11:47,691] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +32: [2022-12-01 18:11:47,691] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +32: [2022-12-01 18:11:47,691] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: [2022-12-01 18:11:47,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-12-01 18:11:47,691] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-12-01 18:11:47,691] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: [2022-12-01 18:11:47,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-12-01 18:11:47,691] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-12-01 18:11:47,692] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +32: [2022-12-01 18:11:47,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt. +32: [2022-12-01 18:11:47,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt +32: [2022-12-01 18:11:47,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +32: [2022-12-01 18:11:47,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt. +32: [2022-12-01 18:11:47,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt. +32: [2022-12-01 18:11:47,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt. +32: [2022-12-01 18:11:47,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt +32: [2022-12-01 18:11:47,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt +32: [2022-12-01 18:11:47,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt +32: [2022-12-01 18:11:47,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +32: [2022-12-01 18:11:47,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +32: [2022-12-01 18:11:47,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: [2022-12-01 18:11:47,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-12-01 18:11:47,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-12-01 18:11:47,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: [2022-12-01 18:11:47,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. + 0: [2022-12-01 18:11:47,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-12-01 18:11:47,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-12-01 18:11:47,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: [2022-12-01 18:11:47,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-12-01 18:11:47,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-12-01 18:11:47,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +34: [2022-12-01 18:11:47,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt. +34: [2022-12-01 18:11:47,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt. +34: [2022-12-01 18:11:47,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt. +34: [2022-12-01 18:11:47,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt. +34: [2022-12-01 18:11:47,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt. +34: [2022-12-01 18:11:47,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt. +34: [2022-12-01 18:11:47,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt. +34: [2022-12-01 18:11:47,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt +34: [2022-12-01 18:11:47,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt +34: [2022-12-01 18:11:47,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt +34: [2022-12-01 18:11:47,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt +34: [2022-12-01 18:11:47,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt +34: [2022-12-01 18:11:47,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt +34: [2022-12-01 18:11:47,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt +34: [2022-12-01 18:11:47,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +34: [2022-12-01 18:11:47,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +34: [2022-12-01 18:11:47,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +34: [2022-12-01 18:11:47,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +34: [2022-12-01 18:11:47,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +34: [2022-12-01 18:11:47,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +34: [2022-12-01 18:11:47,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +34: [2022-12-01 18:11:47,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt. +34: [2022-12-01 18:11:47,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt +34: [2022-12-01 18:11:47,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-12-01 18:11:47,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-12-01 18:11:47,847] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-12-01 18:11:47,847] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-12-01 18:11:47,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-12-01 18:11:47,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-12-01 18:11:47,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-12-01 18:11:47,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-12-01 18:11:47,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-12-01 18:11:47,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-12-01 18:11:47,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-12-01 18:11:47,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-12-01 18:11:47,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +39: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt. +39: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt. +39: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt. +39: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt. +39: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt. +39: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt. +39: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt. +39: [2022-12-01 18:11:47,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt +39: [2022-12-01 18:11:47,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt +39: [2022-12-01 18:11:47,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt +39: [2022-12-01 18:11:47,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt +39: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt. +39: [2022-12-01 18:11:47,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt +39: [2022-12-01 18:11:47,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt +39: [2022-12-01 18:11:47,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt +39: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +39: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +39: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +39: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +39: [2022-12-01 18:11:47,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt +39: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +39: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +39: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +39: [2022-12-01 18:11:47,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-12-01 18:11:47,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-12-01 18:11:47,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-12-01 18:11:47,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +19: [2022-12-01 18:11:47,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-12-01 18:11:47,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-12-01 18:11:47,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-12-01 18:11:47,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-12-01 18:11:47,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +19: [2022-12-01 18:11:47,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +49: [2022-12-01 18:11:47,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt. +49: [2022-12-01 18:11:47,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt. +49: [2022-12-01 18:11:47,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt +49: [2022-12-01 18:11:47,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt +49: [2022-12-01 18:11:47,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +49: [2022-12-01 18:11:47,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +51: [2022-12-01 18:11:47,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt. +51: [2022-12-01 18:11:47,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt. +51: [2022-12-01 18:11:47,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt. +51: [2022-12-01 18:11:47,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt. +51: [2022-12-01 18:11:47,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt. +51: [2022-12-01 18:11:47,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt +51: [2022-12-01 18:11:47,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt +51: [2022-12-01 18:11:47,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt +51: [2022-12-01 18:11:47,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt +51: [2022-12-01 18:11:47,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt +51: [2022-12-01 18:11:47,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +51: [2022-12-01 18:11:47,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +51: [2022-12-01 18:11:47,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +51: [2022-12-01 18:11:47,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +51: [2022-12-01 18:11:47,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +51: [2022-12-01 18:11:47,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt. +51: [2022-12-01 18:11:47,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt +51: [2022-12-01 18:11:47,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +51: [2022-12-01 18:11:47,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt. +20: [2022-12-01 18:11:47,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +51: [2022-12-01 18:11:47,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt +51: [2022-12-01 18:11:47,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +51: [2022-12-01 18:11:47,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt. +20: [2022-12-01 18:11:47,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +51: [2022-12-01 18:11:47,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt +51: [2022-12-01 18:11:47,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-12-01 18:11:47,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-12-01 18:11:47,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-12-01 18:11:47,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-12-01 18:11:47,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-12-01 18:11:47,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-12-01 18:11:47,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-12-01 18:11:47,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +29: [2022-12-01 18:11:47,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-12-01 18:11:47,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-12-01 18:11:47,864] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-12-01 18:11:47,864] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-12-01 18:11:47,864] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-12-01 18:11:47,864] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-12-01 18:11:47,864] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +29: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +29: [2022-12-01 18:11:47,864] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +29: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +29: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +29: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +29: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-12-01 18:11:47,864] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-12-01 18:11:47,864] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +29: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +37: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt. +37: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt. +37: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt. +37: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt. +37: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt. +37: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt. +37: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt. +37: [2022-12-01 18:11:47,864] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt +37: [2022-12-01 18:11:47,864] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt +37: [2022-12-01 18:11:47,864] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt +37: [2022-12-01 18:11:47,864] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt +37: [2022-12-01 18:11:47,864] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt +37: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +37: [2022-12-01 18:11:47,864] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt +37: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +37: [2022-12-01 18:11:47,864] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt +37: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt. +37: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +37: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +37: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +37: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +37: [2022-12-01 18:11:47,864] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +37: [2022-12-01 18:11:47,865] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt +37: [2022-12-01 18:11:47,865] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +60: [2022-12-01 18:11:47,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt. +60: [2022-12-01 18:11:47,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt. +60: [2022-12-01 18:11:47,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt. +28: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +60: [2022-12-01 18:11:47,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt +28: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +60: [2022-12-01 18:11:47,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt +60: [2022-12-01 18:11:47,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt +28: [2022-12-01 18:11:47,867] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-12-01 18:11:47,867] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-12-01 18:11:47,867] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +60: [2022-12-01 18:11:47,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-12-01 18:11:47,867] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +60: [2022-12-01 18:11:47,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +60: [2022-12-01 18:11:47,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-12-01 18:11:47,867] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-12-01 18:11:47,867] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-12-01 18:11:47,867] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +60: [2022-12-01 18:11:47,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt. +60: [2022-12-01 18:11:47,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt. +28: [2022-12-01 18:11:47,867] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +60: [2022-12-01 18:11:47,867] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt +60: [2022-12-01 18:11:47,867] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt +28: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +60: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt. +28: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +60: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt. +28: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +60: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt. +60: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +60: [2022-12-01 18:11:47,867] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt +60: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +60: [2022-12-01 18:11:47,867] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt +60: [2022-12-01 18:11:47,867] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt +60: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +60: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +60: [2022-12-01 18:11:47,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +50: [2022-12-01 18:11:47,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt. +50: [2022-12-01 18:11:47,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt. +50: [2022-12-01 18:11:47,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt. +50: [2022-12-01 18:11:47,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt. +50: [2022-12-01 18:11:47,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt. +50: [2022-12-01 18:11:47,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt. +50: [2022-12-01 18:11:47,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt. +50: [2022-12-01 18:11:47,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt. +50: [2022-12-01 18:11:47,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt +50: [2022-12-01 18:11:47,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt +50: [2022-12-01 18:11:47,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt +50: [2022-12-01 18:11:47,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt +50: [2022-12-01 18:11:47,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt +50: [2022-12-01 18:11:47,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt +50: [2022-12-01 18:11:47,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +50: [2022-12-01 18:11:47,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +50: [2022-12-01 18:11:47,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +50: [2022-12-01 18:11:47,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt +50: [2022-12-01 18:11:47,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +50: [2022-12-01 18:11:47,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +50: [2022-12-01 18:11:47,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +50: [2022-12-01 18:11:47,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt +50: [2022-12-01 18:11:47,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +50: [2022-12-01 18:11:47,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +25: [2022-12-01 18:11:47,872] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-12-01 18:11:47,872] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-12-01 18:11:47,872] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +52: [2022-12-01 18:11:47,881] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt. +52: [2022-12-01 18:11:47,881] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt. +52: [2022-12-01 18:11:47,881] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt +52: [2022-12-01 18:11:47,881] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt +52: [2022-12-01 18:11:47,881] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +52: [2022-12-01 18:11:47,881] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +52: [2022-12-01 18:11:47,881] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt. +52: [2022-12-01 18:11:47,881] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt +52: [2022-12-01 18:11:47,881] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +52: [2022-12-01 18:11:47,881] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt. +52: [2022-12-01 18:11:47,881] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt. +52: [2022-12-01 18:11:47,881] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt +52: [2022-12-01 18:11:47,881] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt +52: [2022-12-01 18:11:47,881] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +52: [2022-12-01 18:11:47,881] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-12-01 18:11:47,883] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-12-01 18:11:47,883] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-12-01 18:11:47,883] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-12-01 18:11:47,883] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-12-01 18:11:47,883] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +25: [2022-12-01 18:11:47,884] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-12-01 18:11:47,884] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-12-01 18:11:47,884] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-12-01 18:11:47,884] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +25: [2022-12-01 18:11:47,884] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt + 2: [2022-12-01 18:11:47,883] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-12-01 18:11:47,883] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 2: [2022-12-01 18:11:47,883] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-12-01 18:11:47,883] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-12-01 18:11:47,883] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-12-01 18:11:47,883] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-12-01 18:11:47,883] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-12-01 18:11:47,883] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-12-01 18:11:47,883] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-12-01 18:11:47,883] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +25: [2022-12-01 18:11:47,884] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-12-01 18:11:47,883] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-12-01 18:11:47,883] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-12-01 18:11:47,883] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-12-01 18:11:47,883] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-12-01 18:11:47,883] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-12-01 18:11:47,883] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-12-01 18:11:47,883] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-12-01 18:11:47,883] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-12-01 18:11:47,883] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 7: [2022-12-01 18:11:47,884] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-12-01 18:11:47,884] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-12-01 18:11:47,884] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-12-01 18:11:47,884] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-12-01 18:11:47,884] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 1: [2022-12-01 18:11:47,886] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-12-01 18:11:47,886] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-12-01 18:11:47,886] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-12-01 18:11:47,886] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 7: [2022-12-01 18:11:47,884] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-12-01 18:11:47,884] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-12-01 18:11:47,884] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-12-01 18:11:47,885] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-12-01 18:11:47,885] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-12-01 18:11:47,885] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-12-01 18:11:47,885] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-12-01 18:11:47,885] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-12-01 18:11:47,885] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-12-01 18:11:47,885] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 7: [2022-12-01 18:11:47,885] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-12-01 18:11:47,885] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-12-01 18:11:47,885] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 7: [2022-12-01 18:11:47,885] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 7: [2022-12-01 18:11:47,885] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 7: [2022-12-01 18:11:47,885] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 7: [2022-12-01 18:11:47,885] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-12-01 18:11:47,886] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 7: [2022-12-01 18:11:47,885] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 7: [2022-12-01 18:11:47,885] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-12-01 18:11:47,886] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-12-01 18:11:47,886] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-12-01 18:11:47,886] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-12-01 18:11:47,886] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-12-01 18:11:47,886] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-12-01 18:11:47,886] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-12-01 18:11:47,886] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-12-01 18:11:47,886] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-12-01 18:11:47,886] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-12-01 18:11:47,886] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +54: [2022-12-01 18:11:47,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt. +54: [2022-12-01 18:11:47,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt. +54: [2022-12-01 18:11:47,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt. +54: [2022-12-01 18:11:47,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt. +54: [2022-12-01 18:11:47,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt. + 1: [2022-12-01 18:11:47,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-12-01 18:11:47,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-12-01 18:11:47,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-12-01 18:11:47,888] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-12-01 18:11:47,888] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-12-01 18:11:47,889] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-12-01 18:11:47,889] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-12-01 18:11:47,889] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-12-01 18:11:47,889] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +49: [2022-12-01 18:11:47,889] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt. +49: [2022-12-01 18:11:47,889] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt +49: [2022-12-01 18:11:47,889] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +54: [2022-12-01 18:11:47,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt. +54: [2022-12-01 18:11:47,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt. +54: [2022-12-01 18:11:47,888] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt +54: [2022-12-01 18:11:47,888] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt +54: [2022-12-01 18:11:47,888] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt +54: [2022-12-01 18:11:47,888] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt +54: [2022-12-01 18:11:47,888] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt +54: [2022-12-01 18:11:47,888] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt +54: [2022-12-01 18:11:47,888] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt +54: [2022-12-01 18:11:47,888] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +54: [2022-12-01 18:11:47,888] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +54: [2022-12-01 18:11:47,888] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +54: [2022-12-01 18:11:47,888] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +54: [2022-12-01 18:11:47,888] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +54: [2022-12-01 18:11:47,888] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +54: [2022-12-01 18:11:47,888] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-12-01 18:11:47,889] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-12-01 18:11:47,889] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-12-01 18:11:47,889] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-12-01 18:11:47,889] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-12-01 18:11:47,889] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +48: [2022-12-01 18:11:47,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt. +48: [2022-12-01 18:11:47,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt. +48: [2022-12-01 18:11:47,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt. +48: [2022-12-01 18:11:47,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt. +19: [2022-12-01 18:11:47,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +18: [2022-12-01 18:11:47,889] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-12-01 18:11:47,889] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +48: [2022-12-01 18:11:47,891] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt +18: [2022-12-01 18:11:47,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-12-01 18:11:47,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-12-01 18:11:47,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-12-01 18:11:47,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-12-01 18:11:47,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +48: [2022-12-01 18:11:47,891] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt +48: [2022-12-01 18:11:47,891] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt +48: [2022-12-01 18:11:47,891] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt +18: [2022-12-01 18:11:47,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-12-01 18:11:47,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-12-01 18:11:47,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-12-01 18:11:47,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-12-01 18:11:47,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-12-01 18:11:47,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-12-01 18:11:47,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +48: [2022-12-01 18:11:47,891] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-12-01 18:11:47,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-12-01 18:11:47,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-12-01 18:11:47,889] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-12-01 18:11:47,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-12-01 18:11:47,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +48: [2022-12-01 18:11:47,891] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +48: [2022-12-01 18:11:47,891] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +48: [2022-12-01 18:11:47,891] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-12-01 18:11:47,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-12-01 18:11:47,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-12-01 18:11:47,892] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +54: [2022-12-01 18:11:47,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt. + 6: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-12-01 18:11:47,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-12-01 18:11:47,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-12-01 18:11:47,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-12-01 18:11:47,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-12-01 18:11:47,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-12-01 18:11:47,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-12-01 18:11:47,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +19: [2022-12-01 18:11:47,891] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt + 6: [2022-12-01 18:11:47,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +19: [2022-12-01 18:11:47,891] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +54: [2022-12-01 18:11:47,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt +54: [2022-12-01 18:11:47,892] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +40: [2022-12-01 18:11:47,893] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt. +40: [2022-12-01 18:11:47,893] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt. +40: [2022-12-01 18:11:47,893] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt. +40: [2022-12-01 18:11:47,893] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt. +40: [2022-12-01 18:11:47,893] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt. +21: [2022-12-01 18:11:47,896] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +40: [2022-12-01 18:11:47,893] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt. +40: [2022-12-01 18:11:47,893] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt. +21: [2022-12-01 18:11:47,896] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +40: [2022-12-01 18:11:47,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt +40: [2022-12-01 18:11:47,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt +21: [2022-12-01 18:11:47,897] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +40: [2022-12-01 18:11:47,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt +40: [2022-12-01 18:11:47,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt +40: [2022-12-01 18:11:47,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt +40: [2022-12-01 18:11:47,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt +40: [2022-12-01 18:11:47,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt +40: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +40: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +40: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +40: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +40: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +40: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +40: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +40: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt. +40: [2022-12-01 18:11:47,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt +40: [2022-12-01 18:11:47,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-12-01 18:11:47,899] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-12-01 18:11:47,899] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +20: [2022-12-01 18:11:47,901] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-12-01 18:11:47,901] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-12-01 18:11:47,901] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +52: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt. +48: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt. +48: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt. +52: [2022-12-01 18:11:47,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt +52: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 5: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +26: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. + 5: [2022-12-01 18:11:47,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-12-01 18:11:47,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-12-01 18:11:47,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +26: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-12-01 18:11:47,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt + 5: [2022-12-01 18:11:47,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +26: [2022-12-01 18:11:47,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +48: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt. + 5: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 5: [2022-12-01 18:11:47,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-12-01 18:11:47,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-12-01 18:11:47,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 5: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-12-01 18:11:47,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +48: [2022-12-01 18:11:47,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt +48: [2022-12-01 18:11:47,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt + 5: [2022-12-01 18:11:47,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +26: [2022-12-01 18:11:47,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-12-01 18:11:47,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +48: [2022-12-01 18:11:47,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt +16: [2022-12-01 18:11:47,899] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-12-01 18:11:47,899] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-12-01 18:11:47,899] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-12-01 18:11:47,899] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-12-01 18:11:47,899] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. + 5: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-12-01 18:11:47,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +48: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +48: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-12-01 18:11:47,899] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-12-01 18:11:47,899] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt + 5: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 5: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-12-01 18:11:47,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +48: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-12-01 18:11:47,899] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-12-01 18:11:47,899] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt + 5: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 5: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-12-01 18:11:47,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-12-01 18:11:47,899] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-12-01 18:11:47,899] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-12-01 18:11:47,899] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-12-01 18:11:47,899] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-12-01 18:11:47,899] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-12-01 18:11:47,899] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +26: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-12-01 18:11:47,899] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-12-01 18:11:47,899] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-12-01 18:11:47,899] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-12-01 18:11:47,899] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-12-01 18:11:47,899] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-12-01 18:11:47,899] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-12-01 18:11:47,899] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +52: [2022-12-01 18:11:47,905] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt. +52: [2022-12-01 18:11:47,905] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt +35: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt. +35: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt. +35: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt. +35: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt. +52: [2022-12-01 18:11:47,905] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +45: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt. +45: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt. +45: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt. +45: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt. +45: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt. +45: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt. +45: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt. +45: [2022-12-01 18:11:47,907] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt +45: [2022-12-01 18:11:47,907] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt +45: [2022-12-01 18:11:47,907] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt +45: [2022-12-01 18:11:47,907] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt +45: [2022-12-01 18:11:47,907] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt +45: [2022-12-01 18:11:47,907] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt +45: [2022-12-01 18:11:47,907] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt +45: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +45: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +45: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +45: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +45: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +45: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt. +45: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +45: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +45: [2022-12-01 18:11:47,907] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt +45: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +35: [2022-12-01 18:11:47,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt. +35: [2022-12-01 18:11:47,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt +35: [2022-12-01 18:11:47,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt +35: [2022-12-01 18:11:47,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt +35: [2022-12-01 18:11:47,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt +35: [2022-12-01 18:11:47,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt +35: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +35: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +35: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt. +35: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt. +35: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt. +35: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +35: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +35: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: [2022-12-01 18:11:47,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +35: [2022-12-01 18:11:47,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt + 0: [2022-12-01 18:11:47,908] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +35: [2022-12-01 18:11:47,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt +35: [2022-12-01 18:11:47,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt +35: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +35: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +35: [2022-12-01 18:11:47,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +19: [2022-12-01 18:11:47,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-12-01 18:11:47,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-12-01 18:11:47,908] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-12-01 18:11:47,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-12-01 18:11:47,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-12-01 18:11:47,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +12: [2022-12-01 18:11:47,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +42: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt. +42: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt. +42: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt. +42: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt. +12: [2022-12-01 18:11:47,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-12-01 18:11:47,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-12-01 18:11:47,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-12-01 18:11:47,909] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-12-01 18:11:47,909] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-12-01 18:11:47,909] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +12: [2022-12-01 18:11:47,909] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-12-01 18:11:47,909] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-12-01 18:11:47,909] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +12: [2022-12-01 18:11:47,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-12-01 18:11:47,909] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +12: [2022-12-01 18:11:47,909] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +12: [2022-12-01 18:11:47,909] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-12-01 18:11:47,909] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +12: [2022-12-01 18:11:47,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +12: [2022-12-01 18:11:47,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-12-01 18:11:47,909] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-12-01 18:11:47,909] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-12-01 18:11:47,909] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +12: [2022-12-01 18:11:47,909] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-12-01 18:11:47,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-12-01 18:11:47,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-12-01 18:11:47,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-12-01 18:11:47,908] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-12-01 18:11:47,908] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-12-01 18:11:47,908] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-12-01 18:11:47,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-12-01 18:11:47,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-12-01 18:11:47,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-12-01 18:11:47,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-12-01 18:11:47,909] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-12-01 18:11:47,909] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-12-01 18:11:47,909] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-12-01 18:11:47,909] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-12-01 18:11:47,909] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-12-01 18:11:47,909] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-12-01 18:11:47,909] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-12-01 18:11:47,909] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +41: [2022-12-01 18:11:47,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt. +41: [2022-12-01 18:11:47,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt. +41: [2022-12-01 18:11:47,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt. +41: [2022-12-01 18:11:47,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt. +41: [2022-12-01 18:11:47,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt. +41: [2022-12-01 18:11:47,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt. +41: [2022-12-01 18:11:47,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt. +41: [2022-12-01 18:11:47,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt. +42: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt. +41: [2022-12-01 18:11:47,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt +41: [2022-12-01 18:11:47,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt +41: [2022-12-01 18:11:47,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt +41: [2022-12-01 18:11:47,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt +41: [2022-12-01 18:11:47,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt +42: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt. +42: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt. +41: [2022-12-01 18:11:47,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt +41: [2022-12-01 18:11:47,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt +41: [2022-12-01 18:11:47,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt +42: [2022-12-01 18:11:47,907] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt +41: [2022-12-01 18:11:47,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +41: [2022-12-01 18:11:47,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +41: [2022-12-01 18:11:47,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +41: [2022-12-01 18:11:47,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +41: [2022-12-01 18:11:47,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +41: [2022-12-01 18:11:47,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +41: [2022-12-01 18:11:47,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +41: [2022-12-01 18:11:47,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +42: [2022-12-01 18:11:47,907] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt +42: [2022-12-01 18:11:47,907] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt +42: [2022-12-01 18:11:47,907] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt +42: [2022-12-01 18:11:47,907] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt +42: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +42: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +42: [2022-12-01 18:11:47,907] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt +42: [2022-12-01 18:11:47,907] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt +42: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +42: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +42: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +42: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +42: [2022-12-01 18:11:47,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +42: [2022-12-01 18:11:47,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt. +42: [2022-12-01 18:11:47,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt +42: [2022-12-01 18:11:47,908] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-12-01 18:11:47,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +12: [2022-12-01 18:11:47,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-12-01 18:11:47,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-12-01 18:11:47,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +53: [2022-12-01 18:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt. +53: [2022-12-01 18:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt. +53: [2022-12-01 18:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt. +53: [2022-12-01 18:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt. +53: [2022-12-01 18:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt. +53: [2022-12-01 18:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt. +53: [2022-12-01 18:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt. +53: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt +53: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt +53: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt +53: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt +53: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt +53: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +53: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +53: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt +53: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt +53: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +53: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-12-01 18:11:47,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +53: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-12-01 18:11:47,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +53: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +53: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +17: [2022-12-01 18:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-12-01 18:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-12-01 18:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-12-01 18:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-12-01 18:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +53: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt. +53: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt +53: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-12-01 18:11:47,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-12-01 18:11:47,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +17: [2022-12-01 18:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-12-01 18:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-12-01 18:11:47,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-12-01 18:11:47,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-12-01 18:11:47,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-12-01 18:11:47,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-12-01 18:11:47,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-12-01 18:11:47,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-12-01 18:11:47,915] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +17: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +17: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +17: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +17: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +17: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +17: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +17: [2022-12-01 18:11:47,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-12-01 18:11:47,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-12-01 18:11:47,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-12-01 18:11:47,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-12-01 18:11:47,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-12-01 18:11:47,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-12-01 18:11:47,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-12-01 18:11:47,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-12-01 18:11:47,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +27: [2022-12-01 18:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-12-01 18:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +20: [2022-12-01 18:11:47,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-12-01 18:11:47,919] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-12-01 18:11:47,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-12-01 18:11:47,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-12-01 18:11:47,919] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-12-01 18:11:47,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +36: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt. +36: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt. +36: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt. +36: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt. +11: [2022-12-01 18:11:47,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-12-01 18:11:47,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-12-01 18:11:47,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-12-01 18:11:47,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-12-01 18:11:47,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-12-01 18:11:47,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-12-01 18:11:47,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-12-01 18:11:47,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-12-01 18:11:47,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-12-01 18:11:47,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-12-01 18:11:47,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-12-01 18:11:47,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-12-01 18:11:47,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-12-01 18:11:47,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-12-01 18:11:47,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-12-01 18:11:47,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-12-01 18:11:47,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-12-01 18:11:47,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-12-01 18:11:47,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-12-01 18:11:47,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-12-01 18:11:47,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-12-01 18:11:47,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +25: [2022-12-01 18:11:47,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-12-01 18:11:47,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-12-01 18:11:47,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +36: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt. +27: [2022-12-01 18:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +36: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt +36: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt. +36: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt. +27: [2022-12-01 18:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-12-01 18:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-12-01 18:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-12-01 18:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +36: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt +36: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt +27: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +36: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt +27: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-12-01 18:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +36: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt. +27: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +36: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt +27: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +27: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +36: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +36: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +36: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +27: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +36: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +36: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +27: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +27: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +36: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt +36: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt +27: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +36: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt +27: [2022-12-01 18:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +36: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +36: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +36: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +27: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +27: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +27: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +27: [2022-12-01 18:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-12-01 18:11:47,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-12-01 18:11:47,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-12-01 18:11:47,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-12-01 18:11:47,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-12-01 18:11:47,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +62: [2022-12-01 18:11:47,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt. +58: [2022-12-01 18:11:47,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt. +58: [2022-12-01 18:11:47,923] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt. +58: [2022-12-01 18:11:47,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt. +58: [2022-12-01 18:11:47,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt. +62: [2022-12-01 18:11:47,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt. +62: [2022-12-01 18:11:47,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt. +62: [2022-12-01 18:11:47,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt. +62: [2022-12-01 18:11:47,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt. +62: [2022-12-01 18:11:47,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt. +62: [2022-12-01 18:11:47,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt. +62: [2022-12-01 18:11:47,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt. +62: [2022-12-01 18:11:47,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt +62: [2022-12-01 18:11:47,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt +62: [2022-12-01 18:11:47,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt +62: [2022-12-01 18:11:47,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +62: [2022-12-01 18:11:47,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt +62: [2022-12-01 18:11:47,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt +62: [2022-12-01 18:11:47,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt +62: [2022-12-01 18:11:47,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt +62: [2022-12-01 18:11:47,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt +62: [2022-12-01 18:11:47,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +62: [2022-12-01 18:11:47,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +62: [2022-12-01 18:11:47,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +62: [2022-12-01 18:11:47,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +62: [2022-12-01 18:11:47,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +62: [2022-12-01 18:11:47,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +62: [2022-12-01 18:11:47,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-12-01 18:11:47,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-12-01 18:11:47,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-12-01 18:11:47,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-12-01 18:11:47,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-12-01 18:11:47,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-12-01 18:11:47,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-12-01 18:11:47,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-12-01 18:11:47,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-12-01 18:11:47,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-12-01 18:11:47,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-12-01 18:11:47,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-12-01 18:11:47,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-12-01 18:11:47,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-12-01 18:11:47,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-12-01 18:11:47,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-12-01 18:11:47,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +58: [2022-12-01 18:11:47,923] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt. +58: [2022-12-01 18:11:47,923] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt +58: [2022-12-01 18:11:47,923] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt +58: [2022-12-01 18:11:47,923] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt. +58: [2022-12-01 18:11:47,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +58: [2022-12-01 18:11:47,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +58: [2022-12-01 18:11:47,923] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt +58: [2022-12-01 18:11:47,923] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt +58: [2022-12-01 18:11:47,923] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt +58: [2022-12-01 18:11:47,923] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt +58: [2022-12-01 18:11:47,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +58: [2022-12-01 18:11:47,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +58: [2022-12-01 18:11:47,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +58: [2022-12-01 18:11:47,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +58: [2022-12-01 18:11:47,924] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt. +58: [2022-12-01 18:11:47,924] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt. +58: [2022-12-01 18:11:47,924] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt +58: [2022-12-01 18:11:47,924] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt +58: [2022-12-01 18:11:47,924] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +58: [2022-12-01 18:11:47,924] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-12-01 18:11:47,927] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-12-01 18:11:47,927] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-12-01 18:11:47,927] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-12-01 18:11:47,930] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-12-01 18:11:47,930] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-12-01 18:11:47,930] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-12-01 18:11:47,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-12-01 18:11:47,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-12-01 18:11:47,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-12-01 18:11:47,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-12-01 18:11:47,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-12-01 18:11:47,931] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-12-01 18:11:47,931] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-12-01 18:11:47,931] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-12-01 18:11:47,931] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-12-01 18:11:47,931] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-12-01 18:11:47,931] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-12-01 18:11:47,931] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 9: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-12-01 18:11:47,932] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-12-01 18:11:47,932] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-12-01 18:11:47,932] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-12-01 18:11:47,932] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 9: [2022-12-01 18:11:47,932] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-12-01 18:11:47,932] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 9: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 9: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 9: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 9: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 9: [2022-12-01 18:11:47,932] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +24: [2022-12-01 18:11:47,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-12-01 18:11:47,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-12-01 18:11:47,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +38: [2022-12-01 18:11:47,933] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt. +38: [2022-12-01 18:11:47,933] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt. +38: [2022-12-01 18:11:47,933] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt. +38: [2022-12-01 18:11:47,933] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt. +38: [2022-12-01 18:11:47,933] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt. +22: [2022-12-01 18:11:47,932] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +38: [2022-12-01 18:11:47,933] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt. +38: [2022-12-01 18:11:47,933] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt +38: [2022-12-01 18:11:47,933] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt +38: [2022-12-01 18:11:47,933] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt +38: [2022-12-01 18:11:47,933] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt +38: [2022-12-01 18:11:47,933] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt +38: [2022-12-01 18:11:47,933] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt. +38: [2022-12-01 18:11:47,933] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +38: [2022-12-01 18:11:47,933] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt +38: [2022-12-01 18:11:47,933] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +38: [2022-12-01 18:11:47,933] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +38: [2022-12-01 18:11:47,933] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +38: [2022-12-01 18:11:47,933] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +38: [2022-12-01 18:11:47,933] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +38: [2022-12-01 18:11:47,933] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt +38: [2022-12-01 18:11:47,933] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt. +38: [2022-12-01 18:11:47,933] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +38: [2022-12-01 18:11:47,933] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt +38: [2022-12-01 18:11:47,933] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-12-01 18:11:47,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-12-01 18:11:47,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-12-01 18:11:47,932] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-12-01 18:11:47,932] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-12-01 18:11:47,932] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-12-01 18:11:47,932] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-12-01 18:11:47,932] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-12-01 18:11:47,932] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +31: [2022-12-01 18:11:47,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-12-01 18:11:47,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-12-01 18:11:47,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +30: [2022-12-01 18:11:47,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +44: [2022-12-01 18:11:47,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt. +44: [2022-12-01 18:11:47,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt. +44: [2022-12-01 18:11:47,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt. +31: [2022-12-01 18:11:47,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-12-01 18:11:47,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-12-01 18:11:47,936] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-12-01 18:11:47,936] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-12-01 18:11:47,936] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-12-01 18:11:47,936] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +31: [2022-12-01 18:11:47,936] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-12-01 18:11:47,936] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +31: [2022-12-01 18:11:47,936] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-12-01 18:11:47,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +31: [2022-12-01 18:11:47,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +31: [2022-12-01 18:11:47,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +44: [2022-12-01 18:11:47,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt. +44: [2022-12-01 18:11:47,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt. +44: [2022-12-01 18:11:47,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt. +44: [2022-12-01 18:11:47,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt. +44: [2022-12-01 18:11:47,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt. +44: [2022-12-01 18:11:47,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt +44: [2022-12-01 18:11:47,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt +30: [2022-12-01 18:11:47,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +44: [2022-12-01 18:11:47,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt +44: [2022-12-01 18:11:47,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt +44: [2022-12-01 18:11:47,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt +44: [2022-12-01 18:11:47,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt +30: [2022-12-01 18:11:47,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +44: [2022-12-01 18:11:47,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt +44: [2022-12-01 18:11:47,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +44: [2022-12-01 18:11:47,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt +44: [2022-12-01 18:11:47,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +44: [2022-12-01 18:11:47,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +44: [2022-12-01 18:11:47,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +44: [2022-12-01 18:11:47,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +44: [2022-12-01 18:11:47,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +44: [2022-12-01 18:11:47,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +44: [2022-12-01 18:11:47,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +31: [2022-12-01 18:11:47,938] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-12-01 18:11:47,939] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-12-01 18:11:47,939] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +33: [2022-12-01 18:11:47,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt. +33: [2022-12-01 18:11:47,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt. +33: [2022-12-01 18:11:47,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt. +33: [2022-12-01 18:11:47,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt. +33: [2022-12-01 18:11:47,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt. +33: [2022-12-01 18:11:47,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt. +33: [2022-12-01 18:11:47,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt. +33: [2022-12-01 18:11:47,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt. +33: [2022-12-01 18:11:47,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt +33: [2022-12-01 18:11:47,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt +33: [2022-12-01 18:11:47,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt +33: [2022-12-01 18:11:47,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt +33: [2022-12-01 18:11:47,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt +33: [2022-12-01 18:11:47,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt +33: [2022-12-01 18:11:47,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt +33: [2022-12-01 18:11:47,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt +33: [2022-12-01 18:11:47,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +33: [2022-12-01 18:11:47,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +33: [2022-12-01 18:11:47,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +33: [2022-12-01 18:11:47,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +33: [2022-12-01 18:11:47,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +33: [2022-12-01 18:11:47,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +33: [2022-12-01 18:11:47,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +33: [2022-12-01 18:11:47,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +19: [2022-12-01 18:11:47,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-12-01 18:11:47,946] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +23: [2022-12-01 18:11:47,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-12-01 18:11:47,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-12-01 18:11:47,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-12-01 18:11:47,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-12-01 18:11:47,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +19: [2022-12-01 18:11:47,946] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +23: [2022-12-01 18:11:47,946] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-12-01 18:11:47,946] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-12-01 18:11:47,946] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-12-01 18:11:47,946] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-12-01 18:11:47,946] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-12-01 18:11:47,946] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +23: [2022-12-01 18:11:47,946] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +23: [2022-12-01 18:11:47,946] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +23: [2022-12-01 18:11:47,946] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +23: [2022-12-01 18:11:47,946] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 8: [2022-12-01 18:11:47,946] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-12-01 18:11:47,946] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-12-01 18:11:47,946] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-12-01 18:11:47,946] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-12-01 18:11:47,946] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-12-01 18:11:47,946] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-12-01 18:11:47,946] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-12-01 18:11:47,946] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-12-01 18:11:47,946] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-12-01 18:11:47,946] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-12-01 18:11:47,946] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-12-01 18:11:47,946] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-12-01 18:11:47,946] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 8: [2022-12-01 18:11:47,946] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 8: [2022-12-01 18:11:47,946] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-12-01 18:11:47,946] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-12-01 18:11:47,946] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-12-01 18:11:47,946] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-12-01 18:11:47,946] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 8: [2022-12-01 18:11:47,946] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 8: [2022-12-01 18:11:47,947] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 8: [2022-12-01 18:11:47,947] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 8: [2022-12-01 18:11:47,947] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 8: [2022-12-01 18:11:47,947] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +25: [2022-12-01 18:11:47,950] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-12-01 18:11:47,950] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-12-01 18:11:47,950] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +61: [2022-12-01 18:11:47,951] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt. +61: [2022-12-01 18:11:47,951] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt. +61: [2022-12-01 18:11:47,951] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt. +61: [2022-12-01 18:11:47,951] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt. +61: [2022-12-01 18:11:47,951] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt. +19: [2022-12-01 18:11:47,954] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-12-01 18:11:47,954] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-12-01 18:11:47,954] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +61: [2022-12-01 18:11:47,951] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt. +61: [2022-12-01 18:11:47,951] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt. +61: [2022-12-01 18:11:47,951] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt. +61: [2022-12-01 18:11:47,952] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt +61: [2022-12-01 18:11:47,952] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt +61: [2022-12-01 18:11:47,952] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt +61: [2022-12-01 18:11:47,952] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt +61: [2022-12-01 18:11:47,952] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt +61: [2022-12-01 18:11:47,952] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt +61: [2022-12-01 18:11:47,952] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt +61: [2022-12-01 18:11:47,952] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt +61: [2022-12-01 18:11:47,952] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +61: [2022-12-01 18:11:47,952] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +61: [2022-12-01 18:11:47,952] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +61: [2022-12-01 18:11:47,952] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +61: [2022-12-01 18:11:47,952] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +61: [2022-12-01 18:11:47,952] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +61: [2022-12-01 18:11:47,952] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +61: [2022-12-01 18:11:47,952] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 9: [2022-12-01 18:11:47,956] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-12-01 18:11:47,956] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-12-01 18:11:47,956] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-12-01 18:11:47,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-12-01 18:11:47,959] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-12-01 18:11:47,959] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +56: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt. +56: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt. +56: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt. +56: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt. +56: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt. +56: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt. +56: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt. +56: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt. +56: [2022-12-01 18:11:47,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt +56: [2022-12-01 18:11:47,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt +56: [2022-12-01 18:11:47,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt +56: [2022-12-01 18:11:47,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt +56: [2022-12-01 18:11:47,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt +56: [2022-12-01 18:11:47,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt +56: [2022-12-01 18:11:47,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt +56: [2022-12-01 18:11:47,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt +56: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +56: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +56: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +56: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +56: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +56: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +56: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +56: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +46: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt. +46: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt. +46: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt. +46: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt. +46: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt. +46: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt. +46: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt. +46: [2022-12-01 18:11:47,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt. +46: [2022-12-01 18:11:47,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt +46: [2022-12-01 18:11:47,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt +46: [2022-12-01 18:11:47,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt +46: [2022-12-01 18:11:47,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt +46: [2022-12-01 18:11:47,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt +46: [2022-12-01 18:11:47,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt +46: [2022-12-01 18:11:47,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt +46: [2022-12-01 18:11:47,964] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt +46: [2022-12-01 18:11:47,964] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +46: [2022-12-01 18:11:47,964] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +46: [2022-12-01 18:11:47,964] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +46: [2022-12-01 18:11:47,964] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +46: [2022-12-01 18:11:47,964] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +46: [2022-12-01 18:11:47,964] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +46: [2022-12-01 18:11:47,964] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +46: [2022-12-01 18:11:47,964] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +63: [2022-12-01 18:11:47,965] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt. +63: [2022-12-01 18:11:47,965] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt. +63: [2022-12-01 18:11:47,965] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt. +63: [2022-12-01 18:11:47,965] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt. +63: [2022-12-01 18:11:47,965] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt. +63: [2022-12-01 18:11:47,965] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt. +63: [2022-12-01 18:11:47,965] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt. +63: [2022-12-01 18:11:47,965] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt. +63: [2022-12-01 18:11:47,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt +63: [2022-12-01 18:11:47,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt +63: [2022-12-01 18:11:47,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt +63: [2022-12-01 18:11:47,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt +63: [2022-12-01 18:11:47,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt +63: [2022-12-01 18:11:47,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt +63: [2022-12-01 18:11:47,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt +63: [2022-12-01 18:11:47,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt +63: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +63: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +63: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +63: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +63: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +63: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +63: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +63: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +47: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt. +47: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt. +47: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt. +47: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt. +47: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt. +47: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt. +47: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt. +47: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt. +47: [2022-12-01 18:11:47,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt +47: [2022-12-01 18:11:47,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt +47: [2022-12-01 18:11:47,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt +47: [2022-12-01 18:11:47,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt +47: [2022-12-01 18:11:47,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt +47: [2022-12-01 18:11:47,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt +47: [2022-12-01 18:11:47,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt +47: [2022-12-01 18:11:47,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt +47: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +47: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +47: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +47: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +47: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +47: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +47: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +47: [2022-12-01 18:11:47,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +49: [2022-12-01 18:11:47,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt. +49: [2022-12-01 18:11:47,967] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt +49: [2022-12-01 18:11:47,967] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-12-01 18:11:47,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-12-01 18:11:47,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-12-01 18:11:47,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-12-01 18:11:47,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-12-01 18:11:47,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-12-01 18:11:47,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-12-01 18:11:47,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-12-01 18:11:47,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-12-01 18:11:47,967] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-12-01 18:11:47,967] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-12-01 18:11:47,967] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-12-01 18:11:47,967] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-12-01 18:11:47,967] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-12-01 18:11:47,968] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-12-01 18:11:47,968] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-12-01 18:11:47,968] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-12-01 18:11:47,968] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +22: [2022-12-01 18:11:47,968] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +13: [2022-12-01 18:11:47,968] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-12-01 18:11:47,968] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-12-01 18:11:47,968] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-12-01 18:11:47,968] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-12-01 18:11:47,968] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +13: [2022-12-01 18:11:47,968] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-12-01 18:11:47,968] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-12-01 18:11:47,968] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-12-01 18:11:47,968] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-12-01 18:11:47,969] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-12-01 18:11:47,969] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-12-01 18:11:47,969] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +57: [2022-12-01 18:11:47,969] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt. +57: [2022-12-01 18:11:47,969] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt. +57: [2022-12-01 18:11:47,969] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt. +24: [2022-12-01 18:11:47,970] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-12-01 18:11:47,970] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-12-01 18:11:47,970] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +52: [2022-12-01 18:11:47,970] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt. +52: [2022-12-01 18:11:47,970] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt +52: [2022-12-01 18:11:47,970] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-12-01 18:11:47,970] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-12-01 18:11:47,970] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-12-01 18:11:47,970] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +57: [2022-12-01 18:11:47,969] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt. +57: [2022-12-01 18:11:47,969] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt. +57: [2022-12-01 18:11:47,969] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt. +57: [2022-12-01 18:11:47,969] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt. +57: [2022-12-01 18:11:47,969] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt +57: [2022-12-01 18:11:47,969] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt +57: [2022-12-01 18:11:47,969] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt +57: [2022-12-01 18:11:47,969] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt +57: [2022-12-01 18:11:47,969] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt +57: [2022-12-01 18:11:47,969] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt +57: [2022-12-01 18:11:47,969] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt +57: [2022-12-01 18:11:47,969] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +57: [2022-12-01 18:11:47,969] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +57: [2022-12-01 18:11:47,969] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +57: [2022-12-01 18:11:47,969] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +57: [2022-12-01 18:11:47,969] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +57: [2022-12-01 18:11:47,969] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +57: [2022-12-01 18:11:47,969] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +57: [2022-12-01 18:11:47,970] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt. +57: [2022-12-01 18:11:47,970] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt +57: [2022-12-01 18:11:47,970] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +43: [2022-12-01 18:11:47,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt. +43: [2022-12-01 18:11:47,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt. +43: [2022-12-01 18:11:47,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt. +43: [2022-12-01 18:11:47,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt. +43: [2022-12-01 18:11:47,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt. +14: [2022-12-01 18:11:47,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-12-01 18:11:47,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-12-01 18:11:47,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-12-01 18:11:47,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-12-01 18:11:47,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +43: [2022-12-01 18:11:47,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt. +43: [2022-12-01 18:11:47,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt. +43: [2022-12-01 18:11:47,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt. +14: [2022-12-01 18:11:47,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +43: [2022-12-01 18:11:47,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt +43: [2022-12-01 18:11:47,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt +43: [2022-12-01 18:11:47,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt +43: [2022-12-01 18:11:47,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt +14: [2022-12-01 18:11:47,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-12-01 18:11:47,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-12-01 18:11:47,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +43: [2022-12-01 18:11:47,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt +43: [2022-12-01 18:11:47,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt +43: [2022-12-01 18:11:47,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt +43: [2022-12-01 18:11:47,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt +43: [2022-12-01 18:11:47,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +43: [2022-12-01 18:11:47,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-12-01 18:11:47,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-12-01 18:11:47,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +43: [2022-12-01 18:11:47,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-12-01 18:11:47,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-12-01 18:11:47,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +43: [2022-12-01 18:11:47,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +43: [2022-12-01 18:11:47,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +43: [2022-12-01 18:11:47,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +43: [2022-12-01 18:11:47,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +43: [2022-12-01 18:11:47,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-12-01 18:11:47,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-12-01 18:11:47,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-12-01 18:11:47,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-12-01 18:11:47,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-12-01 18:11:47,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-12-01 18:11:47,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-12-01 18:11:47,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +14: [2022-12-01 18:11:47,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-12-01 18:11:47,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-12-01 18:11:47,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-12-01 18:11:47,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +49: [2022-12-01 18:11:47,976] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt. +49: [2022-12-01 18:11:47,976] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt +49: [2022-12-01 18:11:47,976] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 3: [2022-12-01 18:11:47,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-12-01 18:11:47,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-12-01 18:11:47,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-12-01 18:11:47,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-12-01 18:11:47,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-12-01 18:11:47,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-12-01 18:11:47,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-12-01 18:11:47,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-12-01 18:11:47,977] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-12-01 18:11:47,977] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-12-01 18:11:47,977] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-12-01 18:11:47,977] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-12-01 18:11:47,977] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-12-01 18:11:47,977] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 3: [2022-12-01 18:11:47,977] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 3: [2022-12-01 18:11:47,977] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 3: [2022-12-01 18:11:47,977] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 3: [2022-12-01 18:11:47,977] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 3: [2022-12-01 18:11:47,977] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-12-01 18:11:47,977] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-12-01 18:11:47,977] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-12-01 18:11:47,977] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 3: [2022-12-01 18:11:47,977] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 3: [2022-12-01 18:11:47,977] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-12-01 18:11:47,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-12-01 18:11:47,977] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-12-01 18:11:47,977] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-12-01 18:11:47,978] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-12-01 18:11:47,978] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-12-01 18:11:47,978] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-12-01 18:11:47,982] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-12-01 18:11:47,982] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-12-01 18:11:47,982] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-12-01 18:11:47,982] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-12-01 18:11:47,983] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-12-01 18:11:47,983] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-12-01 18:11:47,984] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-12-01 18:11:47,984] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-12-01 18:11:47,984] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +23: [2022-12-01 18:11:47,989] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-12-01 18:11:47,989] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-12-01 18:11:47,989] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +23: [2022-12-01 18:11:47,996] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +30: [2022-12-01 18:11:47,996] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +23: [2022-12-01 18:11:47,996] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-12-01 18:11:47,996] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-12-01 18:11:47,996] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-12-01 18:11:47,996] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-12-01 18:11:47,998] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-12-01 18:11:47,998] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-12-01 18:11:47,998] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +59: [2022-12-01 18:11:47,999] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt. +59: [2022-12-01 18:11:47,999] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt. +59: [2022-12-01 18:11:47,999] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt. +59: [2022-12-01 18:11:47,999] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt. +59: [2022-12-01 18:11:47,999] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt. +59: [2022-12-01 18:11:47,999] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt. +59: [2022-12-01 18:11:47,999] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt. +59: [2022-12-01 18:11:47,999] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt. +59: [2022-12-01 18:11:48,000] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt +59: [2022-12-01 18:11:48,000] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt +59: [2022-12-01 18:11:48,000] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt +59: [2022-12-01 18:11:48,000] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt +59: [2022-12-01 18:11:48,000] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt +59: [2022-12-01 18:11:48,000] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt +59: [2022-12-01 18:11:48,000] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt +59: [2022-12-01 18:11:48,000] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt +59: [2022-12-01 18:11:48,000] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +59: [2022-12-01 18:11:48,000] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +59: [2022-12-01 18:11:48,000] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +59: [2022-12-01 18:11:48,000] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +59: [2022-12-01 18:11:48,000] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +59: [2022-12-01 18:11:48,000] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +59: [2022-12-01 18:11:48,000] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +59: [2022-12-01 18:11:48,000] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +31: [2022-12-01 18:11:48,004] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-12-01 18:11:48,004] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-12-01 18:11:48,004] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-12-01 18:11:48,004] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-12-01 18:11:48,004] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +31: [2022-12-01 18:11:48,004] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +48: [2022-12-01 18:11:48,020] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt. +48: [2022-12-01 18:11:48,020] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt +48: [2022-12-01 18:11:48,020] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +49: [2022-12-01 18:11:48,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt. +49: [2022-12-01 18:11:48,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt +49: [2022-12-01 18:11:48,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +55: [2022-12-01 18:11:48,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt. +55: [2022-12-01 18:11:48,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt. +55: [2022-12-01 18:11:48,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt. +55: [2022-12-01 18:11:48,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt. +55: [2022-12-01 18:11:48,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt. +55: [2022-12-01 18:11:48,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt. +55: [2022-12-01 18:11:48,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt. +55: [2022-12-01 18:11:48,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt. +55: [2022-12-01 18:11:48,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt +55: [2022-12-01 18:11:48,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt +49: [2022-12-01 18:11:48,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt. +55: [2022-12-01 18:11:48,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt +55: [2022-12-01 18:11:48,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt +49: [2022-12-01 18:11:48,025] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt +55: [2022-12-01 18:11:48,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt +55: [2022-12-01 18:11:48,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt +49: [2022-12-01 18:11:48,025] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +55: [2022-12-01 18:11:48,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt +55: [2022-12-01 18:11:48,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt +55: [2022-12-01 18:11:48,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +55: [2022-12-01 18:11:48,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +55: [2022-12-01 18:11:48,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +55: [2022-12-01 18:11:48,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +55: [2022-12-01 18:11:48,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +55: [2022-12-01 18:11:48,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +55: [2022-12-01 18:11:48,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +55: [2022-12-01 18:11:48,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +25: [2022-12-01 18:11:48,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-12-01 18:11:48,026] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-12-01 18:11:48,026] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +25: [2022-12-01 18:11:48,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-12-01 18:11:48,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-12-01 18:11:48,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +23: [2022-12-01 18:11:48,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-12-01 18:11:48,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-12-01 18:11:48,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-12-01 18:11:48,047] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +19: [2022-12-01 18:11:48,047] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +14: [2022-12-01 18:11:48,047] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-12-01 18:11:48,047] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +19: [2022-12-01 18:11:48,047] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-12-01 18:11:48,047] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-12-01 18:11:48,062] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-12-01 18:11:48,062] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-12-01 18:11:48,062] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-12-01 18:11:48,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-12-01 18:11:48,063] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-12-01 18:11:48,063] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +49: [2022-12-01 18:11:48,064] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt. +49: [2022-12-01 18:11:48,064] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt +49: [2022-12-01 18:11:48,064] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +19: [2022-12-01 18:11:48,083] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-12-01 18:11:48,083] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-12-01 18:11:48,083] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +25: [2022-12-01 18:11:48,096] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-12-01 18:11:48,096] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step10000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-12-01 18:11:48,096] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: successfully saved checkpoint at iteration 10000 to checkpoints_3b977boscar +63: time (ms) | save-checkpoint: 6399.15 +63: iteration 10010/ 73814 | consumed samples: 5125120 | consumed tokens: 10496245760 | elapsed time per iteration (s): 2.96 | learning rate: 1.929E-04 | global batch size: 512 | lm loss: 2.352384E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 172.918 | TFLOPs: 17.80 | +63: iteration 10020/ 73814 | consumed samples: 5130240 | consumed tokens: 10506731520 | elapsed time per iteration (s): 2.27 | learning rate: 1.929E-04 | global batch size: 512 | lm loss: 2.364848E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.636 | TFLOPs: 23.23 | +63: iteration 10030/ 73814 | consumed samples: 5135360 | consumed tokens: 10517217280 | elapsed time per iteration (s): 2.24 | learning rate: 1.929E-04 | global batch size: 512 | lm loss: 2.357238E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.794 | TFLOPs: 23.55 | +63: iteration 10040/ 73814 | consumed samples: 5140480 | consumed tokens: 10527703040 | elapsed time per iteration (s): 2.23 | learning rate: 1.929E-04 | global batch size: 512 | lm loss: 2.346733E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.750 | TFLOPs: 23.65 | +63: iteration 10050/ 73814 | consumed samples: 5145600 | consumed tokens: 10538188800 | elapsed time per iteration (s): 2.23 | learning rate: 1.929E-04 | global batch size: 512 | lm loss: 2.343660E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.638 | TFLOPs: 23.64 | +63: iteration 10060/ 73814 | consumed samples: 5150720 | consumed tokens: 10548674560 | elapsed time per iteration (s): 2.30 | learning rate: 1.929E-04 | global batch size: 512 | lm loss: 2.347319E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.033 | TFLOPs: 22.96 | +63: iteration 10070/ 73814 | consumed samples: 5155840 | consumed tokens: 10559160320 | elapsed time per iteration (s): 2.23 | learning rate: 1.929E-04 | global batch size: 512 | lm loss: 2.359571E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.262 | TFLOPs: 23.60 | +63: iteration 10080/ 73814 | consumed samples: 5160960 | consumed tokens: 10569646080 | elapsed time per iteration (s): 2.23 | learning rate: 1.928E-04 | global batch size: 512 | lm loss: 2.348169E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.784 | TFLOPs: 23.66 | +63: iteration 10090/ 73814 | consumed samples: 5166080 | consumed tokens: 10580131840 | elapsed time per iteration (s): 2.49 | learning rate: 1.928E-04 | global batch size: 512 | lm loss: 2.361574E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.285 | TFLOPs: 21.13 | +63: iteration 10100/ 73814 | consumed samples: 5171200 | consumed tokens: 10590617600 | elapsed time per iteration (s): 2.24 | learning rate: 1.928E-04 | global batch size: 512 | lm loss: 2.359919E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.220 | TFLOPs: 23.49 | +63: iteration 10110/ 73814 | consumed samples: 5176320 | consumed tokens: 10601103360 | elapsed time per iteration (s): 2.40 | learning rate: 1.928E-04 | global batch size: 512 | lm loss: 2.351995E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.767 | TFLOPs: 22.01 | +63: iteration 10120/ 73814 | consumed samples: 5181440 | consumed tokens: 10611589120 | elapsed time per iteration (s): 2.23 | learning rate: 1.928E-04 | global batch size: 512 | lm loss: 2.343447E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.800 | TFLOPs: 23.66 | +63: iteration 10130/ 73814 | consumed samples: 5186560 | consumed tokens: 10622074880 | elapsed time per iteration (s): 2.25 | learning rate: 1.928E-04 | global batch size: 512 | lm loss: 2.375507E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.983 | TFLOPs: 23.47 | +63: iteration 10140/ 73814 | consumed samples: 5191680 | consumed tokens: 10632560640 | elapsed time per iteration (s): 2.24 | learning rate: 1.927E-04 | global batch size: 512 | lm loss: 2.351221E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.320 | TFLOPs: 23.50 | +63: iteration 10150/ 73814 | consumed samples: 5196800 | consumed tokens: 10643046400 | elapsed time per iteration (s): 2.27 | learning rate: 1.927E-04 | global batch size: 512 | lm loss: 2.342868E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.526 | TFLOPs: 23.22 | +63: iteration 10160/ 73814 | consumed samples: 5201920 | consumed tokens: 10653532160 | elapsed time per iteration (s): 2.37 | learning rate: 1.927E-04 | global batch size: 512 | lm loss: 2.339786E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.968 | TFLOPs: 22.23 | +63: iteration 10170/ 73814 | consumed samples: 5207040 | consumed tokens: 10664017920 | elapsed time per iteration (s): 2.25 | learning rate: 1.927E-04 | global batch size: 512 | lm loss: 2.381935E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.397 | TFLOPs: 23.41 | +63: iteration 10180/ 73814 | consumed samples: 5212160 | consumed tokens: 10674503680 | elapsed time per iteration (s): 2.23 | learning rate: 1.927E-04 | global batch size: 512 | lm loss: 2.345105E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.217 | TFLOPs: 23.60 | +63: iteration 10190/ 73814 | consumed samples: 5217280 | consumed tokens: 10684989440 | elapsed time per iteration (s): 2.34 | learning rate: 1.927E-04 | global batch size: 512 | lm loss: 2.373639E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.458 | TFLOPs: 22.49 | +63: iteration 10200/ 73814 | consumed samples: 5222400 | consumed tokens: 10695475200 | elapsed time per iteration (s): 2.32 | learning rate: 1.927E-04 | global batch size: 512 | lm loss: 2.350360E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.507 | TFLOPs: 22.70 | +63: iteration 10210/ 73814 | consumed samples: 5227520 | consumed tokens: 10705960960 | elapsed time per iteration (s): 2.25 | learning rate: 1.926E-04 | global batch size: 512 | lm loss: 2.320099E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.713 | TFLOPs: 23.44 | +63: iteration 10220/ 73814 | consumed samples: 5232640 | consumed tokens: 10716446720 | elapsed time per iteration (s): 2.22 | learning rate: 1.926E-04 | global batch size: 512 | lm loss: 2.353613E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.193 | TFLOPs: 23.70 | +63: iteration 10230/ 73814 | consumed samples: 5237760 | consumed tokens: 10726932480 | elapsed time per iteration (s): 2.25 | learning rate: 1.926E-04 | global batch size: 512 | lm loss: 2.330679E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.977 | TFLOPs: 23.47 | +63: iteration 10240/ 73814 | consumed samples: 5242880 | consumed tokens: 10737418240 | elapsed time per iteration (s): 2.23 | learning rate: 1.926E-04 | global batch size: 512 | lm loss: 2.347454E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.733 | TFLOPs: 23.65 | +63: iteration 10250/ 73814 | consumed samples: 5248000 | consumed tokens: 10747904000 | elapsed time per iteration (s): 2.25 | learning rate: 1.926E-04 | global batch size: 512 | lm loss: 2.343542E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.394 | TFLOPs: 23.41 | +63: iteration 10260/ 73814 | consumed samples: 5253120 | consumed tokens: 10758389760 | elapsed time per iteration (s): 2.42 | learning rate: 1.926E-04 | global batch size: 512 | lm loss: 2.338734E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.505 | TFLOPs: 21.77 | +63: iteration 10270/ 73814 | consumed samples: 5258240 | consumed tokens: 10768875520 | elapsed time per iteration (s): 2.23 | learning rate: 1.925E-04 | global batch size: 512 | lm loss: 2.356112E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.678 | TFLOPs: 23.64 | +63: iteration 10280/ 73814 | consumed samples: 5263360 | consumed tokens: 10779361280 | elapsed time per iteration (s): 2.23 | learning rate: 1.925E-04 | global batch size: 512 | lm loss: 2.339367E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.220 | TFLOPs: 23.60 | +63: iteration 10290/ 73814 | consumed samples: 5268480 | consumed tokens: 10789847040 | elapsed time per iteration (s): 2.25 | learning rate: 1.925E-04 | global batch size: 512 | lm loss: 2.334610E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.855 | TFLOPs: 23.46 | +63: iteration 10300/ 73814 | consumed samples: 5273600 | consumed tokens: 10800332800 | elapsed time per iteration (s): 2.23 | learning rate: 1.925E-04 | global batch size: 512 | lm loss: 2.342241E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.687 | TFLOPs: 23.65 | +63: iteration 10310/ 73814 | consumed samples: 5278720 | consumed tokens: 10810818560 | elapsed time per iteration (s): 2.25 | learning rate: 1.925E-04 | global batch size: 512 | lm loss: 2.358314E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.678 | TFLOPs: 23.44 | +63: iteration 10320/ 73814 | consumed samples: 5283840 | consumed tokens: 10821304320 | elapsed time per iteration (s): 2.23 | learning rate: 1.925E-04 | global batch size: 512 | lm loss: 2.333007E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.803 | TFLOPs: 23.66 | +63: iteration 10330/ 73814 | consumed samples: 5288960 | consumed tokens: 10831790080 | elapsed time per iteration (s): 2.23 | learning rate: 1.925E-04 | global batch size: 512 | lm loss: 2.339991E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.105 | TFLOPs: 23.69 | +63: iteration 10340/ 73814 | consumed samples: 5294080 | consumed tokens: 10842275840 | elapsed time per iteration (s): 2.23 | learning rate: 1.924E-04 | global batch size: 512 | lm loss: 2.342688E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.398 | TFLOPs: 23.62 | +63: iteration 10350/ 73814 | consumed samples: 5299200 | consumed tokens: 10852761600 | elapsed time per iteration (s): 2.23 | learning rate: 1.924E-04 | global batch size: 512 | lm loss: 2.366839E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.052 | TFLOPs: 23.68 | +63: iteration 10360/ 73814 | consumed samples: 5304320 | consumed tokens: 10863247360 | elapsed time per iteration (s): 2.23 | learning rate: 1.924E-04 | global batch size: 512 | lm loss: 2.315987E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.338 | TFLOPs: 23.61 | +63: iteration 10370/ 73814 | consumed samples: 5309440 | consumed tokens: 10873733120 | elapsed time per iteration (s): 2.23 | learning rate: 1.924E-04 | global batch size: 512 | lm loss: 2.351279E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.506 | TFLOPs: 23.63 | +63: iteration 10380/ 73814 | consumed samples: 5314560 | consumed tokens: 10884218880 | elapsed time per iteration (s): 2.23 | learning rate: 1.924E-04 | global batch size: 512 | lm loss: 2.345596E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.068 | TFLOPs: 23.68 | +63: iteration 10390/ 73814 | consumed samples: 5319680 | consumed tokens: 10894704640 | elapsed time per iteration (s): 2.23 | learning rate: 1.924E-04 | global batch size: 512 | lm loss: 2.333018E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.981 | TFLOPs: 23.68 | +63: iteration 10400/ 73814 | consumed samples: 5324800 | consumed tokens: 10905190400 | elapsed time per iteration (s): 2.26 | learning rate: 1.923E-04 | global batch size: 512 | lm loss: 2.357286E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.289 | TFLOPs: 23.30 | +63: iteration 10410/ 73814 | consumed samples: 5329920 | consumed tokens: 10915676160 | elapsed time per iteration (s): 2.23 | learning rate: 1.923E-04 | global batch size: 512 | lm loss: 2.343488E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.776 | TFLOPs: 23.65 | +63: iteration 10420/ 73814 | consumed samples: 5335040 | consumed tokens: 10926161920 | elapsed time per iteration (s): 2.28 | learning rate: 1.923E-04 | global batch size: 512 | lm loss: 2.353926E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.645 | TFLOPs: 23.13 | +63: iteration 10430/ 73814 | consumed samples: 5340160 | consumed tokens: 10936647680 | elapsed time per iteration (s): 2.26 | learning rate: 1.923E-04 | global batch size: 512 | lm loss: 2.320466E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.352 | TFLOPs: 23.30 | +63: iteration 10440/ 73814 | consumed samples: 5345280 | consumed tokens: 10947133440 | elapsed time per iteration (s): 2.23 | learning rate: 1.923E-04 | global batch size: 512 | lm loss: 2.358501E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.682 | TFLOPs: 23.64 | +63: iteration 10450/ 73814 | consumed samples: 5350400 | consumed tokens: 10957619200 | elapsed time per iteration (s): 2.24 | learning rate: 1.923E-04 | global batch size: 512 | lm loss: 2.350499E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.318 | TFLOPs: 23.50 | +63: iteration 10460/ 73814 | consumed samples: 5355520 | consumed tokens: 10968104960 | elapsed time per iteration (s): 2.23 | learning rate: 1.923E-04 | global batch size: 512 | lm loss: 2.339346E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.982 | TFLOPs: 23.68 | +63: iteration 10470/ 73814 | consumed samples: 5360640 | consumed tokens: 10978590720 | elapsed time per iteration (s): 2.25 | learning rate: 1.922E-04 | global batch size: 512 | lm loss: 2.345801E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.115 | TFLOPs: 23.38 | +63: iteration 10480/ 73814 | consumed samples: 5365760 | consumed tokens: 10989076480 | elapsed time per iteration (s): 2.23 | learning rate: 1.922E-04 | global batch size: 512 | lm loss: 2.334875E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.559 | TFLOPs: 23.63 | +63: iteration 10490/ 73814 | consumed samples: 5370880 | consumed tokens: 10999562240 | elapsed time per iteration (s): 2.28 | learning rate: 1.922E-04 | global batch size: 512 | lm loss: 2.354631E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.387 | TFLOPs: 23.10 | +63: iteration 10500/ 73814 | consumed samples: 5376000 | consumed tokens: 11010048000 | elapsed time per iteration (s): 2.23 | learning rate: 1.922E-04 | global batch size: 512 | lm loss: 2.336014E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.724 | TFLOPs: 23.65 | +63: iteration 10510/ 73814 | consumed samples: 5381120 | consumed tokens: 11020533760 | elapsed time per iteration (s): 2.23 | learning rate: 1.922E-04 | global batch size: 512 | lm loss: 2.334819E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.707 | TFLOPs: 23.65 | +63: iteration 10520/ 73814 | consumed samples: 5386240 | consumed tokens: 11031019520 | elapsed time per iteration (s): 2.24 | learning rate: 1.922E-04 | global batch size: 512 | lm loss: 2.353338E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.601 | TFLOPs: 23.53 | +63: iteration 10530/ 73814 | consumed samples: 5391360 | consumed tokens: 11041505280 | elapsed time per iteration (s): 2.23 | learning rate: 1.921E-04 | global batch size: 512 | lm loss: 2.360174E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.694 | TFLOPs: 23.65 | +63: iteration 10540/ 73814 | consumed samples: 5396480 | consumed tokens: 11051991040 | elapsed time per iteration (s): 2.24 | learning rate: 1.921E-04 | global batch size: 512 | lm loss: 2.350892E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.957 | TFLOPs: 23.57 | +63: iteration 10550/ 73814 | consumed samples: 5401600 | consumed tokens: 11062476800 | elapsed time per iteration (s): 2.23 | learning rate: 1.921E-04 | global batch size: 512 | lm loss: 2.355856E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.723 | TFLOPs: 23.65 | +63: iteration 10560/ 73814 | consumed samples: 5406720 | consumed tokens: 11072962560 | elapsed time per iteration (s): 2.23 | learning rate: 1.921E-04 | global batch size: 512 | lm loss: 2.340486E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.595 | TFLOPs: 23.64 | +63: iteration 10570/ 73814 | consumed samples: 5411840 | consumed tokens: 11083448320 | elapsed time per iteration (s): 2.25 | learning rate: 1.921E-04 | global batch size: 512 | lm loss: 2.342814E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.768 | TFLOPs: 23.45 | +63: iteration 10580/ 73814 | consumed samples: 5416960 | consumed tokens: 11093934080 | elapsed time per iteration (s): 2.25 | learning rate: 1.921E-04 | global batch size: 512 | lm loss: 2.335849E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.248 | TFLOPs: 23.39 | +63: iteration 10590/ 73814 | consumed samples: 5422080 | consumed tokens: 11104419840 | elapsed time per iteration (s): 2.23 | learning rate: 1.920E-04 | global batch size: 512 | lm loss: 2.342797E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.557 | TFLOPs: 23.63 | +63: iteration 10600/ 73814 | consumed samples: 5427200 | consumed tokens: 11114905600 | elapsed time per iteration (s): 2.23 | learning rate: 1.920E-04 | global batch size: 512 | lm loss: 2.351302E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.816 | TFLOPs: 23.66 | +63: iteration 10610/ 73814 | consumed samples: 5432320 | consumed tokens: 11125391360 | elapsed time per iteration (s): 2.23 | learning rate: 1.920E-04 | global batch size: 512 | lm loss: 2.349630E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.320 | TFLOPs: 23.61 | +63: iteration 10620/ 73814 | consumed samples: 5437440 | consumed tokens: 11135877120 | elapsed time per iteration (s): 2.24 | learning rate: 1.920E-04 | global batch size: 512 | lm loss: 2.343709E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.253 | TFLOPs: 23.50 | +63: iteration 10630/ 73814 | consumed samples: 5442560 | consumed tokens: 11146362880 | elapsed time per iteration (s): 2.27 | learning rate: 1.920E-04 | global batch size: 512 | lm loss: 2.330534E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.774 | TFLOPs: 23.24 | +63: iteration 10640/ 73814 | consumed samples: 5447680 | consumed tokens: 11156848640 | elapsed time per iteration (s): 2.22 | learning rate: 1.920E-04 | global batch size: 512 | lm loss: 2.325150E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.679 | TFLOPs: 23.75 | +63: iteration 10650/ 73814 | consumed samples: 5452800 | consumed tokens: 11167334400 | elapsed time per iteration (s): 2.23 | learning rate: 1.920E-04 | global batch size: 512 | lm loss: 2.331705E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.901 | TFLOPs: 23.67 | +63: iteration 10660/ 73814 | consumed samples: 5457920 | consumed tokens: 11177820160 | elapsed time per iteration (s): 2.23 | learning rate: 1.919E-04 | global batch size: 512 | lm loss: 2.324128E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.593 | TFLOPs: 23.64 | +63: iteration 10670/ 73814 | consumed samples: 5463040 | consumed tokens: 11188305920 | elapsed time per iteration (s): 2.25 | learning rate: 1.919E-04 | global batch size: 512 | lm loss: 2.330019E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.665 | TFLOPs: 23.44 | +63: iteration 10680/ 73814 | consumed samples: 5468160 | consumed tokens: 11198791680 | elapsed time per iteration (s): 2.23 | learning rate: 1.919E-04 | global batch size: 512 | lm loss: 2.328805E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.933 | TFLOPs: 23.67 | +63: iteration 10690/ 73814 | consumed samples: 5473280 | consumed tokens: 11209277440 | elapsed time per iteration (s): 2.23 | learning rate: 1.919E-04 | global batch size: 512 | lm loss: 2.348411E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.987 | TFLOPs: 23.68 | +63: iteration 10700/ 73814 | consumed samples: 5478400 | consumed tokens: 11219763200 | elapsed time per iteration (s): 2.23 | learning rate: 1.919E-04 | global batch size: 512 | lm loss: 2.342784E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.228 | TFLOPs: 23.60 | +63: iteration 10710/ 73814 | consumed samples: 5483520 | consumed tokens: 11230248960 | elapsed time per iteration (s): 2.25 | learning rate: 1.919E-04 | global batch size: 512 | lm loss: 2.337997E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.870 | TFLOPs: 23.46 | +63: iteration 10720/ 73814 | consumed samples: 5488640 | consumed tokens: 11240734720 | elapsed time per iteration (s): 2.23 | learning rate: 1.918E-04 | global batch size: 512 | lm loss: 2.351507E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.532 | TFLOPs: 23.63 | +63: iteration 10730/ 73814 | consumed samples: 5493760 | consumed tokens: 11251220480 | elapsed time per iteration (s): 2.24 | learning rate: 1.918E-04 | global batch size: 512 | lm loss: 2.309242E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.763 | TFLOPs: 23.55 | +63: iteration 10740/ 73814 | consumed samples: 5498880 | consumed tokens: 11261706240 | elapsed time per iteration (s): 2.25 | learning rate: 1.918E-04 | global batch size: 512 | lm loss: 2.336728E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.094 | TFLOPs: 23.38 | +63: iteration 10750/ 73814 | consumed samples: 5504000 | consumed tokens: 11272192000 | elapsed time per iteration (s): 2.28 | learning rate: 1.918E-04 | global batch size: 512 | lm loss: 2.346712E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.308 | TFLOPs: 23.09 | +63: iteration 10760/ 73814 | consumed samples: 5509120 | consumed tokens: 11282677760 | elapsed time per iteration (s): 2.23 | learning rate: 1.918E-04 | global batch size: 512 | lm loss: 2.342706E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.362 | TFLOPs: 23.61 | +63: iteration 10770/ 73814 | consumed samples: 5514240 | consumed tokens: 11293163520 | elapsed time per iteration (s): 2.24 | learning rate: 1.918E-04 | global batch size: 512 | lm loss: 2.331857E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.518 | TFLOPs: 23.52 | +63: iteration 10780/ 73814 | consumed samples: 5519360 | consumed tokens: 11303649280 | elapsed time per iteration (s): 2.24 | learning rate: 1.917E-04 | global batch size: 512 | lm loss: 2.336632E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.870 | TFLOPs: 23.56 | +63: iteration 10790/ 73814 | consumed samples: 5524480 | consumed tokens: 11314135040 | elapsed time per iteration (s): 2.23 | learning rate: 1.917E-04 | global batch size: 512 | lm loss: 2.298926E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.252 | TFLOPs: 23.60 | +63: iteration 10800/ 73814 | consumed samples: 5529600 | consumed tokens: 11324620800 | elapsed time per iteration (s): 2.24 | learning rate: 1.917E-04 | global batch size: 512 | lm loss: 2.302671E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.884 | TFLOPs: 23.56 | +63: iteration 10810/ 73814 | consumed samples: 5534720 | consumed tokens: 11335106560 | elapsed time per iteration (s): 2.23 | learning rate: 1.917E-04 | global batch size: 512 | lm loss: 2.328084E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.801 | TFLOPs: 23.66 | +63: iteration 10820/ 73814 | consumed samples: 5539840 | consumed tokens: 11345592320 | elapsed time per iteration (s): 2.23 | learning rate: 1.917E-04 | global batch size: 512 | lm loss: 2.320296E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.345 | TFLOPs: 23.61 | +63: iteration 10830/ 73814 | consumed samples: 5544960 | consumed tokens: 11356078080 | elapsed time per iteration (s): 2.24 | learning rate: 1.917E-04 | global batch size: 512 | lm loss: 2.335595E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.807 | TFLOPs: 23.55 | +63: iteration 10840/ 73814 | consumed samples: 5550080 | consumed tokens: 11366563840 | elapsed time per iteration (s): 2.24 | learning rate: 1.916E-04 | global batch size: 512 | lm loss: 2.339491E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.355 | TFLOPs: 23.51 | +63: iteration 10850/ 73814 | consumed samples: 5555200 | consumed tokens: 11377049600 | elapsed time per iteration (s): 2.25 | learning rate: 1.916E-04 | global batch size: 512 | lm loss: 2.324080E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.553 | TFLOPs: 23.43 | +63: iteration 10860/ 73814 | consumed samples: 5560320 | consumed tokens: 11387535360 | elapsed time per iteration (s): 2.23 | learning rate: 1.916E-04 | global batch size: 512 | lm loss: 2.346440E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.601 | TFLOPs: 23.64 | +63: iteration 10870/ 73814 | consumed samples: 5565440 | consumed tokens: 11398021120 | elapsed time per iteration (s): 2.23 | learning rate: 1.916E-04 | global batch size: 512 | lm loss: 2.331327E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.703 | TFLOPs: 23.65 | +63: iteration 10880/ 73814 | consumed samples: 5570560 | consumed tokens: 11408506880 | elapsed time per iteration (s): 2.23 | learning rate: 1.916E-04 | global batch size: 512 | lm loss: 2.326114E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.591 | TFLOPs: 23.64 | +63: iteration 10890/ 73814 | consumed samples: 5575680 | consumed tokens: 11418992640 | elapsed time per iteration (s): 2.23 | learning rate: 1.916E-04 | global batch size: 512 | lm loss: 2.350912E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.039 | TFLOPs: 23.68 | +63: iteration 10900/ 73814 | consumed samples: 5580800 | consumed tokens: 11429478400 | elapsed time per iteration (s): 2.23 | learning rate: 1.915E-04 | global batch size: 512 | lm loss: 2.327876E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.651 | TFLOPs: 23.64 | +63: iteration 10910/ 73814 | consumed samples: 5585920 | consumed tokens: 11439964160 | elapsed time per iteration (s): 2.22 | learning rate: 1.915E-04 | global batch size: 512 | lm loss: 2.334839E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.196 | TFLOPs: 23.70 | +63: iteration 10920/ 73814 | consumed samples: 5591040 | consumed tokens: 11450449920 | elapsed time per iteration (s): 2.24 | learning rate: 1.915E-04 | global batch size: 512 | lm loss: 2.341839E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.722 | TFLOPs: 23.55 | +63: iteration 10930/ 73814 | consumed samples: 5596160 | consumed tokens: 11460935680 | elapsed time per iteration (s): 2.25 | learning rate: 1.915E-04 | global batch size: 512 | lm loss: 2.333372E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.857 | TFLOPs: 23.46 | +63: iteration 10940/ 73814 | consumed samples: 5601280 | consumed tokens: 11471421440 | elapsed time per iteration (s): 2.24 | learning rate: 1.915E-04 | global batch size: 512 | lm loss: 2.323840E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.200 | TFLOPs: 23.49 | +63: iteration 10950/ 73814 | consumed samples: 5606400 | consumed tokens: 11481907200 | elapsed time per iteration (s): 2.25 | learning rate: 1.915E-04 | global batch size: 512 | lm loss: 2.314883E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.005 | TFLOPs: 23.47 | +63: iteration 10960/ 73814 | consumed samples: 5611520 | consumed tokens: 11492392960 | elapsed time per iteration (s): 2.24 | learning rate: 1.914E-04 | global batch size: 512 | lm loss: 2.355016E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.945 | TFLOPs: 23.57 | +63: iteration 10970/ 73814 | consumed samples: 5616640 | consumed tokens: 11502878720 | elapsed time per iteration (s): 2.23 | learning rate: 1.914E-04 | global batch size: 512 | lm loss: 2.336485E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.486 | TFLOPs: 23.62 | +63: iteration 10980/ 73814 | consumed samples: 5621760 | consumed tokens: 11513364480 | elapsed time per iteration (s): 2.25 | learning rate: 1.914E-04 | global batch size: 512 | lm loss: 2.343114E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.013 | TFLOPs: 23.47 | +63: iteration 10990/ 73814 | consumed samples: 5626880 | consumed tokens: 11523850240 | elapsed time per iteration (s): 2.23 | learning rate: 1.914E-04 | global batch size: 512 | lm loss: 2.341659E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.093 | TFLOPs: 23.58 | +63: iteration 11000/ 73814 | consumed samples: 5632000 | consumed tokens: 11534336000 | elapsed time per iteration (s): 2.23 | learning rate: 1.914E-04 | global batch size: 512 | lm loss: 2.321405E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.880 | TFLOPs: 23.67 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 11000 | lm loss value: 2.295531E+00 | lm loss PPL: 9.929710E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 11010/ 73814 | consumed samples: 5637120 | consumed tokens: 11544821760 | elapsed time per iteration (s): 2.30 | learning rate: 1.914E-04 | global batch size: 512 | lm loss: 2.317060E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.276 | TFLOPs: 22.88 | +63: iteration 11020/ 73814 | consumed samples: 5642240 | consumed tokens: 11555307520 | elapsed time per iteration (s): 2.23 | learning rate: 1.913E-04 | global batch size: 512 | lm loss: 2.312231E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.035 | TFLOPs: 23.68 | +63: iteration 11030/ 73814 | consumed samples: 5647360 | consumed tokens: 11565793280 | elapsed time per iteration (s): 2.23 | learning rate: 1.913E-04 | global batch size: 512 | lm loss: 2.305017E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.467 | TFLOPs: 23.62 | +63: iteration 11040/ 73814 | consumed samples: 5652480 | consumed tokens: 11576279040 | elapsed time per iteration (s): 2.29 | learning rate: 1.913E-04 | global batch size: 512 | lm loss: 2.318272E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.220 | TFLOPs: 22.98 | +63: iteration 11050/ 73814 | consumed samples: 5657600 | consumed tokens: 11586764800 | elapsed time per iteration (s): 2.25 | learning rate: 1.913E-04 | global batch size: 512 | lm loss: 2.314353E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.865 | TFLOPs: 23.46 | +63: iteration 11060/ 73814 | consumed samples: 5662720 | consumed tokens: 11597250560 | elapsed time per iteration (s): 2.23 | learning rate: 1.913E-04 | global batch size: 512 | lm loss: 2.303586E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.566 | TFLOPs: 23.63 | +63: iteration 11070/ 73814 | consumed samples: 5667840 | consumed tokens: 11607736320 | elapsed time per iteration (s): 2.23 | learning rate: 1.913E-04 | global batch size: 512 | lm loss: 2.319815E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.697 | TFLOPs: 23.65 | +63: iteration 11080/ 73814 | consumed samples: 5672960 | consumed tokens: 11618222080 | elapsed time per iteration (s): 2.26 | learning rate: 1.913E-04 | global batch size: 512 | lm loss: 2.303759E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.456 | TFLOPs: 23.31 | +63: iteration 11090/ 73814 | consumed samples: 5678080 | consumed tokens: 11628707840 | elapsed time per iteration (s): 2.27 | learning rate: 1.912E-04 | global batch size: 512 | lm loss: 2.306792E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.175 | TFLOPs: 23.18 | +63: iteration 11100/ 73814 | consumed samples: 5683200 | consumed tokens: 11639193600 | elapsed time per iteration (s): 2.23 | learning rate: 1.912E-04 | global batch size: 512 | lm loss: 2.322407E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.636 | TFLOPs: 23.64 | +63: iteration 11110/ 73814 | consumed samples: 5688320 | consumed tokens: 11649679360 | elapsed time per iteration (s): 2.23 | learning rate: 1.912E-04 | global batch size: 512 | lm loss: 2.320359E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.537 | TFLOPs: 23.63 | +63: iteration 11120/ 73814 | consumed samples: 5693440 | consumed tokens: 11660165120 | elapsed time per iteration (s): 2.24 | learning rate: 1.912E-04 | global batch size: 512 | lm loss: 2.331126E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.788 | TFLOPs: 23.55 | +63: iteration 11130/ 73814 | consumed samples: 5698560 | consumed tokens: 11670650880 | elapsed time per iteration (s): 2.23 | learning rate: 1.912E-04 | global batch size: 512 | lm loss: 2.335414E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.855 | TFLOPs: 23.66 | +63: iteration 11140/ 73814 | consumed samples: 5703680 | consumed tokens: 11681136640 | elapsed time per iteration (s): 2.26 | learning rate: 1.912E-04 | global batch size: 512 | lm loss: 2.348224E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.535 | TFLOPs: 23.32 | +63: iteration 11150/ 73814 | consumed samples: 5708800 | consumed tokens: 11691622400 | elapsed time per iteration (s): 2.24 | learning rate: 1.911E-04 | global batch size: 512 | lm loss: 2.324199E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.933 | TFLOPs: 23.57 | +63: iteration 11160/ 73814 | consumed samples: 5713920 | consumed tokens: 11702108160 | elapsed time per iteration (s): 2.23 | learning rate: 1.911E-04 | global batch size: 512 | lm loss: 2.335030E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.005 | TFLOPs: 23.68 | +63: iteration 11170/ 73814 | consumed samples: 5719040 | consumed tokens: 11712593920 | elapsed time per iteration (s): 2.27 | learning rate: 1.911E-04 | global batch size: 512 | lm loss: 2.314105E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.047 | TFLOPs: 23.27 | +63: iteration 11180/ 73814 | consumed samples: 5724160 | consumed tokens: 11723079680 | elapsed time per iteration (s): 2.25 | learning rate: 1.911E-04 | global batch size: 512 | lm loss: 2.352768E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.002 | TFLOPs: 23.47 | +63: iteration 11190/ 73814 | consumed samples: 5729280 | consumed tokens: 11733565440 | elapsed time per iteration (s): 2.23 | learning rate: 1.911E-04 | global batch size: 512 | lm loss: 2.329029E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.493 | TFLOPs: 23.63 | +63: iteration 11200/ 73814 | consumed samples: 5734400 | consumed tokens: 11744051200 | elapsed time per iteration (s): 2.23 | learning rate: 1.910E-04 | global batch size: 512 | lm loss: 3.893810E+00 | grad norm: 15.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.330 | TFLOPs: 23.61 | +63: iteration 11210/ 73814 | consumed samples: 5739520 | consumed tokens: 11754536960 | elapsed time per iteration (s): 2.26 | learning rate: 1.910E-04 | global batch size: 512 | lm loss: 8.425855E+00 | grad norm: 2.728 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.782 | TFLOPs: 23.35 | +63: iteration 11220/ 73814 | consumed samples: 5744640 | consumed tokens: 11765022720 | elapsed time per iteration (s): 2.25 | learning rate: 1.910E-04 | global batch size: 512 | lm loss: 7.655738E+00 | grad norm: 1.913 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.995 | TFLOPs: 23.47 | +63: iteration 11230/ 73814 | consumed samples: 5749760 | consumed tokens: 11775508480 | elapsed time per iteration (s): 2.26 | learning rate: 1.910E-04 | global batch size: 512 | lm loss: 7.058557E+00 | grad norm: 1.430 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.724 | TFLOPs: 23.34 | +63: iteration 11240/ 73814 | consumed samples: 5754880 | consumed tokens: 11785994240 | elapsed time per iteration (s): 2.25 | learning rate: 1.910E-04 | global batch size: 512 | lm loss: 6.637472E+00 | grad norm: 1.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.506 | TFLOPs: 23.42 | +63: iteration 11250/ 73814 | consumed samples: 5760000 | consumed tokens: 11796480000 | elapsed time per iteration (s): 2.24 | learning rate: 1.910E-04 | global batch size: 512 | lm loss: 6.416357E+00 | grad norm: 1.381 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.392 | TFLOPs: 23.51 | +63: iteration 11260/ 73814 | consumed samples: 5765120 | consumed tokens: 11806965760 | elapsed time per iteration (s): 2.24 | learning rate: 1.909E-04 | global batch size: 512 | lm loss: 6.169735E+00 | grad norm: 0.919 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.331 | TFLOPs: 23.51 | +63: iteration 11270/ 73814 | consumed samples: 5770240 | consumed tokens: 11817451520 | elapsed time per iteration (s): 2.26 | learning rate: 1.909E-04 | global batch size: 512 | lm loss: 5.880679E+00 | grad norm: 0.924 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.979 | TFLOPs: 23.37 | +63: iteration 11280/ 73814 | consumed samples: 5775360 | consumed tokens: 11827937280 | elapsed time per iteration (s): 2.29 | learning rate: 1.909E-04 | global batch size: 512 | lm loss: 5.536455E+00 | grad norm: 1.055 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.838 | TFLOPs: 23.04 | +63: iteration 11290/ 73814 | consumed samples: 5780480 | consumed tokens: 11838423040 | elapsed time per iteration (s): 2.30 | learning rate: 1.909E-04 | global batch size: 512 | lm loss: 5.152246E+00 | grad norm: 1.571 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.911 | TFLOPs: 22.95 | +63: iteration 11300/ 73814 | consumed samples: 5785600 | consumed tokens: 11848908800 | elapsed time per iteration (s): 2.27 | learning rate: 1.909E-04 | global batch size: 512 | lm loss: 4.360960E+00 | grad norm: 2.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.888 | TFLOPs: 23.25 | +63: iteration 11310/ 73814 | consumed samples: 5790720 | consumed tokens: 11859394560 | elapsed time per iteration (s): 2.27 | learning rate: 1.909E-04 | global batch size: 512 | lm loss: 3.622615E+00 | grad norm: 0.797 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.744 | TFLOPs: 23.24 | +63: iteration 11320/ 73814 | consumed samples: 5795840 | consumed tokens: 11869880320 | elapsed time per iteration (s): 2.27 | learning rate: 1.908E-04 | global batch size: 512 | lm loss: 3.162132E+00 | grad norm: 1.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.947 | TFLOPs: 23.26 | +63: iteration 11330/ 73814 | consumed samples: 5800960 | consumed tokens: 11880366080 | elapsed time per iteration (s): 2.25 | learning rate: 1.908E-04 | global batch size: 512 | lm loss: 2.905637E+00 | grad norm: 1.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.656 | TFLOPs: 23.44 | +63: iteration 11340/ 73814 | consumed samples: 5806080 | consumed tokens: 11890851840 | elapsed time per iteration (s): 2.24 | learning rate: 1.908E-04 | global batch size: 512 | lm loss: 2.695418E+00 | grad norm: 0.471 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.966 | TFLOPs: 23.57 | +63: iteration 11350/ 73814 | consumed samples: 5811200 | consumed tokens: 11901337600 | elapsed time per iteration (s): 2.27 | learning rate: 1.908E-04 | global batch size: 512 | lm loss: 2.564061E+00 | grad norm: 0.495 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.427 | TFLOPs: 23.21 | +63: iteration 11360/ 73814 | consumed samples: 5816320 | consumed tokens: 11911823360 | elapsed time per iteration (s): 2.23 | learning rate: 1.908E-04 | global batch size: 512 | lm loss: 2.517565E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.558 | TFLOPs: 23.63 | +63: iteration 11370/ 73814 | consumed samples: 5821440 | consumed tokens: 11922309120 | elapsed time per iteration (s): 2.24 | learning rate: 1.908E-04 | global batch size: 512 | lm loss: 2.450111E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.519 | TFLOPs: 23.52 | +63: iteration 11380/ 73814 | consumed samples: 5826560 | consumed tokens: 11932794880 | elapsed time per iteration (s): 2.25 | learning rate: 1.907E-04 | global batch size: 512 | lm loss: 2.415194E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.772 | TFLOPs: 23.45 | +63: iteration 11390/ 73814 | consumed samples: 5831680 | consumed tokens: 11943280640 | elapsed time per iteration (s): 2.24 | learning rate: 1.907E-04 | global batch size: 512 | lm loss: 2.398043E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.316 | TFLOPs: 23.50 | +63: iteration 11400/ 73814 | consumed samples: 5836800 | consumed tokens: 11953766400 | elapsed time per iteration (s): 2.23 | learning rate: 1.907E-04 | global batch size: 512 | lm loss: 2.396192E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.658 | TFLOPs: 23.64 | +63: iteration 11410/ 73814 | consumed samples: 5841920 | consumed tokens: 11964252160 | elapsed time per iteration (s): 2.24 | learning rate: 1.907E-04 | global batch size: 512 | lm loss: 2.392848E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.535 | TFLOPs: 23.53 | +63: iteration 11420/ 73814 | consumed samples: 5847040 | consumed tokens: 11974737920 | elapsed time per iteration (s): 2.22 | learning rate: 1.907E-04 | global batch size: 512 | lm loss: 2.390963E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.251 | TFLOPs: 23.70 | +63: iteration 11430/ 73814 | consumed samples: 5852160 | consumed tokens: 11985223680 | elapsed time per iteration (s): 2.23 | learning rate: 1.907E-04 | global batch size: 512 | lm loss: 2.377236E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.445 | TFLOPs: 23.62 | +63: iteration 11440/ 73814 | consumed samples: 5857280 | consumed tokens: 11995709440 | elapsed time per iteration (s): 2.23 | learning rate: 1.906E-04 | global batch size: 512 | lm loss: 2.375863E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.721 | TFLOPs: 23.65 | +63: iteration 11450/ 73814 | consumed samples: 5862400 | consumed tokens: 12006195200 | elapsed time per iteration (s): 2.22 | learning rate: 1.906E-04 | global batch size: 512 | lm loss: 2.356289E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.202 | TFLOPs: 23.70 | +63: iteration 11460/ 73814 | consumed samples: 5867520 | consumed tokens: 12016680960 | elapsed time per iteration (s): 2.23 | learning rate: 1.906E-04 | global batch size: 512 | lm loss: 2.373834E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.489 | TFLOPs: 23.62 | +63: iteration 11470/ 73814 | consumed samples: 5872640 | consumed tokens: 12027166720 | elapsed time per iteration (s): 2.23 | learning rate: 1.906E-04 | global batch size: 512 | lm loss: 2.349480E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.079 | TFLOPs: 23.69 | +63: iteration 11480/ 73814 | consumed samples: 5877760 | consumed tokens: 12037652480 | elapsed time per iteration (s): 2.23 | learning rate: 1.906E-04 | global batch size: 512 | lm loss: 2.353876E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.826 | TFLOPs: 23.66 | +63: iteration 11490/ 73814 | consumed samples: 5882880 | consumed tokens: 12048138240 | elapsed time per iteration (s): 2.23 | learning rate: 1.906E-04 | global batch size: 512 | lm loss: 2.349720E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.122 | TFLOPs: 23.59 | +63: iteration 11500/ 73814 | consumed samples: 5888000 | consumed tokens: 12058624000 | elapsed time per iteration (s): 2.23 | learning rate: 1.905E-04 | global batch size: 512 | lm loss: 2.351199E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.215 | TFLOPs: 23.60 | +63: iteration 11510/ 73814 | consumed samples: 5893120 | consumed tokens: 12069109760 | elapsed time per iteration (s): 2.23 | learning rate: 1.905E-04 | global batch size: 512 | lm loss: 2.353934E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.351 | TFLOPs: 23.61 | +63: iteration 11520/ 73814 | consumed samples: 5898240 | consumed tokens: 12079595520 | elapsed time per iteration (s): 2.23 | learning rate: 1.905E-04 | global batch size: 512 | lm loss: 2.367454E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.754 | TFLOPs: 23.65 | +63: iteration 11530/ 73814 | consumed samples: 5903360 | consumed tokens: 12090081280 | elapsed time per iteration (s): 2.24 | learning rate: 1.905E-04 | global batch size: 512 | lm loss: 2.324876E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.603 | TFLOPs: 23.53 | +63: iteration 11540/ 73814 | consumed samples: 5908480 | consumed tokens: 12100567040 | elapsed time per iteration (s): 2.25 | learning rate: 1.905E-04 | global batch size: 512 | lm loss: 2.338945E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.218 | TFLOPs: 23.39 | +63: iteration 11550/ 73814 | consumed samples: 5913600 | consumed tokens: 12111052800 | elapsed time per iteration (s): 2.24 | learning rate: 1.905E-04 | global batch size: 512 | lm loss: 2.352134E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.960 | TFLOPs: 23.57 | +63: iteration 11560/ 73814 | consumed samples: 5918720 | consumed tokens: 12121538560 | elapsed time per iteration (s): 2.23 | learning rate: 1.904E-04 | global batch size: 512 | lm loss: 2.308576E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.771 | TFLOPs: 23.65 | +63: iteration 11570/ 73814 | consumed samples: 5923840 | consumed tokens: 12132024320 | elapsed time per iteration (s): 2.23 | learning rate: 1.904E-04 | global batch size: 512 | lm loss: 2.342340E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.508 | TFLOPs: 23.63 | +63: iteration 11580/ 73814 | consumed samples: 5928960 | consumed tokens: 12142510080 | elapsed time per iteration (s): 2.23 | learning rate: 1.904E-04 | global batch size: 512 | lm loss: 2.327102E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.032 | TFLOPs: 23.68 | +63: iteration 11590/ 73814 | consumed samples: 5934080 | consumed tokens: 12152995840 | elapsed time per iteration (s): 2.24 | learning rate: 1.904E-04 | global batch size: 512 | lm loss: 2.330302E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.051 | TFLOPs: 23.58 | +63: iteration 11600/ 73814 | consumed samples: 5939200 | consumed tokens: 12163481600 | elapsed time per iteration (s): 2.25 | learning rate: 1.904E-04 | global batch size: 512 | lm loss: 2.345116E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.563 | TFLOPs: 23.43 | +63: iteration 11610/ 73814 | consumed samples: 5944320 | consumed tokens: 12173967360 | elapsed time per iteration (s): 2.26 | learning rate: 1.903E-04 | global batch size: 512 | lm loss: 2.329795E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.712 | TFLOPs: 23.34 | +63: iteration 11620/ 73814 | consumed samples: 5949440 | consumed tokens: 12184453120 | elapsed time per iteration (s): 2.31 | learning rate: 1.903E-04 | global batch size: 512 | lm loss: 2.348823E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.521 | TFLOPs: 22.80 | +63: iteration 11630/ 73814 | consumed samples: 5954560 | consumed tokens: 12194938880 | elapsed time per iteration (s): 2.31 | learning rate: 1.903E-04 | global batch size: 512 | lm loss: 2.312769E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.028 | TFLOPs: 22.86 | +63: iteration 11640/ 73814 | consumed samples: 5959680 | consumed tokens: 12205424640 | elapsed time per iteration (s): 2.23 | learning rate: 1.903E-04 | global batch size: 512 | lm loss: 2.339883E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.721 | TFLOPs: 23.65 | +63: iteration 11650/ 73814 | consumed samples: 5964800 | consumed tokens: 12215910400 | elapsed time per iteration (s): 2.40 | learning rate: 1.903E-04 | global batch size: 512 | lm loss: 2.324089E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.035 | TFLOPs: 21.93 | +63: iteration 11660/ 73814 | consumed samples: 5969920 | consumed tokens: 12226396160 | elapsed time per iteration (s): 2.29 | learning rate: 1.903E-04 | global batch size: 512 | lm loss: 2.336277E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.624 | TFLOPs: 23.02 | +63: iteration 11670/ 73814 | consumed samples: 5975040 | consumed tokens: 12236881920 | elapsed time per iteration (s): 2.40 | learning rate: 1.902E-04 | global batch size: 512 | lm loss: 2.329716E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.214 | TFLOPs: 21.95 | +63: iteration 11680/ 73814 | consumed samples: 5980160 | consumed tokens: 12247367680 | elapsed time per iteration (s): 2.36 | learning rate: 1.902E-04 | global batch size: 512 | lm loss: 2.333617E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.302 | TFLOPs: 22.37 | +63: iteration 11690/ 73814 | consumed samples: 5985280 | consumed tokens: 12257853440 | elapsed time per iteration (s): 2.52 | learning rate: 1.902E-04 | global batch size: 512 | lm loss: 2.333783E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 203.064 | TFLOPs: 20.90 | +63: iteration 11700/ 73814 | consumed samples: 5990400 | consumed tokens: 12268339200 | elapsed time per iteration (s): 2.32 | learning rate: 1.902E-04 | global batch size: 512 | lm loss: 2.320069E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.701 | TFLOPs: 22.72 | +63: iteration 11710/ 73814 | consumed samples: 5995520 | consumed tokens: 12278824960 | elapsed time per iteration (s): 2.24 | learning rate: 1.902E-04 | global batch size: 512 | lm loss: 2.327172E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.326 | TFLOPs: 23.51 | +63: iteration 11720/ 73814 | consumed samples: 6000640 | consumed tokens: 12289310720 | elapsed time per iteration (s): 2.29 | learning rate: 1.902E-04 | global batch size: 512 | lm loss: 2.326547E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.111 | TFLOPs: 22.97 | +63: iteration 11730/ 73814 | consumed samples: 6005760 | consumed tokens: 12299796480 | elapsed time per iteration (s): 2.59 | learning rate: 1.901E-04 | global batch size: 512 | lm loss: 2.330671E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 197.731 | TFLOPs: 20.36 | +63: iteration 11740/ 73814 | consumed samples: 6010880 | consumed tokens: 12310282240 | elapsed time per iteration (s): 2.36 | learning rate: 1.901E-04 | global batch size: 512 | lm loss: 2.317817E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.779 | TFLOPs: 22.32 | +63: iteration 11750/ 73814 | consumed samples: 6016000 | consumed tokens: 12320768000 | elapsed time per iteration (s): 2.30 | learning rate: 1.901E-04 | global batch size: 512 | lm loss: 2.324717E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.692 | TFLOPs: 22.93 | +63: iteration 11760/ 73814 | consumed samples: 6021120 | consumed tokens: 12331253760 | elapsed time per iteration (s): 2.25 | learning rate: 1.901E-04 | global batch size: 512 | lm loss: 2.319159E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.299 | TFLOPs: 23.40 | +63: iteration 11770/ 73814 | consumed samples: 6026240 | consumed tokens: 12341739520 | elapsed time per iteration (s): 2.22 | learning rate: 1.901E-04 | global batch size: 512 | lm loss: 2.331721E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.245 | TFLOPs: 23.70 | +63: iteration 11780/ 73814 | consumed samples: 6031360 | consumed tokens: 12352225280 | elapsed time per iteration (s): 2.25 | learning rate: 1.900E-04 | global batch size: 512 | lm loss: 2.339297E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.799 | TFLOPs: 23.45 | +63: iteration 11790/ 73814 | consumed samples: 6036480 | consumed tokens: 12362711040 | elapsed time per iteration (s): 2.28 | learning rate: 1.900E-04 | global batch size: 512 | lm loss: 2.318416E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.860 | TFLOPs: 23.15 | +63: iteration 11800/ 73814 | consumed samples: 6041600 | consumed tokens: 12373196800 | elapsed time per iteration (s): 2.26 | learning rate: 1.900E-04 | global batch size: 512 | lm loss: 2.318064E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.484 | TFLOPs: 23.32 | +63: iteration 11810/ 73814 | consumed samples: 6046720 | consumed tokens: 12383682560 | elapsed time per iteration (s): 2.27 | learning rate: 1.900E-04 | global batch size: 512 | lm loss: 2.330643E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.643 | TFLOPs: 23.23 | +63: iteration 11820/ 73814 | consumed samples: 6051840 | consumed tokens: 12394168320 | elapsed time per iteration (s): 2.41 | learning rate: 1.900E-04 | global batch size: 512 | lm loss: 2.312863E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.401 | TFLOPs: 21.87 | +63: iteration 11830/ 73814 | consumed samples: 6056960 | consumed tokens: 12404654080 | elapsed time per iteration (s): 2.23 | learning rate: 1.900E-04 | global batch size: 512 | lm loss: 2.327100E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.142 | TFLOPs: 23.59 | +63: iteration 11840/ 73814 | consumed samples: 6062080 | consumed tokens: 12415139840 | elapsed time per iteration (s): 2.25 | learning rate: 1.899E-04 | global batch size: 512 | lm loss: 2.323448E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.284 | TFLOPs: 23.40 | +63: iteration 11850/ 73814 | consumed samples: 6067200 | consumed tokens: 12425625600 | elapsed time per iteration (s): 2.25 | learning rate: 1.899E-04 | global batch size: 512 | lm loss: 2.311898E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.079 | TFLOPs: 23.38 | +63: iteration 11860/ 73814 | consumed samples: 6072320 | consumed tokens: 12436111360 | elapsed time per iteration (s): 2.23 | learning rate: 1.899E-04 | global batch size: 512 | lm loss: 2.320917E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.401 | TFLOPs: 23.62 | +63: iteration 11870/ 73814 | consumed samples: 6077440 | consumed tokens: 12446597120 | elapsed time per iteration (s): 2.23 | learning rate: 1.899E-04 | global batch size: 512 | lm loss: 2.302584E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.215 | TFLOPs: 23.60 | +63: iteration 11880/ 73814 | consumed samples: 6082560 | consumed tokens: 12457082880 | elapsed time per iteration (s): 2.24 | learning rate: 1.899E-04 | global batch size: 512 | lm loss: 2.320019E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.351 | TFLOPs: 23.51 | +63: iteration 11890/ 73814 | consumed samples: 6087680 | consumed tokens: 12467568640 | elapsed time per iteration (s): 2.26 | learning rate: 1.899E-04 | global batch size: 512 | lm loss: 2.308557E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.461 | TFLOPs: 23.31 | +63: iteration 11900/ 73814 | consumed samples: 6092800 | consumed tokens: 12478054400 | elapsed time per iteration (s): 2.30 | learning rate: 1.898E-04 | global batch size: 512 | lm loss: 2.325126E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.469 | TFLOPs: 22.90 | +63: iteration 11910/ 73814 | consumed samples: 6097920 | consumed tokens: 12488540160 | elapsed time per iteration (s): 2.24 | learning rate: 1.898E-04 | global batch size: 512 | lm loss: 2.301128E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.684 | TFLOPs: 23.54 | +63: iteration 11920/ 73814 | consumed samples: 6103040 | consumed tokens: 12499025920 | elapsed time per iteration (s): 2.23 | learning rate: 1.898E-04 | global batch size: 512 | lm loss: 2.306763E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.111 | TFLOPs: 23.59 | +63: iteration 11930/ 73814 | consumed samples: 6108160 | consumed tokens: 12509511680 | elapsed time per iteration (s): 2.30 | learning rate: 1.898E-04 | global batch size: 512 | lm loss: 2.302435E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.648 | TFLOPs: 22.92 | +63: iteration 11940/ 73814 | consumed samples: 6113280 | consumed tokens: 12519997440 | elapsed time per iteration (s): 2.26 | learning rate: 1.898E-04 | global batch size: 512 | lm loss: 2.333486E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.966 | TFLOPs: 23.37 | +63: iteration 11950/ 73814 | consumed samples: 6118400 | consumed tokens: 12530483200 | elapsed time per iteration (s): 2.25 | learning rate: 1.897E-04 | global batch size: 512 | lm loss: 2.308919E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.619 | TFLOPs: 23.43 | +63: iteration 11960/ 73814 | consumed samples: 6123520 | consumed tokens: 12540968960 | elapsed time per iteration (s): 2.23 | learning rate: 1.897E-04 | global batch size: 512 | lm loss: 2.328579E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.779 | TFLOPs: 23.65 | +63: iteration 11970/ 73814 | consumed samples: 6128640 | consumed tokens: 12551454720 | elapsed time per iteration (s): 2.27 | learning rate: 1.897E-04 | global batch size: 512 | lm loss: 2.328238E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.636 | TFLOPs: 23.23 | +63: iteration 11980/ 73814 | consumed samples: 6133760 | consumed tokens: 12561940480 | elapsed time per iteration (s): 2.23 | learning rate: 1.897E-04 | global batch size: 512 | lm loss: 2.316047E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.150 | TFLOPs: 23.59 | +63: iteration 11990/ 73814 | consumed samples: 6138880 | consumed tokens: 12572426240 | elapsed time per iteration (s): 2.49 | learning rate: 1.897E-04 | global batch size: 512 | lm loss: 2.304049E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.363 | TFLOPs: 21.14 | + 0: [2022-12-01 19:27:02,165] [INFO] [logging.py:68:log_dist] [Rank 0] step=12000, skipped=0, lr=[0.00018965621138466397, 0.00018965621138466397, 0.00018965621138466397], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 12000/ 73814 | consumed samples: 6144000 | consumed tokens: 12582912000 | elapsed time per iteration (s): 2.29 | learning rate: 1.897E-04 | global batch size: 512 | lm loss: 2.330812E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.466 | TFLOPs: 23.00 | + 0: steps: 12000 loss: 2.3529 iter time (s): 2.255 samples/sec: 227.069 +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 12000 | lm loss value: 2.246625E+00 | lm loss PPL: 9.455768E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 12010/ 73814 | consumed samples: 6149120 | consumed tokens: 12593397760 | elapsed time per iteration (s): 2.32 | learning rate: 1.896E-04 | global batch size: 512 | lm loss: 2.310658E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.514 | TFLOPs: 22.70 | +63: iteration 12020/ 73814 | consumed samples: 6154240 | consumed tokens: 12603883520 | elapsed time per iteration (s): 2.32 | learning rate: 1.896E-04 | global batch size: 512 | lm loss: 2.297065E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.553 | TFLOPs: 22.70 | +63: iteration 12030/ 73814 | consumed samples: 6159360 | consumed tokens: 12614369280 | elapsed time per iteration (s): 2.28 | learning rate: 1.896E-04 | global batch size: 512 | lm loss: 2.324677E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.494 | TFLOPs: 23.11 | +63: iteration 12040/ 73814 | consumed samples: 6164480 | consumed tokens: 12624855040 | elapsed time per iteration (s): 2.23 | learning rate: 1.896E-04 | global batch size: 512 | lm loss: 2.301252E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.844 | TFLOPs: 23.66 | +63: iteration 12050/ 73814 | consumed samples: 6169600 | consumed tokens: 12635340800 | elapsed time per iteration (s): 2.23 | learning rate: 1.896E-04 | global batch size: 512 | lm loss: 2.307470E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.150 | TFLOPs: 23.59 | +63: iteration 12060/ 73814 | consumed samples: 6174720 | consumed tokens: 12645826560 | elapsed time per iteration (s): 2.23 | learning rate: 1.895E-04 | global batch size: 512 | lm loss: 2.285180E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.427 | TFLOPs: 23.62 | +63: iteration 12070/ 73814 | consumed samples: 6179840 | consumed tokens: 12656312320 | elapsed time per iteration (s): 2.24 | learning rate: 1.895E-04 | global batch size: 512 | lm loss: 2.297468E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.231 | TFLOPs: 23.50 | +63: iteration 12080/ 73814 | consumed samples: 6184960 | consumed tokens: 12666798080 | elapsed time per iteration (s): 2.27 | learning rate: 1.895E-04 | global batch size: 512 | lm loss: 2.300235E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.505 | TFLOPs: 23.21 | +63: iteration 12090/ 73814 | consumed samples: 6190080 | consumed tokens: 12677283840 | elapsed time per iteration (s): 2.22 | learning rate: 1.895E-04 | global batch size: 512 | lm loss: 2.322384E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.242 | TFLOPs: 23.70 | +63: iteration 12100/ 73814 | consumed samples: 6195200 | consumed tokens: 12687769600 | elapsed time per iteration (s): 2.25 | learning rate: 1.895E-04 | global batch size: 512 | lm loss: 2.312201E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.831 | TFLOPs: 23.45 | +63: iteration 12110/ 73814 | consumed samples: 6200320 | consumed tokens: 12698255360 | elapsed time per iteration (s): 2.24 | learning rate: 1.895E-04 | global batch size: 512 | lm loss: 2.284837E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.244 | TFLOPs: 23.50 | +63: iteration 12120/ 73814 | consumed samples: 6205440 | consumed tokens: 12708741120 | elapsed time per iteration (s): 2.24 | learning rate: 1.894E-04 | global batch size: 512 | lm loss: 2.306027E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.003 | TFLOPs: 23.57 | +63: iteration 12130/ 73814 | consumed samples: 6210560 | consumed tokens: 12719226880 | elapsed time per iteration (s): 2.25 | learning rate: 1.894E-04 | global batch size: 512 | lm loss: 2.300065E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.979 | TFLOPs: 23.47 | +63: iteration 12140/ 73814 | consumed samples: 6215680 | consumed tokens: 12729712640 | elapsed time per iteration (s): 2.23 | learning rate: 1.894E-04 | global batch size: 512 | lm loss: 2.310812E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.293 | TFLOPs: 23.60 | +63: iteration 12150/ 73814 | consumed samples: 6220800 | consumed tokens: 12740198400 | elapsed time per iteration (s): 2.24 | learning rate: 1.894E-04 | global batch size: 512 | lm loss: 2.335243E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.555 | TFLOPs: 23.53 | +63: iteration 12160/ 73814 | consumed samples: 6225920 | consumed tokens: 12750684160 | elapsed time per iteration (s): 2.26 | learning rate: 1.894E-04 | global batch size: 512 | lm loss: 2.304946E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.376 | TFLOPs: 23.30 | +63: iteration 12170/ 73814 | consumed samples: 6231040 | consumed tokens: 12761169920 | elapsed time per iteration (s): 2.23 | learning rate: 1.893E-04 | global batch size: 512 | lm loss: 2.319456E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.456 | TFLOPs: 23.62 | +63: iteration 12180/ 73814 | consumed samples: 6236160 | consumed tokens: 12771655680 | elapsed time per iteration (s): 2.24 | learning rate: 1.893E-04 | global batch size: 512 | lm loss: 2.290770E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.556 | TFLOPs: 23.53 | +63: iteration 12190/ 73814 | consumed samples: 6241280 | consumed tokens: 12782141440 | elapsed time per iteration (s): 2.23 | learning rate: 1.893E-04 | global batch size: 512 | lm loss: 2.296506E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.380 | TFLOPs: 23.61 | +63: iteration 12200/ 73814 | consumed samples: 6246400 | consumed tokens: 12792627200 | elapsed time per iteration (s): 2.25 | learning rate: 1.893E-04 | global batch size: 512 | lm loss: 2.321611E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.762 | TFLOPs: 23.45 | +63: iteration 12210/ 73814 | consumed samples: 6251520 | consumed tokens: 12803112960 | elapsed time per iteration (s): 2.23 | learning rate: 1.893E-04 | global batch size: 512 | lm loss: 2.328786E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.511 | TFLOPs: 23.63 | +63: iteration 12220/ 73814 | consumed samples: 6256640 | consumed tokens: 12813598720 | elapsed time per iteration (s): 2.27 | learning rate: 1.893E-04 | global batch size: 512 | lm loss: 2.309590E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.344 | TFLOPs: 23.20 | +63: iteration 12230/ 73814 | consumed samples: 6261760 | consumed tokens: 12824084480 | elapsed time per iteration (s): 2.23 | learning rate: 1.892E-04 | global batch size: 512 | lm loss: 2.319596E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.855 | TFLOPs: 23.66 | +63: iteration 12240/ 73814 | consumed samples: 6266880 | consumed tokens: 12834570240 | elapsed time per iteration (s): 2.25 | learning rate: 1.892E-04 | global batch size: 512 | lm loss: 2.323145E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.440 | TFLOPs: 23.41 | +63: iteration 12250/ 73814 | consumed samples: 6272000 | consumed tokens: 12845056000 | elapsed time per iteration (s): 2.25 | learning rate: 1.892E-04 | global batch size: 512 | lm loss: 2.317336E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.323 | TFLOPs: 23.40 | +63: iteration 12260/ 73814 | consumed samples: 6277120 | consumed tokens: 12855541760 | elapsed time per iteration (s): 2.24 | learning rate: 1.892E-04 | global batch size: 512 | lm loss: 2.308538E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.375 | TFLOPs: 23.51 | +63: iteration 12270/ 73814 | consumed samples: 6282240 | consumed tokens: 12866027520 | elapsed time per iteration (s): 2.23 | learning rate: 1.892E-04 | global batch size: 512 | lm loss: 2.318266E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.978 | TFLOPs: 23.68 | +63: iteration 12280/ 73814 | consumed samples: 6287360 | consumed tokens: 12876513280 | elapsed time per iteration (s): 2.23 | learning rate: 1.891E-04 | global batch size: 512 | lm loss: 2.291937E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.865 | TFLOPs: 23.66 | +63: iteration 12290/ 73814 | consumed samples: 6292480 | consumed tokens: 12886999040 | elapsed time per iteration (s): 2.26 | learning rate: 1.891E-04 | global batch size: 512 | lm loss: 2.284977E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.678 | TFLOPs: 23.34 | +63: iteration 12300/ 73814 | consumed samples: 6297600 | consumed tokens: 12897484800 | elapsed time per iteration (s): 2.23 | learning rate: 1.891E-04 | global batch size: 512 | lm loss: 2.311936E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.962 | TFLOPs: 23.67 | +63: iteration 12310/ 73814 | consumed samples: 6302720 | consumed tokens: 12907970560 | elapsed time per iteration (s): 2.23 | learning rate: 1.891E-04 | global batch size: 512 | lm loss: 2.307483E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.748 | TFLOPs: 23.65 | +63: iteration 12320/ 73814 | consumed samples: 6307840 | consumed tokens: 12918456320 | elapsed time per iteration (s): 2.24 | learning rate: 1.891E-04 | global batch size: 512 | lm loss: 2.302147E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.042 | TFLOPs: 23.58 | +63: iteration 12330/ 73814 | consumed samples: 6312960 | consumed tokens: 12928942080 | elapsed time per iteration (s): 2.24 | learning rate: 1.891E-04 | global batch size: 512 | lm loss: 2.307329E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.473 | TFLOPs: 23.52 | +63: iteration 12340/ 73814 | consumed samples: 6318080 | consumed tokens: 12939427840 | elapsed time per iteration (s): 2.25 | learning rate: 1.890E-04 | global batch size: 512 | lm loss: 2.325726E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.464 | TFLOPs: 23.42 | +63: iteration 12350/ 73814 | consumed samples: 6323200 | consumed tokens: 12949913600 | elapsed time per iteration (s): 2.24 | learning rate: 1.890E-04 | global batch size: 512 | lm loss: 2.283771E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.724 | TFLOPs: 23.55 | +63: iteration 12360/ 73814 | consumed samples: 6328320 | consumed tokens: 12960399360 | elapsed time per iteration (s): 2.28 | learning rate: 1.890E-04 | global batch size: 512 | lm loss: 2.309807E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.916 | TFLOPs: 23.15 | +63: iteration 12370/ 73814 | consumed samples: 6333440 | consumed tokens: 12970885120 | elapsed time per iteration (s): 2.26 | learning rate: 1.890E-04 | global batch size: 512 | lm loss: 2.261733E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.234 | TFLOPs: 23.29 | +63: iteration 12380/ 73814 | consumed samples: 6338560 | consumed tokens: 12981370880 | elapsed time per iteration (s): 2.26 | learning rate: 1.890E-04 | global batch size: 512 | lm loss: 2.296510E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.463 | TFLOPs: 23.31 | +63: iteration 12390/ 73814 | consumed samples: 6343680 | consumed tokens: 12991856640 | elapsed time per iteration (s): 2.24 | learning rate: 1.889E-04 | global batch size: 512 | lm loss: 2.298263E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.184 | TFLOPs: 23.49 | +63: iteration 12400/ 73814 | consumed samples: 6348800 | consumed tokens: 13002342400 | elapsed time per iteration (s): 2.25 | learning rate: 1.889E-04 | global batch size: 512 | lm loss: 2.307557E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.299 | TFLOPs: 23.40 | +63: iteration 12410/ 73814 | consumed samples: 6353920 | consumed tokens: 13012828160 | elapsed time per iteration (s): 2.22 | learning rate: 1.889E-04 | global batch size: 512 | lm loss: 2.311091E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.115 | TFLOPs: 23.69 | +63: iteration 12420/ 73814 | consumed samples: 6359040 | consumed tokens: 13023313920 | elapsed time per iteration (s): 2.23 | learning rate: 1.889E-04 | global batch size: 512 | lm loss: 2.285261E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.607 | TFLOPs: 23.64 | +63: iteration 12430/ 73814 | consumed samples: 6364160 | consumed tokens: 13033799680 | elapsed time per iteration (s): 2.25 | learning rate: 1.889E-04 | global batch size: 512 | lm loss: 2.316138E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.109 | TFLOPs: 23.38 | +63: iteration 12440/ 73814 | consumed samples: 6369280 | consumed tokens: 13044285440 | elapsed time per iteration (s): 2.23 | learning rate: 1.888E-04 | global batch size: 512 | lm loss: 2.284705E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.173 | TFLOPs: 23.59 | +63: iteration 12450/ 73814 | consumed samples: 6374400 | consumed tokens: 13054771200 | elapsed time per iteration (s): 2.27 | learning rate: 1.888E-04 | global batch size: 512 | lm loss: 2.292340E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.529 | TFLOPs: 23.22 | +63: iteration 12460/ 73814 | consumed samples: 6379520 | consumed tokens: 13065256960 | elapsed time per iteration (s): 2.24 | learning rate: 1.888E-04 | global batch size: 512 | lm loss: 2.291663E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.956 | TFLOPs: 23.57 | +63: iteration 12470/ 73814 | consumed samples: 6384640 | consumed tokens: 13075742720 | elapsed time per iteration (s): 2.25 | learning rate: 1.888E-04 | global batch size: 512 | lm loss: 2.318699E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.170 | TFLOPs: 23.39 | +63: iteration 12480/ 73814 | consumed samples: 6389760 | consumed tokens: 13086228480 | elapsed time per iteration (s): 2.24 | learning rate: 1.888E-04 | global batch size: 512 | lm loss: 2.306120E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.574 | TFLOPs: 23.53 | +63: iteration 12490/ 73814 | consumed samples: 6394880 | consumed tokens: 13096714240 | elapsed time per iteration (s): 2.24 | learning rate: 1.888E-04 | global batch size: 512 | lm loss: 2.315037E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.444 | TFLOPs: 23.52 | +63: iteration 12500/ 73814 | consumed samples: 6400000 | consumed tokens: 13107200000 | elapsed time per iteration (s): 2.25 | learning rate: 1.887E-04 | global batch size: 512 | lm loss: 2.288127E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.715 | TFLOPs: 23.44 | +63: iteration 12510/ 73814 | consumed samples: 6405120 | consumed tokens: 13117685760 | elapsed time per iteration (s): 2.23 | learning rate: 1.887E-04 | global batch size: 512 | lm loss: 2.310660E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.724 | TFLOPs: 23.65 | +63: iteration 12520/ 73814 | consumed samples: 6410240 | consumed tokens: 13128171520 | elapsed time per iteration (s): 2.23 | learning rate: 1.887E-04 | global batch size: 512 | lm loss: 2.304023E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.613 | TFLOPs: 23.64 | +63: iteration 12530/ 73814 | consumed samples: 6415360 | consumed tokens: 13138657280 | elapsed time per iteration (s): 2.25 | learning rate: 1.887E-04 | global batch size: 512 | lm loss: 2.316924E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.896 | TFLOPs: 23.46 | +63: iteration 12540/ 73814 | consumed samples: 6420480 | consumed tokens: 13149143040 | elapsed time per iteration (s): 2.22 | learning rate: 1.887E-04 | global batch size: 512 | lm loss: 2.278364E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.392 | TFLOPs: 23.72 | +63: iteration 12550/ 73814 | consumed samples: 6425600 | consumed tokens: 13159628800 | elapsed time per iteration (s): 2.25 | learning rate: 1.886E-04 | global batch size: 512 | lm loss: 2.287313E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.413 | TFLOPs: 23.41 | +63: iteration 12560/ 73814 | consumed samples: 6430720 | consumed tokens: 13170114560 | elapsed time per iteration (s): 2.23 | learning rate: 1.886E-04 | global batch size: 512 | lm loss: 2.298581E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.088 | TFLOPs: 23.58 | +63: iteration 12570/ 73814 | consumed samples: 6435840 | consumed tokens: 13180600320 | elapsed time per iteration (s): 2.25 | learning rate: 1.886E-04 | global batch size: 512 | lm loss: 2.308604E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.863 | TFLOPs: 23.46 | +63: iteration 12580/ 73814 | consumed samples: 6440960 | consumed tokens: 13191086080 | elapsed time per iteration (s): 2.23 | learning rate: 1.886E-04 | global batch size: 512 | lm loss: 2.289581E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.370 | TFLOPs: 23.61 | +63: iteration 12590/ 73814 | consumed samples: 6446080 | consumed tokens: 13201571840 | elapsed time per iteration (s): 2.24 | learning rate: 1.886E-04 | global batch size: 512 | lm loss: 2.305499E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.416 | TFLOPs: 23.51 | +63: iteration 12600/ 73814 | consumed samples: 6451200 | consumed tokens: 13212057600 | elapsed time per iteration (s): 2.23 | learning rate: 1.885E-04 | global batch size: 512 | lm loss: 2.264989E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.972 | TFLOPs: 23.67 | +63: iteration 12610/ 73814 | consumed samples: 6456320 | consumed tokens: 13222543360 | elapsed time per iteration (s): 2.23 | learning rate: 1.885E-04 | global batch size: 512 | lm loss: 2.279233E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.278 | TFLOPs: 23.60 | +63: iteration 12620/ 73814 | consumed samples: 6461440 | consumed tokens: 13233029120 | elapsed time per iteration (s): 2.23 | learning rate: 1.885E-04 | global batch size: 512 | lm loss: 2.292369E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.917 | TFLOPs: 23.67 | +63: iteration 12630/ 73814 | consumed samples: 6466560 | consumed tokens: 13243514880 | elapsed time per iteration (s): 2.23 | learning rate: 1.885E-04 | global batch size: 512 | lm loss: 2.306108E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.631 | TFLOPs: 23.64 | +63: iteration 12640/ 73814 | consumed samples: 6471680 | consumed tokens: 13254000640 | elapsed time per iteration (s): 2.25 | learning rate: 1.885E-04 | global batch size: 512 | lm loss: 2.264714E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.607 | TFLOPs: 23.43 | +63: iteration 12650/ 73814 | consumed samples: 6476800 | consumed tokens: 13264486400 | elapsed time per iteration (s): 2.24 | learning rate: 1.885E-04 | global batch size: 512 | lm loss: 2.303053E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.487 | TFLOPs: 23.52 | +63: iteration 12660/ 73814 | consumed samples: 6481920 | consumed tokens: 13274972160 | elapsed time per iteration (s): 2.23 | learning rate: 1.884E-04 | global batch size: 512 | lm loss: 2.302892E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.460 | TFLOPs: 23.62 | +63: iteration 12670/ 73814 | consumed samples: 6487040 | consumed tokens: 13285457920 | elapsed time per iteration (s): 2.23 | learning rate: 1.884E-04 | global batch size: 512 | lm loss: 2.291294E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.142 | TFLOPs: 23.59 | +63: iteration 12680/ 73814 | consumed samples: 6492160 | consumed tokens: 13295943680 | elapsed time per iteration (s): 2.23 | learning rate: 1.884E-04 | global batch size: 512 | lm loss: 2.275397E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.045 | TFLOPs: 23.68 | +63: iteration 12690/ 73814 | consumed samples: 6497280 | consumed tokens: 13306429440 | elapsed time per iteration (s): 2.24 | learning rate: 1.884E-04 | global batch size: 512 | lm loss: 2.271956E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.801 | TFLOPs: 23.55 | +63: iteration 12700/ 73814 | consumed samples: 6502400 | consumed tokens: 13316915200 | elapsed time per iteration (s): 2.26 | learning rate: 1.884E-04 | global batch size: 512 | lm loss: 2.276921E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.817 | TFLOPs: 23.35 | +63: iteration 12710/ 73814 | consumed samples: 6507520 | consumed tokens: 13327400960 | elapsed time per iteration (s): 2.23 | learning rate: 1.883E-04 | global batch size: 512 | lm loss: 2.257510E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.513 | TFLOPs: 23.63 | +63: iteration 12720/ 73814 | consumed samples: 6512640 | consumed tokens: 13337886720 | elapsed time per iteration (s): 2.24 | learning rate: 1.883E-04 | global batch size: 512 | lm loss: 2.292522E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.923 | TFLOPs: 23.57 | +63: iteration 12730/ 73814 | consumed samples: 6517760 | consumed tokens: 13348372480 | elapsed time per iteration (s): 2.24 | learning rate: 1.883E-04 | global batch size: 512 | lm loss: 2.283412E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.074 | TFLOPs: 23.48 | +63: iteration 12740/ 73814 | consumed samples: 6522880 | consumed tokens: 13358858240 | elapsed time per iteration (s): 2.25 | learning rate: 1.883E-04 | global batch size: 512 | lm loss: 2.282735E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.503 | TFLOPs: 23.42 | +63: iteration 12750/ 73814 | consumed samples: 6528000 | consumed tokens: 13369344000 | elapsed time per iteration (s): 2.23 | learning rate: 1.883E-04 | global batch size: 512 | lm loss: 2.287585E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.734 | TFLOPs: 23.65 | +63: iteration 12760/ 73814 | consumed samples: 6533120 | consumed tokens: 13379829760 | elapsed time per iteration (s): 2.23 | learning rate: 1.882E-04 | global batch size: 512 | lm loss: 2.300900E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.555 | TFLOPs: 23.63 | +63: iteration 12770/ 73814 | consumed samples: 6538240 | consumed tokens: 13390315520 | elapsed time per iteration (s): 2.23 | learning rate: 1.882E-04 | global batch size: 512 | lm loss: 2.295681E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.210 | TFLOPs: 23.60 | +63: iteration 12780/ 73814 | consumed samples: 6543360 | consumed tokens: 13400801280 | elapsed time per iteration (s): 2.23 | learning rate: 1.882E-04 | global batch size: 512 | lm loss: 2.303437E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.473 | TFLOPs: 23.62 | +63: iteration 12790/ 73814 | consumed samples: 6548480 | consumed tokens: 13411287040 | elapsed time per iteration (s): 2.23 | learning rate: 1.882E-04 | global batch size: 512 | lm loss: 2.294982E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.467 | TFLOPs: 23.62 | +63: iteration 12800/ 73814 | consumed samples: 6553600 | consumed tokens: 13421772800 | elapsed time per iteration (s): 2.24 | learning rate: 1.882E-04 | global batch size: 512 | lm loss: 2.284058E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.283 | TFLOPs: 23.50 | +63: iteration 12810/ 73814 | consumed samples: 6558720 | consumed tokens: 13432258560 | elapsed time per iteration (s): 2.23 | learning rate: 1.881E-04 | global batch size: 512 | lm loss: 2.289766E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.962 | TFLOPs: 23.67 | +63: iteration 12820/ 73814 | consumed samples: 6563840 | consumed tokens: 13442744320 | elapsed time per iteration (s): 2.29 | learning rate: 1.881E-04 | global batch size: 512 | lm loss: 2.264272E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.421 | TFLOPs: 23.00 | +63: iteration 12830/ 73814 | consumed samples: 6568960 | consumed tokens: 13453230080 | elapsed time per iteration (s): 2.24 | learning rate: 1.881E-04 | global batch size: 512 | lm loss: 2.284724E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.501 | TFLOPs: 23.52 | +63: iteration 12840/ 73814 | consumed samples: 6574080 | consumed tokens: 13463715840 | elapsed time per iteration (s): 2.23 | learning rate: 1.881E-04 | global batch size: 512 | lm loss: 2.289934E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.086 | TFLOPs: 23.69 | +63: iteration 12850/ 73814 | consumed samples: 6579200 | consumed tokens: 13474201600 | elapsed time per iteration (s): 2.25 | learning rate: 1.881E-04 | global batch size: 512 | lm loss: 2.295495E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.400 | TFLOPs: 23.41 | +63: iteration 12860/ 73814 | consumed samples: 6584320 | consumed tokens: 13484687360 | elapsed time per iteration (s): 2.24 | learning rate: 1.881E-04 | global batch size: 512 | lm loss: 2.282500E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.252 | TFLOPs: 23.50 | +63: iteration 12870/ 73814 | consumed samples: 6589440 | consumed tokens: 13495173120 | elapsed time per iteration (s): 2.24 | learning rate: 1.880E-04 | global batch size: 512 | lm loss: 2.260032E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.031 | TFLOPs: 23.58 | +63: iteration 12880/ 73814 | consumed samples: 6594560 | consumed tokens: 13505658880 | elapsed time per iteration (s): 2.23 | learning rate: 1.880E-04 | global batch size: 512 | lm loss: 2.312569E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.994 | TFLOPs: 23.68 | +63: iteration 12890/ 73814 | consumed samples: 6599680 | consumed tokens: 13516144640 | elapsed time per iteration (s): 2.23 | learning rate: 1.880E-04 | global batch size: 512 | lm loss: 2.278153E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.711 | TFLOPs: 23.65 | +63: iteration 12900/ 73814 | consumed samples: 6604800 | consumed tokens: 13526630400 | elapsed time per iteration (s): 2.29 | learning rate: 1.880E-04 | global batch size: 512 | lm loss: 2.276746E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.815 | TFLOPs: 23.04 | +63: iteration 12910/ 73814 | consumed samples: 6609920 | consumed tokens: 13537116160 | elapsed time per iteration (s): 2.23 | learning rate: 1.880E-04 | global batch size: 512 | lm loss: 2.273495E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.007 | TFLOPs: 23.68 | +63: iteration 12920/ 73814 | consumed samples: 6615040 | consumed tokens: 13547601920 | elapsed time per iteration (s): 2.23 | learning rate: 1.879E-04 | global batch size: 512 | lm loss: 2.270873E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.496 | TFLOPs: 23.63 | +63: iteration 12930/ 73814 | consumed samples: 6620160 | consumed tokens: 13558087680 | elapsed time per iteration (s): 2.23 | learning rate: 1.879E-04 | global batch size: 512 | lm loss: 2.293449E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.746 | TFLOPs: 23.65 | +63: iteration 12940/ 73814 | consumed samples: 6625280 | consumed tokens: 13568573440 | elapsed time per iteration (s): 2.22 | learning rate: 1.879E-04 | global batch size: 512 | lm loss: 2.271691E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.120 | TFLOPs: 23.69 | +63: iteration 12950/ 73814 | consumed samples: 6630400 | consumed tokens: 13579059200 | elapsed time per iteration (s): 2.23 | learning rate: 1.879E-04 | global batch size: 512 | lm loss: 2.290498E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.880 | TFLOPs: 23.67 | +63: iteration 12960/ 73814 | consumed samples: 6635520 | consumed tokens: 13589544960 | elapsed time per iteration (s): 2.28 | learning rate: 1.879E-04 | global batch size: 512 | lm loss: 2.280058E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.420 | TFLOPs: 23.10 | +63: iteration 12970/ 73814 | consumed samples: 6640640 | consumed tokens: 13600030720 | elapsed time per iteration (s): 2.24 | learning rate: 1.878E-04 | global batch size: 512 | lm loss: 2.273801E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.753 | TFLOPs: 23.55 | +63: iteration 12980/ 73814 | consumed samples: 6645760 | consumed tokens: 13610516480 | elapsed time per iteration (s): 2.24 | learning rate: 1.878E-04 | global batch size: 512 | lm loss: 2.304962E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.694 | TFLOPs: 23.54 | +63: iteration 12990/ 73814 | consumed samples: 6650880 | consumed tokens: 13621002240 | elapsed time per iteration (s): 2.23 | learning rate: 1.878E-04 | global batch size: 512 | lm loss: 2.257854E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.344 | TFLOPs: 23.61 | +63: iteration 13000/ 73814 | consumed samples: 6656000 | consumed tokens: 13631488000 | elapsed time per iteration (s): 2.24 | learning rate: 1.878E-04 | global batch size: 512 | lm loss: 2.293624E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.489 | TFLOPs: 23.52 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 13000 | lm loss value: 2.186968E+00 | lm loss PPL: 8.908163E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 13010/ 73814 | consumed samples: 6661120 | consumed tokens: 13641973760 | elapsed time per iteration (s): 2.30 | learning rate: 1.878E-04 | global batch size: 512 | lm loss: 2.276762E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.704 | TFLOPs: 22.93 | +63: iteration 13020/ 73814 | consumed samples: 6666240 | consumed tokens: 13652459520 | elapsed time per iteration (s): 2.23 | learning rate: 1.877E-04 | global batch size: 512 | lm loss: 2.290306E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.908 | TFLOPs: 23.67 | +63: iteration 13030/ 73814 | consumed samples: 6671360 | consumed tokens: 13662945280 | elapsed time per iteration (s): 2.27 | learning rate: 1.877E-04 | global batch size: 512 | lm loss: 2.252218E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.104 | TFLOPs: 23.17 | +63: iteration 13040/ 73814 | consumed samples: 6676480 | consumed tokens: 13673431040 | elapsed time per iteration (s): 2.24 | learning rate: 1.877E-04 | global batch size: 512 | lm loss: 2.276574E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.507 | TFLOPs: 23.52 | +63: iteration 13050/ 73814 | consumed samples: 6681600 | consumed tokens: 13683916800 | elapsed time per iteration (s): 2.25 | learning rate: 1.877E-04 | global batch size: 512 | lm loss: 2.311008E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.988 | TFLOPs: 23.47 | +63: iteration 13060/ 73814 | consumed samples: 6686720 | consumed tokens: 13694402560 | elapsed time per iteration (s): 2.24 | learning rate: 1.877E-04 | global batch size: 512 | lm loss: 2.282360E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.258 | TFLOPs: 23.50 | +63: iteration 13070/ 73814 | consumed samples: 6691840 | consumed tokens: 13704888320 | elapsed time per iteration (s): 2.23 | learning rate: 1.876E-04 | global batch size: 512 | lm loss: 2.257223E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.084 | TFLOPs: 23.69 | +63: iteration 13080/ 73814 | consumed samples: 6696960 | consumed tokens: 13715374080 | elapsed time per iteration (s): 2.36 | learning rate: 1.876E-04 | global batch size: 512 | lm loss: 2.284024E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.198 | TFLOPs: 22.36 | +63: iteration 13090/ 73814 | consumed samples: 6702080 | consumed tokens: 13725859840 | elapsed time per iteration (s): 2.24 | learning rate: 1.876E-04 | global batch size: 512 | lm loss: 2.279974E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.631 | TFLOPs: 23.54 | +63: iteration 13100/ 73814 | consumed samples: 6707200 | consumed tokens: 13736345600 | elapsed time per iteration (s): 2.23 | learning rate: 1.876E-04 | global batch size: 512 | lm loss: 2.289312E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.783 | TFLOPs: 23.66 | +63: iteration 13110/ 73814 | consumed samples: 6712320 | consumed tokens: 13746831360 | elapsed time per iteration (s): 2.23 | learning rate: 1.876E-04 | global batch size: 512 | lm loss: 2.276481E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.425 | TFLOPs: 23.62 | +63: iteration 13120/ 73814 | consumed samples: 6717440 | consumed tokens: 13757317120 | elapsed time per iteration (s): 2.23 | learning rate: 1.875E-04 | global batch size: 512 | lm loss: 2.279736E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.911 | TFLOPs: 23.67 | +63: iteration 13130/ 73814 | consumed samples: 6722560 | consumed tokens: 13767802880 | elapsed time per iteration (s): 2.23 | learning rate: 1.875E-04 | global batch size: 512 | lm loss: 2.273706E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.803 | TFLOPs: 23.66 | +63: iteration 13140/ 73814 | consumed samples: 6727680 | consumed tokens: 13778288640 | elapsed time per iteration (s): 2.25 | learning rate: 1.875E-04 | global batch size: 512 | lm loss: 2.290747E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.020 | TFLOPs: 23.47 | +63: iteration 13150/ 73814 | consumed samples: 6732800 | consumed tokens: 13788774400 | elapsed time per iteration (s): 2.23 | learning rate: 1.875E-04 | global batch size: 512 | lm loss: 2.286356E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.665 | TFLOPs: 23.64 | +63: iteration 13160/ 73814 | consumed samples: 6737920 | consumed tokens: 13799260160 | elapsed time per iteration (s): 2.23 | learning rate: 1.875E-04 | global batch size: 512 | lm loss: 2.296809E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.869 | TFLOPs: 23.66 | +63: iteration 13170/ 73814 | consumed samples: 6743040 | consumed tokens: 13809745920 | elapsed time per iteration (s): 2.25 | learning rate: 1.874E-04 | global batch size: 512 | lm loss: 2.268897E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.949 | TFLOPs: 23.47 | +63: iteration 13180/ 73814 | consumed samples: 6748160 | consumed tokens: 13820231680 | elapsed time per iteration (s): 2.23 | learning rate: 1.874E-04 | global batch size: 512 | lm loss: 2.288358E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.814 | TFLOPs: 23.66 | +63: iteration 13190/ 73814 | consumed samples: 6753280 | consumed tokens: 13830717440 | elapsed time per iteration (s): 2.26 | learning rate: 1.874E-04 | global batch size: 512 | lm loss: 2.285231E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.672 | TFLOPs: 23.33 | +63: iteration 13200/ 73814 | consumed samples: 6758400 | consumed tokens: 13841203200 | elapsed time per iteration (s): 2.23 | learning rate: 1.874E-04 | global batch size: 512 | lm loss: 2.289621E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.751 | TFLOPs: 23.65 | +63: iteration 13210/ 73814 | consumed samples: 6763520 | consumed tokens: 13851688960 | elapsed time per iteration (s): 2.23 | learning rate: 1.874E-04 | global batch size: 512 | lm loss: 2.286148E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.241 | TFLOPs: 23.60 | +63: iteration 13220/ 73814 | consumed samples: 6768640 | consumed tokens: 13862174720 | elapsed time per iteration (s): 2.23 | learning rate: 1.874E-04 | global batch size: 512 | lm loss: 2.289992E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.518 | TFLOPs: 23.63 | +63: iteration 13230/ 73814 | consumed samples: 6773760 | consumed tokens: 13872660480 | elapsed time per iteration (s): 2.29 | learning rate: 1.873E-04 | global batch size: 512 | lm loss: 2.276357E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.472 | TFLOPs: 23.01 | +63: iteration 13240/ 73814 | consumed samples: 6778880 | consumed tokens: 13883146240 | elapsed time per iteration (s): 2.26 | learning rate: 1.873E-04 | global batch size: 512 | lm loss: 2.293984E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.978 | TFLOPs: 23.37 | +63: iteration 13250/ 73814 | consumed samples: 6784000 | consumed tokens: 13893632000 | elapsed time per iteration (s): 2.24 | learning rate: 1.873E-04 | global batch size: 512 | lm loss: 2.304171E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.182 | TFLOPs: 23.49 | +63: iteration 13260/ 73814 | consumed samples: 6789120 | consumed tokens: 13904117760 | elapsed time per iteration (s): 2.24 | learning rate: 1.873E-04 | global batch size: 512 | lm loss: 2.275818E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.418 | TFLOPs: 23.51 | +63: iteration 13270/ 73814 | consumed samples: 6794240 | consumed tokens: 13914603520 | elapsed time per iteration (s): 2.24 | learning rate: 1.873E-04 | global batch size: 512 | lm loss: 2.279184E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.490 | TFLOPs: 23.52 | +63: iteration 13280/ 73814 | consumed samples: 6799360 | consumed tokens: 13925089280 | elapsed time per iteration (s): 2.27 | learning rate: 1.872E-04 | global batch size: 512 | lm loss: 2.298787E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.057 | TFLOPs: 23.17 | +63: iteration 13290/ 73814 | consumed samples: 6804480 | consumed tokens: 13935575040 | elapsed time per iteration (s): 2.27 | learning rate: 1.872E-04 | global batch size: 512 | lm loss: 2.279629E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.196 | TFLOPs: 23.18 | +63: iteration 13300/ 73814 | consumed samples: 6809600 | consumed tokens: 13946060800 | elapsed time per iteration (s): 2.25 | learning rate: 1.872E-04 | global batch size: 512 | lm loss: 2.291574E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.140 | TFLOPs: 23.38 | +63: iteration 13310/ 73814 | consumed samples: 6814720 | consumed tokens: 13956546560 | elapsed time per iteration (s): 2.24 | learning rate: 1.872E-04 | global batch size: 512 | lm loss: 2.253298E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.161 | TFLOPs: 23.49 | +63: iteration 13320/ 73814 | consumed samples: 6819840 | consumed tokens: 13967032320 | elapsed time per iteration (s): 2.25 | learning rate: 1.872E-04 | global batch size: 512 | lm loss: 2.267686E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.058 | TFLOPs: 23.48 | +63: iteration 13330/ 73814 | consumed samples: 6824960 | consumed tokens: 13977518080 | elapsed time per iteration (s): 2.24 | learning rate: 1.871E-04 | global batch size: 512 | lm loss: 2.266614E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.218 | TFLOPs: 23.49 | +63: iteration 13340/ 73814 | consumed samples: 6830080 | consumed tokens: 13988003840 | elapsed time per iteration (s): 2.22 | learning rate: 1.871E-04 | global batch size: 512 | lm loss: 2.284007E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.141 | TFLOPs: 23.69 | +63: iteration 13350/ 73814 | consumed samples: 6835200 | consumed tokens: 13998489600 | elapsed time per iteration (s): 2.30 | learning rate: 1.871E-04 | global batch size: 512 | lm loss: 2.298390E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.958 | TFLOPs: 22.95 | +63: iteration 13360/ 73814 | consumed samples: 6840320 | consumed tokens: 14008975360 | elapsed time per iteration (s): 2.28 | learning rate: 1.871E-04 | global batch size: 512 | lm loss: 2.276609E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.536 | TFLOPs: 23.11 | +63: iteration 13370/ 73814 | consumed samples: 6845440 | consumed tokens: 14019461120 | elapsed time per iteration (s): 2.24 | learning rate: 1.871E-04 | global batch size: 512 | lm loss: 2.283401E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.849 | TFLOPs: 23.56 | +63: iteration 13380/ 73814 | consumed samples: 6850560 | consumed tokens: 14029946880 | elapsed time per iteration (s): 2.39 | learning rate: 1.870E-04 | global batch size: 512 | lm loss: 2.266928E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.790 | TFLOPs: 22.01 | +63: iteration 13390/ 73814 | consumed samples: 6855680 | consumed tokens: 14040432640 | elapsed time per iteration (s): 2.36 | learning rate: 1.870E-04 | global batch size: 512 | lm loss: 2.285588E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.108 | TFLOPs: 22.35 | +63: iteration 13400/ 73814 | consumed samples: 6860800 | consumed tokens: 14050918400 | elapsed time per iteration (s): 2.40 | learning rate: 1.870E-04 | global batch size: 512 | lm loss: 2.264262E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.043 | TFLOPs: 21.93 | +63: iteration 13410/ 73814 | consumed samples: 6865920 | consumed tokens: 14061404160 | elapsed time per iteration (s): 2.40 | learning rate: 1.870E-04 | global batch size: 512 | lm loss: 2.262539E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.690 | TFLOPs: 22.00 | +63: iteration 13420/ 73814 | consumed samples: 6871040 | consumed tokens: 14071889920 | elapsed time per iteration (s): 2.55 | learning rate: 1.870E-04 | global batch size: 512 | lm loss: 2.272899E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.492 | TFLOPs: 20.64 | +63: iteration 13430/ 73814 | consumed samples: 6876160 | consumed tokens: 14082375680 | elapsed time per iteration (s): 2.37 | learning rate: 1.869E-04 | global batch size: 512 | lm loss: 2.279236E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.795 | TFLOPs: 22.22 | +63: iteration 13440/ 73814 | consumed samples: 6881280 | consumed tokens: 14092861440 | elapsed time per iteration (s): 2.24 | learning rate: 1.869E-04 | global batch size: 512 | lm loss: 2.288667E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.461 | TFLOPs: 23.52 | +63: iteration 13450/ 73814 | consumed samples: 6886400 | consumed tokens: 14103347200 | elapsed time per iteration (s): 2.34 | learning rate: 1.869E-04 | global batch size: 512 | lm loss: 2.281987E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.668 | TFLOPs: 22.51 | +63: iteration 13460/ 73814 | consumed samples: 6891520 | consumed tokens: 14113832960 | elapsed time per iteration (s): 2.62 | learning rate: 1.869E-04 | global batch size: 512 | lm loss: 2.283509E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 195.061 | TFLOPs: 20.08 | +63: iteration 13470/ 73814 | consumed samples: 6896640 | consumed tokens: 14124318720 | elapsed time per iteration (s): 2.32 | learning rate: 1.869E-04 | global batch size: 512 | lm loss: 2.277721E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.917 | TFLOPs: 22.74 | +63: iteration 13480/ 73814 | consumed samples: 6901760 | consumed tokens: 14134804480 | elapsed time per iteration (s): 2.36 | learning rate: 1.868E-04 | global batch size: 512 | lm loss: 2.295373E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.995 | TFLOPs: 22.34 | +63: iteration 13490/ 73814 | consumed samples: 6906880 | consumed tokens: 14145290240 | elapsed time per iteration (s): 2.24 | learning rate: 1.868E-04 | global batch size: 512 | lm loss: 2.265455E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.208 | TFLOPs: 23.49 | +63: iteration 13500/ 73814 | consumed samples: 6912000 | consumed tokens: 14155776000 | elapsed time per iteration (s): 2.24 | learning rate: 1.868E-04 | global batch size: 512 | lm loss: 2.264694E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.758 | TFLOPs: 23.55 | +63: iteration 13510/ 73814 | consumed samples: 6917120 | consumed tokens: 14166261760 | elapsed time per iteration (s): 2.24 | learning rate: 1.868E-04 | global batch size: 512 | lm loss: 2.267175E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.639 | TFLOPs: 23.54 | +63: iteration 13520/ 73814 | consumed samples: 6922240 | consumed tokens: 14176747520 | elapsed time per iteration (s): 2.29 | learning rate: 1.868E-04 | global batch size: 512 | lm loss: 2.251461E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.681 | TFLOPs: 23.03 | +63: iteration 13530/ 73814 | consumed samples: 6927360 | consumed tokens: 14187233280 | elapsed time per iteration (s): 2.24 | learning rate: 1.867E-04 | global batch size: 512 | lm loss: 2.256332E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.537 | TFLOPs: 23.53 | +63: iteration 13540/ 73814 | consumed samples: 6932480 | consumed tokens: 14197719040 | elapsed time per iteration (s): 2.29 | learning rate: 1.867E-04 | global batch size: 512 | lm loss: 2.262620E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.436 | TFLOPs: 23.00 | +63: iteration 13550/ 73814 | consumed samples: 6937600 | consumed tokens: 14208204800 | elapsed time per iteration (s): 2.41 | learning rate: 1.867E-04 | global batch size: 512 | lm loss: 2.268744E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.709 | TFLOPs: 21.90 | +63: iteration 13560/ 73814 | consumed samples: 6942720 | consumed tokens: 14218690560 | elapsed time per iteration (s): 2.27 | learning rate: 1.867E-04 | global batch size: 512 | lm loss: 2.284887E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.557 | TFLOPs: 23.22 | +63: iteration 13570/ 73814 | consumed samples: 6947840 | consumed tokens: 14229176320 | elapsed time per iteration (s): 2.24 | learning rate: 1.866E-04 | global batch size: 512 | lm loss: 2.261261E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.645 | TFLOPs: 23.54 | +63: iteration 13580/ 73814 | consumed samples: 6952960 | consumed tokens: 14239662080 | elapsed time per iteration (s): 2.23 | learning rate: 1.866E-04 | global batch size: 512 | lm loss: 2.269517E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.834 | TFLOPs: 23.66 | +63: iteration 13590/ 73814 | consumed samples: 6958080 | consumed tokens: 14250147840 | elapsed time per iteration (s): 2.23 | learning rate: 1.866E-04 | global batch size: 512 | lm loss: 2.258794E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.526 | TFLOPs: 23.63 | +63: iteration 13600/ 73814 | consumed samples: 6963200 | consumed tokens: 14260633600 | elapsed time per iteration (s): 2.23 | learning rate: 1.866E-04 | global batch size: 512 | lm loss: 2.271469E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.829 | TFLOPs: 23.66 | +63: iteration 13610/ 73814 | consumed samples: 6968320 | consumed tokens: 14271119360 | elapsed time per iteration (s): 2.23 | learning rate: 1.866E-04 | global batch size: 512 | lm loss: 2.267053E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.751 | TFLOPs: 23.65 | +63: iteration 13620/ 73814 | consumed samples: 6973440 | consumed tokens: 14281605120 | elapsed time per iteration (s): 2.23 | learning rate: 1.865E-04 | global batch size: 512 | lm loss: 2.271548E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.844 | TFLOPs: 23.66 | +63: iteration 13630/ 73814 | consumed samples: 6978560 | consumed tokens: 14292090880 | elapsed time per iteration (s): 2.27 | learning rate: 1.865E-04 | global batch size: 512 | lm loss: 2.260979E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.274 | TFLOPs: 23.19 | +63: iteration 13640/ 73814 | consumed samples: 6983680 | consumed tokens: 14302576640 | elapsed time per iteration (s): 2.25 | learning rate: 1.865E-04 | global batch size: 512 | lm loss: 2.260143E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.492 | TFLOPs: 23.42 | +63: iteration 13650/ 73814 | consumed samples: 6988800 | consumed tokens: 14313062400 | elapsed time per iteration (s): 2.26 | learning rate: 1.865E-04 | global batch size: 512 | lm loss: 2.279113E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.523 | TFLOPs: 23.32 | +63: iteration 13660/ 73814 | consumed samples: 6993920 | consumed tokens: 14323548160 | elapsed time per iteration (s): 2.31 | learning rate: 1.865E-04 | global batch size: 512 | lm loss: 2.253981E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.612 | TFLOPs: 22.81 | +63: iteration 13670/ 73814 | consumed samples: 6999040 | consumed tokens: 14334033920 | elapsed time per iteration (s): 2.25 | learning rate: 1.864E-04 | global batch size: 512 | lm loss: 2.296811E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.777 | TFLOPs: 23.45 | +63: iteration 13680/ 73814 | consumed samples: 7004160 | consumed tokens: 14344519680 | elapsed time per iteration (s): 2.26 | learning rate: 1.864E-04 | global batch size: 512 | lm loss: 4.319169E+00 | grad norm: 11.769 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.604 | TFLOPs: 23.33 | +63: iteration 13690/ 73814 | consumed samples: 7009280 | consumed tokens: 14355005440 | elapsed time per iteration (s): 2.30 | learning rate: 1.864E-04 | global batch size: 512 | lm loss: 5.631391E+00 | grad norm: 3.807 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.246 | TFLOPs: 22.88 | +63: iteration 13700/ 73814 | consumed samples: 7014400 | consumed tokens: 14365491200 | elapsed time per iteration (s): 2.25 | learning rate: 1.864E-04 | global batch size: 512 | lm loss: 3.684755E+00 | grad norm: 1.448 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.134 | TFLOPs: 23.38 | +63: iteration 13710/ 73814 | consumed samples: 7019520 | consumed tokens: 14375976960 | elapsed time per iteration (s): 2.27 | learning rate: 1.864E-04 | global batch size: 512 | lm loss: 2.953260E+00 | grad norm: 1.941 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.584 | TFLOPs: 23.22 | +63: iteration 13720/ 73814 | consumed samples: 7024640 | consumed tokens: 14386462720 | elapsed time per iteration (s): 2.41 | learning rate: 1.863E-04 | global batch size: 512 | lm loss: 2.656266E+00 | grad norm: 0.667 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.309 | TFLOPs: 21.86 | +63: iteration 13730/ 73814 | consumed samples: 7029760 | consumed tokens: 14396948480 | elapsed time per iteration (s): 2.27 | learning rate: 1.863E-04 | global batch size: 512 | lm loss: 2.481550E+00 | grad norm: 0.724 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.094 | TFLOPs: 23.17 | +63: iteration 13740/ 73814 | consumed samples: 7034880 | consumed tokens: 14407434240 | elapsed time per iteration (s): 2.23 | learning rate: 1.863E-04 | global batch size: 512 | lm loss: 2.405144E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.740 | TFLOPs: 23.65 | +63: iteration 13750/ 73814 | consumed samples: 7040000 | consumed tokens: 14417920000 | elapsed time per iteration (s): 2.32 | learning rate: 1.863E-04 | global batch size: 512 | lm loss: 2.352856E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.503 | TFLOPs: 22.70 | +63: iteration 13760/ 73814 | consumed samples: 7045120 | consumed tokens: 14428405760 | elapsed time per iteration (s): 2.26 | learning rate: 1.863E-04 | global batch size: 512 | lm loss: 2.350993E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.701 | TFLOPs: 23.34 | +63: iteration 13770/ 73814 | consumed samples: 7050240 | consumed tokens: 14438891520 | elapsed time per iteration (s): 2.22 | learning rate: 1.862E-04 | global batch size: 512 | lm loss: 2.316113E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.531 | TFLOPs: 23.73 | +63: iteration 13780/ 73814 | consumed samples: 7055360 | consumed tokens: 14449377280 | elapsed time per iteration (s): 2.23 | learning rate: 1.862E-04 | global batch size: 512 | lm loss: 2.323974E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.812 | TFLOPs: 23.66 | +63: iteration 13790/ 73814 | consumed samples: 7060480 | consumed tokens: 14459863040 | elapsed time per iteration (s): 2.23 | learning rate: 1.862E-04 | global batch size: 512 | lm loss: 2.297060E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.958 | TFLOPs: 23.67 | +63: iteration 13800/ 73814 | consumed samples: 7065600 | consumed tokens: 14470348800 | elapsed time per iteration (s): 2.23 | learning rate: 1.862E-04 | global batch size: 512 | lm loss: 2.317110E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.642 | TFLOPs: 23.64 | +63: iteration 13810/ 73814 | consumed samples: 7070720 | consumed tokens: 14480834560 | elapsed time per iteration (s): 2.24 | learning rate: 1.862E-04 | global batch size: 512 | lm loss: 2.311985E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.375 | TFLOPs: 23.51 | +63: iteration 13820/ 73814 | consumed samples: 7075840 | consumed tokens: 14491320320 | elapsed time per iteration (s): 2.23 | learning rate: 1.861E-04 | global batch size: 512 | lm loss: 2.284141E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.989 | TFLOPs: 23.68 | +63: iteration 13830/ 73814 | consumed samples: 7080960 | consumed tokens: 14501806080 | elapsed time per iteration (s): 2.26 | learning rate: 1.861E-04 | global batch size: 512 | lm loss: 2.314113E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.209 | TFLOPs: 23.29 | +63: iteration 13840/ 73814 | consumed samples: 7086080 | consumed tokens: 14512291840 | elapsed time per iteration (s): 2.29 | learning rate: 1.861E-04 | global batch size: 512 | lm loss: 2.289247E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.524 | TFLOPs: 23.01 | +63: iteration 13850/ 73814 | consumed samples: 7091200 | consumed tokens: 14522777600 | elapsed time per iteration (s): 2.29 | learning rate: 1.861E-04 | global batch size: 512 | lm loss: 2.306778E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.507 | TFLOPs: 23.01 | +63: iteration 13860/ 73814 | consumed samples: 7096320 | consumed tokens: 14533263360 | elapsed time per iteration (s): 2.23 | learning rate: 1.861E-04 | global batch size: 512 | lm loss: 2.313080E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.550 | TFLOPs: 23.63 | +63: iteration 13870/ 73814 | consumed samples: 7101440 | consumed tokens: 14543749120 | elapsed time per iteration (s): 2.24 | learning rate: 1.860E-04 | global batch size: 512 | lm loss: 2.282370E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.081 | TFLOPs: 23.58 | +63: iteration 13880/ 73814 | consumed samples: 7106560 | consumed tokens: 14554234880 | elapsed time per iteration (s): 2.29 | learning rate: 1.860E-04 | global batch size: 512 | lm loss: 2.272253E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.256 | TFLOPs: 22.98 | +63: iteration 13890/ 73814 | consumed samples: 7111680 | consumed tokens: 14564720640 | elapsed time per iteration (s): 2.25 | learning rate: 1.860E-04 | global batch size: 512 | lm loss: 2.297960E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.920 | TFLOPs: 23.46 | +63: iteration 13900/ 73814 | consumed samples: 7116800 | consumed tokens: 14575206400 | elapsed time per iteration (s): 2.22 | learning rate: 1.860E-04 | global batch size: 512 | lm loss: 2.284405E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.149 | TFLOPs: 23.69 | +63: iteration 13910/ 73814 | consumed samples: 7121920 | consumed tokens: 14585692160 | elapsed time per iteration (s): 2.23 | learning rate: 1.860E-04 | global batch size: 512 | lm loss: 2.277388E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.911 | TFLOPs: 23.67 | +63: iteration 13920/ 73814 | consumed samples: 7127040 | consumed tokens: 14596177920 | elapsed time per iteration (s): 2.25 | learning rate: 1.859E-04 | global batch size: 512 | lm loss: 2.290755E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.058 | TFLOPs: 23.48 | +63: iteration 13930/ 73814 | consumed samples: 7132160 | consumed tokens: 14606663680 | elapsed time per iteration (s): 2.24 | learning rate: 1.859E-04 | global batch size: 512 | lm loss: 2.301919E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.996 | TFLOPs: 23.57 | +63: iteration 13940/ 73814 | consumed samples: 7137280 | consumed tokens: 14617149440 | elapsed time per iteration (s): 2.23 | learning rate: 1.859E-04 | global batch size: 512 | lm loss: 2.295952E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.715 | TFLOPs: 23.65 | +63: iteration 13950/ 73814 | consumed samples: 7142400 | consumed tokens: 14627635200 | elapsed time per iteration (s): 2.24 | learning rate: 1.859E-04 | global batch size: 512 | lm loss: 2.287795E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.403 | TFLOPs: 23.51 | +63: iteration 13960/ 73814 | consumed samples: 7147520 | consumed tokens: 14638120960 | elapsed time per iteration (s): 2.25 | learning rate: 1.858E-04 | global batch size: 512 | lm loss: 2.292831E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.629 | TFLOPs: 23.43 | +63: iteration 13970/ 73814 | consumed samples: 7152640 | consumed tokens: 14648606720 | elapsed time per iteration (s): 2.25 | learning rate: 1.858E-04 | global batch size: 512 | lm loss: 2.283694E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.800 | TFLOPs: 23.45 | +63: iteration 13980/ 73814 | consumed samples: 7157760 | consumed tokens: 14659092480 | elapsed time per iteration (s): 2.24 | learning rate: 1.858E-04 | global batch size: 512 | lm loss: 2.298780E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.665 | TFLOPs: 23.54 | +63: iteration 13990/ 73814 | consumed samples: 7162880 | consumed tokens: 14669578240 | elapsed time per iteration (s): 2.26 | learning rate: 1.858E-04 | global batch size: 512 | lm loss: 2.294986E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.884 | TFLOPs: 23.36 | + 0: [2022-12-01 20:42:14,851] [INFO] [logging.py:68:log_dist] [Rank 0] step=14000, skipped=0, lr=[0.00018576451656291204, 0.00018576451656291204, 0.00018576451656291204], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] + 0: steps: 14000 loss: 2.2574 iter time (s): 2.254 samples/sec: 227.157 +63: iteration 14000/ 73814 | consumed samples: 7168000 | consumed tokens: 14680064000 | elapsed time per iteration (s): 2.25 | learning rate: 1.858E-04 | global batch size: 512 | lm loss: 2.277211E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.177 | TFLOPs: 23.39 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 14000 | lm loss value: 2.273114E+00 | lm loss PPL: 9.709591E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 14010/ 73814 | consumed samples: 7173120 | consumed tokens: 14690549760 | elapsed time per iteration (s): 2.29 | learning rate: 1.857E-04 | global batch size: 512 | lm loss: 2.264800E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.008 | TFLOPs: 23.06 | +63: iteration 14020/ 73814 | consumed samples: 7178240 | consumed tokens: 14701035520 | elapsed time per iteration (s): 2.23 | learning rate: 1.857E-04 | global batch size: 512 | lm loss: 2.276801E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.501 | TFLOPs: 23.63 | +63: iteration 14030/ 73814 | consumed samples: 7183360 | consumed tokens: 14711521280 | elapsed time per iteration (s): 2.29 | learning rate: 1.857E-04 | global batch size: 512 | lm loss: 2.269149E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.855 | TFLOPs: 23.04 | +63: iteration 14040/ 73814 | consumed samples: 7188480 | consumed tokens: 14722007040 | elapsed time per iteration (s): 2.25 | learning rate: 1.857E-04 | global batch size: 512 | lm loss: 2.266662E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.479 | TFLOPs: 23.42 | +63: iteration 14050/ 73814 | consumed samples: 7193600 | consumed tokens: 14732492800 | elapsed time per iteration (s): 2.26 | learning rate: 1.857E-04 | global batch size: 512 | lm loss: 2.286042E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.650 | TFLOPs: 23.33 | +63: iteration 14060/ 73814 | consumed samples: 7198720 | consumed tokens: 14742978560 | elapsed time per iteration (s): 2.22 | learning rate: 1.856E-04 | global batch size: 512 | lm loss: 2.256983E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.150 | TFLOPs: 23.69 | +63: iteration 14070/ 73814 | consumed samples: 7203840 | consumed tokens: 14753464320 | elapsed time per iteration (s): 2.24 | learning rate: 1.856E-04 | global batch size: 512 | lm loss: 2.278471E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.393 | TFLOPs: 23.51 | +63: iteration 14080/ 73814 | consumed samples: 7208960 | consumed tokens: 14763950080 | elapsed time per iteration (s): 2.23 | learning rate: 1.856E-04 | global batch size: 512 | lm loss: 2.270013E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.676 | TFLOPs: 23.64 | +63: iteration 14090/ 73814 | consumed samples: 7214080 | consumed tokens: 14774435840 | elapsed time per iteration (s): 2.23 | learning rate: 1.856E-04 | global batch size: 512 | lm loss: 2.268427E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.517 | TFLOPs: 23.63 | +63: iteration 14100/ 73814 | consumed samples: 7219200 | consumed tokens: 14784921600 | elapsed time per iteration (s): 2.25 | learning rate: 1.856E-04 | global batch size: 512 | lm loss: 2.277763E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.240 | TFLOPs: 23.39 | +63: iteration 14110/ 73814 | consumed samples: 7224320 | consumed tokens: 14795407360 | elapsed time per iteration (s): 2.25 | learning rate: 1.855E-04 | global batch size: 512 | lm loss: 2.263819E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.286 | TFLOPs: 23.40 | +63: iteration 14120/ 73814 | consumed samples: 7229440 | consumed tokens: 14805893120 | elapsed time per iteration (s): 2.24 | learning rate: 1.855E-04 | global batch size: 512 | lm loss: 2.265754E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.323 | TFLOPs: 23.50 | +63: iteration 14130/ 73814 | consumed samples: 7234560 | consumed tokens: 14816378880 | elapsed time per iteration (s): 2.23 | learning rate: 1.855E-04 | global batch size: 512 | lm loss: 2.281497E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.667 | TFLOPs: 23.64 | +63: iteration 14140/ 73814 | consumed samples: 7239680 | consumed tokens: 14826864640 | elapsed time per iteration (s): 2.24 | learning rate: 1.855E-04 | global batch size: 512 | lm loss: 2.237163E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.929 | TFLOPs: 23.57 | +63: iteration 14150/ 73814 | consumed samples: 7244800 | consumed tokens: 14837350400 | elapsed time per iteration (s): 2.23 | learning rate: 1.854E-04 | global batch size: 512 | lm loss: 2.259564E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.888 | TFLOPs: 23.67 | +63: iteration 14160/ 73814 | consumed samples: 7249920 | consumed tokens: 14847836160 | elapsed time per iteration (s): 2.27 | learning rate: 1.854E-04 | global batch size: 512 | lm loss: 2.270312E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.376 | TFLOPs: 23.20 | +63: iteration 14170/ 73814 | consumed samples: 7255040 | consumed tokens: 14858321920 | elapsed time per iteration (s): 2.24 | learning rate: 1.854E-04 | global batch size: 512 | lm loss: 2.252283E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.893 | TFLOPs: 23.56 | +63: iteration 14180/ 73814 | consumed samples: 7260160 | consumed tokens: 14868807680 | elapsed time per iteration (s): 2.28 | learning rate: 1.854E-04 | global batch size: 512 | lm loss: 2.265303E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.957 | TFLOPs: 23.16 | +63: iteration 14190/ 73814 | consumed samples: 7265280 | consumed tokens: 14879293440 | elapsed time per iteration (s): 2.23 | learning rate: 1.854E-04 | global batch size: 512 | lm loss: 2.256689E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.874 | TFLOPs: 23.66 | +63: iteration 14200/ 73814 | consumed samples: 7270400 | consumed tokens: 14889779200 | elapsed time per iteration (s): 2.28 | learning rate: 1.853E-04 | global batch size: 512 | lm loss: 2.254612E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.643 | TFLOPs: 23.13 | +63: iteration 14210/ 73814 | consumed samples: 7275520 | consumed tokens: 14900264960 | elapsed time per iteration (s): 2.24 | learning rate: 1.853E-04 | global batch size: 512 | lm loss: 2.248681E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.806 | TFLOPs: 23.55 | +63: iteration 14220/ 73814 | consumed samples: 7280640 | consumed tokens: 14910750720 | elapsed time per iteration (s): 2.24 | learning rate: 1.853E-04 | global batch size: 512 | lm loss: 2.252897E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.074 | TFLOPs: 23.48 | +63: iteration 14230/ 73814 | consumed samples: 7285760 | consumed tokens: 14921236480 | elapsed time per iteration (s): 2.24 | learning rate: 1.853E-04 | global batch size: 512 | lm loss: 2.260080E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.885 | TFLOPs: 23.56 | +63: iteration 14240/ 73814 | consumed samples: 7290880 | consumed tokens: 14931722240 | elapsed time per iteration (s): 2.24 | learning rate: 1.853E-04 | global batch size: 512 | lm loss: 2.256149E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.278 | TFLOPs: 23.50 | +63: iteration 14250/ 73814 | consumed samples: 7296000 | consumed tokens: 14942208000 | elapsed time per iteration (s): 2.22 | learning rate: 1.852E-04 | global batch size: 512 | lm loss: 2.273365E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.139 | TFLOPs: 23.69 | +63: iteration 14260/ 73814 | consumed samples: 7301120 | consumed tokens: 14952693760 | elapsed time per iteration (s): 2.24 | learning rate: 1.852E-04 | global batch size: 512 | lm loss: 2.269131E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.549 | TFLOPs: 23.53 | +63: iteration 14270/ 73814 | consumed samples: 7306240 | consumed tokens: 14963179520 | elapsed time per iteration (s): 2.23 | learning rate: 1.852E-04 | global batch size: 512 | lm loss: 2.248725E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.446 | TFLOPs: 23.62 | +63: iteration 14280/ 73814 | consumed samples: 7311360 | consumed tokens: 14973665280 | elapsed time per iteration (s): 2.25 | learning rate: 1.852E-04 | global batch size: 512 | lm loss: 2.291948E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.596 | TFLOPs: 23.43 | +63: iteration 14290/ 73814 | consumed samples: 7316480 | consumed tokens: 14984151040 | elapsed time per iteration (s): 2.25 | learning rate: 1.852E-04 | global batch size: 512 | lm loss: 2.271835E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.530 | TFLOPs: 23.42 | +63: iteration 14300/ 73814 | consumed samples: 7321600 | consumed tokens: 14994636800 | elapsed time per iteration (s): 2.23 | learning rate: 1.851E-04 | global batch size: 512 | lm loss: 2.255537E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.517 | TFLOPs: 23.63 | +63: iteration 14310/ 73814 | consumed samples: 7326720 | consumed tokens: 15005122560 | elapsed time per iteration (s): 2.23 | learning rate: 1.851E-04 | global batch size: 512 | lm loss: 2.267787E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.105 | TFLOPs: 23.69 | +63: iteration 14320/ 73814 | consumed samples: 7331840 | consumed tokens: 15015608320 | elapsed time per iteration (s): 2.24 | learning rate: 1.851E-04 | global batch size: 512 | lm loss: 2.239155E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.406 | TFLOPs: 23.51 | +63: iteration 14330/ 73814 | consumed samples: 7336960 | consumed tokens: 15026094080 | elapsed time per iteration (s): 2.26 | learning rate: 1.851E-04 | global batch size: 512 | lm loss: 2.262641E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.761 | TFLOPs: 23.34 | +63: iteration 14340/ 73814 | consumed samples: 7342080 | consumed tokens: 15036579840 | elapsed time per iteration (s): 2.23 | learning rate: 1.850E-04 | global batch size: 512 | lm loss: 2.246690E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.572 | TFLOPs: 23.63 | +63: iteration 14350/ 73814 | consumed samples: 7347200 | consumed tokens: 15047065600 | elapsed time per iteration (s): 2.23 | learning rate: 1.850E-04 | global batch size: 512 | lm loss: 2.265434E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.706 | TFLOPs: 23.65 | +63: iteration 14360/ 73814 | consumed samples: 7352320 | consumed tokens: 15057551360 | elapsed time per iteration (s): 2.22 | learning rate: 1.850E-04 | global batch size: 512 | lm loss: 2.267727E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.370 | TFLOPs: 23.72 | +63: iteration 14370/ 73814 | consumed samples: 7357440 | consumed tokens: 15068037120 | elapsed time per iteration (s): 2.24 | learning rate: 1.850E-04 | global batch size: 512 | lm loss: 2.266682E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.360 | TFLOPs: 23.51 | +63: iteration 14380/ 73814 | consumed samples: 7362560 | consumed tokens: 15078522880 | elapsed time per iteration (s): 2.23 | learning rate: 1.850E-04 | global batch size: 512 | lm loss: 2.254849E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.390 | TFLOPs: 23.61 | +63: iteration 14390/ 73814 | consumed samples: 7367680 | consumed tokens: 15089008640 | elapsed time per iteration (s): 2.23 | learning rate: 1.849E-04 | global batch size: 512 | lm loss: 2.239824E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.412 | TFLOPs: 23.62 | +63: iteration 14400/ 73814 | consumed samples: 7372800 | consumed tokens: 15099494400 | elapsed time per iteration (s): 2.23 | learning rate: 1.849E-04 | global batch size: 512 | lm loss: 2.263958E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.571 | TFLOPs: 23.63 | +63: iteration 14410/ 73814 | consumed samples: 7377920 | consumed tokens: 15109980160 | elapsed time per iteration (s): 2.23 | learning rate: 1.849E-04 | global batch size: 512 | lm loss: 2.265734E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.809 | TFLOPs: 23.66 | +63: iteration 14420/ 73814 | consumed samples: 7383040 | consumed tokens: 15120465920 | elapsed time per iteration (s): 2.25 | learning rate: 1.849E-04 | global batch size: 512 | lm loss: 2.269547E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.658 | TFLOPs: 23.44 | +63: iteration 14430/ 73814 | consumed samples: 7388160 | consumed tokens: 15130951680 | elapsed time per iteration (s): 2.24 | learning rate: 1.849E-04 | global batch size: 512 | lm loss: 2.249806E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.775 | TFLOPs: 23.55 | +63: iteration 14440/ 73814 | consumed samples: 7393280 | consumed tokens: 15141437440 | elapsed time per iteration (s): 2.22 | learning rate: 1.848E-04 | global batch size: 512 | lm loss: 2.254285E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.425 | TFLOPs: 23.72 | +63: iteration 14450/ 73814 | consumed samples: 7398400 | consumed tokens: 15151923200 | elapsed time per iteration (s): 2.23 | learning rate: 1.848E-04 | global batch size: 512 | lm loss: 2.273426E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.885 | TFLOPs: 23.67 | +63: iteration 14460/ 73814 | consumed samples: 7403520 | consumed tokens: 15162408960 | elapsed time per iteration (s): 2.26 | learning rate: 1.848E-04 | global batch size: 512 | lm loss: 2.251918E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.821 | TFLOPs: 23.35 | +63: iteration 14470/ 73814 | consumed samples: 7408640 | consumed tokens: 15172894720 | elapsed time per iteration (s): 2.23 | learning rate: 1.848E-04 | global batch size: 512 | lm loss: 2.277766E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.477 | TFLOPs: 23.62 | +63: iteration 14480/ 73814 | consumed samples: 7413760 | consumed tokens: 15183380480 | elapsed time per iteration (s): 2.24 | learning rate: 1.847E-04 | global batch size: 512 | lm loss: 2.276565E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.116 | TFLOPs: 23.48 | +63: iteration 14490/ 73814 | consumed samples: 7418880 | consumed tokens: 15193866240 | elapsed time per iteration (s): 2.25 | learning rate: 1.847E-04 | global batch size: 512 | lm loss: 2.245130E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.563 | TFLOPs: 23.43 | +63: iteration 14500/ 73814 | consumed samples: 7424000 | consumed tokens: 15204352000 | elapsed time per iteration (s): 2.23 | learning rate: 1.847E-04 | global batch size: 512 | lm loss: 2.255575E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.393 | TFLOPs: 23.61 | +63: iteration 14510/ 73814 | consumed samples: 7429120 | consumed tokens: 15214837760 | elapsed time per iteration (s): 2.24 | learning rate: 1.847E-04 | global batch size: 512 | lm loss: 2.253549E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.612 | TFLOPs: 23.53 | +63: iteration 14520/ 73814 | consumed samples: 7434240 | consumed tokens: 15225323520 | elapsed time per iteration (s): 2.23 | learning rate: 1.847E-04 | global batch size: 512 | lm loss: 2.253746E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.151 | TFLOPs: 23.59 | +63: iteration 14530/ 73814 | consumed samples: 7439360 | consumed tokens: 15235809280 | elapsed time per iteration (s): 2.24 | learning rate: 1.846E-04 | global batch size: 512 | lm loss: 2.269995E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.361 | TFLOPs: 23.51 | +63: iteration 14540/ 73814 | consumed samples: 7444480 | consumed tokens: 15246295040 | elapsed time per iteration (s): 2.24 | learning rate: 1.846E-04 | global batch size: 512 | lm loss: 2.237176E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.190 | TFLOPs: 23.49 | +63: iteration 14550/ 73814 | consumed samples: 7449600 | consumed tokens: 15256780800 | elapsed time per iteration (s): 2.25 | learning rate: 1.846E-04 | global batch size: 512 | lm loss: 2.269079E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.161 | TFLOPs: 23.39 | +63: iteration 14560/ 73814 | consumed samples: 7454720 | consumed tokens: 15267266560 | elapsed time per iteration (s): 2.25 | learning rate: 1.846E-04 | global batch size: 512 | lm loss: 2.245151E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.002 | TFLOPs: 23.47 | +63: iteration 14570/ 73814 | consumed samples: 7459840 | consumed tokens: 15277752320 | elapsed time per iteration (s): 2.23 | learning rate: 1.846E-04 | global batch size: 512 | lm loss: 2.262176E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.112 | TFLOPs: 23.69 | +63: iteration 14580/ 73814 | consumed samples: 7464960 | consumed tokens: 15288238080 | elapsed time per iteration (s): 2.25 | learning rate: 1.845E-04 | global batch size: 512 | lm loss: 2.282373E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.439 | TFLOPs: 23.41 | +63: iteration 14590/ 73814 | consumed samples: 7470080 | consumed tokens: 15298723840 | elapsed time per iteration (s): 2.23 | learning rate: 1.845E-04 | global batch size: 512 | lm loss: 2.259986E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.936 | TFLOPs: 23.67 | +63: iteration 14600/ 73814 | consumed samples: 7475200 | consumed tokens: 15309209600 | elapsed time per iteration (s): 2.27 | learning rate: 1.845E-04 | global batch size: 512 | lm loss: 2.282593E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.665 | TFLOPs: 23.23 | +63: iteration 14610/ 73814 | consumed samples: 7480320 | consumed tokens: 15319695360 | elapsed time per iteration (s): 2.24 | learning rate: 1.845E-04 | global batch size: 512 | lm loss: 2.253648E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.795 | TFLOPs: 23.55 | +63: iteration 14620/ 73814 | consumed samples: 7485440 | consumed tokens: 15330181120 | elapsed time per iteration (s): 2.24 | learning rate: 1.844E-04 | global batch size: 512 | lm loss: 2.264364E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.719 | TFLOPs: 23.55 | +63: iteration 14630/ 73814 | consumed samples: 7490560 | consumed tokens: 15340666880 | elapsed time per iteration (s): 2.28 | learning rate: 1.844E-04 | global batch size: 512 | lm loss: 2.258424E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.867 | TFLOPs: 23.15 | +63: iteration 14640/ 73814 | consumed samples: 7495680 | consumed tokens: 15351152640 | elapsed time per iteration (s): 2.24 | learning rate: 1.844E-04 | global batch size: 512 | lm loss: 2.237502E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.817 | TFLOPs: 23.56 | +63: iteration 14650/ 73814 | consumed samples: 7500800 | consumed tokens: 15361638400 | elapsed time per iteration (s): 2.23 | learning rate: 1.844E-04 | global batch size: 512 | lm loss: 2.243286E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.680 | TFLOPs: 23.64 | +63: iteration 14660/ 73814 | consumed samples: 7505920 | consumed tokens: 15372124160 | elapsed time per iteration (s): 2.22 | learning rate: 1.844E-04 | global batch size: 512 | lm loss: 2.254595E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.286 | TFLOPs: 23.71 | +63: iteration 14670/ 73814 | consumed samples: 7511040 | consumed tokens: 15382609920 | elapsed time per iteration (s): 2.25 | learning rate: 1.843E-04 | global batch size: 512 | lm loss: 2.263595E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.808 | TFLOPs: 23.45 | +63: iteration 14680/ 73814 | consumed samples: 7516160 | consumed tokens: 15393095680 | elapsed time per iteration (s): 2.23 | learning rate: 1.843E-04 | global batch size: 512 | lm loss: 2.260838E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.077 | TFLOPs: 23.69 | +63: iteration 14690/ 73814 | consumed samples: 7521280 | consumed tokens: 15403581440 | elapsed time per iteration (s): 2.23 | learning rate: 1.843E-04 | global batch size: 512 | lm loss: 2.239654E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.595 | TFLOPs: 23.64 | +63: iteration 14700/ 73814 | consumed samples: 7526400 | consumed tokens: 15414067200 | elapsed time per iteration (s): 2.22 | learning rate: 1.843E-04 | global batch size: 512 | lm loss: 2.225743E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.336 | TFLOPs: 23.71 | +63: iteration 14710/ 73814 | consumed samples: 7531520 | consumed tokens: 15424552960 | elapsed time per iteration (s): 2.27 | learning rate: 1.842E-04 | global batch size: 512 | lm loss: 2.267954E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.946 | TFLOPs: 23.26 | +63: iteration 14720/ 73814 | consumed samples: 7536640 | consumed tokens: 15435038720 | elapsed time per iteration (s): 2.23 | learning rate: 1.842E-04 | global batch size: 512 | lm loss: 2.272285E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.349 | TFLOPs: 23.61 | +63: iteration 14730/ 73814 | consumed samples: 7541760 | consumed tokens: 15445524480 | elapsed time per iteration (s): 2.25 | learning rate: 1.842E-04 | global batch size: 512 | lm loss: 2.245312E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.875 | TFLOPs: 23.46 | +63: iteration 14740/ 73814 | consumed samples: 7546880 | consumed tokens: 15456010240 | elapsed time per iteration (s): 2.23 | learning rate: 1.842E-04 | global batch size: 512 | lm loss: 2.242079E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.530 | TFLOPs: 23.63 | +63: iteration 14750/ 73814 | consumed samples: 7552000 | consumed tokens: 15466496000 | elapsed time per iteration (s): 2.24 | learning rate: 1.842E-04 | global batch size: 512 | lm loss: 2.232817E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.110 | TFLOPs: 23.48 | +63: iteration 14760/ 73814 | consumed samples: 7557120 | consumed tokens: 15476981760 | elapsed time per iteration (s): 2.24 | learning rate: 1.841E-04 | global batch size: 512 | lm loss: 2.247502E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.695 | TFLOPs: 23.54 | +63: iteration 14770/ 73814 | consumed samples: 7562240 | consumed tokens: 15487467520 | elapsed time per iteration (s): 2.23 | learning rate: 1.841E-04 | global batch size: 512 | lm loss: 2.230793E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.274 | TFLOPs: 23.60 | +63: iteration 14780/ 73814 | consumed samples: 7567360 | consumed tokens: 15497953280 | elapsed time per iteration (s): 2.23 | learning rate: 1.841E-04 | global batch size: 512 | lm loss: 2.253384E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.118 | TFLOPs: 23.59 | +63: iteration 14790/ 73814 | consumed samples: 7572480 | consumed tokens: 15508439040 | elapsed time per iteration (s): 2.23 | learning rate: 1.841E-04 | global batch size: 512 | lm loss: 2.252246E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.958 | TFLOPs: 23.67 | +63: iteration 14800/ 73814 | consumed samples: 7577600 | consumed tokens: 15518924800 | elapsed time per iteration (s): 2.32 | learning rate: 1.840E-04 | global batch size: 512 | lm loss: 2.257011E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.876 | TFLOPs: 22.74 | +63: iteration 14810/ 73814 | consumed samples: 7582720 | consumed tokens: 15529410560 | elapsed time per iteration (s): 2.27 | learning rate: 1.840E-04 | global batch size: 512 | lm loss: 2.249164E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.542 | TFLOPs: 23.22 | +63: iteration 14820/ 73814 | consumed samples: 7587840 | consumed tokens: 15539896320 | elapsed time per iteration (s): 2.23 | learning rate: 1.840E-04 | global batch size: 512 | lm loss: 2.249535E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.527 | TFLOPs: 23.63 | +63: iteration 14830/ 73814 | consumed samples: 7592960 | consumed tokens: 15550382080 | elapsed time per iteration (s): 2.23 | learning rate: 1.840E-04 | global batch size: 512 | lm loss: 2.240433E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.773 | TFLOPs: 23.65 | +63: iteration 14840/ 73814 | consumed samples: 7598080 | consumed tokens: 15560867840 | elapsed time per iteration (s): 2.36 | learning rate: 1.840E-04 | global batch size: 512 | lm loss: 2.261938E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.041 | TFLOPs: 22.34 | +63: iteration 14850/ 73814 | consumed samples: 7603200 | consumed tokens: 15571353600 | elapsed time per iteration (s): 2.24 | learning rate: 1.839E-04 | global batch size: 512 | lm loss: 2.239847E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.426 | TFLOPs: 23.52 | +63: iteration 14860/ 73814 | consumed samples: 7608320 | consumed tokens: 15581839360 | elapsed time per iteration (s): 2.24 | learning rate: 1.839E-04 | global batch size: 512 | lm loss: 2.236571E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.679 | TFLOPs: 23.54 | +63: iteration 14870/ 73814 | consumed samples: 7613440 | consumed tokens: 15592325120 | elapsed time per iteration (s): 2.26 | learning rate: 1.839E-04 | global batch size: 512 | lm loss: 2.250223E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.885 | TFLOPs: 23.36 | +63: iteration 14880/ 73814 | consumed samples: 7618560 | consumed tokens: 15602810880 | elapsed time per iteration (s): 2.23 | learning rate: 1.839E-04 | global batch size: 512 | lm loss: 2.254417E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.706 | TFLOPs: 23.65 | +63: iteration 14890/ 73814 | consumed samples: 7623680 | consumed tokens: 15613296640 | elapsed time per iteration (s): 2.23 | learning rate: 1.839E-04 | global batch size: 512 | lm loss: 2.255197E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.460 | TFLOPs: 23.62 | +63: iteration 14900/ 73814 | consumed samples: 7628800 | consumed tokens: 15623782400 | elapsed time per iteration (s): 2.27 | learning rate: 1.838E-04 | global batch size: 512 | lm loss: 2.261037E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.171 | TFLOPs: 23.18 | +63: iteration 14910/ 73814 | consumed samples: 7633920 | consumed tokens: 15634268160 | elapsed time per iteration (s): 2.23 | learning rate: 1.838E-04 | global batch size: 512 | lm loss: 2.257249E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.438 | TFLOPs: 23.62 | +63: iteration 14920/ 73814 | consumed samples: 7639040 | consumed tokens: 15644753920 | elapsed time per iteration (s): 2.24 | learning rate: 1.838E-04 | global batch size: 512 | lm loss: 2.242578E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.168 | TFLOPs: 23.49 | +63: iteration 14930/ 73814 | consumed samples: 7644160 | consumed tokens: 15655239680 | elapsed time per iteration (s): 2.24 | learning rate: 1.838E-04 | global batch size: 512 | lm loss: 2.239293E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.283 | TFLOPs: 23.50 | +63: iteration 14940/ 73814 | consumed samples: 7649280 | consumed tokens: 15665725440 | elapsed time per iteration (s): 2.23 | learning rate: 1.837E-04 | global batch size: 512 | lm loss: 2.222493E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.676 | TFLOPs: 23.64 | +63: iteration 14950/ 73814 | consumed samples: 7654400 | consumed tokens: 15676211200 | elapsed time per iteration (s): 2.23 | learning rate: 1.837E-04 | global batch size: 512 | lm loss: 2.233852E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.732 | TFLOPs: 23.65 | +63: iteration 14960/ 73814 | consumed samples: 7659520 | consumed tokens: 15686696960 | elapsed time per iteration (s): 2.25 | learning rate: 1.837E-04 | global batch size: 512 | lm loss: 2.245294E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.579 | TFLOPs: 23.43 | +63: iteration 14970/ 73814 | consumed samples: 7664640 | consumed tokens: 15697182720 | elapsed time per iteration (s): 2.22 | learning rate: 1.837E-04 | global batch size: 512 | lm loss: 2.254067E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.346 | TFLOPs: 23.71 | +63: iteration 14980/ 73814 | consumed samples: 7669760 | consumed tokens: 15707668480 | elapsed time per iteration (s): 2.23 | learning rate: 1.837E-04 | global batch size: 512 | lm loss: 2.236012E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.398 | TFLOPs: 23.62 | +63: iteration 14990/ 73814 | consumed samples: 7674880 | consumed tokens: 15718154240 | elapsed time per iteration (s): 2.22 | learning rate: 1.836E-04 | global batch size: 512 | lm loss: 2.240800E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.380 | TFLOPs: 23.72 | +63: iteration 15000/ 73814 | consumed samples: 7680000 | consumed tokens: 15728640000 | elapsed time per iteration (s): 2.25 | learning rate: 1.836E-04 | global batch size: 512 | lm loss: 2.258751E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.700 | TFLOPs: 23.44 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 15000 | lm loss value: 2.147362E+00 | lm loss PPL: 8.562245E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 15010/ 73814 | consumed samples: 7685120 | consumed tokens: 15739125760 | elapsed time per iteration (s): 2.30 | learning rate: 1.836E-04 | global batch size: 512 | lm loss: 2.218462E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.264 | TFLOPs: 22.88 | +63: iteration 15020/ 73814 | consumed samples: 7690240 | consumed tokens: 15749611520 | elapsed time per iteration (s): 2.23 | learning rate: 1.836E-04 | global batch size: 512 | lm loss: 2.246775E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.922 | TFLOPs: 23.67 | +63: iteration 15030/ 73814 | consumed samples: 7695360 | consumed tokens: 15760097280 | elapsed time per iteration (s): 2.23 | learning rate: 1.835E-04 | global batch size: 512 | lm loss: 2.249998E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.952 | TFLOPs: 23.67 | +63: iteration 15040/ 73814 | consumed samples: 7700480 | consumed tokens: 15770583040 | elapsed time per iteration (s): 2.24 | learning rate: 1.835E-04 | global batch size: 512 | lm loss: 2.261909E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.397 | TFLOPs: 23.51 | +63: iteration 15050/ 73814 | consumed samples: 7705600 | consumed tokens: 15781068800 | elapsed time per iteration (s): 2.24 | learning rate: 1.835E-04 | global batch size: 512 | lm loss: 2.233141E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.680 | TFLOPs: 23.54 | +63: iteration 15060/ 73814 | consumed samples: 7710720 | consumed tokens: 15791554560 | elapsed time per iteration (s): 2.25 | learning rate: 1.835E-04 | global batch size: 512 | lm loss: 2.239708E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.899 | TFLOPs: 23.46 | +63: iteration 15070/ 73814 | consumed samples: 7715840 | consumed tokens: 15802040320 | elapsed time per iteration (s): 2.23 | learning rate: 1.835E-04 | global batch size: 512 | lm loss: 2.245682E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.698 | TFLOPs: 23.65 | +63: iteration 15080/ 73814 | consumed samples: 7720960 | consumed tokens: 15812526080 | elapsed time per iteration (s): 2.26 | learning rate: 1.834E-04 | global batch size: 512 | lm loss: 2.242163E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.872 | TFLOPs: 23.36 | +63: iteration 15090/ 73814 | consumed samples: 7726080 | consumed tokens: 15823011840 | elapsed time per iteration (s): 2.31 | learning rate: 1.834E-04 | global batch size: 512 | lm loss: 2.253310E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.788 | TFLOPs: 22.83 | +63: iteration 15100/ 73814 | consumed samples: 7731200 | consumed tokens: 15833497600 | elapsed time per iteration (s): 2.32 | learning rate: 1.834E-04 | global batch size: 512 | lm loss: 2.276082E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.277 | TFLOPs: 22.68 | +63: iteration 15110/ 73814 | consumed samples: 7736320 | consumed tokens: 15843983360 | elapsed time per iteration (s): 2.34 | learning rate: 1.834E-04 | global batch size: 512 | lm loss: 2.234883E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.701 | TFLOPs: 22.51 | +63: iteration 15120/ 73814 | consumed samples: 7741440 | consumed tokens: 15854469120 | elapsed time per iteration (s): 2.38 | learning rate: 1.833E-04 | global batch size: 512 | lm loss: 2.266608E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.430 | TFLOPs: 22.18 | +63: iteration 15130/ 73814 | consumed samples: 7746560 | consumed tokens: 15864954880 | elapsed time per iteration (s): 2.34 | learning rate: 1.833E-04 | global batch size: 512 | lm loss: 2.247935E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.351 | TFLOPs: 22.48 | +63: iteration 15140/ 73814 | consumed samples: 7751680 | consumed tokens: 15875440640 | elapsed time per iteration (s): 2.43 | learning rate: 1.833E-04 | global batch size: 512 | lm loss: 2.238216E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.872 | TFLOPs: 21.71 | +63: iteration 15150/ 73814 | consumed samples: 7756800 | consumed tokens: 15885926400 | elapsed time per iteration (s): 2.49 | learning rate: 1.833E-04 | global batch size: 512 | lm loss: 2.248799E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.735 | TFLOPs: 21.18 | +63: iteration 15160/ 73814 | consumed samples: 7761920 | consumed tokens: 15896412160 | elapsed time per iteration (s): 2.31 | learning rate: 1.832E-04 | global batch size: 512 | lm loss: 2.267768E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.527 | TFLOPs: 22.81 | +63: iteration 15170/ 73814 | consumed samples: 7767040 | consumed tokens: 15906897920 | elapsed time per iteration (s): 2.26 | learning rate: 1.832E-04 | global batch size: 512 | lm loss: 2.235526E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.079 | TFLOPs: 23.27 | +63: iteration 15180/ 73814 | consumed samples: 7772160 | consumed tokens: 15917383680 | elapsed time per iteration (s): 2.26 | learning rate: 1.832E-04 | global batch size: 512 | lm loss: 2.266937E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.212 | TFLOPs: 23.29 | +63: iteration 15190/ 73814 | consumed samples: 7777280 | consumed tokens: 15927869440 | elapsed time per iteration (s): 2.64 | learning rate: 1.832E-04 | global batch size: 512 | lm loss: 2.228656E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 193.647 | TFLOPs: 19.94 | +63: iteration 15200/ 73814 | consumed samples: 7782400 | consumed tokens: 15938355200 | elapsed time per iteration (s): 2.30 | learning rate: 1.832E-04 | global batch size: 512 | lm loss: 2.263333E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.739 | TFLOPs: 22.93 | +63: iteration 15210/ 73814 | consumed samples: 7787520 | consumed tokens: 15948840960 | elapsed time per iteration (s): 2.32 | learning rate: 1.831E-04 | global batch size: 512 | lm loss: 2.278925E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.719 | TFLOPs: 22.72 | +63: iteration 15220/ 73814 | consumed samples: 7792640 | consumed tokens: 15959326720 | elapsed time per iteration (s): 2.24 | learning rate: 1.831E-04 | global batch size: 512 | lm loss: 2.223001E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.056 | TFLOPs: 23.58 | +63: iteration 15230/ 73814 | consumed samples: 7797760 | consumed tokens: 15969812480 | elapsed time per iteration (s): 2.23 | learning rate: 1.831E-04 | global batch size: 512 | lm loss: 2.229542E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.910 | TFLOPs: 23.67 | +63: iteration 15240/ 73814 | consumed samples: 7802880 | consumed tokens: 15980298240 | elapsed time per iteration (s): 2.23 | learning rate: 1.831E-04 | global batch size: 512 | lm loss: 2.234788E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.978 | TFLOPs: 23.68 | +63: iteration 15250/ 73814 | consumed samples: 7808000 | consumed tokens: 15990784000 | elapsed time per iteration (s): 2.23 | learning rate: 1.830E-04 | global batch size: 512 | lm loss: 2.246557E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.526 | TFLOPs: 23.63 | +63: iteration 15260/ 73814 | consumed samples: 7813120 | consumed tokens: 16001269760 | elapsed time per iteration (s): 2.23 | learning rate: 1.830E-04 | global batch size: 512 | lm loss: 2.221829E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.804 | TFLOPs: 23.66 | +63: iteration 15270/ 73814 | consumed samples: 7818240 | consumed tokens: 16011755520 | elapsed time per iteration (s): 2.28 | learning rate: 1.830E-04 | global batch size: 512 | lm loss: 2.249355E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.845 | TFLOPs: 23.15 | +63: iteration 15280/ 73814 | consumed samples: 7823360 | consumed tokens: 16022241280 | elapsed time per iteration (s): 2.50 | learning rate: 1.830E-04 | global batch size: 512 | lm loss: 2.239737E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 204.664 | TFLOPs: 21.07 | +63: iteration 15290/ 73814 | consumed samples: 7828480 | consumed tokens: 16032727040 | elapsed time per iteration (s): 2.26 | learning rate: 1.830E-04 | global batch size: 512 | lm loss: 2.243782E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.705 | TFLOPs: 23.34 | +63: iteration 15300/ 73814 | consumed samples: 7833600 | consumed tokens: 16043212800 | elapsed time per iteration (s): 2.25 | learning rate: 1.829E-04 | global batch size: 512 | lm loss: 2.228030E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.559 | TFLOPs: 23.43 | +63: iteration 15310/ 73814 | consumed samples: 7838720 | consumed tokens: 16053698560 | elapsed time per iteration (s): 2.25 | learning rate: 1.829E-04 | global batch size: 512 | lm loss: 2.265209E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.873 | TFLOPs: 23.46 | +63: iteration 15320/ 73814 | consumed samples: 7843840 | consumed tokens: 16064184320 | elapsed time per iteration (s): 2.23 | learning rate: 1.829E-04 | global batch size: 512 | lm loss: 2.250774E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.836 | TFLOPs: 23.66 | +63: iteration 15330/ 73814 | consumed samples: 7848960 | consumed tokens: 16074670080 | elapsed time per iteration (s): 2.23 | learning rate: 1.829E-04 | global batch size: 512 | lm loss: 2.241812E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.714 | TFLOPs: 23.65 | +63: iteration 15340/ 73814 | consumed samples: 7854080 | consumed tokens: 16085155840 | elapsed time per iteration (s): 2.24 | learning rate: 1.828E-04 | global batch size: 512 | lm loss: 2.238900E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.154 | TFLOPs: 23.49 | +63: iteration 15350/ 73814 | consumed samples: 7859200 | consumed tokens: 16095641600 | elapsed time per iteration (s): 2.27 | learning rate: 1.828E-04 | global batch size: 512 | lm loss: 2.227750E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.678 | TFLOPs: 23.23 | +63: iteration 15360/ 73814 | consumed samples: 7864320 | consumed tokens: 16106127360 | elapsed time per iteration (s): 2.26 | learning rate: 1.828E-04 | global batch size: 512 | lm loss: 2.221270E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.645 | TFLOPs: 23.33 | +63: iteration 15370/ 73814 | consumed samples: 7869440 | consumed tokens: 16116613120 | elapsed time per iteration (s): 2.24 | learning rate: 1.828E-04 | global batch size: 512 | lm loss: 2.231286E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.837 | TFLOPs: 23.56 | +63: iteration 15380/ 73814 | consumed samples: 7874560 | consumed tokens: 16127098880 | elapsed time per iteration (s): 2.23 | learning rate: 1.828E-04 | global batch size: 512 | lm loss: 2.268191E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.443 | TFLOPs: 23.62 | +63: iteration 15390/ 73814 | consumed samples: 7879680 | consumed tokens: 16137584640 | elapsed time per iteration (s): 2.31 | learning rate: 1.827E-04 | global batch size: 512 | lm loss: 2.236303E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.906 | TFLOPs: 22.84 | +63: iteration 15400/ 73814 | consumed samples: 7884800 | consumed tokens: 16148070400 | elapsed time per iteration (s): 2.27 | learning rate: 1.827E-04 | global batch size: 512 | lm loss: 2.230241E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.592 | TFLOPs: 23.22 | +63: iteration 15410/ 73814 | consumed samples: 7889920 | consumed tokens: 16158556160 | elapsed time per iteration (s): 2.25 | learning rate: 1.827E-04 | global batch size: 512 | lm loss: 2.219876E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.783 | TFLOPs: 23.45 | +63: iteration 15420/ 73814 | consumed samples: 7895040 | consumed tokens: 16169041920 | elapsed time per iteration (s): 2.22 | learning rate: 1.827E-04 | global batch size: 512 | lm loss: 2.228075E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.132 | TFLOPs: 23.69 | +63: iteration 15430/ 73814 | consumed samples: 7900160 | consumed tokens: 16179527680 | elapsed time per iteration (s): 2.31 | learning rate: 1.826E-04 | global batch size: 512 | lm loss: 2.232249E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.935 | TFLOPs: 22.85 | +63: iteration 15440/ 73814 | consumed samples: 7905280 | consumed tokens: 16190013440 | elapsed time per iteration (s): 2.25 | learning rate: 1.826E-04 | global batch size: 512 | lm loss: 2.236814E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.053 | TFLOPs: 23.48 | +63: iteration 15450/ 73814 | consumed samples: 7910400 | consumed tokens: 16200499200 | elapsed time per iteration (s): 2.41 | learning rate: 1.826E-04 | global batch size: 512 | lm loss: 2.248515E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.459 | TFLOPs: 21.87 | +63: iteration 15460/ 73814 | consumed samples: 7915520 | consumed tokens: 16210984960 | elapsed time per iteration (s): 2.30 | learning rate: 1.826E-04 | global batch size: 512 | lm loss: 2.249883E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.847 | TFLOPs: 22.94 | +63: iteration 15470/ 73814 | consumed samples: 7920640 | consumed tokens: 16221470720 | elapsed time per iteration (s): 2.24 | learning rate: 1.825E-04 | global batch size: 512 | lm loss: 2.242914E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.247 | TFLOPs: 23.50 | +63: iteration 15480/ 73814 | consumed samples: 7925760 | consumed tokens: 16231956480 | elapsed time per iteration (s): 2.37 | learning rate: 1.825E-04 | global batch size: 512 | lm loss: 2.216184E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.097 | TFLOPs: 22.25 | +63: iteration 15490/ 73814 | consumed samples: 7930880 | consumed tokens: 16242442240 | elapsed time per iteration (s): 2.23 | learning rate: 1.825E-04 | global batch size: 512 | lm loss: 2.225705E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.537 | TFLOPs: 23.63 | +63: iteration 15500/ 73814 | consumed samples: 7936000 | consumed tokens: 16252928000 | elapsed time per iteration (s): 2.24 | learning rate: 1.825E-04 | global batch size: 512 | lm loss: 2.212577E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.292 | TFLOPs: 23.50 | +63: iteration 15510/ 73814 | consumed samples: 7941120 | consumed tokens: 16263413760 | elapsed time per iteration (s): 2.23 | learning rate: 1.825E-04 | global batch size: 512 | lm loss: 2.238728E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.769 | TFLOPs: 23.65 | +63: iteration 15520/ 73814 | consumed samples: 7946240 | consumed tokens: 16273899520 | elapsed time per iteration (s): 2.24 | learning rate: 1.824E-04 | global batch size: 512 | lm loss: 2.236735E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.663 | TFLOPs: 23.54 | +63: iteration 15530/ 73814 | consumed samples: 7951360 | consumed tokens: 16284385280 | elapsed time per iteration (s): 2.24 | learning rate: 1.824E-04 | global batch size: 512 | lm loss: 2.231900E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.819 | TFLOPs: 23.56 | +63: iteration 15540/ 73814 | consumed samples: 7956480 | consumed tokens: 16294871040 | elapsed time per iteration (s): 2.25 | learning rate: 1.824E-04 | global batch size: 512 | lm loss: 2.232783E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.964 | TFLOPs: 23.47 | +63: iteration 15550/ 73814 | consumed samples: 7961600 | consumed tokens: 16305356800 | elapsed time per iteration (s): 2.23 | learning rate: 1.824E-04 | global batch size: 512 | lm loss: 2.226620E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.913 | TFLOPs: 23.67 | +63: iteration 15560/ 73814 | consumed samples: 7966720 | consumed tokens: 16315842560 | elapsed time per iteration (s): 2.26 | learning rate: 1.823E-04 | global batch size: 512 | lm loss: 2.225549E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.505 | TFLOPs: 23.32 | +63: iteration 15570/ 73814 | consumed samples: 7971840 | consumed tokens: 16326328320 | elapsed time per iteration (s): 2.30 | learning rate: 1.823E-04 | global batch size: 512 | lm loss: 2.226610E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.474 | TFLOPs: 22.90 | +63: iteration 15580/ 73814 | consumed samples: 7976960 | consumed tokens: 16336814080 | elapsed time per iteration (s): 2.23 | learning rate: 1.823E-04 | global batch size: 512 | lm loss: 2.230495E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.482 | TFLOPs: 23.62 | +63: iteration 15590/ 73814 | consumed samples: 7982080 | consumed tokens: 16347299840 | elapsed time per iteration (s): 2.24 | learning rate: 1.823E-04 | global batch size: 512 | lm loss: 2.235134E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.076 | TFLOPs: 23.58 | +63: iteration 15600/ 73814 | consumed samples: 7987200 | consumed tokens: 16357785600 | elapsed time per iteration (s): 2.26 | learning rate: 1.822E-04 | global batch size: 512 | lm loss: 2.230338E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.875 | TFLOPs: 23.36 | +63: iteration 15610/ 73814 | consumed samples: 7992320 | consumed tokens: 16368271360 | elapsed time per iteration (s): 2.23 | learning rate: 1.822E-04 | global batch size: 512 | lm loss: 2.244384E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.189 | TFLOPs: 23.59 | +63: iteration 15620/ 73814 | consumed samples: 7997440 | consumed tokens: 16378757120 | elapsed time per iteration (s): 2.28 | learning rate: 1.822E-04 | global batch size: 512 | lm loss: 2.223679E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.574 | TFLOPs: 23.12 | +63: iteration 15630/ 73814 | consumed samples: 8002560 | consumed tokens: 16389242880 | elapsed time per iteration (s): 2.26 | learning rate: 1.822E-04 | global batch size: 512 | lm loss: 2.237334E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.748 | TFLOPs: 23.34 | +63: iteration 15640/ 73814 | consumed samples: 8007680 | consumed tokens: 16399728640 | elapsed time per iteration (s): 2.23 | learning rate: 1.822E-04 | global batch size: 512 | lm loss: 2.237467E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.194 | TFLOPs: 23.59 | +63: iteration 15650/ 73814 | consumed samples: 8012800 | consumed tokens: 16410214400 | elapsed time per iteration (s): 2.25 | learning rate: 1.821E-04 | global batch size: 512 | lm loss: 2.240512E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.853 | TFLOPs: 23.46 | +63: iteration 15660/ 73814 | consumed samples: 8017920 | consumed tokens: 16420700160 | elapsed time per iteration (s): 2.24 | learning rate: 1.821E-04 | global batch size: 512 | lm loss: 2.254098E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.359 | TFLOPs: 23.51 | +63: iteration 15670/ 73814 | consumed samples: 8023040 | consumed tokens: 16431185920 | elapsed time per iteration (s): 2.29 | learning rate: 1.821E-04 | global batch size: 512 | lm loss: 2.235872E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.899 | TFLOPs: 23.05 | +63: iteration 15680/ 73814 | consumed samples: 8028160 | consumed tokens: 16441671680 | elapsed time per iteration (s): 2.26 | learning rate: 1.821E-04 | global batch size: 512 | lm loss: 2.231553E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.608 | TFLOPs: 23.33 | +63: iteration 15690/ 73814 | consumed samples: 8033280 | consumed tokens: 16452157440 | elapsed time per iteration (s): 2.22 | learning rate: 1.820E-04 | global batch size: 512 | lm loss: 2.231574E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.499 | TFLOPs: 23.73 | +63: iteration 15700/ 73814 | consumed samples: 8038400 | consumed tokens: 16462643200 | elapsed time per iteration (s): 2.23 | learning rate: 1.820E-04 | global batch size: 512 | lm loss: 2.236914E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.110 | TFLOPs: 23.59 | +63: iteration 15710/ 73814 | consumed samples: 8043520 | consumed tokens: 16473128960 | elapsed time per iteration (s): 2.23 | learning rate: 1.820E-04 | global batch size: 512 | lm loss: 2.204438E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.174 | TFLOPs: 23.59 | +63: iteration 15720/ 73814 | consumed samples: 8048640 | consumed tokens: 16483614720 | elapsed time per iteration (s): 2.25 | learning rate: 1.820E-04 | global batch size: 512 | lm loss: 2.230239E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.286 | TFLOPs: 23.40 | +63: iteration 15730/ 73814 | consumed samples: 8053760 | consumed tokens: 16494100480 | elapsed time per iteration (s): 2.34 | learning rate: 1.819E-04 | global batch size: 512 | lm loss: 2.230597E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.365 | TFLOPs: 22.48 | +63: iteration 15740/ 73814 | consumed samples: 8058880 | consumed tokens: 16504586240 | elapsed time per iteration (s): 2.22 | learning rate: 1.819E-04 | global batch size: 512 | lm loss: 2.227459E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.327 | TFLOPs: 23.71 | +63: iteration 15750/ 73814 | consumed samples: 8064000 | consumed tokens: 16515072000 | elapsed time per iteration (s): 2.24 | learning rate: 1.819E-04 | global batch size: 512 | lm loss: 2.230771E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.781 | TFLOPs: 23.55 | +63: iteration 15760/ 73814 | consumed samples: 8069120 | consumed tokens: 16525557760 | elapsed time per iteration (s): 2.23 | learning rate: 1.819E-04 | global batch size: 512 | lm loss: 2.234644E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.796 | TFLOPs: 23.66 | +63: iteration 15770/ 73814 | consumed samples: 8074240 | consumed tokens: 16536043520 | elapsed time per iteration (s): 2.22 | learning rate: 1.819E-04 | global batch size: 512 | lm loss: 2.218672E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.415 | TFLOPs: 23.72 | +63: iteration 15780/ 73814 | consumed samples: 8079360 | consumed tokens: 16546529280 | elapsed time per iteration (s): 2.23 | learning rate: 1.818E-04 | global batch size: 512 | lm loss: 2.241992E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.817 | TFLOPs: 23.66 | +63: iteration 15790/ 73814 | consumed samples: 8084480 | consumed tokens: 16557015040 | elapsed time per iteration (s): 2.23 | learning rate: 1.818E-04 | global batch size: 512 | lm loss: 2.258646E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.960 | TFLOPs: 23.67 | +63: iteration 15800/ 73814 | consumed samples: 8089600 | consumed tokens: 16567500800 | elapsed time per iteration (s): 2.23 | learning rate: 1.818E-04 | global batch size: 512 | lm loss: 2.260485E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.267 | TFLOPs: 23.60 | +63: iteration 15810/ 73814 | consumed samples: 8094720 | consumed tokens: 16577986560 | elapsed time per iteration (s): 2.23 | learning rate: 1.818E-04 | global batch size: 512 | lm loss: 2.247794E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.716 | TFLOPs: 23.65 | +63: iteration 15820/ 73814 | consumed samples: 8099840 | consumed tokens: 16588472320 | elapsed time per iteration (s): 2.27 | learning rate: 1.817E-04 | global batch size: 512 | lm loss: 2.230680E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.229 | TFLOPs: 23.19 | +63: iteration 15830/ 73814 | consumed samples: 8104960 | consumed tokens: 16598958080 | elapsed time per iteration (s): 2.23 | learning rate: 1.817E-04 | global batch size: 512 | lm loss: 2.229206E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.773 | TFLOPs: 23.65 | +63: iteration 15840/ 73814 | consumed samples: 8110080 | consumed tokens: 16609443840 | elapsed time per iteration (s): 2.24 | learning rate: 1.817E-04 | global batch size: 512 | lm loss: 2.240925E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.430 | TFLOPs: 23.52 | +63: iteration 15850/ 73814 | consumed samples: 8115200 | consumed tokens: 16619929600 | elapsed time per iteration (s): 2.22 | learning rate: 1.817E-04 | global batch size: 512 | lm loss: 2.227346E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.133 | TFLOPs: 23.69 | +63: iteration 15860/ 73814 | consumed samples: 8120320 | consumed tokens: 16630415360 | elapsed time per iteration (s): 2.25 | learning rate: 1.816E-04 | global batch size: 512 | lm loss: 2.228730E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.844 | TFLOPs: 23.46 | +63: iteration 15870/ 73814 | consumed samples: 8125440 | consumed tokens: 16640901120 | elapsed time per iteration (s): 2.23 | learning rate: 1.816E-04 | global batch size: 512 | lm loss: 2.231746E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.061 | TFLOPs: 23.68 | +63: iteration 15880/ 73814 | consumed samples: 8130560 | consumed tokens: 16651386880 | elapsed time per iteration (s): 2.25 | learning rate: 1.816E-04 | global batch size: 512 | lm loss: 2.225132E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.848 | TFLOPs: 23.46 | +63: iteration 15890/ 73814 | consumed samples: 8135680 | consumed tokens: 16661872640 | elapsed time per iteration (s): 2.23 | learning rate: 1.816E-04 | global batch size: 512 | lm loss: 2.244456E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.619 | TFLOPs: 23.64 | +63: iteration 15900/ 73814 | consumed samples: 8140800 | consumed tokens: 16672358400 | elapsed time per iteration (s): 2.22 | learning rate: 1.815E-04 | global batch size: 512 | lm loss: 2.223605E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.513 | TFLOPs: 23.73 | +63: iteration 15910/ 73814 | consumed samples: 8145920 | consumed tokens: 16682844160 | elapsed time per iteration (s): 2.23 | learning rate: 1.815E-04 | global batch size: 512 | lm loss: 2.234198E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.965 | TFLOPs: 23.67 | +63: iteration 15920/ 73814 | consumed samples: 8151040 | consumed tokens: 16693329920 | elapsed time per iteration (s): 2.23 | learning rate: 1.815E-04 | global batch size: 512 | lm loss: 2.234515E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.161 | TFLOPs: 23.59 | +63: iteration 15930/ 73814 | consumed samples: 8156160 | consumed tokens: 16703815680 | elapsed time per iteration (s): 2.25 | learning rate: 1.815E-04 | global batch size: 512 | lm loss: 2.215918E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.741 | TFLOPs: 23.44 | +63: iteration 15940/ 73814 | consumed samples: 8161280 | consumed tokens: 16714301440 | elapsed time per iteration (s): 2.31 | learning rate: 1.815E-04 | global batch size: 512 | lm loss: 2.210932E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.788 | TFLOPs: 22.83 | +63: iteration 15950/ 73814 | consumed samples: 8166400 | consumed tokens: 16724787200 | elapsed time per iteration (s): 2.25 | learning rate: 1.814E-04 | global batch size: 512 | lm loss: 2.226594E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.453 | TFLOPs: 23.42 | +63: iteration 15960/ 73814 | consumed samples: 8171520 | consumed tokens: 16735272960 | elapsed time per iteration (s): 2.23 | learning rate: 1.814E-04 | global batch size: 512 | lm loss: 2.206502E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.483 | TFLOPs: 23.62 | +63: iteration 15970/ 73814 | consumed samples: 8176640 | consumed tokens: 16745758720 | elapsed time per iteration (s): 2.25 | learning rate: 1.814E-04 | global batch size: 512 | lm loss: 2.243919E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.790 | TFLOPs: 23.45 | +63: iteration 15980/ 73814 | consumed samples: 8181760 | consumed tokens: 16756244480 | elapsed time per iteration (s): 2.22 | learning rate: 1.814E-04 | global batch size: 512 | lm loss: 2.247636E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.269 | TFLOPs: 23.71 | +63: iteration 15990/ 73814 | consumed samples: 8186880 | consumed tokens: 16766730240 | elapsed time per iteration (s): 2.23 | learning rate: 1.813E-04 | global batch size: 512 | lm loss: 2.233838E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.568 | TFLOPs: 23.63 | + 0: [2022-12-01 21:57:24,065] [INFO] [logging.py:68:log_dist] [Rank 0] step=16000, skipped=0, lr=[0.00018131305699812354, 0.00018131305699812354, 0.00018131305699812354], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] + 0: steps: 16000 loss: 2.2603 iter time (s): 2.252 samples/sec: 227.333 +63: iteration 16000/ 73814 | consumed samples: 8192000 | consumed tokens: 16777216000 | elapsed time per iteration (s): 2.24 | learning rate: 1.813E-04 | global batch size: 512 | lm loss: 2.227007E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.496 | TFLOPs: 23.52 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 16000 | lm loss value: 2.183786E+00 | lm loss PPL: 8.879861E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 16010/ 73814 | consumed samples: 8197120 | consumed tokens: 16787701760 | elapsed time per iteration (s): 2.29 | learning rate: 1.813E-04 | global batch size: 512 | lm loss: 2.220899E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.056 | TFLOPs: 23.07 | +63: iteration 16020/ 73814 | consumed samples: 8202240 | consumed tokens: 16798187520 | elapsed time per iteration (s): 2.23 | learning rate: 1.813E-04 | global batch size: 512 | lm loss: 2.247190E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.246 | TFLOPs: 23.60 | +63: iteration 16030/ 73814 | consumed samples: 8207360 | consumed tokens: 16808673280 | elapsed time per iteration (s): 2.22 | learning rate: 1.812E-04 | global batch size: 512 | lm loss: 2.237818E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.243 | TFLOPs: 23.70 | +63: iteration 16040/ 73814 | consumed samples: 8212480 | consumed tokens: 16819159040 | elapsed time per iteration (s): 2.23 | learning rate: 1.812E-04 | global batch size: 512 | lm loss: 2.219868E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.776 | TFLOPs: 23.65 | +63: iteration 16050/ 73814 | consumed samples: 8217600 | consumed tokens: 16829644800 | elapsed time per iteration (s): 2.23 | learning rate: 1.812E-04 | global batch size: 512 | lm loss: 2.211180E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.654 | TFLOPs: 23.64 | +63: iteration 16060/ 73814 | consumed samples: 8222720 | consumed tokens: 16840130560 | elapsed time per iteration (s): 2.25 | learning rate: 1.812E-04 | global batch size: 512 | lm loss: 2.217960E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.020 | TFLOPs: 23.47 | +63: iteration 16070/ 73814 | consumed samples: 8227840 | consumed tokens: 16850616320 | elapsed time per iteration (s): 2.24 | learning rate: 1.811E-04 | global batch size: 512 | lm loss: 2.245742E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.901 | TFLOPs: 23.56 | +63: iteration 16080/ 73814 | consumed samples: 8232960 | consumed tokens: 16861102080 | elapsed time per iteration (s): 2.23 | learning rate: 1.811E-04 | global batch size: 512 | lm loss: 2.226408E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.700 | TFLOPs: 23.65 | +63: iteration 16090/ 73814 | consumed samples: 8238080 | consumed tokens: 16871587840 | elapsed time per iteration (s): 2.22 | learning rate: 1.811E-04 | global batch size: 512 | lm loss: 2.210062E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.342 | TFLOPs: 23.71 | +63: iteration 16100/ 73814 | consumed samples: 8243200 | consumed tokens: 16882073600 | elapsed time per iteration (s): 2.23 | learning rate: 1.811E-04 | global batch size: 512 | lm loss: 2.213621E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.629 | TFLOPs: 23.64 | +63: iteration 16110/ 73814 | consumed samples: 8248320 | consumed tokens: 16892559360 | elapsed time per iteration (s): 2.24 | learning rate: 1.811E-04 | global batch size: 512 | lm loss: 2.224769E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.097 | TFLOPs: 23.48 | +63: iteration 16120/ 73814 | consumed samples: 8253440 | consumed tokens: 16903045120 | elapsed time per iteration (s): 2.24 | learning rate: 1.810E-04 | global batch size: 512 | lm loss: 2.225478E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.206 | TFLOPs: 23.49 | +63: iteration 16130/ 73814 | consumed samples: 8258560 | consumed tokens: 16913530880 | elapsed time per iteration (s): 2.23 | learning rate: 1.810E-04 | global batch size: 512 | lm loss: 2.245727E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.182 | TFLOPs: 23.59 | +63: iteration 16140/ 73814 | consumed samples: 8263680 | consumed tokens: 16924016640 | elapsed time per iteration (s): 2.23 | learning rate: 1.810E-04 | global batch size: 512 | lm loss: 2.210911E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.702 | TFLOPs: 23.65 | +63: iteration 16150/ 73814 | consumed samples: 8268800 | consumed tokens: 16934502400 | elapsed time per iteration (s): 2.26 | learning rate: 1.810E-04 | global batch size: 512 | lm loss: 2.222839E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.594 | TFLOPs: 23.33 | +63: iteration 16160/ 73814 | consumed samples: 8273920 | consumed tokens: 16944988160 | elapsed time per iteration (s): 2.23 | learning rate: 1.809E-04 | global batch size: 512 | lm loss: 2.239654E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.766 | TFLOPs: 23.65 | +63: iteration 16170/ 73814 | consumed samples: 8279040 | consumed tokens: 16955473920 | elapsed time per iteration (s): 2.25 | learning rate: 1.809E-04 | global batch size: 512 | lm loss: 2.214417E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.991 | TFLOPs: 23.47 | +63: iteration 16180/ 73814 | consumed samples: 8284160 | consumed tokens: 16965959680 | elapsed time per iteration (s): 2.24 | learning rate: 1.809E-04 | global batch size: 512 | lm loss: 2.228404E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.529 | TFLOPs: 23.53 | +63: iteration 16190/ 73814 | consumed samples: 8289280 | consumed tokens: 16976445440 | elapsed time per iteration (s): 2.23 | learning rate: 1.809E-04 | global batch size: 512 | lm loss: 2.207952E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.092 | TFLOPs: 23.58 | +63: iteration 16200/ 73814 | consumed samples: 8294400 | consumed tokens: 16986931200 | elapsed time per iteration (s): 2.25 | learning rate: 1.808E-04 | global batch size: 512 | lm loss: 2.235960E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.288 | TFLOPs: 23.40 | +63: iteration 16210/ 73814 | consumed samples: 8299520 | consumed tokens: 16997416960 | elapsed time per iteration (s): 2.24 | learning rate: 1.808E-04 | global batch size: 512 | lm loss: 2.231627E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.360 | TFLOPs: 23.51 | +63: iteration 16220/ 73814 | consumed samples: 8304640 | consumed tokens: 17007902720 | elapsed time per iteration (s): 2.26 | learning rate: 1.808E-04 | global batch size: 512 | lm loss: 2.219069E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.629 | TFLOPs: 23.33 | +63: iteration 16230/ 73814 | consumed samples: 8309760 | consumed tokens: 17018388480 | elapsed time per iteration (s): 2.22 | learning rate: 1.808E-04 | global batch size: 512 | lm loss: 2.231528E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.145 | TFLOPs: 23.69 | +63: iteration 16240/ 73814 | consumed samples: 8314880 | consumed tokens: 17028874240 | elapsed time per iteration (s): 2.25 | learning rate: 1.807E-04 | global batch size: 512 | lm loss: 2.231098E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.521 | TFLOPs: 23.42 | +63: iteration 16250/ 73814 | consumed samples: 8320000 | consumed tokens: 17039360000 | elapsed time per iteration (s): 2.23 | learning rate: 1.807E-04 | global batch size: 512 | lm loss: 2.226990E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.026 | TFLOPs: 23.68 | +63: iteration 16260/ 73814 | consumed samples: 8325120 | consumed tokens: 17049845760 | elapsed time per iteration (s): 2.23 | learning rate: 1.807E-04 | global batch size: 512 | lm loss: 2.234414E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.703 | TFLOPs: 23.65 | +63: iteration 16270/ 73814 | consumed samples: 8330240 | consumed tokens: 17060331520 | elapsed time per iteration (s): 2.24 | learning rate: 1.807E-04 | global batch size: 512 | lm loss: 2.197708E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.268 | TFLOPs: 23.50 | +63: iteration 16280/ 73814 | consumed samples: 8335360 | consumed tokens: 17070817280 | elapsed time per iteration (s): 2.26 | learning rate: 1.806E-04 | global batch size: 512 | lm loss: 2.260530E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.313 | TFLOPs: 23.30 | +63: iteration 16290/ 73814 | consumed samples: 8340480 | consumed tokens: 17081303040 | elapsed time per iteration (s): 2.23 | learning rate: 1.806E-04 | global batch size: 512 | lm loss: 2.217120E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.711 | TFLOPs: 23.65 | +63: iteration 16300/ 73814 | consumed samples: 8345600 | consumed tokens: 17091788800 | elapsed time per iteration (s): 2.22 | learning rate: 1.806E-04 | global batch size: 512 | lm loss: 2.209665E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.470 | TFLOPs: 23.73 | +63: iteration 16310/ 73814 | consumed samples: 8350720 | consumed tokens: 17102274560 | elapsed time per iteration (s): 2.23 | learning rate: 1.806E-04 | global batch size: 512 | lm loss: 2.219737E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.042 | TFLOPs: 23.68 | +63: iteration 16320/ 73814 | consumed samples: 8355840 | consumed tokens: 17112760320 | elapsed time per iteration (s): 2.23 | learning rate: 1.806E-04 | global batch size: 512 | lm loss: 2.244376E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.828 | TFLOPs: 23.66 | +63: iteration 16330/ 73814 | consumed samples: 8360960 | consumed tokens: 17123246080 | elapsed time per iteration (s): 2.24 | learning rate: 1.805E-04 | global batch size: 512 | lm loss: 2.224066E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.544 | TFLOPs: 23.53 | +63: iteration 16340/ 73814 | consumed samples: 8366080 | consumed tokens: 17133731840 | elapsed time per iteration (s): 2.23 | learning rate: 1.805E-04 | global batch size: 512 | lm loss: 2.188983E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.154 | TFLOPs: 23.59 | +63: iteration 16350/ 73814 | consumed samples: 8371200 | consumed tokens: 17144217600 | elapsed time per iteration (s): 2.23 | learning rate: 1.805E-04 | global batch size: 512 | lm loss: 2.208722E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.856 | TFLOPs: 23.66 | +63: iteration 16360/ 73814 | consumed samples: 8376320 | consumed tokens: 17154703360 | elapsed time per iteration (s): 2.28 | learning rate: 1.805E-04 | global batch size: 512 | lm loss: 2.234302E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.022 | TFLOPs: 23.16 | +63: iteration 16370/ 73814 | consumed samples: 8381440 | consumed tokens: 17165189120 | elapsed time per iteration (s): 2.24 | learning rate: 1.804E-04 | global batch size: 512 | lm loss: 2.234137E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.888 | TFLOPs: 23.56 | +63: iteration 16380/ 73814 | consumed samples: 8386560 | consumed tokens: 17175674880 | elapsed time per iteration (s): 2.23 | learning rate: 1.804E-04 | global batch size: 512 | lm loss: 2.210676E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.877 | TFLOPs: 23.66 | +63: iteration 16390/ 73814 | consumed samples: 8391680 | consumed tokens: 17186160640 | elapsed time per iteration (s): 2.25 | learning rate: 1.804E-04 | global batch size: 512 | lm loss: 2.220967E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.996 | TFLOPs: 23.47 | +63: iteration 16400/ 73814 | consumed samples: 8396800 | consumed tokens: 17196646400 | elapsed time per iteration (s): 2.23 | learning rate: 1.804E-04 | global batch size: 512 | lm loss: 2.233613E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.717 | TFLOPs: 23.65 | +63: iteration 16410/ 73814 | consumed samples: 8401920 | consumed tokens: 17207132160 | elapsed time per iteration (s): 2.22 | learning rate: 1.803E-04 | global batch size: 512 | lm loss: 2.248132E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.240 | TFLOPs: 23.70 | +63: iteration 16420/ 73814 | consumed samples: 8407040 | consumed tokens: 17217617920 | elapsed time per iteration (s): 2.23 | learning rate: 1.803E-04 | global batch size: 512 | lm loss: 2.233547E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.096 | TFLOPs: 23.58 | +63: iteration 16430/ 73814 | consumed samples: 8412160 | consumed tokens: 17228103680 | elapsed time per iteration (s): 2.23 | learning rate: 1.803E-04 | global batch size: 512 | lm loss: 2.216387E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.742 | TFLOPs: 23.65 | +63: iteration 16440/ 73814 | consumed samples: 8417280 | consumed tokens: 17238589440 | elapsed time per iteration (s): 2.22 | learning rate: 1.803E-04 | global batch size: 512 | lm loss: 2.230094E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.182 | TFLOPs: 23.70 | +63: iteration 16450/ 73814 | consumed samples: 8422400 | consumed tokens: 17249075200 | elapsed time per iteration (s): 2.24 | learning rate: 1.802E-04 | global batch size: 512 | lm loss: 2.234843E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.993 | TFLOPs: 23.57 | +63: iteration 16460/ 73814 | consumed samples: 8427520 | consumed tokens: 17259560960 | elapsed time per iteration (s): 2.31 | learning rate: 1.802E-04 | global batch size: 512 | lm loss: 2.209507E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.878 | TFLOPs: 22.84 | +63: iteration 16470/ 73814 | consumed samples: 8432640 | consumed tokens: 17270046720 | elapsed time per iteration (s): 2.23 | learning rate: 1.802E-04 | global batch size: 512 | lm loss: 2.230224E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.849 | TFLOPs: 23.66 | +63: iteration 16480/ 73814 | consumed samples: 8437760 | consumed tokens: 17280532480 | elapsed time per iteration (s): 2.26 | learning rate: 1.802E-04 | global batch size: 512 | lm loss: 2.220671E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.061 | TFLOPs: 23.27 | +63: iteration 16490/ 73814 | consumed samples: 8442880 | consumed tokens: 17291018240 | elapsed time per iteration (s): 2.23 | learning rate: 1.801E-04 | global batch size: 512 | lm loss: 2.229710E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.853 | TFLOPs: 23.66 | +63: iteration 16500/ 73814 | consumed samples: 8448000 | consumed tokens: 17301504000 | elapsed time per iteration (s): 2.24 | learning rate: 1.801E-04 | global batch size: 512 | lm loss: 2.225126E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.872 | TFLOPs: 23.56 | +63: iteration 16510/ 73814 | consumed samples: 8453120 | consumed tokens: 17311989760 | elapsed time per iteration (s): 2.24 | learning rate: 1.801E-04 | global batch size: 512 | lm loss: 2.215589E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.848 | TFLOPs: 23.56 | +63: iteration 16520/ 73814 | consumed samples: 8458240 | consumed tokens: 17322475520 | elapsed time per iteration (s): 2.27 | learning rate: 1.801E-04 | global batch size: 512 | lm loss: 2.233440E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.879 | TFLOPs: 23.25 | +63: iteration 16530/ 73814 | consumed samples: 8463360 | consumed tokens: 17332961280 | elapsed time per iteration (s): 2.35 | learning rate: 1.800E-04 | global batch size: 512 | lm loss: 2.217363E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.237 | TFLOPs: 22.47 | +63: iteration 16540/ 73814 | consumed samples: 8468480 | consumed tokens: 17343447040 | elapsed time per iteration (s): 2.24 | learning rate: 1.800E-04 | global batch size: 512 | lm loss: 2.227616E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.332 | TFLOPs: 23.51 | +63: iteration 16550/ 73814 | consumed samples: 8473600 | consumed tokens: 17353932800 | elapsed time per iteration (s): 2.23 | learning rate: 1.800E-04 | global batch size: 512 | lm loss: 2.226926E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.482 | TFLOPs: 23.62 | +63: iteration 16560/ 73814 | consumed samples: 8478720 | consumed tokens: 17364418560 | elapsed time per iteration (s): 2.23 | learning rate: 1.800E-04 | global batch size: 512 | lm loss: 2.185792E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.450 | TFLOPs: 23.62 | +63: iteration 16570/ 73814 | consumed samples: 8483840 | consumed tokens: 17374904320 | elapsed time per iteration (s): 2.32 | learning rate: 1.799E-04 | global batch size: 512 | lm loss: 2.218275E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.875 | TFLOPs: 22.74 | +63: iteration 16580/ 73814 | consumed samples: 8488960 | consumed tokens: 17385390080 | elapsed time per iteration (s): 2.23 | learning rate: 1.799E-04 | global batch size: 512 | lm loss: 2.202969E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.434 | TFLOPs: 23.62 | +63: iteration 16590/ 73814 | consumed samples: 8494080 | consumed tokens: 17395875840 | elapsed time per iteration (s): 2.24 | learning rate: 1.799E-04 | global batch size: 512 | lm loss: 2.213263E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.541 | TFLOPs: 23.53 | +63: iteration 16600/ 73814 | consumed samples: 8499200 | consumed tokens: 17406361600 | elapsed time per iteration (s): 2.25 | learning rate: 1.799E-04 | global batch size: 512 | lm loss: 2.188936E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.798 | TFLOPs: 23.45 | +63: iteration 16610/ 73814 | consumed samples: 8504320 | consumed tokens: 17416847360 | elapsed time per iteration (s): 2.23 | learning rate: 1.798E-04 | global batch size: 512 | lm loss: 2.214474E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.830 | TFLOPs: 23.66 | +63: iteration 16620/ 73814 | consumed samples: 8509440 | consumed tokens: 17427333120 | elapsed time per iteration (s): 2.22 | learning rate: 1.798E-04 | global batch size: 512 | lm loss: 2.205136E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.224 | TFLOPs: 23.70 | +63: iteration 16630/ 73814 | consumed samples: 8514560 | consumed tokens: 17437818880 | elapsed time per iteration (s): 2.28 | learning rate: 1.798E-04 | global batch size: 512 | lm loss: 2.219730E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.320 | TFLOPs: 23.09 | +63: iteration 16640/ 73814 | consumed samples: 8519680 | consumed tokens: 17448304640 | elapsed time per iteration (s): 2.23 | learning rate: 1.798E-04 | global batch size: 512 | lm loss: 2.232644E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.373 | TFLOPs: 23.61 | +63: iteration 16650/ 73814 | consumed samples: 8524800 | consumed tokens: 17458790400 | elapsed time per iteration (s): 2.25 | learning rate: 1.798E-04 | global batch size: 512 | lm loss: 2.221854E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.759 | TFLOPs: 23.45 | +63: iteration 16660/ 73814 | consumed samples: 8529920 | consumed tokens: 17469276160 | elapsed time per iteration (s): 2.25 | learning rate: 1.797E-04 | global batch size: 512 | lm loss: 2.208554E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.582 | TFLOPs: 23.43 | +63: iteration 16670/ 73814 | consumed samples: 8535040 | consumed tokens: 17479761920 | elapsed time per iteration (s): 2.23 | learning rate: 1.797E-04 | global batch size: 512 | lm loss: 2.214237E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.077 | TFLOPs: 23.69 | +63: iteration 16680/ 73814 | consumed samples: 8540160 | consumed tokens: 17490247680 | elapsed time per iteration (s): 2.25 | learning rate: 1.797E-04 | global batch size: 512 | lm loss: 2.229555E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.057 | TFLOPs: 23.48 | +63: iteration 16690/ 73814 | consumed samples: 8545280 | consumed tokens: 17500733440 | elapsed time per iteration (s): 2.24 | learning rate: 1.797E-04 | global batch size: 512 | lm loss: 2.244731E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.482 | TFLOPs: 23.52 | +63: iteration 16700/ 73814 | consumed samples: 8550400 | consumed tokens: 17511219200 | elapsed time per iteration (s): 2.25 | learning rate: 1.796E-04 | global batch size: 512 | lm loss: 2.219756E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.742 | TFLOPs: 23.44 | +63: iteration 16710/ 73814 | consumed samples: 8555520 | consumed tokens: 17521704960 | elapsed time per iteration (s): 2.26 | learning rate: 1.796E-04 | global batch size: 512 | lm loss: 2.234089E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.479 | TFLOPs: 23.31 | +63: iteration 16720/ 73814 | consumed samples: 8560640 | consumed tokens: 17532190720 | elapsed time per iteration (s): 2.25 | learning rate: 1.796E-04 | global batch size: 512 | lm loss: 2.230058E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.195 | TFLOPs: 23.39 | +63: iteration 16730/ 73814 | consumed samples: 8565760 | consumed tokens: 17542676480 | elapsed time per iteration (s): 2.23 | learning rate: 1.796E-04 | global batch size: 512 | lm loss: 2.218862E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.588 | TFLOPs: 23.64 | +63: iteration 16740/ 73814 | consumed samples: 8570880 | consumed tokens: 17553162240 | elapsed time per iteration (s): 2.23 | learning rate: 1.795E-04 | global batch size: 512 | lm loss: 2.219553E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.402 | TFLOPs: 23.62 | +63: iteration 16750/ 73814 | consumed samples: 8576000 | consumed tokens: 17563648000 | elapsed time per iteration (s): 2.23 | learning rate: 1.795E-04 | global batch size: 512 | lm loss: 2.211935E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.127 | TFLOPs: 23.59 | +63: iteration 16760/ 73814 | consumed samples: 8581120 | consumed tokens: 17574133760 | elapsed time per iteration (s): 2.23 | learning rate: 1.795E-04 | global batch size: 512 | lm loss: 2.208623E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.937 | TFLOPs: 23.67 | +63: iteration 16770/ 73814 | consumed samples: 8586240 | consumed tokens: 17584619520 | elapsed time per iteration (s): 2.24 | learning rate: 1.795E-04 | global batch size: 512 | lm loss: 2.241441E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.854 | TFLOPs: 23.56 | +63: iteration 16780/ 73814 | consumed samples: 8591360 | consumed tokens: 17595105280 | elapsed time per iteration (s): 2.25 | learning rate: 1.794E-04 | global batch size: 512 | lm loss: 3.277051E+00 | grad norm: 7.687 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.421 | TFLOPs: 23.41 | +63: iteration 16790/ 73814 | consumed samples: 8596480 | consumed tokens: 17605591040 | elapsed time per iteration (s): 2.25 | learning rate: 1.794E-04 | global batch size: 512 | lm loss: 3.177929E+00 | grad norm: 2.787 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.537 | TFLOPs: 23.42 | +63: iteration 16800/ 73814 | consumed samples: 8601600 | consumed tokens: 17616076800 | elapsed time per iteration (s): 2.26 | learning rate: 1.794E-04 | global batch size: 512 | lm loss: 2.654745E+00 | grad norm: 1.734 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.077 | TFLOPs: 23.27 | +63: iteration 16810/ 73814 | consumed samples: 8606720 | consumed tokens: 17626562560 | elapsed time per iteration (s): 2.31 | learning rate: 1.794E-04 | global batch size: 512 | lm loss: 2.510540E+00 | grad norm: 2.006 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.071 | TFLOPs: 22.86 | +63: iteration 16820/ 73814 | consumed samples: 8611840 | consumed tokens: 17637048320 | elapsed time per iteration (s): 2.27 | learning rate: 1.793E-04 | global batch size: 512 | lm loss: 2.427401E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.303 | TFLOPs: 23.19 | +63: iteration 16830/ 73814 | consumed samples: 8616960 | consumed tokens: 17647534080 | elapsed time per iteration (s): 2.36 | learning rate: 1.793E-04 | global batch size: 512 | lm loss: 2.316476E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.337 | TFLOPs: 22.37 | +63: iteration 16840/ 73814 | consumed samples: 8622080 | consumed tokens: 17658019840 | elapsed time per iteration (s): 2.31 | learning rate: 1.793E-04 | global batch size: 512 | lm loss: 2.296780E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.038 | TFLOPs: 22.86 | +63: iteration 16850/ 73814 | consumed samples: 8627200 | consumed tokens: 17668505600 | elapsed time per iteration (s): 2.38 | learning rate: 1.793E-04 | global batch size: 512 | lm loss: 2.280380E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.894 | TFLOPs: 22.12 | +63: iteration 16860/ 73814 | consumed samples: 8632320 | consumed tokens: 17678991360 | elapsed time per iteration (s): 2.34 | learning rate: 1.792E-04 | global batch size: 512 | lm loss: 2.279314E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.268 | TFLOPs: 22.57 | +63: iteration 16870/ 73814 | consumed samples: 8637440 | consumed tokens: 17689477120 | elapsed time per iteration (s): 2.47 | learning rate: 1.792E-04 | global batch size: 512 | lm loss: 2.250634E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 207.361 | TFLOPs: 21.35 | +63: iteration 16880/ 73814 | consumed samples: 8642560 | consumed tokens: 17699962880 | elapsed time per iteration (s): 2.56 | learning rate: 1.792E-04 | global batch size: 512 | lm loss: 2.240849E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.612 | TFLOPs: 20.55 | +63: iteration 16890/ 73814 | consumed samples: 8647680 | consumed tokens: 17710448640 | elapsed time per iteration (s): 2.28 | learning rate: 1.792E-04 | global batch size: 512 | lm loss: 2.247768E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.109 | TFLOPs: 23.07 | +63: iteration 16900/ 73814 | consumed samples: 8652800 | consumed tokens: 17720934400 | elapsed time per iteration (s): 2.32 | learning rate: 1.791E-04 | global batch size: 512 | lm loss: 2.220591E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.901 | TFLOPs: 22.74 | +63: iteration 16910/ 73814 | consumed samples: 8657920 | consumed tokens: 17731420160 | elapsed time per iteration (s): 2.38 | learning rate: 1.791E-04 | global batch size: 512 | lm loss: 2.229600E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.038 | TFLOPs: 22.14 | +63: iteration 16920/ 73814 | consumed samples: 8663040 | consumed tokens: 17741905920 | elapsed time per iteration (s): 2.42 | learning rate: 1.791E-04 | global batch size: 512 | lm loss: 2.240261E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.605 | TFLOPs: 21.78 | +63: iteration 16930/ 73814 | consumed samples: 8668160 | consumed tokens: 17752391680 | elapsed time per iteration (s): 2.30 | learning rate: 1.791E-04 | global batch size: 512 | lm loss: 2.255967E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.865 | TFLOPs: 22.94 | +63: iteration 16940/ 73814 | consumed samples: 8673280 | consumed tokens: 17762877440 | elapsed time per iteration (s): 2.33 | learning rate: 1.790E-04 | global batch size: 512 | lm loss: 2.232453E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.555 | TFLOPs: 22.60 | +63: iteration 16950/ 73814 | consumed samples: 8678400 | consumed tokens: 17773363200 | elapsed time per iteration (s): 2.24 | learning rate: 1.790E-04 | global batch size: 512 | lm loss: 2.222358E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.680 | TFLOPs: 23.54 | +63: iteration 16960/ 73814 | consumed samples: 8683520 | consumed tokens: 17783848960 | elapsed time per iteration (s): 2.23 | learning rate: 1.790E-04 | global batch size: 512 | lm loss: 2.204856E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.830 | TFLOPs: 23.66 | +63: iteration 16970/ 73814 | consumed samples: 8688640 | consumed tokens: 17794334720 | elapsed time per iteration (s): 2.23 | learning rate: 1.790E-04 | global batch size: 512 | lm loss: 2.213845E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.987 | TFLOPs: 23.68 | +63: iteration 16980/ 73814 | consumed samples: 8693760 | consumed tokens: 17804820480 | elapsed time per iteration (s): 2.23 | learning rate: 1.789E-04 | global batch size: 512 | lm loss: 2.219487E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.808 | TFLOPs: 23.66 | +63: iteration 16990/ 73814 | consumed samples: 8698880 | consumed tokens: 17815306240 | elapsed time per iteration (s): 2.24 | learning rate: 1.789E-04 | global batch size: 512 | lm loss: 2.204128E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.587 | TFLOPs: 23.53 | +63: iteration 17000/ 73814 | consumed samples: 8704000 | consumed tokens: 17825792000 | elapsed time per iteration (s): 2.24 | learning rate: 1.789E-04 | global batch size: 512 | lm loss: 2.236695E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.115 | TFLOPs: 23.48 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 17000 | lm loss value: 2.159683E+00 | lm loss PPL: 8.668389E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 17010/ 73814 | consumed samples: 8709120 | consumed tokens: 17836277760 | elapsed time per iteration (s): 2.39 | learning rate: 1.789E-04 | global batch size: 512 | lm loss: 2.228209E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.131 | TFLOPs: 22.04 | +63: iteration 17020/ 73814 | consumed samples: 8714240 | consumed tokens: 17846763520 | elapsed time per iteration (s): 2.25 | learning rate: 1.788E-04 | global batch size: 512 | lm loss: 2.232475E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.821 | TFLOPs: 23.45 | +63: iteration 17030/ 73814 | consumed samples: 8719360 | consumed tokens: 17857249280 | elapsed time per iteration (s): 2.26 | learning rate: 1.788E-04 | global batch size: 512 | lm loss: 2.221248E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.323 | TFLOPs: 23.30 | +63: iteration 17040/ 73814 | consumed samples: 8724480 | consumed tokens: 17867735040 | elapsed time per iteration (s): 2.25 | learning rate: 1.788E-04 | global batch size: 512 | lm loss: 2.222149E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.709 | TFLOPs: 23.44 | +63: iteration 17050/ 73814 | consumed samples: 8729600 | consumed tokens: 17878220800 | elapsed time per iteration (s): 2.33 | learning rate: 1.788E-04 | global batch size: 512 | lm loss: 2.218308E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.194 | TFLOPs: 22.67 | +63: iteration 17060/ 73814 | consumed samples: 8734720 | consumed tokens: 17888706560 | elapsed time per iteration (s): 2.24 | learning rate: 1.787E-04 | global batch size: 512 | lm loss: 2.223986E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.793 | TFLOPs: 23.55 | +63: iteration 17070/ 73814 | consumed samples: 8739840 | consumed tokens: 17899192320 | elapsed time per iteration (s): 2.24 | learning rate: 1.787E-04 | global batch size: 512 | lm loss: 2.207481E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.606 | TFLOPs: 23.53 | +63: iteration 17080/ 73814 | consumed samples: 8744960 | consumed tokens: 17909678080 | elapsed time per iteration (s): 2.28 | learning rate: 1.787E-04 | global batch size: 512 | lm loss: 2.212162E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.318 | TFLOPs: 23.09 | +63: iteration 17090/ 73814 | consumed samples: 8750080 | consumed tokens: 17920163840 | elapsed time per iteration (s): 2.28 | learning rate: 1.787E-04 | global batch size: 512 | lm loss: 2.217925E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.519 | TFLOPs: 23.11 | +63: iteration 17100/ 73814 | consumed samples: 8755200 | consumed tokens: 17930649600 | elapsed time per iteration (s): 2.26 | learning rate: 1.786E-04 | global batch size: 512 | lm loss: 2.226181E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.320 | TFLOPs: 23.30 | +63: iteration 17110/ 73814 | consumed samples: 8760320 | consumed tokens: 17941135360 | elapsed time per iteration (s): 2.24 | learning rate: 1.786E-04 | global batch size: 512 | lm loss: 2.238775E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.837 | TFLOPs: 23.56 | +63: iteration 17120/ 73814 | consumed samples: 8765440 | consumed tokens: 17951621120 | elapsed time per iteration (s): 2.29 | learning rate: 1.786E-04 | global batch size: 512 | lm loss: 2.198798E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.405 | TFLOPs: 23.00 | +63: iteration 17130/ 73814 | consumed samples: 8770560 | consumed tokens: 17962106880 | elapsed time per iteration (s): 2.42 | learning rate: 1.786E-04 | global batch size: 512 | lm loss: 2.188202E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.181 | TFLOPs: 21.74 | +63: iteration 17140/ 73814 | consumed samples: 8775680 | consumed tokens: 17972592640 | elapsed time per iteration (s): 2.23 | learning rate: 1.785E-04 | global batch size: 512 | lm loss: 2.213644E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.251 | TFLOPs: 23.60 | +63: iteration 17150/ 73814 | consumed samples: 8780800 | consumed tokens: 17983078400 | elapsed time per iteration (s): 2.28 | learning rate: 1.785E-04 | global batch size: 512 | lm loss: 2.217804E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.297 | TFLOPs: 23.09 | +63: iteration 17160/ 73814 | consumed samples: 8785920 | consumed tokens: 17993564160 | elapsed time per iteration (s): 2.23 | learning rate: 1.785E-04 | global batch size: 512 | lm loss: 2.199508E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.175 | TFLOPs: 23.59 | +63: iteration 17170/ 73814 | consumed samples: 8791040 | consumed tokens: 18004049920 | elapsed time per iteration (s): 2.27 | learning rate: 1.785E-04 | global batch size: 512 | lm loss: 2.216170E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.443 | TFLOPs: 23.21 | +63: iteration 17180/ 73814 | consumed samples: 8796160 | consumed tokens: 18014535680 | elapsed time per iteration (s): 2.35 | learning rate: 1.784E-04 | global batch size: 512 | lm loss: 2.223194E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.630 | TFLOPs: 22.40 | +63: iteration 17190/ 73814 | consumed samples: 8801280 | consumed tokens: 18025021440 | elapsed time per iteration (s): 2.28 | learning rate: 1.784E-04 | global batch size: 512 | lm loss: 2.221042E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.331 | TFLOPs: 23.09 | +63: iteration 17200/ 73814 | consumed samples: 8806400 | consumed tokens: 18035507200 | elapsed time per iteration (s): 2.29 | learning rate: 1.784E-04 | global batch size: 512 | lm loss: 2.186606E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.684 | TFLOPs: 23.03 | +63: iteration 17210/ 73814 | consumed samples: 8811520 | consumed tokens: 18045992960 | elapsed time per iteration (s): 2.33 | learning rate: 1.784E-04 | global batch size: 512 | lm loss: 2.212097E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.493 | TFLOPs: 22.60 | +63: iteration 17220/ 73814 | consumed samples: 8816640 | consumed tokens: 18056478720 | elapsed time per iteration (s): 2.24 | learning rate: 1.783E-04 | global batch size: 512 | lm loss: 2.195907E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.674 | TFLOPs: 23.54 | +63: iteration 17230/ 73814 | consumed samples: 8821760 | consumed tokens: 18066964480 | elapsed time per iteration (s): 2.24 | learning rate: 1.783E-04 | global batch size: 512 | lm loss: 2.209291E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.299 | TFLOPs: 23.50 | +63: iteration 17240/ 73814 | consumed samples: 8826880 | consumed tokens: 18077450240 | elapsed time per iteration (s): 2.26 | learning rate: 1.783E-04 | global batch size: 512 | lm loss: 2.198357E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.477 | TFLOPs: 23.31 | +63: iteration 17250/ 73814 | consumed samples: 8832000 | consumed tokens: 18087936000 | elapsed time per iteration (s): 2.26 | learning rate: 1.783E-04 | global batch size: 512 | lm loss: 2.220726E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.786 | TFLOPs: 23.35 | +63: iteration 17260/ 73814 | consumed samples: 8837120 | consumed tokens: 18098421760 | elapsed time per iteration (s): 2.25 | learning rate: 1.782E-04 | global batch size: 512 | lm loss: 2.200795E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.749 | TFLOPs: 23.45 | +63: iteration 17270/ 73814 | consumed samples: 8842240 | consumed tokens: 18108907520 | elapsed time per iteration (s): 2.25 | learning rate: 1.782E-04 | global batch size: 512 | lm loss: 2.213826E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.053 | TFLOPs: 23.48 | +63: iteration 17280/ 73814 | consumed samples: 8847360 | consumed tokens: 18119393280 | elapsed time per iteration (s): 2.24 | learning rate: 1.782E-04 | global batch size: 512 | lm loss: 2.219326E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.193 | TFLOPs: 23.49 | +63: iteration 17290/ 73814 | consumed samples: 8852480 | consumed tokens: 18129879040 | elapsed time per iteration (s): 2.23 | learning rate: 1.782E-04 | global batch size: 512 | lm loss: 2.194973E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.623 | TFLOPs: 23.64 | +63: iteration 17300/ 73814 | consumed samples: 8857600 | consumed tokens: 18140364800 | elapsed time per iteration (s): 2.25 | learning rate: 1.781E-04 | global batch size: 512 | lm loss: 2.216392E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.314 | TFLOPs: 23.40 | +63: iteration 17310/ 73814 | consumed samples: 8862720 | consumed tokens: 18150850560 | elapsed time per iteration (s): 2.26 | learning rate: 1.781E-04 | global batch size: 512 | lm loss: 2.209149E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.585 | TFLOPs: 23.33 | +63: iteration 17320/ 73814 | consumed samples: 8867840 | consumed tokens: 18161336320 | elapsed time per iteration (s): 2.23 | learning rate: 1.781E-04 | global batch size: 512 | lm loss: 2.208189E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.268 | TFLOPs: 23.60 | +63: iteration 17330/ 73814 | consumed samples: 8872960 | consumed tokens: 18171822080 | elapsed time per iteration (s): 2.26 | learning rate: 1.781E-04 | global batch size: 512 | lm loss: 2.224094E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.979 | TFLOPs: 23.37 | +63: iteration 17340/ 73814 | consumed samples: 8878080 | consumed tokens: 18182307840 | elapsed time per iteration (s): 2.25 | learning rate: 1.780E-04 | global batch size: 512 | lm loss: 2.206300E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.733 | TFLOPs: 23.44 | +63: iteration 17350/ 73814 | consumed samples: 8883200 | consumed tokens: 18192793600 | elapsed time per iteration (s): 2.30 | learning rate: 1.780E-04 | global batch size: 512 | lm loss: 2.212489E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.769 | TFLOPs: 22.93 | +63: iteration 17360/ 73814 | consumed samples: 8888320 | consumed tokens: 18203279360 | elapsed time per iteration (s): 2.24 | learning rate: 1.780E-04 | global batch size: 512 | lm loss: 2.220548E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.206 | TFLOPs: 23.49 | +63: iteration 17370/ 73814 | consumed samples: 8893440 | consumed tokens: 18213765120 | elapsed time per iteration (s): 2.28 | learning rate: 1.780E-04 | global batch size: 512 | lm loss: 2.197610E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.948 | TFLOPs: 23.16 | +63: iteration 17380/ 73814 | consumed samples: 8898560 | consumed tokens: 18224250880 | elapsed time per iteration (s): 2.28 | learning rate: 1.779E-04 | global batch size: 512 | lm loss: 2.225627E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.639 | TFLOPs: 23.13 | +63: iteration 17390/ 73814 | consumed samples: 8903680 | consumed tokens: 18234736640 | elapsed time per iteration (s): 2.24 | learning rate: 1.779E-04 | global batch size: 512 | lm loss: 2.184678E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.332 | TFLOPs: 23.51 | +63: iteration 17400/ 73814 | consumed samples: 8908800 | consumed tokens: 18245222400 | elapsed time per iteration (s): 2.23 | learning rate: 1.779E-04 | global batch size: 512 | lm loss: 2.206459E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.606 | TFLOPs: 23.64 | +63: iteration 17410/ 73814 | consumed samples: 8913920 | consumed tokens: 18255708160 | elapsed time per iteration (s): 2.25 | learning rate: 1.779E-04 | global batch size: 512 | lm loss: 2.185460E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.311 | TFLOPs: 23.40 | +63: iteration 17420/ 73814 | consumed samples: 8919040 | consumed tokens: 18266193920 | elapsed time per iteration (s): 2.24 | learning rate: 1.778E-04 | global batch size: 512 | lm loss: 2.225385E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.056 | TFLOPs: 23.58 | +63: iteration 17430/ 73814 | consumed samples: 8924160 | consumed tokens: 18276679680 | elapsed time per iteration (s): 2.24 | learning rate: 1.778E-04 | global batch size: 512 | lm loss: 2.209153E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.993 | TFLOPs: 23.57 | +63: iteration 17440/ 73814 | consumed samples: 8929280 | consumed tokens: 18287165440 | elapsed time per iteration (s): 2.23 | learning rate: 1.778E-04 | global batch size: 512 | lm loss: 2.216533E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.489 | TFLOPs: 23.62 | +63: iteration 17450/ 73814 | consumed samples: 8934400 | consumed tokens: 18297651200 | elapsed time per iteration (s): 2.23 | learning rate: 1.778E-04 | global batch size: 512 | lm loss: 2.216168E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.814 | TFLOPs: 23.66 | +63: iteration 17460/ 73814 | consumed samples: 8939520 | consumed tokens: 18308136960 | elapsed time per iteration (s): 2.51 | learning rate: 1.777E-04 | global batch size: 512 | lm loss: 2.198201E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 203.779 | TFLOPs: 20.98 | +63: iteration 17470/ 73814 | consumed samples: 8944640 | consumed tokens: 18318622720 | elapsed time per iteration (s): 2.23 | learning rate: 1.777E-04 | global batch size: 512 | lm loss: 2.185354E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.227 | TFLOPs: 23.60 | +63: iteration 17480/ 73814 | consumed samples: 8949760 | consumed tokens: 18329108480 | elapsed time per iteration (s): 2.28 | learning rate: 1.777E-04 | global batch size: 512 | lm loss: 2.187747E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.844 | TFLOPs: 23.15 | +63: iteration 17490/ 73814 | consumed samples: 8954880 | consumed tokens: 18339594240 | elapsed time per iteration (s): 2.23 | learning rate: 1.777E-04 | global batch size: 512 | lm loss: 2.199245E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.488 | TFLOPs: 23.62 | +63: iteration 17500/ 73814 | consumed samples: 8960000 | consumed tokens: 18350080000 | elapsed time per iteration (s): 2.23 | learning rate: 1.776E-04 | global batch size: 512 | lm loss: 2.210031E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.853 | TFLOPs: 23.66 | +63: iteration 17510/ 73814 | consumed samples: 8965120 | consumed tokens: 18360565760 | elapsed time per iteration (s): 2.25 | learning rate: 1.776E-04 | global batch size: 512 | lm loss: 2.204885E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.986 | TFLOPs: 23.47 | +63: iteration 17520/ 73814 | consumed samples: 8970240 | consumed tokens: 18371051520 | elapsed time per iteration (s): 2.24 | learning rate: 1.776E-04 | global batch size: 512 | lm loss: 2.179840E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.716 | TFLOPs: 23.55 | +63: iteration 17530/ 73814 | consumed samples: 8975360 | consumed tokens: 18381537280 | elapsed time per iteration (s): 2.24 | learning rate: 1.776E-04 | global batch size: 512 | lm loss: 2.216109E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.069 | TFLOPs: 23.58 | +63: iteration 17540/ 73814 | consumed samples: 8980480 | consumed tokens: 18392023040 | elapsed time per iteration (s): 2.25 | learning rate: 1.775E-04 | global batch size: 512 | lm loss: 2.202172E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.260 | TFLOPs: 23.40 | +63: iteration 17550/ 73814 | consumed samples: 8985600 | consumed tokens: 18402508800 | elapsed time per iteration (s): 2.30 | learning rate: 1.775E-04 | global batch size: 512 | lm loss: 2.181548E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.936 | TFLOPs: 22.95 | +63: iteration 17560/ 73814 | consumed samples: 8990720 | consumed tokens: 18412994560 | elapsed time per iteration (s): 2.23 | learning rate: 1.775E-04 | global batch size: 512 | lm loss: 2.174413E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.257 | TFLOPs: 23.60 | +63: iteration 17570/ 73814 | consumed samples: 8995840 | consumed tokens: 18423480320 | elapsed time per iteration (s): 2.26 | learning rate: 1.774E-04 | global batch size: 512 | lm loss: 2.221156E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.607 | TFLOPs: 23.33 | +63: iteration 17580/ 73814 | consumed samples: 9000960 | consumed tokens: 18433966080 | elapsed time per iteration (s): 2.24 | learning rate: 1.774E-04 | global batch size: 512 | lm loss: 2.218449E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.777 | TFLOPs: 23.55 | +63: iteration 17590/ 73814 | consumed samples: 9006080 | consumed tokens: 18444451840 | elapsed time per iteration (s): 2.28 | learning rate: 1.774E-04 | global batch size: 512 | lm loss: 2.191337E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.469 | TFLOPs: 23.11 | +63: iteration 17600/ 73814 | consumed samples: 9011200 | consumed tokens: 18454937600 | elapsed time per iteration (s): 2.28 | learning rate: 1.774E-04 | global batch size: 512 | lm loss: 2.230636E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.985 | TFLOPs: 23.16 | +63: iteration 17610/ 73814 | consumed samples: 9016320 | consumed tokens: 18465423360 | elapsed time per iteration (s): 2.26 | learning rate: 1.773E-04 | global batch size: 512 | lm loss: 2.215954E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.425 | TFLOPs: 23.31 | +63: iteration 17620/ 73814 | consumed samples: 9021440 | consumed tokens: 18475909120 | elapsed time per iteration (s): 2.27 | learning rate: 1.773E-04 | global batch size: 512 | lm loss: 2.212980E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.989 | TFLOPs: 23.26 | +63: iteration 17630/ 73814 | consumed samples: 9026560 | consumed tokens: 18486394880 | elapsed time per iteration (s): 2.23 | learning rate: 1.773E-04 | global batch size: 512 | lm loss: 2.200768E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.242 | TFLOPs: 23.60 | +63: iteration 17640/ 73814 | consumed samples: 9031680 | consumed tokens: 18496880640 | elapsed time per iteration (s): 2.23 | learning rate: 1.773E-04 | global batch size: 512 | lm loss: 2.213228E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.560 | TFLOPs: 23.63 | +63: iteration 17650/ 73814 | consumed samples: 9036800 | consumed tokens: 18507366400 | elapsed time per iteration (s): 2.24 | learning rate: 1.772E-04 | global batch size: 512 | lm loss: 2.211686E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.416 | TFLOPs: 23.51 | +63: iteration 17660/ 73814 | consumed samples: 9041920 | consumed tokens: 18517852160 | elapsed time per iteration (s): 2.29 | learning rate: 1.772E-04 | global batch size: 512 | lm loss: 2.189738E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.835 | TFLOPs: 23.04 | +63: iteration 17670/ 73814 | consumed samples: 9047040 | consumed tokens: 18528337920 | elapsed time per iteration (s): 2.23 | learning rate: 1.772E-04 | global batch size: 512 | lm loss: 2.176914E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.901 | TFLOPs: 23.67 | +63: iteration 17680/ 73814 | consumed samples: 9052160 | consumed tokens: 18538823680 | elapsed time per iteration (s): 2.26 | learning rate: 1.772E-04 | global batch size: 512 | lm loss: 2.211588E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.264 | TFLOPs: 23.29 | +63: iteration 17690/ 73814 | consumed samples: 9057280 | consumed tokens: 18549309440 | elapsed time per iteration (s): 2.23 | learning rate: 1.771E-04 | global batch size: 512 | lm loss: 2.210017E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.531 | TFLOPs: 23.63 | +63: iteration 17700/ 73814 | consumed samples: 9062400 | consumed tokens: 18559795200 | elapsed time per iteration (s): 2.25 | learning rate: 1.771E-04 | global batch size: 512 | lm loss: 2.206830E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.850 | TFLOPs: 23.46 | +63: iteration 17710/ 73814 | consumed samples: 9067520 | consumed tokens: 18570280960 | elapsed time per iteration (s): 2.24 | learning rate: 1.771E-04 | global batch size: 512 | lm loss: 2.207844E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.808 | TFLOPs: 23.55 | +63: iteration 17720/ 73814 | consumed samples: 9072640 | consumed tokens: 18580766720 | elapsed time per iteration (s): 2.27 | learning rate: 1.771E-04 | global batch size: 512 | lm loss: 2.195174E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.941 | TFLOPs: 23.26 | +63: iteration 17730/ 73814 | consumed samples: 9077760 | consumed tokens: 18591252480 | elapsed time per iteration (s): 2.23 | learning rate: 1.770E-04 | global batch size: 512 | lm loss: 2.189419E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.124 | TFLOPs: 23.59 | +63: iteration 17740/ 73814 | consumed samples: 9082880 | consumed tokens: 18601738240 | elapsed time per iteration (s): 2.24 | learning rate: 1.770E-04 | global batch size: 512 | lm loss: 2.202417E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.591 | TFLOPs: 23.53 | +63: iteration 17750/ 73814 | consumed samples: 9088000 | consumed tokens: 18612224000 | elapsed time per iteration (s): 2.23 | learning rate: 1.770E-04 | global batch size: 512 | lm loss: 2.200933E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.677 | TFLOPs: 23.64 | +63: iteration 17760/ 73814 | consumed samples: 9093120 | consumed tokens: 18622709760 | elapsed time per iteration (s): 2.24 | learning rate: 1.770E-04 | global batch size: 512 | lm loss: 2.200560E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.438 | TFLOPs: 23.52 | +63: iteration 17770/ 73814 | consumed samples: 9098240 | consumed tokens: 18633195520 | elapsed time per iteration (s): 2.24 | learning rate: 1.769E-04 | global batch size: 512 | lm loss: 2.229148E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.764 | TFLOPs: 23.55 | +63: iteration 17780/ 73814 | consumed samples: 9103360 | consumed tokens: 18643681280 | elapsed time per iteration (s): 2.26 | learning rate: 1.769E-04 | global batch size: 512 | lm loss: 2.196521E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.697 | TFLOPs: 23.34 | +63: iteration 17790/ 73814 | consumed samples: 9108480 | consumed tokens: 18654167040 | elapsed time per iteration (s): 2.27 | learning rate: 1.769E-04 | global batch size: 512 | lm loss: 2.198037E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.513 | TFLOPs: 23.22 | +63: iteration 17800/ 73814 | consumed samples: 9113600 | consumed tokens: 18664652800 | elapsed time per iteration (s): 2.25 | learning rate: 1.769E-04 | global batch size: 512 | lm loss: 2.228332E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.364 | TFLOPs: 23.41 | +63: iteration 17810/ 73814 | consumed samples: 9118720 | consumed tokens: 18675138560 | elapsed time per iteration (s): 2.27 | learning rate: 1.768E-04 | global batch size: 512 | lm loss: 2.201135E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.033 | TFLOPs: 23.27 | +63: iteration 17820/ 73814 | consumed samples: 9123840 | consumed tokens: 18685624320 | elapsed time per iteration (s): 2.27 | learning rate: 1.768E-04 | global batch size: 512 | lm loss: 2.228439E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.517 | TFLOPs: 23.22 | +63: iteration 17830/ 73814 | consumed samples: 9128960 | consumed tokens: 18696110080 | elapsed time per iteration (s): 2.45 | learning rate: 1.768E-04 | global batch size: 512 | lm loss: 2.200439E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.303 | TFLOPs: 21.55 | +63: iteration 17840/ 73814 | consumed samples: 9134080 | consumed tokens: 18706595840 | elapsed time per iteration (s): 2.25 | learning rate: 1.768E-04 | global batch size: 512 | lm loss: 2.199863E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.910 | TFLOPs: 23.46 | +63: iteration 17850/ 73814 | consumed samples: 9139200 | consumed tokens: 18717081600 | elapsed time per iteration (s): 2.22 | learning rate: 1.767E-04 | global batch size: 512 | lm loss: 2.203009E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.190 | TFLOPs: 23.70 | +63: iteration 17860/ 73814 | consumed samples: 9144320 | consumed tokens: 18727567360 | elapsed time per iteration (s): 2.24 | learning rate: 1.767E-04 | global batch size: 512 | lm loss: 2.195428E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.607 | TFLOPs: 23.53 | +63: iteration 17870/ 73814 | consumed samples: 9149440 | consumed tokens: 18738053120 | elapsed time per iteration (s): 2.23 | learning rate: 1.767E-04 | global batch size: 512 | lm loss: 2.205767E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.291 | TFLOPs: 23.60 | +63: iteration 17880/ 73814 | consumed samples: 9154560 | consumed tokens: 18748538880 | elapsed time per iteration (s): 2.25 | learning rate: 1.766E-04 | global batch size: 512 | lm loss: 2.197165E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.744 | TFLOPs: 23.45 | +63: iteration 17890/ 73814 | consumed samples: 9159680 | consumed tokens: 18759024640 | elapsed time per iteration (s): 2.23 | learning rate: 1.766E-04 | global batch size: 512 | lm loss: 2.177758E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.681 | TFLOPs: 23.64 | +63: iteration 17900/ 73814 | consumed samples: 9164800 | consumed tokens: 18769510400 | elapsed time per iteration (s): 2.25 | learning rate: 1.766E-04 | global batch size: 512 | lm loss: 2.223076E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.003 | TFLOPs: 23.47 | +63: iteration 17910/ 73814 | consumed samples: 9169920 | consumed tokens: 18779996160 | elapsed time per iteration (s): 2.25 | learning rate: 1.766E-04 | global batch size: 512 | lm loss: 2.198489E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.576 | TFLOPs: 23.43 | +63: iteration 17920/ 73814 | consumed samples: 9175040 | consumed tokens: 18790481920 | elapsed time per iteration (s): 2.23 | learning rate: 1.765E-04 | global batch size: 512 | lm loss: 2.197737E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.499 | TFLOPs: 23.63 | +63: iteration 17930/ 73814 | consumed samples: 9180160 | consumed tokens: 18800967680 | elapsed time per iteration (s): 2.23 | learning rate: 1.765E-04 | global batch size: 512 | lm loss: 2.199663E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.638 | TFLOPs: 23.64 | +63: iteration 17940/ 73814 | consumed samples: 9185280 | consumed tokens: 18811453440 | elapsed time per iteration (s): 2.23 | learning rate: 1.765E-04 | global batch size: 512 | lm loss: 2.204319E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.153 | TFLOPs: 23.59 | +63: iteration 17950/ 73814 | consumed samples: 9190400 | consumed tokens: 18821939200 | elapsed time per iteration (s): 2.24 | learning rate: 1.765E-04 | global batch size: 512 | lm loss: 2.193209E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.528 | TFLOPs: 23.53 | +63: iteration 17960/ 73814 | consumed samples: 9195520 | consumed tokens: 18832424960 | elapsed time per iteration (s): 2.25 | learning rate: 1.764E-04 | global batch size: 512 | lm loss: 2.219411E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.592 | TFLOPs: 23.43 | +63: iteration 17970/ 73814 | consumed samples: 9200640 | consumed tokens: 18842910720 | elapsed time per iteration (s): 2.24 | learning rate: 1.764E-04 | global batch size: 512 | lm loss: 2.183924E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.124 | TFLOPs: 23.48 | +63: iteration 17980/ 73814 | consumed samples: 9205760 | consumed tokens: 18853396480 | elapsed time per iteration (s): 2.23 | learning rate: 1.764E-04 | global batch size: 512 | lm loss: 2.187956E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.040 | TFLOPs: 23.68 | +63: iteration 17990/ 73814 | consumed samples: 9210880 | consumed tokens: 18863882240 | elapsed time per iteration (s): 2.26 | learning rate: 1.764E-04 | global batch size: 512 | lm loss: 2.169079E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.108 | TFLOPs: 23.28 | + 0: [2022-12-01 23:12:42,557] [INFO] [logging.py:68:log_dist] [Rank 0] step=18000, skipped=0, lr=[0.00017633472104268896, 0.00017633472104268896, 0.00017633472104268896], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 18000/ 73814 | consumed samples: 9216000 | consumed tokens: 18874368000 | elapsed time per iteration (s): 2.23 | learning rate: 1.763E-04 | global batch size: 512 | lm loss: 2.198676E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.437 | TFLOPs: 23.62 | + 0: steps: 18000 loss: 2.1672 iter time (s): 2.257 samples/sec: 226.866 +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 18000 | lm loss value: 2.085676E+00 | lm loss PPL: 8.050029E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 18010/ 73814 | consumed samples: 9221120 | consumed tokens: 18884853760 | elapsed time per iteration (s): 2.35 | learning rate: 1.763E-04 | global batch size: 512 | lm loss: 2.195174E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.089 | TFLOPs: 22.45 | +63: iteration 18020/ 73814 | consumed samples: 9226240 | consumed tokens: 18895339520 | elapsed time per iteration (s): 2.23 | learning rate: 1.763E-04 | global batch size: 512 | lm loss: 2.186134E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.492 | TFLOPs: 23.63 | +63: iteration 18030/ 73814 | consumed samples: 9231360 | consumed tokens: 18905825280 | elapsed time per iteration (s): 2.23 | learning rate: 1.763E-04 | global batch size: 512 | lm loss: 2.191183E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.352 | TFLOPs: 23.61 | +63: iteration 18040/ 73814 | consumed samples: 9236480 | consumed tokens: 18916311040 | elapsed time per iteration (s): 2.23 | learning rate: 1.762E-04 | global batch size: 512 | lm loss: 2.198825E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.432 | TFLOPs: 23.62 | +63: iteration 18050/ 73814 | consumed samples: 9241600 | consumed tokens: 18926796800 | elapsed time per iteration (s): 2.25 | learning rate: 1.762E-04 | global batch size: 512 | lm loss: 2.208871E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.549 | TFLOPs: 23.43 | +63: iteration 18060/ 73814 | consumed samples: 9246720 | consumed tokens: 18937282560 | elapsed time per iteration (s): 2.23 | learning rate: 1.762E-04 | global batch size: 512 | lm loss: 2.198164E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.922 | TFLOPs: 23.67 | +63: iteration 18070/ 73814 | consumed samples: 9251840 | consumed tokens: 18947768320 | elapsed time per iteration (s): 2.23 | learning rate: 1.762E-04 | global batch size: 512 | lm loss: 2.177944E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.322 | TFLOPs: 23.61 | +63: iteration 18080/ 73814 | consumed samples: 9256960 | consumed tokens: 18958254080 | elapsed time per iteration (s): 2.23 | learning rate: 1.761E-04 | global batch size: 512 | lm loss: 2.208655E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.201 | TFLOPs: 23.60 | +63: iteration 18090/ 73814 | consumed samples: 9262080 | consumed tokens: 18968739840 | elapsed time per iteration (s): 2.25 | learning rate: 1.761E-04 | global batch size: 512 | lm loss: 2.192758E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.620 | TFLOPs: 23.43 | +63: iteration 18100/ 73814 | consumed samples: 9267200 | consumed tokens: 18979225600 | elapsed time per iteration (s): 2.24 | learning rate: 1.761E-04 | global batch size: 512 | lm loss: 2.195399E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.340 | TFLOPs: 23.51 | +63: iteration 18110/ 73814 | consumed samples: 9272320 | consumed tokens: 18989711360 | elapsed time per iteration (s): 2.24 | learning rate: 1.760E-04 | global batch size: 512 | lm loss: 2.196631E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.444 | TFLOPs: 23.52 | +63: iteration 18120/ 73814 | consumed samples: 9277440 | consumed tokens: 19000197120 | elapsed time per iteration (s): 2.23 | learning rate: 1.760E-04 | global batch size: 512 | lm loss: 2.202824E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.892 | TFLOPs: 23.67 | +63: iteration 18130/ 73814 | consumed samples: 9282560 | consumed tokens: 19010682880 | elapsed time per iteration (s): 2.25 | learning rate: 1.760E-04 | global batch size: 512 | lm loss: 2.193845E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.982 | TFLOPs: 23.47 | +63: iteration 18140/ 73814 | consumed samples: 9287680 | consumed tokens: 19021168640 | elapsed time per iteration (s): 2.22 | learning rate: 1.760E-04 | global batch size: 512 | lm loss: 2.187969E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.263 | TFLOPs: 23.70 | +63: iteration 18150/ 73814 | consumed samples: 9292800 | consumed tokens: 19031654400 | elapsed time per iteration (s): 2.24 | learning rate: 1.759E-04 | global batch size: 512 | lm loss: 2.197659E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.776 | TFLOPs: 23.55 | +63: iteration 18160/ 73814 | consumed samples: 9297920 | consumed tokens: 19042140160 | elapsed time per iteration (s): 2.23 | learning rate: 1.759E-04 | global batch size: 512 | lm loss: 2.182150E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.824 | TFLOPs: 23.66 | +63: iteration 18170/ 73814 | consumed samples: 9303040 | consumed tokens: 19052625920 | elapsed time per iteration (s): 2.24 | learning rate: 1.759E-04 | global batch size: 512 | lm loss: 2.188105E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.044 | TFLOPs: 23.58 | +63: iteration 18180/ 73814 | consumed samples: 9308160 | consumed tokens: 19063111680 | elapsed time per iteration (s): 2.23 | learning rate: 1.759E-04 | global batch size: 512 | lm loss: 2.212949E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.794 | TFLOPs: 23.66 | +63: iteration 18190/ 73814 | consumed samples: 9313280 | consumed tokens: 19073597440 | elapsed time per iteration (s): 2.30 | learning rate: 1.758E-04 | global batch size: 512 | lm loss: 2.214917E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.890 | TFLOPs: 22.95 | +63: iteration 18200/ 73814 | consumed samples: 9318400 | consumed tokens: 19084083200 | elapsed time per iteration (s): 2.25 | learning rate: 1.758E-04 | global batch size: 512 | lm loss: 2.192968E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.928 | TFLOPs: 23.46 | +63: iteration 18210/ 73814 | consumed samples: 9323520 | consumed tokens: 19094568960 | elapsed time per iteration (s): 2.26 | learning rate: 1.758E-04 | global batch size: 512 | lm loss: 2.193811E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.372 | TFLOPs: 23.30 | +63: iteration 18220/ 73814 | consumed samples: 9328640 | consumed tokens: 19105054720 | elapsed time per iteration (s): 2.24 | learning rate: 1.758E-04 | global batch size: 512 | lm loss: 2.168589E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.486 | TFLOPs: 23.52 | +63: iteration 18230/ 73814 | consumed samples: 9333760 | consumed tokens: 19115540480 | elapsed time per iteration (s): 2.23 | learning rate: 1.757E-04 | global batch size: 512 | lm loss: 2.195997E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.738 | TFLOPs: 23.65 | +63: iteration 18240/ 73814 | consumed samples: 9338880 | consumed tokens: 19126026240 | elapsed time per iteration (s): 2.23 | learning rate: 1.757E-04 | global batch size: 512 | lm loss: 2.193490E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.439 | TFLOPs: 23.62 | +63: iteration 18250/ 73814 | consumed samples: 9344000 | consumed tokens: 19136512000 | elapsed time per iteration (s): 2.23 | learning rate: 1.757E-04 | global batch size: 512 | lm loss: 2.201430E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.899 | TFLOPs: 23.67 | +63: iteration 18260/ 73814 | consumed samples: 9349120 | consumed tokens: 19146997760 | elapsed time per iteration (s): 2.29 | learning rate: 1.757E-04 | global batch size: 512 | lm loss: 2.205032E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.886 | TFLOPs: 23.05 | +63: iteration 18270/ 73814 | consumed samples: 9354240 | consumed tokens: 19157483520 | elapsed time per iteration (s): 2.25 | learning rate: 1.756E-04 | global batch size: 512 | lm loss: 2.178435E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.462 | TFLOPs: 23.42 | +63: iteration 18280/ 73814 | consumed samples: 9359360 | consumed tokens: 19167969280 | elapsed time per iteration (s): 2.26 | learning rate: 1.756E-04 | global batch size: 512 | lm loss: 2.181948E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.897 | TFLOPs: 23.36 | +63: iteration 18290/ 73814 | consumed samples: 9364480 | consumed tokens: 19178455040 | elapsed time per iteration (s): 2.38 | learning rate: 1.756E-04 | global batch size: 512 | lm loss: 2.207521E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.420 | TFLOPs: 22.18 | +63: iteration 18300/ 73814 | consumed samples: 9369600 | consumed tokens: 19188940800 | elapsed time per iteration (s): 2.24 | learning rate: 1.755E-04 | global batch size: 512 | lm loss: 2.193965E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.750 | TFLOPs: 23.55 | +63: iteration 18310/ 73814 | consumed samples: 9374720 | consumed tokens: 19199426560 | elapsed time per iteration (s): 2.23 | learning rate: 1.755E-04 | global batch size: 512 | lm loss: 2.206183E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.586 | TFLOPs: 23.63 | +63: iteration 18320/ 73814 | consumed samples: 9379840 | consumed tokens: 19209912320 | elapsed time per iteration (s): 2.25 | learning rate: 1.755E-04 | global batch size: 512 | lm loss: 2.193613E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.986 | TFLOPs: 23.47 | +63: iteration 18330/ 73814 | consumed samples: 9384960 | consumed tokens: 19220398080 | elapsed time per iteration (s): 5.30 | learning rate: 1.755E-04 | global batch size: 512 | lm loss: 2.189120E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.614 | TFLOPs: 9.95 | +63: iteration 18340/ 73814 | consumed samples: 9390080 | consumed tokens: 19230883840 | elapsed time per iteration (s): 2.29 | learning rate: 1.754E-04 | global batch size: 512 | lm loss: 2.175703E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.299 | TFLOPs: 22.99 | +63: iteration 18350/ 73814 | consumed samples: 9395200 | consumed tokens: 19241369600 | elapsed time per iteration (s): 2.25 | learning rate: 1.754E-04 | global batch size: 512 | lm loss: 2.223504E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.525 | TFLOPs: 23.42 | +63: iteration 18360/ 73814 | consumed samples: 9400320 | consumed tokens: 19251855360 | elapsed time per iteration (s): 2.24 | learning rate: 1.754E-04 | global batch size: 512 | lm loss: 2.220195E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.521 | TFLOPs: 23.53 | +63: iteration 18370/ 73814 | consumed samples: 9405440 | consumed tokens: 19262341120 | elapsed time per iteration (s): 2.24 | learning rate: 1.754E-04 | global batch size: 512 | lm loss: 2.209523E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.801 | TFLOPs: 23.55 | +63: iteration 18380/ 73814 | consumed samples: 9410560 | consumed tokens: 19272826880 | elapsed time per iteration (s): 2.24 | learning rate: 1.753E-04 | global batch size: 512 | lm loss: 2.175325E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.164 | TFLOPs: 23.49 | +63: iteration 18390/ 73814 | consumed samples: 9415680 | consumed tokens: 19283312640 | elapsed time per iteration (s): 2.28 | learning rate: 1.753E-04 | global batch size: 512 | lm loss: 2.170679E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.767 | TFLOPs: 23.14 | +63: iteration 18400/ 73814 | consumed samples: 9420800 | consumed tokens: 19293798400 | elapsed time per iteration (s): 2.24 | learning rate: 1.753E-04 | global batch size: 512 | lm loss: 2.178458E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.089 | TFLOPs: 23.48 | +63: iteration 18410/ 73814 | consumed samples: 9425920 | consumed tokens: 19304284160 | elapsed time per iteration (s): 2.23 | learning rate: 1.753E-04 | global batch size: 512 | lm loss: 2.173994E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.985 | TFLOPs: 23.68 | +63: iteration 18420/ 73814 | consumed samples: 9431040 | consumed tokens: 19314769920 | elapsed time per iteration (s): 2.25 | learning rate: 1.752E-04 | global batch size: 512 | lm loss: 2.219340E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.245 | TFLOPs: 23.39 | +63: iteration 18430/ 73814 | consumed samples: 9436160 | consumed tokens: 19325255680 | elapsed time per iteration (s): 2.25 | learning rate: 1.752E-04 | global batch size: 512 | lm loss: 2.183057E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.547 | TFLOPs: 23.42 | +63: iteration 18440/ 73814 | consumed samples: 9441280 | consumed tokens: 19335741440 | elapsed time per iteration (s): 2.28 | learning rate: 1.752E-04 | global batch size: 512 | lm loss: 2.174909E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.763 | TFLOPs: 23.14 | +63: iteration 18450/ 73814 | consumed samples: 9446400 | consumed tokens: 19346227200 | elapsed time per iteration (s): 2.23 | learning rate: 1.751E-04 | global batch size: 512 | lm loss: 2.202690E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.349 | TFLOPs: 23.61 | +63: iteration 18460/ 73814 | consumed samples: 9451520 | consumed tokens: 19356712960 | elapsed time per iteration (s): 2.23 | learning rate: 1.751E-04 | global batch size: 512 | lm loss: 2.194992E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.957 | TFLOPs: 23.67 | +63: iteration 18470/ 73814 | consumed samples: 9456640 | consumed tokens: 19367198720 | elapsed time per iteration (s): 2.23 | learning rate: 1.751E-04 | global batch size: 512 | lm loss: 2.192691E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.161 | TFLOPs: 23.59 | +63: iteration 18480/ 73814 | consumed samples: 9461760 | consumed tokens: 19377684480 | elapsed time per iteration (s): 2.24 | learning rate: 1.751E-04 | global batch size: 512 | lm loss: 2.170497E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.749 | TFLOPs: 23.55 | +63: iteration 18490/ 73814 | consumed samples: 9466880 | consumed tokens: 19388170240 | elapsed time per iteration (s): 2.25 | learning rate: 1.750E-04 | global batch size: 512 | lm loss: 2.187788E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.331 | TFLOPs: 23.40 | +63: iteration 18500/ 73814 | consumed samples: 9472000 | consumed tokens: 19398656000 | elapsed time per iteration (s): 2.24 | learning rate: 1.750E-04 | global batch size: 512 | lm loss: 2.202316E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.816 | TFLOPs: 23.56 | +63: iteration 18510/ 73814 | consumed samples: 9477120 | consumed tokens: 19409141760 | elapsed time per iteration (s): 2.27 | learning rate: 1.750E-04 | global batch size: 512 | lm loss: 2.188983E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.846 | TFLOPs: 23.25 | +63: iteration 18520/ 73814 | consumed samples: 9482240 | consumed tokens: 19419627520 | elapsed time per iteration (s): 2.27 | learning rate: 1.750E-04 | global batch size: 512 | lm loss: 2.176656E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.920 | TFLOPs: 23.26 | +63: iteration 18530/ 73814 | consumed samples: 9487360 | consumed tokens: 19430113280 | elapsed time per iteration (s): 2.28 | learning rate: 1.749E-04 | global batch size: 512 | lm loss: 2.194371E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.105 | TFLOPs: 23.07 | +63: iteration 18540/ 73814 | consumed samples: 9492480 | consumed tokens: 19440599040 | elapsed time per iteration (s): 2.40 | learning rate: 1.749E-04 | global batch size: 512 | lm loss: 2.198178E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.551 | TFLOPs: 21.98 | +63: iteration 18550/ 73814 | consumed samples: 9497600 | consumed tokens: 19451084800 | elapsed time per iteration (s): 2.29 | learning rate: 1.749E-04 | global batch size: 512 | lm loss: 2.184428E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.927 | TFLOPs: 23.05 | +63: iteration 18560/ 73814 | consumed samples: 9502720 | consumed tokens: 19461570560 | elapsed time per iteration (s): 2.32 | learning rate: 1.749E-04 | global batch size: 512 | lm loss: 2.183604E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.348 | TFLOPs: 22.68 | +63: iteration 18570/ 73814 | consumed samples: 9507840 | consumed tokens: 19472056320 | elapsed time per iteration (s): 2.29 | learning rate: 1.748E-04 | global batch size: 512 | lm loss: 2.190381E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.754 | TFLOPs: 23.03 | +63: iteration 18580/ 73814 | consumed samples: 9512960 | consumed tokens: 19482542080 | elapsed time per iteration (s): 2.47 | learning rate: 1.748E-04 | global batch size: 512 | lm loss: 2.165984E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.886 | TFLOPs: 21.30 | +63: iteration 18590/ 73814 | consumed samples: 9518080 | consumed tokens: 19493027840 | elapsed time per iteration (s): 2.55 | learning rate: 1.748E-04 | global batch size: 512 | lm loss: 2.176632E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.082 | TFLOPs: 20.70 | +63: iteration 18600/ 73814 | consumed samples: 9523200 | consumed tokens: 19503513600 | elapsed time per iteration (s): 2.41 | learning rate: 1.747E-04 | global batch size: 512 | lm loss: 2.189182E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.827 | TFLOPs: 21.91 | +63: iteration 18610/ 73814 | consumed samples: 9528320 | consumed tokens: 19513999360 | elapsed time per iteration (s): 2.26 | learning rate: 1.747E-04 | global batch size: 512 | lm loss: 2.189580E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.627 | TFLOPs: 23.33 | +63: iteration 18620/ 73814 | consumed samples: 9533440 | consumed tokens: 19524485120 | elapsed time per iteration (s): 2.37 | learning rate: 1.747E-04 | global batch size: 512 | lm loss: 2.191785E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.145 | TFLOPs: 22.25 | +63: iteration 18630/ 73814 | consumed samples: 9538560 | consumed tokens: 19534970880 | elapsed time per iteration (s): 2.52 | learning rate: 1.747E-04 | global batch size: 512 | lm loss: 2.192806E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.814 | TFLOPs: 20.88 | +63: iteration 18640/ 73814 | consumed samples: 9543680 | consumed tokens: 19545456640 | elapsed time per iteration (s): 2.36 | learning rate: 1.746E-04 | global batch size: 512 | lm loss: 2.175754E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.756 | TFLOPs: 22.31 | +63: iteration 18650/ 73814 | consumed samples: 9548800 | consumed tokens: 19555942400 | elapsed time per iteration (s): 2.30 | learning rate: 1.746E-04 | global batch size: 512 | lm loss: 2.208281E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.235 | TFLOPs: 22.88 | +63: iteration 18660/ 73814 | consumed samples: 9553920 | consumed tokens: 19566428160 | elapsed time per iteration (s): 2.23 | learning rate: 1.746E-04 | global batch size: 512 | lm loss: 2.184069E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.454 | TFLOPs: 23.62 | +63: iteration 18670/ 73814 | consumed samples: 9559040 | consumed tokens: 19576913920 | elapsed time per iteration (s): 2.28 | learning rate: 1.746E-04 | global batch size: 512 | lm loss: 2.196734E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.502 | TFLOPs: 23.11 | +63: iteration 18680/ 73814 | consumed samples: 9564160 | consumed tokens: 19587399680 | elapsed time per iteration (s): 2.29 | learning rate: 1.745E-04 | global batch size: 512 | lm loss: 2.202697E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.827 | TFLOPs: 23.04 | +63: iteration 18690/ 73814 | consumed samples: 9569280 | consumed tokens: 19597885440 | elapsed time per iteration (s): 2.23 | learning rate: 1.745E-04 | global batch size: 512 | lm loss: 2.183409E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.442 | TFLOPs: 23.62 | +63: iteration 18700/ 73814 | consumed samples: 9574400 | consumed tokens: 19608371200 | elapsed time per iteration (s): 2.24 | learning rate: 1.745E-04 | global batch size: 512 | lm loss: 2.180585E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.487 | TFLOPs: 23.52 | +63: iteration 18710/ 73814 | consumed samples: 9579520 | consumed tokens: 19618856960 | elapsed time per iteration (s): 2.25 | learning rate: 1.744E-04 | global batch size: 512 | lm loss: 2.192087E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.857 | TFLOPs: 23.46 | +63: iteration 18720/ 73814 | consumed samples: 9584640 | consumed tokens: 19629342720 | elapsed time per iteration (s): 2.32 | learning rate: 1.744E-04 | global batch size: 512 | lm loss: 2.196059E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.391 | TFLOPs: 22.69 | +63: iteration 18730/ 73814 | consumed samples: 9589760 | consumed tokens: 19639828480 | elapsed time per iteration (s): 2.24 | learning rate: 1.744E-04 | global batch size: 512 | lm loss: 2.175480E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.302 | TFLOPs: 23.50 | +63: iteration 18740/ 73814 | consumed samples: 9594880 | consumed tokens: 19650314240 | elapsed time per iteration (s): 2.23 | learning rate: 1.744E-04 | global batch size: 512 | lm loss: 2.189099E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.611 | TFLOPs: 23.64 | +63: iteration 18750/ 73814 | consumed samples: 9600000 | consumed tokens: 19660800000 | elapsed time per iteration (s): 2.23 | learning rate: 1.743E-04 | global batch size: 512 | lm loss: 2.196359E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.910 | TFLOPs: 23.67 | +63: iteration 18760/ 73814 | consumed samples: 9605120 | consumed tokens: 19671285760 | elapsed time per iteration (s): 2.29 | learning rate: 1.743E-04 | global batch size: 512 | lm loss: 2.196839E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.292 | TFLOPs: 22.99 | +63: iteration 18770/ 73814 | consumed samples: 9610240 | consumed tokens: 19681771520 | elapsed time per iteration (s): 2.24 | learning rate: 1.743E-04 | global batch size: 512 | lm loss: 2.196661E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.269 | TFLOPs: 23.50 | +63: iteration 18780/ 73814 | consumed samples: 9615360 | consumed tokens: 19692257280 | elapsed time per iteration (s): 2.24 | learning rate: 1.743E-04 | global batch size: 512 | lm loss: 2.208944E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.324 | TFLOPs: 23.50 | +63: iteration 18790/ 73814 | consumed samples: 9620480 | consumed tokens: 19702743040 | elapsed time per iteration (s): 2.25 | learning rate: 1.742E-04 | global batch size: 512 | lm loss: 2.191989E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.992 | TFLOPs: 23.47 | +63: iteration 18800/ 73814 | consumed samples: 9625600 | consumed tokens: 19713228800 | elapsed time per iteration (s): 2.26 | learning rate: 1.742E-04 | global batch size: 512 | lm loss: 2.171591E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.646 | TFLOPs: 23.33 | +63: iteration 18810/ 73814 | consumed samples: 9630720 | consumed tokens: 19723714560 | elapsed time per iteration (s): 2.22 | learning rate: 1.742E-04 | global batch size: 512 | lm loss: 2.189638E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.208 | TFLOPs: 23.70 | +63: iteration 18820/ 73814 | consumed samples: 9635840 | consumed tokens: 19734200320 | elapsed time per iteration (s): 2.23 | learning rate: 1.741E-04 | global batch size: 512 | lm loss: 2.190157E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.579 | TFLOPs: 23.63 | +63: iteration 18830/ 73814 | consumed samples: 9640960 | consumed tokens: 19744686080 | elapsed time per iteration (s): 2.23 | learning rate: 1.741E-04 | global batch size: 512 | lm loss: 2.174850E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.325 | TFLOPs: 23.61 | +63: iteration 18840/ 73814 | consumed samples: 9646080 | consumed tokens: 19755171840 | elapsed time per iteration (s): 2.24 | learning rate: 1.741E-04 | global batch size: 512 | lm loss: 2.194560E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.313 | TFLOPs: 23.50 | +63: iteration 18850/ 73814 | consumed samples: 9651200 | consumed tokens: 19765657600 | elapsed time per iteration (s): 2.23 | learning rate: 1.741E-04 | global batch size: 512 | lm loss: 2.200522E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.665 | TFLOPs: 23.64 | +63: iteration 18860/ 73814 | consumed samples: 9656320 | consumed tokens: 19776143360 | elapsed time per iteration (s): 2.24 | learning rate: 1.740E-04 | global batch size: 512 | lm loss: 2.171881E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.079 | TFLOPs: 23.48 | +63: iteration 18870/ 73814 | consumed samples: 9661440 | consumed tokens: 19786629120 | elapsed time per iteration (s): 2.30 | learning rate: 1.740E-04 | global batch size: 512 | lm loss: 2.185257E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.033 | TFLOPs: 22.96 | +63: iteration 18880/ 73814 | consumed samples: 9666560 | consumed tokens: 19797114880 | elapsed time per iteration (s): 2.24 | learning rate: 1.740E-04 | global batch size: 512 | lm loss: 2.193923E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.775 | TFLOPs: 23.55 | +63: iteration 18890/ 73814 | consumed samples: 9671680 | consumed tokens: 19807600640 | elapsed time per iteration (s): 2.27 | learning rate: 1.740E-04 | global batch size: 512 | lm loss: 2.192880E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.520 | TFLOPs: 23.22 | +63: iteration 18900/ 73814 | consumed samples: 9676800 | consumed tokens: 19818086400 | elapsed time per iteration (s): 2.25 | learning rate: 1.739E-04 | global batch size: 512 | lm loss: 2.183029E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.918 | TFLOPs: 23.46 | +63: iteration 18910/ 73814 | consumed samples: 9681920 | consumed tokens: 19828572160 | elapsed time per iteration (s): 2.25 | learning rate: 1.739E-04 | global batch size: 512 | lm loss: 2.186730E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.596 | TFLOPs: 23.43 | +63: iteration 18920/ 73814 | consumed samples: 9687040 | consumed tokens: 19839057920 | elapsed time per iteration (s): 2.32 | learning rate: 1.739E-04 | global batch size: 512 | lm loss: 2.172781E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.662 | TFLOPs: 22.72 | +63: iteration 18930/ 73814 | consumed samples: 9692160 | consumed tokens: 19849543680 | elapsed time per iteration (s): 2.23 | learning rate: 1.739E-04 | global batch size: 512 | lm loss: 2.179069E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.431 | TFLOPs: 23.62 | +63: iteration 18940/ 73814 | consumed samples: 9697280 | consumed tokens: 19860029440 | elapsed time per iteration (s): 2.25 | learning rate: 1.738E-04 | global batch size: 512 | lm loss: 2.186789E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.353 | TFLOPs: 23.40 | +63: iteration 18950/ 73814 | consumed samples: 9702400 | consumed tokens: 19870515200 | elapsed time per iteration (s): 2.24 | learning rate: 1.738E-04 | global batch size: 512 | lm loss: 2.195744E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.269 | TFLOPs: 23.50 | +63: iteration 18960/ 73814 | consumed samples: 9707520 | consumed tokens: 19881000960 | elapsed time per iteration (s): 2.25 | learning rate: 1.738E-04 | global batch size: 512 | lm loss: 2.175420E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.861 | TFLOPs: 23.46 | +63: iteration 18970/ 73814 | consumed samples: 9712640 | consumed tokens: 19891486720 | elapsed time per iteration (s): 2.24 | learning rate: 1.737E-04 | global batch size: 512 | lm loss: 2.169166E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.801 | TFLOPs: 23.55 | +63: iteration 18980/ 73814 | consumed samples: 9717760 | consumed tokens: 19901972480 | elapsed time per iteration (s): 2.25 | learning rate: 1.737E-04 | global batch size: 512 | lm loss: 2.215828E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.221 | TFLOPs: 23.39 | +63: iteration 18990/ 73814 | consumed samples: 9722880 | consumed tokens: 19912458240 | elapsed time per iteration (s): 2.23 | learning rate: 1.737E-04 | global batch size: 512 | lm loss: 2.173211E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.674 | TFLOPs: 23.64 | +63: iteration 19000/ 73814 | consumed samples: 9728000 | consumed tokens: 19922944000 | elapsed time per iteration (s): 2.22 | learning rate: 1.737E-04 | global batch size: 512 | lm loss: 2.188605E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.222 | TFLOPs: 23.70 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 19000 | lm loss value: 2.128400E+00 | lm loss PPL: 8.401415E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 19010/ 73814 | consumed samples: 9733120 | consumed tokens: 19933429760 | elapsed time per iteration (s): 2.30 | learning rate: 1.736E-04 | global batch size: 512 | lm loss: 2.195342E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.941 | TFLOPs: 22.95 | +63: iteration 19020/ 73814 | consumed samples: 9738240 | consumed tokens: 19943915520 | elapsed time per iteration (s): 2.28 | learning rate: 1.736E-04 | global batch size: 512 | lm loss: 2.197145E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.682 | TFLOPs: 23.13 | +63: iteration 19030/ 73814 | consumed samples: 9743360 | consumed tokens: 19954401280 | elapsed time per iteration (s): 2.23 | learning rate: 1.736E-04 | global batch size: 512 | lm loss: 2.192949E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.054 | TFLOPs: 23.68 | +63: iteration 19040/ 73814 | consumed samples: 9748480 | consumed tokens: 19964887040 | elapsed time per iteration (s): 2.23 | learning rate: 1.735E-04 | global batch size: 512 | lm loss: 2.192373E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.728 | TFLOPs: 23.65 | +63: iteration 19050/ 73814 | consumed samples: 9753600 | consumed tokens: 19975372800 | elapsed time per iteration (s): 2.24 | learning rate: 1.735E-04 | global batch size: 512 | lm loss: 2.175759E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.041 | TFLOPs: 23.58 | +63: iteration 19060/ 73814 | consumed samples: 9758720 | consumed tokens: 19985858560 | elapsed time per iteration (s): 2.29 | learning rate: 1.735E-04 | global batch size: 512 | lm loss: 2.170010E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.574 | TFLOPs: 23.02 | +63: iteration 19070/ 73814 | consumed samples: 9763840 | consumed tokens: 19996344320 | elapsed time per iteration (s): 2.24 | learning rate: 1.735E-04 | global batch size: 512 | lm loss: 2.141648E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.824 | TFLOPs: 23.56 | +63: iteration 19080/ 73814 | consumed samples: 9768960 | consumed tokens: 20006830080 | elapsed time per iteration (s): 2.25 | learning rate: 1.734E-04 | global batch size: 512 | lm loss: 2.186425E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.219 | TFLOPs: 23.39 | +63: iteration 19090/ 73814 | consumed samples: 9774080 | consumed tokens: 20017315840 | elapsed time per iteration (s): 2.31 | learning rate: 1.734E-04 | global batch size: 512 | lm loss: 2.171825E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.941 | TFLOPs: 22.85 | +63: iteration 19100/ 73814 | consumed samples: 9779200 | consumed tokens: 20027801600 | elapsed time per iteration (s): 2.23 | learning rate: 1.734E-04 | global batch size: 512 | lm loss: 2.172186E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.172 | TFLOPs: 23.59 | +63: iteration 19110/ 73814 | consumed samples: 9784320 | consumed tokens: 20038287360 | elapsed time per iteration (s): 2.23 | learning rate: 1.734E-04 | global batch size: 512 | lm loss: 2.180119E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.216 | TFLOPs: 23.60 | +63: iteration 19120/ 73814 | consumed samples: 9789440 | consumed tokens: 20048773120 | elapsed time per iteration (s): 2.24 | learning rate: 1.733E-04 | global batch size: 512 | lm loss: 2.170415E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.619 | TFLOPs: 23.54 | +63: iteration 19130/ 73814 | consumed samples: 9794560 | consumed tokens: 20059258880 | elapsed time per iteration (s): 2.23 | learning rate: 1.733E-04 | global batch size: 512 | lm loss: 2.192902E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.874 | TFLOPs: 23.66 | +63: iteration 19140/ 73814 | consumed samples: 9799680 | consumed tokens: 20069744640 | elapsed time per iteration (s): 2.51 | learning rate: 1.733E-04 | global batch size: 512 | lm loss: 2.188643E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 203.943 | TFLOPs: 20.99 | +63: iteration 19150/ 73814 | consumed samples: 9804800 | consumed tokens: 20080230400 | elapsed time per iteration (s): 2.31 | learning rate: 1.732E-04 | global batch size: 512 | lm loss: 2.178211E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.465 | TFLOPs: 22.80 | +63: iteration 19160/ 73814 | consumed samples: 9809920 | consumed tokens: 20090716160 | elapsed time per iteration (s): 2.26 | learning rate: 1.732E-04 | global batch size: 512 | lm loss: 2.179842E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.582 | TFLOPs: 23.33 | +63: iteration 19170/ 73814 | consumed samples: 9815040 | consumed tokens: 20101201920 | elapsed time per iteration (s): 2.25 | learning rate: 1.732E-04 | global batch size: 512 | lm loss: 2.196117E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.776 | TFLOPs: 23.45 | +63: iteration 19180/ 73814 | consumed samples: 9820160 | consumed tokens: 20111687680 | elapsed time per iteration (s): 2.25 | learning rate: 1.732E-04 | global batch size: 512 | lm loss: 2.159341E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.044 | TFLOPs: 23.48 | +63: iteration 19190/ 73814 | consumed samples: 9825280 | consumed tokens: 20122173440 | elapsed time per iteration (s): 2.28 | learning rate: 1.731E-04 | global batch size: 512 | lm loss: 2.152567E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.765 | TFLOPs: 23.14 | +63: iteration 19200/ 73814 | consumed samples: 9830400 | consumed tokens: 20132659200 | elapsed time per iteration (s): 2.23 | learning rate: 1.731E-04 | global batch size: 512 | lm loss: 2.202216E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.091 | TFLOPs: 23.58 | +63: iteration 19210/ 73814 | consumed samples: 9835520 | consumed tokens: 20143144960 | elapsed time per iteration (s): 2.26 | learning rate: 1.731E-04 | global batch size: 512 | lm loss: 2.182720E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.981 | TFLOPs: 23.37 | +63: iteration 19220/ 73814 | consumed samples: 9840640 | consumed tokens: 20153630720 | elapsed time per iteration (s): 2.23 | learning rate: 1.731E-04 | global batch size: 512 | lm loss: 2.194963E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.296 | TFLOPs: 23.60 | +63: iteration 19230/ 73814 | consumed samples: 9845760 | consumed tokens: 20164116480 | elapsed time per iteration (s): 2.27 | learning rate: 1.730E-04 | global batch size: 512 | lm loss: 2.173573E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.079 | TFLOPs: 23.17 | +63: iteration 19240/ 73814 | consumed samples: 9850880 | consumed tokens: 20174602240 | elapsed time per iteration (s): 2.24 | learning rate: 1.730E-04 | global batch size: 512 | lm loss: 2.180169E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.075 | TFLOPs: 23.58 | +63: iteration 19250/ 73814 | consumed samples: 9856000 | consumed tokens: 20185088000 | elapsed time per iteration (s): 2.23 | learning rate: 1.730E-04 | global batch size: 512 | lm loss: 2.196341E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.924 | TFLOPs: 23.67 | +63: iteration 19260/ 73814 | consumed samples: 9861120 | consumed tokens: 20195573760 | elapsed time per iteration (s): 2.27 | learning rate: 1.729E-04 | global batch size: 512 | lm loss: 2.179099E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.065 | TFLOPs: 23.17 | +63: iteration 19270/ 73814 | consumed samples: 9866240 | consumed tokens: 20206059520 | elapsed time per iteration (s): 2.25 | learning rate: 1.729E-04 | global batch size: 512 | lm loss: 2.160521E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.944 | TFLOPs: 23.47 | +63: iteration 19280/ 73814 | consumed samples: 9871360 | consumed tokens: 20216545280 | elapsed time per iteration (s): 2.24 | learning rate: 1.729E-04 | global batch size: 512 | lm loss: 2.201604E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.897 | TFLOPs: 23.56 | +63: iteration 19290/ 73814 | consumed samples: 9876480 | consumed tokens: 20227031040 | elapsed time per iteration (s): 2.25 | learning rate: 1.729E-04 | global batch size: 512 | lm loss: 2.165569E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.703 | TFLOPs: 23.44 | +63: iteration 19300/ 73814 | consumed samples: 9881600 | consumed tokens: 20237516800 | elapsed time per iteration (s): 2.25 | learning rate: 1.728E-04 | global batch size: 512 | lm loss: 2.189637E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.977 | TFLOPs: 23.47 | +63: iteration 19310/ 73814 | consumed samples: 9886720 | consumed tokens: 20248002560 | elapsed time per iteration (s): 2.35 | learning rate: 1.728E-04 | global batch size: 512 | lm loss: 2.171568E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.492 | TFLOPs: 22.39 | +63: iteration 19320/ 73814 | consumed samples: 9891840 | consumed tokens: 20258488320 | elapsed time per iteration (s): 2.24 | learning rate: 1.728E-04 | global batch size: 512 | lm loss: 2.169902E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.619 | TFLOPs: 23.54 | +63: iteration 19330/ 73814 | consumed samples: 9896960 | consumed tokens: 20268974080 | elapsed time per iteration (s): 2.24 | learning rate: 1.728E-04 | global batch size: 512 | lm loss: 2.192746E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.340 | TFLOPs: 23.51 | +63: iteration 19340/ 73814 | consumed samples: 9902080 | consumed tokens: 20279459840 | elapsed time per iteration (s): 2.24 | learning rate: 1.727E-04 | global batch size: 512 | lm loss: 2.160937E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.921 | TFLOPs: 23.57 | +63: iteration 19350/ 73814 | consumed samples: 9907200 | consumed tokens: 20289945600 | elapsed time per iteration (s): 2.24 | learning rate: 1.727E-04 | global batch size: 512 | lm loss: 2.145635E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.719 | TFLOPs: 23.55 | +63: iteration 19360/ 73814 | consumed samples: 9912320 | consumed tokens: 20300431360 | elapsed time per iteration (s): 2.24 | learning rate: 1.727E-04 | global batch size: 512 | lm loss: 2.179933E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.569 | TFLOPs: 23.53 | +63: iteration 19370/ 73814 | consumed samples: 9917440 | consumed tokens: 20310917120 | elapsed time per iteration (s): 2.23 | learning rate: 1.726E-04 | global batch size: 512 | lm loss: 2.186036E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.113 | TFLOPs: 23.59 | +63: iteration 19380/ 73814 | consumed samples: 9922560 | consumed tokens: 20321402880 | elapsed time per iteration (s): 2.24 | learning rate: 1.726E-04 | global batch size: 512 | lm loss: 2.182372E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.263 | TFLOPs: 23.50 | +63: iteration 19390/ 73814 | consumed samples: 9927680 | consumed tokens: 20331888640 | elapsed time per iteration (s): 2.24 | learning rate: 1.726E-04 | global batch size: 512 | lm loss: 2.204581E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.526 | TFLOPs: 23.53 | +63: iteration 19400/ 73814 | consumed samples: 9932800 | consumed tokens: 20342374400 | elapsed time per iteration (s): 2.23 | learning rate: 1.726E-04 | global batch size: 512 | lm loss: 2.187270E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.678 | TFLOPs: 23.64 | +63: iteration 19410/ 73814 | consumed samples: 9937920 | consumed tokens: 20352860160 | elapsed time per iteration (s): 2.24 | learning rate: 1.725E-04 | global batch size: 512 | lm loss: 2.148225E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.631 | TFLOPs: 23.54 | +63: iteration 19420/ 73814 | consumed samples: 9943040 | consumed tokens: 20363345920 | elapsed time per iteration (s): 2.24 | learning rate: 1.725E-04 | global batch size: 512 | lm loss: 2.171638E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.228 | TFLOPs: 23.49 | +63: iteration 19430/ 73814 | consumed samples: 9948160 | consumed tokens: 20373831680 | elapsed time per iteration (s): 2.25 | learning rate: 1.725E-04 | global batch size: 512 | lm loss: 2.172869E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.995 | TFLOPs: 23.47 | +63: iteration 19440/ 73814 | consumed samples: 9953280 | consumed tokens: 20384317440 | elapsed time per iteration (s): 2.25 | learning rate: 1.724E-04 | global batch size: 512 | lm loss: 2.178713E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.061 | TFLOPs: 23.48 | +63: iteration 19450/ 73814 | consumed samples: 9958400 | consumed tokens: 20394803200 | elapsed time per iteration (s): 2.24 | learning rate: 1.724E-04 | global batch size: 512 | lm loss: 2.175944E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.396 | TFLOPs: 23.51 | +63: iteration 19460/ 73814 | consumed samples: 9963520 | consumed tokens: 20405288960 | elapsed time per iteration (s): 2.25 | learning rate: 1.724E-04 | global batch size: 512 | lm loss: 2.179384E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.989 | TFLOPs: 23.47 | +63: iteration 19470/ 73814 | consumed samples: 9968640 | consumed tokens: 20415774720 | elapsed time per iteration (s): 2.24 | learning rate: 1.724E-04 | global batch size: 512 | lm loss: 2.174133E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.568 | TFLOPs: 23.53 | +63: iteration 19480/ 73814 | consumed samples: 9973760 | consumed tokens: 20426260480 | elapsed time per iteration (s): 2.23 | learning rate: 1.723E-04 | global batch size: 512 | lm loss: 2.154562E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.554 | TFLOPs: 23.63 | +63: iteration 19490/ 73814 | consumed samples: 9978880 | consumed tokens: 20436746240 | elapsed time per iteration (s): 2.27 | learning rate: 1.723E-04 | global batch size: 512 | lm loss: 2.197371E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.840 | TFLOPs: 23.25 | +63: iteration 19500/ 73814 | consumed samples: 9984000 | consumed tokens: 20447232000 | elapsed time per iteration (s): 2.23 | learning rate: 1.723E-04 | global batch size: 512 | lm loss: 2.172922E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.504 | TFLOPs: 23.63 | +63: iteration 19510/ 73814 | consumed samples: 9989120 | consumed tokens: 20457717760 | elapsed time per iteration (s): 2.25 | learning rate: 1.722E-04 | global batch size: 512 | lm loss: 2.169347E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.973 | TFLOPs: 23.47 | +63: iteration 19520/ 73814 | consumed samples: 9994240 | consumed tokens: 20468203520 | elapsed time per iteration (s): 2.24 | learning rate: 1.722E-04 | global batch size: 512 | lm loss: 2.184747E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.539 | TFLOPs: 23.53 | +63: iteration 19530/ 73814 | consumed samples: 9999360 | consumed tokens: 20478689280 | elapsed time per iteration (s): 2.29 | learning rate: 1.722E-04 | global batch size: 512 | lm loss: 2.190490E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.757 | TFLOPs: 23.03 | +63: iteration 19540/ 73814 | consumed samples: 10004480 | consumed tokens: 20489175040 | elapsed time per iteration (s): 2.43 | learning rate: 1.722E-04 | global batch size: 512 | lm loss: 2.194391E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.819 | TFLOPs: 21.70 | +63: iteration 19550/ 73814 | consumed samples: 10009600 | consumed tokens: 20499660800 | elapsed time per iteration (s): 2.24 | learning rate: 1.721E-04 | global batch size: 512 | lm loss: 2.169715E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.983 | TFLOPs: 23.57 | +63: iteration 19560/ 73814 | consumed samples: 10014720 | consumed tokens: 20510146560 | elapsed time per iteration (s): 2.24 | learning rate: 1.721E-04 | global batch size: 512 | lm loss: 2.167698E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.401 | TFLOPs: 23.51 | +63: iteration 19570/ 73814 | consumed samples: 10019840 | consumed tokens: 20520632320 | elapsed time per iteration (s): 2.23 | learning rate: 1.721E-04 | global batch size: 512 | lm loss: 2.179263E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.871 | TFLOPs: 23.66 | +63: iteration 19580/ 73814 | consumed samples: 10024960 | consumed tokens: 20531118080 | elapsed time per iteration (s): 2.24 | learning rate: 1.721E-04 | global batch size: 512 | lm loss: 2.158159E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.446 | TFLOPs: 23.52 | +63: iteration 19590/ 73814 | consumed samples: 10030080 | consumed tokens: 20541603840 | elapsed time per iteration (s): 2.23 | learning rate: 1.720E-04 | global batch size: 512 | lm loss: 2.182897E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.044 | TFLOPs: 23.68 | +63: iteration 19600/ 73814 | consumed samples: 10035200 | consumed tokens: 20552089600 | elapsed time per iteration (s): 2.25 | learning rate: 1.720E-04 | global batch size: 512 | lm loss: 2.195140E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.601 | TFLOPs: 23.43 | +63: iteration 19610/ 73814 | consumed samples: 10040320 | consumed tokens: 20562575360 | elapsed time per iteration (s): 2.23 | learning rate: 1.720E-04 | global batch size: 512 | lm loss: 2.179964E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.015 | TFLOPs: 23.68 | +63: iteration 19620/ 73814 | consumed samples: 10045440 | consumed tokens: 20573061120 | elapsed time per iteration (s): 2.25 | learning rate: 1.719E-04 | global batch size: 512 | lm loss: 2.154892E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.964 | TFLOPs: 23.47 | +63: iteration 19630/ 73814 | consumed samples: 10050560 | consumed tokens: 20583546880 | elapsed time per iteration (s): 2.24 | learning rate: 1.719E-04 | global batch size: 512 | lm loss: 2.171380E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.184 | TFLOPs: 23.49 | +63: iteration 19640/ 73814 | consumed samples: 10055680 | consumed tokens: 20594032640 | elapsed time per iteration (s): 2.23 | learning rate: 1.719E-04 | global batch size: 512 | lm loss: 2.160172E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.530 | TFLOPs: 23.63 | +63: iteration 19650/ 73814 | consumed samples: 10060800 | consumed tokens: 20604518400 | elapsed time per iteration (s): 2.26 | learning rate: 1.719E-04 | global batch size: 512 | lm loss: 2.187967E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.056 | TFLOPs: 23.27 | +63: iteration 19660/ 73814 | consumed samples: 10065920 | consumed tokens: 20615004160 | elapsed time per iteration (s): 2.22 | learning rate: 1.718E-04 | global batch size: 512 | lm loss: 2.159426E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.479 | TFLOPs: 23.73 | +63: iteration 19670/ 73814 | consumed samples: 10071040 | consumed tokens: 20625489920 | elapsed time per iteration (s): 2.23 | learning rate: 1.718E-04 | global batch size: 512 | lm loss: 2.171613E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.886 | TFLOPs: 23.67 | +63: iteration 19680/ 73814 | consumed samples: 10076160 | consumed tokens: 20635975680 | elapsed time per iteration (s): 2.25 | learning rate: 1.718E-04 | global batch size: 512 | lm loss: 2.186095E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.671 | TFLOPs: 23.44 | +63: iteration 19690/ 73814 | consumed samples: 10081280 | consumed tokens: 20646461440 | elapsed time per iteration (s): 2.24 | learning rate: 1.717E-04 | global batch size: 512 | lm loss: 2.159299E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.694 | TFLOPs: 23.54 | +63: iteration 19700/ 73814 | consumed samples: 10086400 | consumed tokens: 20656947200 | elapsed time per iteration (s): 2.24 | learning rate: 1.717E-04 | global batch size: 512 | lm loss: 2.178403E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.466 | TFLOPs: 23.52 | +63: iteration 19710/ 73814 | consumed samples: 10091520 | consumed tokens: 20667432960 | elapsed time per iteration (s): 2.23 | learning rate: 1.717E-04 | global batch size: 512 | lm loss: 2.167395E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.096 | TFLOPs: 23.58 | +63: iteration 19720/ 73814 | consumed samples: 10096640 | consumed tokens: 20677918720 | elapsed time per iteration (s): 2.27 | learning rate: 1.717E-04 | global batch size: 512 | lm loss: 2.181588E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.289 | TFLOPs: 23.19 | +63: iteration 19730/ 73814 | consumed samples: 10101760 | consumed tokens: 20688404480 | elapsed time per iteration (s): 2.23 | learning rate: 1.716E-04 | global batch size: 512 | lm loss: 2.140603E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.724 | TFLOPs: 23.65 | +63: iteration 19740/ 73814 | consumed samples: 10106880 | consumed tokens: 20698890240 | elapsed time per iteration (s): 2.23 | learning rate: 1.716E-04 | global batch size: 512 | lm loss: 2.179965E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.884 | TFLOPs: 23.67 | +63: iteration 19750/ 73814 | consumed samples: 10112000 | consumed tokens: 20709376000 | elapsed time per iteration (s): 2.25 | learning rate: 1.716E-04 | global batch size: 512 | lm loss: 2.179599E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.838 | TFLOPs: 23.45 | +63: iteration 19760/ 73814 | consumed samples: 10117120 | consumed tokens: 20719861760 | elapsed time per iteration (s): 2.24 | learning rate: 1.715E-04 | global batch size: 512 | lm loss: 2.186039E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.266 | TFLOPs: 23.50 | +63: iteration 19770/ 73814 | consumed samples: 10122240 | consumed tokens: 20730347520 | elapsed time per iteration (s): 2.24 | learning rate: 1.715E-04 | global batch size: 512 | lm loss: 2.156417E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.021 | TFLOPs: 23.58 | +63: iteration 19780/ 73814 | consumed samples: 10127360 | consumed tokens: 20740833280 | elapsed time per iteration (s): 2.39 | learning rate: 1.715E-04 | global batch size: 512 | lm loss: 2.172924E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.807 | TFLOPs: 22.01 | +63: iteration 19790/ 73814 | consumed samples: 10132480 | consumed tokens: 20751319040 | elapsed time per iteration (s): 2.25 | learning rate: 1.715E-04 | global batch size: 512 | lm loss: 2.173396E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.151 | TFLOPs: 23.38 | +63: iteration 19800/ 73814 | consumed samples: 10137600 | consumed tokens: 20761804800 | elapsed time per iteration (s): 2.24 | learning rate: 1.714E-04 | global batch size: 512 | lm loss: 2.186319E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.485 | TFLOPs: 23.52 | +63: iteration 19810/ 73814 | consumed samples: 10142720 | consumed tokens: 20772290560 | elapsed time per iteration (s): 2.23 | learning rate: 1.714E-04 | global batch size: 512 | lm loss: 2.184529E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.226 | TFLOPs: 23.60 | +63: iteration 19820/ 73814 | consumed samples: 10147840 | consumed tokens: 20782776320 | elapsed time per iteration (s): 2.26 | learning rate: 1.714E-04 | global batch size: 512 | lm loss: 2.166254E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.495 | TFLOPs: 23.32 | +63: iteration 19830/ 73814 | consumed samples: 10152960 | consumed tokens: 20793262080 | elapsed time per iteration (s): 2.24 | learning rate: 1.713E-04 | global batch size: 512 | lm loss: 2.173495E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.547 | TFLOPs: 23.53 | +63: iteration 19840/ 73814 | consumed samples: 10158080 | consumed tokens: 20803747840 | elapsed time per iteration (s): 2.24 | learning rate: 1.713E-04 | global batch size: 512 | lm loss: 2.166185E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.284 | TFLOPs: 23.50 | +63: iteration 19850/ 73814 | consumed samples: 10163200 | consumed tokens: 20814233600 | elapsed time per iteration (s): 2.24 | learning rate: 1.713E-04 | global batch size: 512 | lm loss: 2.183871E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.553 | TFLOPs: 23.53 | +63: iteration 19860/ 73814 | consumed samples: 10168320 | consumed tokens: 20824719360 | elapsed time per iteration (s): 2.23 | learning rate: 1.713E-04 | global batch size: 512 | lm loss: 2.152829E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.441 | TFLOPs: 23.62 | +63: iteration 19870/ 73814 | consumed samples: 10173440 | consumed tokens: 20835205120 | elapsed time per iteration (s): 2.24 | learning rate: 1.712E-04 | global batch size: 512 | lm loss: 2.157190E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.065 | TFLOPs: 23.48 | +63: iteration 19880/ 73814 | consumed samples: 10178560 | consumed tokens: 20845690880 | elapsed time per iteration (s): 2.22 | learning rate: 1.712E-04 | global batch size: 512 | lm loss: 2.173903E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.130 | TFLOPs: 23.69 | +63: iteration 19890/ 73814 | consumed samples: 10183680 | consumed tokens: 20856176640 | elapsed time per iteration (s): 2.25 | learning rate: 1.712E-04 | global batch size: 512 | lm loss: 2.157351E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.351 | TFLOPs: 23.40 | +63: iteration 19900/ 73814 | consumed samples: 10188800 | consumed tokens: 20866662400 | elapsed time per iteration (s): 2.29 | learning rate: 1.712E-04 | global batch size: 512 | lm loss: 2.168526E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.444 | TFLOPs: 23.00 | +63: iteration 19910/ 73814 | consumed samples: 10193920 | consumed tokens: 20877148160 | elapsed time per iteration (s): 2.24 | learning rate: 1.711E-04 | global batch size: 512 | lm loss: 2.182497E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.825 | TFLOPs: 23.56 | +63: iteration 19920/ 73814 | consumed samples: 10199040 | consumed tokens: 20887633920 | elapsed time per iteration (s): 2.25 | learning rate: 1.711E-04 | global batch size: 512 | lm loss: 2.202108E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.494 | TFLOPs: 23.42 | +63: iteration 19930/ 73814 | consumed samples: 10204160 | consumed tokens: 20898119680 | elapsed time per iteration (s): 2.23 | learning rate: 1.711E-04 | global batch size: 512 | lm loss: 2.184424E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.905 | TFLOPs: 23.67 | +63: iteration 19940/ 73814 | consumed samples: 10209280 | consumed tokens: 20908605440 | elapsed time per iteration (s): 2.26 | learning rate: 1.710E-04 | global batch size: 512 | lm loss: 2.706683E+00 | grad norm: 37.496 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.284 | TFLOPs: 23.29 | +63: iteration 19950/ 73814 | consumed samples: 10214400 | consumed tokens: 20919091200 | elapsed time per iteration (s): 2.28 | learning rate: 1.710E-04 | global batch size: 512 | lm loss: 6.228648E+00 | grad norm: 11.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.964 | TFLOPs: 23.16 | +63: iteration 19960/ 73814 | consumed samples: 10219520 | consumed tokens: 20929576960 | elapsed time per iteration (s): 2.24 | learning rate: 1.710E-04 | global batch size: 512 | lm loss: 8.451620E+00 | grad norm: 2.570 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.529 | TFLOPs: 23.53 | +63: iteration 19970/ 73814 | consumed samples: 10224640 | consumed tokens: 20940062720 | elapsed time per iteration (s): 2.29 | learning rate: 1.710E-04 | global batch size: 512 | lm loss: 7.380288E+00 | grad norm: 1.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.175 | TFLOPs: 22.97 | +63: iteration 19980/ 73814 | consumed samples: 10229760 | consumed tokens: 20950548480 | elapsed time per iteration (s): 2.24 | learning rate: 1.709E-04 | global batch size: 512 | lm loss: 6.228305E+00 | grad norm: 0.820 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.379 | TFLOPs: 23.51 | +63: iteration 19990/ 73814 | consumed samples: 10234880 | consumed tokens: 20961034240 | elapsed time per iteration (s): 2.26 | learning rate: 1.709E-04 | global batch size: 512 | lm loss: 5.359808E+00 | grad norm: 1.997 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.499 | TFLOPs: 23.32 | + 0: [2022-12-02 00:28:33,338] [INFO] [logging.py:68:log_dist] [Rank 0] step=20000, skipped=0, lr=[0.00017086628972647912, 0.00017086628972647912, 0.00017086628972647912], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] + 0: steps: 20000 loss: 3.4671 iter time (s): 2.272 samples/sec: 225.306 +63: iteration 20000/ 73814 | consumed samples: 10240000 | consumed tokens: 20971520000 | elapsed time per iteration (s): 2.35 | learning rate: 1.709E-04 | global batch size: 512 | lm loss: 3.899232E+00 | grad norm: 1.518 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.935 | TFLOPs: 22.44 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 20000 | lm loss value: 3.191180E+00 | lm loss PPL: 2.431711E+01 | +63: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 20000 to checkpoints_3b977boscar + 0: [2022-12-02 00:28:34,175] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step20000 is begin to save! +32: [2022-12-02 00:28:34,235] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_21-model_00-model_states.pt... + 0: [2022-12-02 00:28:34,256] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_01-model_00-model_states.pt... +32: [2022-12-02 00:28:34,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_21-model_00-model_states.pt. +32: [2022-12-02 00:28:34,618] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_22-model_00-model_states.pt... + 0: [2022-12-02 00:28:34,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_01-model_00-model_states.pt. + 0: [2022-12-02 00:28:34,744] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_03-model_00-model_states.pt... +32: [2022-12-02 00:28:34,846] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_22-model_00-model_states.pt. +32: [2022-12-02 00:28:34,847] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_23-model_00-model_states.pt... + 0: [2022-12-02 00:28:34,970] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_03-model_00-model_states.pt. + 0: [2022-12-02 00:28:34,970] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_04-model_00-model_states.pt... +32: [2022-12-02 00:28:35,071] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_23-model_00-model_states.pt. +32: [2022-12-02 00:28:35,072] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_24-model_00-model_states.pt... + 0: [2022-12-02 00:28:35,197] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_04-model_00-model_states.pt. + 0: [2022-12-02 00:28:35,198] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_05-model_00-model_states.pt... +32: [2022-12-02 00:28:35,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_24-model_00-model_states.pt. +32: [2022-12-02 00:28:35,302] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_25-model_00-model_states.pt... + 0: [2022-12-02 00:28:35,423] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_05-model_00-model_states.pt. + 0: [2022-12-02 00:28:35,423] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_06-model_00-model_states.pt... +32: [2022-12-02 00:28:35,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_25-model_00-model_states.pt. +32: [2022-12-02 00:28:35,533] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_26-model_00-model_states.pt... + 0: [2022-12-02 00:28:35,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_06-model_00-model_states.pt. + 0: [2022-12-02 00:28:35,654] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_07-model_00-model_states.pt... +32: [2022-12-02 00:28:35,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_26-model_00-model_states.pt. +32: [2022-12-02 00:28:35,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_27-model_00-model_states.pt... + 0: [2022-12-02 00:28:35,880] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_07-model_00-model_states.pt. + 0: [2022-12-02 00:28:35,880] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_08-model_00-model_states.pt... +32: [2022-12-02 00:28:35,987] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_27-model_00-model_states.pt. +32: [2022-12-02 00:28:35,988] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_28-model_00-model_states.pt... + 0: [2022-12-02 00:28:36,113] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_08-model_00-model_states.pt. + 0: [2022-12-02 00:28:36,114] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_09-model_00-model_states.pt... +32: [2022-12-02 00:28:36,215] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_28-model_00-model_states.pt. +32: [2022-12-02 00:28:36,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_29-model_00-model_states.pt... + 0: [2022-12-02 00:28:36,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_09-model_00-model_states.pt. + 0: [2022-12-02 00:28:36,344] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_10-model_00-model_states.pt... +32: [2022-12-02 00:28:36,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_29-model_00-model_states.pt. +32: [2022-12-02 00:28:36,441] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_30-model_00-model_states.pt... + 0: [2022-12-02 00:28:36,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_10-model_00-model_states.pt. + 0: [2022-12-02 00:28:36,569] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_11-model_00-model_states.pt... +32: [2022-12-02 00:28:36,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_30-model_00-model_states.pt. +32: [2022-12-02 00:28:36,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_31-model_00-model_states.pt... + 0: [2022-12-02 00:28:36,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_11-model_00-model_states.pt. + 0: [2022-12-02 00:28:36,793] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_12-model_00-model_states.pt... +32: [2022-12-02 00:28:36,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_31-model_00-model_states.pt. +32: [2022-12-02 00:28:36,891] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_32-model_00-model_states.pt... + 0: [2022-12-02 00:28:37,021] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_12-model_00-model_states.pt. + 0: [2022-12-02 00:28:37,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_13-model_00-model_states.pt... +32: [2022-12-02 00:28:37,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_32-model_00-model_states.pt. +32: [2022-12-02 00:28:37,119] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_33-model_00-model_states.pt... + 0: [2022-12-02 00:28:37,248] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_13-model_00-model_states.pt. + 0: [2022-12-02 00:28:37,249] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_14-model_00-model_states.pt... +32: [2022-12-02 00:28:37,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_33-model_00-model_states.pt. +32: [2022-12-02 00:28:37,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_34-model_00-model_states.pt... + 0: [2022-12-02 00:28:37,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 00:28:37,473] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_15-model_00-model_states.pt... +32: [2022-12-02 00:28:37,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_34-model_00-model_states.pt. +32: [2022-12-02 00:28:37,576] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_35-model_00-model_states.pt... + 0: [2022-12-02 00:28:37,702] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_15-model_00-model_states.pt. + 0: [2022-12-02 00:28:37,703] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_16-model_00-model_states.pt... +32: [2022-12-02 00:28:37,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_35-model_00-model_states.pt. +32: [2022-12-02 00:28:37,804] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_36-model_00-model_states.pt... + 0: [2022-12-02 00:28:37,926] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_16-model_00-model_states.pt. + 0: [2022-12-02 00:28:37,927] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_17-model_00-model_states.pt... +32: [2022-12-02 00:28:38,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_36-model_00-model_states.pt. +32: [2022-12-02 00:28:38,028] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_37-model_00-model_states.pt... + 0: [2022-12-02 00:28:38,152] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_17-model_00-model_states.pt. + 0: [2022-12-02 00:28:38,152] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_18-model_00-model_states.pt... +32: [2022-12-02 00:28:38,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_37-model_00-model_states.pt. +32: [2022-12-02 00:28:38,258] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_38-model_00-model_states.pt... + 0: [2022-12-02 00:28:38,385] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_18-model_00-model_states.pt. + 0: [2022-12-02 00:28:38,385] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_19-model_00-model_states.pt... +32: [2022-12-02 00:28:38,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_38-model_00-model_states.pt. +32: [2022-12-02 00:28:38,483] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_40-model_00-model_states.pt... +32: [2022-12-02 00:28:38,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_40-model_00-model_states.pt. +32: [2022-12-02 00:28:38,487] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/mp_rank_01_model_states.pt... +32: [2022-12-02 00:28:38,522] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/mp_rank_01_model_states.pt. + 0: [2022-12-02 00:28:38,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_19-model_00-model_states.pt. + 0: [2022-12-02 00:28:38,613] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/layer_20-model_00-model_states.pt... + 0: [2022-12-02 00:28:38,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/layer_20-model_00-model_states.pt. + 0: [2022-12-02 00:28:38,845] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_3b977boscar/global_step20000/mp_rank_00_model_states.pt + 0: [2022-12-02 00:28:38,845] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/mp_rank_00_model_states.pt... + 0: [2022-12-02 00:28:38,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/mp_rank_00_model_states.pt. +54: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt... +54: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt... +54: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt... +54: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt... +54: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt... +56: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt... +56: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt... +56: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt... +56: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt... +56: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt... +52: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt... +52: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt... +52: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt... +52: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt... +52: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt... +62: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt... +62: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt... +62: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt... +34: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt... +34: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt... +34: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt... +34: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt... +34: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt... +32: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt... +32: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt... +32: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt... +32: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt... +60: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt... +60: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt... +60: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt... +60: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt... +60: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt... +55: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt... +55: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt... +55: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt... +55: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt... +55: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt... +47: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt... +47: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt... +47: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt... +47: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt... +40: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt... +40: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt... +54: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt... +56: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt... +56: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt... +56: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt... +52: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt... +52: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt... +52: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt... +61: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt... +61: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt... +61: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt... +61: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt... +61: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt... +63: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt... +63: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt... +63: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt... +63: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt... +63: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt... +53: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt... +53: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt... +53: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt... +53: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt... +53: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt... +33: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt... +33: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt... +33: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt... +33: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt... +33: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt... +59: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt... +59: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt... +59: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt... +59: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt... +59: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt... +62: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt... +62: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt... +62: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt... +58: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt... +58: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt... +58: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt... +58: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt... +38: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt... +38: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt... +38: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt... +38: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt... +38: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt... +44: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt... +44: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt... +44: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt... +44: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt... +44: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt... +48: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt... +48: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt... +48: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt... +48: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt... +48: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt... +34: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt... +43: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt... +43: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt... +43: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt... +43: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt... +43: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt... +36: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt... +36: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt... +36: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt... +36: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt... +36: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt... +35: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt... +35: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt... +35: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt... +35: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt... +35: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt... +39: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt... +39: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt... +39: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt... +39: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt... +39: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt... +50: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt... +50: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt... +50: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt... +50: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt... +50: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt... +32: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt... +32: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt... +32: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt... +51: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt... +51: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt... +51: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt... +51: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt... +60: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt... +60: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt... +60: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt... +49: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt... +49: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt... +49: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt... +49: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt... +46: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt... +46: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt... +46: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt... +46: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt... +46: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt... +41: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt... +41: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt... +41: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt... +41: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt... +41: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt... +55: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt... +55: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt... +55: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt... +47: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt... +47: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt... +47: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt... +47: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt... +45: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt... +45: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt... +45: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt... +45: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt... +45: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt... +37: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt... +37: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt... +37: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt... +37: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt... +37: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt... +40: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt... +40: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt... +40: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt... +40: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt... +40: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt... +42: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt... +42: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt... +42: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt... +42: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt... +42: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt... +57: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt... +57: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt... +57: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt... +57: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt... +57: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt... + 0: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +54: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt... +54: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt... +61: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt... +61: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt... +63: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt... +63: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt... +63: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt... +53: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt... +53: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt... +53: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt... +33: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt... +33: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt... +33: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt... +59: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt... +59: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt... +59: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt... +62: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt... +62: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt... +58: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt... +58: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt... +58: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt... +58: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt... +38: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt... +38: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt... +38: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt... +44: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt... +44: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt... +44: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt... +48: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt... +48: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt... +48: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt... +34: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt... +43: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt... +43: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt... +36: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt... +36: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt... +35: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt... +35: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt... +39: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt... +50: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt... +50: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt... +50: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt... +32: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt... +51: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt... +51: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt... +51: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt... +51: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt... +49: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt... +49: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt... +49: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt... +46: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt... +46: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt... +41: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt... +41: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt... +41: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt... +45: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt... +45: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt... +45: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt... +37: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt... +40: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt... +42: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt... +42: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt... +42: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt... +57: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt... + 0: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +20: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +61: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt... + 1: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +11: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +28: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +22: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +12: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +26: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +34: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt... +43: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt... +36: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt... +35: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt... + 2: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +39: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt... +39: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt... + 4: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 6: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +31: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +49: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt... +46: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt... + 3: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +27: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... + 8: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... +16: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +14: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +17: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +29: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +30: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +24: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +23: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +23: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +37: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt... +57: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt... +57: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt... + 0: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 7: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +19: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +20: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +15: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... + 1: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +11: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... + 5: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... + 5: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +28: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +22: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +22: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +12: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +18: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +18: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +26: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... + 9: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 2: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +25: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... + 4: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 6: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +13: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +31: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... + 3: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +27: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... + 8: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... +16: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +14: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +17: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +17: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +29: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +30: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +24: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +23: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +37: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt... +21: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... + 0: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 7: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +19: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +20: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +15: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... + 1: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +11: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... + 5: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +10: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +28: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +22: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +12: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +18: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +26: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... + 9: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 2: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +25: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... + 4: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 6: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +13: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +31: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +27: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... + 8: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +16: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +14: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +17: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +29: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +30: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +24: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +23: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +21: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... + 0: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 7: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +19: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +20: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +15: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +11: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... + 5: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +10: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +28: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +22: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +12: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +18: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... + 9: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... +25: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... + 4: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 6: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +13: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +27: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +16: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +17: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +30: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +23: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... + 0: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 7: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +20: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +15: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... + 1: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 5: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +10: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +28: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +22: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +18: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... + 9: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... +25: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... + 6: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +13: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +27: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +24: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... + 7: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +20: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +10: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... + 6: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +27: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +24: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +10: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... + 6: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +13: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +24: [2022-12-02 00:28:39,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +10: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +13: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +10: [2022-12-02 00:28:39,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... + 0: [2022-12-02 00:28:39,137] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-12-02 00:28:39,137] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-12-02 00:28:39,137] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +32: [2022-12-02 00:28:39,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt. +32: [2022-12-02 00:28:39,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt +32: [2022-12-02 00:28:39,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +32: [2022-12-02 00:28:39,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt. +32: [2022-12-02 00:28:39,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt +32: [2022-12-02 00:28:39,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: [2022-12-02 00:28:39,153] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-12-02 00:28:39,154] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-12-02 00:28:39,154] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: [2022-12-02 00:28:39,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-12-02 00:28:39,154] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-12-02 00:28:39,154] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +32: [2022-12-02 00:28:39,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt. +32: [2022-12-02 00:28:39,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt +32: [2022-12-02 00:28:39,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +32: [2022-12-02 00:28:39,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt. +32: [2022-12-02 00:28:39,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt +32: [2022-12-02 00:28:39,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +32: [2022-12-02 00:28:39,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt. +32: [2022-12-02 00:28:39,162] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt +32: [2022-12-02 00:28:39,162] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +32: [2022-12-02 00:28:39,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt. +32: [2022-12-02 00:28:39,162] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt +32: [2022-12-02 00:28:39,162] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +32: [2022-12-02 00:28:39,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt. +32: [2022-12-02 00:28:39,162] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt +32: [2022-12-02 00:28:39,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt. +32: [2022-12-02 00:28:39,162] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +32: [2022-12-02 00:28:39,162] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt +32: [2022-12-02 00:28:39,163] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: [2022-12-02 00:28:39,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-12-02 00:28:39,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-12-02 00:28:39,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: [2022-12-02 00:28:39,205] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. + 0: [2022-12-02 00:28:39,205] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-12-02 00:28:39,206] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-12-02 00:28:39,206] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: [2022-12-02 00:28:39,206] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-12-02 00:28:39,206] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-12-02 00:28:39,206] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: [2022-12-02 00:28:39,206] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-12-02 00:28:39,206] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-12-02 00:28:39,206] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +44: [2022-12-02 00:28:39,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt. +44: [2022-12-02 00:28:39,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt +44: [2022-12-02 00:28:39,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +44: [2022-12-02 00:28:39,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt. +44: [2022-12-02 00:28:39,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt +44: [2022-12-02 00:28:39,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +44: [2022-12-02 00:28:39,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt. +44: [2022-12-02 00:28:39,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt +44: [2022-12-02 00:28:39,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +44: [2022-12-02 00:28:39,284] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt. +44: [2022-12-02 00:28:39,284] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt +44: [2022-12-02 00:28:39,284] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: [2022-12-02 00:28:39,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-12-02 00:28:39,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +44: [2022-12-02 00:28:39,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt. +44: [2022-12-02 00:28:39,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt +44: [2022-12-02 00:28:39,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +44: [2022-12-02 00:28:39,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt. +44: [2022-12-02 00:28:39,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt. +44: [2022-12-02 00:28:39,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt. +44: [2022-12-02 00:28:39,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt +44: [2022-12-02 00:28:39,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt +44: [2022-12-02 00:28:39,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt +44: [2022-12-02 00:28:39,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +44: [2022-12-02 00:28:39,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +44: [2022-12-02 00:28:39,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +54: [2022-12-02 00:28:39,327] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt. +54: [2022-12-02 00:28:39,327] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt. +54: [2022-12-02 00:28:39,327] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt. +54: [2022-12-02 00:28:39,327] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt. +54: [2022-12-02 00:28:39,327] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt +54: [2022-12-02 00:28:39,327] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt +54: [2022-12-02 00:28:39,327] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt +54: [2022-12-02 00:28:39,327] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt +54: [2022-12-02 00:28:39,327] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +54: [2022-12-02 00:28:39,327] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +54: [2022-12-02 00:28:39,327] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +54: [2022-12-02 00:28:39,327] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +54: [2022-12-02 00:28:39,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt. +54: [2022-12-02 00:28:39,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt. +54: [2022-12-02 00:28:39,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt. +54: [2022-12-02 00:28:39,328] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt +54: [2022-12-02 00:28:39,328] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt +54: [2022-12-02 00:28:39,328] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt +54: [2022-12-02 00:28:39,328] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +54: [2022-12-02 00:28:39,328] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +54: [2022-12-02 00:28:39,328] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +54: [2022-12-02 00:28:39,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt. +54: [2022-12-02 00:28:39,329] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt +54: [2022-12-02 00:28:39,329] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +22: [2022-12-02 00:28:39,331] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-12-02 00:28:39,331] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-12-02 00:28:39,331] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +40: [2022-12-02 00:28:39,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt. +40: [2022-12-02 00:28:39,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt. +49: [2022-12-02 00:28:39,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt. +49: [2022-12-02 00:28:39,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt. +49: [2022-12-02 00:28:39,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt +49: [2022-12-02 00:28:39,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt +49: [2022-12-02 00:28:39,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +49: [2022-12-02 00:28:39,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +40: [2022-12-02 00:28:39,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt. +40: [2022-12-02 00:28:39,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt +40: [2022-12-02 00:28:39,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt +40: [2022-12-02 00:28:39,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +40: [2022-12-02 00:28:39,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt +40: [2022-12-02 00:28:39,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +40: [2022-12-02 00:28:39,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +40: [2022-12-02 00:28:39,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt. +40: [2022-12-02 00:28:39,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt. +40: [2022-12-02 00:28:39,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt. +40: [2022-12-02 00:28:39,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt. +40: [2022-12-02 00:28:39,335] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt +40: [2022-12-02 00:28:39,335] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt +40: [2022-12-02 00:28:39,335] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt +40: [2022-12-02 00:28:39,335] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt +40: [2022-12-02 00:28:39,335] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +40: [2022-12-02 00:28:39,335] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +40: [2022-12-02 00:28:39,335] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +40: [2022-12-02 00:28:39,335] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +40: [2022-12-02 00:28:39,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt. +40: [2022-12-02 00:28:39,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt +40: [2022-12-02 00:28:39,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 8: [2022-12-02 00:28:39,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-12-02 00:28:39,339] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-12-02 00:28:39,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +45: [2022-12-02 00:28:39,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt. +45: [2022-12-02 00:28:39,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt. +33: [2022-12-02 00:28:39,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt. +33: [2022-12-02 00:28:39,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt +33: [2022-12-02 00:28:39,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt. +33: [2022-12-02 00:28:39,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +33: [2022-12-02 00:28:39,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt +33: [2022-12-02 00:28:39,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +33: [2022-12-02 00:28:39,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt. +33: [2022-12-02 00:28:39,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt +33: [2022-12-02 00:28:39,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 8: [2022-12-02 00:28:39,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-12-02 00:28:39,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-12-02 00:28:39,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 8: [2022-12-02 00:28:39,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-12-02 00:28:39,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-12-02 00:28:39,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 8: [2022-12-02 00:28:39,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. +49: [2022-12-02 00:28:39,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt. +49: [2022-12-02 00:28:39,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt. +49: [2022-12-02 00:28:39,342] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt +49: [2022-12-02 00:28:39,342] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt +49: [2022-12-02 00:28:39,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +49: [2022-12-02 00:28:39,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +45: [2022-12-02 00:28:39,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt. +45: [2022-12-02 00:28:39,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt +45: [2022-12-02 00:28:39,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt +45: [2022-12-02 00:28:39,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt. +45: [2022-12-02 00:28:39,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +45: [2022-12-02 00:28:39,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt +45: [2022-12-02 00:28:39,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +45: [2022-12-02 00:28:39,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +45: [2022-12-02 00:28:39,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt +45: [2022-12-02 00:28:39,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +45: [2022-12-02 00:28:39,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt. +45: [2022-12-02 00:28:39,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt +45: [2022-12-02 00:28:39,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt. +45: [2022-12-02 00:28:39,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt. +45: [2022-12-02 00:28:39,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt +45: [2022-12-02 00:28:39,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +45: [2022-12-02 00:28:39,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +45: [2022-12-02 00:28:39,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt +45: [2022-12-02 00:28:39,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +45: [2022-12-02 00:28:39,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt. +45: [2022-12-02 00:28:39,345] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt +45: [2022-12-02 00:28:39,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +61: [2022-12-02 00:28:39,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt. +61: [2022-12-02 00:28:39,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt. +61: [2022-12-02 00:28:39,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt. +61: [2022-12-02 00:28:39,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt +61: [2022-12-02 00:28:39,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt +61: [2022-12-02 00:28:39,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt +61: [2022-12-02 00:28:39,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +61: [2022-12-02 00:28:39,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +61: [2022-12-02 00:28:39,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-12-02 00:28:39,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +33: [2022-12-02 00:28:39,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt. +51: [2022-12-02 00:28:39,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt. +51: [2022-12-02 00:28:39,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt. +51: [2022-12-02 00:28:39,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt. +10: [2022-12-02 00:28:39,345] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-12-02 00:28:39,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-12-02 00:28:39,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-12-02 00:28:39,346] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-12-02 00:28:39,346] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-12-02 00:28:39,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-12-02 00:28:39,347] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-12-02 00:28:39,347] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-12-02 00:28:39,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-12-02 00:28:39,347] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +51: [2022-12-02 00:28:39,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt. +10: [2022-12-02 00:28:39,347] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +51: [2022-12-02 00:28:39,350] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt +51: [2022-12-02 00:28:39,350] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt +51: [2022-12-02 00:28:39,350] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt +51: [2022-12-02 00:28:39,350] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +51: [2022-12-02 00:28:39,350] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +51: [2022-12-02 00:28:39,350] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt +51: [2022-12-02 00:28:39,350] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +51: [2022-12-02 00:28:39,350] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +51: [2022-12-02 00:28:39,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt. +51: [2022-12-02 00:28:39,350] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt +51: [2022-12-02 00:28:39,350] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +30: [2022-12-02 00:28:39,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-12-02 00:28:39,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +10: [2022-12-02 00:28:39,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +51: [2022-12-02 00:28:39,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt. +51: [2022-12-02 00:28:39,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt +10: [2022-12-02 00:28:39,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +51: [2022-12-02 00:28:39,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-12-02 00:28:39,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-12-02 00:28:39,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-12-02 00:28:39,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-12-02 00:28:39,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-12-02 00:28:39,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +30: [2022-12-02 00:28:39,350] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +51: [2022-12-02 00:28:39,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt. +30: [2022-12-02 00:28:39,350] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-12-02 00:28:39,350] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +30: [2022-12-02 00:28:39,350] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +51: [2022-12-02 00:28:39,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt +51: [2022-12-02 00:28:39,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt. +51: [2022-12-02 00:28:39,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +51: [2022-12-02 00:28:39,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt +10: [2022-12-02 00:28:39,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-12-02 00:28:39,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +51: [2022-12-02 00:28:39,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +61: [2022-12-02 00:28:39,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt. +30: [2022-12-02 00:28:39,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-12-02 00:28:39,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-12-02 00:28:39,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +61: [2022-12-02 00:28:39,352] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt +61: [2022-12-02 00:28:39,352] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +61: [2022-12-02 00:28:39,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt. +61: [2022-12-02 00:28:39,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt. +61: [2022-12-02 00:28:39,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt. +61: [2022-12-02 00:28:39,352] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt +61: [2022-12-02 00:28:39,352] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt +61: [2022-12-02 00:28:39,352] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt +61: [2022-12-02 00:28:39,352] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +61: [2022-12-02 00:28:39,352] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +61: [2022-12-02 00:28:39,352] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +61: [2022-12-02 00:28:39,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt. +61: [2022-12-02 00:28:39,352] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt +61: [2022-12-02 00:28:39,353] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +25: [2022-12-02 00:28:39,353] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-12-02 00:28:39,353] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-12-02 00:28:39,353] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +33: [2022-12-02 00:28:39,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt +33: [2022-12-02 00:28:39,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt. +33: [2022-12-02 00:28:39,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt. +33: [2022-12-02 00:28:39,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +33: [2022-12-02 00:28:39,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt +33: [2022-12-02 00:28:39,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt +33: [2022-12-02 00:28:39,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +33: [2022-12-02 00:28:39,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +24: [2022-12-02 00:28:39,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-12-02 00:28:39,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-12-02 00:28:39,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. + 6: [2022-12-02 00:28:39,354] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-12-02 00:28:39,354] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-12-02 00:28:39,354] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +24: [2022-12-02 00:28:39,353] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-12-02 00:28:39,353] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-12-02 00:28:39,353] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-12-02 00:28:39,353] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +24: [2022-12-02 00:28:39,353] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +24: [2022-12-02 00:28:39,353] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-12-02 00:28:39,355] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-12-02 00:28:39,355] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-12-02 00:28:39,355] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-12-02 00:28:39,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-12-02 00:28:39,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-12-02 00:28:39,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-12-02 00:28:39,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-12-02 00:28:39,355] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-12-02 00:28:39,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-12-02 00:28:39,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-12-02 00:28:39,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-12-02 00:28:39,355] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-12-02 00:28:39,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-12-02 00:28:39,355] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-12-02 00:28:39,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-12-02 00:28:39,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-12-02 00:28:39,355] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-12-02 00:28:39,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-12-02 00:28:39,356] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-12-02 00:28:39,356] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-12-02 00:28:39,356] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +38: [2022-12-02 00:28:39,365] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt. +38: [2022-12-02 00:28:39,365] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt. +38: [2022-12-02 00:28:39,365] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt. +38: [2022-12-02 00:28:39,365] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt +38: [2022-12-02 00:28:39,365] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt. +38: [2022-12-02 00:28:39,365] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt. +38: [2022-12-02 00:28:39,365] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt. +38: [2022-12-02 00:28:39,365] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt +38: [2022-12-02 00:28:39,365] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt +38: [2022-12-02 00:28:39,366] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +38: [2022-12-02 00:28:39,366] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +38: [2022-12-02 00:28:39,366] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +38: [2022-12-02 00:28:39,366] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt +38: [2022-12-02 00:28:39,366] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt +38: [2022-12-02 00:28:39,366] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt +38: [2022-12-02 00:28:39,366] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +38: [2022-12-02 00:28:39,366] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +38: [2022-12-02 00:28:39,366] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +19: [2022-12-02 00:28:39,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-12-02 00:28:39,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-12-02 00:28:39,369] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-12-02 00:28:39,369] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +19: [2022-12-02 00:28:39,369] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-12-02 00:28:39,369] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-12-02 00:28:39,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-12-02 00:28:39,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-12-02 00:28:39,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-12-02 00:28:39,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-12-02 00:28:39,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-12-02 00:28:39,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-12-02 00:28:39,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-12-02 00:28:39,369] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-12-02 00:28:39,369] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-12-02 00:28:39,369] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-12-02 00:28:39,369] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-12-02 00:28:39,369] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-12-02 00:28:39,369] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-12-02 00:28:39,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-12-02 00:28:39,370] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-12-02 00:28:39,370] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 8: [2022-12-02 00:28:39,342] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-12-02 00:28:39,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 8: [2022-12-02 00:28:39,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-12-02 00:28:39,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-12-02 00:28:39,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 8: [2022-12-02 00:28:39,361] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-12-02 00:28:39,361] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-12-02 00:28:39,361] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-12-02 00:28:39,371] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-12-02 00:28:39,371] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-12-02 00:28:39,371] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-12-02 00:28:39,371] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-12-02 00:28:39,371] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-12-02 00:28:39,371] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-12-02 00:28:39,371] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-12-02 00:28:39,371] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-12-02 00:28:39,371] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-12-02 00:28:39,371] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-12-02 00:28:39,371] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-12-02 00:28:39,371] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-12-02 00:28:39,371] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +62: [2022-12-02 00:28:39,353] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt. +62: [2022-12-02 00:28:39,353] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt +62: [2022-12-02 00:28:39,353] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +62: [2022-12-02 00:28:39,353] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt. +62: [2022-12-02 00:28:39,354] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt +62: [2022-12-02 00:28:39,354] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +62: [2022-12-02 00:28:39,354] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt. +62: [2022-12-02 00:28:39,354] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt +62: [2022-12-02 00:28:39,354] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +62: [2022-12-02 00:28:39,371] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt. +62: [2022-12-02 00:28:39,371] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt +62: [2022-12-02 00:28:39,371] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +62: [2022-12-02 00:28:39,371] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt. +62: [2022-12-02 00:28:39,371] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt. +62: [2022-12-02 00:28:39,372] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt +62: [2022-12-02 00:28:39,372] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt +62: [2022-12-02 00:28:39,372] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +62: [2022-12-02 00:28:39,372] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-12-02 00:28:39,372] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +35: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt. +35: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt. + 6: [2022-12-02 00:28:39,372] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-12-02 00:28:39,372] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +35: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt. +35: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt. +35: [2022-12-02 00:28:39,370] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt +35: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt. +35: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt. +35: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt. +35: [2022-12-02 00:28:39,370] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt +35: [2022-12-02 00:28:39,370] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt +35: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +35: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +35: [2022-12-02 00:28:39,370] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt +35: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +35: [2022-12-02 00:28:39,370] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt +35: [2022-12-02 00:28:39,370] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt +35: [2022-12-02 00:28:39,370] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt +35: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +35: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +35: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +35: [2022-12-02 00:28:39,370] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +22: [2022-12-02 00:28:39,375] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +63: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt. +63: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt. +63: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt. +63: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt. +63: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt. +63: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt. +63: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt. +63: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt. +63: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt +63: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt +63: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt +63: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt +63: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt +63: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt +63: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt +63: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt +63: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +63: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +63: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +63: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +63: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +63: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +63: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +63: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +46: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt. +46: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt. +46: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt. +46: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt. +46: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt. +18: [2022-12-02 00:28:39,375] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-12-02 00:28:39,375] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-12-02 00:28:39,375] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-12-02 00:28:39,375] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-12-02 00:28:39,375] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +46: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt +46: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt +46: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt +46: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt +46: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt +46: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +46: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +46: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +46: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +46: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +52: [2022-12-02 00:28:39,374] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt. +52: [2022-12-02 00:28:39,374] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt. +52: [2022-12-02 00:28:39,374] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt. +59: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt. +59: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt. +59: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt. +59: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt. +59: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt. + 4: [2022-12-02 00:28:39,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +12: [2022-12-02 00:28:39,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-12-02 00:28:39,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-12-02 00:28:39,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-12-02 00:28:39,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +59: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt. +59: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt. +59: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt +59: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt +59: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt +59: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt +59: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt +59: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt +59: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt +59: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt. +59: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +59: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +59: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +59: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +59: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +59: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +59: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +59: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt +59: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +18: [2022-12-02 00:28:39,375] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-12-02 00:28:39,375] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-12-02 00:28:39,375] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-12-02 00:28:39,375] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-12-02 00:28:39,375] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-12-02 00:28:39,375] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-12-02 00:28:39,375] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-12-02 00:28:39,375] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-12-02 00:28:39,375] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-12-02 00:28:39,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +18: [2022-12-02 00:28:39,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +18: [2022-12-02 00:28:39,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +18: [2022-12-02 00:28:39,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +18: [2022-12-02 00:28:39,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +18: [2022-12-02 00:28:39,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-12-02 00:28:39,378] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +18: [2022-12-02 00:28:39,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-12-02 00:28:39,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +18: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. + 4: [2022-12-02 00:28:39,379] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +18: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt + 4: [2022-12-02 00:28:39,379] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +18: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-12-02 00:28:39,379] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-12-02 00:28:39,379] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-12-02 00:28:39,379] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-12-02 00:28:39,379] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +52: [2022-12-02 00:28:39,374] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt. +52: [2022-12-02 00:28:39,374] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt. +52: [2022-12-02 00:28:39,375] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt +52: [2022-12-02 00:28:39,375] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt +52: [2022-12-02 00:28:39,375] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt +52: [2022-12-02 00:28:39,375] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt +52: [2022-12-02 00:28:39,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +52: [2022-12-02 00:28:39,375] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt +52: [2022-12-02 00:28:39,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +52: [2022-12-02 00:28:39,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +52: [2022-12-02 00:28:39,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +52: [2022-12-02 00:28:39,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +52: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt. +52: [2022-12-02 00:28:39,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt +52: [2022-12-02 00:28:39,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +52: [2022-12-02 00:28:39,377] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt. +52: [2022-12-02 00:28:39,377] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt +52: [2022-12-02 00:28:39,377] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +25: [2022-12-02 00:28:39,384] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-12-02 00:28:39,384] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-12-02 00:28:39,384] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +35: [2022-12-02 00:28:39,379] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt. +43: [2022-12-02 00:28:39,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt. +43: [2022-12-02 00:28:39,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt. +43: [2022-12-02 00:28:39,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt. +43: [2022-12-02 00:28:39,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt. +43: [2022-12-02 00:28:39,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt. +12: [2022-12-02 00:28:39,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-12-02 00:28:39,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-12-02 00:28:39,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-12-02 00:28:39,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +12: [2022-12-02 00:28:39,378] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-12-02 00:28:39,378] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-12-02 00:28:39,378] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-12-02 00:28:39,378] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-12-02 00:28:39,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-12-02 00:28:39,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-12-02 00:28:39,378] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-12-02 00:28:39,378] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-12-02 00:28:39,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-12-02 00:28:39,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-12-02 00:28:39,378] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-12-02 00:28:39,378] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt + 5: [2022-12-02 00:28:39,384] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +12: [2022-12-02 00:28:39,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-12-02 00:28:39,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-12-02 00:28:39,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-12-02 00:28:39,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-12-02 00:28:39,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-12-02 00:28:39,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-12-02 00:28:39,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-12-02 00:28:39,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +11: [2022-12-02 00:28:39,384] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-12-02 00:28:39,384] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-12-02 00:28:39,384] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-12-02 00:28:39,384] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-12-02 00:28:39,384] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +43: [2022-12-02 00:28:39,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt. +43: [2022-12-02 00:28:39,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt. +43: [2022-12-02 00:28:39,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt. +43: [2022-12-02 00:28:39,382] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt +43: [2022-12-02 00:28:39,382] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt +43: [2022-12-02 00:28:39,382] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt +43: [2022-12-02 00:28:39,382] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt +43: [2022-12-02 00:28:39,382] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt +43: [2022-12-02 00:28:39,382] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt +43: [2022-12-02 00:28:39,382] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt +43: [2022-12-02 00:28:39,382] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +43: [2022-12-02 00:28:39,382] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt + 5: [2022-12-02 00:28:39,384] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +43: [2022-12-02 00:28:39,382] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +43: [2022-12-02 00:28:39,382] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-12-02 00:28:39,384] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +43: [2022-12-02 00:28:39,382] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +43: [2022-12-02 00:28:39,382] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +43: [2022-12-02 00:28:39,382] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-12-02 00:28:39,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +43: [2022-12-02 00:28:39,382] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +43: [2022-12-02 00:28:39,382] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-12-02 00:28:39,384] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-12-02 00:28:39,384] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-12-02 00:28:39,384] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-12-02 00:28:39,384] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-12-02 00:28:39,384] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-12-02 00:28:39,385] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-12-02 00:28:39,385] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-12-02 00:28:39,385] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-12-02 00:28:39,385] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-12-02 00:28:39,385] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-12-02 00:28:39,385] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-12-02 00:28:39,386] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-12-02 00:28:39,386] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-12-02 00:28:39,386] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-12-02 00:28:39,385] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-12-02 00:28:39,386] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-12-02 00:28:39,386] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +11: [2022-12-02 00:28:39,384] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. + 5: [2022-12-02 00:28:39,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +11: [2022-12-02 00:28:39,385] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-12-02 00:28:39,385] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-12-02 00:28:39,385] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-12-02 00:28:39,385] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-12-02 00:28:39,385] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt + 5: [2022-12-02 00:28:39,387] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +11: [2022-12-02 00:28:39,385] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt + 5: [2022-12-02 00:28:39,387] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +11: [2022-12-02 00:28:39,385] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +11: [2022-12-02 00:28:39,385] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +11: [2022-12-02 00:28:39,385] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +11: [2022-12-02 00:28:39,385] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +11: [2022-12-02 00:28:39,385] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +11: [2022-12-02 00:28:39,385] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +35: [2022-12-02 00:28:39,379] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt +35: [2022-12-02 00:28:39,379] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-12-02 00:28:39,383] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-12-02 00:28:39,383] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-12-02 00:28:39,383] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-12-02 00:28:39,383] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-12-02 00:28:39,383] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-12-02 00:28:39,383] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-12-02 00:28:39,383] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-12-02 00:28:39,383] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-12-02 00:28:39,391] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 2: [2022-12-02 00:28:39,391] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-12-02 00:28:39,391] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-12-02 00:28:39,391] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +37: [2022-12-02 00:28:39,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt. +37: [2022-12-02 00:28:39,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt. +19: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. + 2: [2022-12-02 00:28:39,391] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 2: [2022-12-02 00:28:39,391] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-12-02 00:28:39,391] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-12-02 00:28:39,391] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-12-02 00:28:39,391] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-12-02 00:28:39,391] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-12-02 00:28:39,391] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-12-02 00:28:39,391] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +22: [2022-12-02 00:28:39,390] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +31: [2022-12-02 00:28:39,393] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-12-02 00:28:39,393] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-12-02 00:28:39,393] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-12-02 00:28:39,393] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-12-02 00:28:39,393] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +60: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt. +60: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt. +60: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt. +41: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt. +41: [2022-12-02 00:28:39,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt +41: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +41: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt. +58: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt. +58: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt. +58: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt. +58: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt. +58: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt. +23: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +41: [2022-12-02 00:28:39,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt +41: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt. +58: [2022-12-02 00:28:39,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt +58: [2022-12-02 00:28:39,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt +58: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt. +58: [2022-12-02 00:28:39,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt +41: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +58: [2022-12-02 00:28:39,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt +58: [2022-12-02 00:28:39,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt +41: [2022-12-02 00:28:39,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt +58: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +58: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +41: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +58: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +58: [2022-12-02 00:28:39,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt +58: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +58: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +41: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt. +58: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +41: [2022-12-02 00:28:39,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt +58: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt. +41: [2022-12-02 00:28:39,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +58: [2022-12-02 00:28:39,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt +41: [2022-12-02 00:28:39,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt. +58: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +58: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt. +41: [2022-12-02 00:28:39,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt +58: [2022-12-02 00:28:39,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt +58: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +41: [2022-12-02 00:28:39,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +41: [2022-12-02 00:28:39,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt. +41: [2022-12-02 00:28:39,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt. +41: [2022-12-02 00:28:39,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt. +41: [2022-12-02 00:28:39,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt +41: [2022-12-02 00:28:39,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt +22: [2022-12-02 00:28:39,391] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +41: [2022-12-02 00:28:39,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt +22: [2022-12-02 00:28:39,391] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +41: [2022-12-02 00:28:39,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +22: [2022-12-02 00:28:39,393] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +21: [2022-12-02 00:28:39,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-12-02 00:28:39,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-12-02 00:28:39,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +22: [2022-12-02 00:28:39,393] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +21: [2022-12-02 00:28:39,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +22: [2022-12-02 00:28:39,393] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-12-02 00:28:39,398] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-12-02 00:28:39,398] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-12-02 00:28:39,398] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-12-02 00:28:39,398] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-12-02 00:28:39,398] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +23: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +23: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-12-02 00:28:39,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +23: [2022-12-02 00:28:39,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-12-02 00:28:39,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +23: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +31: [2022-12-02 00:28:39,393] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +60: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt. +60: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt. +60: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt. +60: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt. +60: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt. +31: [2022-12-02 00:28:39,393] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-12-02 00:28:39,393] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +60: [2022-12-02 00:28:39,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt +31: [2022-12-02 00:28:39,393] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-12-02 00:28:39,393] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-12-02 00:28:39,393] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-12-02 00:28:39,393] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-12-02 00:28:39,393] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +60: [2022-12-02 00:28:39,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt +31: [2022-12-02 00:28:39,393] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +41: [2022-12-02 00:28:39,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +60: [2022-12-02 00:28:39,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt +60: [2022-12-02 00:28:39,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt +31: [2022-12-02 00:28:39,393] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +31: [2022-12-02 00:28:39,393] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +31: [2022-12-02 00:28:39,393] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +41: [2022-12-02 00:28:39,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +60: [2022-12-02 00:28:39,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt +60: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +60: [2022-12-02 00:28:39,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt +31: [2022-12-02 00:28:39,393] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +31: [2022-12-02 00:28:39,393] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +60: [2022-12-02 00:28:39,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt +31: [2022-12-02 00:28:39,393] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +60: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +31: [2022-12-02 00:28:39,393] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +60: [2022-12-02 00:28:39,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt +27: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +60: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +60: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +60: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +60: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +60: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +60: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +37: [2022-12-02 00:28:39,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt. +37: [2022-12-02 00:28:39,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt. +37: [2022-12-02 00:28:39,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt. +37: [2022-12-02 00:28:39,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt. +37: [2022-12-02 00:28:39,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt. +37: [2022-12-02 00:28:39,388] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt +37: [2022-12-02 00:28:39,388] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt +37: [2022-12-02 00:28:39,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt. +37: [2022-12-02 00:28:39,388] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt +37: [2022-12-02 00:28:39,388] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt +37: [2022-12-02 00:28:39,388] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt +37: [2022-12-02 00:28:39,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +37: [2022-12-02 00:28:39,388] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt +37: [2022-12-02 00:28:39,388] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt +37: [2022-12-02 00:28:39,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +37: [2022-12-02 00:28:39,388] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt +37: [2022-12-02 00:28:39,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +37: [2022-12-02 00:28:39,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +37: [2022-12-02 00:28:39,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +37: [2022-12-02 00:28:39,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +37: [2022-12-02 00:28:39,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +37: [2022-12-02 00:28:39,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +19: [2022-12-02 00:28:39,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +31: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-12-02 00:28:39,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +27: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-12-02 00:28:39,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-12-02 00:28:39,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-12-02 00:28:39,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +27: [2022-12-02 00:28:39,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +27: [2022-12-02 00:28:39,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-12-02 00:28:39,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-12-02 00:28:39,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +27: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +27: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +27: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +27: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +27: [2022-12-02 00:28:39,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-12-02 00:28:39,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-12-02 00:28:39,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-12-02 00:28:39,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-12-02 00:28:39,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-12-02 00:28:39,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-12-02 00:28:39,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-12-02 00:28:39,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-12-02 00:28:39,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-12-02 00:28:39,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-12-02 00:28:39,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-12-02 00:28:39,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-12-02 00:28:39,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-12-02 00:28:39,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-12-02 00:28:39,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-12-02 00:28:39,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-12-02 00:28:39,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-12-02 00:28:39,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-12-02 00:28:39,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-12-02 00:28:39,403] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-12-02 00:28:39,403] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-12-02 00:28:39,403] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-12-02 00:28:39,403] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-12-02 00:28:39,403] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-12-02 00:28:39,403] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-12-02 00:28:39,403] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-12-02 00:28:39,403] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-12-02 00:28:39,403] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +49: [2022-12-02 00:28:39,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt. +29: [2022-12-02 00:28:39,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-12-02 00:28:39,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-12-02 00:28:39,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-12-02 00:28:39,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-12-02 00:28:39,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +49: [2022-12-02 00:28:39,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt +24: [2022-12-02 00:28:39,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +49: [2022-12-02 00:28:39,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +24: [2022-12-02 00:28:39,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-12-02 00:28:39,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +30: [2022-12-02 00:28:39,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-12-02 00:28:39,409] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-12-02 00:28:39,409] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +29: [2022-12-02 00:28:39,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-12-02 00:28:39,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-12-02 00:28:39,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-12-02 00:28:39,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-12-02 00:28:39,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-12-02 00:28:39,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +29: [2022-12-02 00:28:39,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +29: [2022-12-02 00:28:39,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +29: [2022-12-02 00:28:39,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +29: [2022-12-02 00:28:39,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +29: [2022-12-02 00:28:39,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-12-02 00:28:39,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-12-02 00:28:39,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +29: [2022-12-02 00:28:39,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-12-02 00:28:39,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-12-02 00:28:39,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +29: [2022-12-02 00:28:39,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-12-02 00:28:39,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-12-02 00:28:39,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +48: [2022-12-02 00:28:39,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt. +48: [2022-12-02 00:28:39,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt. +48: [2022-12-02 00:28:39,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt. +48: [2022-12-02 00:28:39,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt. +48: [2022-12-02 00:28:39,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt. +48: [2022-12-02 00:28:39,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt. +48: [2022-12-02 00:28:39,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt. +48: [2022-12-02 00:28:39,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt +48: [2022-12-02 00:28:39,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt. +48: [2022-12-02 00:28:39,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt +48: [2022-12-02 00:28:39,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt +48: [2022-12-02 00:28:39,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt +48: [2022-12-02 00:28:39,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt +48: [2022-12-02 00:28:39,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt +48: [2022-12-02 00:28:39,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +48: [2022-12-02 00:28:39,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +48: [2022-12-02 00:28:39,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +48: [2022-12-02 00:28:39,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +48: [2022-12-02 00:28:39,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +48: [2022-12-02 00:28:39,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt +48: [2022-12-02 00:28:39,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt +48: [2022-12-02 00:28:39,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +48: [2022-12-02 00:28:39,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +48: [2022-12-02 00:28:39,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +19: [2022-12-02 00:28:39,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +24: [2022-12-02 00:28:39,416] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-12-02 00:28:39,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-12-02 00:28:39,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-12-02 00:28:39,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-12-02 00:28:39,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-12-02 00:28:39,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-12-02 00:28:39,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-12-02 00:28:39,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-12-02 00:28:39,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-12-02 00:28:39,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-12-02 00:28:39,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-12-02 00:28:39,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-12-02 00:28:39,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-12-02 00:28:39,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-12-02 00:28:39,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-12-02 00:28:39,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-12-02 00:28:39,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-12-02 00:28:39,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-12-02 00:28:39,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-12-02 00:28:39,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-12-02 00:28:39,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-12-02 00:28:39,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-12-02 00:28:39,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-12-02 00:28:39,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-12-02 00:28:39,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-12-02 00:28:39,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-12-02 00:28:39,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-12-02 00:28:39,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-12-02 00:28:39,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-12-02 00:28:39,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-12-02 00:28:39,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-12-02 00:28:39,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-12-02 00:28:39,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +19: [2022-12-02 00:28:39,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +55: [2022-12-02 00:28:39,416] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt. +55: [2022-12-02 00:28:39,416] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt. +55: [2022-12-02 00:28:39,416] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt. +55: [2022-12-02 00:28:39,416] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt. +55: [2022-12-02 00:28:39,416] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt. +19: [2022-12-02 00:28:39,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-12-02 00:28:39,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-12-02 00:28:39,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-12-02 00:28:39,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-12-02 00:28:39,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-12-02 00:28:39,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-12-02 00:28:39,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-12-02 00:28:39,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-12-02 00:28:39,421] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-12-02 00:28:39,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-12-02 00:28:39,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-12-02 00:28:39,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-12-02 00:28:39,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-12-02 00:28:39,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-12-02 00:28:39,421] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-12-02 00:28:39,421] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-12-02 00:28:39,421] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-12-02 00:28:39,421] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-12-02 00:28:39,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-12-02 00:28:39,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-12-02 00:28:39,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-12-02 00:28:39,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +55: [2022-12-02 00:28:39,416] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt. +55: [2022-12-02 00:28:39,416] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt. +55: [2022-12-02 00:28:39,416] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt +55: [2022-12-02 00:28:39,416] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt +55: [2022-12-02 00:28:39,416] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt +55: [2022-12-02 00:28:39,416] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt +55: [2022-12-02 00:28:39,416] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt +55: [2022-12-02 00:28:39,416] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt +55: [2022-12-02 00:28:39,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +55: [2022-12-02 00:28:39,416] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt +55: [2022-12-02 00:28:39,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +55: [2022-12-02 00:28:39,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +55: [2022-12-02 00:28:39,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +55: [2022-12-02 00:28:39,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +55: [2022-12-02 00:28:39,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +55: [2022-12-02 00:28:39,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +55: [2022-12-02 00:28:39,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt. +55: [2022-12-02 00:28:39,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt +55: [2022-12-02 00:28:39,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 3: [2022-12-02 00:28:39,423] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-12-02 00:28:39,423] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-12-02 00:28:39,423] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-12-02 00:28:39,423] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-12-02 00:28:39,423] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 3: [2022-12-02 00:28:39,423] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 3: [2022-12-02 00:28:39,424] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-12-02 00:28:39,424] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-12-02 00:28:39,424] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-12-02 00:28:39,424] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-12-02 00:28:39,424] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-12-02 00:28:39,424] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-12-02 00:28:39,424] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 3: [2022-12-02 00:28:39,424] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 3: [2022-12-02 00:28:39,424] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 3: [2022-12-02 00:28:39,424] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-12-02 00:28:39,424] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-12-02 00:28:39,424] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-12-02 00:28:39,424] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-12-02 00:28:39,424] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 3: [2022-12-02 00:28:39,424] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 3: [2022-12-02 00:28:39,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-12-02 00:28:39,425] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-12-02 00:28:39,425] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-12-02 00:28:39,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-12-02 00:28:39,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-12-02 00:28:39,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +25: [2022-12-02 00:28:39,427] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-12-02 00:28:39,427] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-12-02 00:28:39,427] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +13: [2022-12-02 00:28:39,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-12-02 00:28:39,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-12-02 00:28:39,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-12-02 00:28:39,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +19: [2022-12-02 00:28:39,424] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +24: [2022-12-02 00:28:39,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-12-02 00:28:39,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-12-02 00:28:39,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +53: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt. +53: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt. +53: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt. +53: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt. +53: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt. +13: [2022-12-02 00:28:39,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-12-02 00:28:39,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +53: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt. +53: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt. +13: [2022-12-02 00:28:39,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-12-02 00:28:39,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-12-02 00:28:39,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-12-02 00:28:39,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-12-02 00:28:39,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +53: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt +13: [2022-12-02 00:28:39,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +53: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt +13: [2022-12-02 00:28:39,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +13: [2022-12-02 00:28:39,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +13: [2022-12-02 00:28:39,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +13: [2022-12-02 00:28:39,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +13: [2022-12-02 00:28:39,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-12-02 00:28:39,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +53: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt. +53: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt +13: [2022-12-02 00:28:39,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-12-02 00:28:39,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +53: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt +53: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt +13: [2022-12-02 00:28:39,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +13: [2022-12-02 00:28:39,427] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +53: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt +53: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt +13: [2022-12-02 00:28:39,427] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +13: [2022-12-02 00:28:39,427] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +53: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +53: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +53: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +53: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +53: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +53: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt +53: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +53: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +53: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +50: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt. +50: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt. +50: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt. +50: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt. +50: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt. +16: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +50: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt. +50: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt. +50: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt. +50: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt +50: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt +50: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt +50: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt +50: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt +50: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt +50: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt +50: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +50: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +50: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +50: [2022-12-02 00:28:39,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt +50: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +50: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +50: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +50: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +42: [2022-12-02 00:28:39,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt. +42: [2022-12-02 00:28:39,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt. +42: [2022-12-02 00:28:39,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt. +50: [2022-12-02 00:28:39,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-12-02 00:28:39,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +42: [2022-12-02 00:28:39,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt. +42: [2022-12-02 00:28:39,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt. +42: [2022-12-02 00:28:39,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt. +42: [2022-12-02 00:28:39,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt. +42: [2022-12-02 00:28:39,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt. +42: [2022-12-02 00:28:39,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt +42: [2022-12-02 00:28:39,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt +19: [2022-12-02 00:28:39,424] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +42: [2022-12-02 00:28:39,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt +42: [2022-12-02 00:28:39,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt +19: [2022-12-02 00:28:39,424] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +42: [2022-12-02 00:28:39,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt +42: [2022-12-02 00:28:39,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt +42: [2022-12-02 00:28:39,430] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +42: [2022-12-02 00:28:39,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt +42: [2022-12-02 00:28:39,430] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +42: [2022-12-02 00:28:39,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt +42: [2022-12-02 00:28:39,430] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +42: [2022-12-02 00:28:39,430] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +42: [2022-12-02 00:28:39,430] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +42: [2022-12-02 00:28:39,430] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +42: [2022-12-02 00:28:39,430] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +42: [2022-12-02 00:28:39,430] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-12-02 00:28:39,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-12-02 00:28:39,431] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +25: [2022-12-02 00:28:39,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-12-02 00:28:39,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-12-02 00:28:39,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-12-02 00:28:39,435] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-12-02 00:28:39,436] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-12-02 00:28:39,436] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +11: [2022-12-02 00:28:39,436] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-12-02 00:28:39,437] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-12-02 00:28:39,437] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +11: [2022-12-02 00:28:39,437] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-12-02 00:28:39,437] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-12-02 00:28:39,437] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +38: [2022-12-02 00:28:39,439] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt. +38: [2022-12-02 00:28:39,439] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt +38: [2022-12-02 00:28:39,439] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +38: [2022-12-02 00:28:39,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt. +38: [2022-12-02 00:28:39,441] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt +38: [2022-12-02 00:28:39,441] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +47: [2022-12-02 00:28:39,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt. +47: [2022-12-02 00:28:39,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt. +47: [2022-12-02 00:28:39,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt. +47: [2022-12-02 00:28:39,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt. +47: [2022-12-02 00:28:39,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt. +47: [2022-12-02 00:28:39,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt. +47: [2022-12-02 00:28:39,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt. +47: [2022-12-02 00:28:39,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt. +47: [2022-12-02 00:28:39,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt +47: [2022-12-02 00:28:39,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt +47: [2022-12-02 00:28:39,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt +47: [2022-12-02 00:28:39,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt +47: [2022-12-02 00:28:39,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt +47: [2022-12-02 00:28:39,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +47: [2022-12-02 00:28:39,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt +47: [2022-12-02 00:28:39,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt +47: [2022-12-02 00:28:39,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +47: [2022-12-02 00:28:39,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt +47: [2022-12-02 00:28:39,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +47: [2022-12-02 00:28:39,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +47: [2022-12-02 00:28:39,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +47: [2022-12-02 00:28:39,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +47: [2022-12-02 00:28:39,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +47: [2022-12-02 00:28:39,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +34: [2022-12-02 00:28:39,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt. +34: [2022-12-02 00:28:39,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt. +34: [2022-12-02 00:28:39,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt +34: [2022-12-02 00:28:39,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt +34: [2022-12-02 00:28:39,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +34: [2022-12-02 00:28:39,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +34: [2022-12-02 00:28:39,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt. +34: [2022-12-02 00:28:39,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt. +34: [2022-12-02 00:28:39,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt +34: [2022-12-02 00:28:39,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt +34: [2022-12-02 00:28:39,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +34: [2022-12-02 00:28:39,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 8: [2022-12-02 00:28:39,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. +34: [2022-12-02 00:28:39,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt. +34: [2022-12-02 00:28:39,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt. +34: [2022-12-02 00:28:39,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt. +34: [2022-12-02 00:28:39,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt +34: [2022-12-02 00:28:39,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt. +34: [2022-12-02 00:28:39,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt +34: [2022-12-02 00:28:39,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt +34: [2022-12-02 00:28:39,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +34: [2022-12-02 00:28:39,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt +34: [2022-12-02 00:28:39,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +34: [2022-12-02 00:28:39,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +34: [2022-12-02 00:28:39,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-12-02 00:28:39,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-12-02 00:28:39,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-12-02 00:28:39,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 8: [2022-12-02 00:28:39,444] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-12-02 00:28:39,444] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 8: [2022-12-02 00:28:39,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 7: [2022-12-02 00:28:39,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-12-02 00:28:39,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-12-02 00:28:39,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-12-02 00:28:39,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-12-02 00:28:39,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 8: [2022-12-02 00:28:39,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-12-02 00:28:39,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 9: [2022-12-02 00:28:39,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-12-02 00:28:39,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-12-02 00:28:39,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-12-02 00:28:39,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-12-02 00:28:39,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-12-02 00:28:39,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-12-02 00:28:39,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-12-02 00:28:39,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-12-02 00:28:39,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-12-02 00:28:39,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-12-02 00:28:39,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-12-02 00:28:39,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-12-02 00:28:39,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-12-02 00:28:39,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-12-02 00:28:39,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 9: [2022-12-02 00:28:39,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-12-02 00:28:39,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 9: [2022-12-02 00:28:39,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 9: [2022-12-02 00:28:39,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 9: [2022-12-02 00:28:39,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 9: [2022-12-02 00:28:39,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 9: [2022-12-02 00:28:39,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-12-02 00:28:39,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 9: [2022-12-02 00:28:39,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +49: [2022-12-02 00:28:39,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt. + 7: [2022-12-02 00:28:39,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-12-02 00:28:39,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-12-02 00:28:39,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-12-02 00:28:39,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-12-02 00:28:39,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-12-02 00:28:39,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-12-02 00:28:39,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-12-02 00:28:39,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-12-02 00:28:39,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-12-02 00:28:39,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +49: [2022-12-02 00:28:39,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt + 7: [2022-12-02 00:28:39,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +49: [2022-12-02 00:28:39,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-12-02 00:28:39,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-12-02 00:28:39,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-12-02 00:28:39,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-12-02 00:28:39,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-12-02 00:28:39,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-12-02 00:28:39,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-12-02 00:28:39,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-12-02 00:28:39,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +46: [2022-12-02 00:28:39,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt. +46: [2022-12-02 00:28:39,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt +46: [2022-12-02 00:28:39,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-12-02 00:28:39,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-12-02 00:28:39,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-12-02 00:28:39,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-12-02 00:28:39,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-12-02 00:28:39,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-12-02 00:28:39,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-12-02 00:28:39,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +33: [2022-12-02 00:28:39,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt. +26: [2022-12-02 00:28:39,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-12-02 00:28:39,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-12-02 00:28:39,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-12-02 00:28:39,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +33: [2022-12-02 00:28:39,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt +26: [2022-12-02 00:28:39,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-12-02 00:28:39,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +33: [2022-12-02 00:28:39,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-12-02 00:28:39,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-12-02 00:28:39,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-12-02 00:28:39,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-12-02 00:28:39,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-12-02 00:28:39,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-12-02 00:28:39,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-12-02 00:28:39,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-12-02 00:28:39,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-12-02 00:28:39,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-12-02 00:28:39,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-12-02 00:28:39,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +19: [2022-12-02 00:28:39,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-12-02 00:28:39,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +30: [2022-12-02 00:28:39,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +19: [2022-12-02 00:28:39,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +30: [2022-12-02 00:28:39,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-12-02 00:28:39,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +30: [2022-12-02 00:28:39,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-12-02 00:28:39,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-12-02 00:28:39,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +57: [2022-12-02 00:28:39,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt. +57: [2022-12-02 00:28:39,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt. +57: [2022-12-02 00:28:39,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt. +57: [2022-12-02 00:28:39,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt. +57: [2022-12-02 00:28:39,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt. +57: [2022-12-02 00:28:39,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt. +57: [2022-12-02 00:28:39,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt +57: [2022-12-02 00:28:39,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt. +57: [2022-12-02 00:28:39,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt +57: [2022-12-02 00:28:39,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt +57: [2022-12-02 00:28:39,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt. +57: [2022-12-02 00:28:39,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt +57: [2022-12-02 00:28:39,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +57: [2022-12-02 00:28:39,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +57: [2022-12-02 00:28:39,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +57: [2022-12-02 00:28:39,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +57: [2022-12-02 00:28:39,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt +57: [2022-12-02 00:28:39,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt +57: [2022-12-02 00:28:39,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt +57: [2022-12-02 00:28:39,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt +57: [2022-12-02 00:28:39,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +57: [2022-12-02 00:28:39,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +57: [2022-12-02 00:28:39,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +57: [2022-12-02 00:28:39,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-12-02 00:28:39,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-12-02 00:28:39,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-12-02 00:28:39,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-12-02 00:28:39,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-12-02 00:28:39,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-12-02 00:28:39,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-12-02 00:28:39,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-12-02 00:28:39,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-12-02 00:28:39,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-12-02 00:28:39,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-12-02 00:28:39,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-12-02 00:28:39,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-12-02 00:28:39,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-12-02 00:28:39,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-12-02 00:28:39,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-12-02 00:28:39,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-12-02 00:28:39,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-12-02 00:28:39,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-12-02 00:28:39,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-12-02 00:28:39,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-12-02 00:28:39,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-12-02 00:28:39,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-12-02 00:28:39,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-12-02 00:28:39,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +56: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt. +56: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt. +56: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt. +56: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt. +56: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt. +56: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt. +56: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt. +56: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt. +56: [2022-12-02 00:28:39,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt +56: [2022-12-02 00:28:39,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt +56: [2022-12-02 00:28:39,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt +56: [2022-12-02 00:28:39,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt +39: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt. +39: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt. +39: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt. +39: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt. +39: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt. +56: [2022-12-02 00:28:39,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt +56: [2022-12-02 00:28:39,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt +56: [2022-12-02 00:28:39,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt +56: [2022-12-02 00:28:39,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt +39: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt. +39: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt. +56: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +56: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +39: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt. +39: [2022-12-02 00:28:39,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt +39: [2022-12-02 00:28:39,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt +39: [2022-12-02 00:28:39,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt +39: [2022-12-02 00:28:39,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt +56: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +39: [2022-12-02 00:28:39,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt +39: [2022-12-02 00:28:39,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt +39: [2022-12-02 00:28:39,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt +56: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +56: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +39: [2022-12-02 00:28:39,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt +56: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +56: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +56: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +39: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +39: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +39: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +39: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +39: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +39: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +39: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +39: [2022-12-02 00:28:39,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +30: [2022-12-02 00:28:39,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-12-02 00:28:39,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-12-02 00:28:39,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-12-02 00:28:39,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-12-02 00:28:39,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +30: [2022-12-02 00:28:39,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +25: [2022-12-02 00:28:39,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +22: [2022-12-02 00:28:39,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +22: [2022-12-02 00:28:39,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +22: [2022-12-02 00:28:39,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +36: [2022-12-02 00:28:39,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt. +36: [2022-12-02 00:28:39,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt. +36: [2022-12-02 00:28:39,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt. +36: [2022-12-02 00:28:39,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt. +36: [2022-12-02 00:28:39,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt. +36: [2022-12-02 00:28:39,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt. +36: [2022-12-02 00:28:39,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt. +36: [2022-12-02 00:28:39,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt. +36: [2022-12-02 00:28:39,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt +36: [2022-12-02 00:28:39,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt +36: [2022-12-02 00:28:39,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt +36: [2022-12-02 00:28:39,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt +36: [2022-12-02 00:28:39,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt +36: [2022-12-02 00:28:39,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt +36: [2022-12-02 00:28:39,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt +36: [2022-12-02 00:28:39,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt +36: [2022-12-02 00:28:39,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +36: [2022-12-02 00:28:39,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +36: [2022-12-02 00:28:39,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +36: [2022-12-02 00:28:39,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +36: [2022-12-02 00:28:39,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +36: [2022-12-02 00:28:39,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +36: [2022-12-02 00:28:39,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +36: [2022-12-02 00:28:39,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +23: [2022-12-02 00:28:39,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-12-02 00:28:39,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-12-02 00:28:39,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +19: [2022-12-02 00:28:39,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-12-02 00:28:39,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-12-02 00:28:39,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +62: [2022-12-02 00:28:39,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt. +62: [2022-12-02 00:28:39,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt +62: [2022-12-02 00:28:39,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +62: [2022-12-02 00:28:39,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt. +62: [2022-12-02 00:28:39,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt +62: [2022-12-02 00:28:39,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-12-02 00:28:39,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-12-02 00:28:39,494] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-12-02 00:28:39,494] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +25: [2022-12-02 00:28:39,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-12-02 00:28:39,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-12-02 00:28:39,498] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-12-02 00:28:39,498] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-12-02 00:28:39,498] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +46: [2022-12-02 00:28:39,498] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt. +46: [2022-12-02 00:28:39,498] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt +46: [2022-12-02 00:28:39,498] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +52: [2022-12-02 00:28:39,498] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt. +52: [2022-12-02 00:28:39,498] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt +52: [2022-12-02 00:28:39,498] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +46: [2022-12-02 00:28:39,501] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt. +46: [2022-12-02 00:28:39,501] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt +46: [2022-12-02 00:28:39,501] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +22: [2022-12-02 00:28:39,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-12-02 00:28:39,503] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-12-02 00:28:39,503] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +25: [2022-12-02 00:28:39,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-12-02 00:28:39,503] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-12-02 00:28:39,503] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +25: [2022-12-02 00:28:39,516] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-12-02 00:28:39,516] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-12-02 00:28:39,517] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +25: [2022-12-02 00:28:39,516] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-12-02 00:28:39,517] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-12-02 00:28:39,517] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-12-02 00:28:39,517] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-12-02 00:28:39,517] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-12-02 00:28:39,517] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-12-02 00:28:39,522] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-12-02 00:28:39,522] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-12-02 00:28:39,523] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +23: [2022-12-02 00:28:39,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-12-02 00:28:39,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-12-02 00:28:39,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +23: [2022-12-02 00:28:39,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-12-02 00:28:39,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-12-02 00:28:39,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +23: [2022-12-02 00:28:39,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-12-02 00:28:39,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-12-02 00:28:39,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +19: [2022-12-02 00:28:39,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-12-02 00:28:39,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-12-02 00:28:39,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +49: [2022-12-02 00:28:39,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt. +49: [2022-12-02 00:28:39,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt +49: [2022-12-02 00:28:39,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +24: [2022-12-02 00:28:39,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-12-02 00:28:39,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-12-02 00:28:39,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +24: [2022-12-02 00:28:39,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-12-02 00:28:39,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-12-02 00:28:39,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +49: [2022-12-02 00:28:39,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt. +49: [2022-12-02 00:28:39,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt +49: [2022-12-02 00:28:39,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-12-02 00:28:39,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-12-02 00:28:39,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-12-02 00:28:39,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +22: [2022-12-02 00:28:39,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-12-02 00:28:39,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-12-02 00:28:39,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +22: [2022-12-02 00:28:39,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-12-02 00:28:39,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-12-02 00:28:39,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +23: [2022-12-02 00:28:39,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-12-02 00:28:39,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-12-02 00:28:39,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +33: [2022-12-02 00:28:39,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt. +33: [2022-12-02 00:28:39,590] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step20000/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt +33: [2022-12-02 00:28:39,590] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: successfully saved checkpoint at iteration 20000 to checkpoints_3b977boscar +63: time (ms) | save-checkpoint: 5537.69 +63: iteration 20010/ 73814 | consumed samples: 10245120 | consumed tokens: 20982005760 | elapsed time per iteration (s): 2.86 | learning rate: 1.708E-04 | global batch size: 512 | lm loss: 3.063236E+00 | grad norm: 2.570 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 178.961 | TFLOPs: 18.42 | +63: iteration 20020/ 73814 | consumed samples: 10250240 | consumed tokens: 20992491520 | elapsed time per iteration (s): 2.24 | learning rate: 1.708E-04 | global batch size: 512 | lm loss: 2.652744E+00 | grad norm: 0.645 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.504 | TFLOPs: 23.52 | +63: iteration 20030/ 73814 | consumed samples: 10255360 | consumed tokens: 21002977280 | elapsed time per iteration (s): 2.24 | learning rate: 1.708E-04 | global batch size: 512 | lm loss: 2.477065E+00 | grad norm: 0.425 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.466 | TFLOPs: 23.52 | +63: iteration 20040/ 73814 | consumed samples: 10260480 | consumed tokens: 21013463040 | elapsed time per iteration (s): 2.24 | learning rate: 1.708E-04 | global batch size: 512 | lm loss: 2.355538E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.483 | TFLOPs: 23.52 | +63: iteration 20050/ 73814 | consumed samples: 10265600 | consumed tokens: 21023948800 | elapsed time per iteration (s): 2.27 | learning rate: 1.707E-04 | global batch size: 512 | lm loss: 2.306993E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.847 | TFLOPs: 23.25 | +63: iteration 20060/ 73814 | consumed samples: 10270720 | consumed tokens: 21034434560 | elapsed time per iteration (s): 2.30 | learning rate: 1.707E-04 | global batch size: 512 | lm loss: 2.268224E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.490 | TFLOPs: 22.90 | +63: iteration 20070/ 73814 | consumed samples: 10275840 | consumed tokens: 21044920320 | elapsed time per iteration (s): 2.24 | learning rate: 1.707E-04 | global batch size: 512 | lm loss: 2.226239E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.612 | TFLOPs: 23.53 | +63: iteration 20080/ 73814 | consumed samples: 10280960 | consumed tokens: 21055406080 | elapsed time per iteration (s): 2.35 | learning rate: 1.706E-04 | global batch size: 512 | lm loss: 2.227117E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.312 | TFLOPs: 22.47 | +63: iteration 20090/ 73814 | consumed samples: 10286080 | consumed tokens: 21065891840 | elapsed time per iteration (s): 2.23 | learning rate: 1.706E-04 | global batch size: 512 | lm loss: 2.219862E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.672 | TFLOPs: 23.64 | +63: iteration 20100/ 73814 | consumed samples: 10291200 | consumed tokens: 21076377600 | elapsed time per iteration (s): 2.25 | learning rate: 1.706E-04 | global batch size: 512 | lm loss: 2.224330E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.899 | TFLOPs: 23.46 | +63: iteration 20110/ 73814 | consumed samples: 10296320 | consumed tokens: 21086863360 | elapsed time per iteration (s): 2.23 | learning rate: 1.706E-04 | global batch size: 512 | lm loss: 2.235164E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.107 | TFLOPs: 23.59 | +63: iteration 20120/ 73814 | consumed samples: 10301440 | consumed tokens: 21097349120 | elapsed time per iteration (s): 2.25 | learning rate: 1.705E-04 | global batch size: 512 | lm loss: 2.205782E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.131 | TFLOPs: 23.38 | +63: iteration 20130/ 73814 | consumed samples: 10306560 | consumed tokens: 21107834880 | elapsed time per iteration (s): 2.25 | learning rate: 1.705E-04 | global batch size: 512 | lm loss: 2.226724E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.858 | TFLOPs: 23.46 | +63: iteration 20140/ 73814 | consumed samples: 10311680 | consumed tokens: 21118320640 | elapsed time per iteration (s): 2.23 | learning rate: 1.705E-04 | global batch size: 512 | lm loss: 2.200936E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.168 | TFLOPs: 23.59 | +63: iteration 20150/ 73814 | consumed samples: 10316800 | consumed tokens: 21128806400 | elapsed time per iteration (s): 2.26 | learning rate: 1.704E-04 | global batch size: 512 | lm loss: 2.199120E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.441 | TFLOPs: 23.31 | +63: iteration 20160/ 73814 | consumed samples: 10321920 | consumed tokens: 21139292160 | elapsed time per iteration (s): 2.23 | learning rate: 1.704E-04 | global batch size: 512 | lm loss: 2.199777E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.837 | TFLOPs: 23.66 | +63: iteration 20170/ 73814 | consumed samples: 10327040 | consumed tokens: 21149777920 | elapsed time per iteration (s): 2.28 | learning rate: 1.704E-04 | global batch size: 512 | lm loss: 2.203226E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.030 | TFLOPs: 23.17 | +63: iteration 20180/ 73814 | consumed samples: 10332160 | consumed tokens: 21160263680 | elapsed time per iteration (s): 2.23 | learning rate: 1.704E-04 | global batch size: 512 | lm loss: 2.217142E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.813 | TFLOPs: 23.66 | +63: iteration 20190/ 73814 | consumed samples: 10337280 | consumed tokens: 21170749440 | elapsed time per iteration (s): 2.22 | learning rate: 1.703E-04 | global batch size: 512 | lm loss: 2.200846E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.119 | TFLOPs: 23.69 | +63: iteration 20200/ 73814 | consumed samples: 10342400 | consumed tokens: 21181235200 | elapsed time per iteration (s): 2.24 | learning rate: 1.703E-04 | global batch size: 512 | lm loss: 2.198257E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.156 | TFLOPs: 23.49 | +63: iteration 20210/ 73814 | consumed samples: 10347520 | consumed tokens: 21191720960 | elapsed time per iteration (s): 2.23 | learning rate: 1.703E-04 | global batch size: 512 | lm loss: 2.195520E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.974 | TFLOPs: 23.67 | +63: iteration 20220/ 73814 | consumed samples: 10352640 | consumed tokens: 21202206720 | elapsed time per iteration (s): 2.24 | learning rate: 1.702E-04 | global batch size: 512 | lm loss: 2.185571E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.378 | TFLOPs: 23.51 | +63: iteration 20230/ 73814 | consumed samples: 10357760 | consumed tokens: 21212692480 | elapsed time per iteration (s): 2.24 | learning rate: 1.702E-04 | global batch size: 512 | lm loss: 2.196248E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.902 | TFLOPs: 23.56 | +63: iteration 20240/ 73814 | consumed samples: 10362880 | consumed tokens: 21223178240 | elapsed time per iteration (s): 2.25 | learning rate: 1.702E-04 | global batch size: 512 | lm loss: 2.174399E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.079 | TFLOPs: 23.38 | +63: iteration 20250/ 73814 | consumed samples: 10368000 | consumed tokens: 21233664000 | elapsed time per iteration (s): 2.28 | learning rate: 1.702E-04 | global batch size: 512 | lm loss: 2.195751E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.931 | TFLOPs: 23.16 | +63: iteration 20260/ 73814 | consumed samples: 10373120 | consumed tokens: 21244149760 | elapsed time per iteration (s): 2.29 | learning rate: 1.701E-04 | global batch size: 512 | lm loss: 2.195382E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.136 | TFLOPs: 22.97 | +63: iteration 20270/ 73814 | consumed samples: 10378240 | consumed tokens: 21254635520 | elapsed time per iteration (s): 2.43 | learning rate: 1.701E-04 | global batch size: 512 | lm loss: 2.185381E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.872 | TFLOPs: 21.71 | +63: iteration 20280/ 73814 | consumed samples: 10383360 | consumed tokens: 21265121280 | elapsed time per iteration (s): 2.46 | learning rate: 1.701E-04 | global batch size: 512 | lm loss: 2.176891E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.410 | TFLOPs: 21.45 | +63: iteration 20290/ 73814 | consumed samples: 10388480 | consumed tokens: 21275607040 | elapsed time per iteration (s): 2.28 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 2.177762E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.886 | TFLOPs: 23.15 | +63: iteration 20300/ 73814 | consumed samples: 10393600 | consumed tokens: 21286092800 | elapsed time per iteration (s): 2.31 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 2.176282E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.983 | TFLOPs: 22.85 | +63: iteration 20310/ 73814 | consumed samples: 10398720 | consumed tokens: 21296578560 | elapsed time per iteration (s): 2.58 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 2.200808E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.305 | TFLOPs: 20.41 | +63: iteration 20320/ 73814 | consumed samples: 10403840 | consumed tokens: 21307064320 | elapsed time per iteration (s): 2.63 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 2.200586E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 194.512 | TFLOPs: 20.02 | +63: iteration 20330/ 73814 | consumed samples: 10408960 | consumed tokens: 21317550080 | elapsed time per iteration (s): 2.23 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 2.186976E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.124 | TFLOPs: 23.59 | +63: iteration 20340/ 73814 | consumed samples: 10414080 | consumed tokens: 21328035840 | elapsed time per iteration (s): 2.30 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 2.168192E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.786 | TFLOPs: 22.93 | +63: iteration 20350/ 73814 | consumed samples: 10419200 | consumed tokens: 21338521600 | elapsed time per iteration (s): 2.41 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 2.139817E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.812 | TFLOPs: 21.91 | +63: iteration 20360/ 73814 | consumed samples: 10424320 | consumed tokens: 21349007360 | elapsed time per iteration (s): 2.37 | learning rate: 1.698E-04 | global batch size: 512 | lm loss: 2.208604E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.470 | TFLOPs: 22.28 | +63: iteration 20370/ 73814 | consumed samples: 10429440 | consumed tokens: 21359493120 | elapsed time per iteration (s): 2.31 | learning rate: 1.698E-04 | global batch size: 512 | lm loss: 2.160182E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.947 | TFLOPs: 22.85 | +63: iteration 20380/ 73814 | consumed samples: 10434560 | consumed tokens: 21369978880 | elapsed time per iteration (s): 2.25 | learning rate: 1.698E-04 | global batch size: 512 | lm loss: 2.173345E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.818 | TFLOPs: 23.45 | +63: iteration 20390/ 73814 | consumed samples: 10439680 | consumed tokens: 21380464640 | elapsed time per iteration (s): 2.25 | learning rate: 1.697E-04 | global batch size: 512 | lm loss: 2.202462E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.925 | TFLOPs: 23.46 | +63: iteration 20400/ 73814 | consumed samples: 10444800 | consumed tokens: 21390950400 | elapsed time per iteration (s): 2.27 | learning rate: 1.697E-04 | global batch size: 512 | lm loss: 2.187980E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.443 | TFLOPs: 23.21 | +63: iteration 20410/ 73814 | consumed samples: 10449920 | consumed tokens: 21401436160 | elapsed time per iteration (s): 2.23 | learning rate: 1.697E-04 | global batch size: 512 | lm loss: 2.156117E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.116 | TFLOPs: 23.59 | +63: iteration 20420/ 73814 | consumed samples: 10455040 | consumed tokens: 21411921920 | elapsed time per iteration (s): 2.29 | learning rate: 1.697E-04 | global batch size: 512 | lm loss: 2.168702E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.438 | TFLOPs: 23.00 | +63: iteration 20430/ 73814 | consumed samples: 10460160 | consumed tokens: 21422407680 | elapsed time per iteration (s): 2.23 | learning rate: 1.696E-04 | global batch size: 512 | lm loss: 2.172523E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.712 | TFLOPs: 23.65 | +63: iteration 20440/ 73814 | consumed samples: 10465280 | consumed tokens: 21432893440 | elapsed time per iteration (s): 2.27 | learning rate: 1.696E-04 | global batch size: 512 | lm loss: 2.167193E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.320 | TFLOPs: 23.20 | +63: iteration 20450/ 73814 | consumed samples: 10470400 | consumed tokens: 21443379200 | elapsed time per iteration (s): 2.24 | learning rate: 1.696E-04 | global batch size: 512 | lm loss: 2.178405E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.258 | TFLOPs: 23.50 | +63: iteration 20460/ 73814 | consumed samples: 10475520 | consumed tokens: 21453864960 | elapsed time per iteration (s): 2.23 | learning rate: 1.695E-04 | global batch size: 512 | lm loss: 2.148330E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.332 | TFLOPs: 23.61 | +63: iteration 20470/ 73814 | consumed samples: 10480640 | consumed tokens: 21464350720 | elapsed time per iteration (s): 2.23 | learning rate: 1.695E-04 | global batch size: 512 | lm loss: 2.187147E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.919 | TFLOPs: 23.67 | +63: iteration 20480/ 73814 | consumed samples: 10485760 | consumed tokens: 21474836480 | elapsed time per iteration (s): 2.24 | learning rate: 1.695E-04 | global batch size: 512 | lm loss: 2.167917E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.679 | TFLOPs: 23.54 | +63: iteration 20490/ 73814 | consumed samples: 10490880 | consumed tokens: 21485322240 | elapsed time per iteration (s): 2.24 | learning rate: 1.695E-04 | global batch size: 512 | lm loss: 2.163837E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.363 | TFLOPs: 23.51 | +63: iteration 20500/ 73814 | consumed samples: 10496000 | consumed tokens: 21495808000 | elapsed time per iteration (s): 2.25 | learning rate: 1.694E-04 | global batch size: 512 | lm loss: 2.190903E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.040 | TFLOPs: 23.48 | +63: iteration 20510/ 73814 | consumed samples: 10501120 | consumed tokens: 21506293760 | elapsed time per iteration (s): 2.23 | learning rate: 1.694E-04 | global batch size: 512 | lm loss: 2.172452E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.039 | TFLOPs: 23.68 | +63: iteration 20520/ 73814 | consumed samples: 10506240 | consumed tokens: 21516779520 | elapsed time per iteration (s): 2.22 | learning rate: 1.694E-04 | global batch size: 512 | lm loss: 2.185047E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.180 | TFLOPs: 23.70 | +63: iteration 20530/ 73814 | consumed samples: 10511360 | consumed tokens: 21527265280 | elapsed time per iteration (s): 2.25 | learning rate: 1.693E-04 | global batch size: 512 | lm loss: 2.197416E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.922 | TFLOPs: 23.46 | +63: iteration 20540/ 73814 | consumed samples: 10516480 | consumed tokens: 21537751040 | elapsed time per iteration (s): 2.23 | learning rate: 1.693E-04 | global batch size: 512 | lm loss: 2.159995E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.482 | TFLOPs: 23.62 | +63: iteration 20550/ 73814 | consumed samples: 10521600 | consumed tokens: 21548236800 | elapsed time per iteration (s): 2.24 | learning rate: 1.693E-04 | global batch size: 512 | lm loss: 2.148495E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.997 | TFLOPs: 23.57 | +63: iteration 20560/ 73814 | consumed samples: 10526720 | consumed tokens: 21558722560 | elapsed time per iteration (s): 2.24 | learning rate: 1.693E-04 | global batch size: 512 | lm loss: 2.186684E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.064 | TFLOPs: 23.58 | +63: iteration 20570/ 73814 | consumed samples: 10531840 | consumed tokens: 21569208320 | elapsed time per iteration (s): 2.23 | learning rate: 1.692E-04 | global batch size: 512 | lm loss: 2.181837E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.895 | TFLOPs: 23.67 | +63: iteration 20580/ 73814 | consumed samples: 10536960 | consumed tokens: 21579694080 | elapsed time per iteration (s): 2.24 | learning rate: 1.692E-04 | global batch size: 512 | lm loss: 2.168378E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.695 | TFLOPs: 23.54 | +63: iteration 20590/ 73814 | consumed samples: 10542080 | consumed tokens: 21590179840 | elapsed time per iteration (s): 2.30 | learning rate: 1.692E-04 | global batch size: 512 | lm loss: 2.161476E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.195 | TFLOPs: 22.87 | +63: iteration 20600/ 73814 | consumed samples: 10547200 | consumed tokens: 21600665600 | elapsed time per iteration (s): 2.24 | learning rate: 1.691E-04 | global batch size: 512 | lm loss: 2.164405E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.033 | TFLOPs: 23.58 | +63: iteration 20610/ 73814 | consumed samples: 10552320 | consumed tokens: 21611151360 | elapsed time per iteration (s): 2.24 | learning rate: 1.691E-04 | global batch size: 512 | lm loss: 2.176045E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.041 | TFLOPs: 23.58 | +63: iteration 20620/ 73814 | consumed samples: 10557440 | consumed tokens: 21621637120 | elapsed time per iteration (s): 2.52 | learning rate: 1.691E-04 | global batch size: 512 | lm loss: 2.164178E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.913 | TFLOPs: 20.89 | +63: iteration 20630/ 73814 | consumed samples: 10562560 | consumed tokens: 21632122880 | elapsed time per iteration (s): 2.23 | learning rate: 1.690E-04 | global batch size: 512 | lm loss: 2.170249E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.434 | TFLOPs: 23.62 | +63: iteration 20640/ 73814 | consumed samples: 10567680 | consumed tokens: 21642608640 | elapsed time per iteration (s): 2.27 | learning rate: 1.690E-04 | global batch size: 512 | lm loss: 2.163361E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.162 | TFLOPs: 23.18 | +63: iteration 20650/ 73814 | consumed samples: 10572800 | consumed tokens: 21653094400 | elapsed time per iteration (s): 2.26 | learning rate: 1.690E-04 | global batch size: 512 | lm loss: 2.170715E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.626 | TFLOPs: 23.33 | +63: iteration 20660/ 73814 | consumed samples: 10577920 | consumed tokens: 21663580160 | elapsed time per iteration (s): 2.25 | learning rate: 1.690E-04 | global batch size: 512 | lm loss: 2.163317E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.752 | TFLOPs: 23.45 | +63: iteration 20670/ 73814 | consumed samples: 10583040 | consumed tokens: 21674065920 | elapsed time per iteration (s): 2.22 | learning rate: 1.689E-04 | global batch size: 512 | lm loss: 2.153574E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.292 | TFLOPs: 23.71 | +63: iteration 20680/ 73814 | consumed samples: 10588160 | consumed tokens: 21684551680 | elapsed time per iteration (s): 2.23 | learning rate: 1.689E-04 | global batch size: 512 | lm loss: 2.195632E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.786 | TFLOPs: 23.66 | +63: iteration 20690/ 73814 | consumed samples: 10593280 | consumed tokens: 21695037440 | elapsed time per iteration (s): 2.23 | learning rate: 1.689E-04 | global batch size: 512 | lm loss: 2.167280E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.207 | TFLOPs: 23.60 | +63: iteration 20700/ 73814 | consumed samples: 10598400 | consumed tokens: 21705523200 | elapsed time per iteration (s): 2.24 | learning rate: 1.688E-04 | global batch size: 512 | lm loss: 2.179412E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.494 | TFLOPs: 23.52 | +63: iteration 20710/ 73814 | consumed samples: 10603520 | consumed tokens: 21716008960 | elapsed time per iteration (s): 2.25 | learning rate: 1.688E-04 | global batch size: 512 | lm loss: 2.173574E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.369 | TFLOPs: 23.41 | +63: iteration 20720/ 73814 | consumed samples: 10608640 | consumed tokens: 21726494720 | elapsed time per iteration (s): 2.23 | learning rate: 1.688E-04 | global batch size: 512 | lm loss: 2.170927E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.907 | TFLOPs: 23.67 | +63: iteration 20730/ 73814 | consumed samples: 10613760 | consumed tokens: 21736980480 | elapsed time per iteration (s): 2.22 | learning rate: 1.688E-04 | global batch size: 512 | lm loss: 2.169807E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.173 | TFLOPs: 23.70 | +63: iteration 20740/ 73814 | consumed samples: 10618880 | consumed tokens: 21747466240 | elapsed time per iteration (s): 2.23 | learning rate: 1.687E-04 | global batch size: 512 | lm loss: 2.162275E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.599 | TFLOPs: 23.64 | +63: iteration 20750/ 73814 | consumed samples: 10624000 | consumed tokens: 21757952000 | elapsed time per iteration (s): 2.30 | learning rate: 1.687E-04 | global batch size: 512 | lm loss: 2.153394E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.393 | TFLOPs: 22.89 | +63: iteration 20760/ 73814 | consumed samples: 10629120 | consumed tokens: 21768437760 | elapsed time per iteration (s): 2.23 | learning rate: 1.687E-04 | global batch size: 512 | lm loss: 2.151972E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.991 | TFLOPs: 23.68 | +63: iteration 20770/ 73814 | consumed samples: 10634240 | consumed tokens: 21778923520 | elapsed time per iteration (s): 2.23 | learning rate: 1.686E-04 | global batch size: 512 | lm loss: 2.174658E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.346 | TFLOPs: 23.61 | +63: iteration 20780/ 73814 | consumed samples: 10639360 | consumed tokens: 21789409280 | elapsed time per iteration (s): 2.29 | learning rate: 1.686E-04 | global batch size: 512 | lm loss: 2.161567E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.053 | TFLOPs: 23.07 | +63: iteration 20790/ 73814 | consumed samples: 10644480 | consumed tokens: 21799895040 | elapsed time per iteration (s): 2.24 | learning rate: 1.686E-04 | global batch size: 512 | lm loss: 2.162656E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.702 | TFLOPs: 23.54 | +63: iteration 20800/ 73814 | consumed samples: 10649600 | consumed tokens: 21810380800 | elapsed time per iteration (s): 2.25 | learning rate: 1.686E-04 | global batch size: 512 | lm loss: 2.178303E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.114 | TFLOPs: 23.38 | +63: iteration 20810/ 73814 | consumed samples: 10654720 | consumed tokens: 21820866560 | elapsed time per iteration (s): 2.25 | learning rate: 1.685E-04 | global batch size: 512 | lm loss: 2.126506E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.767 | TFLOPs: 23.45 | +63: iteration 20820/ 73814 | consumed samples: 10659840 | consumed tokens: 21831352320 | elapsed time per iteration (s): 2.23 | learning rate: 1.685E-04 | global batch size: 512 | lm loss: 2.189853E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.091 | TFLOPs: 23.58 | +63: iteration 20830/ 73814 | consumed samples: 10664960 | consumed tokens: 21841838080 | elapsed time per iteration (s): 2.23 | learning rate: 1.685E-04 | global batch size: 512 | lm loss: 2.158898E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.160 | TFLOPs: 23.59 | +63: iteration 20840/ 73814 | consumed samples: 10670080 | consumed tokens: 21852323840 | elapsed time per iteration (s): 2.24 | learning rate: 1.684E-04 | global batch size: 512 | lm loss: 2.171152E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.967 | TFLOPs: 23.57 | +63: iteration 20850/ 73814 | consumed samples: 10675200 | consumed tokens: 21862809600 | elapsed time per iteration (s): 2.27 | learning rate: 1.684E-04 | global batch size: 512 | lm loss: 2.166955E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.862 | TFLOPs: 23.25 | +63: iteration 20860/ 73814 | consumed samples: 10680320 | consumed tokens: 21873295360 | elapsed time per iteration (s): 2.44 | learning rate: 1.684E-04 | global batch size: 512 | lm loss: 2.151954E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.106 | TFLOPs: 21.63 | +63: iteration 20870/ 73814 | consumed samples: 10685440 | consumed tokens: 21883781120 | elapsed time per iteration (s): 2.25 | learning rate: 1.683E-04 | global batch size: 512 | lm loss: 2.178063E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.061 | TFLOPs: 23.48 | +63: iteration 20880/ 73814 | consumed samples: 10690560 | consumed tokens: 21894266880 | elapsed time per iteration (s): 2.25 | learning rate: 1.683E-04 | global batch size: 512 | lm loss: 2.146039E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.105 | TFLOPs: 23.38 | +63: iteration 20890/ 73814 | consumed samples: 10695680 | consumed tokens: 21904752640 | elapsed time per iteration (s): 2.27 | learning rate: 1.683E-04 | global batch size: 512 | lm loss: 2.165981E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.986 | TFLOPs: 23.26 | +63: iteration 20900/ 73814 | consumed samples: 10700800 | consumed tokens: 21915238400 | elapsed time per iteration (s): 2.24 | learning rate: 1.683E-04 | global batch size: 512 | lm loss: 2.166240E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.829 | TFLOPs: 23.56 | +63: iteration 20910/ 73814 | consumed samples: 10705920 | consumed tokens: 21925724160 | elapsed time per iteration (s): 2.25 | learning rate: 1.682E-04 | global batch size: 512 | lm loss: 2.170028E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.549 | TFLOPs: 23.43 | +63: iteration 20920/ 73814 | consumed samples: 10711040 | consumed tokens: 21936209920 | elapsed time per iteration (s): 2.23 | learning rate: 1.682E-04 | global batch size: 512 | lm loss: 2.157280E+00 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.872 | TFLOPs: 23.66 | +63: iteration 20930/ 73814 | consumed samples: 10716160 | consumed tokens: 21946695680 | elapsed time per iteration (s): 2.24 | learning rate: 1.682E-04 | global batch size: 512 | lm loss: 2.157542E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.067 | TFLOPs: 23.48 | +63: iteration 20940/ 73814 | consumed samples: 10721280 | consumed tokens: 21957181440 | elapsed time per iteration (s): 2.24 | learning rate: 1.681E-04 | global batch size: 512 | lm loss: 2.155682E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.584 | TFLOPs: 23.53 | +63: iteration 20950/ 73814 | consumed samples: 10726400 | consumed tokens: 21967667200 | elapsed time per iteration (s): 2.24 | learning rate: 1.681E-04 | global batch size: 512 | lm loss: 2.171500E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.159 | TFLOPs: 23.49 | +63: iteration 20960/ 73814 | consumed samples: 10731520 | consumed tokens: 21978152960 | elapsed time per iteration (s): 2.23 | learning rate: 1.681E-04 | global batch size: 512 | lm loss: 2.163670E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.931 | TFLOPs: 23.67 | +63: iteration 20970/ 73814 | consumed samples: 10736640 | consumed tokens: 21988638720 | elapsed time per iteration (s): 2.25 | learning rate: 1.680E-04 | global batch size: 512 | lm loss: 2.145445E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.242 | TFLOPs: 23.39 | +63: iteration 20980/ 73814 | consumed samples: 10741760 | consumed tokens: 21999124480 | elapsed time per iteration (s): 2.25 | learning rate: 1.680E-04 | global batch size: 512 | lm loss: 2.157401E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.836 | TFLOPs: 23.45 | +63: iteration 20990/ 73814 | consumed samples: 10746880 | consumed tokens: 22009610240 | elapsed time per iteration (s): 2.22 | learning rate: 1.680E-04 | global batch size: 512 | lm loss: 2.185891E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.280 | TFLOPs: 23.71 | +63: iteration 21000/ 73814 | consumed samples: 10752000 | consumed tokens: 22020096000 | elapsed time per iteration (s): 2.24 | learning rate: 1.680E-04 | global batch size: 512 | lm loss: 2.166452E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.689 | TFLOPs: 23.54 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 21000 | lm loss value: 2.112110E+00 | lm loss PPL: 8.265663E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 21010/ 73814 | consumed samples: 10757120 | consumed tokens: 22030581760 | elapsed time per iteration (s): 2.28 | learning rate: 1.679E-04 | global batch size: 512 | lm loss: 2.167144E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.206 | TFLOPs: 23.08 | +63: iteration 21020/ 73814 | consumed samples: 10762240 | consumed tokens: 22041067520 | elapsed time per iteration (s): 2.24 | learning rate: 1.679E-04 | global batch size: 512 | lm loss: 2.180206E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.470 | TFLOPs: 23.52 | +63: iteration 21030/ 73814 | consumed samples: 10767360 | consumed tokens: 22051553280 | elapsed time per iteration (s): 2.46 | learning rate: 1.679E-04 | global batch size: 512 | lm loss: 2.155409E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 207.903 | TFLOPs: 21.40 | +63: iteration 21040/ 73814 | consumed samples: 10772480 | consumed tokens: 22062039040 | elapsed time per iteration (s): 2.24 | learning rate: 1.678E-04 | global batch size: 512 | lm loss: 2.166257E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.256 | TFLOPs: 23.50 | +63: iteration 21050/ 73814 | consumed samples: 10777600 | consumed tokens: 22072524800 | elapsed time per iteration (s): 2.23 | learning rate: 1.678E-04 | global batch size: 512 | lm loss: 2.151794E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.149 | TFLOPs: 23.59 | +63: iteration 21060/ 73814 | consumed samples: 10782720 | consumed tokens: 22083010560 | elapsed time per iteration (s): 2.24 | learning rate: 1.678E-04 | global batch size: 512 | lm loss: 2.173144E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.253 | TFLOPs: 23.50 | +63: iteration 21070/ 73814 | consumed samples: 10787840 | consumed tokens: 22093496320 | elapsed time per iteration (s): 2.22 | learning rate: 1.678E-04 | global batch size: 512 | lm loss: 2.146389E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.148 | TFLOPs: 23.69 | +63: iteration 21080/ 73814 | consumed samples: 10792960 | consumed tokens: 22103982080 | elapsed time per iteration (s): 2.23 | learning rate: 1.677E-04 | global batch size: 512 | lm loss: 2.148304E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.102 | TFLOPs: 23.69 | +63: iteration 21090/ 73814 | consumed samples: 10798080 | consumed tokens: 22114467840 | elapsed time per iteration (s): 2.23 | learning rate: 1.677E-04 | global batch size: 512 | lm loss: 2.146221E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.707 | TFLOPs: 23.65 | +63: iteration 21100/ 73814 | consumed samples: 10803200 | consumed tokens: 22124953600 | elapsed time per iteration (s): 2.22 | learning rate: 1.677E-04 | global batch size: 512 | lm loss: 2.156348E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.235 | TFLOPs: 23.70 | +63: iteration 21110/ 73814 | consumed samples: 10808320 | consumed tokens: 22135439360 | elapsed time per iteration (s): 2.23 | learning rate: 1.676E-04 | global batch size: 512 | lm loss: 2.188187E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.383 | TFLOPs: 23.61 | +63: iteration 21120/ 73814 | consumed samples: 10813440 | consumed tokens: 22145925120 | elapsed time per iteration (s): 2.23 | learning rate: 1.676E-04 | global batch size: 512 | lm loss: 2.155397E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.448 | TFLOPs: 23.62 | +63: iteration 21130/ 73814 | consumed samples: 10818560 | consumed tokens: 22156410880 | elapsed time per iteration (s): 2.24 | learning rate: 1.676E-04 | global batch size: 512 | lm loss: 2.155959E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.321 | TFLOPs: 23.50 | +63: iteration 21140/ 73814 | consumed samples: 10823680 | consumed tokens: 22166896640 | elapsed time per iteration (s): 2.23 | learning rate: 1.675E-04 | global batch size: 512 | lm loss: 2.151132E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.811 | TFLOPs: 23.66 | +63: iteration 21150/ 73814 | consumed samples: 10828800 | consumed tokens: 22177382400 | elapsed time per iteration (s): 2.25 | learning rate: 1.675E-04 | global batch size: 512 | lm loss: 2.120502E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.068 | TFLOPs: 23.38 | +63: iteration 21160/ 73814 | consumed samples: 10833920 | consumed tokens: 22187868160 | elapsed time per iteration (s): 2.23 | learning rate: 1.675E-04 | global batch size: 512 | lm loss: 2.150968E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.272 | TFLOPs: 23.60 | +63: iteration 21170/ 73814 | consumed samples: 10839040 | consumed tokens: 22198353920 | elapsed time per iteration (s): 2.45 | learning rate: 1.675E-04 | global batch size: 512 | lm loss: 2.157939E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.793 | TFLOPs: 21.49 | +63: iteration 21180/ 73814 | consumed samples: 10844160 | consumed tokens: 22208839680 | elapsed time per iteration (s): 2.26 | learning rate: 1.674E-04 | global batch size: 512 | lm loss: 2.161529E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.978 | TFLOPs: 23.37 | +63: iteration 21190/ 73814 | consumed samples: 10849280 | consumed tokens: 22219325440 | elapsed time per iteration (s): 2.24 | learning rate: 1.674E-04 | global batch size: 512 | lm loss: 2.164813E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.160 | TFLOPs: 23.49 | +63: iteration 21200/ 73814 | consumed samples: 10854400 | consumed tokens: 22229811200 | elapsed time per iteration (s): 2.24 | learning rate: 1.674E-04 | global batch size: 512 | lm loss: 2.154648E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.891 | TFLOPs: 23.56 | +63: iteration 21210/ 73814 | consumed samples: 10859520 | consumed tokens: 22240296960 | elapsed time per iteration (s): 2.28 | learning rate: 1.673E-04 | global batch size: 512 | lm loss: 2.143959E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.891 | TFLOPs: 23.15 | +63: iteration 21220/ 73814 | consumed samples: 10864640 | consumed tokens: 22250782720 | elapsed time per iteration (s): 2.27 | learning rate: 1.673E-04 | global batch size: 512 | lm loss: 2.171040E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.956 | TFLOPs: 23.26 | +63: iteration 21230/ 73814 | consumed samples: 10869760 | consumed tokens: 22261268480 | elapsed time per iteration (s): 2.22 | learning rate: 1.673E-04 | global batch size: 512 | lm loss: 2.166379E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.118 | TFLOPs: 23.69 | +63: iteration 21240/ 73814 | consumed samples: 10874880 | consumed tokens: 22271754240 | elapsed time per iteration (s): 2.23 | learning rate: 1.672E-04 | global batch size: 512 | lm loss: 2.164828E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.351 | TFLOPs: 23.61 | +63: iteration 21250/ 73814 | consumed samples: 10880000 | consumed tokens: 22282240000 | elapsed time per iteration (s): 2.24 | learning rate: 1.672E-04 | global batch size: 512 | lm loss: 2.154095E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.117 | TFLOPs: 23.48 | +63: iteration 21260/ 73814 | consumed samples: 10885120 | consumed tokens: 22292725760 | elapsed time per iteration (s): 2.25 | learning rate: 1.672E-04 | global batch size: 512 | lm loss: 2.160655E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.696 | TFLOPs: 23.44 | +63: iteration 21270/ 73814 | consumed samples: 10890240 | consumed tokens: 22303211520 | elapsed time per iteration (s): 2.24 | learning rate: 1.672E-04 | global batch size: 512 | lm loss: 2.166379E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.238 | TFLOPs: 23.50 | +63: iteration 21280/ 73814 | consumed samples: 10895360 | consumed tokens: 22313697280 | elapsed time per iteration (s): 2.24 | learning rate: 1.671E-04 | global batch size: 512 | lm loss: 2.164168E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.628 | TFLOPs: 23.54 | +63: iteration 21290/ 73814 | consumed samples: 10900480 | consumed tokens: 22324183040 | elapsed time per iteration (s): 2.23 | learning rate: 1.671E-04 | global batch size: 512 | lm loss: 2.156946E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.570 | TFLOPs: 23.63 | +63: iteration 21300/ 73814 | consumed samples: 10905600 | consumed tokens: 22334668800 | elapsed time per iteration (s): 2.23 | learning rate: 1.671E-04 | global batch size: 512 | lm loss: 2.172247E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.485 | TFLOPs: 23.62 | +63: iteration 21310/ 73814 | consumed samples: 10910720 | consumed tokens: 22345154560 | elapsed time per iteration (s): 2.23 | learning rate: 1.670E-04 | global batch size: 512 | lm loss: 2.175367E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.850 | TFLOPs: 23.66 | +63: iteration 21320/ 73814 | consumed samples: 10915840 | consumed tokens: 22355640320 | elapsed time per iteration (s): 2.23 | learning rate: 1.670E-04 | global batch size: 512 | lm loss: 2.141307E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.936 | TFLOPs: 23.67 | +63: iteration 21330/ 73814 | consumed samples: 10920960 | consumed tokens: 22366126080 | elapsed time per iteration (s): 2.24 | learning rate: 1.670E-04 | global batch size: 512 | lm loss: 2.142910E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.310 | TFLOPs: 23.50 | +63: iteration 21340/ 73814 | consumed samples: 10926080 | consumed tokens: 22376611840 | elapsed time per iteration (s): 2.23 | learning rate: 1.669E-04 | global batch size: 512 | lm loss: 2.143781E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.706 | TFLOPs: 23.65 | +63: iteration 21350/ 73814 | consumed samples: 10931200 | consumed tokens: 22387097600 | elapsed time per iteration (s): 2.24 | learning rate: 1.669E-04 | global batch size: 512 | lm loss: 2.154073E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.229 | TFLOPs: 23.50 | +63: iteration 21360/ 73814 | consumed samples: 10936320 | consumed tokens: 22397583360 | elapsed time per iteration (s): 2.23 | learning rate: 1.669E-04 | global batch size: 512 | lm loss: 2.142933E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.811 | TFLOPs: 23.66 | +63: iteration 21370/ 73814 | consumed samples: 10941440 | consumed tokens: 22408069120 | elapsed time per iteration (s): 2.24 | learning rate: 1.669E-04 | global batch size: 512 | lm loss: 2.170040E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.202 | TFLOPs: 23.49 | +63: iteration 21380/ 73814 | consumed samples: 10946560 | consumed tokens: 22418554880 | elapsed time per iteration (s): 2.23 | learning rate: 1.668E-04 | global batch size: 512 | lm loss: 2.161022E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.580 | TFLOPs: 23.63 | +63: iteration 21390/ 73814 | consumed samples: 10951680 | consumed tokens: 22429040640 | elapsed time per iteration (s): 2.23 | learning rate: 1.668E-04 | global batch size: 512 | lm loss: 2.143394E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.949 | TFLOPs: 23.67 | +63: iteration 21400/ 73814 | consumed samples: 10956800 | consumed tokens: 22439526400 | elapsed time per iteration (s): 2.24 | learning rate: 1.668E-04 | global batch size: 512 | lm loss: 2.145992E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.474 | TFLOPs: 23.52 | +63: iteration 21410/ 73814 | consumed samples: 10961920 | consumed tokens: 22450012160 | elapsed time per iteration (s): 2.23 | learning rate: 1.667E-04 | global batch size: 512 | lm loss: 2.148467E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.652 | TFLOPs: 23.64 | +63: iteration 21420/ 73814 | consumed samples: 10967040 | consumed tokens: 22460497920 | elapsed time per iteration (s): 2.23 | learning rate: 1.667E-04 | global batch size: 512 | lm loss: 2.183349E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.140 | TFLOPs: 23.59 | +63: iteration 21430/ 73814 | consumed samples: 10972160 | consumed tokens: 22470983680 | elapsed time per iteration (s): 2.23 | learning rate: 1.667E-04 | global batch size: 512 | lm loss: 2.156053E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.131 | TFLOPs: 23.59 | +63: iteration 21440/ 73814 | consumed samples: 10977280 | consumed tokens: 22481469440 | elapsed time per iteration (s): 2.25 | learning rate: 1.666E-04 | global batch size: 512 | lm loss: 2.169710E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.657 | TFLOPs: 23.44 | +63: iteration 21450/ 73814 | consumed samples: 10982400 | consumed tokens: 22491955200 | elapsed time per iteration (s): 2.28 | learning rate: 1.666E-04 | global batch size: 512 | lm loss: 2.163560E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.858 | TFLOPs: 23.15 | +63: iteration 21460/ 73814 | consumed samples: 10987520 | consumed tokens: 22502440960 | elapsed time per iteration (s): 2.23 | learning rate: 1.666E-04 | global batch size: 512 | lm loss: 2.164210E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.887 | TFLOPs: 23.67 | +63: iteration 21470/ 73814 | consumed samples: 10992640 | consumed tokens: 22512926720 | elapsed time per iteration (s): 2.23 | learning rate: 1.666E-04 | global batch size: 512 | lm loss: 2.151131E+00 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.836 | TFLOPs: 23.66 | +63: iteration 21480/ 73814 | consumed samples: 10997760 | consumed tokens: 22523412480 | elapsed time per iteration (s): 2.23 | learning rate: 1.665E-04 | global batch size: 512 | lm loss: 2.158797E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.005 | TFLOPs: 23.68 | +63: iteration 21490/ 73814 | consumed samples: 11002880 | consumed tokens: 22533898240 | elapsed time per iteration (s): 2.24 | learning rate: 1.665E-04 | global batch size: 512 | lm loss: 2.139681E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.264 | TFLOPs: 23.50 | +63: iteration 21500/ 73814 | consumed samples: 11008000 | consumed tokens: 22544384000 | elapsed time per iteration (s): 2.24 | learning rate: 1.665E-04 | global batch size: 512 | lm loss: 2.131361E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.748 | TFLOPs: 23.55 | +63: iteration 21510/ 73814 | consumed samples: 11013120 | consumed tokens: 22554869760 | elapsed time per iteration (s): 2.39 | learning rate: 1.664E-04 | global batch size: 512 | lm loss: 2.162085E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.559 | TFLOPs: 22.09 | +63: iteration 21520/ 73814 | consumed samples: 11018240 | consumed tokens: 22565355520 | elapsed time per iteration (s): 2.23 | learning rate: 1.664E-04 | global batch size: 512 | lm loss: 2.146582E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.680 | TFLOPs: 23.64 | +63: iteration 21530/ 73814 | consumed samples: 11023360 | consumed tokens: 22575841280 | elapsed time per iteration (s): 2.24 | learning rate: 1.664E-04 | global batch size: 512 | lm loss: 2.166101E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.325 | TFLOPs: 23.50 | +63: iteration 21540/ 73814 | consumed samples: 11028480 | consumed tokens: 22586327040 | elapsed time per iteration (s): 2.25 | learning rate: 1.663E-04 | global batch size: 512 | lm loss: 2.148501E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.057 | TFLOPs: 23.48 | +63: iteration 21550/ 73814 | consumed samples: 11033600 | consumed tokens: 22596812800 | elapsed time per iteration (s): 2.23 | learning rate: 1.663E-04 | global batch size: 512 | lm loss: 2.141586E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.183 | TFLOPs: 23.59 | +63: iteration 21560/ 73814 | consumed samples: 11038720 | consumed tokens: 22607298560 | elapsed time per iteration (s): 2.23 | learning rate: 1.663E-04 | global batch size: 512 | lm loss: 2.167625E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.976 | TFLOPs: 23.67 | +63: iteration 21570/ 73814 | consumed samples: 11043840 | consumed tokens: 22617784320 | elapsed time per iteration (s): 2.23 | learning rate: 1.663E-04 | global batch size: 512 | lm loss: 2.153738E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.878 | TFLOPs: 23.66 | +63: iteration 21580/ 73814 | consumed samples: 11048960 | consumed tokens: 22628270080 | elapsed time per iteration (s): 2.23 | learning rate: 1.662E-04 | global batch size: 512 | lm loss: 2.147982E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.949 | TFLOPs: 23.67 | +63: iteration 21590/ 73814 | consumed samples: 11054080 | consumed tokens: 22638755840 | elapsed time per iteration (s): 2.23 | learning rate: 1.662E-04 | global batch size: 512 | lm loss: 2.155216E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.104 | TFLOPs: 23.69 | +63: iteration 21600/ 73814 | consumed samples: 11059200 | consumed tokens: 22649241600 | elapsed time per iteration (s): 2.25 | learning rate: 1.662E-04 | global batch size: 512 | lm loss: 2.157235E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.945 | TFLOPs: 23.47 | +63: iteration 21610/ 73814 | consumed samples: 11064320 | consumed tokens: 22659727360 | elapsed time per iteration (s): 2.24 | learning rate: 1.661E-04 | global batch size: 512 | lm loss: 2.144298E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.380 | TFLOPs: 23.51 | +63: iteration 21620/ 73814 | consumed samples: 11069440 | consumed tokens: 22670213120 | elapsed time per iteration (s): 2.32 | learning rate: 1.661E-04 | global batch size: 512 | lm loss: 2.161790E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.913 | TFLOPs: 22.74 | +63: iteration 21630/ 73814 | consumed samples: 11074560 | consumed tokens: 22680698880 | elapsed time per iteration (s): 2.23 | learning rate: 1.661E-04 | global batch size: 512 | lm loss: 2.144303E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.817 | TFLOPs: 23.66 | +63: iteration 21640/ 73814 | consumed samples: 11079680 | consumed tokens: 22691184640 | elapsed time per iteration (s): 2.24 | learning rate: 1.660E-04 | global batch size: 512 | lm loss: 2.175185E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.591 | TFLOPs: 23.53 | +63: iteration 21650/ 73814 | consumed samples: 11084800 | consumed tokens: 22701670400 | elapsed time per iteration (s): 2.37 | learning rate: 1.660E-04 | global batch size: 512 | lm loss: 2.144813E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.305 | TFLOPs: 22.27 | +63: iteration 21660/ 73814 | consumed samples: 11089920 | consumed tokens: 22712156160 | elapsed time per iteration (s): 2.24 | learning rate: 1.660E-04 | global batch size: 512 | lm loss: 2.140215E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.426 | TFLOPs: 23.52 | +63: iteration 21670/ 73814 | consumed samples: 11095040 | consumed tokens: 22722641920 | elapsed time per iteration (s): 2.23 | learning rate: 1.660E-04 | global batch size: 512 | lm loss: 2.161675E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.825 | TFLOPs: 23.66 | +63: iteration 21680/ 73814 | consumed samples: 11100160 | consumed tokens: 22733127680 | elapsed time per iteration (s): 2.23 | learning rate: 1.659E-04 | global batch size: 512 | lm loss: 2.138337E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.419 | TFLOPs: 23.62 | +63: iteration 21690/ 73814 | consumed samples: 11105280 | consumed tokens: 22743613440 | elapsed time per iteration (s): 2.30 | learning rate: 1.659E-04 | global batch size: 512 | lm loss: 2.180380E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.725 | TFLOPs: 22.93 | +63: iteration 21700/ 73814 | consumed samples: 11110400 | consumed tokens: 22754099200 | elapsed time per iteration (s): 2.23 | learning rate: 1.659E-04 | global batch size: 512 | lm loss: 2.154499E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.688 | TFLOPs: 23.65 | +63: iteration 21710/ 73814 | consumed samples: 11115520 | consumed tokens: 22764584960 | elapsed time per iteration (s): 2.23 | learning rate: 1.658E-04 | global batch size: 512 | lm loss: 2.156574E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.267 | TFLOPs: 23.60 | +63: iteration 21720/ 73814 | consumed samples: 11120640 | consumed tokens: 22775070720 | elapsed time per iteration (s): 2.22 | learning rate: 1.658E-04 | global batch size: 512 | lm loss: 2.158263E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.133 | TFLOPs: 23.69 | +63: iteration 21730/ 73814 | consumed samples: 11125760 | consumed tokens: 22785556480 | elapsed time per iteration (s): 2.35 | learning rate: 1.658E-04 | global batch size: 512 | lm loss: 2.138477E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.150 | TFLOPs: 22.46 | +63: iteration 21740/ 73814 | consumed samples: 11130880 | consumed tokens: 22796042240 | elapsed time per iteration (s): 2.23 | learning rate: 1.657E-04 | global batch size: 512 | lm loss: 2.143848E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.028 | TFLOPs: 23.68 | +63: iteration 21750/ 73814 | consumed samples: 11136000 | consumed tokens: 22806528000 | elapsed time per iteration (s): 2.29 | learning rate: 1.657E-04 | global batch size: 512 | lm loss: 2.161815E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.200 | TFLOPs: 22.98 | +63: iteration 21760/ 73814 | consumed samples: 11141120 | consumed tokens: 22817013760 | elapsed time per iteration (s): 2.23 | learning rate: 1.657E-04 | global batch size: 512 | lm loss: 2.163134E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.612 | TFLOPs: 23.64 | +63: iteration 21770/ 73814 | consumed samples: 11146240 | consumed tokens: 22827499520 | elapsed time per iteration (s): 2.24 | learning rate: 1.657E-04 | global batch size: 512 | lm loss: 2.139875E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.137 | TFLOPs: 23.49 | +63: iteration 21780/ 73814 | consumed samples: 11151360 | consumed tokens: 22837985280 | elapsed time per iteration (s): 2.30 | learning rate: 1.656E-04 | global batch size: 512 | lm loss: 2.139294E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.959 | TFLOPs: 22.95 | +63: iteration 21790/ 73814 | consumed samples: 11156480 | consumed tokens: 22848471040 | elapsed time per iteration (s): 2.23 | learning rate: 1.656E-04 | global batch size: 512 | lm loss: 2.122279E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.099 | TFLOPs: 23.69 | +63: iteration 21800/ 73814 | consumed samples: 11161600 | consumed tokens: 22858956800 | elapsed time per iteration (s): 2.23 | learning rate: 1.656E-04 | global batch size: 512 | lm loss: 2.161804E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.430 | TFLOPs: 23.62 | +63: iteration 21810/ 73814 | consumed samples: 11166720 | consumed tokens: 22869442560 | elapsed time per iteration (s): 2.35 | learning rate: 1.655E-04 | global batch size: 512 | lm loss: 2.149942E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.747 | TFLOPs: 22.42 | +63: iteration 21820/ 73814 | consumed samples: 11171840 | consumed tokens: 22879928320 | elapsed time per iteration (s): 2.24 | learning rate: 1.655E-04 | global batch size: 512 | lm loss: 2.155093E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.072 | TFLOPs: 23.58 | +63: iteration 21830/ 73814 | consumed samples: 11176960 | consumed tokens: 22890414080 | elapsed time per iteration (s): 2.25 | learning rate: 1.655E-04 | global batch size: 512 | lm loss: 2.146341E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.004 | TFLOPs: 23.47 | +63: iteration 21840/ 73814 | consumed samples: 11182080 | consumed tokens: 22900899840 | elapsed time per iteration (s): 2.34 | learning rate: 1.654E-04 | global batch size: 512 | lm loss: 2.139636E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.672 | TFLOPs: 22.51 | +63: iteration 21850/ 73814 | consumed samples: 11187200 | consumed tokens: 22911385600 | elapsed time per iteration (s): 2.23 | learning rate: 1.654E-04 | global batch size: 512 | lm loss: 2.153938E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.706 | TFLOPs: 23.65 | +63: iteration 21860/ 73814 | consumed samples: 11192320 | consumed tokens: 22921871360 | elapsed time per iteration (s): 2.28 | learning rate: 1.654E-04 | global batch size: 512 | lm loss: 2.169544E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.472 | TFLOPs: 23.11 | +63: iteration 21870/ 73814 | consumed samples: 11197440 | consumed tokens: 22932357120 | elapsed time per iteration (s): 2.27 | learning rate: 1.653E-04 | global batch size: 512 | lm loss: 2.142989E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.306 | TFLOPs: 23.19 | +63: iteration 21880/ 73814 | consumed samples: 11202560 | consumed tokens: 22942842880 | elapsed time per iteration (s): 2.23 | learning rate: 1.653E-04 | global batch size: 512 | lm loss: 2.131114E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.533 | TFLOPs: 23.63 | +63: iteration 21890/ 73814 | consumed samples: 11207680 | consumed tokens: 22953328640 | elapsed time per iteration (s): 2.29 | learning rate: 1.653E-04 | global batch size: 512 | lm loss: 2.153532E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.213 | TFLOPs: 22.98 | +63: iteration 21900/ 73814 | consumed samples: 11212800 | consumed tokens: 22963814400 | elapsed time per iteration (s): 2.23 | learning rate: 1.653E-04 | global batch size: 512 | lm loss: 2.154857E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.126 | TFLOPs: 23.59 | +63: iteration 21910/ 73814 | consumed samples: 11217920 | consumed tokens: 22974300160 | elapsed time per iteration (s): 2.23 | learning rate: 1.652E-04 | global batch size: 512 | lm loss: 2.167710E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.653 | TFLOPs: 23.64 | +63: iteration 21920/ 73814 | consumed samples: 11223040 | consumed tokens: 22984785920 | elapsed time per iteration (s): 2.23 | learning rate: 1.652E-04 | global batch size: 512 | lm loss: 2.163604E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.809 | TFLOPs: 23.66 | +63: iteration 21930/ 73814 | consumed samples: 11228160 | consumed tokens: 22995271680 | elapsed time per iteration (s): 2.24 | learning rate: 1.652E-04 | global batch size: 512 | lm loss: 2.125140E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.447 | TFLOPs: 23.52 | +63: iteration 21940/ 73814 | consumed samples: 11233280 | consumed tokens: 23005757440 | elapsed time per iteration (s): 2.23 | learning rate: 1.651E-04 | global batch size: 512 | lm loss: 2.148516E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.814 | TFLOPs: 23.66 | +63: iteration 21950/ 73814 | consumed samples: 11238400 | consumed tokens: 23016243200 | elapsed time per iteration (s): 2.24 | learning rate: 1.651E-04 | global batch size: 512 | lm loss: 2.125679E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.808 | TFLOPs: 23.55 | +63: iteration 21960/ 73814 | consumed samples: 11243520 | consumed tokens: 23026728960 | elapsed time per iteration (s): 2.44 | learning rate: 1.651E-04 | global batch size: 512 | lm loss: 2.152927E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.143 | TFLOPs: 21.63 | +63: iteration 21970/ 73814 | consumed samples: 11248640 | consumed tokens: 23037214720 | elapsed time per iteration (s): 2.29 | learning rate: 1.650E-04 | global batch size: 512 | lm loss: 2.152779E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.978 | TFLOPs: 23.06 | +63: iteration 21980/ 73814 | consumed samples: 11253760 | consumed tokens: 23047700480 | elapsed time per iteration (s): 2.26 | learning rate: 1.650E-04 | global batch size: 512 | lm loss: 2.155037E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.763 | TFLOPs: 23.34 | +63: iteration 21990/ 73814 | consumed samples: 11258880 | consumed tokens: 23058186240 | elapsed time per iteration (s): 2.41 | learning rate: 1.650E-04 | global batch size: 512 | lm loss: 2.167919E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.139 | TFLOPs: 21.84 | + 0: [2022-12-02 01:44:03,584] [INFO] [logging.py:68:log_dist] [Rank 0] step=22000, skipped=0, lr=[0.00016494816501058866, 0.00016494816501058866, 0.00016494816501058866], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 22000/ 73814 | consumed samples: 11264000 | consumed tokens: 23068672000 | elapsed time per iteration (s): 2.39 | learning rate: 1.649E-04 | global batch size: 512 | lm loss: 2.172891E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.492 | TFLOPs: 22.08 | + 0: steps: 22000 loss: 2.1573 iter time (s): 2.261 samples/sec: 226.496 +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 22000 | lm loss value: 2.131447E+00 | lm loss PPL: 8.427055E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 22010/ 73814 | consumed samples: 11269120 | consumed tokens: 23079157760 | elapsed time per iteration (s): 2.31 | learning rate: 1.649E-04 | global batch size: 512 | lm loss: 2.145470E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.943 | TFLOPs: 22.85 | +63: iteration 22020/ 73814 | consumed samples: 11274240 | consumed tokens: 23089643520 | elapsed time per iteration (s): 2.34 | learning rate: 1.649E-04 | global batch size: 512 | lm loss: 2.146897E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.459 | TFLOPs: 22.49 | +63: iteration 22030/ 73814 | consumed samples: 11279360 | consumed tokens: 23100129280 | elapsed time per iteration (s): 2.38 | learning rate: 1.649E-04 | global batch size: 512 | lm loss: 2.156330E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.976 | TFLOPs: 22.13 | +63: iteration 22040/ 73814 | consumed samples: 11284480 | consumed tokens: 23110615040 | elapsed time per iteration (s): 2.75 | learning rate: 1.648E-04 | global batch size: 512 | lm loss: 2.124398E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 185.930 | TFLOPs: 19.14 | +63: iteration 22050/ 73814 | consumed samples: 11289600 | consumed tokens: 23121100800 | elapsed time per iteration (s): 2.44 | learning rate: 1.648E-04 | global batch size: 512 | lm loss: 2.146826E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.536 | TFLOPs: 21.57 | +63: iteration 22060/ 73814 | consumed samples: 11294720 | consumed tokens: 23131586560 | elapsed time per iteration (s): 2.29 | learning rate: 1.648E-04 | global batch size: 512 | lm loss: 2.123958E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.578 | TFLOPs: 23.02 | +63: iteration 22070/ 73814 | consumed samples: 11299840 | consumed tokens: 23142072320 | elapsed time per iteration (s): 2.30 | learning rate: 1.647E-04 | global batch size: 512 | lm loss: 2.143052E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.088 | TFLOPs: 22.97 | +63: iteration 22080/ 73814 | consumed samples: 11304960 | consumed tokens: 23152558080 | elapsed time per iteration (s): 2.35 | learning rate: 1.647E-04 | global batch size: 512 | lm loss: 2.158017E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.606 | TFLOPs: 22.40 | +63: iteration 22090/ 73814 | consumed samples: 11310080 | consumed tokens: 23163043840 | elapsed time per iteration (s): 2.26 | learning rate: 1.647E-04 | global batch size: 512 | lm loss: 2.158058E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.145 | TFLOPs: 23.28 | +63: iteration 22100/ 73814 | consumed samples: 11315200 | consumed tokens: 23173529600 | elapsed time per iteration (s): 2.29 | learning rate: 1.646E-04 | global batch size: 512 | lm loss: 2.155559E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.962 | TFLOPs: 23.06 | +63: iteration 22110/ 73814 | consumed samples: 11320320 | consumed tokens: 23184015360 | elapsed time per iteration (s): 2.24 | learning rate: 1.646E-04 | global batch size: 512 | lm loss: 2.136158E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.766 | TFLOPs: 23.55 | +63: iteration 22120/ 73814 | consumed samples: 11325440 | consumed tokens: 23194501120 | elapsed time per iteration (s): 2.24 | learning rate: 1.646E-04 | global batch size: 512 | lm loss: 2.164499E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.956 | TFLOPs: 23.57 | +63: iteration 22130/ 73814 | consumed samples: 11330560 | consumed tokens: 23204986880 | elapsed time per iteration (s): 2.25 | learning rate: 1.645E-04 | global batch size: 512 | lm loss: 2.155261E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.853 | TFLOPs: 23.46 | +63: iteration 22140/ 73814 | consumed samples: 11335680 | consumed tokens: 23215472640 | elapsed time per iteration (s): 2.25 | learning rate: 1.645E-04 | global batch size: 512 | lm loss: 2.123468E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.589 | TFLOPs: 23.43 | +63: iteration 22150/ 73814 | consumed samples: 11340800 | consumed tokens: 23225958400 | elapsed time per iteration (s): 2.24 | learning rate: 1.645E-04 | global batch size: 512 | lm loss: 2.125693E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.447 | TFLOPs: 23.52 | +63: iteration 22160/ 73814 | consumed samples: 11345920 | consumed tokens: 23236444160 | elapsed time per iteration (s): 2.29 | learning rate: 1.645E-04 | global batch size: 512 | lm loss: 2.159585E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.481 | TFLOPs: 23.01 | +63: iteration 22170/ 73814 | consumed samples: 11351040 | consumed tokens: 23246929920 | elapsed time per iteration (s): 2.28 | learning rate: 1.644E-04 | global batch size: 512 | lm loss: 2.140281E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.673 | TFLOPs: 23.13 | +63: iteration 22180/ 73814 | consumed samples: 11356160 | consumed tokens: 23257415680 | elapsed time per iteration (s): 2.23 | learning rate: 1.644E-04 | global batch size: 512 | lm loss: 2.145556E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.700 | TFLOPs: 23.65 | +63: iteration 22190/ 73814 | consumed samples: 11361280 | consumed tokens: 23267901440 | elapsed time per iteration (s): 2.22 | learning rate: 1.644E-04 | global batch size: 512 | lm loss: 2.172328E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.336 | TFLOPs: 23.71 | +63: iteration 22200/ 73814 | consumed samples: 11366400 | consumed tokens: 23278387200 | elapsed time per iteration (s): 2.23 | learning rate: 1.643E-04 | global batch size: 512 | lm loss: 2.137753E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.341 | TFLOPs: 23.61 | +63: iteration 22210/ 73814 | consumed samples: 11371520 | consumed tokens: 23288872960 | elapsed time per iteration (s): 2.24 | learning rate: 1.643E-04 | global batch size: 512 | lm loss: 2.144498E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.815 | TFLOPs: 23.56 | +63: iteration 22220/ 73814 | consumed samples: 11376640 | consumed tokens: 23299358720 | elapsed time per iteration (s): 2.25 | learning rate: 1.643E-04 | global batch size: 512 | lm loss: 2.157416E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.657 | TFLOPs: 23.44 | +63: iteration 22230/ 73814 | consumed samples: 11381760 | consumed tokens: 23309844480 | elapsed time per iteration (s): 2.23 | learning rate: 1.642E-04 | global batch size: 512 | lm loss: 2.142372E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.668 | TFLOPs: 23.64 | +63: iteration 22240/ 73814 | consumed samples: 11386880 | consumed tokens: 23320330240 | elapsed time per iteration (s): 2.24 | learning rate: 1.642E-04 | global batch size: 512 | lm loss: 2.130952E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.120 | TFLOPs: 23.48 | +63: iteration 22250/ 73814 | consumed samples: 11392000 | consumed tokens: 23330816000 | elapsed time per iteration (s): 2.23 | learning rate: 1.642E-04 | global batch size: 512 | lm loss: 2.138088E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.878 | TFLOPs: 23.66 | +63: iteration 22260/ 73814 | consumed samples: 11397120 | consumed tokens: 23341301760 | elapsed time per iteration (s): 2.24 | learning rate: 1.641E-04 | global batch size: 512 | lm loss: 2.162767E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.674 | TFLOPs: 23.54 | +63: iteration 22270/ 73814 | consumed samples: 11402240 | consumed tokens: 23351787520 | elapsed time per iteration (s): 2.25 | learning rate: 1.641E-04 | global batch size: 512 | lm loss: 2.143850E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.837 | TFLOPs: 23.45 | +63: iteration 22280/ 73814 | consumed samples: 11407360 | consumed tokens: 23362273280 | elapsed time per iteration (s): 2.23 | learning rate: 1.641E-04 | global batch size: 512 | lm loss: 2.134552E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.104 | TFLOPs: 23.69 | +63: iteration 22290/ 73814 | consumed samples: 11412480 | consumed tokens: 23372759040 | elapsed time per iteration (s): 2.23 | learning rate: 1.641E-04 | global batch size: 512 | lm loss: 2.158908E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.477 | TFLOPs: 23.62 | +63: iteration 22300/ 73814 | consumed samples: 11417600 | consumed tokens: 23383244800 | elapsed time per iteration (s): 2.24 | learning rate: 1.640E-04 | global batch size: 512 | lm loss: 2.146452E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.799 | TFLOPs: 23.55 | +63: iteration 22310/ 73814 | consumed samples: 11422720 | consumed tokens: 23393730560 | elapsed time per iteration (s): 2.29 | learning rate: 1.640E-04 | global batch size: 512 | lm loss: 2.142508E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.105 | TFLOPs: 22.97 | +63: iteration 22320/ 73814 | consumed samples: 11427840 | consumed tokens: 23404216320 | elapsed time per iteration (s): 2.25 | learning rate: 1.640E-04 | global batch size: 512 | lm loss: 2.148767E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.695 | TFLOPs: 23.44 | +63: iteration 22330/ 73814 | consumed samples: 11432960 | consumed tokens: 23414702080 | elapsed time per iteration (s): 2.24 | learning rate: 1.639E-04 | global batch size: 512 | lm loss: 2.144498E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.633 | TFLOPs: 23.54 | +63: iteration 22340/ 73814 | consumed samples: 11438080 | consumed tokens: 23425187840 | elapsed time per iteration (s): 2.24 | learning rate: 1.639E-04 | global batch size: 512 | lm loss: 2.157267E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.113 | TFLOPs: 23.48 | +63: iteration 22350/ 73814 | consumed samples: 11443200 | consumed tokens: 23435673600 | elapsed time per iteration (s): 2.49 | learning rate: 1.639E-04 | global batch size: 512 | lm loss: 2.142623E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.763 | TFLOPs: 21.18 | +63: iteration 22360/ 73814 | consumed samples: 11448320 | consumed tokens: 23446159360 | elapsed time per iteration (s): 2.28 | learning rate: 1.638E-04 | global batch size: 512 | lm loss: 2.138889E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.796 | TFLOPs: 23.14 | +63: iteration 22370/ 73814 | consumed samples: 11453440 | consumed tokens: 23456645120 | elapsed time per iteration (s): 2.25 | learning rate: 1.638E-04 | global batch size: 512 | lm loss: 2.147893E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.203 | TFLOPs: 23.39 | +63: iteration 22380/ 73814 | consumed samples: 11458560 | consumed tokens: 23467130880 | elapsed time per iteration (s): 2.23 | learning rate: 1.638E-04 | global batch size: 512 | lm loss: 2.137595E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.077 | TFLOPs: 23.69 | +63: iteration 22390/ 73814 | consumed samples: 11463680 | consumed tokens: 23477616640 | elapsed time per iteration (s): 2.28 | learning rate: 1.637E-04 | global batch size: 512 | lm loss: 2.148190E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.514 | TFLOPs: 23.11 | +63: iteration 22400/ 73814 | consumed samples: 11468800 | consumed tokens: 23488102400 | elapsed time per iteration (s): 2.23 | learning rate: 1.637E-04 | global batch size: 512 | lm loss: 2.155440E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.812 | TFLOPs: 23.66 | +63: iteration 22410/ 73814 | consumed samples: 11473920 | consumed tokens: 23498588160 | elapsed time per iteration (s): 2.24 | learning rate: 1.637E-04 | global batch size: 512 | lm loss: 2.146629E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.613 | TFLOPs: 23.53 | +63: iteration 22420/ 73814 | consumed samples: 11479040 | consumed tokens: 23509073920 | elapsed time per iteration (s): 2.24 | learning rate: 1.637E-04 | global batch size: 512 | lm loss: 2.139570E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.717 | TFLOPs: 23.55 | +63: iteration 22430/ 73814 | consumed samples: 11484160 | consumed tokens: 23519559680 | elapsed time per iteration (s): 2.25 | learning rate: 1.636E-04 | global batch size: 512 | lm loss: 2.123856E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.219 | TFLOPs: 23.39 | +63: iteration 22440/ 73814 | consumed samples: 11489280 | consumed tokens: 23530045440 | elapsed time per iteration (s): 2.23 | learning rate: 1.636E-04 | global batch size: 512 | lm loss: 2.115441E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.163 | TFLOPs: 23.59 | +63: iteration 22450/ 73814 | consumed samples: 11494400 | consumed tokens: 23540531200 | elapsed time per iteration (s): 2.23 | learning rate: 1.636E-04 | global batch size: 512 | lm loss: 2.144420E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.841 | TFLOPs: 23.66 | +63: iteration 22460/ 73814 | consumed samples: 11499520 | consumed tokens: 23551016960 | elapsed time per iteration (s): 2.23 | learning rate: 1.635E-04 | global batch size: 512 | lm loss: 2.115646E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.367 | TFLOPs: 23.61 | +63: iteration 22470/ 73814 | consumed samples: 11504640 | consumed tokens: 23561502720 | elapsed time per iteration (s): 2.34 | learning rate: 1.635E-04 | global batch size: 512 | lm loss: 2.138815E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.861 | TFLOPs: 22.53 | +63: iteration 22480/ 73814 | consumed samples: 11509760 | consumed tokens: 23571988480 | elapsed time per iteration (s): 2.23 | learning rate: 1.635E-04 | global batch size: 512 | lm loss: 2.163507E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.487 | TFLOPs: 23.62 | +63: iteration 22490/ 73814 | consumed samples: 11514880 | consumed tokens: 23582474240 | elapsed time per iteration (s): 2.23 | learning rate: 1.634E-04 | global batch size: 512 | lm loss: 2.124843E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.730 | TFLOPs: 23.65 | +63: iteration 22500/ 73814 | consumed samples: 11520000 | consumed tokens: 23592960000 | elapsed time per iteration (s): 2.25 | learning rate: 1.634E-04 | global batch size: 512 | lm loss: 2.140863E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.016 | TFLOPs: 23.47 | +63: iteration 22510/ 73814 | consumed samples: 11525120 | consumed tokens: 23603445760 | elapsed time per iteration (s): 2.23 | learning rate: 1.634E-04 | global batch size: 512 | lm loss: 2.127270E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.570 | TFLOPs: 23.63 | +63: iteration 22520/ 73814 | consumed samples: 11530240 | consumed tokens: 23613931520 | elapsed time per iteration (s): 2.24 | learning rate: 1.633E-04 | global batch size: 512 | lm loss: 2.150200E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.157 | TFLOPs: 23.49 | +63: iteration 22530/ 73814 | consumed samples: 11535360 | consumed tokens: 23624417280 | elapsed time per iteration (s): 2.23 | learning rate: 1.633E-04 | global batch size: 512 | lm loss: 2.127592E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.546 | TFLOPs: 23.63 | +63: iteration 22540/ 73814 | consumed samples: 11540480 | consumed tokens: 23634903040 | elapsed time per iteration (s): 2.24 | learning rate: 1.633E-04 | global batch size: 512 | lm loss: 2.153169E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.925 | TFLOPs: 23.57 | +63: iteration 22550/ 73814 | consumed samples: 11545600 | consumed tokens: 23645388800 | elapsed time per iteration (s): 2.23 | learning rate: 1.632E-04 | global batch size: 512 | lm loss: 2.144619E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.454 | TFLOPs: 23.62 | +63: iteration 22560/ 73814 | consumed samples: 11550720 | consumed tokens: 23655874560 | elapsed time per iteration (s): 2.23 | learning rate: 1.632E-04 | global batch size: 512 | lm loss: 2.150496E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.794 | TFLOPs: 23.66 | +63: iteration 22570/ 73814 | consumed samples: 11555840 | consumed tokens: 23666360320 | elapsed time per iteration (s): 2.24 | learning rate: 1.632E-04 | global batch size: 512 | lm loss: 2.146788E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.218 | TFLOPs: 23.49 | +63: iteration 22580/ 73814 | consumed samples: 11560960 | consumed tokens: 23676846080 | elapsed time per iteration (s): 2.24 | learning rate: 1.632E-04 | global batch size: 512 | lm loss: 2.128152E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.371 | TFLOPs: 23.51 | +63: iteration 22590/ 73814 | consumed samples: 11566080 | consumed tokens: 23687331840 | elapsed time per iteration (s): 2.47 | learning rate: 1.631E-04 | global batch size: 512 | lm loss: 2.138967E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.878 | TFLOPs: 21.30 | +63: iteration 22600/ 73814 | consumed samples: 11571200 | consumed tokens: 23697817600 | elapsed time per iteration (s): 2.24 | learning rate: 1.631E-04 | global batch size: 512 | lm loss: 2.133886E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.524 | TFLOPs: 23.53 | +63: iteration 22610/ 73814 | consumed samples: 11576320 | consumed tokens: 23708303360 | elapsed time per iteration (s): 2.25 | learning rate: 1.631E-04 | global batch size: 512 | lm loss: 2.159949E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.586 | TFLOPs: 23.43 | +63: iteration 22620/ 73814 | consumed samples: 11581440 | consumed tokens: 23718789120 | elapsed time per iteration (s): 2.26 | learning rate: 1.630E-04 | global batch size: 512 | lm loss: 2.152701E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.827 | TFLOPs: 23.35 | +63: iteration 22630/ 73814 | consumed samples: 11586560 | consumed tokens: 23729274880 | elapsed time per iteration (s): 2.23 | learning rate: 1.630E-04 | global batch size: 512 | lm loss: 2.129256E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.893 | TFLOPs: 23.67 | +63: iteration 22640/ 73814 | consumed samples: 11591680 | consumed tokens: 23739760640 | elapsed time per iteration (s): 2.23 | learning rate: 1.630E-04 | global batch size: 512 | lm loss: 2.136490E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.095 | TFLOPs: 23.69 | +63: iteration 22650/ 73814 | consumed samples: 11596800 | consumed tokens: 23750246400 | elapsed time per iteration (s): 2.23 | learning rate: 1.629E-04 | global batch size: 512 | lm loss: 2.152748E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.750 | TFLOPs: 23.65 | +63: iteration 22660/ 73814 | consumed samples: 11601920 | consumed tokens: 23760732160 | elapsed time per iteration (s): 2.23 | learning rate: 1.629E-04 | global batch size: 512 | lm loss: 2.148585E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.090 | TFLOPs: 23.69 | +63: iteration 22670/ 73814 | consumed samples: 11607040 | consumed tokens: 23771217920 | elapsed time per iteration (s): 2.27 | learning rate: 1.629E-04 | global batch size: 512 | lm loss: 2.162911E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.040 | TFLOPs: 23.27 | +63: iteration 22680/ 73814 | consumed samples: 11612160 | consumed tokens: 23781703680 | elapsed time per iteration (s): 2.23 | learning rate: 1.628E-04 | global batch size: 512 | lm loss: 2.129526E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.091 | TFLOPs: 23.69 | +63: iteration 22690/ 73814 | consumed samples: 11617280 | consumed tokens: 23792189440 | elapsed time per iteration (s): 2.23 | learning rate: 1.628E-04 | global batch size: 512 | lm loss: 2.145420E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.808 | TFLOPs: 23.66 | +63: iteration 22700/ 73814 | consumed samples: 11622400 | consumed tokens: 23802675200 | elapsed time per iteration (s): 2.24 | learning rate: 1.628E-04 | global batch size: 512 | lm loss: 2.131500E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.048 | TFLOPs: 23.58 | +63: iteration 22710/ 73814 | consumed samples: 11627520 | consumed tokens: 23813160960 | elapsed time per iteration (s): 2.23 | learning rate: 1.627E-04 | global batch size: 512 | lm loss: 2.151861E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.849 | TFLOPs: 23.66 | +63: iteration 22720/ 73814 | consumed samples: 11632640 | consumed tokens: 23823646720 | elapsed time per iteration (s): 2.24 | learning rate: 1.627E-04 | global batch size: 512 | lm loss: 2.149197E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.196 | TFLOPs: 23.49 | +63: iteration 22730/ 73814 | consumed samples: 11637760 | consumed tokens: 23834132480 | elapsed time per iteration (s): 2.23 | learning rate: 1.627E-04 | global batch size: 512 | lm loss: 2.142736E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.474 | TFLOPs: 23.62 | +63: iteration 22740/ 73814 | consumed samples: 11642880 | consumed tokens: 23844618240 | elapsed time per iteration (s): 2.23 | learning rate: 1.627E-04 | global batch size: 512 | lm loss: 2.122873E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.657 | TFLOPs: 23.64 | +63: iteration 22750/ 73814 | consumed samples: 11648000 | consumed tokens: 23855104000 | elapsed time per iteration (s): 2.36 | learning rate: 1.626E-04 | global batch size: 512 | lm loss: 2.153838E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.185 | TFLOPs: 22.36 | +63: iteration 22760/ 73814 | consumed samples: 11653120 | consumed tokens: 23865589760 | elapsed time per iteration (s): 2.35 | learning rate: 1.626E-04 | global batch size: 512 | lm loss: 2.126006E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.565 | TFLOPs: 22.40 | +63: iteration 22770/ 73814 | consumed samples: 11658240 | consumed tokens: 23876075520 | elapsed time per iteration (s): 2.23 | learning rate: 1.626E-04 | global batch size: 512 | lm loss: 2.131204E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.839 | TFLOPs: 23.66 | +63: iteration 22780/ 73814 | consumed samples: 11663360 | consumed tokens: 23886561280 | elapsed time per iteration (s): 2.23 | learning rate: 1.625E-04 | global batch size: 512 | lm loss: 2.127256E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.745 | TFLOPs: 23.65 | +63: iteration 22790/ 73814 | consumed samples: 11668480 | consumed tokens: 23897047040 | elapsed time per iteration (s): 2.24 | learning rate: 1.625E-04 | global batch size: 512 | lm loss: 2.131916E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.082 | TFLOPs: 23.48 | +63: iteration 22800/ 73814 | consumed samples: 11673600 | consumed tokens: 23907532800 | elapsed time per iteration (s): 2.23 | learning rate: 1.625E-04 | global batch size: 512 | lm loss: 2.133385E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.360 | TFLOPs: 23.61 | +63: iteration 22810/ 73814 | consumed samples: 11678720 | consumed tokens: 23918018560 | elapsed time per iteration (s): 2.23 | learning rate: 1.624E-04 | global batch size: 512 | lm loss: 2.142082E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.605 | TFLOPs: 23.64 | +63: iteration 22820/ 73814 | consumed samples: 11683840 | consumed tokens: 23928504320 | elapsed time per iteration (s): 2.22 | learning rate: 1.624E-04 | global batch size: 512 | lm loss: 2.134004E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.136 | TFLOPs: 23.69 | +63: iteration 22830/ 73814 | consumed samples: 11688960 | consumed tokens: 23938990080 | elapsed time per iteration (s): 2.24 | learning rate: 1.624E-04 | global batch size: 512 | lm loss: 2.130897E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.622 | TFLOPs: 23.54 | +63: iteration 22840/ 73814 | consumed samples: 11694080 | consumed tokens: 23949475840 | elapsed time per iteration (s): 2.24 | learning rate: 1.623E-04 | global batch size: 512 | lm loss: 2.140252E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.435 | TFLOPs: 23.52 | +63: iteration 22850/ 73814 | consumed samples: 11699200 | consumed tokens: 23959961600 | elapsed time per iteration (s): 2.24 | learning rate: 1.623E-04 | global batch size: 512 | lm loss: 2.118338E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.163 | TFLOPs: 23.49 | +63: iteration 22860/ 73814 | consumed samples: 11704320 | consumed tokens: 23970447360 | elapsed time per iteration (s): 2.23 | learning rate: 1.623E-04 | global batch size: 512 | lm loss: 2.145820E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.602 | TFLOPs: 23.64 | +63: iteration 22870/ 73814 | consumed samples: 11709440 | consumed tokens: 23980933120 | elapsed time per iteration (s): 2.24 | learning rate: 1.622E-04 | global batch size: 512 | lm loss: 2.148207E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.164 | TFLOPs: 23.49 | +63: iteration 22880/ 73814 | consumed samples: 11714560 | consumed tokens: 23991418880 | elapsed time per iteration (s): 2.23 | learning rate: 1.622E-04 | global batch size: 512 | lm loss: 2.141317E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.920 | TFLOPs: 23.67 | +63: iteration 22890/ 73814 | consumed samples: 11719680 | consumed tokens: 24001904640 | elapsed time per iteration (s): 2.22 | learning rate: 1.622E-04 | global batch size: 512 | lm loss: 2.145883E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.267 | TFLOPs: 23.70 | +63: iteration 22900/ 73814 | consumed samples: 11724800 | consumed tokens: 24012390400 | elapsed time per iteration (s): 2.60 | learning rate: 1.621E-04 | global batch size: 512 | lm loss: 2.145012E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 197.016 | TFLOPs: 20.28 | +63: iteration 22910/ 73814 | consumed samples: 11729920 | consumed tokens: 24022876160 | elapsed time per iteration (s): 2.24 | learning rate: 1.621E-04 | global batch size: 512 | lm loss: 2.141141E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.422 | TFLOPs: 23.51 | +63: iteration 22920/ 73814 | consumed samples: 11735040 | consumed tokens: 24033361920 | elapsed time per iteration (s): 2.24 | learning rate: 1.621E-04 | global batch size: 512 | lm loss: 2.135489E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.198 | TFLOPs: 23.49 | +63: iteration 22930/ 73814 | consumed samples: 11740160 | consumed tokens: 24043847680 | elapsed time per iteration (s): 2.23 | learning rate: 1.621E-04 | global batch size: 512 | lm loss: 2.143657E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.838 | TFLOPs: 23.66 | +63: iteration 22940/ 73814 | consumed samples: 11745280 | consumed tokens: 24054333440 | elapsed time per iteration (s): 2.32 | learning rate: 1.620E-04 | global batch size: 512 | lm loss: 2.134051E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.651 | TFLOPs: 22.71 | +63: iteration 22950/ 73814 | consumed samples: 11750400 | consumed tokens: 24064819200 | elapsed time per iteration (s): 2.22 | learning rate: 1.620E-04 | global batch size: 512 | lm loss: 2.132222E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.181 | TFLOPs: 23.70 | +63: iteration 22960/ 73814 | consumed samples: 11755520 | consumed tokens: 24075304960 | elapsed time per iteration (s): 2.24 | learning rate: 1.620E-04 | global batch size: 512 | lm loss: 2.133525E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.810 | TFLOPs: 23.55 | +63: iteration 22970/ 73814 | consumed samples: 11760640 | consumed tokens: 24085790720 | elapsed time per iteration (s): 2.23 | learning rate: 1.619E-04 | global batch size: 512 | lm loss: 2.152894E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.619 | TFLOPs: 23.64 | +63: iteration 22980/ 73814 | consumed samples: 11765760 | consumed tokens: 24096276480 | elapsed time per iteration (s): 2.24 | learning rate: 1.619E-04 | global batch size: 512 | lm loss: 2.138208E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.904 | TFLOPs: 23.56 | +63: iteration 22990/ 73814 | consumed samples: 11770880 | consumed tokens: 24106762240 | elapsed time per iteration (s): 2.23 | learning rate: 1.619E-04 | global batch size: 512 | lm loss: 2.133684E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.849 | TFLOPs: 23.66 | +63: iteration 23000/ 73814 | consumed samples: 11776000 | consumed tokens: 24117248000 | elapsed time per iteration (s): 2.24 | learning rate: 1.618E-04 | global batch size: 512 | lm loss: 2.128025E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.647 | TFLOPs: 23.54 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 23000 | lm loss value: 2.040009E+00 | lm loss PPL: 7.690675E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 23010/ 73814 | consumed samples: 11781120 | consumed tokens: 24127733760 | elapsed time per iteration (s): 2.32 | learning rate: 1.618E-04 | global batch size: 512 | lm loss: 2.140107E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.504 | TFLOPs: 22.70 | +63: iteration 23020/ 73814 | consumed samples: 11786240 | consumed tokens: 24138219520 | elapsed time per iteration (s): 2.23 | learning rate: 1.618E-04 | global batch size: 512 | lm loss: 2.137890E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.434 | TFLOPs: 23.62 | +63: iteration 23030/ 73814 | consumed samples: 11791360 | consumed tokens: 24148705280 | elapsed time per iteration (s): 2.22 | learning rate: 1.617E-04 | global batch size: 512 | lm loss: 2.137852E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.241 | TFLOPs: 23.70 | +63: iteration 23040/ 73814 | consumed samples: 11796480 | consumed tokens: 24159191040 | elapsed time per iteration (s): 2.24 | learning rate: 1.617E-04 | global batch size: 512 | lm loss: 2.128481E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.205 | TFLOPs: 23.49 | +63: iteration 23050/ 73814 | consumed samples: 11801600 | consumed tokens: 24169676800 | elapsed time per iteration (s): 2.26 | learning rate: 1.617E-04 | global batch size: 512 | lm loss: 2.137108E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.674 | TFLOPs: 23.33 | +63: iteration 23060/ 73814 | consumed samples: 11806720 | consumed tokens: 24180162560 | elapsed time per iteration (s): 2.25 | learning rate: 1.616E-04 | global batch size: 512 | lm loss: 2.151042E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.557 | TFLOPs: 23.43 | +63: iteration 23070/ 73814 | consumed samples: 11811840 | consumed tokens: 24190648320 | elapsed time per iteration (s): 2.22 | learning rate: 1.616E-04 | global batch size: 512 | lm loss: 2.161153E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.335 | TFLOPs: 23.71 | +63: iteration 23080/ 73814 | consumed samples: 11816960 | consumed tokens: 24201134080 | elapsed time per iteration (s): 2.30 | learning rate: 1.616E-04 | global batch size: 512 | lm loss: 2.132503E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.981 | TFLOPs: 22.95 | +63: iteration 23090/ 73814 | consumed samples: 11822080 | consumed tokens: 24211619840 | elapsed time per iteration (s): 2.23 | learning rate: 1.615E-04 | global batch size: 512 | lm loss: 2.140394E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.068 | TFLOPs: 23.68 | +63: iteration 23100/ 73814 | consumed samples: 11827200 | consumed tokens: 24222105600 | elapsed time per iteration (s): 2.25 | learning rate: 1.615E-04 | global batch size: 512 | lm loss: 2.137730E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.656 | TFLOPs: 23.44 | +63: iteration 23110/ 73814 | consumed samples: 11832320 | consumed tokens: 24232591360 | elapsed time per iteration (s): 2.23 | learning rate: 1.615E-04 | global batch size: 512 | lm loss: 2.141087E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.531 | TFLOPs: 23.63 | +63: iteration 23120/ 73814 | consumed samples: 11837440 | consumed tokens: 24243077120 | elapsed time per iteration (s): 2.23 | learning rate: 1.615E-04 | global batch size: 512 | lm loss: 2.115510E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.737 | TFLOPs: 23.65 | +63: iteration 23130/ 73814 | consumed samples: 11842560 | consumed tokens: 24253562880 | elapsed time per iteration (s): 2.23 | learning rate: 1.614E-04 | global batch size: 512 | lm loss: 2.142896E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.026 | TFLOPs: 23.68 | +63: iteration 23140/ 73814 | consumed samples: 11847680 | consumed tokens: 24264048640 | elapsed time per iteration (s): 2.23 | learning rate: 1.614E-04 | global batch size: 512 | lm loss: 2.145770E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.590 | TFLOPs: 23.64 | +63: iteration 23150/ 73814 | consumed samples: 11852800 | consumed tokens: 24274534400 | elapsed time per iteration (s): 2.24 | learning rate: 1.614E-04 | global batch size: 512 | lm loss: 2.153425E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.147 | TFLOPs: 23.49 | +63: iteration 23160/ 73814 | consumed samples: 11857920 | consumed tokens: 24285020160 | elapsed time per iteration (s): 2.23 | learning rate: 1.613E-04 | global batch size: 512 | lm loss: 2.130902E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.695 | TFLOPs: 23.65 | +63: iteration 23170/ 73814 | consumed samples: 11863040 | consumed tokens: 24295505920 | elapsed time per iteration (s): 2.28 | learning rate: 1.613E-04 | global batch size: 512 | lm loss: 2.155993E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.748 | TFLOPs: 23.14 | +63: iteration 23180/ 73814 | consumed samples: 11868160 | consumed tokens: 24305991680 | elapsed time per iteration (s): 2.23 | learning rate: 1.613E-04 | global batch size: 512 | lm loss: 2.134418E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.460 | TFLOPs: 23.62 | +63: iteration 23190/ 73814 | consumed samples: 11873280 | consumed tokens: 24316477440 | elapsed time per iteration (s): 2.23 | learning rate: 1.612E-04 | global batch size: 512 | lm loss: 2.131209E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.380 | TFLOPs: 23.61 | +63: iteration 23200/ 73814 | consumed samples: 11878400 | consumed tokens: 24326963200 | elapsed time per iteration (s): 2.23 | learning rate: 1.612E-04 | global batch size: 512 | lm loss: 2.120708E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.599 | TFLOPs: 23.64 | +63: iteration 23210/ 73814 | consumed samples: 11883520 | consumed tokens: 24337448960 | elapsed time per iteration (s): 2.24 | learning rate: 1.612E-04 | global batch size: 512 | lm loss: 2.162083E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.757 | TFLOPs: 23.55 | +63: iteration 23220/ 73814 | consumed samples: 11888640 | consumed tokens: 24347934720 | elapsed time per iteration (s): 2.49 | learning rate: 1.611E-04 | global batch size: 512 | lm loss: 2.141195E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.017 | TFLOPs: 21.21 | +63: iteration 23230/ 73814 | consumed samples: 11893760 | consumed tokens: 24358420480 | elapsed time per iteration (s): 2.27 | learning rate: 1.611E-04 | global batch size: 512 | lm loss: 2.156305E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.652 | TFLOPs: 23.23 | +63: iteration 23240/ 73814 | consumed samples: 11898880 | consumed tokens: 24368906240 | elapsed time per iteration (s): 2.23 | learning rate: 1.611E-04 | global batch size: 512 | lm loss: 2.135173E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.384 | TFLOPs: 23.61 | +63: iteration 23250/ 73814 | consumed samples: 11904000 | consumed tokens: 24379392000 | elapsed time per iteration (s): 2.23 | learning rate: 1.610E-04 | global batch size: 512 | lm loss: 2.131822E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.844 | TFLOPs: 23.66 | +63: iteration 23260/ 73814 | consumed samples: 11909120 | consumed tokens: 24389877760 | elapsed time per iteration (s): 2.24 | learning rate: 1.610E-04 | global batch size: 512 | lm loss: 2.136484E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.795 | TFLOPs: 23.55 | +63: iteration 23270/ 73814 | consumed samples: 11914240 | consumed tokens: 24400363520 | elapsed time per iteration (s): 2.24 | learning rate: 1.610E-04 | global batch size: 512 | lm loss: 2.128087E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.493 | TFLOPs: 23.52 | +63: iteration 23280/ 73814 | consumed samples: 11919360 | consumed tokens: 24410849280 | elapsed time per iteration (s): 2.23 | learning rate: 1.609E-04 | global batch size: 512 | lm loss: 2.125919E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.790 | TFLOPs: 23.66 | +63: iteration 23290/ 73814 | consumed samples: 11924480 | consumed tokens: 24421335040 | elapsed time per iteration (s): 2.29 | learning rate: 1.609E-04 | global batch size: 512 | lm loss: 2.141507E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.035 | TFLOPs: 23.06 | +63: iteration 23300/ 73814 | consumed samples: 11929600 | consumed tokens: 24431820800 | elapsed time per iteration (s): 2.25 | learning rate: 1.609E-04 | global batch size: 512 | lm loss: 2.136930E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.111 | TFLOPs: 23.38 | +63: iteration 23310/ 73814 | consumed samples: 11934720 | consumed tokens: 24442306560 | elapsed time per iteration (s): 2.22 | learning rate: 1.608E-04 | global batch size: 512 | lm loss: 2.145493E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.169 | TFLOPs: 23.69 | +63: iteration 23320/ 73814 | consumed samples: 11939840 | consumed tokens: 24452792320 | elapsed time per iteration (s): 2.23 | learning rate: 1.608E-04 | global batch size: 512 | lm loss: 2.125060E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.915 | TFLOPs: 23.67 | +63: iteration 23330/ 73814 | consumed samples: 11944960 | consumed tokens: 24463278080 | elapsed time per iteration (s): 2.27 | learning rate: 1.608E-04 | global batch size: 512 | lm loss: 2.103849E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.024 | TFLOPs: 23.27 | +63: iteration 23340/ 73814 | consumed samples: 11950080 | consumed tokens: 24473763840 | elapsed time per iteration (s): 2.23 | learning rate: 1.608E-04 | global batch size: 512 | lm loss: 2.128255E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.545 | TFLOPs: 23.63 | +63: iteration 23350/ 73814 | consumed samples: 11955200 | consumed tokens: 24484249600 | elapsed time per iteration (s): 2.26 | learning rate: 1.607E-04 | global batch size: 512 | lm loss: 2.137670E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.557 | TFLOPs: 23.32 | +63: iteration 23360/ 73814 | consumed samples: 11960320 | consumed tokens: 24494735360 | elapsed time per iteration (s): 2.23 | learning rate: 1.607E-04 | global batch size: 512 | lm loss: 2.136381E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.513 | TFLOPs: 23.63 | +63: iteration 23370/ 73814 | consumed samples: 11965440 | consumed tokens: 24505221120 | elapsed time per iteration (s): 2.23 | learning rate: 1.607E-04 | global batch size: 512 | lm loss: 2.138643E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.016 | TFLOPs: 23.68 | +63: iteration 23380/ 73814 | consumed samples: 11970560 | consumed tokens: 24515706880 | elapsed time per iteration (s): 2.45 | learning rate: 1.606E-04 | global batch size: 512 | lm loss: 2.155738E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.785 | TFLOPs: 21.49 | +63: iteration 23390/ 73814 | consumed samples: 11975680 | consumed tokens: 24526192640 | elapsed time per iteration (s): 2.23 | learning rate: 1.606E-04 | global batch size: 512 | lm loss: 2.129884E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.843 | TFLOPs: 23.66 | +63: iteration 23400/ 73814 | consumed samples: 11980800 | consumed tokens: 24536678400 | elapsed time per iteration (s): 2.24 | learning rate: 1.606E-04 | global batch size: 512 | lm loss: 2.121532E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.075 | TFLOPs: 23.48 | +63: iteration 23410/ 73814 | consumed samples: 11985920 | consumed tokens: 24547164160 | elapsed time per iteration (s): 2.30 | learning rate: 1.605E-04 | global batch size: 512 | lm loss: 2.118460E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.787 | TFLOPs: 22.93 | +63: iteration 23420/ 73814 | consumed samples: 11991040 | consumed tokens: 24557649920 | elapsed time per iteration (s): 2.23 | learning rate: 1.605E-04 | global batch size: 512 | lm loss: 2.110391E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.821 | TFLOPs: 23.66 | +63: iteration 23430/ 73814 | consumed samples: 11996160 | consumed tokens: 24568135680 | elapsed time per iteration (s): 2.24 | learning rate: 1.605E-04 | global batch size: 512 | lm loss: 2.134450E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.170 | TFLOPs: 23.49 | +63: iteration 23440/ 73814 | consumed samples: 12001280 | consumed tokens: 24578621440 | elapsed time per iteration (s): 2.25 | learning rate: 1.604E-04 | global batch size: 512 | lm loss: 2.122777E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.310 | TFLOPs: 23.40 | +63: iteration 23450/ 73814 | consumed samples: 12006400 | consumed tokens: 24589107200 | elapsed time per iteration (s): 2.30 | learning rate: 1.604E-04 | global batch size: 512 | lm loss: 2.136347E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.764 | TFLOPs: 22.93 | +63: iteration 23460/ 73814 | consumed samples: 12011520 | consumed tokens: 24599592960 | elapsed time per iteration (s): 2.25 | learning rate: 1.604E-04 | global batch size: 512 | lm loss: 2.103901E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.278 | TFLOPs: 23.40 | +63: iteration 23470/ 73814 | consumed samples: 12016640 | consumed tokens: 24610078720 | elapsed time per iteration (s): 2.25 | learning rate: 1.603E-04 | global batch size: 512 | lm loss: 2.117800E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.060 | TFLOPs: 23.48 | +63: iteration 23480/ 73814 | consumed samples: 12021760 | consumed tokens: 24620564480 | elapsed time per iteration (s): 2.23 | learning rate: 1.603E-04 | global batch size: 512 | lm loss: 2.145197E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.399 | TFLOPs: 23.62 | +63: iteration 23490/ 73814 | consumed samples: 12026880 | consumed tokens: 24631050240 | elapsed time per iteration (s): 2.25 | learning rate: 1.603E-04 | global batch size: 512 | lm loss: 2.122004E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.113 | TFLOPs: 23.38 | +63: iteration 23500/ 73814 | consumed samples: 12032000 | consumed tokens: 24641536000 | elapsed time per iteration (s): 2.22 | learning rate: 1.602E-04 | global batch size: 512 | lm loss: 2.145369E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.569 | TFLOPs: 23.74 | +63: iteration 23510/ 73814 | consumed samples: 12037120 | consumed tokens: 24652021760 | elapsed time per iteration (s): 2.31 | learning rate: 1.602E-04 | global batch size: 512 | lm loss: 2.125850E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.597 | TFLOPs: 22.81 | +63: iteration 23520/ 73814 | consumed samples: 12042240 | consumed tokens: 24662507520 | elapsed time per iteration (s): 2.23 | learning rate: 1.602E-04 | global batch size: 512 | lm loss: 2.127260E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.704 | TFLOPs: 23.65 | +63: iteration 23530/ 73814 | consumed samples: 12047360 | consumed tokens: 24672993280 | elapsed time per iteration (s): 2.28 | learning rate: 1.601E-04 | global batch size: 512 | lm loss: 2.115012E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.254 | TFLOPs: 23.09 | +63: iteration 23540/ 73814 | consumed samples: 12052480 | consumed tokens: 24683479040 | elapsed time per iteration (s): 2.24 | learning rate: 1.601E-04 | global batch size: 512 | lm loss: 2.117873E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.928 | TFLOPs: 23.57 | +63: iteration 23550/ 73814 | consumed samples: 12057600 | consumed tokens: 24693964800 | elapsed time per iteration (s): 2.24 | learning rate: 1.601E-04 | global batch size: 512 | lm loss: 2.140005E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.630 | TFLOPs: 23.54 | +63: iteration 23560/ 73814 | consumed samples: 12062720 | consumed tokens: 24704450560 | elapsed time per iteration (s): 2.30 | learning rate: 1.600E-04 | global batch size: 512 | lm loss: 2.152517E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.909 | TFLOPs: 22.95 | +63: iteration 23570/ 73814 | consumed samples: 12067840 | consumed tokens: 24714936320 | elapsed time per iteration (s): 2.30 | learning rate: 1.600E-04 | global batch size: 512 | lm loss: 2.116241E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.402 | TFLOPs: 22.90 | +63: iteration 23580/ 73814 | consumed samples: 12072960 | consumed tokens: 24725422080 | elapsed time per iteration (s): 2.31 | learning rate: 1.600E-04 | global batch size: 512 | lm loss: 2.127277E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.780 | TFLOPs: 22.83 | +63: iteration 23590/ 73814 | consumed samples: 12078080 | consumed tokens: 24735907840 | elapsed time per iteration (s): 2.24 | learning rate: 1.600E-04 | global batch size: 512 | lm loss: 2.123364E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.518 | TFLOPs: 23.52 | +63: iteration 23600/ 73814 | consumed samples: 12083200 | consumed tokens: 24746393600 | elapsed time per iteration (s): 2.23 | learning rate: 1.599E-04 | global batch size: 512 | lm loss: 2.138837E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.735 | TFLOPs: 23.65 | +63: iteration 23610/ 73814 | consumed samples: 12088320 | consumed tokens: 24756879360 | elapsed time per iteration (s): 2.24 | learning rate: 1.599E-04 | global batch size: 512 | lm loss: 2.146090E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.035 | TFLOPs: 23.58 | +63: iteration 23620/ 73814 | consumed samples: 12093440 | consumed tokens: 24767365120 | elapsed time per iteration (s): 2.24 | learning rate: 1.599E-04 | global batch size: 512 | lm loss: 2.119131E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.144 | TFLOPs: 23.49 | +63: iteration 23630/ 73814 | consumed samples: 12098560 | consumed tokens: 24777850880 | elapsed time per iteration (s): 2.26 | learning rate: 1.598E-04 | global batch size: 512 | lm loss: 2.145773E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.206 | TFLOPs: 23.29 | +63: iteration 23640/ 73814 | consumed samples: 12103680 | consumed tokens: 24788336640 | elapsed time per iteration (s): 2.24 | learning rate: 1.598E-04 | global batch size: 512 | lm loss: 2.139421E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.137 | TFLOPs: 23.49 | +63: iteration 23650/ 73814 | consumed samples: 12108800 | consumed tokens: 24798822400 | elapsed time per iteration (s): 2.25 | learning rate: 1.598E-04 | global batch size: 512 | lm loss: 2.113523E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.051 | TFLOPs: 23.48 | +63: iteration 23660/ 73814 | consumed samples: 12113920 | consumed tokens: 24809308160 | elapsed time per iteration (s): 2.23 | learning rate: 1.597E-04 | global batch size: 512 | lm loss: 2.140022E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.898 | TFLOPs: 23.67 | +63: iteration 23670/ 73814 | consumed samples: 12119040 | consumed tokens: 24819793920 | elapsed time per iteration (s): 2.24 | learning rate: 1.597E-04 | global batch size: 512 | lm loss: 2.138354E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.621 | TFLOPs: 23.54 | +63: iteration 23680/ 73814 | consumed samples: 12124160 | consumed tokens: 24830279680 | elapsed time per iteration (s): 2.40 | learning rate: 1.597E-04 | global batch size: 512 | lm loss: 2.154690E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.495 | TFLOPs: 21.98 | +63: iteration 23690/ 73814 | consumed samples: 12129280 | consumed tokens: 24840765440 | elapsed time per iteration (s): 2.36 | learning rate: 1.596E-04 | global batch size: 512 | lm loss: 2.137551E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.149 | TFLOPs: 22.35 | +63: iteration 23700/ 73814 | consumed samples: 12134400 | consumed tokens: 24851251200 | elapsed time per iteration (s): 2.29 | learning rate: 1.596E-04 | global batch size: 512 | lm loss: 2.122976E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.042 | TFLOPs: 23.06 | +63: iteration 23710/ 73814 | consumed samples: 12139520 | consumed tokens: 24861736960 | elapsed time per iteration (s): 2.43 | learning rate: 1.596E-04 | global batch size: 512 | lm loss: 2.157576E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.640 | TFLOPs: 21.68 | +63: iteration 23720/ 73814 | consumed samples: 12144640 | consumed tokens: 24872222720 | elapsed time per iteration (s): 2.40 | learning rate: 1.595E-04 | global batch size: 512 | lm loss: 2.105961E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.718 | TFLOPs: 22.00 | +63: iteration 23730/ 73814 | consumed samples: 12149760 | consumed tokens: 24882708480 | elapsed time per iteration (s): 2.37 | learning rate: 1.595E-04 | global batch size: 512 | lm loss: 2.152238E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.404 | TFLOPs: 22.28 | +63: iteration 23740/ 73814 | consumed samples: 12154880 | consumed tokens: 24893194240 | elapsed time per iteration (s): 2.28 | learning rate: 1.595E-04 | global batch size: 512 | lm loss: 2.133915E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.430 | TFLOPs: 23.10 | +63: iteration 23750/ 73814 | consumed samples: 12160000 | consumed tokens: 24903680000 | elapsed time per iteration (s): 2.44 | learning rate: 1.594E-04 | global batch size: 512 | lm loss: 2.118390E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.689 | TFLOPs: 21.59 | +63: iteration 23760/ 73814 | consumed samples: 12165120 | consumed tokens: 24914165760 | elapsed time per iteration (s): 2.76 | learning rate: 1.594E-04 | global batch size: 512 | lm loss: 2.147425E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 185.695 | TFLOPs: 19.12 | +63: iteration 23770/ 73814 | consumed samples: 12170240 | consumed tokens: 24924651520 | elapsed time per iteration (s): 2.59 | learning rate: 1.594E-04 | global batch size: 512 | lm loss: 2.145325E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 197.509 | TFLOPs: 20.33 | +63: iteration 23780/ 73814 | consumed samples: 12175360 | consumed tokens: 24935137280 | elapsed time per iteration (s): 2.29 | learning rate: 1.593E-04 | global batch size: 512 | lm loss: 2.124780E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.430 | TFLOPs: 23.00 | +63: iteration 23790/ 73814 | consumed samples: 12180480 | consumed tokens: 24945623040 | elapsed time per iteration (s): 2.30 | learning rate: 1.593E-04 | global batch size: 512 | lm loss: 2.141462E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.994 | TFLOPs: 22.96 | +63: iteration 23800/ 73814 | consumed samples: 12185600 | consumed tokens: 24956108800 | elapsed time per iteration (s): 2.43 | learning rate: 1.593E-04 | global batch size: 512 | lm loss: 2.128352E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.318 | TFLOPs: 21.65 | +63: iteration 23810/ 73814 | consumed samples: 12190720 | consumed tokens: 24966594560 | elapsed time per iteration (s): 2.32 | learning rate: 1.592E-04 | global batch size: 512 | lm loss: 2.120735E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.454 | TFLOPs: 22.69 | +63: iteration 23820/ 73814 | consumed samples: 12195840 | consumed tokens: 24977080320 | elapsed time per iteration (s): 2.26 | learning rate: 1.592E-04 | global batch size: 512 | lm loss: 2.156026E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.293 | TFLOPs: 23.30 | +63: iteration 23830/ 73814 | consumed samples: 12200960 | consumed tokens: 24987566080 | elapsed time per iteration (s): 2.27 | learning rate: 1.592E-04 | global batch size: 512 | lm loss: 2.130397E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.922 | TFLOPs: 23.26 | +63: iteration 23840/ 73814 | consumed samples: 12206080 | consumed tokens: 24998051840 | elapsed time per iteration (s): 2.26 | learning rate: 1.591E-04 | global batch size: 512 | lm loss: 2.135416E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.675 | TFLOPs: 23.34 | +63: iteration 23850/ 73814 | consumed samples: 12211200 | consumed tokens: 25008537600 | elapsed time per iteration (s): 2.23 | learning rate: 1.591E-04 | global batch size: 512 | lm loss: 2.126995E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.595 | TFLOPs: 23.64 | +63: iteration 23860/ 73814 | consumed samples: 12216320 | consumed tokens: 25019023360 | elapsed time per iteration (s): 2.24 | learning rate: 1.591E-04 | global batch size: 512 | lm loss: 2.125302E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.457 | TFLOPs: 23.52 | +63: iteration 23870/ 73814 | consumed samples: 12221440 | consumed tokens: 25029509120 | elapsed time per iteration (s): 2.25 | learning rate: 1.590E-04 | global batch size: 512 | lm loss: 2.115580E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.679 | TFLOPs: 23.44 | +63: iteration 23880/ 73814 | consumed samples: 12226560 | consumed tokens: 25039994880 | elapsed time per iteration (s): 2.23 | learning rate: 1.590E-04 | global batch size: 512 | lm loss: 2.135407E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.728 | TFLOPs: 23.65 | +63: iteration 23890/ 73814 | consumed samples: 12231680 | consumed tokens: 25050480640 | elapsed time per iteration (s): 2.32 | learning rate: 1.590E-04 | global batch size: 512 | lm loss: 2.129984E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.135 | TFLOPs: 22.76 | +63: iteration 23900/ 73814 | consumed samples: 12236800 | consumed tokens: 25060966400 | elapsed time per iteration (s): 2.25 | learning rate: 1.589E-04 | global batch size: 512 | lm loss: 2.129880E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.590 | TFLOPs: 23.43 | +63: iteration 23910/ 73814 | consumed samples: 12241920 | consumed tokens: 25071452160 | elapsed time per iteration (s): 2.23 | learning rate: 1.589E-04 | global batch size: 512 | lm loss: 2.137286E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.818 | TFLOPs: 23.66 | +63: iteration 23920/ 73814 | consumed samples: 12247040 | consumed tokens: 25081937920 | elapsed time per iteration (s): 2.26 | learning rate: 1.589E-04 | global batch size: 512 | lm loss: 2.137980E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.031 | TFLOPs: 23.37 | +63: iteration 23930/ 73814 | consumed samples: 12252160 | consumed tokens: 25092423680 | elapsed time per iteration (s): 2.26 | learning rate: 1.589E-04 | global batch size: 512 | lm loss: 2.132209E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.436 | TFLOPs: 23.31 | +63: iteration 23940/ 73814 | consumed samples: 12257280 | consumed tokens: 25102909440 | elapsed time per iteration (s): 2.23 | learning rate: 1.588E-04 | global batch size: 512 | lm loss: 2.125011E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.631 | TFLOPs: 23.64 | +63: iteration 23950/ 73814 | consumed samples: 12262400 | consumed tokens: 25113395200 | elapsed time per iteration (s): 2.24 | learning rate: 1.588E-04 | global batch size: 512 | lm loss: 2.129712E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.090 | TFLOPs: 23.48 | +63: iteration 23960/ 73814 | consumed samples: 12267520 | consumed tokens: 25123880960 | elapsed time per iteration (s): 2.24 | learning rate: 1.588E-04 | global batch size: 512 | lm loss: 2.115765E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.391 | TFLOPs: 23.51 | +63: iteration 23970/ 73814 | consumed samples: 12272640 | consumed tokens: 25134366720 | elapsed time per iteration (s): 2.23 | learning rate: 1.587E-04 | global batch size: 512 | lm loss: 2.119798E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.610 | TFLOPs: 23.64 | +63: iteration 23980/ 73814 | consumed samples: 12277760 | consumed tokens: 25144852480 | elapsed time per iteration (s): 2.23 | learning rate: 1.587E-04 | global batch size: 512 | lm loss: 2.123870E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.093 | TFLOPs: 23.69 | +63: iteration 23990/ 73814 | consumed samples: 12282880 | consumed tokens: 25155338240 | elapsed time per iteration (s): 2.24 | learning rate: 1.587E-04 | global batch size: 512 | lm loss: 2.122916E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.887 | TFLOPs: 23.56 | + 0: [2022-12-02 02:59:42,398] [INFO] [logging.py:68:log_dist] [Rank 0] step=24000, skipped=0, lr=[0.0001586240712888517, 0.0001586240712888517, 0.0001586240712888517], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 24000/ 73814 | consumed samples: 12288000 | consumed tokens: 25165824000 | elapsed time per iteration (s): 2.23 | learning rate: 1.586E-04 | global batch size: 512 | lm loss: 2.144200E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.679 | TFLOPs: 23.64 | + 0: steps: 24000 loss: 2.1858 iter time (s): 2.267 samples/sec: 225.883 +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 24000 | lm loss value: 2.108968E+00 | lm loss PPL: 8.239738E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 24010/ 73814 | consumed samples: 12293120 | consumed tokens: 25176309760 | elapsed time per iteration (s): 2.28 | learning rate: 1.586E-04 | global batch size: 512 | lm loss: 2.137923E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.564 | TFLOPs: 23.12 | +63: iteration 24020/ 73814 | consumed samples: 12298240 | consumed tokens: 25186795520 | elapsed time per iteration (s): 2.26 | learning rate: 1.586E-04 | global batch size: 512 | lm loss: 2.120920E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.033 | TFLOPs: 23.37 | +63: iteration 24030/ 73814 | consumed samples: 12303360 | consumed tokens: 25197281280 | elapsed time per iteration (s): 2.30 | learning rate: 1.585E-04 | global batch size: 512 | lm loss: 2.108950E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.135 | TFLOPs: 22.87 | +63: iteration 24040/ 73814 | consumed samples: 12308480 | consumed tokens: 25207767040 | elapsed time per iteration (s): 2.31 | learning rate: 1.585E-04 | global batch size: 512 | lm loss: 2.115636E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.412 | TFLOPs: 22.79 | +63: iteration 24050/ 73814 | consumed samples: 12313600 | consumed tokens: 25218252800 | elapsed time per iteration (s): 2.23 | learning rate: 1.585E-04 | global batch size: 512 | lm loss: 2.147178E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.851 | TFLOPs: 23.66 | +63: iteration 24060/ 73814 | consumed samples: 12318720 | consumed tokens: 25228738560 | elapsed time per iteration (s): 2.23 | learning rate: 1.584E-04 | global batch size: 512 | lm loss: 2.120731E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.676 | TFLOPs: 23.64 | +63: iteration 24070/ 73814 | consumed samples: 12323840 | consumed tokens: 25239224320 | elapsed time per iteration (s): 2.27 | learning rate: 1.584E-04 | global batch size: 512 | lm loss: 2.137996E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.947 | TFLOPs: 23.26 | +63: iteration 24080/ 73814 | consumed samples: 12328960 | consumed tokens: 25249710080 | elapsed time per iteration (s): 2.29 | learning rate: 1.584E-04 | global batch size: 512 | lm loss: 2.133118E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.124 | TFLOPs: 22.97 | +63: iteration 24090/ 73814 | consumed samples: 12334080 | consumed tokens: 25260195840 | elapsed time per iteration (s): 2.25 | learning rate: 1.583E-04 | global batch size: 512 | lm loss: 2.144154E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.926 | TFLOPs: 23.46 | +63: iteration 24100/ 73814 | consumed samples: 12339200 | consumed tokens: 25270681600 | elapsed time per iteration (s): 2.25 | learning rate: 1.583E-04 | global batch size: 512 | lm loss: 2.123253E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.717 | TFLOPs: 23.44 | +63: iteration 24110/ 73814 | consumed samples: 12344320 | consumed tokens: 25281167360 | elapsed time per iteration (s): 2.23 | learning rate: 1.583E-04 | global batch size: 512 | lm loss: 2.122743E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.026 | TFLOPs: 23.68 | +63: iteration 24120/ 73814 | consumed samples: 12349440 | consumed tokens: 25291653120 | elapsed time per iteration (s): 2.22 | learning rate: 1.582E-04 | global batch size: 512 | lm loss: 2.115144E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.167 | TFLOPs: 23.69 | +63: iteration 24130/ 73814 | consumed samples: 12354560 | consumed tokens: 25302138880 | elapsed time per iteration (s): 2.23 | learning rate: 1.582E-04 | global batch size: 512 | lm loss: 2.113510E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.136 | TFLOPs: 23.59 | +63: iteration 24140/ 73814 | consumed samples: 12359680 | consumed tokens: 25312624640 | elapsed time per iteration (s): 2.25 | learning rate: 1.582E-04 | global batch size: 512 | lm loss: 2.150600E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.017 | TFLOPs: 23.47 | +63: iteration 24150/ 73814 | consumed samples: 12364800 | consumed tokens: 25323110400 | elapsed time per iteration (s): 2.25 | learning rate: 1.581E-04 | global batch size: 512 | lm loss: 2.125055E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.259 | TFLOPs: 23.40 | +63: iteration 24160/ 73814 | consumed samples: 12369920 | consumed tokens: 25333596160 | elapsed time per iteration (s): 2.23 | learning rate: 1.581E-04 | global batch size: 512 | lm loss: 2.117209E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.721 | TFLOPs: 23.65 | +63: iteration 24170/ 73814 | consumed samples: 12375040 | consumed tokens: 25344081920 | elapsed time per iteration (s): 2.26 | learning rate: 1.581E-04 | global batch size: 512 | lm loss: 2.104738E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.524 | TFLOPs: 23.32 | +63: iteration 24180/ 73814 | consumed samples: 12380160 | consumed tokens: 25354567680 | elapsed time per iteration (s): 2.24 | learning rate: 1.580E-04 | global batch size: 512 | lm loss: 2.124251E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.992 | TFLOPs: 23.57 | +63: iteration 24190/ 73814 | consumed samples: 12385280 | consumed tokens: 25365053440 | elapsed time per iteration (s): 4.36 | learning rate: 1.580E-04 | global batch size: 512 | lm loss: 2.112031E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 117.473 | TFLOPs: 12.09 | +63: iteration 24200/ 73814 | consumed samples: 12390400 | consumed tokens: 25375539200 | elapsed time per iteration (s): 2.22 | learning rate: 1.580E-04 | global batch size: 512 | lm loss: 2.129442E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.439 | TFLOPs: 23.72 | +63: iteration 24210/ 73814 | consumed samples: 12395520 | consumed tokens: 25386024960 | elapsed time per iteration (s): 2.26 | learning rate: 1.579E-04 | global batch size: 512 | lm loss: 2.138474E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.009 | TFLOPs: 23.37 | +63: iteration 24220/ 73814 | consumed samples: 12400640 | consumed tokens: 25396510720 | elapsed time per iteration (s): 2.26 | learning rate: 1.579E-04 | global batch size: 512 | lm loss: 2.133654E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.624 | TFLOPs: 23.33 | +63: iteration 24230/ 73814 | consumed samples: 12405760 | consumed tokens: 25406996480 | elapsed time per iteration (s): 2.23 | learning rate: 1.579E-04 | global batch size: 512 | lm loss: 2.111572E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.100 | TFLOPs: 23.58 | +63: iteration 24240/ 73814 | consumed samples: 12410880 | consumed tokens: 25417482240 | elapsed time per iteration (s): 2.26 | learning rate: 1.578E-04 | global batch size: 512 | lm loss: 2.150537E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.302 | TFLOPs: 23.30 | +63: iteration 24250/ 73814 | consumed samples: 12416000 | consumed tokens: 25427968000 | elapsed time per iteration (s): 2.23 | learning rate: 1.578E-04 | global batch size: 512 | lm loss: 2.117002E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.928 | TFLOPs: 23.67 | +63: iteration 24260/ 73814 | consumed samples: 12421120 | consumed tokens: 25438453760 | elapsed time per iteration (s): 2.23 | learning rate: 1.578E-04 | global batch size: 512 | lm loss: 2.141878E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.207 | TFLOPs: 23.60 | +63: iteration 24270/ 73814 | consumed samples: 12426240 | consumed tokens: 25448939520 | elapsed time per iteration (s): 2.23 | learning rate: 1.577E-04 | global batch size: 512 | lm loss: 2.125115E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.635 | TFLOPs: 23.64 | +63: iteration 24280/ 73814 | consumed samples: 12431360 | consumed tokens: 25459425280 | elapsed time per iteration (s): 2.24 | learning rate: 1.577E-04 | global batch size: 512 | lm loss: 2.127551E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.497 | TFLOPs: 23.52 | +63: iteration 24290/ 73814 | consumed samples: 12436480 | consumed tokens: 25469911040 | elapsed time per iteration (s): 2.23 | learning rate: 1.577E-04 | global batch size: 512 | lm loss: 2.146133E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.406 | TFLOPs: 23.62 | +63: iteration 24300/ 73814 | consumed samples: 12441600 | consumed tokens: 25480396800 | elapsed time per iteration (s): 2.23 | learning rate: 1.576E-04 | global batch size: 512 | lm loss: 2.117399E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.569 | TFLOPs: 23.63 | +63: iteration 24310/ 73814 | consumed samples: 12446720 | consumed tokens: 25490882560 | elapsed time per iteration (s): 2.25 | learning rate: 1.576E-04 | global batch size: 512 | lm loss: 2.105838E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.759 | TFLOPs: 23.45 | +63: iteration 24320/ 73814 | consumed samples: 12451840 | consumed tokens: 25501368320 | elapsed time per iteration (s): 2.24 | learning rate: 1.576E-04 | global batch size: 512 | lm loss: 2.148779E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.207 | TFLOPs: 23.49 | +63: iteration 24330/ 73814 | consumed samples: 12456960 | consumed tokens: 25511854080 | elapsed time per iteration (s): 2.24 | learning rate: 1.575E-04 | global batch size: 512 | lm loss: 2.144521E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.423 | TFLOPs: 23.52 | +63: iteration 24340/ 73814 | consumed samples: 12462080 | consumed tokens: 25522339840 | elapsed time per iteration (s): 2.23 | learning rate: 1.575E-04 | global batch size: 512 | lm loss: 2.123911E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.518 | TFLOPs: 23.63 | +63: iteration 24350/ 73814 | consumed samples: 12467200 | consumed tokens: 25532825600 | elapsed time per iteration (s): 2.23 | learning rate: 1.575E-04 | global batch size: 512 | lm loss: 2.098087E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.078 | TFLOPs: 23.69 | +63: iteration 24360/ 73814 | consumed samples: 12472320 | consumed tokens: 25543311360 | elapsed time per iteration (s): 2.23 | learning rate: 1.574E-04 | global batch size: 512 | lm loss: 2.107344E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.787 | TFLOPs: 23.66 | +63: iteration 24370/ 73814 | consumed samples: 12477440 | consumed tokens: 25553797120 | elapsed time per iteration (s): 2.25 | learning rate: 1.574E-04 | global batch size: 512 | lm loss: 2.104422E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.462 | TFLOPs: 23.42 | +63: iteration 24380/ 73814 | consumed samples: 12482560 | consumed tokens: 25564282880 | elapsed time per iteration (s): 2.22 | learning rate: 1.574E-04 | global batch size: 512 | lm loss: 2.088928E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.333 | TFLOPs: 23.71 | +63: iteration 24390/ 73814 | consumed samples: 12487680 | consumed tokens: 25574768640 | elapsed time per iteration (s): 2.23 | learning rate: 1.573E-04 | global batch size: 512 | lm loss: 2.136722E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.667 | TFLOPs: 23.64 | +63: iteration 24400/ 73814 | consumed samples: 12492800 | consumed tokens: 25585254400 | elapsed time per iteration (s): 2.25 | learning rate: 1.573E-04 | global batch size: 512 | lm loss: 2.105279E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.765 | TFLOPs: 23.45 | +63: iteration 24410/ 73814 | consumed samples: 12497920 | consumed tokens: 25595740160 | elapsed time per iteration (s): 2.23 | learning rate: 1.573E-04 | global batch size: 512 | lm loss: 2.117169E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.649 | TFLOPs: 23.64 | +63: iteration 24420/ 73814 | consumed samples: 12503040 | consumed tokens: 25606225920 | elapsed time per iteration (s): 2.24 | learning rate: 1.572E-04 | global batch size: 512 | lm loss: 2.151973E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.514 | TFLOPs: 23.52 | +63: iteration 24430/ 73814 | consumed samples: 12508160 | consumed tokens: 25616711680 | elapsed time per iteration (s): 2.23 | learning rate: 1.572E-04 | global batch size: 512 | lm loss: 2.117623E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.589 | TFLOPs: 23.64 | +63: iteration 24440/ 73814 | consumed samples: 12513280 | consumed tokens: 25627197440 | elapsed time per iteration (s): 2.29 | learning rate: 1.572E-04 | global batch size: 512 | lm loss: 2.109112E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.040 | TFLOPs: 23.06 | +63: iteration 24450/ 73814 | consumed samples: 12518400 | consumed tokens: 25637683200 | elapsed time per iteration (s): 2.23 | learning rate: 1.571E-04 | global batch size: 512 | lm loss: 2.115492E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.254 | TFLOPs: 23.60 | +63: iteration 24460/ 73814 | consumed samples: 12523520 | consumed tokens: 25648168960 | elapsed time per iteration (s): 2.25 | learning rate: 1.571E-04 | global batch size: 512 | lm loss: 2.100542E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.779 | TFLOPs: 23.45 | +63: iteration 24470/ 73814 | consumed samples: 12528640 | consumed tokens: 25658654720 | elapsed time per iteration (s): 2.26 | learning rate: 1.571E-04 | global batch size: 512 | lm loss: 2.120052E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.992 | TFLOPs: 23.37 | +63: iteration 24480/ 73814 | consumed samples: 12533760 | consumed tokens: 25669140480 | elapsed time per iteration (s): 2.33 | learning rate: 1.571E-04 | global batch size: 512 | lm loss: 2.111908E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.388 | TFLOPs: 22.58 | +63: iteration 24490/ 73814 | consumed samples: 12538880 | consumed tokens: 25679626240 | elapsed time per iteration (s): 2.24 | learning rate: 1.570E-04 | global batch size: 512 | lm loss: 2.091244E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.767 | TFLOPs: 23.55 | +63: iteration 24500/ 73814 | consumed samples: 12544000 | consumed tokens: 25690112000 | elapsed time per iteration (s): 2.25 | learning rate: 1.570E-04 | global batch size: 512 | lm loss: 2.137162E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.886 | TFLOPs: 23.46 | +63: iteration 24510/ 73814 | consumed samples: 12549120 | consumed tokens: 25700597760 | elapsed time per iteration (s): 2.24 | learning rate: 1.570E-04 | global batch size: 512 | lm loss: 2.117679E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.847 | TFLOPs: 23.56 | +63: iteration 24520/ 73814 | consumed samples: 12554240 | consumed tokens: 25711083520 | elapsed time per iteration (s): 2.22 | learning rate: 1.569E-04 | global batch size: 512 | lm loss: 2.112038E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.290 | TFLOPs: 23.71 | +63: iteration 24530/ 73814 | consumed samples: 12559360 | consumed tokens: 25721569280 | elapsed time per iteration (s): 2.25 | learning rate: 1.569E-04 | global batch size: 512 | lm loss: 2.135894E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.038 | TFLOPs: 23.48 | +63: iteration 24540/ 73814 | consumed samples: 12564480 | consumed tokens: 25732055040 | elapsed time per iteration (s): 2.23 | learning rate: 1.569E-04 | global batch size: 512 | lm loss: 2.117431E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.551 | TFLOPs: 23.63 | +63: iteration 24550/ 73814 | consumed samples: 12569600 | consumed tokens: 25742540800 | elapsed time per iteration (s): 2.26 | learning rate: 1.568E-04 | global batch size: 512 | lm loss: 2.123814E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.932 | TFLOPs: 23.36 | +63: iteration 24560/ 73814 | consumed samples: 12574720 | consumed tokens: 25753026560 | elapsed time per iteration (s): 2.24 | learning rate: 1.568E-04 | global batch size: 512 | lm loss: 2.142411E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.817 | TFLOPs: 23.56 | +63: iteration 24570/ 73814 | consumed samples: 12579840 | consumed tokens: 25763512320 | elapsed time per iteration (s): 2.24 | learning rate: 1.568E-04 | global batch size: 512 | lm loss: 2.127033E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.626 | TFLOPs: 23.54 | +63: iteration 24580/ 73814 | consumed samples: 12584960 | consumed tokens: 25773998080 | elapsed time per iteration (s): 2.23 | learning rate: 1.567E-04 | global batch size: 512 | lm loss: 2.123444E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.674 | TFLOPs: 23.64 | +63: iteration 24590/ 73814 | consumed samples: 12590080 | consumed tokens: 25784483840 | elapsed time per iteration (s): 2.23 | learning rate: 1.567E-04 | global batch size: 512 | lm loss: 2.122458E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.022 | TFLOPs: 23.68 | +63: iteration 24600/ 73814 | consumed samples: 12595200 | consumed tokens: 25794969600 | elapsed time per iteration (s): 2.23 | learning rate: 1.567E-04 | global batch size: 512 | lm loss: 2.135982E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.552 | TFLOPs: 23.63 | +63: iteration 24610/ 73814 | consumed samples: 12600320 | consumed tokens: 25805455360 | elapsed time per iteration (s): 2.49 | learning rate: 1.566E-04 | global batch size: 512 | lm loss: 2.112626E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.730 | TFLOPs: 21.18 | +63: iteration 24620/ 73814 | consumed samples: 12605440 | consumed tokens: 25815941120 | elapsed time per iteration (s): 2.23 | learning rate: 1.566E-04 | global batch size: 512 | lm loss: 2.133453E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.296 | TFLOPs: 23.60 | +63: iteration 24630/ 73814 | consumed samples: 12610560 | consumed tokens: 25826426880 | elapsed time per iteration (s): 2.26 | learning rate: 1.566E-04 | global batch size: 512 | lm loss: 2.127607E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.441 | TFLOPs: 23.31 | +63: iteration 24640/ 73814 | consumed samples: 12615680 | consumed tokens: 25836912640 | elapsed time per iteration (s): 2.23 | learning rate: 1.565E-04 | global batch size: 512 | lm loss: 2.129609E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.070 | TFLOPs: 23.68 | +63: iteration 24650/ 73814 | consumed samples: 12620800 | consumed tokens: 25847398400 | elapsed time per iteration (s): 2.22 | learning rate: 1.565E-04 | global batch size: 512 | lm loss: 2.123710E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.121 | TFLOPs: 23.69 | +63: iteration 24660/ 73814 | consumed samples: 12625920 | consumed tokens: 25857884160 | elapsed time per iteration (s): 2.30 | learning rate: 1.565E-04 | global batch size: 512 | lm loss: 2.107428E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.760 | TFLOPs: 22.93 | +63: iteration 24670/ 73814 | consumed samples: 12631040 | consumed tokens: 25868369920 | elapsed time per iteration (s): 2.23 | learning rate: 1.564E-04 | global batch size: 512 | lm loss: 2.128546E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.959 | TFLOPs: 23.67 | +63: iteration 24680/ 73814 | consumed samples: 12636160 | consumed tokens: 25878855680 | elapsed time per iteration (s): 2.30 | learning rate: 1.564E-04 | global batch size: 512 | lm loss: 2.114993E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.291 | TFLOPs: 22.88 | +63: iteration 24690/ 73814 | consumed samples: 12641280 | consumed tokens: 25889341440 | elapsed time per iteration (s): 2.25 | learning rate: 1.564E-04 | global batch size: 512 | lm loss: 2.129648E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.935 | TFLOPs: 23.46 | +63: iteration 24700/ 73814 | consumed samples: 12646400 | consumed tokens: 25899827200 | elapsed time per iteration (s): 2.24 | learning rate: 1.563E-04 | global batch size: 512 | lm loss: 2.115692E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.670 | TFLOPs: 23.54 | +63: iteration 24710/ 73814 | consumed samples: 12651520 | consumed tokens: 25910312960 | elapsed time per iteration (s): 2.23 | learning rate: 1.563E-04 | global batch size: 512 | lm loss: 2.111346E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.276 | TFLOPs: 23.60 | +63: iteration 24720/ 73814 | consumed samples: 12656640 | consumed tokens: 25920798720 | elapsed time per iteration (s): 2.24 | learning rate: 1.563E-04 | global batch size: 512 | lm loss: 2.119602E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.701 | TFLOPs: 23.54 | +63: iteration 24730/ 73814 | consumed samples: 12661760 | consumed tokens: 25931284480 | elapsed time per iteration (s): 2.23 | learning rate: 1.562E-04 | global batch size: 512 | lm loss: 2.102851E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.016 | TFLOPs: 23.68 | +63: iteration 24740/ 73814 | consumed samples: 12666880 | consumed tokens: 25941770240 | elapsed time per iteration (s): 2.23 | learning rate: 1.562E-04 | global batch size: 512 | lm loss: 2.090354E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.923 | TFLOPs: 23.67 | +63: iteration 24750/ 73814 | consumed samples: 12672000 | consumed tokens: 25952256000 | elapsed time per iteration (s): 2.24 | learning rate: 1.562E-04 | global batch size: 512 | lm loss: 2.106293E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.684 | TFLOPs: 23.54 | +63: iteration 24760/ 73814 | consumed samples: 12677120 | consumed tokens: 25962741760 | elapsed time per iteration (s): 2.28 | learning rate: 1.561E-04 | global batch size: 512 | lm loss: 2.124252E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.872 | TFLOPs: 23.15 | +63: iteration 24770/ 73814 | consumed samples: 12682240 | consumed tokens: 25973227520 | elapsed time per iteration (s): 2.23 | learning rate: 1.561E-04 | global batch size: 512 | lm loss: 2.112288E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.684 | TFLOPs: 23.64 | +63: iteration 24780/ 73814 | consumed samples: 12687360 | consumed tokens: 25983713280 | elapsed time per iteration (s): 2.22 | learning rate: 1.561E-04 | global batch size: 512 | lm loss: 2.121990E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.144 | TFLOPs: 23.69 | +63: iteration 24790/ 73814 | consumed samples: 12692480 | consumed tokens: 25994199040 | elapsed time per iteration (s): 2.23 | learning rate: 1.560E-04 | global batch size: 512 | lm loss: 2.112947E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.932 | TFLOPs: 23.67 | +63: iteration 24800/ 73814 | consumed samples: 12697600 | consumed tokens: 26004684800 | elapsed time per iteration (s): 2.23 | learning rate: 1.560E-04 | global batch size: 512 | lm loss: 2.129108E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.024 | TFLOPs: 23.68 | +63: iteration 24810/ 73814 | consumed samples: 12702720 | consumed tokens: 26015170560 | elapsed time per iteration (s): 2.25 | learning rate: 1.560E-04 | global batch size: 512 | lm loss: 2.124159E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.834 | TFLOPs: 23.45 | +63: iteration 24820/ 73814 | consumed samples: 12707840 | consumed tokens: 26025656320 | elapsed time per iteration (s): 2.23 | learning rate: 1.559E-04 | global batch size: 512 | lm loss: 2.135523E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.855 | TFLOPs: 23.66 | +63: iteration 24830/ 73814 | consumed samples: 12712960 | consumed tokens: 26036142080 | elapsed time per iteration (s): 2.24 | learning rate: 1.559E-04 | global batch size: 512 | lm loss: 2.103025E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.104 | TFLOPs: 23.48 | +63: iteration 24840/ 73814 | consumed samples: 12718080 | consumed tokens: 26046627840 | elapsed time per iteration (s): 2.23 | learning rate: 1.559E-04 | global batch size: 512 | lm loss: 2.106935E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.309 | TFLOPs: 23.61 | +63: iteration 24850/ 73814 | consumed samples: 12723200 | consumed tokens: 26057113600 | elapsed time per iteration (s): 2.25 | learning rate: 1.558E-04 | global batch size: 512 | lm loss: 2.115502E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.832 | TFLOPs: 23.45 | +63: iteration 24860/ 73814 | consumed samples: 12728320 | consumed tokens: 26067599360 | elapsed time per iteration (s): 2.23 | learning rate: 1.558E-04 | global batch size: 512 | lm loss: 2.096416E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.864 | TFLOPs: 23.66 | +63: iteration 24870/ 73814 | consumed samples: 12733440 | consumed tokens: 26078085120 | elapsed time per iteration (s): 2.23 | learning rate: 1.558E-04 | global batch size: 512 | lm loss: 2.119752E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.103 | TFLOPs: 23.59 | +63: iteration 24880/ 73814 | consumed samples: 12738560 | consumed tokens: 26088570880 | elapsed time per iteration (s): 2.51 | learning rate: 1.557E-04 | global batch size: 512 | lm loss: 2.136691E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 204.201 | TFLOPs: 21.02 | +63: iteration 24890/ 73814 | consumed samples: 12743680 | consumed tokens: 26099056640 | elapsed time per iteration (s): 2.23 | learning rate: 1.557E-04 | global batch size: 512 | lm loss: 2.105421E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.288 | TFLOPs: 23.60 | +63: iteration 24900/ 73814 | consumed samples: 12748800 | consumed tokens: 26109542400 | elapsed time per iteration (s): 2.23 | learning rate: 1.557E-04 | global batch size: 512 | lm loss: 2.106412E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.675 | TFLOPs: 23.64 | +63: iteration 24910/ 73814 | consumed samples: 12753920 | consumed tokens: 26120028160 | elapsed time per iteration (s): 2.24 | learning rate: 1.556E-04 | global batch size: 512 | lm loss: 3.749245E+00 | grad norm: 19.736 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.871 | TFLOPs: 23.56 | +63: iteration 24920/ 73814 | consumed samples: 12759040 | consumed tokens: 26130513920 | elapsed time per iteration (s): 2.25 | learning rate: 1.556E-04 | global batch size: 512 | lm loss: 4.908496E+00 | grad norm: 9.818 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.477 | TFLOPs: 23.42 | +63: iteration 24930/ 73814 | consumed samples: 12764160 | consumed tokens: 26140999680 | elapsed time per iteration (s): 2.25 | learning rate: 1.556E-04 | global batch size: 512 | lm loss: 3.193615E+00 | grad norm: 3.002 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.231 | TFLOPs: 23.39 | +63: iteration 24940/ 73814 | consumed samples: 12769280 | consumed tokens: 26151485440 | elapsed time per iteration (s): 2.24 | learning rate: 1.555E-04 | global batch size: 512 | lm loss: 2.551385E+00 | grad norm: 1.000 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.356 | TFLOPs: 23.51 | +63: iteration 24950/ 73814 | consumed samples: 12774400 | consumed tokens: 26161971200 | elapsed time per iteration (s): 2.53 | learning rate: 1.555E-04 | global batch size: 512 | lm loss: 2.286480E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.703 | TFLOPs: 20.87 | +63: iteration 24960/ 73814 | consumed samples: 12779520 | consumed tokens: 26172456960 | elapsed time per iteration (s): 2.24 | learning rate: 1.555E-04 | global batch size: 512 | lm loss: 2.204565E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.721 | TFLOPs: 23.55 | +63: iteration 24970/ 73814 | consumed samples: 12784640 | consumed tokens: 26182942720 | elapsed time per iteration (s): 2.22 | learning rate: 1.554E-04 | global batch size: 512 | lm loss: 2.188138E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.177 | TFLOPs: 23.70 | +63: iteration 24980/ 73814 | consumed samples: 12789760 | consumed tokens: 26193428480 | elapsed time per iteration (s): 2.23 | learning rate: 1.554E-04 | global batch size: 512 | lm loss: 2.167602E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.590 | TFLOPs: 23.64 | +63: iteration 24990/ 73814 | consumed samples: 12794880 | consumed tokens: 26203914240 | elapsed time per iteration (s): 2.23 | learning rate: 1.554E-04 | global batch size: 512 | lm loss: 2.135188E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.470 | TFLOPs: 23.62 | +63: iteration 25000/ 73814 | consumed samples: 12800000 | consumed tokens: 26214400000 | elapsed time per iteration (s): 2.25 | learning rate: 1.553E-04 | global batch size: 512 | lm loss: 2.139527E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.692 | TFLOPs: 23.44 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 25000 | lm loss value: 2.116723E+00 | lm loss PPL: 8.303880E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 25010/ 73814 | consumed samples: 12805120 | consumed tokens: 26224885760 | elapsed time per iteration (s): 2.31 | learning rate: 1.553E-04 | global batch size: 512 | lm loss: 2.156100E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.216 | TFLOPs: 22.77 | +63: iteration 25020/ 73814 | consumed samples: 12810240 | consumed tokens: 26235371520 | elapsed time per iteration (s): 2.22 | learning rate: 1.553E-04 | global batch size: 512 | lm loss: 2.114540E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.321 | TFLOPs: 23.71 | +63: iteration 25030/ 73814 | consumed samples: 12815360 | consumed tokens: 26245857280 | elapsed time per iteration (s): 2.26 | learning rate: 1.552E-04 | global batch size: 512 | lm loss: 2.144834E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.756 | TFLOPs: 23.34 | +63: iteration 25040/ 73814 | consumed samples: 12820480 | consumed tokens: 26256343040 | elapsed time per iteration (s): 2.23 | learning rate: 1.552E-04 | global batch size: 512 | lm loss: 2.143022E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.817 | TFLOPs: 23.66 | +63: iteration 25050/ 73814 | consumed samples: 12825600 | consumed tokens: 26266828800 | elapsed time per iteration (s): 2.22 | learning rate: 1.552E-04 | global batch size: 512 | lm loss: 2.133625E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.158 | TFLOPs: 23.69 | +63: iteration 25060/ 73814 | consumed samples: 12830720 | consumed tokens: 26277314560 | elapsed time per iteration (s): 2.25 | learning rate: 1.551E-04 | global batch size: 512 | lm loss: 2.133835E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.516 | TFLOPs: 23.42 | +63: iteration 25070/ 73814 | consumed samples: 12835840 | consumed tokens: 26287800320 | elapsed time per iteration (s): 2.23 | learning rate: 1.551E-04 | global batch size: 512 | lm loss: 2.106315E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.088 | TFLOPs: 23.69 | +63: iteration 25080/ 73814 | consumed samples: 12840960 | consumed tokens: 26298286080 | elapsed time per iteration (s): 2.30 | learning rate: 1.551E-04 | global batch size: 512 | lm loss: 2.141257E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.029 | TFLOPs: 22.96 | +63: iteration 25090/ 73814 | consumed samples: 12846080 | consumed tokens: 26308771840 | elapsed time per iteration (s): 2.40 | learning rate: 1.550E-04 | global batch size: 512 | lm loss: 2.152523E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.374 | TFLOPs: 21.97 | +63: iteration 25100/ 73814 | consumed samples: 12851200 | consumed tokens: 26319257600 | elapsed time per iteration (s): 2.24 | learning rate: 1.550E-04 | global batch size: 512 | lm loss: 2.122449E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.619 | TFLOPs: 23.54 | +63: iteration 25110/ 73814 | consumed samples: 12856320 | consumed tokens: 26329743360 | elapsed time per iteration (s): 2.24 | learning rate: 1.550E-04 | global batch size: 512 | lm loss: 2.113548E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.213 | TFLOPs: 23.49 | +63: iteration 25120/ 73814 | consumed samples: 12861440 | consumed tokens: 26340229120 | elapsed time per iteration (s): 2.24 | learning rate: 1.549E-04 | global batch size: 512 | lm loss: 2.128293E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.097 | TFLOPs: 23.48 | +63: iteration 25130/ 73814 | consumed samples: 12866560 | consumed tokens: 26350714880 | elapsed time per iteration (s): 2.24 | learning rate: 1.549E-04 | global batch size: 512 | lm loss: 2.136176E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.238 | TFLOPs: 23.50 | +63: iteration 25140/ 73814 | consumed samples: 12871680 | consumed tokens: 26361200640 | elapsed time per iteration (s): 2.25 | learning rate: 1.549E-04 | global batch size: 512 | lm loss: 2.127077E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.873 | TFLOPs: 23.46 | +63: iteration 25150/ 73814 | consumed samples: 12876800 | consumed tokens: 26371686400 | elapsed time per iteration (s): 2.24 | learning rate: 1.548E-04 | global batch size: 512 | lm loss: 2.117810E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.423 | TFLOPs: 23.52 | +63: iteration 25160/ 73814 | consumed samples: 12881920 | consumed tokens: 26382172160 | elapsed time per iteration (s): 2.23 | learning rate: 1.548E-04 | global batch size: 512 | lm loss: 2.146640E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.941 | TFLOPs: 23.67 | +63: iteration 25170/ 73814 | consumed samples: 12887040 | consumed tokens: 26392657920 | elapsed time per iteration (s): 2.36 | learning rate: 1.548E-04 | global batch size: 512 | lm loss: 2.113665E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.936 | TFLOPs: 22.33 | +63: iteration 25180/ 73814 | consumed samples: 12892160 | consumed tokens: 26403143680 | elapsed time per iteration (s): 2.24 | learning rate: 1.547E-04 | global batch size: 512 | lm loss: 2.119900E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.011 | TFLOPs: 23.58 | +63: iteration 25190/ 73814 | consumed samples: 12897280 | consumed tokens: 26413629440 | elapsed time per iteration (s): 2.24 | learning rate: 1.547E-04 | global batch size: 512 | lm loss: 2.122824E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.330 | TFLOPs: 23.51 | +63: iteration 25200/ 73814 | consumed samples: 12902400 | consumed tokens: 26424115200 | elapsed time per iteration (s): 2.26 | learning rate: 1.547E-04 | global batch size: 512 | lm loss: 2.107882E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.197 | TFLOPs: 23.29 | +63: iteration 25210/ 73814 | consumed samples: 12907520 | consumed tokens: 26434600960 | elapsed time per iteration (s): 2.26 | learning rate: 1.546E-04 | global batch size: 512 | lm loss: 2.135880E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.874 | TFLOPs: 23.36 | +63: iteration 25220/ 73814 | consumed samples: 12912640 | consumed tokens: 26445086720 | elapsed time per iteration (s): 2.25 | learning rate: 1.546E-04 | global batch size: 512 | lm loss: 2.117094E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.878 | TFLOPs: 23.46 | +63: iteration 25230/ 73814 | consumed samples: 12917760 | consumed tokens: 26455572480 | elapsed time per iteration (s): 2.22 | learning rate: 1.546E-04 | global batch size: 512 | lm loss: 2.136969E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.380 | TFLOPs: 23.72 | +63: iteration 25240/ 73814 | consumed samples: 12922880 | consumed tokens: 26466058240 | elapsed time per iteration (s): 2.22 | learning rate: 1.545E-04 | global batch size: 512 | lm loss: 2.112125E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.126 | TFLOPs: 23.69 | +63: iteration 25250/ 73814 | consumed samples: 12928000 | consumed tokens: 26476544000 | elapsed time per iteration (s): 2.34 | learning rate: 1.545E-04 | global batch size: 512 | lm loss: 2.115517E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.654 | TFLOPs: 22.51 | +63: iteration 25260/ 73814 | consumed samples: 12933120 | consumed tokens: 26487029760 | elapsed time per iteration (s): 2.24 | learning rate: 1.545E-04 | global batch size: 512 | lm loss: 2.127362E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.075 | TFLOPs: 23.58 | +63: iteration 25270/ 73814 | consumed samples: 12938240 | consumed tokens: 26497515520 | elapsed time per iteration (s): 2.25 | learning rate: 1.544E-04 | global batch size: 512 | lm loss: 2.150530E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.513 | TFLOPs: 23.42 | +63: iteration 25280/ 73814 | consumed samples: 12943360 | consumed tokens: 26508001280 | elapsed time per iteration (s): 2.27 | learning rate: 1.544E-04 | global batch size: 512 | lm loss: 2.113215E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.587 | TFLOPs: 23.22 | +63: iteration 25290/ 73814 | consumed samples: 12948480 | consumed tokens: 26518487040 | elapsed time per iteration (s): 2.25 | learning rate: 1.544E-04 | global batch size: 512 | lm loss: 2.119104E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.899 | TFLOPs: 23.46 | +63: iteration 25300/ 73814 | consumed samples: 12953600 | consumed tokens: 26528972800 | elapsed time per iteration (s): 2.25 | learning rate: 1.543E-04 | global batch size: 512 | lm loss: 2.110740E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.415 | TFLOPs: 23.41 | +63: iteration 25310/ 73814 | consumed samples: 12958720 | consumed tokens: 26539458560 | elapsed time per iteration (s): 2.23 | learning rate: 1.543E-04 | global batch size: 512 | lm loss: 2.123669E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.949 | TFLOPs: 23.67 | +63: iteration 25320/ 73814 | consumed samples: 12963840 | consumed tokens: 26549944320 | elapsed time per iteration (s): 2.23 | learning rate: 1.543E-04 | global batch size: 512 | lm loss: 2.116448E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.258 | TFLOPs: 23.60 | +63: iteration 25330/ 73814 | consumed samples: 12968960 | consumed tokens: 26560430080 | elapsed time per iteration (s): 2.24 | learning rate: 1.542E-04 | global batch size: 512 | lm loss: 2.107257E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.343 | TFLOPs: 23.51 | +63: iteration 25340/ 73814 | consumed samples: 12974080 | consumed tokens: 26570915840 | elapsed time per iteration (s): 2.25 | learning rate: 1.542E-04 | global batch size: 512 | lm loss: 2.102364E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.572 | TFLOPs: 23.43 | +63: iteration 25350/ 73814 | consumed samples: 12979200 | consumed tokens: 26581401600 | elapsed time per iteration (s): 2.23 | learning rate: 1.541E-04 | global batch size: 512 | lm loss: 2.110460E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.324 | TFLOPs: 23.61 | +63: iteration 25360/ 73814 | consumed samples: 12984320 | consumed tokens: 26591887360 | elapsed time per iteration (s): 2.24 | learning rate: 1.541E-04 | global batch size: 512 | lm loss: 2.130358E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.378 | TFLOPs: 23.51 | +63: iteration 25370/ 73814 | consumed samples: 12989440 | consumed tokens: 26602373120 | elapsed time per iteration (s): 2.24 | learning rate: 1.541E-04 | global batch size: 512 | lm loss: 2.107767E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.945 | TFLOPs: 23.57 | +63: iteration 25380/ 73814 | consumed samples: 12994560 | consumed tokens: 26612858880 | elapsed time per iteration (s): 2.23 | learning rate: 1.540E-04 | global batch size: 512 | lm loss: 2.138131E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.008 | TFLOPs: 23.68 | +63: iteration 25390/ 73814 | consumed samples: 12999680 | consumed tokens: 26623344640 | elapsed time per iteration (s): 2.23 | learning rate: 1.540E-04 | global batch size: 512 | lm loss: 2.133768E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.238 | TFLOPs: 23.60 | +63: iteration 25400/ 73814 | consumed samples: 13004800 | consumed tokens: 26633830400 | elapsed time per iteration (s): 2.23 | learning rate: 1.540E-04 | global batch size: 512 | lm loss: 2.126443E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.896 | TFLOPs: 23.67 | +63: iteration 25410/ 73814 | consumed samples: 13009920 | consumed tokens: 26644316160 | elapsed time per iteration (s): 2.28 | learning rate: 1.539E-04 | global batch size: 512 | lm loss: 2.121904E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.071 | TFLOPs: 23.07 | +63: iteration 25420/ 73814 | consumed samples: 13015040 | consumed tokens: 26654801920 | elapsed time per iteration (s): 2.26 | learning rate: 1.539E-04 | global batch size: 512 | lm loss: 2.116725E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.563 | TFLOPs: 23.32 | +63: iteration 25430/ 73814 | consumed samples: 13020160 | consumed tokens: 26665287680 | elapsed time per iteration (s): 2.43 | learning rate: 1.539E-04 | global batch size: 512 | lm loss: 2.122519E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.924 | TFLOPs: 21.71 | +63: iteration 25440/ 73814 | consumed samples: 13025280 | consumed tokens: 26675773440 | elapsed time per iteration (s): 2.47 | learning rate: 1.538E-04 | global batch size: 512 | lm loss: 2.114436E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 207.125 | TFLOPs: 21.32 | +63: iteration 25450/ 73814 | consumed samples: 13030400 | consumed tokens: 26686259200 | elapsed time per iteration (s): 2.24 | learning rate: 1.538E-04 | global batch size: 512 | lm loss: 2.139503E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.511 | TFLOPs: 23.52 | +63: iteration 25460/ 73814 | consumed samples: 13035520 | consumed tokens: 26696744960 | elapsed time per iteration (s): 2.24 | learning rate: 1.538E-04 | global batch size: 512 | lm loss: 2.102200E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.050 | TFLOPs: 23.58 | +63: iteration 25470/ 73814 | consumed samples: 13040640 | consumed tokens: 26707230720 | elapsed time per iteration (s): 2.54 | learning rate: 1.537E-04 | global batch size: 512 | lm loss: 2.108533E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.786 | TFLOPs: 20.77 | +63: iteration 25480/ 73814 | consumed samples: 13045760 | consumed tokens: 26717716480 | elapsed time per iteration (s): 2.62 | learning rate: 1.537E-04 | global batch size: 512 | lm loss: 2.109678E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 195.622 | TFLOPs: 20.14 | +63: iteration 25490/ 73814 | consumed samples: 13050880 | consumed tokens: 26728202240 | elapsed time per iteration (s): 2.62 | learning rate: 1.537E-04 | global batch size: 512 | lm loss: 2.112702E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 195.066 | TFLOPs: 20.08 | +63: iteration 25500/ 73814 | consumed samples: 13056000 | consumed tokens: 26738688000 | elapsed time per iteration (s): 2.23 | learning rate: 1.536E-04 | global batch size: 512 | lm loss: 2.124987E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.727 | TFLOPs: 23.65 | +63: iteration 25510/ 73814 | consumed samples: 13061120 | consumed tokens: 26749173760 | elapsed time per iteration (s): 2.38 | learning rate: 1.536E-04 | global batch size: 512 | lm loss: 2.129186E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.535 | TFLOPs: 22.19 | +63: iteration 25520/ 73814 | consumed samples: 13066240 | consumed tokens: 26759659520 | elapsed time per iteration (s): 2.50 | learning rate: 1.536E-04 | global batch size: 512 | lm loss: 2.101489E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 204.961 | TFLOPs: 21.10 | +63: iteration 25530/ 73814 | consumed samples: 13071360 | consumed tokens: 26770145280 | elapsed time per iteration (s): 2.28 | learning rate: 1.535E-04 | global batch size: 512 | lm loss: 2.126423E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.555 | TFLOPs: 23.12 | +63: iteration 25540/ 73814 | consumed samples: 13076480 | consumed tokens: 26780631040 | elapsed time per iteration (s): 2.24 | learning rate: 1.535E-04 | global batch size: 512 | lm loss: 2.110649E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.301 | TFLOPs: 23.50 | +63: iteration 25550/ 73814 | consumed samples: 13081600 | consumed tokens: 26791116800 | elapsed time per iteration (s): 2.22 | learning rate: 1.535E-04 | global batch size: 512 | lm loss: 2.119221E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.119 | TFLOPs: 23.69 | +63: iteration 25560/ 73814 | consumed samples: 13086720 | consumed tokens: 26801602560 | elapsed time per iteration (s): 2.23 | learning rate: 1.534E-04 | global batch size: 512 | lm loss: 2.111975E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.787 | TFLOPs: 23.66 | +63: iteration 25570/ 73814 | consumed samples: 13091840 | consumed tokens: 26812088320 | elapsed time per iteration (s): 2.24 | learning rate: 1.534E-04 | global batch size: 512 | lm loss: 2.091606E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.359 | TFLOPs: 23.51 | +63: iteration 25580/ 73814 | consumed samples: 13096960 | consumed tokens: 26822574080 | elapsed time per iteration (s): 2.30 | learning rate: 1.534E-04 | global batch size: 512 | lm loss: 2.122168E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.371 | TFLOPs: 22.89 | +63: iteration 25590/ 73814 | consumed samples: 13102080 | consumed tokens: 26833059840 | elapsed time per iteration (s): 2.24 | learning rate: 1.533E-04 | global batch size: 512 | lm loss: 2.109468E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.256 | TFLOPs: 23.50 | +63: iteration 25600/ 73814 | consumed samples: 13107200 | consumed tokens: 26843545600 | elapsed time per iteration (s): 2.23 | learning rate: 1.533E-04 | global batch size: 512 | lm loss: 2.099472E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.337 | TFLOPs: 23.61 | +63: iteration 25610/ 73814 | consumed samples: 13112320 | consumed tokens: 26854031360 | elapsed time per iteration (s): 2.36 | learning rate: 1.533E-04 | global batch size: 512 | lm loss: 2.079674E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.206 | TFLOPs: 22.36 | +63: iteration 25620/ 73814 | consumed samples: 13117440 | consumed tokens: 26864517120 | elapsed time per iteration (s): 2.24 | learning rate: 1.532E-04 | global batch size: 512 | lm loss: 2.111634E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.624 | TFLOPs: 23.54 | +63: iteration 25630/ 73814 | consumed samples: 13122560 | consumed tokens: 26875002880 | elapsed time per iteration (s): 2.24 | learning rate: 1.532E-04 | global batch size: 512 | lm loss: 2.090632E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.836 | TFLOPs: 23.56 | +63: iteration 25640/ 73814 | consumed samples: 13127680 | consumed tokens: 26885488640 | elapsed time per iteration (s): 2.27 | learning rate: 1.532E-04 | global batch size: 512 | lm loss: 2.115437E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.490 | TFLOPs: 23.21 | +63: iteration 25650/ 73814 | consumed samples: 13132800 | consumed tokens: 26895974400 | elapsed time per iteration (s): 2.25 | learning rate: 1.531E-04 | global batch size: 512 | lm loss: 2.115276E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.953 | TFLOPs: 23.47 | +63: iteration 25660/ 73814 | consumed samples: 13137920 | consumed tokens: 26906460160 | elapsed time per iteration (s): 2.24 | learning rate: 1.531E-04 | global batch size: 512 | lm loss: 2.101712E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.120 | TFLOPs: 23.48 | +63: iteration 25670/ 73814 | consumed samples: 13143040 | consumed tokens: 26916945920 | elapsed time per iteration (s): 2.26 | learning rate: 1.531E-04 | global batch size: 512 | lm loss: 2.105233E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.469 | TFLOPs: 23.31 | +63: iteration 25680/ 73814 | consumed samples: 13148160 | consumed tokens: 26927431680 | elapsed time per iteration (s): 2.27 | learning rate: 1.530E-04 | global batch size: 512 | lm loss: 2.105260E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.640 | TFLOPs: 23.23 | +63: iteration 25690/ 73814 | consumed samples: 13153280 | consumed tokens: 26937917440 | elapsed time per iteration (s): 2.25 | learning rate: 1.530E-04 | global batch size: 512 | lm loss: 2.110471E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.848 | TFLOPs: 23.46 | +63: iteration 25700/ 73814 | consumed samples: 13158400 | consumed tokens: 26948403200 | elapsed time per iteration (s): 2.23 | learning rate: 1.530E-04 | global batch size: 512 | lm loss: 2.125997E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.276 | TFLOPs: 23.60 | +63: iteration 25710/ 73814 | consumed samples: 13163520 | consumed tokens: 26958888960 | elapsed time per iteration (s): 2.24 | learning rate: 1.529E-04 | global batch size: 512 | lm loss: 2.113656E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.882 | TFLOPs: 23.56 | +63: iteration 25720/ 73814 | consumed samples: 13168640 | consumed tokens: 26969374720 | elapsed time per iteration (s): 2.30 | learning rate: 1.529E-04 | global batch size: 512 | lm loss: 2.105491E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.161 | TFLOPs: 22.87 | +63: iteration 25730/ 73814 | consumed samples: 13173760 | consumed tokens: 26979860480 | elapsed time per iteration (s): 2.23 | learning rate: 1.529E-04 | global batch size: 512 | lm loss: 2.127836E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.661 | TFLOPs: 23.64 | +63: iteration 25740/ 73814 | consumed samples: 13178880 | consumed tokens: 26990346240 | elapsed time per iteration (s): 2.37 | learning rate: 1.528E-04 | global batch size: 512 | lm loss: 2.103403E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.210 | TFLOPs: 22.26 | +63: iteration 25750/ 73814 | consumed samples: 13184000 | consumed tokens: 27000832000 | elapsed time per iteration (s): 2.24 | learning rate: 1.528E-04 | global batch size: 512 | lm loss: 2.116471E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.160 | TFLOPs: 23.49 | +63: iteration 25760/ 73814 | consumed samples: 13189120 | consumed tokens: 27011317760 | elapsed time per iteration (s): 2.27 | learning rate: 1.528E-04 | global batch size: 512 | lm loss: 2.107942E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.937 | TFLOPs: 23.26 | +63: iteration 25770/ 73814 | consumed samples: 13194240 | consumed tokens: 27021803520 | elapsed time per iteration (s): 2.23 | learning rate: 1.527E-04 | global batch size: 512 | lm loss: 2.099609E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.083 | TFLOPs: 23.69 | +63: iteration 25780/ 73814 | consumed samples: 13199360 | consumed tokens: 27032289280 | elapsed time per iteration (s): 2.24 | learning rate: 1.527E-04 | global batch size: 512 | lm loss: 2.094444E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.841 | TFLOPs: 23.56 | +63: iteration 25790/ 73814 | consumed samples: 13204480 | consumed tokens: 27042775040 | elapsed time per iteration (s): 2.25 | learning rate: 1.527E-04 | global batch size: 512 | lm loss: 2.111733E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.344 | TFLOPs: 23.40 | +63: iteration 25800/ 73814 | consumed samples: 13209600 | consumed tokens: 27053260800 | elapsed time per iteration (s): 2.23 | learning rate: 1.526E-04 | global batch size: 512 | lm loss: 2.103914E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.034 | TFLOPs: 23.68 | +63: iteration 25810/ 73814 | consumed samples: 13214720 | consumed tokens: 27063746560 | elapsed time per iteration (s): 2.31 | learning rate: 1.526E-04 | global batch size: 512 | lm loss: 2.091852E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.435 | TFLOPs: 22.80 | +63: iteration 25820/ 73814 | consumed samples: 13219840 | consumed tokens: 27074232320 | elapsed time per iteration (s): 2.25 | learning rate: 1.526E-04 | global batch size: 512 | lm loss: 2.084658E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.717 | TFLOPs: 23.44 | +63: iteration 25830/ 73814 | consumed samples: 13224960 | consumed tokens: 27084718080 | elapsed time per iteration (s): 2.23 | learning rate: 1.525E-04 | global batch size: 512 | lm loss: 2.108236E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.613 | TFLOPs: 23.64 | +63: iteration 25840/ 73814 | consumed samples: 13230080 | consumed tokens: 27095203840 | elapsed time per iteration (s): 2.23 | learning rate: 1.525E-04 | global batch size: 512 | lm loss: 2.094159E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.920 | TFLOPs: 23.67 | +63: iteration 25850/ 73814 | consumed samples: 13235200 | consumed tokens: 27105689600 | elapsed time per iteration (s): 2.24 | learning rate: 1.525E-04 | global batch size: 512 | lm loss: 2.118045E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.440 | TFLOPs: 23.52 | +63: iteration 25860/ 73814 | consumed samples: 13240320 | consumed tokens: 27116175360 | elapsed time per iteration (s): 2.24 | learning rate: 1.524E-04 | global batch size: 512 | lm loss: 2.105796E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.754 | TFLOPs: 23.55 | +63: iteration 25870/ 73814 | consumed samples: 13245440 | consumed tokens: 27126661120 | elapsed time per iteration (s): 2.26 | learning rate: 1.524E-04 | global batch size: 512 | lm loss: 2.107909E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.067 | TFLOPs: 23.27 | +63: iteration 25880/ 73814 | consumed samples: 13250560 | consumed tokens: 27137146880 | elapsed time per iteration (s): 2.23 | learning rate: 1.524E-04 | global batch size: 512 | lm loss: 2.119444E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.848 | TFLOPs: 23.66 | +63: iteration 25890/ 73814 | consumed samples: 13255680 | consumed tokens: 27147632640 | elapsed time per iteration (s): 2.23 | learning rate: 1.523E-04 | global batch size: 512 | lm loss: 2.090603E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.986 | TFLOPs: 23.68 | +63: iteration 25900/ 73814 | consumed samples: 13260800 | consumed tokens: 27158118400 | elapsed time per iteration (s): 2.32 | learning rate: 1.523E-04 | global batch size: 512 | lm loss: 2.104458E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.012 | TFLOPs: 22.75 | +63: iteration 25910/ 73814 | consumed samples: 13265920 | consumed tokens: 27168604160 | elapsed time per iteration (s): 2.25 | learning rate: 1.522E-04 | global batch size: 512 | lm loss: 2.113121E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.639 | TFLOPs: 23.43 | +63: iteration 25920/ 73814 | consumed samples: 13271040 | consumed tokens: 27179089920 | elapsed time per iteration (s): 2.23 | learning rate: 1.522E-04 | global batch size: 512 | lm loss: 2.125007E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.708 | TFLOPs: 23.65 | +63: iteration 25930/ 73814 | consumed samples: 13276160 | consumed tokens: 27189575680 | elapsed time per iteration (s): 2.23 | learning rate: 1.522E-04 | global batch size: 512 | lm loss: 2.095550E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.923 | TFLOPs: 23.67 | +63: iteration 25940/ 73814 | consumed samples: 13281280 | consumed tokens: 27200061440 | elapsed time per iteration (s): 2.23 | learning rate: 1.521E-04 | global batch size: 512 | lm loss: 2.097761E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.189 | TFLOPs: 23.59 | +63: iteration 25950/ 73814 | consumed samples: 13286400 | consumed tokens: 27210547200 | elapsed time per iteration (s): 2.27 | learning rate: 1.521E-04 | global batch size: 512 | lm loss: 2.124270E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.044 | TFLOPs: 23.27 | +63: iteration 25960/ 73814 | consumed samples: 13291520 | consumed tokens: 27221032960 | elapsed time per iteration (s): 2.24 | learning rate: 1.521E-04 | global batch size: 512 | lm loss: 2.116355E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.266 | TFLOPs: 23.50 | +63: iteration 25970/ 73814 | consumed samples: 13296640 | consumed tokens: 27231518720 | elapsed time per iteration (s): 2.25 | learning rate: 1.520E-04 | global batch size: 512 | lm loss: 2.103767E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.216 | TFLOPs: 23.39 | +63: iteration 25980/ 73814 | consumed samples: 13301760 | consumed tokens: 27242004480 | elapsed time per iteration (s): 2.24 | learning rate: 1.520E-04 | global batch size: 512 | lm loss: 2.106178E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.814 | TFLOPs: 23.56 | +63: iteration 25990/ 73814 | consumed samples: 13306880 | consumed tokens: 27252490240 | elapsed time per iteration (s): 2.25 | learning rate: 1.520E-04 | global batch size: 512 | lm loss: 2.085527E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.960 | TFLOPs: 23.47 | + 0: [2022-12-02 04:15:25,106] [INFO] [logging.py:68:log_dist] [Rank 0] step=26000, skipped=0, lr=[0.00015194073234250097, 0.00015194073234250097, 0.00015194073234250097], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 26000/ 73814 | consumed samples: 13312000 | consumed tokens: 27262976000 | elapsed time per iteration (s): 2.23 | learning rate: 1.519E-04 | global batch size: 512 | lm loss: 2.107636E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.393 | TFLOPs: 23.61 | + 0: steps: 26000 loss: 2.0360 iter time (s): 2.269 samples/sec: 225.663 +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 26000 | lm loss value: 2.091407E+00 | lm loss PPL: 8.096295E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 26010/ 73814 | consumed samples: 13317120 | consumed tokens: 27273461760 | elapsed time per iteration (s): 2.30 | learning rate: 1.519E-04 | global batch size: 512 | lm loss: 2.072150E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.877 | TFLOPs: 22.94 | +63: iteration 26020/ 73814 | consumed samples: 13322240 | consumed tokens: 27283947520 | elapsed time per iteration (s): 2.23 | learning rate: 1.519E-04 | global batch size: 512 | lm loss: 2.105173E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.222 | TFLOPs: 23.60 | +63: iteration 26030/ 73814 | consumed samples: 13327360 | consumed tokens: 27294433280 | elapsed time per iteration (s): 2.26 | learning rate: 1.518E-04 | global batch size: 512 | lm loss: 2.122054E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.766 | TFLOPs: 23.34 | +63: iteration 26040/ 73814 | consumed samples: 13332480 | consumed tokens: 27304919040 | elapsed time per iteration (s): 2.23 | learning rate: 1.518E-04 | global batch size: 512 | lm loss: 2.121200E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.994 | TFLOPs: 23.68 | +63: iteration 26050/ 73814 | consumed samples: 13337600 | consumed tokens: 27315404800 | elapsed time per iteration (s): 2.25 | learning rate: 1.518E-04 | global batch size: 512 | lm loss: 2.131693E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.908 | TFLOPs: 23.46 | +63: iteration 26060/ 73814 | consumed samples: 13342720 | consumed tokens: 27325890560 | elapsed time per iteration (s): 2.23 | learning rate: 1.517E-04 | global batch size: 512 | lm loss: 2.084652E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.765 | TFLOPs: 23.65 | +63: iteration 26070/ 73814 | consumed samples: 13347840 | consumed tokens: 27336376320 | elapsed time per iteration (s): 2.24 | learning rate: 1.517E-04 | global batch size: 512 | lm loss: 2.081149E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.013 | TFLOPs: 23.58 | +63: iteration 26080/ 73814 | consumed samples: 13352960 | consumed tokens: 27346862080 | elapsed time per iteration (s): 2.23 | learning rate: 1.517E-04 | global batch size: 512 | lm loss: 2.114415E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.592 | TFLOPs: 23.64 | +63: iteration 26090/ 73814 | consumed samples: 13358080 | consumed tokens: 27357347840 | elapsed time per iteration (s): 2.26 | learning rate: 1.516E-04 | global batch size: 512 | lm loss: 2.098701E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.634 | TFLOPs: 23.33 | +63: iteration 26100/ 73814 | consumed samples: 13363200 | consumed tokens: 27367833600 | elapsed time per iteration (s): 2.23 | learning rate: 1.516E-04 | global batch size: 512 | lm loss: 2.098871E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.784 | TFLOPs: 23.66 | +63: iteration 26110/ 73814 | consumed samples: 13368320 | consumed tokens: 27378319360 | elapsed time per iteration (s): 2.23 | learning rate: 1.516E-04 | global batch size: 512 | lm loss: 2.100715E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.617 | TFLOPs: 23.64 | +63: iteration 26120/ 73814 | consumed samples: 13373440 | consumed tokens: 27388805120 | elapsed time per iteration (s): 2.29 | learning rate: 1.515E-04 | global batch size: 512 | lm loss: 2.119443E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.037 | TFLOPs: 23.06 | +63: iteration 26130/ 73814 | consumed samples: 13378560 | consumed tokens: 27399290880 | elapsed time per iteration (s): 2.23 | learning rate: 1.515E-04 | global batch size: 512 | lm loss: 2.118626E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.179 | TFLOPs: 23.59 | +63: iteration 26140/ 73814 | consumed samples: 13383680 | consumed tokens: 27409776640 | elapsed time per iteration (s): 2.23 | learning rate: 1.515E-04 | global batch size: 512 | lm loss: 2.101582E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.966 | TFLOPs: 23.67 | +63: iteration 26150/ 73814 | consumed samples: 13388800 | consumed tokens: 27420262400 | elapsed time per iteration (s): 2.23 | learning rate: 1.514E-04 | global batch size: 512 | lm loss: 2.130053E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.898 | TFLOPs: 23.67 | +63: iteration 26160/ 73814 | consumed samples: 13393920 | consumed tokens: 27430748160 | elapsed time per iteration (s): 2.25 | learning rate: 1.514E-04 | global batch size: 512 | lm loss: 2.091076E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.682 | TFLOPs: 23.44 | +63: iteration 26170/ 73814 | consumed samples: 13399040 | consumed tokens: 27441233920 | elapsed time per iteration (s): 2.23 | learning rate: 1.514E-04 | global batch size: 512 | lm loss: 2.125694E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.824 | TFLOPs: 23.66 | +63: iteration 26180/ 73814 | consumed samples: 13404160 | consumed tokens: 27451719680 | elapsed time per iteration (s): 2.24 | learning rate: 1.513E-04 | global batch size: 512 | lm loss: 2.105938E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.408 | TFLOPs: 23.51 | +63: iteration 26190/ 73814 | consumed samples: 13409280 | consumed tokens: 27462205440 | elapsed time per iteration (s): 2.23 | learning rate: 1.513E-04 | global batch size: 512 | lm loss: 2.094243E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.325 | TFLOPs: 23.61 | +63: iteration 26200/ 73814 | consumed samples: 13414400 | consumed tokens: 27472691200 | elapsed time per iteration (s): 2.33 | learning rate: 1.513E-04 | global batch size: 512 | lm loss: 2.109302E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.721 | TFLOPs: 22.62 | +63: iteration 26210/ 73814 | consumed samples: 13419520 | consumed tokens: 27483176960 | elapsed time per iteration (s): 2.23 | learning rate: 1.512E-04 | global batch size: 512 | lm loss: 2.102679E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.561 | TFLOPs: 23.63 | +63: iteration 26220/ 73814 | consumed samples: 13424640 | consumed tokens: 27493662720 | elapsed time per iteration (s): 2.22 | learning rate: 1.512E-04 | global batch size: 512 | lm loss: 2.084575E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.198 | TFLOPs: 23.70 | +63: iteration 26230/ 73814 | consumed samples: 13429760 | consumed tokens: 27504148480 | elapsed time per iteration (s): 2.24 | learning rate: 1.512E-04 | global batch size: 512 | lm loss: 2.111203E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.883 | TFLOPs: 23.56 | +63: iteration 26240/ 73814 | consumed samples: 13434880 | consumed tokens: 27514634240 | elapsed time per iteration (s): 2.24 | learning rate: 1.511E-04 | global batch size: 512 | lm loss: 2.088695E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.071 | TFLOPs: 23.48 | +63: iteration 26250/ 73814 | consumed samples: 13440000 | consumed tokens: 27525120000 | elapsed time per iteration (s): 2.22 | learning rate: 1.511E-04 | global batch size: 512 | lm loss: 2.073451E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.343 | TFLOPs: 23.71 | +63: iteration 26260/ 73814 | consumed samples: 13445120 | consumed tokens: 27535605760 | elapsed time per iteration (s): 2.24 | learning rate: 1.510E-04 | global batch size: 512 | lm loss: 2.110693E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.121 | TFLOPs: 23.48 | +63: iteration 26270/ 73814 | consumed samples: 13450240 | consumed tokens: 27546091520 | elapsed time per iteration (s): 2.24 | learning rate: 1.510E-04 | global batch size: 512 | lm loss: 2.118287E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.890 | TFLOPs: 23.56 | +63: iteration 26280/ 73814 | consumed samples: 13455360 | consumed tokens: 27556577280 | elapsed time per iteration (s): 2.24 | learning rate: 1.510E-04 | global batch size: 512 | lm loss: 2.091682E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.295 | TFLOPs: 23.50 | +63: iteration 26290/ 73814 | consumed samples: 13460480 | consumed tokens: 27567063040 | elapsed time per iteration (s): 2.23 | learning rate: 1.509E-04 | global batch size: 512 | lm loss: 2.135856E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.088 | TFLOPs: 23.69 | +63: iteration 26300/ 73814 | consumed samples: 13465600 | consumed tokens: 27577548800 | elapsed time per iteration (s): 2.23 | learning rate: 1.509E-04 | global batch size: 512 | lm loss: 2.125183E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.432 | TFLOPs: 23.62 | +63: iteration 26310/ 73814 | consumed samples: 13470720 | consumed tokens: 27588034560 | elapsed time per iteration (s): 2.25 | learning rate: 1.509E-04 | global batch size: 512 | lm loss: 2.115381E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.320 | TFLOPs: 23.40 | +63: iteration 26320/ 73814 | consumed samples: 13475840 | consumed tokens: 27598520320 | elapsed time per iteration (s): 2.26 | learning rate: 1.508E-04 | global batch size: 512 | lm loss: 2.126045E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.748 | TFLOPs: 23.34 | +63: iteration 26330/ 73814 | consumed samples: 13480960 | consumed tokens: 27609006080 | elapsed time per iteration (s): 2.26 | learning rate: 1.508E-04 | global batch size: 512 | lm loss: 2.109710E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.857 | TFLOPs: 23.35 | +63: iteration 26340/ 73814 | consumed samples: 13486080 | consumed tokens: 27619491840 | elapsed time per iteration (s): 2.57 | learning rate: 1.508E-04 | global batch size: 512 | lm loss: 2.103443E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.273 | TFLOPs: 20.51 | +63: iteration 26350/ 73814 | consumed samples: 13491200 | consumed tokens: 27629977600 | elapsed time per iteration (s): 2.23 | learning rate: 1.507E-04 | global batch size: 512 | lm loss: 2.106334E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.878 | TFLOPs: 23.66 | +63: iteration 26360/ 73814 | consumed samples: 13496320 | consumed tokens: 27640463360 | elapsed time per iteration (s): 2.46 | learning rate: 1.507E-04 | global batch size: 512 | lm loss: 2.119760E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.368 | TFLOPs: 21.45 | +63: iteration 26370/ 73814 | consumed samples: 13501440 | consumed tokens: 27650949120 | elapsed time per iteration (s): 2.25 | learning rate: 1.507E-04 | global batch size: 512 | lm loss: 2.111678E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.779 | TFLOPs: 23.45 | +63: iteration 26380/ 73814 | consumed samples: 13506560 | consumed tokens: 27661434880 | elapsed time per iteration (s): 2.32 | learning rate: 1.506E-04 | global batch size: 512 | lm loss: 2.110340E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.944 | TFLOPs: 22.75 | +63: iteration 26390/ 73814 | consumed samples: 13511680 | consumed tokens: 27671920640 | elapsed time per iteration (s): 2.25 | learning rate: 1.506E-04 | global batch size: 512 | lm loss: 2.063263E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.972 | TFLOPs: 23.47 | +63: iteration 26400/ 73814 | consumed samples: 13516800 | consumed tokens: 27682406400 | elapsed time per iteration (s): 2.27 | learning rate: 1.506E-04 | global batch size: 512 | lm loss: 2.106754E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.330 | TFLOPs: 23.20 | +63: iteration 26410/ 73814 | consumed samples: 13521920 | consumed tokens: 27692892160 | elapsed time per iteration (s): 2.25 | learning rate: 1.505E-04 | global batch size: 512 | lm loss: 2.116747E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.313 | TFLOPs: 23.40 | +63: iteration 26420/ 73814 | consumed samples: 13527040 | consumed tokens: 27703377920 | elapsed time per iteration (s): 2.23 | learning rate: 1.505E-04 | global batch size: 512 | lm loss: 2.097214E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.861 | TFLOPs: 23.66 | +63: iteration 26430/ 73814 | consumed samples: 13532160 | consumed tokens: 27713863680 | elapsed time per iteration (s): 2.27 | learning rate: 1.505E-04 | global batch size: 512 | lm loss: 2.126033E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.303 | TFLOPs: 23.19 | +63: iteration 26440/ 73814 | consumed samples: 13537280 | consumed tokens: 27724349440 | elapsed time per iteration (s): 2.37 | learning rate: 1.504E-04 | global batch size: 512 | lm loss: 2.096822E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.728 | TFLOPs: 22.21 | +63: iteration 26450/ 73814 | consumed samples: 13542400 | consumed tokens: 27734835200 | elapsed time per iteration (s): 2.23 | learning rate: 1.504E-04 | global batch size: 512 | lm loss: 2.108520E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.712 | TFLOPs: 23.65 | +63: iteration 26460/ 73814 | consumed samples: 13547520 | consumed tokens: 27745320960 | elapsed time per iteration (s): 2.23 | learning rate: 1.504E-04 | global batch size: 512 | lm loss: 2.105662E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.710 | TFLOPs: 23.65 | +63: iteration 26470/ 73814 | consumed samples: 13552640 | consumed tokens: 27755806720 | elapsed time per iteration (s): 2.23 | learning rate: 1.503E-04 | global batch size: 512 | lm loss: 2.103308E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.424 | TFLOPs: 23.62 | +63: iteration 26480/ 73814 | consumed samples: 13557760 | consumed tokens: 27766292480 | elapsed time per iteration (s): 2.24 | learning rate: 1.503E-04 | global batch size: 512 | lm loss: 2.075414E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.833 | TFLOPs: 23.56 | +63: iteration 26490/ 73814 | consumed samples: 13562880 | consumed tokens: 27776778240 | elapsed time per iteration (s): 2.23 | learning rate: 1.503E-04 | global batch size: 512 | lm loss: 2.085321E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.685 | TFLOPs: 23.65 | +63: iteration 26500/ 73814 | consumed samples: 13568000 | consumed tokens: 27787264000 | elapsed time per iteration (s): 2.24 | learning rate: 1.502E-04 | global batch size: 512 | lm loss: 2.106953E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.890 | TFLOPs: 23.56 | +63: iteration 26510/ 73814 | consumed samples: 13573120 | consumed tokens: 27797749760 | elapsed time per iteration (s): 2.24 | learning rate: 1.502E-04 | global batch size: 512 | lm loss: 2.110820E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.355 | TFLOPs: 23.51 | +63: iteration 26520/ 73814 | consumed samples: 13578240 | consumed tokens: 27808235520 | elapsed time per iteration (s): 2.23 | learning rate: 1.502E-04 | global batch size: 512 | lm loss: 2.106032E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.107 | TFLOPs: 23.59 | +63: iteration 26530/ 73814 | consumed samples: 13583360 | consumed tokens: 27818721280 | elapsed time per iteration (s): 2.25 | learning rate: 1.501E-04 | global batch size: 512 | lm loss: 2.111218E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.473 | TFLOPs: 23.42 | +63: iteration 26540/ 73814 | consumed samples: 13588480 | consumed tokens: 27829207040 | elapsed time per iteration (s): 2.25 | learning rate: 1.501E-04 | global batch size: 512 | lm loss: 2.117283E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.052 | TFLOPs: 23.37 | +63: iteration 26550/ 73814 | consumed samples: 13593600 | consumed tokens: 27839692800 | elapsed time per iteration (s): 2.23 | learning rate: 1.500E-04 | global batch size: 512 | lm loss: 2.089590E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.968 | TFLOPs: 23.67 | +63: iteration 26560/ 73814 | consumed samples: 13598720 | consumed tokens: 27850178560 | elapsed time per iteration (s): 2.23 | learning rate: 1.500E-04 | global batch size: 512 | lm loss: 2.097777E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.097 | TFLOPs: 23.69 | +63: iteration 26570/ 73814 | consumed samples: 13603840 | consumed tokens: 27860664320 | elapsed time per iteration (s): 2.23 | learning rate: 1.500E-04 | global batch size: 512 | lm loss: 2.121923E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.861 | TFLOPs: 23.66 | +63: iteration 26580/ 73814 | consumed samples: 13608960 | consumed tokens: 27871150080 | elapsed time per iteration (s): 2.23 | learning rate: 1.499E-04 | global batch size: 512 | lm loss: 2.088078E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.534 | TFLOPs: 23.63 | +63: iteration 26590/ 73814 | consumed samples: 13614080 | consumed tokens: 27881635840 | elapsed time per iteration (s): 2.30 | learning rate: 1.499E-04 | global batch size: 512 | lm loss: 2.078016E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.586 | TFLOPs: 22.91 | +63: iteration 26600/ 73814 | consumed samples: 13619200 | consumed tokens: 27892121600 | elapsed time per iteration (s): 2.30 | learning rate: 1.499E-04 | global batch size: 512 | lm loss: 2.096302E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.889 | TFLOPs: 22.95 | +63: iteration 26610/ 73814 | consumed samples: 13624320 | consumed tokens: 27902607360 | elapsed time per iteration (s): 2.53 | learning rate: 1.498E-04 | global batch size: 512 | lm loss: 2.097150E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.062 | TFLOPs: 20.80 | +63: iteration 26620/ 73814 | consumed samples: 13629440 | consumed tokens: 27913093120 | elapsed time per iteration (s): 2.26 | learning rate: 1.498E-04 | global batch size: 512 | lm loss: 2.100729E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.863 | TFLOPs: 23.35 | +63: iteration 26630/ 73814 | consumed samples: 13634560 | consumed tokens: 27923578880 | elapsed time per iteration (s): 2.24 | learning rate: 1.498E-04 | global batch size: 512 | lm loss: 2.105431E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.816 | TFLOPs: 23.56 | +63: iteration 26640/ 73814 | consumed samples: 13639680 | consumed tokens: 27934064640 | elapsed time per iteration (s): 2.23 | learning rate: 1.497E-04 | global batch size: 512 | lm loss: 2.093981E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.772 | TFLOPs: 23.65 | +63: iteration 26650/ 73814 | consumed samples: 13644800 | consumed tokens: 27944550400 | elapsed time per iteration (s): 2.23 | learning rate: 1.497E-04 | global batch size: 512 | lm loss: 2.097218E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.856 | TFLOPs: 23.66 | +63: iteration 26660/ 73814 | consumed samples: 13649920 | consumed tokens: 27955036160 | elapsed time per iteration (s): 2.24 | learning rate: 1.497E-04 | global batch size: 512 | lm loss: 2.102412E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.749 | TFLOPs: 23.55 | +63: iteration 26670/ 73814 | consumed samples: 13655040 | consumed tokens: 27965521920 | elapsed time per iteration (s): 2.33 | learning rate: 1.496E-04 | global batch size: 512 | lm loss: 2.089926E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.051 | TFLOPs: 22.65 | +63: iteration 26680/ 73814 | consumed samples: 13660160 | consumed tokens: 27976007680 | elapsed time per iteration (s): 2.24 | learning rate: 1.496E-04 | global batch size: 512 | lm loss: 2.100579E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.985 | TFLOPs: 23.57 | +63: iteration 26690/ 73814 | consumed samples: 13665280 | consumed tokens: 27986493440 | elapsed time per iteration (s): 2.23 | learning rate: 1.496E-04 | global batch size: 512 | lm loss: 2.092320E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.898 | TFLOPs: 23.67 | +63: iteration 26700/ 73814 | consumed samples: 13670400 | consumed tokens: 27996979200 | elapsed time per iteration (s): 2.25 | learning rate: 1.495E-04 | global batch size: 512 | lm loss: 2.120744E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.497 | TFLOPs: 23.42 | +63: iteration 26710/ 73814 | consumed samples: 13675520 | consumed tokens: 28007464960 | elapsed time per iteration (s): 2.25 | learning rate: 1.495E-04 | global batch size: 512 | lm loss: 2.104804E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.939 | TFLOPs: 23.47 | +63: iteration 26720/ 73814 | consumed samples: 13680640 | consumed tokens: 28017950720 | elapsed time per iteration (s): 2.23 | learning rate: 1.495E-04 | global batch size: 512 | lm loss: 2.113936E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.886 | TFLOPs: 23.67 | +63: iteration 26730/ 73814 | consumed samples: 13685760 | consumed tokens: 28028436480 | elapsed time per iteration (s): 2.23 | learning rate: 1.494E-04 | global batch size: 512 | lm loss: 2.098041E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.989 | TFLOPs: 23.68 | +63: iteration 26740/ 73814 | consumed samples: 13690880 | consumed tokens: 28038922240 | elapsed time per iteration (s): 2.25 | learning rate: 1.494E-04 | global batch size: 512 | lm loss: 2.079652E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.922 | TFLOPs: 23.46 | +63: iteration 26750/ 73814 | consumed samples: 13696000 | consumed tokens: 28049408000 | elapsed time per iteration (s): 2.23 | learning rate: 1.494E-04 | global batch size: 512 | lm loss: 2.113746E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.882 | TFLOPs: 23.67 | +63: iteration 26760/ 73814 | consumed samples: 13701120 | consumed tokens: 28059893760 | elapsed time per iteration (s): 2.24 | learning rate: 1.493E-04 | global batch size: 512 | lm loss: 2.102520E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.885 | TFLOPs: 23.56 | +63: iteration 26770/ 73814 | consumed samples: 13706240 | consumed tokens: 28070379520 | elapsed time per iteration (s): 2.23 | learning rate: 1.493E-04 | global batch size: 512 | lm loss: 2.081583E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.194 | TFLOPs: 23.59 | +63: iteration 26780/ 73814 | consumed samples: 13711360 | consumed tokens: 28080865280 | elapsed time per iteration (s): 2.24 | learning rate: 1.492E-04 | global batch size: 512 | lm loss: 2.087236E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.799 | TFLOPs: 23.55 | +63: iteration 26790/ 73814 | consumed samples: 13716480 | consumed tokens: 28091351040 | elapsed time per iteration (s): 2.23 | learning rate: 1.492E-04 | global batch size: 512 | lm loss: 2.095549E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.876 | TFLOPs: 23.66 | +63: iteration 26800/ 73814 | consumed samples: 13721600 | consumed tokens: 28101836800 | elapsed time per iteration (s): 2.23 | learning rate: 1.492E-04 | global batch size: 512 | lm loss: 2.097470E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.092 | TFLOPs: 23.58 | +63: iteration 26810/ 73814 | consumed samples: 13726720 | consumed tokens: 28112322560 | elapsed time per iteration (s): 2.32 | learning rate: 1.491E-04 | global batch size: 512 | lm loss: 2.093481E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.320 | TFLOPs: 22.68 | +63: iteration 26820/ 73814 | consumed samples: 13731840 | consumed tokens: 28122808320 | elapsed time per iteration (s): 2.25 | learning rate: 1.491E-04 | global batch size: 512 | lm loss: 2.087767E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.631 | TFLOPs: 23.43 | +63: iteration 26830/ 73814 | consumed samples: 13736960 | consumed tokens: 28133294080 | elapsed time per iteration (s): 2.23 | learning rate: 1.491E-04 | global batch size: 512 | lm loss: 2.072563E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.268 | TFLOPs: 23.60 | +63: iteration 26840/ 73814 | consumed samples: 13742080 | consumed tokens: 28143779840 | elapsed time per iteration (s): 2.25 | learning rate: 1.490E-04 | global batch size: 512 | lm loss: 2.107371E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.251 | TFLOPs: 23.39 | +63: iteration 26850/ 73814 | consumed samples: 13747200 | consumed tokens: 28154265600 | elapsed time per iteration (s): 2.24 | learning rate: 1.490E-04 | global batch size: 512 | lm loss: 2.099035E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.329 | TFLOPs: 23.51 | +63: iteration 26860/ 73814 | consumed samples: 13752320 | consumed tokens: 28164751360 | elapsed time per iteration (s): 2.26 | learning rate: 1.490E-04 | global batch size: 512 | lm loss: 2.134676E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.968 | TFLOPs: 23.37 | +63: iteration 26870/ 73814 | consumed samples: 13757440 | consumed tokens: 28175237120 | elapsed time per iteration (s): 2.24 | learning rate: 1.489E-04 | global batch size: 512 | lm loss: 2.069117E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.784 | TFLOPs: 23.55 | +63: iteration 26880/ 73814 | consumed samples: 13762560 | consumed tokens: 28185722880 | elapsed time per iteration (s): 2.25 | learning rate: 1.489E-04 | global batch size: 512 | lm loss: 2.098178E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.161 | TFLOPs: 23.39 | +63: iteration 26890/ 73814 | consumed samples: 13767680 | consumed tokens: 28196208640 | elapsed time per iteration (s): 2.29 | learning rate: 1.489E-04 | global batch size: 512 | lm loss: 2.104082E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.807 | TFLOPs: 23.04 | +63: iteration 26900/ 73814 | consumed samples: 13772800 | consumed tokens: 28206694400 | elapsed time per iteration (s): 2.23 | learning rate: 1.488E-04 | global batch size: 512 | lm loss: 2.096924E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.587 | TFLOPs: 23.63 | +63: iteration 26910/ 73814 | consumed samples: 13777920 | consumed tokens: 28217180160 | elapsed time per iteration (s): 2.29 | learning rate: 1.488E-04 | global batch size: 512 | lm loss: 2.123294E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.467 | TFLOPs: 23.00 | +63: iteration 26920/ 73814 | consumed samples: 13783040 | consumed tokens: 28227665920 | elapsed time per iteration (s): 2.23 | learning rate: 1.488E-04 | global batch size: 512 | lm loss: 2.083947E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.930 | TFLOPs: 23.67 | +63: iteration 26930/ 73814 | consumed samples: 13788160 | consumed tokens: 28238151680 | elapsed time per iteration (s): 2.23 | learning rate: 1.487E-04 | global batch size: 512 | lm loss: 2.103165E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.197 | TFLOPs: 23.59 | +63: iteration 26940/ 73814 | consumed samples: 13793280 | consumed tokens: 28248637440 | elapsed time per iteration (s): 2.29 | learning rate: 1.487E-04 | global batch size: 512 | lm loss: 2.125100E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.856 | TFLOPs: 23.04 | +63: iteration 26950/ 73814 | consumed samples: 13798400 | consumed tokens: 28259123200 | elapsed time per iteration (s): 2.23 | learning rate: 1.487E-04 | global batch size: 512 | lm loss: 2.077712E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.837 | TFLOPs: 23.66 | +63: iteration 26960/ 73814 | consumed samples: 13803520 | consumed tokens: 28269608960 | elapsed time per iteration (s): 2.24 | learning rate: 1.486E-04 | global batch size: 512 | lm loss: 2.095900E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.679 | TFLOPs: 23.54 | +63: iteration 26970/ 73814 | consumed samples: 13808640 | consumed tokens: 28280094720 | elapsed time per iteration (s): 2.29 | learning rate: 1.486E-04 | global batch size: 512 | lm loss: 2.098211E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.383 | TFLOPs: 23.00 | +63: iteration 26980/ 73814 | consumed samples: 13813760 | consumed tokens: 28290580480 | elapsed time per iteration (s): 2.27 | learning rate: 1.485E-04 | global batch size: 512 | lm loss: 2.082858E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.553 | TFLOPs: 23.22 | +63: iteration 26990/ 73814 | consumed samples: 13818880 | consumed tokens: 28301066240 | elapsed time per iteration (s): 2.23 | learning rate: 1.485E-04 | global batch size: 512 | lm loss: 2.093094E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.903 | TFLOPs: 23.67 | +63: iteration 27000/ 73814 | consumed samples: 13824000 | consumed tokens: 28311552000 | elapsed time per iteration (s): 2.29 | learning rate: 1.485E-04 | global batch size: 512 | lm loss: 2.120016E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.294 | TFLOPs: 22.99 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 27000 | lm loss value: 2.008930E+00 | lm loss PPL: 7.455334E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 27010/ 73814 | consumed samples: 13829120 | consumed tokens: 28322037760 | elapsed time per iteration (s): 2.34 | learning rate: 1.484E-04 | global batch size: 512 | lm loss: 2.108360E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.217 | TFLOPs: 22.57 | +63: iteration 27020/ 73814 | consumed samples: 13834240 | consumed tokens: 28332523520 | elapsed time per iteration (s): 2.23 | learning rate: 1.484E-04 | global batch size: 512 | lm loss: 2.098209E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.657 | TFLOPs: 23.64 | +63: iteration 27030/ 73814 | consumed samples: 13839360 | consumed tokens: 28343009280 | elapsed time per iteration (s): 2.23 | learning rate: 1.484E-04 | global batch size: 512 | lm loss: 2.119231E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.886 | TFLOPs: 23.67 | +63: iteration 27040/ 73814 | consumed samples: 13844480 | consumed tokens: 28353495040 | elapsed time per iteration (s): 2.24 | learning rate: 1.483E-04 | global batch size: 512 | lm loss: 2.110223E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.602 | TFLOPs: 23.53 | +63: iteration 27050/ 73814 | consumed samples: 13849600 | consumed tokens: 28363980800 | elapsed time per iteration (s): 2.22 | learning rate: 1.483E-04 | global batch size: 512 | lm loss: 2.101287E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.268 | TFLOPs: 23.70 | +63: iteration 27060/ 73814 | consumed samples: 13854720 | consumed tokens: 28374466560 | elapsed time per iteration (s): 2.23 | learning rate: 1.483E-04 | global batch size: 512 | lm loss: 2.107094E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.662 | TFLOPs: 23.64 | +63: iteration 27070/ 73814 | consumed samples: 13859840 | consumed tokens: 28384952320 | elapsed time per iteration (s): 2.23 | learning rate: 1.482E-04 | global batch size: 512 | lm loss: 2.117388E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.667 | TFLOPs: 23.64 | +63: iteration 27080/ 73814 | consumed samples: 13864960 | consumed tokens: 28395438080 | elapsed time per iteration (s): 2.23 | learning rate: 1.482E-04 | global batch size: 512 | lm loss: 2.099021E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.007 | TFLOPs: 23.68 | +63: iteration 27090/ 73814 | consumed samples: 13870080 | consumed tokens: 28405923840 | elapsed time per iteration (s): 2.25 | learning rate: 1.482E-04 | global batch size: 512 | lm loss: 2.083901E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.543 | TFLOPs: 23.42 | +63: iteration 27100/ 73814 | consumed samples: 13875200 | consumed tokens: 28416409600 | elapsed time per iteration (s): 2.23 | learning rate: 1.481E-04 | global batch size: 512 | lm loss: 2.090911E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.100 | TFLOPs: 23.69 | +63: iteration 27110/ 73814 | consumed samples: 13880320 | consumed tokens: 28426895360 | elapsed time per iteration (s): 2.23 | learning rate: 1.481E-04 | global batch size: 512 | lm loss: 2.120676E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.798 | TFLOPs: 23.66 | +63: iteration 27120/ 73814 | consumed samples: 13885440 | consumed tokens: 28437381120 | elapsed time per iteration (s): 2.23 | learning rate: 1.481E-04 | global batch size: 512 | lm loss: 2.112650E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.469 | TFLOPs: 23.62 | +63: iteration 27130/ 73814 | consumed samples: 13890560 | consumed tokens: 28447866880 | elapsed time per iteration (s): 2.23 | learning rate: 1.480E-04 | global batch size: 512 | lm loss: 2.108331E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.719 | TFLOPs: 23.65 | +63: iteration 27140/ 73814 | consumed samples: 13895680 | consumed tokens: 28458352640 | elapsed time per iteration (s): 2.31 | learning rate: 1.480E-04 | global batch size: 512 | lm loss: 2.104543E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.630 | TFLOPs: 22.82 | +63: iteration 27150/ 73814 | consumed samples: 13900800 | consumed tokens: 28468838400 | elapsed time per iteration (s): 2.44 | learning rate: 1.480E-04 | global batch size: 512 | lm loss: 2.094589E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.629 | TFLOPs: 21.58 | +63: iteration 27160/ 73814 | consumed samples: 13905920 | consumed tokens: 28479324160 | elapsed time per iteration (s): 2.38 | learning rate: 1.479E-04 | global batch size: 512 | lm loss: 2.110880E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.758 | TFLOPs: 22.11 | +63: iteration 27170/ 73814 | consumed samples: 13911040 | consumed tokens: 28489809920 | elapsed time per iteration (s): 2.47 | learning rate: 1.479E-04 | global batch size: 512 | lm loss: 2.080698E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 207.230 | TFLOPs: 21.33 | +63: iteration 27180/ 73814 | consumed samples: 13916160 | consumed tokens: 28500295680 | elapsed time per iteration (s): 2.26 | learning rate: 1.478E-04 | global batch size: 512 | lm loss: 2.082658E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.669 | TFLOPs: 23.33 | +63: iteration 27190/ 73814 | consumed samples: 13921280 | consumed tokens: 28510781440 | elapsed time per iteration (s): 2.46 | learning rate: 1.478E-04 | global batch size: 512 | lm loss: 2.078461E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 207.977 | TFLOPs: 21.41 | +63: iteration 27200/ 73814 | consumed samples: 13926400 | consumed tokens: 28521267200 | elapsed time per iteration (s): 2.75 | learning rate: 1.478E-04 | global batch size: 512 | lm loss: 2.101612E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 186.487 | TFLOPs: 19.20 | +63: iteration 27210/ 73814 | consumed samples: 13931520 | consumed tokens: 28531752960 | elapsed time per iteration (s): 2.65 | learning rate: 1.477E-04 | global batch size: 512 | lm loss: 2.109964E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 192.979 | TFLOPs: 19.87 | +63: iteration 27220/ 73814 | consumed samples: 13936640 | consumed tokens: 28542238720 | elapsed time per iteration (s): 2.27 | learning rate: 1.477E-04 | global batch size: 512 | lm loss: 2.080021E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.122 | TFLOPs: 23.18 | +63: iteration 27230/ 73814 | consumed samples: 13941760 | consumed tokens: 28552724480 | elapsed time per iteration (s): 2.31 | learning rate: 1.477E-04 | global batch size: 512 | lm loss: 2.092145E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.607 | TFLOPs: 22.81 | +63: iteration 27240/ 73814 | consumed samples: 13946880 | consumed tokens: 28563210240 | elapsed time per iteration (s): 2.27 | learning rate: 1.476E-04 | global batch size: 512 | lm loss: 2.100485E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.033 | TFLOPs: 23.27 | +63: iteration 27250/ 73814 | consumed samples: 13952000 | consumed tokens: 28573696000 | elapsed time per iteration (s): 2.45 | learning rate: 1.476E-04 | global batch size: 512 | lm loss: 2.079618E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.263 | TFLOPs: 21.54 | +63: iteration 27260/ 73814 | consumed samples: 13957120 | consumed tokens: 28584181760 | elapsed time per iteration (s): 2.32 | learning rate: 1.476E-04 | global batch size: 512 | lm loss: 2.095500E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.359 | TFLOPs: 22.68 | +63: iteration 27270/ 73814 | consumed samples: 13962240 | consumed tokens: 28594667520 | elapsed time per iteration (s): 2.24 | learning rate: 1.475E-04 | global batch size: 512 | lm loss: 2.095383E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.923 | TFLOPs: 23.57 | +63: iteration 27280/ 73814 | consumed samples: 13967360 | consumed tokens: 28605153280 | elapsed time per iteration (s): 2.25 | learning rate: 1.475E-04 | global batch size: 512 | lm loss: 2.108330E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.761 | TFLOPs: 23.45 | +63: iteration 27290/ 73814 | consumed samples: 13972480 | consumed tokens: 28615639040 | elapsed time per iteration (s): 2.23 | learning rate: 1.475E-04 | global batch size: 512 | lm loss: 2.072009E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.353 | TFLOPs: 23.61 | +63: iteration 27300/ 73814 | consumed samples: 13977600 | consumed tokens: 28626124800 | elapsed time per iteration (s): 2.23 | learning rate: 1.474E-04 | global batch size: 512 | lm loss: 2.092028E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.583 | TFLOPs: 23.63 | +63: iteration 27310/ 73814 | consumed samples: 13982720 | consumed tokens: 28636610560 | elapsed time per iteration (s): 2.22 | learning rate: 1.474E-04 | global batch size: 512 | lm loss: 2.114598E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.135 | TFLOPs: 23.69 | +63: iteration 27320/ 73814 | consumed samples: 13987840 | consumed tokens: 28647096320 | elapsed time per iteration (s): 2.30 | learning rate: 1.474E-04 | global batch size: 512 | lm loss: 2.095139E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.953 | TFLOPs: 22.95 | +63: iteration 27330/ 73814 | consumed samples: 13992960 | consumed tokens: 28657582080 | elapsed time per iteration (s): 2.32 | learning rate: 1.473E-04 | global batch size: 512 | lm loss: 2.089538E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.881 | TFLOPs: 22.74 | +63: iteration 27340/ 73814 | consumed samples: 13998080 | consumed tokens: 28668067840 | elapsed time per iteration (s): 2.64 | learning rate: 1.473E-04 | global batch size: 512 | lm loss: 2.101814E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 193.862 | TFLOPs: 19.96 | +63: iteration 27350/ 73814 | consumed samples: 14003200 | consumed tokens: 28678553600 | elapsed time per iteration (s): 2.23 | learning rate: 1.473E-04 | global batch size: 512 | lm loss: 2.109004E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.648 | TFLOPs: 23.64 | +63: iteration 27360/ 73814 | consumed samples: 14008320 | consumed tokens: 28689039360 | elapsed time per iteration (s): 2.23 | learning rate: 1.472E-04 | global batch size: 512 | lm loss: 2.095741E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.623 | TFLOPs: 23.64 | +63: iteration 27370/ 73814 | consumed samples: 14013440 | consumed tokens: 28699525120 | elapsed time per iteration (s): 2.25 | learning rate: 1.472E-04 | global batch size: 512 | lm loss: 2.088248E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.509 | TFLOPs: 23.42 | +63: iteration 27380/ 73814 | consumed samples: 14018560 | consumed tokens: 28710010880 | elapsed time per iteration (s): 2.25 | learning rate: 1.471E-04 | global batch size: 512 | lm loss: 2.130146E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.041 | TFLOPs: 23.48 | +63: iteration 27390/ 73814 | consumed samples: 14023680 | consumed tokens: 28720496640 | elapsed time per iteration (s): 3.96 | learning rate: 1.471E-04 | global batch size: 512 | lm loss: 2.124877E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 129.444 | TFLOPs: 13.33 | +63: iteration 27400/ 73814 | consumed samples: 14028800 | consumed tokens: 28730982400 | elapsed time per iteration (s): 2.23 | learning rate: 1.471E-04 | global batch size: 512 | lm loss: 2.107934E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.830 | TFLOPs: 23.66 | +63: iteration 27410/ 73814 | consumed samples: 14033920 | consumed tokens: 28741468160 | elapsed time per iteration (s): 2.23 | learning rate: 1.470E-04 | global batch size: 512 | lm loss: 2.108315E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.619 | TFLOPs: 23.64 | +63: iteration 27420/ 73814 | consumed samples: 14039040 | consumed tokens: 28751953920 | elapsed time per iteration (s): 2.23 | learning rate: 1.470E-04 | global batch size: 512 | lm loss: 2.094121E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.652 | TFLOPs: 23.64 | +63: iteration 27430/ 73814 | consumed samples: 14044160 | consumed tokens: 28762439680 | elapsed time per iteration (s): 2.29 | learning rate: 1.470E-04 | global batch size: 512 | lm loss: 2.100092E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.116 | TFLOPs: 22.97 | +63: iteration 27440/ 73814 | consumed samples: 14049280 | consumed tokens: 28772925440 | elapsed time per iteration (s): 2.23 | learning rate: 1.469E-04 | global batch size: 512 | lm loss: 2.068587E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.423 | TFLOPs: 23.62 | +63: iteration 27450/ 73814 | consumed samples: 14054400 | consumed tokens: 28783411200 | elapsed time per iteration (s): 2.25 | learning rate: 1.469E-04 | global batch size: 512 | lm loss: 2.094087E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.675 | TFLOPs: 23.44 | +63: iteration 27460/ 73814 | consumed samples: 14059520 | consumed tokens: 28793896960 | elapsed time per iteration (s): 2.23 | learning rate: 1.469E-04 | global batch size: 512 | lm loss: 2.116430E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.443 | TFLOPs: 23.62 | +63: iteration 27470/ 73814 | consumed samples: 14064640 | consumed tokens: 28804382720 | elapsed time per iteration (s): 2.33 | learning rate: 1.468E-04 | global batch size: 512 | lm loss: 2.085300E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.512 | TFLOPs: 22.60 | +63: iteration 27480/ 73814 | consumed samples: 14069760 | consumed tokens: 28814868480 | elapsed time per iteration (s): 2.25 | learning rate: 1.468E-04 | global batch size: 512 | lm loss: 2.094130E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.815 | TFLOPs: 23.45 | +63: iteration 27490/ 73814 | consumed samples: 14074880 | consumed tokens: 28825354240 | elapsed time per iteration (s): 2.25 | learning rate: 1.468E-04 | global batch size: 512 | lm loss: 2.088147E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.793 | TFLOPs: 23.45 | +63: iteration 27500/ 73814 | consumed samples: 14080000 | consumed tokens: 28835840000 | elapsed time per iteration (s): 2.24 | learning rate: 1.467E-04 | global batch size: 512 | lm loss: 2.102097E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.911 | TFLOPs: 23.57 | +63: iteration 27510/ 73814 | consumed samples: 14085120 | consumed tokens: 28846325760 | elapsed time per iteration (s): 2.26 | learning rate: 1.467E-04 | global batch size: 512 | lm loss: 2.098470E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.119 | TFLOPs: 23.28 | +63: iteration 27520/ 73814 | consumed samples: 14090240 | consumed tokens: 28856811520 | elapsed time per iteration (s): 2.29 | learning rate: 1.467E-04 | global batch size: 512 | lm loss: 2.126417E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.450 | TFLOPs: 23.00 | +63: iteration 27530/ 73814 | consumed samples: 14095360 | consumed tokens: 28867297280 | elapsed time per iteration (s): 2.23 | learning rate: 1.466E-04 | global batch size: 512 | lm loss: 2.116942E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.653 | TFLOPs: 23.64 | +63: iteration 27540/ 73814 | consumed samples: 14100480 | consumed tokens: 28877783040 | elapsed time per iteration (s): 2.24 | learning rate: 1.466E-04 | global batch size: 512 | lm loss: 2.096106E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.237 | TFLOPs: 23.50 | +63: iteration 27550/ 73814 | consumed samples: 14105600 | consumed tokens: 28888268800 | elapsed time per iteration (s): 2.23 | learning rate: 1.465E-04 | global batch size: 512 | lm loss: 2.097483E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.821 | TFLOPs: 23.66 | +63: iteration 27560/ 73814 | consumed samples: 14110720 | consumed tokens: 28898754560 | elapsed time per iteration (s): 2.23 | learning rate: 1.465E-04 | global batch size: 512 | lm loss: 2.072342E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.784 | TFLOPs: 23.66 | +63: iteration 27570/ 73814 | consumed samples: 14115840 | consumed tokens: 28909240320 | elapsed time per iteration (s): 2.23 | learning rate: 1.465E-04 | global batch size: 512 | lm loss: 2.102338E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.119 | TFLOPs: 23.59 | +63: iteration 27580/ 73814 | consumed samples: 14120960 | consumed tokens: 28919726080 | elapsed time per iteration (s): 2.23 | learning rate: 1.464E-04 | global batch size: 512 | lm loss: 2.103897E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.723 | TFLOPs: 23.65 | +63: iteration 27590/ 73814 | consumed samples: 14126080 | consumed tokens: 28930211840 | elapsed time per iteration (s): 2.25 | learning rate: 1.464E-04 | global batch size: 512 | lm loss: 2.095473E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.712 | TFLOPs: 23.44 | +63: iteration 27600/ 73814 | consumed samples: 14131200 | consumed tokens: 28940697600 | elapsed time per iteration (s): 2.23 | learning rate: 1.464E-04 | global batch size: 512 | lm loss: 2.086023E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.914 | TFLOPs: 23.67 | +63: iteration 27610/ 73814 | consumed samples: 14136320 | consumed tokens: 28951183360 | elapsed time per iteration (s): 2.33 | learning rate: 1.463E-04 | global batch size: 512 | lm loss: 2.096807E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.969 | TFLOPs: 22.64 | +63: iteration 27620/ 73814 | consumed samples: 14141440 | consumed tokens: 28961669120 | elapsed time per iteration (s): 2.26 | learning rate: 1.463E-04 | global batch size: 512 | lm loss: 2.077666E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.801 | TFLOPs: 23.35 | +63: iteration 27630/ 73814 | consumed samples: 14146560 | consumed tokens: 28972154880 | elapsed time per iteration (s): 2.23 | learning rate: 1.463E-04 | global batch size: 512 | lm loss: 2.123436E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.764 | TFLOPs: 23.65 | +63: iteration 27640/ 73814 | consumed samples: 14151680 | consumed tokens: 28982640640 | elapsed time per iteration (s): 2.24 | learning rate: 1.462E-04 | global batch size: 512 | lm loss: 2.066076E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.094 | TFLOPs: 23.48 | +63: iteration 27650/ 73814 | consumed samples: 14156800 | consumed tokens: 28993126400 | elapsed time per iteration (s): 2.25 | learning rate: 1.462E-04 | global batch size: 512 | lm loss: 2.112298E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.751 | TFLOPs: 23.45 | +63: iteration 27660/ 73814 | consumed samples: 14161920 | consumed tokens: 29003612160 | elapsed time per iteration (s): 2.23 | learning rate: 1.462E-04 | global batch size: 512 | lm loss: 2.087712E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.706 | TFLOPs: 23.65 | +63: iteration 27670/ 73814 | consumed samples: 14167040 | consumed tokens: 29014097920 | elapsed time per iteration (s): 2.24 | learning rate: 1.461E-04 | global batch size: 512 | lm loss: 2.082892E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.709 | TFLOPs: 23.54 | +63: iteration 27680/ 73814 | consumed samples: 14172160 | consumed tokens: 29024583680 | elapsed time per iteration (s): 2.24 | learning rate: 1.461E-04 | global batch size: 512 | lm loss: 2.088667E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.825 | TFLOPs: 23.56 | +63: iteration 27690/ 73814 | consumed samples: 14177280 | consumed tokens: 29035069440 | elapsed time per iteration (s): 2.22 | learning rate: 1.460E-04 | global batch size: 512 | lm loss: 2.085835E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.188 | TFLOPs: 23.70 | +63: iteration 27700/ 73814 | consumed samples: 14182400 | consumed tokens: 29045555200 | elapsed time per iteration (s): 2.23 | learning rate: 1.460E-04 | global batch size: 512 | lm loss: 2.092372E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.965 | TFLOPs: 23.67 | +63: iteration 27710/ 73814 | consumed samples: 14187520 | consumed tokens: 29056040960 | elapsed time per iteration (s): 2.23 | learning rate: 1.460E-04 | global batch size: 512 | lm loss: 2.108566E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.896 | TFLOPs: 23.67 | +63: iteration 27720/ 73814 | consumed samples: 14192640 | consumed tokens: 29066526720 | elapsed time per iteration (s): 2.26 | learning rate: 1.459E-04 | global batch size: 512 | lm loss: 2.083395E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.608 | TFLOPs: 23.33 | +63: iteration 27730/ 73814 | consumed samples: 14197760 | consumed tokens: 29077012480 | elapsed time per iteration (s): 2.23 | learning rate: 1.459E-04 | global batch size: 512 | lm loss: 2.100196E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.779 | TFLOPs: 23.65 | +63: iteration 27740/ 73814 | consumed samples: 14202880 | consumed tokens: 29087498240 | elapsed time per iteration (s): 2.24 | learning rate: 1.459E-04 | global batch size: 512 | lm loss: 2.114702E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.805 | TFLOPs: 23.55 | +63: iteration 27750/ 73814 | consumed samples: 14208000 | consumed tokens: 29097984000 | elapsed time per iteration (s): 2.23 | learning rate: 1.458E-04 | global batch size: 512 | lm loss: 2.094265E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.108 | TFLOPs: 23.59 | +63: iteration 27760/ 73814 | consumed samples: 14213120 | consumed tokens: 29108469760 | elapsed time per iteration (s): 2.24 | learning rate: 1.458E-04 | global batch size: 512 | lm loss: 2.112592E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.462 | TFLOPs: 23.52 | +63: iteration 27770/ 73814 | consumed samples: 14218240 | consumed tokens: 29118955520 | elapsed time per iteration (s): 2.22 | learning rate: 1.458E-04 | global batch size: 512 | lm loss: 2.074694E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.237 | TFLOPs: 23.70 | +63: iteration 27780/ 73814 | consumed samples: 14223360 | consumed tokens: 29129441280 | elapsed time per iteration (s): 2.23 | learning rate: 1.457E-04 | global batch size: 512 | lm loss: 2.099292E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.927 | TFLOPs: 23.67 | +63: iteration 27790/ 73814 | consumed samples: 14228480 | consumed tokens: 29139927040 | elapsed time per iteration (s): 2.23 | learning rate: 1.457E-04 | global batch size: 512 | lm loss: 2.078717E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.300 | TFLOPs: 23.61 | +63: iteration 27800/ 73814 | consumed samples: 14233600 | consumed tokens: 29150412800 | elapsed time per iteration (s): 2.23 | learning rate: 1.457E-04 | global batch size: 512 | lm loss: 2.090715E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.914 | TFLOPs: 23.67 | +63: iteration 27810/ 73814 | consumed samples: 14238720 | consumed tokens: 29160898560 | elapsed time per iteration (s): 2.25 | learning rate: 1.456E-04 | global batch size: 512 | lm loss: 2.090802E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.740 | TFLOPs: 23.44 | +63: iteration 27820/ 73814 | consumed samples: 14243840 | consumed tokens: 29171384320 | elapsed time per iteration (s): 2.24 | learning rate: 1.456E-04 | global batch size: 512 | lm loss: 2.101252E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.730 | TFLOPs: 23.55 | +63: iteration 27830/ 73814 | consumed samples: 14248960 | consumed tokens: 29181870080 | elapsed time per iteration (s): 2.23 | learning rate: 1.456E-04 | global batch size: 512 | lm loss: 2.087524E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.123 | TFLOPs: 23.59 | +63: iteration 27840/ 73814 | consumed samples: 14254080 | consumed tokens: 29192355840 | elapsed time per iteration (s): 2.23 | learning rate: 1.455E-04 | global batch size: 512 | lm loss: 2.089716E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.316 | TFLOPs: 23.61 | +63: iteration 27850/ 73814 | consumed samples: 14259200 | consumed tokens: 29202841600 | elapsed time per iteration (s): 2.24 | learning rate: 1.455E-04 | global batch size: 512 | lm loss: 2.067819E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.966 | TFLOPs: 23.57 | +63: iteration 27860/ 73814 | consumed samples: 14264320 | consumed tokens: 29213327360 | elapsed time per iteration (s): 2.26 | learning rate: 1.454E-04 | global batch size: 512 | lm loss: 2.078993E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.075 | TFLOPs: 23.27 | +63: iteration 27870/ 73814 | consumed samples: 14269440 | consumed tokens: 29223813120 | elapsed time per iteration (s): 2.24 | learning rate: 1.454E-04 | global batch size: 512 | lm loss: 2.097422E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.438 | TFLOPs: 23.52 | +63: iteration 27880/ 73814 | consumed samples: 14274560 | consumed tokens: 29234298880 | elapsed time per iteration (s): 2.23 | learning rate: 1.454E-04 | global batch size: 512 | lm loss: 2.083537E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.182 | TFLOPs: 23.59 | +63: iteration 27890/ 73814 | consumed samples: 14279680 | consumed tokens: 29244784640 | elapsed time per iteration (s): 2.24 | learning rate: 1.453E-04 | global batch size: 512 | lm loss: 2.070560E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.398 | TFLOPs: 23.51 | +63: iteration 27900/ 73814 | consumed samples: 14284800 | consumed tokens: 29255270400 | elapsed time per iteration (s): 2.24 | learning rate: 1.453E-04 | global batch size: 512 | lm loss: 2.095472E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.757 | TFLOPs: 23.55 | +63: iteration 27910/ 73814 | consumed samples: 14289920 | consumed tokens: 29265756160 | elapsed time per iteration (s): 2.29 | learning rate: 1.453E-04 | global batch size: 512 | lm loss: 2.084585E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.627 | TFLOPs: 23.02 | +63: iteration 27920/ 73814 | consumed samples: 14295040 | consumed tokens: 29276241920 | elapsed time per iteration (s): 2.28 | learning rate: 1.452E-04 | global batch size: 512 | lm loss: 2.077077E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.077 | TFLOPs: 23.07 | +63: iteration 27930/ 73814 | consumed samples: 14300160 | consumed tokens: 29286727680 | elapsed time per iteration (s): 2.23 | learning rate: 1.452E-04 | global batch size: 512 | lm loss: 2.091784E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.471 | TFLOPs: 23.62 | +63: iteration 27940/ 73814 | consumed samples: 14305280 | consumed tokens: 29297213440 | elapsed time per iteration (s): 2.23 | learning rate: 1.452E-04 | global batch size: 512 | lm loss: 2.062509E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.304 | TFLOPs: 23.61 | +63: iteration 27950/ 73814 | consumed samples: 14310400 | consumed tokens: 29307699200 | elapsed time per iteration (s): 2.25 | learning rate: 1.451E-04 | global batch size: 512 | lm loss: 2.104902E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.963 | TFLOPs: 23.47 | +63: iteration 27960/ 73814 | consumed samples: 14315520 | consumed tokens: 29318184960 | elapsed time per iteration (s): 2.24 | learning rate: 1.451E-04 | global batch size: 512 | lm loss: 2.084232E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.593 | TFLOPs: 23.53 | +63: iteration 27970/ 73814 | consumed samples: 14320640 | consumed tokens: 29328670720 | elapsed time per iteration (s): 2.27 | learning rate: 1.451E-04 | global batch size: 512 | lm loss: 2.089028E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.882 | TFLOPs: 23.25 | +63: iteration 27980/ 73814 | consumed samples: 14325760 | consumed tokens: 29339156480 | elapsed time per iteration (s): 2.25 | learning rate: 1.450E-04 | global batch size: 512 | lm loss: 2.103264E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.867 | TFLOPs: 23.46 | +63: iteration 27990/ 73814 | consumed samples: 14330880 | consumed tokens: 29349642240 | elapsed time per iteration (s): 2.23 | learning rate: 1.450E-04 | global batch size: 512 | lm loss: 2.099581E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.521 | TFLOPs: 23.63 | + 0: [2022-12-02 05:31:08,416] [INFO] [logging.py:68:log_dist] [Rank 0] step=28000, skipped=0, lr=[0.00014494752613469975, 0.00014494752613469975, 0.00014494752613469975], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] + 0: steps: 28000 loss: 2.0816 iter time (s): 2.269 samples/sec: 225.669 +63: iteration 28000/ 73814 | consumed samples: 14336000 | consumed tokens: 29360128000 | elapsed time per iteration (s): 2.24 | learning rate: 1.449E-04 | global batch size: 512 | lm loss: 2.094423E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.363 | TFLOPs: 23.51 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 28000 | lm loss value: 2.044962E+00 | lm loss PPL: 7.728864E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 28010/ 73814 | consumed samples: 14341120 | consumed tokens: 29370613760 | elapsed time per iteration (s): 2.30 | learning rate: 1.449E-04 | global batch size: 512 | lm loss: 2.105305E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.586 | TFLOPs: 22.91 | +63: iteration 28020/ 73814 | consumed samples: 14346240 | consumed tokens: 29381099520 | elapsed time per iteration (s): 2.24 | learning rate: 1.449E-04 | global batch size: 512 | lm loss: 2.098319E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.264 | TFLOPs: 23.50 | +63: iteration 28030/ 73814 | consumed samples: 14351360 | consumed tokens: 29391585280 | elapsed time per iteration (s): 2.24 | learning rate: 1.448E-04 | global batch size: 512 | lm loss: 2.103810E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.565 | TFLOPs: 23.53 | +63: iteration 28040/ 73814 | consumed samples: 14356480 | consumed tokens: 29402071040 | elapsed time per iteration (s): 2.24 | learning rate: 1.448E-04 | global batch size: 512 | lm loss: 2.072189E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.490 | TFLOPs: 23.52 | +63: iteration 28050/ 73814 | consumed samples: 14361600 | consumed tokens: 29412556800 | elapsed time per iteration (s): 2.27 | learning rate: 1.448E-04 | global batch size: 512 | lm loss: 2.100277E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.676 | TFLOPs: 23.23 | +63: iteration 28060/ 73814 | consumed samples: 14366720 | consumed tokens: 29423042560 | elapsed time per iteration (s): 2.23 | learning rate: 1.447E-04 | global batch size: 512 | lm loss: 2.093171E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.653 | TFLOPs: 23.64 | +63: iteration 28070/ 73814 | consumed samples: 14371840 | consumed tokens: 29433528320 | elapsed time per iteration (s): 2.24 | learning rate: 1.447E-04 | global batch size: 512 | lm loss: 2.081304E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.077 | TFLOPs: 23.48 | +63: iteration 28080/ 73814 | consumed samples: 14376960 | consumed tokens: 29444014080 | elapsed time per iteration (s): 2.23 | learning rate: 1.447E-04 | global batch size: 512 | lm loss: 2.074822E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.801 | TFLOPs: 23.66 | +63: iteration 28090/ 73814 | consumed samples: 14382080 | consumed tokens: 29454499840 | elapsed time per iteration (s): 2.28 | learning rate: 1.446E-04 | global batch size: 512 | lm loss: 2.061934E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.354 | TFLOPs: 23.10 | +63: iteration 28100/ 73814 | consumed samples: 14387200 | consumed tokens: 29464985600 | elapsed time per iteration (s): 2.34 | learning rate: 1.446E-04 | global batch size: 512 | lm loss: 2.094650E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.835 | TFLOPs: 22.53 | +63: iteration 28110/ 73814 | consumed samples: 14392320 | consumed tokens: 29475471360 | elapsed time per iteration (s): 2.25 | learning rate: 1.446E-04 | global batch size: 512 | lm loss: 2.096767E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.108 | TFLOPs: 23.38 | +63: iteration 28120/ 73814 | consumed samples: 14397440 | consumed tokens: 29485957120 | elapsed time per iteration (s): 2.25 | learning rate: 1.445E-04 | global batch size: 512 | lm loss: 2.075609E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.747 | TFLOPs: 23.45 | +63: iteration 28130/ 73814 | consumed samples: 14402560 | consumed tokens: 29496442880 | elapsed time per iteration (s): 2.23 | learning rate: 1.445E-04 | global batch size: 512 | lm loss: 2.094147E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.289 | TFLOPs: 23.60 | +63: iteration 28140/ 73814 | consumed samples: 14407680 | consumed tokens: 29506928640 | elapsed time per iteration (s): 2.23 | learning rate: 1.444E-04 | global batch size: 512 | lm loss: 2.070609E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.866 | TFLOPs: 23.66 | +63: iteration 28150/ 73814 | consumed samples: 14412800 | consumed tokens: 29517414400 | elapsed time per iteration (s): 2.23 | learning rate: 1.444E-04 | global batch size: 512 | lm loss: 2.082344E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.049 | TFLOPs: 23.68 | +63: iteration 28160/ 73814 | consumed samples: 14417920 | consumed tokens: 29527900160 | elapsed time per iteration (s): 2.33 | learning rate: 1.444E-04 | global batch size: 512 | lm loss: 2.107331E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.584 | TFLOPs: 22.61 | +63: iteration 28170/ 73814 | consumed samples: 14423040 | consumed tokens: 29538385920 | elapsed time per iteration (s): 2.24 | learning rate: 1.443E-04 | global batch size: 512 | lm loss: 2.093094E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.401 | TFLOPs: 23.51 | +63: iteration 28180/ 73814 | consumed samples: 14428160 | consumed tokens: 29548871680 | elapsed time per iteration (s): 2.23 | learning rate: 1.443E-04 | global batch size: 512 | lm loss: 2.090451E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.912 | TFLOPs: 23.67 | +63: iteration 28190/ 73814 | consumed samples: 14433280 | consumed tokens: 29559357440 | elapsed time per iteration (s): 2.24 | learning rate: 1.443E-04 | global batch size: 512 | lm loss: 2.081362E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.922 | TFLOPs: 23.57 | +63: iteration 28200/ 73814 | consumed samples: 14438400 | consumed tokens: 29569843200 | elapsed time per iteration (s): 2.23 | learning rate: 1.442E-04 | global batch size: 512 | lm loss: 2.077661E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.571 | TFLOPs: 23.63 | +63: iteration 28210/ 73814 | consumed samples: 14443520 | consumed tokens: 29580328960 | elapsed time per iteration (s): 2.25 | learning rate: 1.442E-04 | global batch size: 512 | lm loss: 2.117751E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.935 | TFLOPs: 23.46 | +63: iteration 28220/ 73814 | consumed samples: 14448640 | consumed tokens: 29590814720 | elapsed time per iteration (s): 2.22 | learning rate: 1.442E-04 | global batch size: 512 | lm loss: 2.052878E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.266 | TFLOPs: 23.70 | +63: iteration 28230/ 73814 | consumed samples: 14453760 | consumed tokens: 29601300480 | elapsed time per iteration (s): 2.23 | learning rate: 1.441E-04 | global batch size: 512 | lm loss: 2.055527E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.581 | TFLOPs: 23.63 | +63: iteration 28240/ 73814 | consumed samples: 14458880 | consumed tokens: 29611786240 | elapsed time per iteration (s): 2.23 | learning rate: 1.441E-04 | global batch size: 512 | lm loss: 2.104971E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.925 | TFLOPs: 23.67 | +63: iteration 28250/ 73814 | consumed samples: 14464000 | consumed tokens: 29622272000 | elapsed time per iteration (s): 2.23 | learning rate: 1.441E-04 | global batch size: 512 | lm loss: 2.095020E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.083 | TFLOPs: 23.69 | +63: iteration 28260/ 73814 | consumed samples: 14469120 | consumed tokens: 29632757760 | elapsed time per iteration (s): 2.23 | learning rate: 1.440E-04 | global batch size: 512 | lm loss: 2.086425E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.024 | TFLOPs: 23.68 | +63: iteration 28270/ 73814 | consumed samples: 14474240 | consumed tokens: 29643243520 | elapsed time per iteration (s): 2.24 | learning rate: 1.440E-04 | global batch size: 512 | lm loss: 2.085748E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.523 | TFLOPs: 23.53 | +63: iteration 28280/ 73814 | consumed samples: 14479360 | consumed tokens: 29653729280 | elapsed time per iteration (s): 2.24 | learning rate: 1.439E-04 | global batch size: 512 | lm loss: 2.066860E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.375 | TFLOPs: 23.51 | +63: iteration 28290/ 73814 | consumed samples: 14484480 | consumed tokens: 29664215040 | elapsed time per iteration (s): 2.24 | learning rate: 1.439E-04 | global batch size: 512 | lm loss: 2.074704E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.044 | TFLOPs: 23.58 | +63: iteration 28300/ 73814 | consumed samples: 14489600 | consumed tokens: 29674700800 | elapsed time per iteration (s): 2.26 | learning rate: 1.439E-04 | global batch size: 512 | lm loss: 2.062845E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.948 | TFLOPs: 23.36 | +63: iteration 28310/ 73814 | consumed samples: 14494720 | consumed tokens: 29685186560 | elapsed time per iteration (s): 2.32 | learning rate: 1.438E-04 | global batch size: 512 | lm loss: 2.085523E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.703 | TFLOPs: 22.72 | +63: iteration 28320/ 73814 | consumed samples: 14499840 | consumed tokens: 29695672320 | elapsed time per iteration (s): 2.44 | learning rate: 1.438E-04 | global batch size: 512 | lm loss: 2.105127E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.703 | TFLOPs: 21.59 | +63: iteration 28330/ 73814 | consumed samples: 14504960 | consumed tokens: 29706158080 | elapsed time per iteration (s): 2.33 | learning rate: 1.438E-04 | global batch size: 512 | lm loss: 2.088038E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.839 | TFLOPs: 22.63 | +63: iteration 28340/ 73814 | consumed samples: 14510080 | consumed tokens: 29716643840 | elapsed time per iteration (s): 2.26 | learning rate: 1.437E-04 | global batch size: 512 | lm loss: 2.113441E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.018 | TFLOPs: 23.37 | +63: iteration 28350/ 73814 | consumed samples: 14515200 | consumed tokens: 29727129600 | elapsed time per iteration (s): 2.23 | learning rate: 1.437E-04 | global batch size: 512 | lm loss: 2.076004E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.934 | TFLOPs: 23.67 | +63: iteration 28360/ 73814 | consumed samples: 14520320 | consumed tokens: 29737615360 | elapsed time per iteration (s): 2.23 | learning rate: 1.437E-04 | global batch size: 512 | lm loss: 2.093506E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.934 | TFLOPs: 23.67 | +63: iteration 28370/ 73814 | consumed samples: 14525440 | consumed tokens: 29748101120 | elapsed time per iteration (s): 2.23 | learning rate: 1.436E-04 | global batch size: 512 | lm loss: 2.103823E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.874 | TFLOPs: 23.66 | +63: iteration 28380/ 73814 | consumed samples: 14530560 | consumed tokens: 29758586880 | elapsed time per iteration (s): 2.22 | learning rate: 1.436E-04 | global batch size: 512 | lm loss: 2.086894E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.114 | TFLOPs: 23.69 | +63: iteration 28390/ 73814 | consumed samples: 14535680 | consumed tokens: 29769072640 | elapsed time per iteration (s): 2.53 | learning rate: 1.436E-04 | global batch size: 512 | lm loss: 2.085439E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.663 | TFLOPs: 20.86 | +63: iteration 28400/ 73814 | consumed samples: 14540800 | consumed tokens: 29779558400 | elapsed time per iteration (s): 2.24 | learning rate: 1.435E-04 | global batch size: 512 | lm loss: 2.066763E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.905 | TFLOPs: 23.56 | +63: iteration 28410/ 73814 | consumed samples: 14545920 | consumed tokens: 29790044160 | elapsed time per iteration (s): 2.22 | learning rate: 1.435E-04 | global batch size: 512 | lm loss: 2.092234E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.325 | TFLOPs: 23.71 | +63: iteration 28420/ 73814 | consumed samples: 14551040 | consumed tokens: 29800529920 | elapsed time per iteration (s): 2.24 | learning rate: 1.434E-04 | global batch size: 512 | lm loss: 2.078982E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.439 | TFLOPs: 23.52 | +63: iteration 28430/ 73814 | consumed samples: 14556160 | consumed tokens: 29811015680 | elapsed time per iteration (s): 2.23 | learning rate: 1.434E-04 | global batch size: 512 | lm loss: 2.088958E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.181 | TFLOPs: 23.59 | +63: iteration 28440/ 73814 | consumed samples: 14561280 | consumed tokens: 29821501440 | elapsed time per iteration (s): 2.39 | learning rate: 1.434E-04 | global batch size: 512 | lm loss: 2.080062E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.521 | TFLOPs: 22.08 | +63: iteration 28450/ 73814 | consumed samples: 14566400 | consumed tokens: 29831987200 | elapsed time per iteration (s): 2.23 | learning rate: 1.433E-04 | global batch size: 512 | lm loss: 2.072980E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.859 | TFLOPs: 23.66 | +63: iteration 28460/ 73814 | consumed samples: 14571520 | consumed tokens: 29842472960 | elapsed time per iteration (s): 2.24 | learning rate: 1.433E-04 | global batch size: 512 | lm loss: 2.088439E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.276 | TFLOPs: 23.50 | +63: iteration 28470/ 73814 | consumed samples: 14576640 | consumed tokens: 29852958720 | elapsed time per iteration (s): 2.24 | learning rate: 1.433E-04 | global batch size: 512 | lm loss: 2.080095E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.544 | TFLOPs: 23.53 | +63: iteration 28480/ 73814 | consumed samples: 14581760 | consumed tokens: 29863444480 | elapsed time per iteration (s): 2.24 | learning rate: 1.432E-04 | global batch size: 512 | lm loss: 2.104931E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.961 | TFLOPs: 23.57 | +63: iteration 28490/ 73814 | consumed samples: 14586880 | consumed tokens: 29873930240 | elapsed time per iteration (s): 2.24 | learning rate: 1.432E-04 | global batch size: 512 | lm loss: 2.076648E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.663 | TFLOPs: 23.54 | +63: iteration 28500/ 73814 | consumed samples: 14592000 | consumed tokens: 29884416000 | elapsed time per iteration (s): 2.24 | learning rate: 1.432E-04 | global batch size: 512 | lm loss: 2.098732E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.419 | TFLOPs: 23.51 | +63: iteration 28510/ 73814 | consumed samples: 14597120 | consumed tokens: 29894901760 | elapsed time per iteration (s): 2.23 | learning rate: 1.431E-04 | global batch size: 512 | lm loss: 2.108797E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.118 | TFLOPs: 23.59 | +63: iteration 28520/ 73814 | consumed samples: 14602240 | consumed tokens: 29905387520 | elapsed time per iteration (s): 2.23 | learning rate: 1.431E-04 | global batch size: 512 | lm loss: 2.073039E+00 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.547 | TFLOPs: 23.63 | +63: iteration 28530/ 73814 | consumed samples: 14607360 | consumed tokens: 29915873280 | elapsed time per iteration (s): 2.23 | learning rate: 1.430E-04 | global batch size: 512 | lm loss: 2.101036E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.102 | TFLOPs: 23.58 | +63: iteration 28540/ 73814 | consumed samples: 14612480 | consumed tokens: 29926359040 | elapsed time per iteration (s): 2.23 | learning rate: 1.430E-04 | global batch size: 512 | lm loss: 2.071335E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.214 | TFLOPs: 23.60 | +63: iteration 28550/ 73814 | consumed samples: 14617600 | consumed tokens: 29936844800 | elapsed time per iteration (s): 2.23 | learning rate: 1.430E-04 | global batch size: 512 | lm loss: 2.109142E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.931 | TFLOPs: 23.67 | +63: iteration 28560/ 73814 | consumed samples: 14622720 | consumed tokens: 29947330560 | elapsed time per iteration (s): 2.24 | learning rate: 1.429E-04 | global batch size: 512 | lm loss: 2.061803E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.204 | TFLOPs: 23.49 | +63: iteration 28570/ 73814 | consumed samples: 14627840 | consumed tokens: 29957816320 | elapsed time per iteration (s): 2.45 | learning rate: 1.429E-04 | global batch size: 512 | lm loss: 2.091000E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.095 | TFLOPs: 21.53 | +63: iteration 28580/ 73814 | consumed samples: 14632960 | consumed tokens: 29968302080 | elapsed time per iteration (s): 2.29 | learning rate: 1.429E-04 | global batch size: 512 | lm loss: 2.083483E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.060 | TFLOPs: 23.07 | +63: iteration 28590/ 73814 | consumed samples: 14638080 | consumed tokens: 29978787840 | elapsed time per iteration (s): 2.30 | learning rate: 1.428E-04 | global batch size: 512 | lm loss: 2.102359E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.266 | TFLOPs: 22.88 | +63: iteration 28600/ 73814 | consumed samples: 14643200 | consumed tokens: 29989273600 | elapsed time per iteration (s): 2.23 | learning rate: 1.428E-04 | global batch size: 512 | lm loss: 2.075028E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.224 | TFLOPs: 23.60 | +63: iteration 28610/ 73814 | consumed samples: 14648320 | consumed tokens: 29999759360 | elapsed time per iteration (s): 2.27 | learning rate: 1.428E-04 | global batch size: 512 | lm loss: 2.074652E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.957 | TFLOPs: 23.26 | +63: iteration 28620/ 73814 | consumed samples: 14653440 | consumed tokens: 30010245120 | elapsed time per iteration (s): 2.25 | learning rate: 1.427E-04 | global batch size: 512 | lm loss: 2.089175E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.998 | TFLOPs: 23.47 | +63: iteration 28630/ 73814 | consumed samples: 14658560 | consumed tokens: 30020730880 | elapsed time per iteration (s): 2.31 | learning rate: 1.427E-04 | global batch size: 512 | lm loss: 2.107117E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.780 | TFLOPs: 22.83 | +63: iteration 28640/ 73814 | consumed samples: 14663680 | consumed tokens: 30031216640 | elapsed time per iteration (s): 2.23 | learning rate: 1.427E-04 | global batch size: 512 | lm loss: 2.086188E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.246 | TFLOPs: 23.60 | +63: iteration 28650/ 73814 | consumed samples: 14668800 | consumed tokens: 30041702400 | elapsed time per iteration (s): 2.24 | learning rate: 1.426E-04 | global batch size: 512 | lm loss: 2.088287E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.520 | TFLOPs: 23.53 | +63: iteration 28660/ 73814 | consumed samples: 14673920 | consumed tokens: 30052188160 | elapsed time per iteration (s): 2.24 | learning rate: 1.426E-04 | global batch size: 512 | lm loss: 2.095934E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.502 | TFLOPs: 23.52 | +63: iteration 28670/ 73814 | consumed samples: 14679040 | consumed tokens: 30062673920 | elapsed time per iteration (s): 2.24 | learning rate: 1.425E-04 | global batch size: 512 | lm loss: 2.092379E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.353 | TFLOPs: 23.51 | +63: iteration 28680/ 73814 | consumed samples: 14684160 | consumed tokens: 30073159680 | elapsed time per iteration (s): 2.60 | learning rate: 1.425E-04 | global batch size: 512 | lm loss: 2.077223E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 196.967 | TFLOPs: 20.28 | +63: iteration 28690/ 73814 | consumed samples: 14689280 | consumed tokens: 30083645440 | elapsed time per iteration (s): 2.23 | learning rate: 1.425E-04 | global batch size: 512 | lm loss: 2.096419E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.727 | TFLOPs: 23.65 | +63: iteration 28700/ 73814 | consumed samples: 14694400 | consumed tokens: 30094131200 | elapsed time per iteration (s): 2.23 | learning rate: 1.424E-04 | global batch size: 512 | lm loss: 2.089313E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.920 | TFLOPs: 23.67 | +63: iteration 28710/ 73814 | consumed samples: 14699520 | consumed tokens: 30104616960 | elapsed time per iteration (s): 2.25 | learning rate: 1.424E-04 | global batch size: 512 | lm loss: 2.090450E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.571 | TFLOPs: 23.43 | +63: iteration 28720/ 73814 | consumed samples: 14704640 | consumed tokens: 30115102720 | elapsed time per iteration (s): 2.27 | learning rate: 1.424E-04 | global batch size: 512 | lm loss: 2.093228E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.340 | TFLOPs: 23.20 | +63: iteration 28730/ 73814 | consumed samples: 14709760 | consumed tokens: 30125588480 | elapsed time per iteration (s): 2.24 | learning rate: 1.423E-04 | global batch size: 512 | lm loss: 2.077508E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.349 | TFLOPs: 23.51 | +63: iteration 28740/ 73814 | consumed samples: 14714880 | consumed tokens: 30136074240 | elapsed time per iteration (s): 2.23 | learning rate: 1.423E-04 | global batch size: 512 | lm loss: 2.073723E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.316 | TFLOPs: 23.61 | +63: iteration 28750/ 73814 | consumed samples: 14720000 | consumed tokens: 30146560000 | elapsed time per iteration (s): 2.23 | learning rate: 1.423E-04 | global batch size: 512 | lm loss: 2.083646E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.957 | TFLOPs: 23.67 | +63: iteration 28760/ 73814 | consumed samples: 14725120 | consumed tokens: 30157045760 | elapsed time per iteration (s): 2.26 | learning rate: 1.422E-04 | global batch size: 512 | lm loss: 2.070963E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.160 | TFLOPs: 23.28 | +63: iteration 28770/ 73814 | consumed samples: 14730240 | consumed tokens: 30167531520 | elapsed time per iteration (s): 2.23 | learning rate: 1.422E-04 | global batch size: 512 | lm loss: 2.098245E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.163 | TFLOPs: 23.59 | +63: iteration 28780/ 73814 | consumed samples: 14735360 | consumed tokens: 30178017280 | elapsed time per iteration (s): 2.25 | learning rate: 1.421E-04 | global batch size: 512 | lm loss: 2.076836E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.960 | TFLOPs: 23.47 | +63: iteration 28790/ 73814 | consumed samples: 14740480 | consumed tokens: 30188503040 | elapsed time per iteration (s): 2.24 | learning rate: 1.421E-04 | global batch size: 512 | lm loss: 2.078912E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.302 | TFLOPs: 23.50 | +63: iteration 28800/ 73814 | consumed samples: 14745600 | consumed tokens: 30198988800 | elapsed time per iteration (s): 2.23 | learning rate: 1.421E-04 | global batch size: 512 | lm loss: 2.063464E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.292 | TFLOPs: 23.60 | +63: iteration 28810/ 73814 | consumed samples: 14750720 | consumed tokens: 30209474560 | elapsed time per iteration (s): 2.23 | learning rate: 1.420E-04 | global batch size: 512 | lm loss: 2.085866E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.045 | TFLOPs: 23.68 | +63: iteration 28820/ 73814 | consumed samples: 14755840 | consumed tokens: 30219960320 | elapsed time per iteration (s): 2.23 | learning rate: 1.420E-04 | global batch size: 512 | lm loss: 2.096854E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.684 | TFLOPs: 23.64 | +63: iteration 28830/ 73814 | consumed samples: 14760960 | consumed tokens: 30230446080 | elapsed time per iteration (s): 2.23 | learning rate: 1.420E-04 | global batch size: 512 | lm loss: 2.075481E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.294 | TFLOPs: 23.60 | +63: iteration 28840/ 73814 | consumed samples: 14766080 | consumed tokens: 30240931840 | elapsed time per iteration (s): 2.23 | learning rate: 1.419E-04 | global batch size: 512 | lm loss: 2.065263E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.947 | TFLOPs: 23.67 | +63: iteration 28850/ 73814 | consumed samples: 14771200 | consumed tokens: 30251417600 | elapsed time per iteration (s): 2.28 | learning rate: 1.419E-04 | global batch size: 512 | lm loss: 2.074529E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.870 | TFLOPs: 23.15 | +63: iteration 28860/ 73814 | consumed samples: 14776320 | consumed tokens: 30261903360 | elapsed time per iteration (s): 2.28 | learning rate: 1.419E-04 | global batch size: 512 | lm loss: 2.069201E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.034 | TFLOPs: 23.17 | +63: iteration 28870/ 73814 | consumed samples: 14781440 | consumed tokens: 30272389120 | elapsed time per iteration (s): 2.39 | learning rate: 1.418E-04 | global batch size: 512 | lm loss: 2.072365E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.967 | TFLOPs: 22.03 | +63: iteration 28880/ 73814 | consumed samples: 14786560 | consumed tokens: 30282874880 | elapsed time per iteration (s): 2.44 | learning rate: 1.418E-04 | global batch size: 512 | lm loss: 2.079712E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.258 | TFLOPs: 21.65 | +63: iteration 28890/ 73814 | consumed samples: 14791680 | consumed tokens: 30293360640 | elapsed time per iteration (s): 2.26 | learning rate: 1.417E-04 | global batch size: 512 | lm loss: 2.097977E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.690 | TFLOPs: 23.34 | +63: iteration 28900/ 73814 | consumed samples: 14796800 | consumed tokens: 30303846400 | elapsed time per iteration (s): 2.26 | learning rate: 1.417E-04 | global batch size: 512 | lm loss: 2.076238E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.177 | TFLOPs: 23.28 | +63: iteration 28910/ 73814 | consumed samples: 14801920 | consumed tokens: 30314332160 | elapsed time per iteration (s): 2.64 | learning rate: 1.417E-04 | global batch size: 512 | lm loss: 2.076950E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 193.871 | TFLOPs: 19.96 | +63: iteration 28920/ 73814 | consumed samples: 14807040 | consumed tokens: 30324817920 | elapsed time per iteration (s): 4.45 | learning rate: 1.416E-04 | global batch size: 512 | lm loss: 2.065724E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 115.163 | TFLOPs: 11.86 | +63: iteration 28930/ 73814 | consumed samples: 14812160 | consumed tokens: 30335303680 | elapsed time per iteration (s): 2.25 | learning rate: 1.416E-04 | global batch size: 512 | lm loss: 2.081586E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.241 | TFLOPs: 23.39 | +63: iteration 28940/ 73814 | consumed samples: 14817280 | consumed tokens: 30345789440 | elapsed time per iteration (s): 2.24 | learning rate: 1.416E-04 | global batch size: 512 | lm loss: 2.075382E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.372 | TFLOPs: 23.51 | +63: iteration 28950/ 73814 | consumed samples: 14822400 | consumed tokens: 30356275200 | elapsed time per iteration (s): 2.39 | learning rate: 1.415E-04 | global batch size: 512 | lm loss: 2.083044E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.430 | TFLOPs: 22.07 | +63: iteration 28960/ 73814 | consumed samples: 14827520 | consumed tokens: 30366760960 | elapsed time per iteration (s): 2.31 | learning rate: 1.415E-04 | global batch size: 512 | lm loss: 2.087886E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.192 | TFLOPs: 22.77 | +63: iteration 28970/ 73814 | consumed samples: 14832640 | consumed tokens: 30377246720 | elapsed time per iteration (s): 2.23 | learning rate: 1.415E-04 | global batch size: 512 | lm loss: 2.096962E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.190 | TFLOPs: 23.59 | +63: iteration 28980/ 73814 | consumed samples: 14837760 | consumed tokens: 30387732480 | elapsed time per iteration (s): 2.25 | learning rate: 1.414E-04 | global batch size: 512 | lm loss: 2.086259E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.683 | TFLOPs: 23.44 | +63: iteration 28990/ 73814 | consumed samples: 14842880 | consumed tokens: 30398218240 | elapsed time per iteration (s): 2.25 | learning rate: 1.414E-04 | global batch size: 512 | lm loss: 2.069695E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.241 | TFLOPs: 23.39 | +63: iteration 29000/ 73814 | consumed samples: 14848000 | consumed tokens: 30408704000 | elapsed time per iteration (s): 2.24 | learning rate: 1.414E-04 | global batch size: 512 | lm loss: 2.068056E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.135 | TFLOPs: 23.49 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 29000 | lm loss value: 2.023677E+00 | lm loss PPL: 7.566093E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 29010/ 73814 | consumed samples: 14853120 | consumed tokens: 30419189760 | elapsed time per iteration (s): 2.30 | learning rate: 1.413E-04 | global batch size: 512 | lm loss: 2.087091E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.390 | TFLOPs: 22.89 | +63: iteration 29020/ 73814 | consumed samples: 14858240 | consumed tokens: 30429675520 | elapsed time per iteration (s): 2.23 | learning rate: 1.413E-04 | global batch size: 512 | lm loss: 2.067283E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.714 | TFLOPs: 23.65 | +63: iteration 29030/ 73814 | consumed samples: 14863360 | consumed tokens: 30440161280 | elapsed time per iteration (s): 2.25 | learning rate: 1.412E-04 | global batch size: 512 | lm loss: 2.098459E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.957 | TFLOPs: 23.47 | +63: iteration 29040/ 73814 | consumed samples: 14868480 | consumed tokens: 30450647040 | elapsed time per iteration (s): 2.34 | learning rate: 1.412E-04 | global batch size: 512 | lm loss: 2.058432E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.715 | TFLOPs: 22.52 | +63: iteration 29050/ 73814 | consumed samples: 14873600 | consumed tokens: 30461132800 | elapsed time per iteration (s): 2.52 | learning rate: 1.412E-04 | global batch size: 512 | lm loss: 2.093826E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.836 | TFLOPs: 20.88 | +63: iteration 29060/ 73814 | consumed samples: 14878720 | consumed tokens: 30471618560 | elapsed time per iteration (s): 2.25 | learning rate: 1.411E-04 | global batch size: 512 | lm loss: 2.068024E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.991 | TFLOPs: 23.47 | +63: iteration 29070/ 73814 | consumed samples: 14883840 | consumed tokens: 30482104320 | elapsed time per iteration (s): 2.22 | learning rate: 1.411E-04 | global batch size: 512 | lm loss: 2.057102E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.156 | TFLOPs: 23.69 | +63: iteration 29080/ 73814 | consumed samples: 14888960 | consumed tokens: 30492590080 | elapsed time per iteration (s): 2.25 | learning rate: 1.411E-04 | global batch size: 512 | lm loss: 2.053056E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.047 | TFLOPs: 23.48 | +63: iteration 29090/ 73814 | consumed samples: 14894080 | consumed tokens: 30503075840 | elapsed time per iteration (s): 2.23 | learning rate: 1.410E-04 | global batch size: 512 | lm loss: 2.066324E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.708 | TFLOPs: 23.65 | +63: iteration 29100/ 73814 | consumed samples: 14899200 | consumed tokens: 30513561600 | elapsed time per iteration (s): 2.23 | learning rate: 1.410E-04 | global batch size: 512 | lm loss: 2.059514E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.915 | TFLOPs: 23.67 | +63: iteration 29110/ 73814 | consumed samples: 14904320 | consumed tokens: 30524047360 | elapsed time per iteration (s): 2.24 | learning rate: 1.410E-04 | global batch size: 512 | lm loss: 2.080631E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.707 | TFLOPs: 23.54 | +63: iteration 29120/ 73814 | consumed samples: 14909440 | consumed tokens: 30534533120 | elapsed time per iteration (s): 2.24 | learning rate: 1.409E-04 | global batch size: 512 | lm loss: 2.085510E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.195 | TFLOPs: 23.49 | +63: iteration 29130/ 73814 | consumed samples: 14914560 | consumed tokens: 30545018880 | elapsed time per iteration (s): 2.22 | learning rate: 1.409E-04 | global batch size: 512 | lm loss: 2.092286E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.348 | TFLOPs: 23.71 | +63: iteration 29140/ 73814 | consumed samples: 14919680 | consumed tokens: 30555504640 | elapsed time per iteration (s): 2.24 | learning rate: 1.408E-04 | global batch size: 512 | lm loss: 2.059518E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.827 | TFLOPs: 23.56 | +63: iteration 29150/ 73814 | consumed samples: 14924800 | consumed tokens: 30565990400 | elapsed time per iteration (s): 2.24 | learning rate: 1.408E-04 | global batch size: 512 | lm loss: 2.080187E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.622 | TFLOPs: 23.54 | +63: iteration 29160/ 73814 | consumed samples: 14929920 | consumed tokens: 30576476160 | elapsed time per iteration (s): 2.23 | learning rate: 1.408E-04 | global batch size: 512 | lm loss: 2.071920E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.626 | TFLOPs: 23.64 | +63: iteration 29170/ 73814 | consumed samples: 14935040 | consumed tokens: 30586961920 | elapsed time per iteration (s): 2.23 | learning rate: 1.407E-04 | global batch size: 512 | lm loss: 2.104076E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.237 | TFLOPs: 23.60 | +63: iteration 29180/ 73814 | consumed samples: 14940160 | consumed tokens: 30597447680 | elapsed time per iteration (s): 2.23 | learning rate: 1.407E-04 | global batch size: 512 | lm loss: 2.067358E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.898 | TFLOPs: 23.67 | +63: iteration 29190/ 73814 | consumed samples: 14945280 | consumed tokens: 30607933440 | elapsed time per iteration (s): 2.51 | learning rate: 1.407E-04 | global batch size: 512 | lm loss: 2.066509E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 203.929 | TFLOPs: 20.99 | +63: iteration 29200/ 73814 | consumed samples: 14950400 | consumed tokens: 30618419200 | elapsed time per iteration (s): 2.23 | learning rate: 1.406E-04 | global batch size: 512 | lm loss: 2.085169E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.644 | TFLOPs: 23.64 | +63: iteration 29210/ 73814 | consumed samples: 14955520 | consumed tokens: 30628904960 | elapsed time per iteration (s): 2.23 | learning rate: 1.406E-04 | global batch size: 512 | lm loss: 2.078870E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.814 | TFLOPs: 23.66 | +63: iteration 29220/ 73814 | consumed samples: 14960640 | consumed tokens: 30639390720 | elapsed time per iteration (s): 2.50 | learning rate: 1.406E-04 | global batch size: 512 | lm loss: 2.071420E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.115 | TFLOPs: 21.12 | +63: iteration 29230/ 73814 | consumed samples: 14965760 | consumed tokens: 30649876480 | elapsed time per iteration (s): 2.27 | learning rate: 1.405E-04 | global batch size: 512 | lm loss: 2.070877E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.350 | TFLOPs: 23.20 | +63: iteration 29240/ 73814 | consumed samples: 14970880 | consumed tokens: 30660362240 | elapsed time per iteration (s): 2.24 | learning rate: 1.405E-04 | global batch size: 512 | lm loss: 2.084378E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.402 | TFLOPs: 23.51 | +63: iteration 29250/ 73814 | consumed samples: 14976000 | consumed tokens: 30670848000 | elapsed time per iteration (s): 2.26 | learning rate: 1.404E-04 | global batch size: 512 | lm loss: 2.088708E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.078 | TFLOPs: 23.27 | +63: iteration 29260/ 73814 | consumed samples: 14981120 | consumed tokens: 30681333760 | elapsed time per iteration (s): 2.26 | learning rate: 1.404E-04 | global batch size: 512 | lm loss: 2.080958E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.650 | TFLOPs: 23.33 | +63: iteration 29270/ 73814 | consumed samples: 14986240 | consumed tokens: 30691819520 | elapsed time per iteration (s): 2.24 | learning rate: 1.404E-04 | global batch size: 512 | lm loss: 2.090444E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.306 | TFLOPs: 23.50 | +63: iteration 29280/ 73814 | consumed samples: 14991360 | consumed tokens: 30702305280 | elapsed time per iteration (s): 2.23 | learning rate: 1.403E-04 | global batch size: 512 | lm loss: 2.061513E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.831 | TFLOPs: 23.66 | +63: iteration 29290/ 73814 | consumed samples: 14996480 | consumed tokens: 30712791040 | elapsed time per iteration (s): 2.25 | learning rate: 1.403E-04 | global batch size: 512 | lm loss: 2.064513E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.225 | TFLOPs: 23.39 | +63: iteration 29300/ 73814 | consumed samples: 15001600 | consumed tokens: 30723276800 | elapsed time per iteration (s): 2.25 | learning rate: 1.403E-04 | global batch size: 512 | lm loss: 2.050303E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.577 | TFLOPs: 23.43 | +63: iteration 29310/ 73814 | consumed samples: 15006720 | consumed tokens: 30733762560 | elapsed time per iteration (s): 2.24 | learning rate: 1.402E-04 | global batch size: 512 | lm loss: 2.071909E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.944 | TFLOPs: 23.57 | +63: iteration 29320/ 73814 | consumed samples: 15011840 | consumed tokens: 30744248320 | elapsed time per iteration (s): 2.23 | learning rate: 1.402E-04 | global batch size: 512 | lm loss: 2.073015E+00 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.836 | TFLOPs: 23.66 | +63: iteration 29330/ 73814 | consumed samples: 15016960 | consumed tokens: 30754734080 | elapsed time per iteration (s): 2.30 | learning rate: 1.402E-04 | global batch size: 512 | lm loss: 2.072822E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.802 | TFLOPs: 22.94 | +63: iteration 29340/ 73814 | consumed samples: 15022080 | consumed tokens: 30765219840 | elapsed time per iteration (s): 2.23 | learning rate: 1.401E-04 | global batch size: 512 | lm loss: 2.092320E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.566 | TFLOPs: 23.63 | +63: iteration 29350/ 73814 | consumed samples: 15027200 | consumed tokens: 30775705600 | elapsed time per iteration (s): 2.23 | learning rate: 1.401E-04 | global batch size: 512 | lm loss: 2.060028E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.725 | TFLOPs: 23.65 | +63: iteration 29360/ 73814 | consumed samples: 15032320 | consumed tokens: 30786191360 | elapsed time per iteration (s): 2.24 | learning rate: 1.400E-04 | global batch size: 512 | lm loss: 2.063999E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.709 | TFLOPs: 23.54 | +63: iteration 29370/ 73814 | consumed samples: 15037440 | consumed tokens: 30796677120 | elapsed time per iteration (s): 2.23 | learning rate: 1.400E-04 | global batch size: 512 | lm loss: 2.093357E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.666 | TFLOPs: 23.64 | +63: iteration 29380/ 73814 | consumed samples: 15042560 | consumed tokens: 30807162880 | elapsed time per iteration (s): 2.23 | learning rate: 1.400E-04 | global batch size: 512 | lm loss: 2.080348E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.124 | TFLOPs: 23.59 | +63: iteration 29390/ 73814 | consumed samples: 15047680 | consumed tokens: 30817648640 | elapsed time per iteration (s): 2.24 | learning rate: 1.399E-04 | global batch size: 512 | lm loss: 2.093798E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.419 | TFLOPs: 23.51 | +63: iteration 29400/ 73814 | consumed samples: 15052800 | consumed tokens: 30828134400 | elapsed time per iteration (s): 2.23 | learning rate: 1.399E-04 | global batch size: 512 | lm loss: 2.103183E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.783 | TFLOPs: 23.66 | +63: iteration 29410/ 73814 | consumed samples: 15057920 | consumed tokens: 30838620160 | elapsed time per iteration (s): 2.23 | learning rate: 1.399E-04 | global batch size: 512 | lm loss: 2.078062E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.382 | TFLOPs: 23.61 | +63: iteration 29420/ 73814 | consumed samples: 15063040 | consumed tokens: 30849105920 | elapsed time per iteration (s): 2.23 | learning rate: 1.398E-04 | global batch size: 512 | lm loss: 2.076206E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.851 | TFLOPs: 23.66 | +63: iteration 29430/ 73814 | consumed samples: 15068160 | consumed tokens: 30859591680 | elapsed time per iteration (s): 2.31 | learning rate: 1.398E-04 | global batch size: 512 | lm loss: 2.076211E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.769 | TFLOPs: 22.83 | +63: iteration 29440/ 73814 | consumed samples: 15073280 | consumed tokens: 30870077440 | elapsed time per iteration (s): 2.23 | learning rate: 1.397E-04 | global batch size: 512 | lm loss: 2.061618E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.243 | TFLOPs: 23.60 | +63: iteration 29450/ 73814 | consumed samples: 15078400 | consumed tokens: 30880563200 | elapsed time per iteration (s): 2.23 | learning rate: 1.397E-04 | global batch size: 512 | lm loss: 2.067639E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.268 | TFLOPs: 23.60 | +63: iteration 29460/ 73814 | consumed samples: 15083520 | consumed tokens: 30891048960 | elapsed time per iteration (s): 2.25 | learning rate: 1.397E-04 | global batch size: 512 | lm loss: 2.062418E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.317 | TFLOPs: 23.40 | +63: iteration 29470/ 73814 | consumed samples: 15088640 | consumed tokens: 30901534720 | elapsed time per iteration (s): 2.25 | learning rate: 1.396E-04 | global batch size: 512 | lm loss: 2.089926E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.604 | TFLOPs: 23.43 | +63: iteration 29480/ 73814 | consumed samples: 15093760 | consumed tokens: 30912020480 | elapsed time per iteration (s): 2.24 | learning rate: 1.396E-04 | global batch size: 512 | lm loss: 2.093072E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.446 | TFLOPs: 23.52 | +63: iteration 29490/ 73814 | consumed samples: 15098880 | consumed tokens: 30922506240 | elapsed time per iteration (s): 2.24 | learning rate: 1.396E-04 | global batch size: 512 | lm loss: 2.051371E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.076 | TFLOPs: 23.48 | +63: iteration 29500/ 73814 | consumed samples: 15104000 | consumed tokens: 30932992000 | elapsed time per iteration (s): 2.26 | learning rate: 1.395E-04 | global batch size: 512 | lm loss: 4.419505E+00 | grad norm: 17.919 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.018 | TFLOPs: 23.37 | +63: iteration 29510/ 73814 | consumed samples: 15109120 | consumed tokens: 30943477760 | elapsed time per iteration (s): 2.26 | learning rate: 1.395E-04 | global batch size: 512 | lm loss: 3.729651E+00 | grad norm: 2.416 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.314 | TFLOPs: 23.30 | +63: iteration 29520/ 73814 | consumed samples: 15114240 | consumed tokens: 30953963520 | elapsed time per iteration (s): 2.25 | learning rate: 1.395E-04 | global batch size: 512 | lm loss: 2.423659E+00 | grad norm: 0.791 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.538 | TFLOPs: 23.42 | +63: iteration 29530/ 73814 | consumed samples: 15119360 | consumed tokens: 30964449280 | elapsed time per iteration (s): 2.23 | learning rate: 1.394E-04 | global batch size: 512 | lm loss: 2.217248E+00 | grad norm: 3.712 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.637 | TFLOPs: 23.64 | +63: iteration 29540/ 73814 | consumed samples: 15124480 | consumed tokens: 30974935040 | elapsed time per iteration (s): 2.23 | learning rate: 1.394E-04 | global batch size: 512 | lm loss: 2.180715E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.984 | TFLOPs: 23.68 | +63: iteration 29550/ 73814 | consumed samples: 15129600 | consumed tokens: 30985420800 | elapsed time per iteration (s): 2.23 | learning rate: 1.393E-04 | global batch size: 512 | lm loss: 2.120257E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.030 | TFLOPs: 23.68 | +63: iteration 29560/ 73814 | consumed samples: 15134720 | consumed tokens: 30995906560 | elapsed time per iteration (s): 2.23 | learning rate: 1.393E-04 | global batch size: 512 | lm loss: 2.098431E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.794 | TFLOPs: 23.66 | +63: iteration 29570/ 73814 | consumed samples: 15139840 | consumed tokens: 31006392320 | elapsed time per iteration (s): 2.23 | learning rate: 1.393E-04 | global batch size: 512 | lm loss: 2.076287E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.167 | TFLOPs: 23.59 | +63: iteration 29580/ 73814 | consumed samples: 15144960 | consumed tokens: 31016878080 | elapsed time per iteration (s): 2.23 | learning rate: 1.392E-04 | global batch size: 512 | lm loss: 2.099829E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.081 | TFLOPs: 23.69 | +63: iteration 29590/ 73814 | consumed samples: 15150080 | consumed tokens: 31027363840 | elapsed time per iteration (s): 2.25 | learning rate: 1.392E-04 | global batch size: 512 | lm loss: 2.095981E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.671 | TFLOPs: 23.44 | +63: iteration 29600/ 73814 | consumed samples: 15155200 | consumed tokens: 31037849600 | elapsed time per iteration (s): 2.23 | learning rate: 1.392E-04 | global batch size: 512 | lm loss: 2.094294E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.315 | TFLOPs: 23.61 | +63: iteration 29610/ 73814 | consumed samples: 15160320 | consumed tokens: 31048335360 | elapsed time per iteration (s): 2.26 | learning rate: 1.391E-04 | global batch size: 512 | lm loss: 2.089132E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.870 | TFLOPs: 23.36 | +63: iteration 29620/ 73814 | consumed samples: 15165440 | consumed tokens: 31058821120 | elapsed time per iteration (s): 2.23 | learning rate: 1.391E-04 | global batch size: 512 | lm loss: 2.103479E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.177 | TFLOPs: 23.59 | +63: iteration 29630/ 73814 | consumed samples: 15170560 | consumed tokens: 31069306880 | elapsed time per iteration (s): 2.36 | learning rate: 1.391E-04 | global batch size: 512 | lm loss: 2.099667E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.284 | TFLOPs: 22.37 | +63: iteration 29640/ 73814 | consumed samples: 15175680 | consumed tokens: 31079792640 | elapsed time per iteration (s): 2.22 | learning rate: 1.390E-04 | global batch size: 512 | lm loss: 2.082645E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.258 | TFLOPs: 23.70 | +63: iteration 29650/ 73814 | consumed samples: 15180800 | consumed tokens: 31090278400 | elapsed time per iteration (s): 2.26 | learning rate: 1.390E-04 | global batch size: 512 | lm loss: 2.088020E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.170 | TFLOPs: 23.28 | +63: iteration 29660/ 73814 | consumed samples: 15185920 | consumed tokens: 31100764160 | elapsed time per iteration (s): 2.23 | learning rate: 1.389E-04 | global batch size: 512 | lm loss: 2.108599E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.113 | TFLOPs: 23.59 | +63: iteration 29670/ 73814 | consumed samples: 15191040 | consumed tokens: 31111249920 | elapsed time per iteration (s): 5.13 | learning rate: 1.389E-04 | global batch size: 512 | lm loss: 2.090464E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 99.817 | TFLOPs: 10.28 | +63: iteration 29680/ 73814 | consumed samples: 15196160 | consumed tokens: 31121735680 | elapsed time per iteration (s): 2.23 | learning rate: 1.389E-04 | global batch size: 512 | lm loss: 2.085756E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.088 | TFLOPs: 23.69 | +63: iteration 29690/ 73814 | consumed samples: 15201280 | consumed tokens: 31132221440 | elapsed time per iteration (s): 2.24 | learning rate: 1.388E-04 | global batch size: 512 | lm loss: 2.072640E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.633 | TFLOPs: 23.54 | +63: iteration 29700/ 73814 | consumed samples: 15206400 | consumed tokens: 31142707200 | elapsed time per iteration (s): 2.23 | learning rate: 1.388E-04 | global batch size: 512 | lm loss: 2.071636E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.814 | TFLOPs: 23.66 | +63: iteration 29710/ 73814 | consumed samples: 15211520 | consumed tokens: 31153192960 | elapsed time per iteration (s): 3.31 | learning rate: 1.388E-04 | global batch size: 512 | lm loss: 2.058948E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 154.766 | TFLOPs: 15.93 | +63: iteration 29720/ 73814 | consumed samples: 15216640 | consumed tokens: 31163678720 | elapsed time per iteration (s): 2.23 | learning rate: 1.387E-04 | global batch size: 512 | lm loss: 2.069641E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.615 | TFLOPs: 23.64 | +63: iteration 29730/ 73814 | consumed samples: 15221760 | consumed tokens: 31174164480 | elapsed time per iteration (s): 2.26 | learning rate: 1.387E-04 | global batch size: 512 | lm loss: 2.068663E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.923 | TFLOPs: 23.36 | +63: iteration 29740/ 73814 | consumed samples: 15226880 | consumed tokens: 31184650240 | elapsed time per iteration (s): 2.22 | learning rate: 1.387E-04 | global batch size: 512 | lm loss: 2.083752E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.191 | TFLOPs: 23.70 | +63: iteration 29750/ 73814 | consumed samples: 15232000 | consumed tokens: 31195136000 | elapsed time per iteration (s): 2.26 | learning rate: 1.386E-04 | global batch size: 512 | lm loss: 2.095756E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.386 | TFLOPs: 23.31 | +63: iteration 29760/ 73814 | consumed samples: 15237120 | consumed tokens: 31205621760 | elapsed time per iteration (s): 2.25 | learning rate: 1.386E-04 | global batch size: 512 | lm loss: 2.077236E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.689 | TFLOPs: 23.44 | +63: iteration 29770/ 73814 | consumed samples: 15242240 | consumed tokens: 31216107520 | elapsed time per iteration (s): 2.28 | learning rate: 1.385E-04 | global batch size: 512 | lm loss: 2.067817E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.329 | TFLOPs: 23.09 | +63: iteration 29780/ 73814 | consumed samples: 15247360 | consumed tokens: 31226593280 | elapsed time per iteration (s): 2.24 | learning rate: 1.385E-04 | global batch size: 512 | lm loss: 2.074988E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.786 | TFLOPs: 23.55 | +63: iteration 29790/ 73814 | consumed samples: 15252480 | consumed tokens: 31237079040 | elapsed time per iteration (s): 2.24 | learning rate: 1.385E-04 | global batch size: 512 | lm loss: 2.083337E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.631 | TFLOPs: 23.54 | +63: iteration 29800/ 73814 | consumed samples: 15257600 | consumed tokens: 31247564800 | elapsed time per iteration (s): 2.33 | learning rate: 1.384E-04 | global batch size: 512 | lm loss: 2.085886E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.022 | TFLOPs: 22.65 | +63: iteration 29810/ 73814 | consumed samples: 15262720 | consumed tokens: 31258050560 | elapsed time per iteration (s): 2.25 | learning rate: 1.384E-04 | global batch size: 512 | lm loss: 2.067494E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.890 | TFLOPs: 23.46 | +63: iteration 29820/ 73814 | consumed samples: 15267840 | consumed tokens: 31268536320 | elapsed time per iteration (s): 2.25 | learning rate: 1.384E-04 | global batch size: 512 | lm loss: 2.076352E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.023 | TFLOPs: 23.47 | +63: iteration 29830/ 73814 | consumed samples: 15272960 | consumed tokens: 31279022080 | elapsed time per iteration (s): 2.23 | learning rate: 1.383E-04 | global batch size: 512 | lm loss: 2.115195E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.564 | TFLOPs: 23.63 | +63: iteration 29840/ 73814 | consumed samples: 15278080 | consumed tokens: 31289507840 | elapsed time per iteration (s): 2.27 | learning rate: 1.383E-04 | global batch size: 512 | lm loss: 2.080920E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.872 | TFLOPs: 23.25 | +63: iteration 29850/ 73814 | consumed samples: 15283200 | consumed tokens: 31299993600 | elapsed time per iteration (s): 2.25 | learning rate: 1.382E-04 | global batch size: 512 | lm loss: 2.065294E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.520 | TFLOPs: 23.42 | +63: iteration 29860/ 73814 | consumed samples: 15288320 | consumed tokens: 31310479360 | elapsed time per iteration (s): 2.32 | learning rate: 1.382E-04 | global batch size: 512 | lm loss: 2.086000E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.357 | TFLOPs: 22.68 | +63: iteration 29870/ 73814 | consumed samples: 15293440 | consumed tokens: 31320965120 | elapsed time per iteration (s): 2.23 | learning rate: 1.382E-04 | global batch size: 512 | lm loss: 2.071279E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.861 | TFLOPs: 23.66 | +63: iteration 29880/ 73814 | consumed samples: 15298560 | consumed tokens: 31331450880 | elapsed time per iteration (s): 2.28 | learning rate: 1.381E-04 | global batch size: 512 | lm loss: 2.054107E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.814 | TFLOPs: 23.14 | +63: iteration 29890/ 73814 | consumed samples: 15303680 | consumed tokens: 31341936640 | elapsed time per iteration (s): 2.23 | learning rate: 1.381E-04 | global batch size: 512 | lm loss: 2.105272E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.598 | TFLOPs: 23.64 | +63: iteration 29900/ 73814 | consumed samples: 15308800 | consumed tokens: 31352422400 | elapsed time per iteration (s): 2.25 | learning rate: 1.381E-04 | global batch size: 512 | lm loss: 2.067794E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.910 | TFLOPs: 23.46 | +63: iteration 29910/ 73814 | consumed samples: 15313920 | consumed tokens: 31362908160 | elapsed time per iteration (s): 2.24 | learning rate: 1.380E-04 | global batch size: 512 | lm loss: 2.070105E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.367 | TFLOPs: 23.51 | +63: iteration 29920/ 73814 | consumed samples: 15319040 | consumed tokens: 31373393920 | elapsed time per iteration (s): 2.26 | learning rate: 1.380E-04 | global batch size: 512 | lm loss: 2.100590E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.741 | TFLOPs: 23.34 | +63: iteration 29930/ 73814 | consumed samples: 15324160 | consumed tokens: 31383879680 | elapsed time per iteration (s): 2.24 | learning rate: 1.380E-04 | global batch size: 512 | lm loss: 2.097984E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.649 | TFLOPs: 23.54 | +63: iteration 29940/ 73814 | consumed samples: 15329280 | consumed tokens: 31394365440 | elapsed time per iteration (s): 2.23 | learning rate: 1.379E-04 | global batch size: 512 | lm loss: 2.089626E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.998 | TFLOPs: 23.68 | +63: iteration 29950/ 73814 | consumed samples: 15334400 | consumed tokens: 31404851200 | elapsed time per iteration (s): 2.27 | learning rate: 1.379E-04 | global batch size: 512 | lm loss: 2.084548E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.390 | TFLOPs: 23.20 | +63: iteration 29960/ 73814 | consumed samples: 15339520 | consumed tokens: 31415336960 | elapsed time per iteration (s): 2.22 | learning rate: 1.378E-04 | global batch size: 512 | lm loss: 2.087811E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.157 | TFLOPs: 23.69 | +63: iteration 29970/ 73814 | consumed samples: 15344640 | consumed tokens: 31425822720 | elapsed time per iteration (s): 2.25 | learning rate: 1.378E-04 | global batch size: 512 | lm loss: 2.067095E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.429 | TFLOPs: 23.41 | +63: iteration 29980/ 73814 | consumed samples: 15349760 | consumed tokens: 31436308480 | elapsed time per iteration (s): 2.22 | learning rate: 1.378E-04 | global batch size: 512 | lm loss: 2.056159E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.126 | TFLOPs: 23.69 | +63: iteration 29990/ 73814 | consumed samples: 15354880 | consumed tokens: 31446794240 | elapsed time per iteration (s): 2.23 | learning rate: 1.377E-04 | global batch size: 512 | lm loss: 2.091820E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.239 | TFLOPs: 23.60 | + 0: [2022-12-02 06:47:31,739] [INFO] [logging.py:68:log_dist] [Rank 0] step=30000, skipped=0, lr=[0.00013769611999540015, 0.00013769611999540015, 0.00013769611999540015], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] + 0: steps: 30000 loss: 2.0774 iter time (s): 2.289 samples/sec: 223.659 +63: iteration 30000/ 73814 | consumed samples: 15360000 | consumed tokens: 31457280000 | elapsed time per iteration (s): 2.23 | learning rate: 1.377E-04 | global batch size: 512 | lm loss: 2.062954E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.453 | TFLOPs: 23.62 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 30000 | lm loss value: 2.000404E+00 | lm loss PPL: 7.392043E+00 | +63: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 30000 to checkpoints_3b977boscar + 0: [2022-12-02 06:47:32,576] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step30000 is begin to save! +32: [2022-12-02 06:47:32,620] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_21-model_00-model_states.pt... + 0: [2022-12-02 06:47:32,624] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_01-model_00-model_states.pt... +32: [2022-12-02 06:47:33,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_21-model_00-model_states.pt. +32: [2022-12-02 06:47:33,144] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_22-model_00-model_states.pt... + 0: [2022-12-02 06:47:33,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_01-model_00-model_states.pt. + 0: [2022-12-02 06:47:33,180] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_03-model_00-model_states.pt... +32: [2022-12-02 06:47:33,377] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_22-model_00-model_states.pt. +32: [2022-12-02 06:47:33,377] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_23-model_00-model_states.pt... + 0: [2022-12-02 06:47:33,408] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_03-model_00-model_states.pt. + 0: [2022-12-02 06:47:33,409] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_04-model_00-model_states.pt... +32: [2022-12-02 06:47:33,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_23-model_00-model_states.pt. +32: [2022-12-02 06:47:33,602] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_24-model_00-model_states.pt... + 0: [2022-12-02 06:47:33,642] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_04-model_00-model_states.pt. + 0: [2022-12-02 06:47:33,642] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_05-model_00-model_states.pt... +32: [2022-12-02 06:47:33,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_24-model_00-model_states.pt. +32: [2022-12-02 06:47:33,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_25-model_00-model_states.pt... + 0: [2022-12-02 06:47:33,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_05-model_00-model_states.pt. + 0: [2022-12-02 06:47:33,865] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_06-model_00-model_states.pt... +32: [2022-12-02 06:47:34,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_25-model_00-model_states.pt. +32: [2022-12-02 06:47:34,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_26-model_00-model_states.pt... + 0: [2022-12-02 06:47:34,092] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_06-model_00-model_states.pt. + 0: [2022-12-02 06:47:34,093] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_07-model_00-model_states.pt... +32: [2022-12-02 06:47:34,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_26-model_00-model_states.pt. +32: [2022-12-02 06:47:34,283] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_27-model_00-model_states.pt... + 0: [2022-12-02 06:47:34,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_07-model_00-model_states.pt. + 0: [2022-12-02 06:47:34,322] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_08-model_00-model_states.pt... +32: [2022-12-02 06:47:34,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_27-model_00-model_states.pt. +32: [2022-12-02 06:47:34,511] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_28-model_00-model_states.pt... + 0: [2022-12-02 06:47:34,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_08-model_00-model_states.pt. + 0: [2022-12-02 06:47:34,547] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_09-model_00-model_states.pt... +32: [2022-12-02 06:47:34,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_28-model_00-model_states.pt. +32: [2022-12-02 06:47:34,743] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_29-model_00-model_states.pt... + 0: [2022-12-02 06:47:34,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_09-model_00-model_states.pt. + 0: [2022-12-02 06:47:34,777] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_10-model_00-model_states.pt... +32: [2022-12-02 06:47:34,970] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_29-model_00-model_states.pt. +32: [2022-12-02 06:47:34,971] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_30-model_00-model_states.pt... + 0: [2022-12-02 06:47:35,005] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_10-model_00-model_states.pt. + 0: [2022-12-02 06:47:35,005] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_11-model_00-model_states.pt... +32: [2022-12-02 06:47:35,196] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_30-model_00-model_states.pt. +32: [2022-12-02 06:47:35,197] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_31-model_00-model_states.pt... + 0: [2022-12-02 06:47:35,232] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_11-model_00-model_states.pt. + 0: [2022-12-02 06:47:35,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_12-model_00-model_states.pt... +32: [2022-12-02 06:47:35,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_31-model_00-model_states.pt. +32: [2022-12-02 06:47:35,422] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_32-model_00-model_states.pt... + 0: [2022-12-02 06:47:35,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_12-model_00-model_states.pt. + 0: [2022-12-02 06:47:35,462] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_13-model_00-model_states.pt... +32: [2022-12-02 06:47:35,646] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_32-model_00-model_states.pt. +32: [2022-12-02 06:47:35,647] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_33-model_00-model_states.pt... + 0: [2022-12-02 06:47:35,684] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_13-model_00-model_states.pt. + 0: [2022-12-02 06:47:35,685] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_14-model_00-model_states.pt... +32: [2022-12-02 06:47:35,879] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_33-model_00-model_states.pt. +32: [2022-12-02 06:47:35,879] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_34-model_00-model_states.pt... + 0: [2022-12-02 06:47:35,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 06:47:35,916] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_15-model_00-model_states.pt... +32: [2022-12-02 06:47:36,107] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_34-model_00-model_states.pt. +32: [2022-12-02 06:47:36,107] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_35-model_00-model_states.pt... + 0: [2022-12-02 06:47:36,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_15-model_00-model_states.pt. + 0: [2022-12-02 06:47:36,143] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_16-model_00-model_states.pt... +32: [2022-12-02 06:47:36,330] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_35-model_00-model_states.pt. +32: [2022-12-02 06:47:36,330] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_36-model_00-model_states.pt... + 0: [2022-12-02 06:47:36,377] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_16-model_00-model_states.pt. + 0: [2022-12-02 06:47:36,377] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_17-model_00-model_states.pt... +32: [2022-12-02 06:47:36,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_36-model_00-model_states.pt. +32: [2022-12-02 06:47:36,560] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_37-model_00-model_states.pt... + 0: [2022-12-02 06:47:36,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_17-model_00-model_states.pt. + 0: [2022-12-02 06:47:36,607] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_18-model_00-model_states.pt... +32: [2022-12-02 06:47:36,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_37-model_00-model_states.pt. +32: [2022-12-02 06:47:36,787] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_38-model_00-model_states.pt... + 0: [2022-12-02 06:47:36,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_18-model_00-model_states.pt. + 0: [2022-12-02 06:47:36,837] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_19-model_00-model_states.pt... +32: [2022-12-02 06:47:37,012] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_38-model_00-model_states.pt. +32: [2022-12-02 06:47:37,012] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_40-model_00-model_states.pt... +32: [2022-12-02 06:47:37,016] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_40-model_00-model_states.pt. +32: [2022-12-02 06:47:37,017] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/mp_rank_01_model_states.pt... +32: [2022-12-02 06:47:37,048] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/mp_rank_01_model_states.pt. + 0: [2022-12-02 06:47:37,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_19-model_00-model_states.pt. + 0: [2022-12-02 06:47:37,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/layer_20-model_00-model_states.pt... + 0: [2022-12-02 06:47:37,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/layer_20-model_00-model_states.pt. + 0: [2022-12-02 06:47:37,290] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_3b977boscar/global_step30000/mp_rank_00_model_states.pt + 0: [2022-12-02 06:47:37,291] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/mp_rank_00_model_states.pt... + 0: [2022-12-02 06:47:37,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/mp_rank_00_model_states.pt. +52: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt... +48: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt... +48: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt... +48: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt... +48: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt... +48: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt... +43: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt... +43: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt... +43: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt... +43: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt... +43: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt... +32: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt... +60: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt... +60: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt... +60: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt... +60: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt... +60: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt... +55: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt... +55: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt... +55: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt... +55: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt... +54: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt... +54: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt... +54: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt... +54: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt... +54: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt... +56: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt... +56: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt... +56: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt... +56: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt... +56: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt... +52: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt... +52: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt... +52: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt... +52: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt... +52: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt... +61: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt... +61: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt... +61: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt... +61: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt... +61: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt... +63: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt... +63: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt... +63: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt... +63: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt... +63: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt... +53: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt... +53: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt... +53: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt... +53: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt... +53: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt... +33: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt... +33: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt... +33: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt... +33: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt... +33: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt... +59: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt... +59: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt... +62: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt... +62: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt... +62: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt... +62: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt... +62: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt... +58: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt... +58: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt... +58: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt... +58: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt... +58: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt... +38: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt... +38: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt... +38: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt... +38: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt... +38: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt... +44: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt... +44: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt... +44: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt... +44: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt... +44: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt... +48: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt... +34: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt... +34: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt... +34: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt... +34: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt... +43: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt... +36: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt... +36: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt... +36: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt... +36: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt... +36: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt... +35: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt... +35: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt... +35: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt... +35: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt... +35: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt... +39: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt... +39: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt... +39: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt... +39: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt... +39: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt... +50: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt... +50: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt... +50: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt... +50: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt... +50: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt... +32: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt... +32: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt... +32: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt... +51: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt... +51: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt... +51: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt... +51: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt... +51: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt... +60: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt... +60: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt... +60: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt... +49: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt... +49: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt... +49: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt... +49: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt... +49: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt... +46: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt... +46: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt... +46: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt... +46: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt... +46: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt... +41: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt... +41: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt... +41: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt... +41: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt... +41: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt... +55: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt... +55: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt... +55: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt... +47: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt... +47: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt... +47: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt... +47: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt... +47: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt... +45: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt... +45: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt... +45: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt... +45: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt... +37: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt... +37: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt... +37: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt... +37: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt... +37: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt... +40: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt... +40: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt... +40: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt... +40: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt... +40: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt... +42: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt... +42: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt... +42: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt... +42: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt... +42: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt... +57: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt... +57: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt... +57: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt... + 0: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +54: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt... +56: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt... +56: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt... +56: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt... +52: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt... +61: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt... +61: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt... +63: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt... +53: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt... +53: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt... +33: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt... +59: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt... +59: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt... +59: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt... +59: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt... +59: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt... +62: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt... +62: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt... +58: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt... +58: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt... +38: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt... +38: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt... +38: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt... +44: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt... +48: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt... +34: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt... +43: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt... +43: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt... +36: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt... +36: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt... +35: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt... +35: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt... +39: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt... +39: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt... +39: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt... +50: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt... +50: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt... +50: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt... +32: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt... +51: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt... +51: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt... +49: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt... +49: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt... +46: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt... +41: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt... +41: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt... +41: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt... +55: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt... +47: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt... +47: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt... +45: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt... +45: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt... +45: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt... +45: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt... +37: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt... +37: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt... +40: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt... +42: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt... +42: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt... +42: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt... +57: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt... +57: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt... +57: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt... +57: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt... + 0: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +54: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt... +54: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt... +52: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt... +61: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt... +63: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt... +53: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt... +33: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt... +33: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt... +59: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt... +62: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt... +58: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt... +26: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +44: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt... +44: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt... +48: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt... +34: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt... +36: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt... +35: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt... +32: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt... +51: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt... +49: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt... +46: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt... +47: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt... +37: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt... +40: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt... +40: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt... +57: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt... + 0: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 7: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +20: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +63: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt... +15: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... + 1: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +11: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... + 5: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +10: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +28: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +22: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +22: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +18: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +26: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +34: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt... + 9: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 2: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +25: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +32: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt... + 4: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 6: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +13: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +31: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +46: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt... + 3: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +27: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... + 8: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +16: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +14: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +17: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +29: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +30: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +24: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +24: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +23: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +21: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... + 0: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 7: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +19: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +20: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +15: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... + 1: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +11: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... + 5: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +10: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +28: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +22: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +12: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +18: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +26: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +34: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt... + 9: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 2: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +25: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +32: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt... + 4: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 6: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +13: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +31: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... + 3: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +27: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... + 8: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... +16: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +14: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +17: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +29: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +30: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +24: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +23: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +21: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... + 0: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 0: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 7: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +19: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +20: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +15: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... + 1: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +11: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 5: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +10: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +28: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +22: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +12: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +18: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +26: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... + 9: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 2: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +25: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... + 4: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 6: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +13: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +31: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... + 3: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +27: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... + 8: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... +16: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +14: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +17: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +29: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +30: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +21: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... + 0: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 7: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +19: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +20: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +15: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... + 1: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +11: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... + 5: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +10: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +28: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +22: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +12: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +18: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +26: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... + 9: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 2: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +25: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... + 4: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +13: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +31: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... + 3: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +27: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... + 8: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +16: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +17: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +29: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +30: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +23: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +21: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... + 0: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 7: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +19: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +15: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... + 1: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +11: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... + 5: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +28: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +22: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +12: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +18: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... + 2: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +25: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... + 4: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +13: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +31: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... + 3: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +27: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... + 8: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... +16: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +14: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +17: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +21: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +19: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +15: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... + 5: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +28: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +22: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +12: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... + 2: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +25: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... + 4: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 3: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 8: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... +16: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +14: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +29: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +23: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +21: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +19: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +15: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... + 5: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +12: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +25: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... + 3: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 8: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... +16: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +29: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +21: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... + 5: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +29: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... + 8: [2022-12-02 06:47:37,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... +32: [2022-12-02 06:47:37,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt. +32: [2022-12-02 06:47:37,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt +32: [2022-12-02 06:47:37,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +32: [2022-12-02 06:47:37,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt. +32: [2022-12-02 06:47:37,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt +32: [2022-12-02 06:47:37,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-12-02 06:47:37,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-12-02 06:47:37,575] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-12-02 06:47:37,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-12-02 06:47:37,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-12-02 06:47:37,575] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-12-02 06:47:37,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +32: [2022-12-02 06:47:37,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt. +32: [2022-12-02 06:47:37,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt +32: [2022-12-02 06:47:37,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +32: [2022-12-02 06:47:37,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt. +32: [2022-12-02 06:47:37,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt +32: [2022-12-02 06:47:37,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +32: [2022-12-02 06:47:37,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt. +32: [2022-12-02 06:47:37,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt. +32: [2022-12-02 06:47:37,595] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt +32: [2022-12-02 06:47:37,595] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt +32: [2022-12-02 06:47:37,595] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +32: [2022-12-02 06:47:37,595] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +32: [2022-12-02 06:47:37,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt. +32: [2022-12-02 06:47:37,599] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt +32: [2022-12-02 06:47:37,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-12-02 06:47:37,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. + 0: [2022-12-02 06:47:37,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-12-02 06:47:37,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-12-02 06:47:37,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-12-02 06:47:37,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-12-02 06:47:37,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-12-02 06:47:37,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-12-02 06:47:37,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-12-02 06:47:37,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-12-02 06:47:37,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-12-02 06:47:37,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-12-02 06:47:37,616] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-12-02 06:47:37,616] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +32: [2022-12-02 06:47:37,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt. +32: [2022-12-02 06:47:37,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt +32: [2022-12-02 06:47:37,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-12-02 06:47:37,645] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-12-02 06:47:37,645] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-12-02 06:47:37,645] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +49: [2022-12-02 06:47:37,692] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt. +49: [2022-12-02 06:47:37,692] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt +49: [2022-12-02 06:47:37,692] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +49: [2022-12-02 06:47:37,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt. +49: [2022-12-02 06:47:37,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt. +49: [2022-12-02 06:47:37,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt +49: [2022-12-02 06:47:37,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +49: [2022-12-02 06:47:37,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt +49: [2022-12-02 06:47:37,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +20: [2022-12-02 06:47:37,697] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-12-02 06:47:37,697] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-12-02 06:47:37,697] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-12-02 06:47:37,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-12-02 06:47:37,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +20: [2022-12-02 06:47:37,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-12-02 06:47:37,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-12-02 06:47:37,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-12-02 06:47:37,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-12-02 06:47:37,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-12-02 06:47:37,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-12-02 06:47:37,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-12-02 06:47:37,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-12-02 06:47:37,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-12-02 06:47:37,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-12-02 06:47:37,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-12-02 06:47:37,701] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-12-02 06:47:37,701] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-12-02 06:47:37,702] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-12-02 06:47:37,702] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-12-02 06:47:37,702] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-12-02 06:47:37,702] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-12-02 06:47:37,702] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-12-02 06:47:37,702] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +43: [2022-12-02 06:47:37,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt. +43: [2022-12-02 06:47:37,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt. +43: [2022-12-02 06:47:37,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt. +43: [2022-12-02 06:47:37,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt +43: [2022-12-02 06:47:37,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt +43: [2022-12-02 06:47:37,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt +43: [2022-12-02 06:47:37,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +43: [2022-12-02 06:47:37,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +43: [2022-12-02 06:47:37,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +53: [2022-12-02 06:47:37,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt. +53: [2022-12-02 06:47:37,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt +53: [2022-12-02 06:47:37,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +53: [2022-12-02 06:47:37,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt. +53: [2022-12-02 06:47:37,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt +53: [2022-12-02 06:47:37,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +53: [2022-12-02 06:47:37,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt. +53: [2022-12-02 06:47:37,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt +53: [2022-12-02 06:47:37,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +53: [2022-12-02 06:47:37,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt. +53: [2022-12-02 06:47:37,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt +53: [2022-12-02 06:47:37,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +43: [2022-12-02 06:47:37,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt. +43: [2022-12-02 06:47:37,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt +43: [2022-12-02 06:47:37,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +43: [2022-12-02 06:47:37,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt. +53: [2022-12-02 06:47:37,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt. +43: [2022-12-02 06:47:37,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt +53: [2022-12-02 06:47:37,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt +43: [2022-12-02 06:47:37,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +53: [2022-12-02 06:47:37,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +43: [2022-12-02 06:47:37,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt. +43: [2022-12-02 06:47:37,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt +43: [2022-12-02 06:47:37,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-12-02 06:47:37,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-12-02 06:47:37,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-12-02 06:47:37,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-12-02 06:47:37,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-12-02 06:47:37,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-12-02 06:47:37,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-12-02 06:47:37,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-12-02 06:47:37,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +43: [2022-12-02 06:47:37,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt. +28: [2022-12-02 06:47:37,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-12-02 06:47:37,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-12-02 06:47:37,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-12-02 06:47:37,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-12-02 06:47:37,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-12-02 06:47:37,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +43: [2022-12-02 06:47:37,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt +28: [2022-12-02 06:47:37,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-12-02 06:47:37,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +43: [2022-12-02 06:47:37,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-12-02 06:47:37,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-12-02 06:47:37,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-12-02 06:47:37,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-12-02 06:47:37,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-12-02 06:47:37,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-12-02 06:47:37,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-12-02 06:47:37,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-12-02 06:47:37,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +45: [2022-12-02 06:47:37,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt. +45: [2022-12-02 06:47:37,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt. +45: [2022-12-02 06:47:37,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt. + 9: [2022-12-02 06:47:37,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-12-02 06:47:37,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-12-02 06:47:37,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 9: [2022-12-02 06:47:37,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-12-02 06:47:37,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-12-02 06:47:37,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 9: [2022-12-02 06:47:37,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-12-02 06:47:37,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-12-02 06:47:37,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 9: [2022-12-02 06:47:37,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-12-02 06:47:37,725] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-12-02 06:47:37,725] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +53: [2022-12-02 06:47:37,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt. +53: [2022-12-02 06:47:37,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt +53: [2022-12-02 06:47:37,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +53: [2022-12-02 06:47:37,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt. +53: [2022-12-02 06:47:37,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt. +53: [2022-12-02 06:47:37,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt +53: [2022-12-02 06:47:37,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt +53: [2022-12-02 06:47:37,731] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +53: [2022-12-02 06:47:37,731] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 9: [2022-12-02 06:47:37,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-12-02 06:47:37,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-12-02 06:47:37,733] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 9: [2022-12-02 06:47:37,733] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-12-02 06:47:37,733] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-12-02 06:47:37,733] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 9: [2022-12-02 06:47:37,733] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-12-02 06:47:37,733] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-12-02 06:47:37,733] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 9: [2022-12-02 06:47:37,733] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-12-02 06:47:37,733] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-12-02 06:47:37,733] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-12-02 06:47:37,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-12-02 06:47:37,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-12-02 06:47:37,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-12-02 06:47:37,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-12-02 06:47:37,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-12-02 06:47:37,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-12-02 06:47:37,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-12-02 06:47:37,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-12-02 06:47:37,738] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-12-02 06:47:37,738] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-12-02 06:47:37,738] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-12-02 06:47:37,738] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +55: [2022-12-02 06:47:37,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt. +55: [2022-12-02 06:47:37,739] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt +55: [2022-12-02 06:47:37,739] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +55: [2022-12-02 06:47:37,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt. +55: [2022-12-02 06:47:37,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt +55: [2022-12-02 06:47:37,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +55: [2022-12-02 06:47:37,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt. +55: [2022-12-02 06:47:37,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt +55: [2022-12-02 06:47:37,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +55: [2022-12-02 06:47:37,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt. +55: [2022-12-02 06:47:37,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt +55: [2022-12-02 06:47:37,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt. +55: [2022-12-02 06:47:37,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +55: [2022-12-02 06:47:37,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt +55: [2022-12-02 06:47:37,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +45: [2022-12-02 06:47:37,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt +45: [2022-12-02 06:47:37,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt +45: [2022-12-02 06:47:37,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt +45: [2022-12-02 06:47:37,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +45: [2022-12-02 06:47:37,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +45: [2022-12-02 06:47:37,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +45: [2022-12-02 06:47:37,734] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt. +45: [2022-12-02 06:47:37,734] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt. +45: [2022-12-02 06:47:37,734] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt +45: [2022-12-02 06:47:37,734] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt +45: [2022-12-02 06:47:37,734] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +45: [2022-12-02 06:47:37,734] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +55: [2022-12-02 06:47:37,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt. +55: [2022-12-02 06:47:37,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt. +55: [2022-12-02 06:47:37,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt. +55: [2022-12-02 06:47:37,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt +55: [2022-12-02 06:47:37,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt +55: [2022-12-02 06:47:37,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt +55: [2022-12-02 06:47:37,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +55: [2022-12-02 06:47:37,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +55: [2022-12-02 06:47:37,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-12-02 06:47:37,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-12-02 06:47:37,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-12-02 06:47:37,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-12-02 06:47:37,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-12-02 06:47:37,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-12-02 06:47:37,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-12-02 06:47:37,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-12-02 06:47:37,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-12-02 06:47:37,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +33: [2022-12-02 06:47:37,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt. +33: [2022-12-02 06:47:37,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt. +33: [2022-12-02 06:47:37,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt. +33: [2022-12-02 06:47:37,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt. +33: [2022-12-02 06:47:37,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt. +33: [2022-12-02 06:47:37,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt +33: [2022-12-02 06:47:37,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt +33: [2022-12-02 06:47:37,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt +33: [2022-12-02 06:47:37,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt +33: [2022-12-02 06:47:37,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt +33: [2022-12-02 06:47:37,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +33: [2022-12-02 06:47:37,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +33: [2022-12-02 06:47:37,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +33: [2022-12-02 06:47:37,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +33: [2022-12-02 06:47:37,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +46: [2022-12-02 06:47:37,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt. +46: [2022-12-02 06:47:37,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt +46: [2022-12-02 06:47:37,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +46: [2022-12-02 06:47:37,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt. +46: [2022-12-02 06:47:37,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt +46: [2022-12-02 06:47:37,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +46: [2022-12-02 06:47:37,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt. +46: [2022-12-02 06:47:37,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt. +46: [2022-12-02 06:47:37,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt. +46: [2022-12-02 06:47:37,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt +46: [2022-12-02 06:47:37,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt +46: [2022-12-02 06:47:37,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt +46: [2022-12-02 06:47:37,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +46: [2022-12-02 06:47:37,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +46: [2022-12-02 06:47:37,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +46: [2022-12-02 06:47:37,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt. +46: [2022-12-02 06:47:37,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt +46: [2022-12-02 06:47:37,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +46: [2022-12-02 06:47:37,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt. +46: [2022-12-02 06:47:37,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt +46: [2022-12-02 06:47:37,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +46: [2022-12-02 06:47:37,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt. +46: [2022-12-02 06:47:37,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt +46: [2022-12-02 06:47:37,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +33: [2022-12-02 06:47:37,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt. +33: [2022-12-02 06:47:37,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt +33: [2022-12-02 06:47:37,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +20: [2022-12-02 06:47:37,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-12-02 06:47:37,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-12-02 06:47:37,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-12-02 06:47:37,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-12-02 06:47:37,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +33: [2022-12-02 06:47:37,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt. +33: [2022-12-02 06:47:37,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt +33: [2022-12-02 06:47:37,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +33: [2022-12-02 06:47:37,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt. +17: [2022-12-02 06:47:37,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-12-02 06:47:37,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-12-02 06:47:37,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-12-02 06:47:37,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-12-02 06:47:37,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +33: [2022-12-02 06:47:37,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt +33: [2022-12-02 06:47:37,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-12-02 06:47:37,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-12-02 06:47:37,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-12-02 06:47:37,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-12-02 06:47:37,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-12-02 06:47:37,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-12-02 06:47:37,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-12-02 06:47:37,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-12-02 06:47:37,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-12-02 06:47:37,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt + 3: [2022-12-02 06:47:37,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +17: [2022-12-02 06:47:37,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-12-02 06:47:37,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-12-02 06:47:37,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-12-02 06:47:37,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-12-02 06:47:37,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-12-02 06:47:37,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-12-02 06:47:37,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-12-02 06:47:37,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-12-02 06:47:37,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-12-02 06:47:37,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-12-02 06:47:37,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-12-02 06:47:37,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-12-02 06:47:37,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-12-02 06:47:37,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-12-02 06:47:37,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-12-02 06:47:37,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-12-02 06:47:37,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-12-02 06:47:37,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-12-02 06:47:37,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-12-02 06:47:37,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-12-02 06:47:37,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-12-02 06:47:37,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-12-02 06:47:37,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-12-02 06:47:37,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-12-02 06:47:37,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-12-02 06:47:37,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-12-02 06:47:37,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-12-02 06:47:37,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-12-02 06:47:37,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-12-02 06:47:37,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-12-02 06:47:37,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-12-02 06:47:37,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-12-02 06:47:37,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-12-02 06:47:37,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +22: [2022-12-02 06:47:37,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-12-02 06:47:37,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +25: [2022-12-02 06:47:37,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-12-02 06:47:37,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +22: [2022-12-02 06:47:37,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-12-02 06:47:37,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-12-02 06:47:37,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +13: [2022-12-02 06:47:37,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-12-02 06:47:37,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-12-02 06:47:37,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +22: [2022-12-02 06:47:37,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-12-02 06:47:37,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-12-02 06:47:37,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +20: [2022-12-02 06:47:37,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +13: [2022-12-02 06:47:37,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-12-02 06:47:37,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-12-02 06:47:37,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-12-02 06:47:37,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-12-02 06:47:37,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-12-02 06:47:37,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-12-02 06:47:37,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +20: [2022-12-02 06:47:37,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +13: [2022-12-02 06:47:37,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +20: [2022-12-02 06:47:37,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-12-02 06:47:37,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-12-02 06:47:37,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-12-02 06:47:37,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-12-02 06:47:37,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +50: [2022-12-02 06:47:37,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt. +50: [2022-12-02 06:47:37,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt. +50: [2022-12-02 06:47:37,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt. +50: [2022-12-02 06:47:37,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt +50: [2022-12-02 06:47:37,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt +50: [2022-12-02 06:47:37,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +50: [2022-12-02 06:47:37,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +50: [2022-12-02 06:47:37,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt +50: [2022-12-02 06:47:37,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-12-02 06:47:37,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-12-02 06:47:37,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-12-02 06:47:37,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-12-02 06:47:37,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +49: [2022-12-02 06:47:37,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt. +49: [2022-12-02 06:47:37,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt +49: [2022-12-02 06:47:37,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +50: [2022-12-02 06:47:37,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt. +50: [2022-12-02 06:47:37,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt +44: [2022-12-02 06:47:37,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt. +44: [2022-12-02 06:47:37,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt. +44: [2022-12-02 06:47:37,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt. +50: [2022-12-02 06:47:37,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +44: [2022-12-02 06:47:37,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt. +44: [2022-12-02 06:47:37,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt +44: [2022-12-02 06:47:37,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt +44: [2022-12-02 06:47:37,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt +44: [2022-12-02 06:47:37,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt +44: [2022-12-02 06:47:37,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +44: [2022-12-02 06:47:37,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +44: [2022-12-02 06:47:37,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +44: [2022-12-02 06:47:37,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +50: [2022-12-02 06:47:37,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt. +50: [2022-12-02 06:47:37,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt +50: [2022-12-02 06:47:37,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +50: [2022-12-02 06:47:37,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt. +50: [2022-12-02 06:47:37,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt. +50: [2022-12-02 06:47:37,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt +50: [2022-12-02 06:47:37,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt +50: [2022-12-02 06:47:37,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +50: [2022-12-02 06:47:37,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +50: [2022-12-02 06:47:37,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt. +50: [2022-12-02 06:47:37,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt +50: [2022-12-02 06:47:37,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +43: [2022-12-02 06:47:37,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt. + 7: [2022-12-02 06:47:37,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-12-02 06:47:37,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-12-02 06:47:37,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-12-02 06:47:37,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-12-02 06:47:37,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +43: [2022-12-02 06:47:37,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt +43: [2022-12-02 06:47:37,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +60: [2022-12-02 06:47:37,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt. +60: [2022-12-02 06:47:37,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt. +60: [2022-12-02 06:47:37,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt. +60: [2022-12-02 06:47:37,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt. +60: [2022-12-02 06:47:37,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt. +60: [2022-12-02 06:47:37,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt. +60: [2022-12-02 06:47:37,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt. +60: [2022-12-02 06:47:37,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt. +60: [2022-12-02 06:47:37,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt +60: [2022-12-02 06:47:37,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt +60: [2022-12-02 06:47:37,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt +60: [2022-12-02 06:47:37,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt +60: [2022-12-02 06:47:37,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt +60: [2022-12-02 06:47:37,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt +60: [2022-12-02 06:47:37,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt +60: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +60: [2022-12-02 06:47:37,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt +60: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +60: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +60: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +60: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +60: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +60: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +60: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-12-02 06:47:37,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-12-02 06:47:37,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-12-02 06:47:37,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-12-02 06:47:37,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-12-02 06:47:37,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-12-02 06:47:37,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-12-02 06:47:37,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-12-02 06:47:37,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-12-02 06:47:37,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-12-02 06:47:37,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-12-02 06:47:37,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-12-02 06:47:37,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-12-02 06:47:37,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-12-02 06:47:37,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-12-02 06:47:37,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-12-02 06:47:37,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-12-02 06:47:37,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-12-02 06:47:37,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-12-02 06:47:37,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +37: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt. +37: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt. +37: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt. +37: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt. +37: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt. +58: [2022-12-02 06:47:37,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt. +58: [2022-12-02 06:47:37,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt. +58: [2022-12-02 06:47:37,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt. +58: [2022-12-02 06:47:37,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt. +58: [2022-12-02 06:47:37,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt. +58: [2022-12-02 06:47:37,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt. +58: [2022-12-02 06:47:37,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt. +58: [2022-12-02 06:47:37,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt. +58: [2022-12-02 06:47:37,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt +58: [2022-12-02 06:47:37,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt +58: [2022-12-02 06:47:37,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt +58: [2022-12-02 06:47:37,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt +58: [2022-12-02 06:47:37,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt +58: [2022-12-02 06:47:37,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt +58: [2022-12-02 06:47:37,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt +58: [2022-12-02 06:47:37,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt +45: [2022-12-02 06:47:37,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt. +58: [2022-12-02 06:47:37,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +58: [2022-12-02 06:47:37,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +58: [2022-12-02 06:47:37,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +58: [2022-12-02 06:47:37,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +58: [2022-12-02 06:47:37,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +58: [2022-12-02 06:47:37,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +58: [2022-12-02 06:47:37,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +58: [2022-12-02 06:47:37,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +45: [2022-12-02 06:47:37,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt +45: [2022-12-02 06:47:37,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +38: [2022-12-02 06:47:37,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt. +38: [2022-12-02 06:47:37,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt. +38: [2022-12-02 06:47:37,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt. +38: [2022-12-02 06:47:37,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt. +38: [2022-12-02 06:47:37,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt. +37: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt. +37: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt. +37: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt. +37: [2022-12-02 06:47:37,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt +37: [2022-12-02 06:47:37,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt +37: [2022-12-02 06:47:37,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt +37: [2022-12-02 06:47:37,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt +37: [2022-12-02 06:47:37,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt +37: [2022-12-02 06:47:37,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt +37: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +37: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +37: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +37: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +37: [2022-12-02 06:47:37,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt +38: [2022-12-02 06:47:37,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt. +38: [2022-12-02 06:47:37,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt. +37: [2022-12-02 06:47:37,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt +38: [2022-12-02 06:47:37,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt. +38: [2022-12-02 06:47:37,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt +38: [2022-12-02 06:47:37,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt +37: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +37: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +38: [2022-12-02 06:47:37,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt +37: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +37: [2022-12-02 06:47:37,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +38: [2022-12-02 06:47:37,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt +38: [2022-12-02 06:47:37,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt +38: [2022-12-02 06:47:37,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt +38: [2022-12-02 06:47:37,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt +38: [2022-12-02 06:47:37,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +38: [2022-12-02 06:47:37,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +38: [2022-12-02 06:47:37,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt +38: [2022-12-02 06:47:37,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +38: [2022-12-02 06:47:37,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +38: [2022-12-02 06:47:37,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +38: [2022-12-02 06:47:37,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +38: [2022-12-02 06:47:37,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +38: [2022-12-02 06:47:37,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-12-02 06:47:37,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +15: [2022-12-02 06:47:37,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-12-02 06:47:37,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-12-02 06:47:37,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-12-02 06:47:37,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-12-02 06:47:37,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +45: [2022-12-02 06:47:37,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt. +15: [2022-12-02 06:47:37,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-12-02 06:47:37,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-12-02 06:47:37,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-12-02 06:47:37,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-12-02 06:47:37,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-12-02 06:47:37,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-12-02 06:47:37,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-12-02 06:47:37,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-12-02 06:47:37,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-12-02 06:47:37,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +15: [2022-12-02 06:47:37,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +15: [2022-12-02 06:47:37,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +15: [2022-12-02 06:47:37,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +15: [2022-12-02 06:47:37,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +15: [2022-12-02 06:47:37,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +15: [2022-12-02 06:47:37,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +15: [2022-12-02 06:47:37,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-12-02 06:47:37,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-12-02 06:47:37,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +45: [2022-12-02 06:47:37,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt +30: [2022-12-02 06:47:37,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +45: [2022-12-02 06:47:37,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-12-02 06:47:37,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +61: [2022-12-02 06:47:37,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt. +61: [2022-12-02 06:47:37,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt. +61: [2022-12-02 06:47:37,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt. +61: [2022-12-02 06:47:37,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt. +61: [2022-12-02 06:47:37,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt. +44: [2022-12-02 06:47:37,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt. +44: [2022-12-02 06:47:37,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt +44: [2022-12-02 06:47:37,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +61: [2022-12-02 06:47:37,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt. +61: [2022-12-02 06:47:37,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt. +61: [2022-12-02 06:47:37,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt. +61: [2022-12-02 06:47:37,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt +61: [2022-12-02 06:47:37,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt +61: [2022-12-02 06:47:37,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt +61: [2022-12-02 06:47:37,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt +61: [2022-12-02 06:47:37,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt +61: [2022-12-02 06:47:37,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt +61: [2022-12-02 06:47:37,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt +61: [2022-12-02 06:47:37,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt +61: [2022-12-02 06:47:37,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +61: [2022-12-02 06:47:37,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +61: [2022-12-02 06:47:37,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +61: [2022-12-02 06:47:37,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +61: [2022-12-02 06:47:37,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +61: [2022-12-02 06:47:37,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +61: [2022-12-02 06:47:37,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +61: [2022-12-02 06:47:37,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +44: [2022-12-02 06:47:37,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt. +36: [2022-12-02 06:47:37,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt. +36: [2022-12-02 06:47:37,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt. +36: [2022-12-02 06:47:37,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt. +36: [2022-12-02 06:47:37,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt. +36: [2022-12-02 06:47:37,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt. +19: [2022-12-02 06:47:37,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +44: [2022-12-02 06:47:37,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt +44: [2022-12-02 06:47:37,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +44: [2022-12-02 06:47:37,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt. +44: [2022-12-02 06:47:37,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt +44: [2022-12-02 06:47:37,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt. +44: [2022-12-02 06:47:37,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +44: [2022-12-02 06:47:37,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt +44: [2022-12-02 06:47:37,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +36: [2022-12-02 06:47:37,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt. +36: [2022-12-02 06:47:37,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt. +36: [2022-12-02 06:47:37,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt. +36: [2022-12-02 06:47:37,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt +36: [2022-12-02 06:47:37,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt +36: [2022-12-02 06:47:37,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt +36: [2022-12-02 06:47:37,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt +36: [2022-12-02 06:47:37,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt +36: [2022-12-02 06:47:37,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt +36: [2022-12-02 06:47:37,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt +36: [2022-12-02 06:47:37,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt +36: [2022-12-02 06:47:37,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +49: [2022-12-02 06:47:37,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt. +36: [2022-12-02 06:47:37,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +36: [2022-12-02 06:47:37,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +49: [2022-12-02 06:47:37,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt +36: [2022-12-02 06:47:37,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +49: [2022-12-02 06:47:37,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +36: [2022-12-02 06:47:37,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +36: [2022-12-02 06:47:37,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +36: [2022-12-02 06:47:37,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +36: [2022-12-02 06:47:37,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +20: [2022-12-02 06:47:37,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-12-02 06:47:37,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-12-02 06:47:37,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +45: [2022-12-02 06:47:37,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt. +19: [2022-12-02 06:47:37,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-12-02 06:47:37,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-12-02 06:47:37,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-12-02 06:47:37,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 5: [2022-12-02 06:47:37,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-12-02 06:47:37,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 2: [2022-12-02 06:47:37,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-12-02 06:47:37,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-12-02 06:47:37,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +35: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt. +35: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt. +35: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt. + 6: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +51: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt. +51: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt. +51: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt. +51: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt. +51: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt. + 4: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +47: [2022-12-02 06:47:37,805] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt. +47: [2022-12-02 06:47:37,805] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt. +47: [2022-12-02 06:47:37,805] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt. +47: [2022-12-02 06:47:37,805] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt. + 6: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-12-02 06:47:37,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-12-02 06:47:37,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-12-02 06:47:37,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-12-02 06:47:37,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-12-02 06:47:37,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +47: [2022-12-02 06:47:37,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt +47: [2022-12-02 06:47:37,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt + 6: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-12-02 06:47:37,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +47: [2022-12-02 06:47:37,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt +47: [2022-12-02 06:47:37,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt +47: [2022-12-02 06:47:37,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +47: [2022-12-02 06:47:37,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-12-02 06:47:37,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +47: [2022-12-02 06:47:37,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +47: [2022-12-02 06:47:37,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-12-02 06:47:37,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 4: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-12-02 06:47:37,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-12-02 06:47:37,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 4: [2022-12-02 06:47:37,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-12-02 06:47:37,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +51: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt. +51: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt. + 4: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 4: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +51: [2022-12-02 06:47:37,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt +51: [2022-12-02 06:47:37,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt +51: [2022-12-02 06:47:37,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt +51: [2022-12-02 06:47:37,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt +51: [2022-12-02 06:47:37,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt +51: [2022-12-02 06:47:37,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt +51: [2022-12-02 06:47:37,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt +51: [2022-12-02 06:47:37,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +51: [2022-12-02 06:47:37,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +51: [2022-12-02 06:47:37,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +51: [2022-12-02 06:47:37,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +35: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt. +35: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt. +51: [2022-12-02 06:47:37,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +51: [2022-12-02 06:47:37,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +35: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt. +35: [2022-12-02 06:47:37,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt +35: [2022-12-02 06:47:37,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt +35: [2022-12-02 06:47:37,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt +51: [2022-12-02 06:47:37,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +35: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +35: [2022-12-02 06:47:37,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt +35: [2022-12-02 06:47:37,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt +35: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +35: [2022-12-02 06:47:37,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt +35: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +51: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt. +35: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +35: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +51: [2022-12-02 06:47:37,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt +35: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +51: [2022-12-02 06:47:37,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 5: [2022-12-02 06:47:37,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-12-02 06:47:37,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-12-02 06:47:37,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-12-02 06:47:37,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-12-02 06:47:37,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +35: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt. + 5: [2022-12-02 06:47:37,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +35: [2022-12-02 06:47:37,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt + 5: [2022-12-02 06:47:37,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-12-02 06:47:37,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +35: [2022-12-02 06:47:37,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 5: [2022-12-02 06:47:37,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-12-02 06:47:37,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-12-02 06:47:37,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 5: [2022-12-02 06:47:37,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-12-02 06:47:37,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 5: [2022-12-02 06:47:37,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-12-02 06:47:37,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-12-02 06:47:37,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 5: [2022-12-02 06:47:37,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 5: [2022-12-02 06:47:37,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-12-02 06:47:37,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 5: [2022-12-02 06:47:37,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 5: [2022-12-02 06:47:37,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 5: [2022-12-02 06:47:37,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-12-02 06:47:37,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-12-02 06:47:37,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-12-02 06:47:37,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-12-02 06:47:37,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-12-02 06:47:37,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-12-02 06:47:37,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-12-02 06:47:37,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-12-02 06:47:37,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-12-02 06:47:37,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-12-02 06:47:37,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-12-02 06:47:37,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-12-02 06:47:37,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-12-02 06:47:37,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-12-02 06:47:37,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-12-02 06:47:37,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-12-02 06:47:37,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-12-02 06:47:37,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-12-02 06:47:37,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-12-02 06:47:37,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-12-02 06:47:37,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-12-02 06:47:37,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-12-02 06:47:37,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-12-02 06:47:37,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-12-02 06:47:37,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-12-02 06:47:37,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-12-02 06:47:37,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-12-02 06:47:37,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. + 2: [2022-12-02 06:47:37,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-12-02 06:47:37,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-12-02 06:47:37,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-12-02 06:47:37,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +45: [2022-12-02 06:47:37,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt +45: [2022-12-02 06:47:37,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +47: [2022-12-02 06:47:37,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt. +47: [2022-12-02 06:47:37,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt +47: [2022-12-02 06:47:37,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +47: [2022-12-02 06:47:37,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt. +47: [2022-12-02 06:47:37,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt + 2: [2022-12-02 06:47:37,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 2: [2022-12-02 06:47:37,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-12-02 06:47:37,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +47: [2022-12-02 06:47:37,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-12-02 06:47:37,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +47: [2022-12-02 06:47:37,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt. + 2: [2022-12-02 06:47:37,804] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 2: [2022-12-02 06:47:37,804] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-12-02 06:47:37,804] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-12-02 06:47:37,804] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-12-02 06:47:37,804] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-12-02 06:47:37,804] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-12-02 06:47:37,804] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-12-02 06:47:37,804] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +24: [2022-12-02 06:47:37,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-12-02 06:47:37,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-12-02 06:47:37,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-12-02 06:47:37,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-12-02 06:47:37,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +24: [2022-12-02 06:47:37,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +47: [2022-12-02 06:47:37,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt +47: [2022-12-02 06:47:37,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +47: [2022-12-02 06:47:37,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt. +47: [2022-12-02 06:47:37,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt +47: [2022-12-02 06:47:37,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 4: [2022-12-02 06:47:37,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +31: [2022-12-02 06:47:37,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-12-02 06:47:37,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-12-02 06:47:37,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-12-02 06:47:37,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-12-02 06:47:37,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-12-02 06:47:37,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +26: [2022-12-02 06:47:37,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-12-02 06:47:37,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-12-02 06:47:37,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-12-02 06:47:37,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-12-02 06:47:37,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-12-02 06:47:37,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-12-02 06:47:37,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-12-02 06:47:37,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-12-02 06:47:37,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-12-02 06:47:37,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-12-02 06:47:37,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-12-02 06:47:37,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-12-02 06:47:37,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-12-02 06:47:37,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-12-02 06:47:37,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-12-02 06:47:37,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-12-02 06:47:37,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +26: [2022-12-02 06:47:37,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +26: [2022-12-02 06:47:37,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +26: [2022-12-02 06:47:37,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +26: [2022-12-02 06:47:37,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +26: [2022-12-02 06:47:37,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +26: [2022-12-02 06:47:37,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +26: [2022-12-02 06:47:37,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-12-02 06:47:37,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +31: [2022-12-02 06:47:37,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-12-02 06:47:37,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-12-02 06:47:37,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-12-02 06:47:37,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-12-02 06:47:37,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-12-02 06:47:37,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-12-02 06:47:37,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-12-02 06:47:37,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-12-02 06:47:37,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +49: [2022-12-02 06:47:37,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt. + 4: [2022-12-02 06:47:37,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-12-02 06:47:37,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-12-02 06:47:37,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-12-02 06:47:37,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 4: [2022-12-02 06:47:37,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-12-02 06:47:37,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-12-02 06:47:37,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 4: [2022-12-02 06:47:37,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 4: [2022-12-02 06:47:37,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-12-02 06:47:37,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-12-02 06:47:37,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +49: [2022-12-02 06:47:37,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt +49: [2022-12-02 06:47:37,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-12-02 06:47:37,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-12-02 06:47:37,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-12-02 06:47:37,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-12-02 06:47:37,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-12-02 06:47:37,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-12-02 06:47:37,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-12-02 06:47:37,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-12-02 06:47:37,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-12-02 06:47:37,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-12-02 06:47:37,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-12-02 06:47:37,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-12-02 06:47:37,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-12-02 06:47:37,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-12-02 06:47:37,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-12-02 06:47:37,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-12-02 06:47:37,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-12-02 06:47:37,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-12-02 06:47:37,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +40: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt. +40: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt. +40: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt. +40: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt. +40: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt. +40: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt. +40: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt. +40: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt. +40: [2022-12-02 06:47:37,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt +40: [2022-12-02 06:47:37,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt +40: [2022-12-02 06:47:37,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt +40: [2022-12-02 06:47:37,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt +40: [2022-12-02 06:47:37,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt +40: [2022-12-02 06:47:37,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt +40: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +40: [2022-12-02 06:47:37,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt +40: [2022-12-02 06:47:37,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt +40: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +40: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +40: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +40: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +40: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +40: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +40: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-12-02 06:47:37,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-12-02 06:47:37,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +27: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +24: [2022-12-02 06:47:37,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-12-02 06:47:37,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-12-02 06:47:37,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +24: [2022-12-02 06:47:37,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-12-02 06:47:37,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-12-02 06:47:37,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +27: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-12-02 06:47:37,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-12-02 06:47:37,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-12-02 06:47:37,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-12-02 06:47:37,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +27: [2022-12-02 06:47:37,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +27: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +27: [2022-12-02 06:47:37,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-12-02 06:47:37,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +27: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +27: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +27: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +27: [2022-12-02 06:47:37,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-12-02 06:47:37,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-12-02 06:47:37,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +14: [2022-12-02 06:47:37,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-12-02 06:47:37,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-12-02 06:47:37,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-12-02 06:47:37,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-12-02 06:47:37,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-12-02 06:47:37,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-12-02 06:47:37,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-12-02 06:47:37,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-12-02 06:47:37,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-12-02 06:47:37,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-12-02 06:47:37,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-12-02 06:47:37,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-12-02 06:47:37,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-12-02 06:47:37,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-12-02 06:47:37,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-12-02 06:47:37,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-12-02 06:47:37,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +14: [2022-12-02 06:47:37,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +14: [2022-12-02 06:47:37,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +14: [2022-12-02 06:47:37,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +14: [2022-12-02 06:47:37,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +14: [2022-12-02 06:47:37,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +14: [2022-12-02 06:47:37,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +14: [2022-12-02 06:47:37,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +48: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt. +56: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt. +56: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt. +56: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt. +56: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt. +56: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt. +56: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt. +56: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt. +56: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt. +56: [2022-12-02 06:47:37,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt +56: [2022-12-02 06:47:37,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt +56: [2022-12-02 06:47:37,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt +56: [2022-12-02 06:47:37,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt +48: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt. +48: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt. +48: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt. +48: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt. +56: [2022-12-02 06:47:37,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt +56: [2022-12-02 06:47:37,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt +56: [2022-12-02 06:47:37,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt +56: [2022-12-02 06:47:37,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt +48: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt. +48: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt. +48: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt. +48: [2022-12-02 06:47:37,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt +56: [2022-12-02 06:47:37,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +56: [2022-12-02 06:47:37,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +56: [2022-12-02 06:47:37,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +48: [2022-12-02 06:47:37,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt +48: [2022-12-02 06:47:37,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt +56: [2022-12-02 06:47:37,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +56: [2022-12-02 06:47:37,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +48: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +56: [2022-12-02 06:47:37,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +48: [2022-12-02 06:47:37,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt +56: [2022-12-02 06:47:37,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +48: [2022-12-02 06:47:37,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt +56: [2022-12-02 06:47:37,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +48: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +48: [2022-12-02 06:47:37,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt +48: [2022-12-02 06:47:37,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt +48: [2022-12-02 06:47:37,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt +48: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +48: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +48: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +48: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +48: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +48: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +49: [2022-12-02 06:47:37,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt. +24: [2022-12-02 06:47:37,833] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-12-02 06:47:37,833] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-12-02 06:47:37,833] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +49: [2022-12-02 06:47:37,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt +49: [2022-12-02 06:47:37,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +49: [2022-12-02 06:47:37,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt. +49: [2022-12-02 06:47:37,832] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt +49: [2022-12-02 06:47:37,832] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-12-02 06:47:37,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-12-02 06:47:37,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-12-02 06:47:37,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +39: [2022-12-02 06:47:37,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt. +39: [2022-12-02 06:47:37,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt. +39: [2022-12-02 06:47:37,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt. +39: [2022-12-02 06:47:37,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt. +39: [2022-12-02 06:47:37,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt. +39: [2022-12-02 06:47:37,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt. +39: [2022-12-02 06:47:37,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt. +39: [2022-12-02 06:47:37,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt. +39: [2022-12-02 06:47:37,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt +39: [2022-12-02 06:47:37,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt +39: [2022-12-02 06:47:37,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt +39: [2022-12-02 06:47:37,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt +39: [2022-12-02 06:47:37,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +39: [2022-12-02 06:47:37,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt +39: [2022-12-02 06:47:37,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt +39: [2022-12-02 06:47:37,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt +39: [2022-12-02 06:47:37,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt +39: [2022-12-02 06:47:37,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +39: [2022-12-02 06:47:37,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +39: [2022-12-02 06:47:37,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +39: [2022-12-02 06:47:37,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +39: [2022-12-02 06:47:37,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +39: [2022-12-02 06:47:37,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +39: [2022-12-02 06:47:37,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-12-02 06:47:37,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +16: [2022-12-02 06:47:37,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-12-02 06:47:37,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-12-02 06:47:37,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-12-02 06:47:37,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-12-02 06:47:37,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-12-02 06:47:37,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-12-02 06:47:37,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-12-02 06:47:37,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-12-02 06:47:37,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-12-02 06:47:37,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-12-02 06:47:37,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-12-02 06:47:37,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-12-02 06:47:37,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-12-02 06:47:37,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-12-02 06:47:37,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-12-02 06:47:37,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-12-02 06:47:37,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-12-02 06:47:37,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-12-02 06:47:37,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-12-02 06:47:37,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-12-02 06:47:37,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-12-02 06:47:37,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-12-02 06:47:37,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +24: [2022-12-02 06:47:37,846] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-12-02 06:47:37,846] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-12-02 06:47:37,846] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-12-02 06:47:37,846] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-12-02 06:47:37,846] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-12-02 06:47:37,846] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-12-02 06:47:37,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-12-02 06:47:37,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-12-02 06:47:37,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +41: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt. +41: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt. +41: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt. +41: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt. +41: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt. +41: [2022-12-02 06:47:37,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt +41: [2022-12-02 06:47:37,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt +41: [2022-12-02 06:47:37,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt +41: [2022-12-02 06:47:37,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt +41: [2022-12-02 06:47:37,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt +41: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +41: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +41: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +63: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt. +63: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt. +63: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt. +63: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt. +41: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +41: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +41: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt. +41: [2022-12-02 06:47:37,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt +41: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +41: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt. +41: [2022-12-02 06:47:37,851] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt +41: [2022-12-02 06:47:37,851] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +63: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt. +63: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt. +63: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt. +63: [2022-12-02 06:47:37,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt +63: [2022-12-02 06:47:37,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt +63: [2022-12-02 06:47:37,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt +63: [2022-12-02 06:47:37,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt +63: [2022-12-02 06:47:37,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt +63: [2022-12-02 06:47:37,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt +63: [2022-12-02 06:47:37,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt +63: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +63: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt. +63: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +63: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +41: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt. +63: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +63: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +63: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +41: [2022-12-02 06:47:37,851] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt +63: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +63: [2022-12-02 06:47:37,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt +41: [2022-12-02 06:47:37,851] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +63: [2022-12-02 06:47:37,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +29: [2022-12-02 06:47:37,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-12-02 06:47:37,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-12-02 06:47:37,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-12-02 06:47:37,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-12-02 06:47:37,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-12-02 06:47:37,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-12-02 06:47:37,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-12-02 06:47:37,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-12-02 06:47:37,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-12-02 06:47:37,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-12-02 06:47:37,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-12-02 06:47:37,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-12-02 06:47:37,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-12-02 06:47:37,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-12-02 06:47:37,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-12-02 06:47:37,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-12-02 06:47:37,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +29: [2022-12-02 06:47:37,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +29: [2022-12-02 06:47:37,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +29: [2022-12-02 06:47:37,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +29: [2022-12-02 06:47:37,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +29: [2022-12-02 06:47:37,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +29: [2022-12-02 06:47:37,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +29: [2022-12-02 06:47:37,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +62: [2022-12-02 06:47:37,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt. +62: [2022-12-02 06:47:37,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt. +62: [2022-12-02 06:47:37,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt. +62: [2022-12-02 06:47:37,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt. +62: [2022-12-02 06:47:37,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt. +62: [2022-12-02 06:47:37,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt. +62: [2022-12-02 06:47:37,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt. +62: [2022-12-02 06:47:37,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt. +62: [2022-12-02 06:47:37,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt +62: [2022-12-02 06:47:37,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt +62: [2022-12-02 06:47:37,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt +62: [2022-12-02 06:47:37,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt +62: [2022-12-02 06:47:37,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt +62: [2022-12-02 06:47:37,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt +62: [2022-12-02 06:47:37,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt +62: [2022-12-02 06:47:37,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt +22: [2022-12-02 06:47:37,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +62: [2022-12-02 06:47:37,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +62: [2022-12-02 06:47:37,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +62: [2022-12-02 06:47:37,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +62: [2022-12-02 06:47:37,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +62: [2022-12-02 06:47:37,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +62: [2022-12-02 06:47:37,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +62: [2022-12-02 06:47:37,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +62: [2022-12-02 06:47:37,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-12-02 06:47:37,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-12-02 06:47:37,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +23: [2022-12-02 06:47:37,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-12-02 06:47:37,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-12-02 06:47:37,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-12-02 06:47:37,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-12-02 06:47:37,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-12-02 06:47:37,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-12-02 06:47:37,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-12-02 06:47:37,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-12-02 06:47:37,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-12-02 06:47:37,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-12-02 06:47:37,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +12: [2022-12-02 06:47:37,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-12-02 06:47:37,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +23: [2022-12-02 06:47:37,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +12: [2022-12-02 06:47:37,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +23: [2022-12-02 06:47:37,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +12: [2022-12-02 06:47:37,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +23: [2022-12-02 06:47:37,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +12: [2022-12-02 06:47:37,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-12-02 06:47:37,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +23: [2022-12-02 06:47:37,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +23: [2022-12-02 06:47:37,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +23: [2022-12-02 06:47:37,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-12-02 06:47:37,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +12: [2022-12-02 06:47:37,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +23: [2022-12-02 06:47:37,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +12: [2022-12-02 06:47:37,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +23: [2022-12-02 06:47:37,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +23: [2022-12-02 06:47:37,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +12: [2022-12-02 06:47:37,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-12-02 06:47:37,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +12: [2022-12-02 06:47:37,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-12-02 06:47:37,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-12-02 06:47:37,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-12-02 06:47:37,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-12-02 06:47:37,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +10: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-12-02 06:47:37,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-12-02 06:47:37,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-12-02 06:47:37,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-12-02 06:47:37,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +10: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +10: [2022-12-02 06:47:37,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +10: [2022-12-02 06:47:37,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-12-02 06:47:37,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-12-02 06:47:37,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +10: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +10: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +10: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +10: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-12-02 06:47:37,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +25: [2022-12-02 06:47:37,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. + 1: [2022-12-02 06:47:37,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-12-02 06:47:37,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-12-02 06:47:37,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-12-02 06:47:37,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-12-02 06:47:37,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-12-02 06:47:37,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-12-02 06:47:37,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-12-02 06:47:37,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-12-02 06:47:37,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-12-02 06:47:37,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-12-02 06:47:37,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-12-02 06:47:37,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-12-02 06:47:37,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-12-02 06:47:37,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-12-02 06:47:37,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-12-02 06:47:37,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +12: [2022-12-02 06:47:37,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-12-02 06:47:37,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-12-02 06:47:37,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-12-02 06:47:37,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-12-02 06:47:37,865] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-12-02 06:47:37,865] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-12-02 06:47:37,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-12-02 06:47:37,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-12-02 06:47:37,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +12: [2022-12-02 06:47:37,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +12: [2022-12-02 06:47:37,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +12: [2022-12-02 06:47:37,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +34: [2022-12-02 06:47:37,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt. +34: [2022-12-02 06:47:37,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt. +34: [2022-12-02 06:47:37,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt. +34: [2022-12-02 06:47:37,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt. +34: [2022-12-02 06:47:37,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt. +34: [2022-12-02 06:47:37,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt. +34: [2022-12-02 06:47:37,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt. +34: [2022-12-02 06:47:37,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt. +34: [2022-12-02 06:47:37,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt +34: [2022-12-02 06:47:37,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt +34: [2022-12-02 06:47:37,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt +34: [2022-12-02 06:47:37,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt +34: [2022-12-02 06:47:37,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt +34: [2022-12-02 06:47:37,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt +34: [2022-12-02 06:47:37,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt +34: [2022-12-02 06:47:37,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt +34: [2022-12-02 06:47:37,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +34: [2022-12-02 06:47:37,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +34: [2022-12-02 06:47:37,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +34: [2022-12-02 06:47:37,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +34: [2022-12-02 06:47:37,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +34: [2022-12-02 06:47:37,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +34: [2022-12-02 06:47:37,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +34: [2022-12-02 06:47:37,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-12-02 06:47:37,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-12-02 06:47:37,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-12-02 06:47:37,869] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-12-02 06:47:37,869] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-12-02 06:47:37,869] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-12-02 06:47:37,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-12-02 06:47:37,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-12-02 06:47:37,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-12-02 06:47:37,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-12-02 06:47:37,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-12-02 06:47:37,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-12-02 06:47:37,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-12-02 06:47:37,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-12-02 06:47:37,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-12-02 06:47:37,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-12-02 06:47:37,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-12-02 06:47:37,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-12-02 06:47:37,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-12-02 06:47:37,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-12-02 06:47:37,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-12-02 06:47:37,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-12-02 06:47:37,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-12-02 06:47:37,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-12-02 06:47:37,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-12-02 06:47:37,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-12-02 06:47:37,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-12-02 06:47:37,872] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-12-02 06:47:37,872] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-12-02 06:47:37,872] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +57: [2022-12-02 06:47:37,875] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt. +57: [2022-12-02 06:47:37,875] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt. +57: [2022-12-02 06:47:37,875] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt. +57: [2022-12-02 06:47:37,875] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt. +57: [2022-12-02 06:47:37,875] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt. +57: [2022-12-02 06:47:37,875] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt. +57: [2022-12-02 06:47:37,875] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt. +57: [2022-12-02 06:47:37,875] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt. +57: [2022-12-02 06:47:37,875] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt +57: [2022-12-02 06:47:37,875] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt +57: [2022-12-02 06:47:37,875] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt +57: [2022-12-02 06:47:37,875] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt +57: [2022-12-02 06:47:37,875] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt +57: [2022-12-02 06:47:37,875] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt +57: [2022-12-02 06:47:37,875] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt +57: [2022-12-02 06:47:37,875] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt +57: [2022-12-02 06:47:37,875] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +57: [2022-12-02 06:47:37,875] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +57: [2022-12-02 06:47:37,875] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +57: [2022-12-02 06:47:37,875] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +57: [2022-12-02 06:47:37,875] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +57: [2022-12-02 06:47:37,875] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +57: [2022-12-02 06:47:37,875] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +57: [2022-12-02 06:47:37,875] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +11: [2022-12-02 06:47:37,878] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-12-02 06:47:37,878] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-12-02 06:47:37,878] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-12-02 06:47:37,878] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-12-02 06:47:37,878] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-12-02 06:47:37,878] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-12-02 06:47:37,878] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-12-02 06:47:37,878] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-12-02 06:47:37,878] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +11: [2022-12-02 06:47:37,878] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +11: [2022-12-02 06:47:37,878] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +11: [2022-12-02 06:47:37,878] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-12-02 06:47:37,879] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-12-02 06:47:37,879] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-12-02 06:47:37,879] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-12-02 06:47:37,879] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +11: [2022-12-02 06:47:37,879] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-12-02 06:47:37,879] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +25: [2022-12-02 06:47:37,880] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +11: [2022-12-02 06:47:37,879] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-12-02 06:47:37,880] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-12-02 06:47:37,880] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +25: [2022-12-02 06:47:37,880] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +11: [2022-12-02 06:47:37,880] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-12-02 06:47:37,880] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +11: [2022-12-02 06:47:37,880] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +11: [2022-12-02 06:47:37,880] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +11: [2022-12-02 06:47:37,881] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-12-02 06:47:37,881] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-12-02 06:47:37,881] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +24: [2022-12-02 06:47:37,887] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-12-02 06:47:37,887] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-12-02 06:47:37,887] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-12-02 06:47:37,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-12-02 06:47:37,888] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-12-02 06:47:37,888] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +42: [2022-12-02 06:47:37,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt. +42: [2022-12-02 06:47:37,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt. +42: [2022-12-02 06:47:37,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt. +42: [2022-12-02 06:47:37,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt. +42: [2022-12-02 06:47:37,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt. +42: [2022-12-02 06:47:37,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt. +42: [2022-12-02 06:47:37,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt. +42: [2022-12-02 06:47:37,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt +42: [2022-12-02 06:47:37,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt +42: [2022-12-02 06:47:37,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt +42: [2022-12-02 06:47:37,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt +42: [2022-12-02 06:47:37,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt +42: [2022-12-02 06:47:37,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +42: [2022-12-02 06:47:37,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +42: [2022-12-02 06:47:37,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +42: [2022-12-02 06:47:37,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt +42: [2022-12-02 06:47:37,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt +42: [2022-12-02 06:47:37,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +42: [2022-12-02 06:47:37,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +42: [2022-12-02 06:47:37,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +42: [2022-12-02 06:47:37,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +52: [2022-12-02 06:47:37,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt. +52: [2022-12-02 06:47:37,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt. +52: [2022-12-02 06:47:37,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt. +52: [2022-12-02 06:47:37,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt. +52: [2022-12-02 06:47:37,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt. +52: [2022-12-02 06:47:37,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt. +52: [2022-12-02 06:47:37,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt. +52: [2022-12-02 06:47:37,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt. +52: [2022-12-02 06:47:37,891] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt +52: [2022-12-02 06:47:37,891] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt +52: [2022-12-02 06:47:37,891] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt +52: [2022-12-02 06:47:37,891] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt +52: [2022-12-02 06:47:37,891] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt +52: [2022-12-02 06:47:37,891] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt +52: [2022-12-02 06:47:37,891] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt +52: [2022-12-02 06:47:37,891] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt +52: [2022-12-02 06:47:37,891] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +52: [2022-12-02 06:47:37,891] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +52: [2022-12-02 06:47:37,891] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +52: [2022-12-02 06:47:37,891] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +52: [2022-12-02 06:47:37,891] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +54: [2022-12-02 06:47:37,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt. +54: [2022-12-02 06:47:37,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt. +52: [2022-12-02 06:47:37,891] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +52: [2022-12-02 06:47:37,891] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +54: [2022-12-02 06:47:37,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt. +52: [2022-12-02 06:47:37,891] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +54: [2022-12-02 06:47:37,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt +54: [2022-12-02 06:47:37,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt +54: [2022-12-02 06:47:37,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt. +54: [2022-12-02 06:47:37,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt +54: [2022-12-02 06:47:37,892] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +54: [2022-12-02 06:47:37,892] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +54: [2022-12-02 06:47:37,892] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +54: [2022-12-02 06:47:37,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt +54: [2022-12-02 06:47:37,892] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +54: [2022-12-02 06:47:37,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt. +54: [2022-12-02 06:47:37,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt. +54: [2022-12-02 06:47:37,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt. +54: [2022-12-02 06:47:37,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt. +54: [2022-12-02 06:47:37,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt +54: [2022-12-02 06:47:37,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt +54: [2022-12-02 06:47:37,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt +54: [2022-12-02 06:47:37,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt +54: [2022-12-02 06:47:37,892] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +54: [2022-12-02 06:47:37,892] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +54: [2022-12-02 06:47:37,892] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +24: [2022-12-02 06:47:37,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +54: [2022-12-02 06:47:37,892] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +24: [2022-12-02 06:47:37,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-12-02 06:47:37,892] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-12-02 06:47:37,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-12-02 06:47:37,893] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-12-02 06:47:37,893] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-12-02 06:47:37,893] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-12-02 06:47:37,893] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-12-02 06:47:37,893] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +35: [2022-12-02 06:47:37,895] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt. +35: [2022-12-02 06:47:37,895] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt +35: [2022-12-02 06:47:37,895] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +42: [2022-12-02 06:47:37,896] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt. +42: [2022-12-02 06:47:37,896] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt +42: [2022-12-02 06:47:37,896] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-12-02 06:47:37,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-12-02 06:47:37,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-12-02 06:47:37,908] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-12-02 06:47:37,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +59: [2022-12-02 06:47:37,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt. +59: [2022-12-02 06:47:37,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt. +59: [2022-12-02 06:47:37,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt. +59: [2022-12-02 06:47:37,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt. +59: [2022-12-02 06:47:37,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt. +59: [2022-12-02 06:47:37,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt. +59: [2022-12-02 06:47:37,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt. +59: [2022-12-02 06:47:37,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt. +59: [2022-12-02 06:47:37,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt +59: [2022-12-02 06:47:37,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt +59: [2022-12-02 06:47:37,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt +59: [2022-12-02 06:47:37,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt +59: [2022-12-02 06:47:37,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt +59: [2022-12-02 06:47:37,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt +59: [2022-12-02 06:47:37,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt +59: [2022-12-02 06:47:37,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt +59: [2022-12-02 06:47:37,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +59: [2022-12-02 06:47:37,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +59: [2022-12-02 06:47:37,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +59: [2022-12-02 06:47:37,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +59: [2022-12-02 06:47:37,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +59: [2022-12-02 06:47:37,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +59: [2022-12-02 06:47:37,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +59: [2022-12-02 06:47:37,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-12-02 06:47:37,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-12-02 06:47:37,915] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +20: [2022-12-02 06:47:37,924] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-12-02 06:47:37,924] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-12-02 06:47:37,924] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-12-02 06:47:37,924] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-12-02 06:47:37,924] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-12-02 06:47:37,924] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-12-02 06:47:37,925] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +20: [2022-12-02 06:47:37,925] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +20: [2022-12-02 06:47:37,925] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-12-02 06:47:37,938] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-12-02 06:47:37,938] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-12-02 06:47:37,938] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-12-02 06:47:37,941] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-12-02 06:47:37,941] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-12-02 06:47:37,941] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-12-02 06:47:37,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-12-02 06:47:37,943] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-12-02 06:47:37,943] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-12-02 06:47:37,978] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-12-02 06:47:37,978] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-12-02 06:47:37,978] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +23: [2022-12-02 06:47:37,993] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +23: [2022-12-02 06:47:37,993] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step30000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-12-02 06:47:37,993] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: successfully saved checkpoint at iteration 30000 to checkpoints_3b977boscar +63: time (ms) | save-checkpoint: 5553.18 +63: iteration 30010/ 73814 | consumed samples: 15365120 | consumed tokens: 31467765760 | elapsed time per iteration (s): 2.84 | learning rate: 1.377E-04 | global batch size: 512 | lm loss: 2.060954E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 180.064 | TFLOPs: 18.54 | +63: iteration 30020/ 73814 | consumed samples: 15370240 | consumed tokens: 31478251520 | elapsed time per iteration (s): 2.26 | learning rate: 1.376E-04 | global batch size: 512 | lm loss: 2.058377E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.046 | TFLOPs: 23.37 | +63: iteration 30030/ 73814 | consumed samples: 15375360 | consumed tokens: 31488737280 | elapsed time per iteration (s): 2.27 | learning rate: 1.376E-04 | global batch size: 512 | lm loss: 2.061256E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.994 | TFLOPs: 23.26 | +63: iteration 30040/ 73814 | consumed samples: 15380480 | consumed tokens: 31499223040 | elapsed time per iteration (s): 2.23 | learning rate: 1.375E-04 | global batch size: 512 | lm loss: 2.082942E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.016 | TFLOPs: 23.68 | +63: iteration 30050/ 73814 | consumed samples: 15385600 | consumed tokens: 31509708800 | elapsed time per iteration (s): 2.23 | learning rate: 1.375E-04 | global batch size: 512 | lm loss: 2.050968E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.571 | TFLOPs: 23.63 | +63: iteration 30060/ 73814 | consumed samples: 15390720 | consumed tokens: 31520194560 | elapsed time per iteration (s): 2.25 | learning rate: 1.375E-04 | global batch size: 512 | lm loss: 2.068657E+00 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.373 | TFLOPs: 23.41 | +63: iteration 30070/ 73814 | consumed samples: 15395840 | consumed tokens: 31530680320 | elapsed time per iteration (s): 2.23 | learning rate: 1.374E-04 | global batch size: 512 | lm loss: 2.056600E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.024 | TFLOPs: 23.68 | +63: iteration 30080/ 73814 | consumed samples: 15400960 | consumed tokens: 31541166080 | elapsed time per iteration (s): 2.25 | learning rate: 1.374E-04 | global batch size: 512 | lm loss: 2.058829E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.021 | TFLOPs: 23.47 | +63: iteration 30090/ 73814 | consumed samples: 15406080 | consumed tokens: 31551651840 | elapsed time per iteration (s): 2.23 | learning rate: 1.374E-04 | global batch size: 512 | lm loss: 2.084270E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.109 | TFLOPs: 23.69 | +63: iteration 30100/ 73814 | consumed samples: 15411200 | consumed tokens: 31562137600 | elapsed time per iteration (s): 2.23 | learning rate: 1.373E-04 | global batch size: 512 | lm loss: 2.076855E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.676 | TFLOPs: 23.64 | +63: iteration 30110/ 73814 | consumed samples: 15416320 | consumed tokens: 31572623360 | elapsed time per iteration (s): 2.27 | learning rate: 1.373E-04 | global batch size: 512 | lm loss: 2.054219E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.807 | TFLOPs: 23.25 | +63: iteration 30120/ 73814 | consumed samples: 15421440 | consumed tokens: 31583109120 | elapsed time per iteration (s): 2.23 | learning rate: 1.373E-04 | global batch size: 512 | lm loss: 2.068597E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.771 | TFLOPs: 23.65 | +63: iteration 30130/ 73814 | consumed samples: 15426560 | consumed tokens: 31593594880 | elapsed time per iteration (s): 2.33 | learning rate: 1.372E-04 | global batch size: 512 | lm loss: 2.086430E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.646 | TFLOPs: 22.61 | +63: iteration 30140/ 73814 | consumed samples: 15431680 | consumed tokens: 31604080640 | elapsed time per iteration (s): 2.40 | learning rate: 1.372E-04 | global batch size: 512 | lm loss: 2.092478E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.047 | TFLOPs: 21.93 | +63: iteration 30150/ 73814 | consumed samples: 15436800 | consumed tokens: 31614566400 | elapsed time per iteration (s): 2.23 | learning rate: 1.371E-04 | global batch size: 512 | lm loss: 2.070144E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.954 | TFLOPs: 23.67 | +63: iteration 30160/ 73814 | consumed samples: 15441920 | consumed tokens: 31625052160 | elapsed time per iteration (s): 2.23 | learning rate: 1.371E-04 | global batch size: 512 | lm loss: 2.075109E+00 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.675 | TFLOPs: 23.64 | +63: iteration 30170/ 73814 | consumed samples: 15447040 | consumed tokens: 31635537920 | elapsed time per iteration (s): 2.24 | learning rate: 1.371E-04 | global batch size: 512 | lm loss: 2.079750E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.503 | TFLOPs: 23.52 | +63: iteration 30180/ 73814 | consumed samples: 15452160 | consumed tokens: 31646023680 | elapsed time per iteration (s): 2.23 | learning rate: 1.370E-04 | global batch size: 512 | lm loss: 2.080713E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.669 | TFLOPs: 23.64 | +63: iteration 30190/ 73814 | consumed samples: 15457280 | consumed tokens: 31656509440 | elapsed time per iteration (s): 2.23 | learning rate: 1.370E-04 | global batch size: 512 | lm loss: 2.082826E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.836 | TFLOPs: 23.66 | +63: iteration 30200/ 73814 | consumed samples: 15462400 | consumed tokens: 31666995200 | elapsed time per iteration (s): 2.23 | learning rate: 1.370E-04 | global batch size: 512 | lm loss: 2.087905E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.663 | TFLOPs: 23.64 | +63: iteration 30210/ 73814 | consumed samples: 15467520 | consumed tokens: 31677480960 | elapsed time per iteration (s): 2.24 | learning rate: 1.369E-04 | global batch size: 512 | lm loss: 2.077423E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.204 | TFLOPs: 23.49 | +63: iteration 30220/ 73814 | consumed samples: 15472640 | consumed tokens: 31687966720 | elapsed time per iteration (s): 2.25 | learning rate: 1.369E-04 | global batch size: 512 | lm loss: 2.065366E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.674 | TFLOPs: 23.44 | +63: iteration 30230/ 73814 | consumed samples: 15477760 | consumed tokens: 31698452480 | elapsed time per iteration (s): 2.23 | learning rate: 1.368E-04 | global batch size: 512 | lm loss: 2.066171E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.893 | TFLOPs: 23.67 | +63: iteration 30240/ 73814 | consumed samples: 15482880 | consumed tokens: 31708938240 | elapsed time per iteration (s): 2.25 | learning rate: 1.368E-04 | global batch size: 512 | lm loss: 2.078778E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.053 | TFLOPs: 23.48 | +63: iteration 30250/ 73814 | consumed samples: 15488000 | consumed tokens: 31719424000 | elapsed time per iteration (s): 2.23 | learning rate: 1.368E-04 | global batch size: 512 | lm loss: 2.074328E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.415 | TFLOPs: 23.62 | +63: iteration 30260/ 73814 | consumed samples: 15493120 | consumed tokens: 31729909760 | elapsed time per iteration (s): 2.23 | learning rate: 1.367E-04 | global batch size: 512 | lm loss: 2.082501E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.442 | TFLOPs: 23.62 | +63: iteration 30270/ 73814 | consumed samples: 15498240 | consumed tokens: 31740395520 | elapsed time per iteration (s): 2.25 | learning rate: 1.367E-04 | global batch size: 512 | lm loss: 2.060619E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.568 | TFLOPs: 23.43 | +63: iteration 30280/ 73814 | consumed samples: 15503360 | consumed tokens: 31750881280 | elapsed time per iteration (s): 2.24 | learning rate: 1.367E-04 | global batch size: 512 | lm loss: 2.055435E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.002 | TFLOPs: 23.57 | +63: iteration 30290/ 73814 | consumed samples: 15508480 | consumed tokens: 31761367040 | elapsed time per iteration (s): 2.31 | learning rate: 1.366E-04 | global batch size: 512 | lm loss: 2.074291E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.940 | TFLOPs: 22.85 | +63: iteration 30300/ 73814 | consumed samples: 15513600 | consumed tokens: 31771852800 | elapsed time per iteration (s): 2.24 | learning rate: 1.366E-04 | global batch size: 512 | lm loss: 2.072805E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.680 | TFLOPs: 23.54 | +63: iteration 30310/ 73814 | consumed samples: 15518720 | consumed tokens: 31782338560 | elapsed time per iteration (s): 2.30 | learning rate: 1.366E-04 | global batch size: 512 | lm loss: 2.067259E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.536 | TFLOPs: 22.91 | +63: iteration 30320/ 73814 | consumed samples: 15523840 | consumed tokens: 31792824320 | elapsed time per iteration (s): 2.23 | learning rate: 1.365E-04 | global batch size: 512 | lm loss: 2.067174E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.511 | TFLOPs: 23.63 | +63: iteration 30330/ 73814 | consumed samples: 15528960 | consumed tokens: 31803310080 | elapsed time per iteration (s): 2.36 | learning rate: 1.365E-04 | global batch size: 512 | lm loss: 2.057980E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.585 | TFLOPs: 22.30 | +63: iteration 30340/ 73814 | consumed samples: 15534080 | consumed tokens: 31813795840 | elapsed time per iteration (s): 2.25 | learning rate: 1.364E-04 | global batch size: 512 | lm loss: 2.090709E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.803 | TFLOPs: 23.45 | +63: iteration 30350/ 73814 | consumed samples: 15539200 | consumed tokens: 31824281600 | elapsed time per iteration (s): 2.24 | learning rate: 1.364E-04 | global batch size: 512 | lm loss: 2.086105E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.667 | TFLOPs: 23.54 | +63: iteration 30360/ 73814 | consumed samples: 15544320 | consumed tokens: 31834767360 | elapsed time per iteration (s): 2.22 | learning rate: 1.364E-04 | global batch size: 512 | lm loss: 2.071305E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.217 | TFLOPs: 23.70 | +63: iteration 30370/ 73814 | consumed samples: 15549440 | consumed tokens: 31845253120 | elapsed time per iteration (s): 2.23 | learning rate: 1.363E-04 | global batch size: 512 | lm loss: 2.054542E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.836 | TFLOPs: 23.66 | +63: iteration 30380/ 73814 | consumed samples: 15554560 | consumed tokens: 31855738880 | elapsed time per iteration (s): 2.26 | learning rate: 1.363E-04 | global batch size: 512 | lm loss: 2.049198E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.916 | TFLOPs: 23.36 | +63: iteration 30390/ 73814 | consumed samples: 15559680 | consumed tokens: 31866224640 | elapsed time per iteration (s): 2.25 | learning rate: 1.363E-04 | global batch size: 512 | lm loss: 2.068674E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.019 | TFLOPs: 23.47 | +63: iteration 30400/ 73814 | consumed samples: 15564800 | consumed tokens: 31876710400 | elapsed time per iteration (s): 2.23 | learning rate: 1.362E-04 | global batch size: 512 | lm loss: 2.053477E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.904 | TFLOPs: 23.67 | +63: iteration 30410/ 73814 | consumed samples: 15569920 | consumed tokens: 31887196160 | elapsed time per iteration (s): 2.22 | learning rate: 1.362E-04 | global batch size: 512 | lm loss: 2.072389E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.485 | TFLOPs: 23.73 | +63: iteration 30420/ 73814 | consumed samples: 15575040 | consumed tokens: 31897681920 | elapsed time per iteration (s): 2.33 | learning rate: 1.361E-04 | global batch size: 512 | lm loss: 2.065335E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.731 | TFLOPs: 22.62 | +63: iteration 30430/ 73814 | consumed samples: 15580160 | consumed tokens: 31908167680 | elapsed time per iteration (s): 2.23 | learning rate: 1.361E-04 | global batch size: 512 | lm loss: 2.060537E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.881 | TFLOPs: 23.67 | +63: iteration 30440/ 73814 | consumed samples: 15585280 | consumed tokens: 31918653440 | elapsed time per iteration (s): 2.23 | learning rate: 1.361E-04 | global batch size: 512 | lm loss: 2.054741E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.003 | TFLOPs: 23.68 | +63: iteration 30450/ 73814 | consumed samples: 15590400 | consumed tokens: 31929139200 | elapsed time per iteration (s): 2.24 | learning rate: 1.360E-04 | global batch size: 512 | lm loss: 2.062663E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.072 | TFLOPs: 23.58 | +63: iteration 30460/ 73814 | consumed samples: 15595520 | consumed tokens: 31939624960 | elapsed time per iteration (s): 2.24 | learning rate: 1.360E-04 | global batch size: 512 | lm loss: 2.058101E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.081 | TFLOPs: 23.58 | +63: iteration 30470/ 73814 | consumed samples: 15600640 | consumed tokens: 31950110720 | elapsed time per iteration (s): 2.24 | learning rate: 1.360E-04 | global batch size: 512 | lm loss: 2.084044E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.208 | TFLOPs: 23.49 | +63: iteration 30480/ 73814 | consumed samples: 15605760 | consumed tokens: 31960596480 | elapsed time per iteration (s): 2.23 | learning rate: 1.359E-04 | global batch size: 512 | lm loss: 2.080781E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.111 | TFLOPs: 23.59 | +63: iteration 30490/ 73814 | consumed samples: 15610880 | consumed tokens: 31971082240 | elapsed time per iteration (s): 2.22 | learning rate: 1.359E-04 | global batch size: 512 | lm loss: 2.066313E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.481 | TFLOPs: 23.73 | +63: iteration 30500/ 73814 | consumed samples: 15616000 | consumed tokens: 31981568000 | elapsed time per iteration (s): 2.23 | learning rate: 1.358E-04 | global batch size: 512 | lm loss: 2.067450E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.707 | TFLOPs: 23.65 | +63: iteration 30510/ 73814 | consumed samples: 15621120 | consumed tokens: 31992053760 | elapsed time per iteration (s): 2.23 | learning rate: 1.358E-04 | global batch size: 512 | lm loss: 2.087259E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.743 | TFLOPs: 23.65 | +63: iteration 30520/ 73814 | consumed samples: 15626240 | consumed tokens: 32002539520 | elapsed time per iteration (s): 2.23 | learning rate: 1.358E-04 | global batch size: 512 | lm loss: 2.061916E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.226 | TFLOPs: 23.60 | +63: iteration 30530/ 73814 | consumed samples: 15631360 | consumed tokens: 32013025280 | elapsed time per iteration (s): 2.27 | learning rate: 1.357E-04 | global batch size: 512 | lm loss: 2.057469E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.455 | TFLOPs: 23.21 | +63: iteration 30540/ 73814 | consumed samples: 15636480 | consumed tokens: 32023511040 | elapsed time per iteration (s): 2.24 | learning rate: 1.357E-04 | global batch size: 512 | lm loss: 2.071920E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.969 | TFLOPs: 23.57 | +63: iteration 30550/ 73814 | consumed samples: 15641600 | consumed tokens: 32033996800 | elapsed time per iteration (s): 2.27 | learning rate: 1.357E-04 | global batch size: 512 | lm loss: 2.058391E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.280 | TFLOPs: 23.19 | +63: iteration 30560/ 73814 | consumed samples: 15646720 | consumed tokens: 32044482560 | elapsed time per iteration (s): 2.26 | learning rate: 1.356E-04 | global batch size: 512 | lm loss: 2.088327E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.275 | TFLOPs: 23.29 | +63: iteration 30570/ 73814 | consumed samples: 15651840 | consumed tokens: 32054968320 | elapsed time per iteration (s): 2.34 | learning rate: 1.356E-04 | global batch size: 512 | lm loss: 2.069849E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.094 | TFLOPs: 22.55 | +63: iteration 30580/ 73814 | consumed samples: 15656960 | consumed tokens: 32065454080 | elapsed time per iteration (s): 2.37 | learning rate: 1.356E-04 | global batch size: 512 | lm loss: 2.076500E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.113 | TFLOPs: 22.25 | +63: iteration 30590/ 73814 | consumed samples: 15662080 | consumed tokens: 32075939840 | elapsed time per iteration (s): 2.24 | learning rate: 1.355E-04 | global batch size: 512 | lm loss: 2.074806E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.468 | TFLOPs: 23.52 | +63: iteration 30600/ 73814 | consumed samples: 15667200 | consumed tokens: 32086425600 | elapsed time per iteration (s): 2.26 | learning rate: 1.355E-04 | global batch size: 512 | lm loss: 2.085756E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.696 | TFLOPs: 23.34 | +63: iteration 30610/ 73814 | consumed samples: 15672320 | consumed tokens: 32096911360 | elapsed time per iteration (s): 2.61 | learning rate: 1.354E-04 | global batch size: 512 | lm loss: 2.038483E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 196.031 | TFLOPs: 20.18 | +63: iteration 30620/ 73814 | consumed samples: 15677440 | consumed tokens: 32107397120 | elapsed time per iteration (s): 2.39 | learning rate: 1.354E-04 | global batch size: 512 | lm loss: 2.074339E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.966 | TFLOPs: 22.03 | +63: iteration 30630/ 73814 | consumed samples: 15682560 | consumed tokens: 32117882880 | elapsed time per iteration (s): 2.60 | learning rate: 1.354E-04 | global batch size: 512 | lm loss: 2.069783E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 197.076 | TFLOPs: 20.29 | +63: iteration 30640/ 73814 | consumed samples: 15687680 | consumed tokens: 32128368640 | elapsed time per iteration (s): 2.26 | learning rate: 1.353E-04 | global batch size: 512 | lm loss: 2.088715E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.994 | TFLOPs: 23.37 | +63: iteration 30650/ 73814 | consumed samples: 15692800 | consumed tokens: 32138854400 | elapsed time per iteration (s): 2.24 | learning rate: 1.353E-04 | global batch size: 512 | lm loss: 2.065135E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.962 | TFLOPs: 23.57 | +63: iteration 30660/ 73814 | consumed samples: 15697920 | consumed tokens: 32149340160 | elapsed time per iteration (s): 2.37 | learning rate: 1.353E-04 | global batch size: 512 | lm loss: 2.036836E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.802 | TFLOPs: 22.22 | +63: iteration 30670/ 73814 | consumed samples: 15703040 | consumed tokens: 32159825920 | elapsed time per iteration (s): 2.26 | learning rate: 1.352E-04 | global batch size: 512 | lm loss: 2.059166E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.087 | TFLOPs: 23.27 | +63: iteration 30680/ 73814 | consumed samples: 15708160 | consumed tokens: 32170311680 | elapsed time per iteration (s): 2.24 | learning rate: 1.352E-04 | global batch size: 512 | lm loss: 2.082181E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.188 | TFLOPs: 23.49 | +63: iteration 30690/ 73814 | consumed samples: 15713280 | consumed tokens: 32180797440 | elapsed time per iteration (s): 2.23 | learning rate: 1.351E-04 | global batch size: 512 | lm loss: 2.057939E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.611 | TFLOPs: 23.64 | +63: iteration 30700/ 73814 | consumed samples: 15718400 | consumed tokens: 32191283200 | elapsed time per iteration (s): 2.22 | learning rate: 1.351E-04 | global batch size: 512 | lm loss: 2.058055E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.195 | TFLOPs: 23.70 | +63: iteration 30710/ 73814 | consumed samples: 15723520 | consumed tokens: 32201768960 | elapsed time per iteration (s): 2.23 | learning rate: 1.351E-04 | global batch size: 512 | lm loss: 2.068237E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.000 | TFLOPs: 23.68 | +63: iteration 30720/ 73814 | consumed samples: 15728640 | consumed tokens: 32212254720 | elapsed time per iteration (s): 2.25 | learning rate: 1.350E-04 | global batch size: 512 | lm loss: 2.062123E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.021 | TFLOPs: 23.47 | +63: iteration 30730/ 73814 | consumed samples: 15733760 | consumed tokens: 32222740480 | elapsed time per iteration (s): 2.24 | learning rate: 1.350E-04 | global batch size: 512 | lm loss: 2.040402E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.079 | TFLOPs: 23.58 | +63: iteration 30740/ 73814 | consumed samples: 15738880 | consumed tokens: 32233226240 | elapsed time per iteration (s): 2.23 | learning rate: 1.350E-04 | global batch size: 512 | lm loss: 2.095042E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.676 | TFLOPs: 23.64 | +63: iteration 30750/ 73814 | consumed samples: 15744000 | consumed tokens: 32243712000 | elapsed time per iteration (s): 2.23 | learning rate: 1.349E-04 | global batch size: 512 | lm loss: 2.051177E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.160 | TFLOPs: 23.59 | +63: iteration 30760/ 73814 | consumed samples: 15749120 | consumed tokens: 32254197760 | elapsed time per iteration (s): 2.41 | learning rate: 1.349E-04 | global batch size: 512 | lm loss: 2.054539E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.792 | TFLOPs: 21.91 | +63: iteration 30770/ 73814 | consumed samples: 15754240 | consumed tokens: 32264683520 | elapsed time per iteration (s): 2.37 | learning rate: 1.348E-04 | global batch size: 512 | lm loss: 2.067015E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.625 | TFLOPs: 22.20 | +63: iteration 30780/ 73814 | consumed samples: 15759360 | consumed tokens: 32275169280 | elapsed time per iteration (s): 2.26 | learning rate: 1.348E-04 | global batch size: 512 | lm loss: 2.077606E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.993 | TFLOPs: 23.37 | +63: iteration 30790/ 73814 | consumed samples: 15764480 | consumed tokens: 32285655040 | elapsed time per iteration (s): 2.25 | learning rate: 1.348E-04 | global batch size: 512 | lm loss: 2.066319E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.466 | TFLOPs: 23.42 | +63: iteration 30800/ 73814 | consumed samples: 15769600 | consumed tokens: 32296140800 | elapsed time per iteration (s): 2.23 | learning rate: 1.347E-04 | global batch size: 512 | lm loss: 2.094821E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.113 | TFLOPs: 23.59 | +63: iteration 30810/ 73814 | consumed samples: 15774720 | consumed tokens: 32306626560 | elapsed time per iteration (s): 2.24 | learning rate: 1.347E-04 | global batch size: 512 | lm loss: 2.061736E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.443 | TFLOPs: 23.52 | +63: iteration 30820/ 73814 | consumed samples: 15779840 | consumed tokens: 32317112320 | elapsed time per iteration (s): 2.25 | learning rate: 1.347E-04 | global batch size: 512 | lm loss: 2.084520E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.338 | TFLOPs: 23.40 | +63: iteration 30830/ 73814 | consumed samples: 15784960 | consumed tokens: 32327598080 | elapsed time per iteration (s): 2.24 | learning rate: 1.346E-04 | global batch size: 512 | lm loss: 2.056308E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.727 | TFLOPs: 23.55 | +63: iteration 30840/ 73814 | consumed samples: 15790080 | consumed tokens: 32338083840 | elapsed time per iteration (s): 2.26 | learning rate: 1.346E-04 | global batch size: 512 | lm loss: 2.050669E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.915 | TFLOPs: 23.36 | +63: iteration 30850/ 73814 | consumed samples: 15795200 | consumed tokens: 32348569600 | elapsed time per iteration (s): 2.26 | learning rate: 1.345E-04 | global batch size: 512 | lm loss: 2.076194E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.772 | TFLOPs: 23.35 | +63: iteration 30860/ 73814 | consumed samples: 15800320 | consumed tokens: 32359055360 | elapsed time per iteration (s): 2.25 | learning rate: 1.345E-04 | global batch size: 512 | lm loss: 2.072072E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.061 | TFLOPs: 23.48 | +63: iteration 30870/ 73814 | consumed samples: 15805440 | consumed tokens: 32369541120 | elapsed time per iteration (s): 2.25 | learning rate: 1.345E-04 | global batch size: 512 | lm loss: 2.045537E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.446 | TFLOPs: 23.41 | +63: iteration 30880/ 73814 | consumed samples: 15810560 | consumed tokens: 32380026880 | elapsed time per iteration (s): 2.27 | learning rate: 1.344E-04 | global batch size: 512 | lm loss: 2.046457E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.868 | TFLOPs: 23.25 | +63: iteration 30890/ 73814 | consumed samples: 15815680 | consumed tokens: 32390512640 | elapsed time per iteration (s): 2.23 | learning rate: 1.344E-04 | global batch size: 512 | lm loss: 2.053021E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.173 | TFLOPs: 23.59 | +63: iteration 30900/ 73814 | consumed samples: 15820800 | consumed tokens: 32400998400 | elapsed time per iteration (s): 2.51 | learning rate: 1.344E-04 | global batch size: 512 | lm loss: 2.075313E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 204.079 | TFLOPs: 21.01 | +63: iteration 30910/ 73814 | consumed samples: 15825920 | consumed tokens: 32411484160 | elapsed time per iteration (s): 2.23 | learning rate: 1.343E-04 | global batch size: 512 | lm loss: 2.094809E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.643 | TFLOPs: 23.64 | +63: iteration 30920/ 73814 | consumed samples: 15831040 | consumed tokens: 32421969920 | elapsed time per iteration (s): 2.22 | learning rate: 1.343E-04 | global batch size: 512 | lm loss: 2.081561E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.184 | TFLOPs: 23.70 | +63: iteration 30930/ 73814 | consumed samples: 15836160 | consumed tokens: 32432455680 | elapsed time per iteration (s): 2.25 | learning rate: 1.343E-04 | global batch size: 512 | lm loss: 2.074601E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.462 | TFLOPs: 23.42 | +63: iteration 30940/ 73814 | consumed samples: 15841280 | consumed tokens: 32442941440 | elapsed time per iteration (s): 2.22 | learning rate: 1.342E-04 | global batch size: 512 | lm loss: 2.076462E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.177 | TFLOPs: 23.70 | +63: iteration 30950/ 73814 | consumed samples: 15846400 | consumed tokens: 32453427200 | elapsed time per iteration (s): 2.26 | learning rate: 1.342E-04 | global batch size: 512 | lm loss: 2.077335E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.883 | TFLOPs: 23.36 | +63: iteration 30960/ 73814 | consumed samples: 15851520 | consumed tokens: 32463912960 | elapsed time per iteration (s): 2.24 | learning rate: 1.341E-04 | global batch size: 512 | lm loss: 2.064656E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.061 | TFLOPs: 23.58 | +63: iteration 30970/ 73814 | consumed samples: 15856640 | consumed tokens: 32474398720 | elapsed time per iteration (s): 2.24 | learning rate: 1.341E-04 | global batch size: 512 | lm loss: 2.043037E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.135 | TFLOPs: 23.49 | +63: iteration 30980/ 73814 | consumed samples: 15861760 | consumed tokens: 32484884480 | elapsed time per iteration (s): 2.23 | learning rate: 1.341E-04 | global batch size: 512 | lm loss: 2.090384E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.454 | TFLOPs: 23.62 | +63: iteration 30990/ 73814 | consumed samples: 15866880 | consumed tokens: 32495370240 | elapsed time per iteration (s): 2.23 | learning rate: 1.340E-04 | global batch size: 512 | lm loss: 2.052666E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.055 | TFLOPs: 23.68 | +63: iteration 31000/ 73814 | consumed samples: 15872000 | consumed tokens: 32505856000 | elapsed time per iteration (s): 2.22 | learning rate: 1.340E-04 | global batch size: 512 | lm loss: 2.054549E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.130 | TFLOPs: 23.69 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 31000 | lm loss value: 2.053909E+00 | lm loss PPL: 7.798324E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 31010/ 73814 | consumed samples: 15877120 | consumed tokens: 32516341760 | elapsed time per iteration (s): 2.30 | learning rate: 1.340E-04 | global batch size: 512 | lm loss: 2.070910E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.600 | TFLOPs: 22.92 | +63: iteration 31020/ 73814 | consumed samples: 15882240 | consumed tokens: 32526827520 | elapsed time per iteration (s): 2.22 | learning rate: 1.339E-04 | global batch size: 512 | lm loss: 2.061003E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.286 | TFLOPs: 23.71 | +63: iteration 31030/ 73814 | consumed samples: 15887360 | consumed tokens: 32537313280 | elapsed time per iteration (s): 2.23 | learning rate: 1.339E-04 | global batch size: 512 | lm loss: 2.051664E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.722 | TFLOPs: 23.65 | +63: iteration 31040/ 73814 | consumed samples: 15892480 | consumed tokens: 32547799040 | elapsed time per iteration (s): 2.23 | learning rate: 1.338E-04 | global batch size: 512 | lm loss: 2.058206E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.276 | TFLOPs: 23.60 | +63: iteration 31050/ 73814 | consumed samples: 15897600 | consumed tokens: 32558284800 | elapsed time per iteration (s): 2.24 | learning rate: 1.338E-04 | global batch size: 512 | lm loss: 2.046252E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.790 | TFLOPs: 23.55 | +63: iteration 31060/ 73814 | consumed samples: 15902720 | consumed tokens: 32568770560 | elapsed time per iteration (s): 2.27 | learning rate: 1.338E-04 | global batch size: 512 | lm loss: 2.046072E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.980 | TFLOPs: 23.26 | +63: iteration 31070/ 73814 | consumed samples: 15907840 | consumed tokens: 32579256320 | elapsed time per iteration (s): 2.24 | learning rate: 1.337E-04 | global batch size: 512 | lm loss: 2.055438E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.863 | TFLOPs: 23.56 | +63: iteration 31080/ 73814 | consumed samples: 15912960 | consumed tokens: 32589742080 | elapsed time per iteration (s): 2.23 | learning rate: 1.337E-04 | global batch size: 512 | lm loss: 2.055077E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.402 | TFLOPs: 23.62 | +63: iteration 31090/ 73814 | consumed samples: 15918080 | consumed tokens: 32600227840 | elapsed time per iteration (s): 2.24 | learning rate: 1.337E-04 | global batch size: 512 | lm loss: 2.057750E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.629 | TFLOPs: 23.54 | +63: iteration 31100/ 73814 | consumed samples: 15923200 | consumed tokens: 32610713600 | elapsed time per iteration (s): 2.23 | learning rate: 1.336E-04 | global batch size: 512 | lm loss: 2.043944E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.163 | TFLOPs: 23.59 | +63: iteration 31110/ 73814 | consumed samples: 15928320 | consumed tokens: 32621199360 | elapsed time per iteration (s): 2.24 | learning rate: 1.336E-04 | global batch size: 512 | lm loss: 2.048070E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.048 | TFLOPs: 23.58 | +63: iteration 31120/ 73814 | consumed samples: 15933440 | consumed tokens: 32631685120 | elapsed time per iteration (s): 2.25 | learning rate: 1.335E-04 | global batch size: 512 | lm loss: 2.076017E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.058 | TFLOPs: 23.37 | +63: iteration 31130/ 73814 | consumed samples: 15938560 | consumed tokens: 32642170880 | elapsed time per iteration (s): 2.25 | learning rate: 1.335E-04 | global batch size: 512 | lm loss: 2.066888E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.544 | TFLOPs: 23.42 | +63: iteration 31140/ 73814 | consumed samples: 15943680 | consumed tokens: 32652656640 | elapsed time per iteration (s): 2.33 | learning rate: 1.335E-04 | global batch size: 512 | lm loss: 2.075839E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.068 | TFLOPs: 22.65 | +63: iteration 31150/ 73814 | consumed samples: 15948800 | consumed tokens: 32663142400 | elapsed time per iteration (s): 2.24 | learning rate: 1.334E-04 | global batch size: 512 | lm loss: 2.044230E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.519 | TFLOPs: 23.52 | +63: iteration 31160/ 73814 | consumed samples: 15953920 | consumed tokens: 32673628160 | elapsed time per iteration (s): 2.24 | learning rate: 1.334E-04 | global batch size: 512 | lm loss: 2.066716E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.239 | TFLOPs: 23.50 | +63: iteration 31170/ 73814 | consumed samples: 15959040 | consumed tokens: 32684113920 | elapsed time per iteration (s): 2.23 | learning rate: 1.334E-04 | global batch size: 512 | lm loss: 2.032259E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.941 | TFLOPs: 23.67 | +63: iteration 31180/ 73814 | consumed samples: 15964160 | consumed tokens: 32694599680 | elapsed time per iteration (s): 2.23 | learning rate: 1.333E-04 | global batch size: 512 | lm loss: 2.048803E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.274 | TFLOPs: 23.60 | +63: iteration 31190/ 73814 | consumed samples: 15969280 | consumed tokens: 32705085440 | elapsed time per iteration (s): 2.23 | learning rate: 1.333E-04 | global batch size: 512 | lm loss: 2.065251E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.251 | TFLOPs: 23.60 | +63: iteration 31200/ 73814 | consumed samples: 15974400 | consumed tokens: 32715571200 | elapsed time per iteration (s): 2.23 | learning rate: 1.332E-04 | global batch size: 512 | lm loss: 2.060353E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.908 | TFLOPs: 23.67 | +63: iteration 31210/ 73814 | consumed samples: 15979520 | consumed tokens: 32726056960 | elapsed time per iteration (s): 2.33 | learning rate: 1.332E-04 | global batch size: 512 | lm loss: 2.053996E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.098 | TFLOPs: 22.66 | +63: iteration 31220/ 73814 | consumed samples: 15984640 | consumed tokens: 32736542720 | elapsed time per iteration (s): 2.22 | learning rate: 1.332E-04 | global batch size: 512 | lm loss: 2.076733E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.211 | TFLOPs: 23.70 | +63: iteration 31230/ 73814 | consumed samples: 15989760 | consumed tokens: 32747028480 | elapsed time per iteration (s): 2.26 | learning rate: 1.331E-04 | global batch size: 512 | lm loss: 2.089676E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.609 | TFLOPs: 23.33 | +63: iteration 31240/ 73814 | consumed samples: 15994880 | consumed tokens: 32757514240 | elapsed time per iteration (s): 2.25 | learning rate: 1.331E-04 | global batch size: 512 | lm loss: 2.069379E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.836 | TFLOPs: 23.45 | +63: iteration 31250/ 73814 | consumed samples: 16000000 | consumed tokens: 32768000000 | elapsed time per iteration (s): 2.23 | learning rate: 1.331E-04 | global batch size: 512 | lm loss: 2.049759E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.872 | TFLOPs: 23.66 | +63: iteration 31260/ 73814 | consumed samples: 16005120 | consumed tokens: 32778485760 | elapsed time per iteration (s): 2.22 | learning rate: 1.330E-04 | global batch size: 512 | lm loss: 2.049197E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.428 | TFLOPs: 23.72 | +63: iteration 31270/ 73814 | consumed samples: 16010240 | consumed tokens: 32788971520 | elapsed time per iteration (s): 2.23 | learning rate: 1.330E-04 | global batch size: 512 | lm loss: 2.059793E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.974 | TFLOPs: 23.67 | +63: iteration 31280/ 73814 | consumed samples: 16015360 | consumed tokens: 32799457280 | elapsed time per iteration (s): 2.26 | learning rate: 1.329E-04 | global batch size: 512 | lm loss: 2.070930E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.413 | TFLOPs: 23.31 | +63: iteration 31290/ 73814 | consumed samples: 16020480 | consumed tokens: 32809943040 | elapsed time per iteration (s): 2.22 | learning rate: 1.329E-04 | global batch size: 512 | lm loss: 2.058600E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.120 | TFLOPs: 23.69 | +63: iteration 31300/ 73814 | consumed samples: 16025600 | consumed tokens: 32820428800 | elapsed time per iteration (s): 2.24 | learning rate: 1.329E-04 | global batch size: 512 | lm loss: 2.030704E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.101 | TFLOPs: 23.48 | +63: iteration 31310/ 73814 | consumed samples: 16030720 | consumed tokens: 32830914560 | elapsed time per iteration (s): 2.23 | learning rate: 1.328E-04 | global batch size: 512 | lm loss: 2.041922E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.508 | TFLOPs: 23.63 | +63: iteration 31320/ 73814 | consumed samples: 16035840 | consumed tokens: 32841400320 | elapsed time per iteration (s): 2.23 | learning rate: 1.328E-04 | global batch size: 512 | lm loss: 2.063968E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.281 | TFLOPs: 23.60 | +63: iteration 31330/ 73814 | consumed samples: 16040960 | consumed tokens: 32851886080 | elapsed time per iteration (s): 2.24 | learning rate: 1.328E-04 | global batch size: 512 | lm loss: 2.057803E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.495 | TFLOPs: 23.52 | +63: iteration 31340/ 73814 | consumed samples: 16046080 | consumed tokens: 32862371840 | elapsed time per iteration (s): 2.31 | learning rate: 1.327E-04 | global batch size: 512 | lm loss: 2.064185E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.532 | TFLOPs: 22.81 | +63: iteration 31350/ 73814 | consumed samples: 16051200 | consumed tokens: 32872857600 | elapsed time per iteration (s): 2.24 | learning rate: 1.327E-04 | global batch size: 512 | lm loss: 2.054997E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.727 | TFLOPs: 23.55 | +63: iteration 31360/ 73814 | consumed samples: 16056320 | consumed tokens: 32883343360 | elapsed time per iteration (s): 2.25 | learning rate: 1.326E-04 | global batch size: 512 | lm loss: 2.060038E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.394 | TFLOPs: 23.41 | +63: iteration 31370/ 73814 | consumed samples: 16061440 | consumed tokens: 32893829120 | elapsed time per iteration (s): 2.23 | learning rate: 1.326E-04 | global batch size: 512 | lm loss: 2.058718E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.136 | TFLOPs: 23.59 | +63: iteration 31380/ 73814 | consumed samples: 16066560 | consumed tokens: 32904314880 | elapsed time per iteration (s): 2.24 | learning rate: 1.326E-04 | global batch size: 512 | lm loss: 2.056667E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.934 | TFLOPs: 23.57 | +63: iteration 31390/ 73814 | consumed samples: 16071680 | consumed tokens: 32914800640 | elapsed time per iteration (s): 2.25 | learning rate: 1.325E-04 | global batch size: 512 | lm loss: 2.077842E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.007 | TFLOPs: 23.47 | +63: iteration 31400/ 73814 | consumed samples: 16076800 | consumed tokens: 32925286400 | elapsed time per iteration (s): 2.24 | learning rate: 1.325E-04 | global batch size: 512 | lm loss: 2.075685E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.589 | TFLOPs: 23.53 | +63: iteration 31410/ 73814 | consumed samples: 16081920 | consumed tokens: 32935772160 | elapsed time per iteration (s): 2.24 | learning rate: 1.325E-04 | global batch size: 512 | lm loss: 2.060925E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.941 | TFLOPs: 23.57 | +63: iteration 31420/ 73814 | consumed samples: 16087040 | consumed tokens: 32946257920 | elapsed time per iteration (s): 2.22 | learning rate: 1.324E-04 | global batch size: 512 | lm loss: 2.057946E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.275 | TFLOPs: 23.71 | +63: iteration 31430/ 73814 | consumed samples: 16092160 | consumed tokens: 32956743680 | elapsed time per iteration (s): 2.29 | learning rate: 1.324E-04 | global batch size: 512 | lm loss: 2.044448E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.152 | TFLOPs: 22.97 | +63: iteration 31440/ 73814 | consumed samples: 16097280 | consumed tokens: 32967229440 | elapsed time per iteration (s): 2.23 | learning rate: 1.323E-04 | global batch size: 512 | lm loss: 2.081841E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.598 | TFLOPs: 23.64 | +63: iteration 31450/ 73814 | consumed samples: 16102400 | consumed tokens: 32977715200 | elapsed time per iteration (s): 2.23 | learning rate: 1.323E-04 | global batch size: 512 | lm loss: 2.067391E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.270 | TFLOPs: 23.60 | +63: iteration 31460/ 73814 | consumed samples: 16107520 | consumed tokens: 32988200960 | elapsed time per iteration (s): 2.23 | learning rate: 1.323E-04 | global batch size: 512 | lm loss: 2.064092E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.783 | TFLOPs: 23.66 | +63: iteration 31470/ 73814 | consumed samples: 16112640 | consumed tokens: 32998686720 | elapsed time per iteration (s): 2.32 | learning rate: 1.322E-04 | global batch size: 512 | lm loss: 2.075661E+00 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.747 | TFLOPs: 22.72 | +63: iteration 31480/ 73814 | consumed samples: 16117760 | consumed tokens: 33009172480 | elapsed time per iteration (s): 2.24 | learning rate: 1.322E-04 | global batch size: 512 | lm loss: 2.047397E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.114 | TFLOPs: 23.48 | +63: iteration 31490/ 73814 | consumed samples: 16122880 | consumed tokens: 33019658240 | elapsed time per iteration (s): 2.24 | learning rate: 1.322E-04 | global batch size: 512 | lm loss: 2.059743E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.066 | TFLOPs: 23.58 | +63: iteration 31500/ 73814 | consumed samples: 16128000 | consumed tokens: 33030144000 | elapsed time per iteration (s): 2.24 | learning rate: 1.321E-04 | global batch size: 512 | lm loss: 2.080315E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.869 | TFLOPs: 23.56 | +63: iteration 31510/ 73814 | consumed samples: 16133120 | consumed tokens: 33040629760 | elapsed time per iteration (s): 2.23 | learning rate: 1.321E-04 | global batch size: 512 | lm loss: 2.060112E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.114 | TFLOPs: 23.59 | +63: iteration 31520/ 73814 | consumed samples: 16138240 | consumed tokens: 33051115520 | elapsed time per iteration (s): 2.23 | learning rate: 1.320E-04 | global batch size: 512 | lm loss: 2.054325E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.174 | TFLOPs: 23.59 | +63: iteration 31530/ 73814 | consumed samples: 16143360 | consumed tokens: 33061601280 | elapsed time per iteration (s): 2.33 | learning rate: 1.320E-04 | global batch size: 512 | lm loss: 2.070469E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.435 | TFLOPs: 22.59 | +63: iteration 31540/ 73814 | consumed samples: 16148480 | consumed tokens: 33072087040 | elapsed time per iteration (s): 2.24 | learning rate: 1.320E-04 | global batch size: 512 | lm loss: 2.049493E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.785 | TFLOPs: 23.55 | +63: iteration 31550/ 73814 | consumed samples: 16153600 | consumed tokens: 33082572800 | elapsed time per iteration (s): 2.24 | learning rate: 1.319E-04 | global batch size: 512 | lm loss: 2.070743E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.866 | TFLOPs: 23.56 | +63: iteration 31560/ 73814 | consumed samples: 16158720 | consumed tokens: 33093058560 | elapsed time per iteration (s): 2.23 | learning rate: 1.319E-04 | global batch size: 512 | lm loss: 2.059454E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.541 | TFLOPs: 23.63 | +63: iteration 31570/ 73814 | consumed samples: 16163840 | consumed tokens: 33103544320 | elapsed time per iteration (s): 2.23 | learning rate: 1.319E-04 | global batch size: 512 | lm loss: 2.071020E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.654 | TFLOPs: 23.64 | +63: iteration 31580/ 73814 | consumed samples: 16168960 | consumed tokens: 33114030080 | elapsed time per iteration (s): 2.22 | learning rate: 1.318E-04 | global batch size: 512 | lm loss: 2.043503E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.175 | TFLOPs: 23.70 | +63: iteration 31590/ 73814 | consumed samples: 16174080 | consumed tokens: 33124515840 | elapsed time per iteration (s): 2.23 | learning rate: 1.318E-04 | global batch size: 512 | lm loss: 2.049089E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.487 | TFLOPs: 23.62 | +63: iteration 31600/ 73814 | consumed samples: 16179200 | consumed tokens: 33135001600 | elapsed time per iteration (s): 2.24 | learning rate: 1.317E-04 | global batch size: 512 | lm loss: 2.058825E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.067 | TFLOPs: 23.58 | +63: iteration 31610/ 73814 | consumed samples: 16184320 | consumed tokens: 33145487360 | elapsed time per iteration (s): 2.22 | learning rate: 1.317E-04 | global batch size: 512 | lm loss: 2.073697E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.279 | TFLOPs: 23.71 | +63: iteration 31620/ 73814 | consumed samples: 16189440 | consumed tokens: 33155973120 | elapsed time per iteration (s): 2.24 | learning rate: 1.317E-04 | global batch size: 512 | lm loss: 2.053340E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.239 | TFLOPs: 23.50 | +63: iteration 31630/ 73814 | consumed samples: 16194560 | consumed tokens: 33166458880 | elapsed time per iteration (s): 2.23 | learning rate: 1.316E-04 | global batch size: 512 | lm loss: 2.068185E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.850 | TFLOPs: 23.66 | +63: iteration 31640/ 73814 | consumed samples: 16199680 | consumed tokens: 33176944640 | elapsed time per iteration (s): 2.25 | learning rate: 1.316E-04 | global batch size: 512 | lm loss: 2.068531E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.925 | TFLOPs: 23.46 | +63: iteration 31650/ 73814 | consumed samples: 16204800 | consumed tokens: 33187430400 | elapsed time per iteration (s): 2.24 | learning rate: 1.316E-04 | global batch size: 512 | lm loss: 2.059502E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.369 | TFLOPs: 23.51 | +63: iteration 31660/ 73814 | consumed samples: 16209920 | consumed tokens: 33197916160 | elapsed time per iteration (s): 2.25 | learning rate: 1.315E-04 | global batch size: 512 | lm loss: 2.077982E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.877 | TFLOPs: 23.46 | +63: iteration 31670/ 73814 | consumed samples: 16215040 | consumed tokens: 33208401920 | elapsed time per iteration (s): 2.26 | learning rate: 1.315E-04 | global batch size: 512 | lm loss: 2.041721E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.189 | TFLOPs: 23.29 | +63: iteration 31680/ 73814 | consumed samples: 16220160 | consumed tokens: 33218887680 | elapsed time per iteration (s): 2.25 | learning rate: 1.314E-04 | global batch size: 512 | lm loss: 2.065540E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.861 | TFLOPs: 23.46 | +63: iteration 31690/ 73814 | consumed samples: 16225280 | consumed tokens: 33229373440 | elapsed time per iteration (s): 2.28 | learning rate: 1.314E-04 | global batch size: 512 | lm loss: 2.062422E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.918 | TFLOPs: 23.15 | +63: iteration 31700/ 73814 | consumed samples: 16230400 | consumed tokens: 33239859200 | elapsed time per iteration (s): 2.26 | learning rate: 1.314E-04 | global batch size: 512 | lm loss: 2.067540E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.700 | TFLOPs: 23.34 | +63: iteration 31710/ 73814 | consumed samples: 16235520 | consumed tokens: 33250344960 | elapsed time per iteration (s): 2.27 | learning rate: 1.313E-04 | global batch size: 512 | lm loss: 2.071347E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.102 | TFLOPs: 23.17 | +63: iteration 31720/ 73814 | consumed samples: 16240640 | consumed tokens: 33260830720 | elapsed time per iteration (s): 2.23 | learning rate: 1.313E-04 | global batch size: 512 | lm loss: 2.099347E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.453 | TFLOPs: 23.62 | +63: iteration 31730/ 73814 | consumed samples: 16245760 | consumed tokens: 33271316480 | elapsed time per iteration (s): 2.33 | learning rate: 1.313E-04 | global batch size: 512 | lm loss: 2.067146E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.172 | TFLOPs: 22.67 | +63: iteration 31740/ 73814 | consumed samples: 16250880 | consumed tokens: 33281802240 | elapsed time per iteration (s): 2.24 | learning rate: 1.312E-04 | global batch size: 512 | lm loss: 2.069376E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.283 | TFLOPs: 23.50 | +63: iteration 31750/ 73814 | consumed samples: 16256000 | consumed tokens: 33292288000 | elapsed time per iteration (s): 2.32 | learning rate: 1.312E-04 | global batch size: 512 | lm loss: 2.069064E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.643 | TFLOPs: 22.71 | +63: iteration 31760/ 73814 | consumed samples: 16261120 | consumed tokens: 33302773760 | elapsed time per iteration (s): 2.30 | learning rate: 1.311E-04 | global batch size: 512 | lm loss: 2.064026E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.594 | TFLOPs: 22.91 | +63: iteration 31770/ 73814 | consumed samples: 16266240 | consumed tokens: 33313259520 | elapsed time per iteration (s): 2.23 | learning rate: 1.311E-04 | global batch size: 512 | lm loss: 2.049607E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.610 | TFLOPs: 23.64 | +63: iteration 31780/ 73814 | consumed samples: 16271360 | consumed tokens: 33323745280 | elapsed time per iteration (s): 2.23 | learning rate: 1.311E-04 | global batch size: 512 | lm loss: 2.047637E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.254 | TFLOPs: 23.60 | +63: iteration 31790/ 73814 | consumed samples: 16276480 | consumed tokens: 33334231040 | elapsed time per iteration (s): 2.24 | learning rate: 1.310E-04 | global batch size: 512 | lm loss: 2.059516E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.303 | TFLOPs: 23.50 | +63: iteration 31800/ 73814 | consumed samples: 16281600 | consumed tokens: 33344716800 | elapsed time per iteration (s): 2.22 | learning rate: 1.310E-04 | global batch size: 512 | lm loss: 2.043773E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.303 | TFLOPs: 23.71 | +63: iteration 31810/ 73814 | consumed samples: 16286720 | consumed tokens: 33355202560 | elapsed time per iteration (s): 2.29 | learning rate: 1.310E-04 | global batch size: 512 | lm loss: 2.050879E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.511 | TFLOPs: 23.01 | +63: iteration 31820/ 73814 | consumed samples: 16291840 | consumed tokens: 33365688320 | elapsed time per iteration (s): 2.24 | learning rate: 1.309E-04 | global batch size: 512 | lm loss: 2.070033E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.268 | TFLOPs: 23.50 | +63: iteration 31830/ 73814 | consumed samples: 16296960 | consumed tokens: 33376174080 | elapsed time per iteration (s): 2.23 | learning rate: 1.309E-04 | global batch size: 512 | lm loss: 2.066070E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.061 | TFLOPs: 23.68 | +63: iteration 31840/ 73814 | consumed samples: 16302080 | consumed tokens: 33386659840 | elapsed time per iteration (s): 2.26 | learning rate: 1.308E-04 | global batch size: 512 | lm loss: 2.055383E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.981 | TFLOPs: 23.37 | +63: iteration 31850/ 73814 | consumed samples: 16307200 | consumed tokens: 33397145600 | elapsed time per iteration (s): 2.23 | learning rate: 1.308E-04 | global batch size: 512 | lm loss: 2.054667E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.883 | TFLOPs: 23.67 | +63: iteration 31860/ 73814 | consumed samples: 16312320 | consumed tokens: 33407631360 | elapsed time per iteration (s): 2.24 | learning rate: 1.308E-04 | global batch size: 512 | lm loss: 2.038346E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.930 | TFLOPs: 23.57 | +63: iteration 31870/ 73814 | consumed samples: 16317440 | consumed tokens: 33418117120 | elapsed time per iteration (s): 2.30 | learning rate: 1.307E-04 | global batch size: 512 | lm loss: 2.048996E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.132 | TFLOPs: 22.87 | +63: iteration 31880/ 73814 | consumed samples: 16322560 | consumed tokens: 33428602880 | elapsed time per iteration (s): 2.25 | learning rate: 1.307E-04 | global batch size: 512 | lm loss: 2.049396E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.646 | TFLOPs: 23.44 | +63: iteration 31890/ 73814 | consumed samples: 16327680 | consumed tokens: 33439088640 | elapsed time per iteration (s): 2.23 | learning rate: 1.307E-04 | global batch size: 512 | lm loss: 2.049552E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.647 | TFLOPs: 23.64 | +63: iteration 31900/ 73814 | consumed samples: 16332800 | consumed tokens: 33449574400 | elapsed time per iteration (s): 2.23 | learning rate: 1.306E-04 | global batch size: 512 | lm loss: 2.052795E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.353 | TFLOPs: 23.61 | +63: iteration 31910/ 73814 | consumed samples: 16337920 | consumed tokens: 33460060160 | elapsed time per iteration (s): 2.23 | learning rate: 1.306E-04 | global batch size: 512 | lm loss: 2.038764E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.221 | TFLOPs: 23.60 | +63: iteration 31920/ 73814 | consumed samples: 16343040 | consumed tokens: 33470545920 | elapsed time per iteration (s): 2.24 | learning rate: 1.305E-04 | global batch size: 512 | lm loss: 2.045216E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.466 | TFLOPs: 23.52 | +63: iteration 31930/ 73814 | consumed samples: 16348160 | consumed tokens: 33481031680 | elapsed time per iteration (s): 2.23 | learning rate: 1.305E-04 | global batch size: 512 | lm loss: 2.057139E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.503 | TFLOPs: 23.63 | +63: iteration 31940/ 73814 | consumed samples: 16353280 | consumed tokens: 33491517440 | elapsed time per iteration (s): 2.23 | learning rate: 1.305E-04 | global batch size: 512 | lm loss: 2.073902E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.289 | TFLOPs: 23.60 | +63: iteration 31950/ 73814 | consumed samples: 16358400 | consumed tokens: 33502003200 | elapsed time per iteration (s): 2.25 | learning rate: 1.304E-04 | global batch size: 512 | lm loss: 2.058470E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.019 | TFLOPs: 23.47 | +63: iteration 31960/ 73814 | consumed samples: 16363520 | consumed tokens: 33512488960 | elapsed time per iteration (s): 2.23 | learning rate: 1.304E-04 | global batch size: 512 | lm loss: 2.046075E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.600 | TFLOPs: 23.64 | +63: iteration 31970/ 73814 | consumed samples: 16368640 | consumed tokens: 33522974720 | elapsed time per iteration (s): 2.23 | learning rate: 1.304E-04 | global batch size: 512 | lm loss: 2.050290E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.785 | TFLOPs: 23.66 | +63: iteration 31980/ 73814 | consumed samples: 16373760 | consumed tokens: 33533460480 | elapsed time per iteration (s): 2.24 | learning rate: 1.303E-04 | global batch size: 512 | lm loss: 2.065484E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.664 | TFLOPs: 23.54 | +63: iteration 31990/ 73814 | consumed samples: 16378880 | consumed tokens: 33543946240 | elapsed time per iteration (s): 2.25 | learning rate: 1.303E-04 | global batch size: 512 | lm loss: 2.062931E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.038 | TFLOPs: 23.48 | + 0: [2022-12-02 08:02:48,264] [INFO] [logging.py:68:log_dist] [Rank 0] step=32000, skipped=0, lr=[0.0001302400888918607, 0.0001302400888918607, 0.0001302400888918607], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 32000/ 73814 | consumed samples: 16384000 | consumed tokens: 33554432000 | elapsed time per iteration (s): 2.23 | learning rate: 1.302E-04 | global batch size: 512 | lm loss: 2.082418E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.748 | TFLOPs: 23.65 | + 0: steps: 32000 loss: 2.0608 iter time (s): 2.254 samples/sec: 227.163 +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 32000 | lm loss value: 1.970253E+00 | lm loss PPL: 7.172494E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 32010/ 73814 | consumed samples: 16389120 | consumed tokens: 33564917760 | elapsed time per iteration (s): 2.60 | learning rate: 1.302E-04 | global batch size: 512 | lm loss: 2.072027E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 196.705 | TFLOPs: 20.25 | +63: iteration 32020/ 73814 | consumed samples: 16394240 | consumed tokens: 33575403520 | elapsed time per iteration (s): 2.23 | learning rate: 1.302E-04 | global batch size: 512 | lm loss: 2.072719E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.762 | TFLOPs: 23.65 | +63: iteration 32030/ 73814 | consumed samples: 16399360 | consumed tokens: 33585889280 | elapsed time per iteration (s): 2.24 | learning rate: 1.301E-04 | global batch size: 512 | lm loss: 2.022445E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.952 | TFLOPs: 23.57 | +63: iteration 32040/ 73814 | consumed samples: 16404480 | consumed tokens: 33596375040 | elapsed time per iteration (s): 2.32 | learning rate: 1.301E-04 | global batch size: 512 | lm loss: 2.025924E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.851 | TFLOPs: 22.74 | +63: iteration 32050/ 73814 | consumed samples: 16409600 | consumed tokens: 33606860800 | elapsed time per iteration (s): 2.31 | learning rate: 1.301E-04 | global batch size: 512 | lm loss: 2.057272E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.009 | TFLOPs: 22.85 | +63: iteration 32060/ 73814 | consumed samples: 16414720 | consumed tokens: 33617346560 | elapsed time per iteration (s): 2.23 | learning rate: 1.300E-04 | global batch size: 512 | lm loss: 2.058170E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.782 | TFLOPs: 23.65 | +63: iteration 32070/ 73814 | consumed samples: 16419840 | consumed tokens: 33627832320 | elapsed time per iteration (s): 2.27 | learning rate: 1.300E-04 | global batch size: 512 | lm loss: 2.060071E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.402 | TFLOPs: 23.20 | +63: iteration 32080/ 73814 | consumed samples: 16424960 | consumed tokens: 33638318080 | elapsed time per iteration (s): 2.26 | learning rate: 1.299E-04 | global batch size: 512 | lm loss: 2.047823E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.973 | TFLOPs: 23.37 | +63: iteration 32090/ 73814 | consumed samples: 16430080 | consumed tokens: 33648803840 | elapsed time per iteration (s): 2.22 | learning rate: 1.299E-04 | global batch size: 512 | lm loss: 2.055185E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.224 | TFLOPs: 23.70 | +63: iteration 32100/ 73814 | consumed samples: 16435200 | consumed tokens: 33659289600 | elapsed time per iteration (s): 2.23 | learning rate: 1.299E-04 | global batch size: 512 | lm loss: 2.050596E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.709 | TFLOPs: 23.65 | +63: iteration 32110/ 73814 | consumed samples: 16440320 | consumed tokens: 33669775360 | elapsed time per iteration (s): 2.33 | learning rate: 1.298E-04 | global batch size: 512 | lm loss: 2.050058E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.163 | TFLOPs: 22.66 | +63: iteration 32120/ 73814 | consumed samples: 16445440 | consumed tokens: 33680261120 | elapsed time per iteration (s): 2.23 | learning rate: 1.298E-04 | global batch size: 512 | lm loss: 2.068894E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.728 | TFLOPs: 23.65 | +63: iteration 32130/ 73814 | consumed samples: 16450560 | consumed tokens: 33690746880 | elapsed time per iteration (s): 2.23 | learning rate: 1.297E-04 | global batch size: 512 | lm loss: 2.049491E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.456 | TFLOPs: 23.62 | +63: iteration 32140/ 73814 | consumed samples: 16455680 | consumed tokens: 33701232640 | elapsed time per iteration (s): 2.22 | learning rate: 1.297E-04 | global batch size: 512 | lm loss: 2.043207E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.422 | TFLOPs: 23.72 | +63: iteration 32150/ 73814 | consumed samples: 16460800 | consumed tokens: 33711718400 | elapsed time per iteration (s): 2.37 | learning rate: 1.297E-04 | global batch size: 512 | lm loss: 2.041229E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.641 | TFLOPs: 22.20 | +63: iteration 32160/ 73814 | consumed samples: 16465920 | consumed tokens: 33722204160 | elapsed time per iteration (s): 2.24 | learning rate: 1.296E-04 | global batch size: 512 | lm loss: 2.067103E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.433 | TFLOPs: 23.52 | +63: iteration 32170/ 73814 | consumed samples: 16471040 | consumed tokens: 33732689920 | elapsed time per iteration (s): 2.24 | learning rate: 1.296E-04 | global batch size: 512 | lm loss: 2.070605E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.476 | TFLOPs: 23.52 | +63: iteration 32180/ 73814 | consumed samples: 16476160 | consumed tokens: 33743175680 | elapsed time per iteration (s): 2.24 | learning rate: 1.296E-04 | global batch size: 512 | lm loss: 2.044168E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.350 | TFLOPs: 23.51 | +63: iteration 32190/ 73814 | consumed samples: 16481280 | consumed tokens: 33753661440 | elapsed time per iteration (s): 2.24 | learning rate: 1.295E-04 | global batch size: 512 | lm loss: 2.062798E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.605 | TFLOPs: 23.53 | +63: iteration 32200/ 73814 | consumed samples: 16486400 | consumed tokens: 33764147200 | elapsed time per iteration (s): 2.23 | learning rate: 1.295E-04 | global batch size: 512 | lm loss: 2.058854E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.086 | TFLOPs: 23.69 | +63: iteration 32210/ 73814 | consumed samples: 16491520 | consumed tokens: 33774632960 | elapsed time per iteration (s): 2.25 | learning rate: 1.294E-04 | global batch size: 512 | lm loss: 2.051215E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.240 | TFLOPs: 23.39 | +63: iteration 32220/ 73814 | consumed samples: 16496640 | consumed tokens: 33785118720 | elapsed time per iteration (s): 2.27 | learning rate: 1.294E-04 | global batch size: 512 | lm loss: 2.045820E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.707 | TFLOPs: 23.24 | +63: iteration 32230/ 73814 | consumed samples: 16501760 | consumed tokens: 33795604480 | elapsed time per iteration (s): 2.24 | learning rate: 1.294E-04 | global batch size: 512 | lm loss: 2.055291E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.714 | TFLOPs: 23.54 | +63: iteration 32240/ 73814 | consumed samples: 16506880 | consumed tokens: 33806090240 | elapsed time per iteration (s): 2.23 | learning rate: 1.293E-04 | global batch size: 512 | lm loss: 2.057775E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.795 | TFLOPs: 23.66 | +63: iteration 32250/ 73814 | consumed samples: 16512000 | consumed tokens: 33816576000 | elapsed time per iteration (s): 2.24 | learning rate: 1.293E-04 | global batch size: 512 | lm loss: 2.043692E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.594 | TFLOPs: 23.53 | +63: iteration 32260/ 73814 | consumed samples: 16517120 | consumed tokens: 33827061760 | elapsed time per iteration (s): 2.23 | learning rate: 1.293E-04 | global batch size: 512 | lm loss: 2.063726E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.735 | TFLOPs: 23.65 | +63: iteration 32270/ 73814 | consumed samples: 16522240 | consumed tokens: 33837547520 | elapsed time per iteration (s): 2.22 | learning rate: 1.292E-04 | global batch size: 512 | lm loss: 2.025886E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.220 | TFLOPs: 23.70 | +63: iteration 32280/ 73814 | consumed samples: 16527360 | consumed tokens: 33848033280 | elapsed time per iteration (s): 2.26 | learning rate: 1.292E-04 | global batch size: 512 | lm loss: 2.031144E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.021 | TFLOPs: 23.37 | +63: iteration 32290/ 73814 | consumed samples: 16532480 | consumed tokens: 33858519040 | elapsed time per iteration (s): 2.35 | learning rate: 1.291E-04 | global batch size: 512 | lm loss: 2.051502E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.248 | TFLOPs: 22.47 | +63: iteration 32300/ 73814 | consumed samples: 16537600 | consumed tokens: 33869004800 | elapsed time per iteration (s): 2.40 | learning rate: 1.291E-04 | global batch size: 512 | lm loss: 2.049426E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.520 | TFLOPs: 21.98 | +63: iteration 32310/ 73814 | consumed samples: 16542720 | consumed tokens: 33879490560 | elapsed time per iteration (s): 2.30 | learning rate: 1.291E-04 | global batch size: 512 | lm loss: 2.071289E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.663 | TFLOPs: 22.92 | +63: iteration 32320/ 73814 | consumed samples: 16547840 | consumed tokens: 33889976320 | elapsed time per iteration (s): 2.31 | learning rate: 1.290E-04 | global batch size: 512 | lm loss: 2.067101E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.254 | TFLOPs: 22.78 | +63: iteration 32330/ 73814 | consumed samples: 16552960 | consumed tokens: 33900462080 | elapsed time per iteration (s): 2.47 | learning rate: 1.290E-04 | global batch size: 512 | lm loss: 2.059879E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.935 | TFLOPs: 21.30 | +63: iteration 32340/ 73814 | consumed samples: 16558080 | consumed tokens: 33910947840 | elapsed time per iteration (s): 2.56 | learning rate: 1.290E-04 | global batch size: 512 | lm loss: 2.048708E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.815 | TFLOPs: 20.57 | +63: iteration 32350/ 73814 | consumed samples: 16563200 | consumed tokens: 33921433600 | elapsed time per iteration (s): 2.59 | learning rate: 1.289E-04 | global batch size: 512 | lm loss: 2.059647E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 197.382 | TFLOPs: 20.32 | +63: iteration 32360/ 73814 | consumed samples: 16568320 | consumed tokens: 33931919360 | elapsed time per iteration (s): 2.34 | learning rate: 1.289E-04 | global batch size: 512 | lm loss: 2.055729E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.983 | TFLOPs: 22.54 | +63: iteration 32370/ 73814 | consumed samples: 16573440 | consumed tokens: 33942405120 | elapsed time per iteration (s): 2.24 | learning rate: 1.288E-04 | global batch size: 512 | lm loss: 2.066894E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.662 | TFLOPs: 23.54 | +63: iteration 32380/ 73814 | consumed samples: 16578560 | consumed tokens: 33952890880 | elapsed time per iteration (s): 2.24 | learning rate: 1.288E-04 | global batch size: 512 | lm loss: 2.082558E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.907 | TFLOPs: 23.56 | +63: iteration 32390/ 73814 | consumed samples: 16583680 | consumed tokens: 33963376640 | elapsed time per iteration (s): 2.35 | learning rate: 1.288E-04 | global batch size: 512 | lm loss: 2.037948E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.303 | TFLOPs: 22.47 | +63: iteration 32400/ 73814 | consumed samples: 16588800 | consumed tokens: 33973862400 | elapsed time per iteration (s): 2.34 | learning rate: 1.287E-04 | global batch size: 512 | lm loss: 2.047334E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.385 | TFLOPs: 22.48 | +63: iteration 32410/ 73814 | consumed samples: 16593920 | consumed tokens: 33984348160 | elapsed time per iteration (s): 2.24 | learning rate: 1.287E-04 | global batch size: 512 | lm loss: 2.069999E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.910 | TFLOPs: 23.57 | +63: iteration 32420/ 73814 | consumed samples: 16599040 | consumed tokens: 33994833920 | elapsed time per iteration (s): 2.26 | learning rate: 1.287E-04 | global batch size: 512 | lm loss: 2.046027E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.657 | TFLOPs: 23.33 | +63: iteration 32430/ 73814 | consumed samples: 16604160 | consumed tokens: 34005319680 | elapsed time per iteration (s): 2.25 | learning rate: 1.286E-04 | global batch size: 512 | lm loss: 2.041841E+00 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.506 | TFLOPs: 23.42 | +63: iteration 32440/ 73814 | consumed samples: 16609280 | consumed tokens: 34015805440 | elapsed time per iteration (s): 2.24 | learning rate: 1.286E-04 | global batch size: 512 | lm loss: 2.044352E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.152 | TFLOPs: 23.49 | +63: iteration 32450/ 73814 | consumed samples: 16614400 | consumed tokens: 34026291200 | elapsed time per iteration (s): 2.27 | learning rate: 1.285E-04 | global batch size: 512 | lm loss: 2.051395E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.685 | TFLOPs: 23.23 | +63: iteration 32460/ 73814 | consumed samples: 16619520 | consumed tokens: 34036776960 | elapsed time per iteration (s): 2.24 | learning rate: 1.285E-04 | global batch size: 512 | lm loss: 2.041323E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.062 | TFLOPs: 23.58 | +63: iteration 32470/ 73814 | consumed samples: 16624640 | consumed tokens: 34047262720 | elapsed time per iteration (s): 2.25 | learning rate: 1.285E-04 | global batch size: 512 | lm loss: 2.061731E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.534 | TFLOPs: 23.42 | +63: iteration 32480/ 73814 | consumed samples: 16629760 | consumed tokens: 34057748480 | elapsed time per iteration (s): 2.25 | learning rate: 1.284E-04 | global batch size: 512 | lm loss: 2.037539E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.554 | TFLOPs: 23.43 | +63: iteration 32490/ 73814 | consumed samples: 16634880 | consumed tokens: 34068234240 | elapsed time per iteration (s): 2.44 | learning rate: 1.284E-04 | global batch size: 512 | lm loss: 2.038740E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.609 | TFLOPs: 21.58 | +63: iteration 32500/ 73814 | consumed samples: 16640000 | consumed tokens: 34078720000 | elapsed time per iteration (s): 2.23 | learning rate: 1.284E-04 | global batch size: 512 | lm loss: 2.058495E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.774 | TFLOPs: 23.65 | +63: iteration 32510/ 73814 | consumed samples: 16645120 | consumed tokens: 34089205760 | elapsed time per iteration (s): 2.23 | learning rate: 1.283E-04 | global batch size: 512 | lm loss: 2.046954E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.620 | TFLOPs: 23.64 | +63: iteration 32520/ 73814 | consumed samples: 16650240 | consumed tokens: 34099691520 | elapsed time per iteration (s): 2.22 | learning rate: 1.283E-04 | global batch size: 512 | lm loss: 2.060129E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.158 | TFLOPs: 23.69 | +63: iteration 32530/ 73814 | consumed samples: 16655360 | consumed tokens: 34110177280 | elapsed time per iteration (s): 2.23 | learning rate: 1.282E-04 | global batch size: 512 | lm loss: 2.040271E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.194 | TFLOPs: 23.59 | +63: iteration 32540/ 73814 | consumed samples: 16660480 | consumed tokens: 34120663040 | elapsed time per iteration (s): 2.23 | learning rate: 1.282E-04 | global batch size: 512 | lm loss: 2.064476E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.015 | TFLOPs: 23.68 | +63: iteration 32550/ 73814 | consumed samples: 16665600 | consumed tokens: 34131148800 | elapsed time per iteration (s): 2.26 | learning rate: 1.282E-04 | global batch size: 512 | lm loss: 2.053492E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.362 | TFLOPs: 23.30 | +63: iteration 32560/ 73814 | consumed samples: 16670720 | consumed tokens: 34141634560 | elapsed time per iteration (s): 2.24 | learning rate: 1.281E-04 | global batch size: 512 | lm loss: 2.036916E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.282 | TFLOPs: 23.50 | +63: iteration 32570/ 73814 | consumed samples: 16675840 | consumed tokens: 34152120320 | elapsed time per iteration (s): 2.24 | learning rate: 1.281E-04 | global batch size: 512 | lm loss: 2.060613E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.690 | TFLOPs: 23.54 | +63: iteration 32580/ 73814 | consumed samples: 16680960 | consumed tokens: 34162606080 | elapsed time per iteration (s): 2.23 | learning rate: 1.280E-04 | global batch size: 512 | lm loss: 2.043964E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.637 | TFLOPs: 23.64 | +63: iteration 32590/ 73814 | consumed samples: 16686080 | consumed tokens: 34173091840 | elapsed time per iteration (s): 2.24 | learning rate: 1.280E-04 | global batch size: 512 | lm loss: 2.062516E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.218 | TFLOPs: 23.49 | +63: iteration 32600/ 73814 | consumed samples: 16691200 | consumed tokens: 34183577600 | elapsed time per iteration (s): 2.23 | learning rate: 1.280E-04 | global batch size: 512 | lm loss: 2.055556E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.503 | TFLOPs: 23.63 | +63: iteration 32610/ 73814 | consumed samples: 16696320 | consumed tokens: 34194063360 | elapsed time per iteration (s): 2.23 | learning rate: 1.279E-04 | global batch size: 512 | lm loss: 2.044795E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.624 | TFLOPs: 23.64 | +63: iteration 32620/ 73814 | consumed samples: 16701440 | consumed tokens: 34204549120 | elapsed time per iteration (s): 2.49 | learning rate: 1.279E-04 | global batch size: 512 | lm loss: 2.068060E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.856 | TFLOPs: 21.19 | +63: iteration 32630/ 73814 | consumed samples: 16706560 | consumed tokens: 34215034880 | elapsed time per iteration (s): 2.31 | learning rate: 1.279E-04 | global batch size: 512 | lm loss: 2.025394E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.446 | TFLOPs: 22.80 | +63: iteration 32640/ 73814 | consumed samples: 16711680 | consumed tokens: 34225520640 | elapsed time per iteration (s): 2.25 | learning rate: 1.278E-04 | global batch size: 512 | lm loss: 2.056433E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.740 | TFLOPs: 23.44 | +63: iteration 32650/ 73814 | consumed samples: 16716800 | consumed tokens: 34236006400 | elapsed time per iteration (s): 2.23 | learning rate: 1.278E-04 | global batch size: 512 | lm loss: 2.049800E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.940 | TFLOPs: 23.67 | +63: iteration 32660/ 73814 | consumed samples: 16721920 | consumed tokens: 34246492160 | elapsed time per iteration (s): 2.24 | learning rate: 1.277E-04 | global batch size: 512 | lm loss: 2.047985E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.928 | TFLOPs: 23.57 | +63: iteration 32670/ 73814 | consumed samples: 16727040 | consumed tokens: 34256977920 | elapsed time per iteration (s): 2.25 | learning rate: 1.277E-04 | global batch size: 512 | lm loss: 2.040231E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.239 | TFLOPs: 23.39 | +63: iteration 32680/ 73814 | consumed samples: 16732160 | consumed tokens: 34267463680 | elapsed time per iteration (s): 2.25 | learning rate: 1.277E-04 | global batch size: 512 | lm loss: 2.061398E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.213 | TFLOPs: 23.39 | +63: iteration 32690/ 73814 | consumed samples: 16737280 | consumed tokens: 34277949440 | elapsed time per iteration (s): 2.26 | learning rate: 1.276E-04 | global batch size: 512 | lm loss: 2.062456E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.757 | TFLOPs: 23.34 | +63: iteration 32700/ 73814 | consumed samples: 16742400 | consumed tokens: 34288435200 | elapsed time per iteration (s): 2.27 | learning rate: 1.276E-04 | global batch size: 512 | lm loss: 2.049652E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.581 | TFLOPs: 23.22 | +63: iteration 32710/ 73814 | consumed samples: 16747520 | consumed tokens: 34298920960 | elapsed time per iteration (s): 2.27 | learning rate: 1.276E-04 | global batch size: 512 | lm loss: 2.037583E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.842 | TFLOPs: 23.25 | +63: iteration 32720/ 73814 | consumed samples: 16752640 | consumed tokens: 34309406720 | elapsed time per iteration (s): 2.24 | learning rate: 1.275E-04 | global batch size: 512 | lm loss: 2.062569E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.968 | TFLOPs: 23.57 | +63: iteration 32730/ 73814 | consumed samples: 16757760 | consumed tokens: 34319892480 | elapsed time per iteration (s): 2.27 | learning rate: 1.275E-04 | global batch size: 512 | lm loss: 2.069771E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.944 | TFLOPs: 23.26 | +63: iteration 32740/ 73814 | consumed samples: 16762880 | consumed tokens: 34330378240 | elapsed time per iteration (s): 2.24 | learning rate: 1.274E-04 | global batch size: 512 | lm loss: 2.062864E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.776 | TFLOPs: 23.55 | +63: iteration 32750/ 73814 | consumed samples: 16768000 | consumed tokens: 34340864000 | elapsed time per iteration (s): 2.25 | learning rate: 1.274E-04 | global batch size: 512 | lm loss: 2.062916E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.087 | TFLOPs: 23.38 | +63: iteration 32760/ 73814 | consumed samples: 16773120 | consumed tokens: 34351349760 | elapsed time per iteration (s): 2.24 | learning rate: 1.274E-04 | global batch size: 512 | lm loss: 2.063561E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.641 | TFLOPs: 23.54 | +63: iteration 32770/ 73814 | consumed samples: 16778240 | consumed tokens: 34361835520 | elapsed time per iteration (s): 2.32 | learning rate: 1.273E-04 | global batch size: 512 | lm loss: 2.069735E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.903 | TFLOPs: 22.74 | +63: iteration 32780/ 73814 | consumed samples: 16783360 | consumed tokens: 34372321280 | elapsed time per iteration (s): 2.26 | learning rate: 1.273E-04 | global batch size: 512 | lm loss: 2.075508E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.197 | TFLOPs: 23.29 | +63: iteration 32790/ 73814 | consumed samples: 16788480 | consumed tokens: 34382807040 | elapsed time per iteration (s): 2.29 | learning rate: 1.273E-04 | global batch size: 512 | lm loss: 2.065924E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.213 | TFLOPs: 22.98 | +63: iteration 32800/ 73814 | consumed samples: 16793600 | consumed tokens: 34393292800 | elapsed time per iteration (s): 2.24 | learning rate: 1.272E-04 | global batch size: 512 | lm loss: 2.088600E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.764 | TFLOPs: 23.55 | +63: iteration 32810/ 73814 | consumed samples: 16798720 | consumed tokens: 34403778560 | elapsed time per iteration (s): 2.28 | learning rate: 1.272E-04 | global batch size: 512 | lm loss: 2.038964E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.765 | TFLOPs: 23.14 | +63: iteration 32820/ 73814 | consumed samples: 16803840 | consumed tokens: 34414264320 | elapsed time per iteration (s): 2.27 | learning rate: 1.271E-04 | global batch size: 512 | lm loss: 2.029016E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.078 | TFLOPs: 23.17 | +63: iteration 32830/ 73814 | consumed samples: 16808960 | consumed tokens: 34424750080 | elapsed time per iteration (s): 2.22 | learning rate: 1.271E-04 | global batch size: 512 | lm loss: 2.059825E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.183 | TFLOPs: 23.70 | +63: iteration 32840/ 73814 | consumed samples: 16814080 | consumed tokens: 34435235840 | elapsed time per iteration (s): 2.25 | learning rate: 1.271E-04 | global batch size: 512 | lm loss: 2.059735E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.552 | TFLOPs: 23.43 | +63: iteration 32850/ 73814 | consumed samples: 16819200 | consumed tokens: 34445721600 | elapsed time per iteration (s): 2.24 | learning rate: 1.270E-04 | global batch size: 512 | lm loss: 2.043372E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.072 | TFLOPs: 23.58 | +63: iteration 32860/ 73814 | consumed samples: 16824320 | consumed tokens: 34456207360 | elapsed time per iteration (s): 2.24 | learning rate: 1.270E-04 | global batch size: 512 | lm loss: 2.077831E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.814 | TFLOPs: 23.56 | +63: iteration 32870/ 73814 | consumed samples: 16829440 | consumed tokens: 34466693120 | elapsed time per iteration (s): 2.26 | learning rate: 1.269E-04 | global batch size: 512 | lm loss: 2.056763E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.657 | TFLOPs: 23.33 | +63: iteration 32880/ 73814 | consumed samples: 16834560 | consumed tokens: 34477178880 | elapsed time per iteration (s): 2.26 | learning rate: 1.269E-04 | global batch size: 512 | lm loss: 2.058776E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.186 | TFLOPs: 23.28 | +63: iteration 32890/ 73814 | consumed samples: 16839680 | consumed tokens: 34487664640 | elapsed time per iteration (s): 2.23 | learning rate: 1.269E-04 | global batch size: 512 | lm loss: 2.043608E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.790 | TFLOPs: 23.66 | +63: iteration 32900/ 73814 | consumed samples: 16844800 | consumed tokens: 34498150400 | elapsed time per iteration (s): 2.26 | learning rate: 1.268E-04 | global batch size: 512 | lm loss: 2.046377E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.379 | TFLOPs: 23.30 | +63: iteration 32910/ 73814 | consumed samples: 16849920 | consumed tokens: 34508636160 | elapsed time per iteration (s): 2.27 | learning rate: 1.268E-04 | global batch size: 512 | lm loss: 2.026584E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.296 | TFLOPs: 23.19 | +63: iteration 32920/ 73814 | consumed samples: 16855040 | consumed tokens: 34519121920 | elapsed time per iteration (s): 2.25 | learning rate: 1.268E-04 | global batch size: 512 | lm loss: 2.058700E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.724 | TFLOPs: 23.44 | +63: iteration 32930/ 73814 | consumed samples: 16860160 | consumed tokens: 34529607680 | elapsed time per iteration (s): 2.24 | learning rate: 1.267E-04 | global batch size: 512 | lm loss: 2.071494E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.624 | TFLOPs: 23.54 | +63: iteration 32940/ 73814 | consumed samples: 16865280 | consumed tokens: 34540093440 | elapsed time per iteration (s): 2.26 | learning rate: 1.267E-04 | global batch size: 512 | lm loss: 2.046546E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.100 | TFLOPs: 23.28 | +63: iteration 32950/ 73814 | consumed samples: 16870400 | consumed tokens: 34550579200 | elapsed time per iteration (s): 2.25 | learning rate: 1.266E-04 | global batch size: 512 | lm loss: 2.059240E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.254 | TFLOPs: 23.39 | +63: iteration 32960/ 73814 | consumed samples: 16875520 | consumed tokens: 34561064960 | elapsed time per iteration (s): 2.23 | learning rate: 1.266E-04 | global batch size: 512 | lm loss: 2.063503E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.299 | TFLOPs: 23.61 | +63: iteration 32970/ 73814 | consumed samples: 16880640 | consumed tokens: 34571550720 | elapsed time per iteration (s): 2.22 | learning rate: 1.266E-04 | global batch size: 512 | lm loss: 2.052196E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.405 | TFLOPs: 23.72 | +63: iteration 32980/ 73814 | consumed samples: 16885760 | consumed tokens: 34582036480 | elapsed time per iteration (s): 2.24 | learning rate: 1.265E-04 | global batch size: 512 | lm loss: 2.045596E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.634 | TFLOPs: 23.54 | +63: iteration 32990/ 73814 | consumed samples: 16890880 | consumed tokens: 34592522240 | elapsed time per iteration (s): 2.23 | learning rate: 1.265E-04 | global batch size: 512 | lm loss: 2.054512E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.201 | TFLOPs: 23.60 | +63: iteration 33000/ 73814 | consumed samples: 16896000 | consumed tokens: 34603008000 | elapsed time per iteration (s): 2.23 | learning rate: 1.265E-04 | global batch size: 512 | lm loss: 2.022326E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.317 | TFLOPs: 23.61 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 33000 | lm loss value: 1.898600E+00 | lm loss PPL: 6.676542E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 33010/ 73814 | consumed samples: 16901120 | consumed tokens: 34613493760 | elapsed time per iteration (s): 2.31 | learning rate: 1.264E-04 | global batch size: 512 | lm loss: 2.038415E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.696 | TFLOPs: 22.82 | +63: iteration 33020/ 73814 | consumed samples: 16906240 | consumed tokens: 34623979520 | elapsed time per iteration (s): 2.23 | learning rate: 1.264E-04 | global batch size: 512 | lm loss: 2.057213E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.643 | TFLOPs: 23.64 | +63: iteration 33030/ 73814 | consumed samples: 16911360 | consumed tokens: 34634465280 | elapsed time per iteration (s): 2.24 | learning rate: 1.263E-04 | global batch size: 512 | lm loss: 2.030589E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.885 | TFLOPs: 23.56 | +63: iteration 33040/ 73814 | consumed samples: 16916480 | consumed tokens: 34644951040 | elapsed time per iteration (s): 2.24 | learning rate: 1.263E-04 | global batch size: 512 | lm loss: 2.033764E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.815 | TFLOPs: 23.56 | +63: iteration 33050/ 73814 | consumed samples: 16921600 | consumed tokens: 34655436800 | elapsed time per iteration (s): 2.24 | learning rate: 1.263E-04 | global batch size: 512 | lm loss: 2.064722E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.783 | TFLOPs: 23.55 | +63: iteration 33060/ 73814 | consumed samples: 16926720 | consumed tokens: 34665922560 | elapsed time per iteration (s): 2.24 | learning rate: 1.262E-04 | global batch size: 512 | lm loss: 2.072169E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.642 | TFLOPs: 23.54 | +63: iteration 33070/ 73814 | consumed samples: 16931840 | consumed tokens: 34676408320 | elapsed time per iteration (s): 2.22 | learning rate: 1.262E-04 | global batch size: 512 | lm loss: 2.051516E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.420 | TFLOPs: 23.72 | +63: iteration 33080/ 73814 | consumed samples: 16936960 | consumed tokens: 34686894080 | elapsed time per iteration (s): 2.26 | learning rate: 1.261E-04 | global batch size: 512 | lm loss: 2.058119E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.638 | TFLOPs: 23.33 | +63: iteration 33090/ 73814 | consumed samples: 16942080 | consumed tokens: 34697379840 | elapsed time per iteration (s): 2.24 | learning rate: 1.261E-04 | global batch size: 512 | lm loss: 2.047274E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.752 | TFLOPs: 23.55 | +63: iteration 33100/ 73814 | consumed samples: 16947200 | consumed tokens: 34707865600 | elapsed time per iteration (s): 2.22 | learning rate: 1.261E-04 | global batch size: 512 | lm loss: 2.060594E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.140 | TFLOPs: 23.69 | +63: iteration 33110/ 73814 | consumed samples: 16952320 | consumed tokens: 34718351360 | elapsed time per iteration (s): 2.23 | learning rate: 1.260E-04 | global batch size: 512 | lm loss: 2.069183E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.340 | TFLOPs: 23.61 | +63: iteration 33120/ 73814 | consumed samples: 16957440 | consumed tokens: 34728837120 | elapsed time per iteration (s): 2.24 | learning rate: 1.260E-04 | global batch size: 512 | lm loss: 2.055889E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.150 | TFLOPs: 23.49 | +63: iteration 33130/ 73814 | consumed samples: 16962560 | consumed tokens: 34739322880 | elapsed time per iteration (s): 2.25 | learning rate: 1.260E-04 | global batch size: 512 | lm loss: 2.015625E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.227 | TFLOPs: 23.39 | +63: iteration 33140/ 73814 | consumed samples: 16967680 | consumed tokens: 34749808640 | elapsed time per iteration (s): 2.23 | learning rate: 1.259E-04 | global batch size: 512 | lm loss: 2.034912E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.106 | TFLOPs: 23.69 | +63: iteration 33150/ 73814 | consumed samples: 16972800 | consumed tokens: 34760294400 | elapsed time per iteration (s): 2.40 | learning rate: 1.259E-04 | global batch size: 512 | lm loss: 2.050429E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.312 | TFLOPs: 21.96 | +63: iteration 33160/ 73814 | consumed samples: 16977920 | consumed tokens: 34770780160 | elapsed time per iteration (s): 2.23 | learning rate: 1.258E-04 | global batch size: 512 | lm loss: 2.055844E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.761 | TFLOPs: 23.65 | +63: iteration 33170/ 73814 | consumed samples: 16983040 | consumed tokens: 34781265920 | elapsed time per iteration (s): 2.27 | learning rate: 1.258E-04 | global batch size: 512 | lm loss: 2.065338E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.160 | TFLOPs: 23.18 | +63: iteration 33180/ 73814 | consumed samples: 16988160 | consumed tokens: 34791751680 | elapsed time per iteration (s): 2.32 | learning rate: 1.258E-04 | global batch size: 512 | lm loss: 2.055287E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.293 | TFLOPs: 22.68 | +63: iteration 33190/ 73814 | consumed samples: 16993280 | consumed tokens: 34802237440 | elapsed time per iteration (s): 2.23 | learning rate: 1.257E-04 | global batch size: 512 | lm loss: 2.050475E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.706 | TFLOPs: 23.65 | +63: iteration 33200/ 73814 | consumed samples: 16998400 | consumed tokens: 34812723200 | elapsed time per iteration (s): 2.31 | learning rate: 1.257E-04 | global batch size: 512 | lm loss: 2.032229E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.505 | TFLOPs: 22.80 | +63: iteration 33210/ 73814 | consumed samples: 17003520 | consumed tokens: 34823208960 | elapsed time per iteration (s): 2.22 | learning rate: 1.257E-04 | global batch size: 512 | lm loss: 2.074824E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.406 | TFLOPs: 23.72 | +63: iteration 33220/ 73814 | consumed samples: 17008640 | consumed tokens: 34833694720 | elapsed time per iteration (s): 2.26 | learning rate: 1.256E-04 | global batch size: 512 | lm loss: 2.054461E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.728 | TFLOPs: 23.34 | +63: iteration 33230/ 73814 | consumed samples: 17013760 | consumed tokens: 34844180480 | elapsed time per iteration (s): 2.22 | learning rate: 1.256E-04 | global batch size: 512 | lm loss: 2.046335E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.209 | TFLOPs: 23.70 | +63: iteration 33240/ 73814 | consumed samples: 17018880 | consumed tokens: 34854666240 | elapsed time per iteration (s): 2.23 | learning rate: 1.255E-04 | global batch size: 512 | lm loss: 2.052785E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.401 | TFLOPs: 23.62 | +63: iteration 33250/ 73814 | consumed samples: 17024000 | consumed tokens: 34865152000 | elapsed time per iteration (s): 2.38 | learning rate: 1.255E-04 | global batch size: 512 | lm loss: 2.082650E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.254 | TFLOPs: 22.16 | +63: iteration 33260/ 73814 | consumed samples: 17029120 | consumed tokens: 34875637760 | elapsed time per iteration (s): 2.28 | learning rate: 1.255E-04 | global batch size: 512 | lm loss: 2.037759E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.988 | TFLOPs: 23.16 | +63: iteration 33270/ 73814 | consumed samples: 17034240 | consumed tokens: 34886123520 | elapsed time per iteration (s): 2.22 | learning rate: 1.254E-04 | global batch size: 512 | lm loss: 2.086300E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.154 | TFLOPs: 23.69 | +63: iteration 33280/ 73814 | consumed samples: 17039360 | consumed tokens: 34896609280 | elapsed time per iteration (s): 2.25 | learning rate: 1.254E-04 | global batch size: 512 | lm loss: 2.039900E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.659 | TFLOPs: 23.44 | +63: iteration 33290/ 73814 | consumed samples: 17044480 | consumed tokens: 34907095040 | elapsed time per iteration (s): 2.26 | learning rate: 1.253E-04 | global batch size: 512 | lm loss: 2.045000E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.335 | TFLOPs: 23.30 | +63: iteration 33300/ 73814 | consumed samples: 17049600 | consumed tokens: 34917580800 | elapsed time per iteration (s): 2.24 | learning rate: 1.253E-04 | global batch size: 512 | lm loss: 2.060115E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.942 | TFLOPs: 23.57 | +63: iteration 33310/ 73814 | consumed samples: 17054720 | consumed tokens: 34928066560 | elapsed time per iteration (s): 2.24 | learning rate: 1.253E-04 | global batch size: 512 | lm loss: 2.019173E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.880 | TFLOPs: 23.56 | +63: iteration 33320/ 73814 | consumed samples: 17059840 | consumed tokens: 34938552320 | elapsed time per iteration (s): 2.23 | learning rate: 1.252E-04 | global batch size: 512 | lm loss: 2.032725E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.056 | TFLOPs: 23.68 | +63: iteration 33330/ 73814 | consumed samples: 17064960 | consumed tokens: 34949038080 | elapsed time per iteration (s): 2.27 | learning rate: 1.252E-04 | global batch size: 512 | lm loss: 2.065006E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.456 | TFLOPs: 23.21 | +63: iteration 33340/ 73814 | consumed samples: 17070080 | consumed tokens: 34959523840 | elapsed time per iteration (s): 2.23 | learning rate: 1.252E-04 | global batch size: 512 | lm loss: 2.031793E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.974 | TFLOPs: 23.67 | +63: iteration 33350/ 73814 | consumed samples: 17075200 | consumed tokens: 34970009600 | elapsed time per iteration (s): 2.27 | learning rate: 1.251E-04 | global batch size: 512 | lm loss: 2.040337E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.811 | TFLOPs: 23.25 | +63: iteration 33360/ 73814 | consumed samples: 17080320 | consumed tokens: 34980495360 | elapsed time per iteration (s): 2.23 | learning rate: 1.251E-04 | global batch size: 512 | lm loss: 2.048453E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.778 | TFLOPs: 23.65 | +63: iteration 33370/ 73814 | consumed samples: 17085440 | consumed tokens: 34990981120 | elapsed time per iteration (s): 2.24 | learning rate: 1.250E-04 | global batch size: 512 | lm loss: 2.037176E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.970 | TFLOPs: 23.57 | +63: iteration 33380/ 73814 | consumed samples: 17090560 | consumed tokens: 35001466880 | elapsed time per iteration (s): 2.22 | learning rate: 1.250E-04 | global batch size: 512 | lm loss: 2.027697E+00 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.172 | TFLOPs: 23.70 | +63: iteration 33390/ 73814 | consumed samples: 17095680 | consumed tokens: 35011952640 | elapsed time per iteration (s): 2.23 | learning rate: 1.250E-04 | global batch size: 512 | lm loss: 2.064969E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.946 | TFLOPs: 23.67 | +63: iteration 33400/ 73814 | consumed samples: 17100800 | consumed tokens: 35022438400 | elapsed time per iteration (s): 2.24 | learning rate: 1.249E-04 | global batch size: 512 | lm loss: 2.057159E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.607 | TFLOPs: 23.53 | +63: iteration 33410/ 73814 | consumed samples: 17105920 | consumed tokens: 35032924160 | elapsed time per iteration (s): 2.23 | learning rate: 1.249E-04 | global batch size: 512 | lm loss: 2.045396E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.876 | TFLOPs: 23.66 | +63: iteration 33420/ 73814 | consumed samples: 17111040 | consumed tokens: 35043409920 | elapsed time per iteration (s): 2.28 | learning rate: 1.249E-04 | global batch size: 512 | lm loss: 2.023798E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.644 | TFLOPs: 23.13 | +63: iteration 33430/ 73814 | consumed samples: 17116160 | consumed tokens: 35053895680 | elapsed time per iteration (s): 2.23 | learning rate: 1.248E-04 | global batch size: 512 | lm loss: 2.036787E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.615 | TFLOPs: 23.64 | +63: iteration 33440/ 73814 | consumed samples: 17121280 | consumed tokens: 35064381440 | elapsed time per iteration (s): 2.24 | learning rate: 1.248E-04 | global batch size: 512 | lm loss: 2.063137E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.689 | TFLOPs: 23.54 | +63: iteration 33450/ 73814 | consumed samples: 17126400 | consumed tokens: 35074867200 | elapsed time per iteration (s): 2.27 | learning rate: 1.247E-04 | global batch size: 512 | lm loss: 2.057432E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.362 | TFLOPs: 23.20 | +63: iteration 33460/ 73814 | consumed samples: 17131520 | consumed tokens: 35085352960 | elapsed time per iteration (s): 2.34 | learning rate: 1.247E-04 | global batch size: 512 | lm loss: 2.035921E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.931 | TFLOPs: 22.54 | +63: iteration 33470/ 73814 | consumed samples: 17136640 | consumed tokens: 35095838720 | elapsed time per iteration (s): 2.24 | learning rate: 1.247E-04 | global batch size: 512 | lm loss: 2.057769E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.198 | TFLOPs: 23.49 | +63: iteration 33480/ 73814 | consumed samples: 17141760 | consumed tokens: 35106324480 | elapsed time per iteration (s): 2.33 | learning rate: 1.246E-04 | global batch size: 512 | lm loss: 2.040393E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.515 | TFLOPs: 22.60 | +63: iteration 33490/ 73814 | consumed samples: 17146880 | consumed tokens: 35116810240 | elapsed time per iteration (s): 2.23 | learning rate: 1.246E-04 | global batch size: 512 | lm loss: 2.073742E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.196 | TFLOPs: 23.59 | +63: iteration 33500/ 73814 | consumed samples: 17152000 | consumed tokens: 35127296000 | elapsed time per iteration (s): 2.32 | learning rate: 1.245E-04 | global batch size: 512 | lm loss: 2.055041E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.628 | TFLOPs: 22.71 | +63: iteration 33510/ 73814 | consumed samples: 17157120 | consumed tokens: 35137781760 | elapsed time per iteration (s): 2.27 | learning rate: 1.245E-04 | global batch size: 512 | lm loss: 2.043774E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.925 | TFLOPs: 23.26 | +63: iteration 33520/ 73814 | consumed samples: 17162240 | consumed tokens: 35148267520 | elapsed time per iteration (s): 2.24 | learning rate: 1.245E-04 | global batch size: 512 | lm loss: 2.040922E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.063 | TFLOPs: 23.48 | +63: iteration 33530/ 73814 | consumed samples: 17167360 | consumed tokens: 35158753280 | elapsed time per iteration (s): 2.26 | learning rate: 1.244E-04 | global batch size: 512 | lm loss: 2.043855E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.432 | TFLOPs: 23.31 | +63: iteration 33540/ 73814 | consumed samples: 17172480 | consumed tokens: 35169239040 | elapsed time per iteration (s): 2.25 | learning rate: 1.244E-04 | global batch size: 512 | lm loss: 2.047379E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.125 | TFLOPs: 23.38 | +63: iteration 33550/ 73814 | consumed samples: 17177600 | consumed tokens: 35179724800 | elapsed time per iteration (s): 2.24 | learning rate: 1.244E-04 | global batch size: 512 | lm loss: 2.024142E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.644 | TFLOPs: 23.54 | +63: iteration 33560/ 73814 | consumed samples: 17182720 | consumed tokens: 35190210560 | elapsed time per iteration (s): 2.28 | learning rate: 1.243E-04 | global batch size: 512 | lm loss: 2.050664E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.784 | TFLOPs: 23.14 | +63: iteration 33570/ 73814 | consumed samples: 17187840 | consumed tokens: 35200696320 | elapsed time per iteration (s): 2.25 | learning rate: 1.243E-04 | global batch size: 512 | lm loss: 2.068951E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.256 | TFLOPs: 23.39 | +63: iteration 33580/ 73814 | consumed samples: 17192960 | consumed tokens: 35211182080 | elapsed time per iteration (s): 2.30 | learning rate: 1.242E-04 | global batch size: 512 | lm loss: 2.050427E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.989 | TFLOPs: 22.96 | +63: iteration 33590/ 73814 | consumed samples: 17198080 | consumed tokens: 35221667840 | elapsed time per iteration (s): 2.24 | learning rate: 1.242E-04 | global batch size: 512 | lm loss: 2.030630E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.024 | TFLOPs: 23.58 | +63: iteration 33600/ 73814 | consumed samples: 17203200 | consumed tokens: 35232153600 | elapsed time per iteration (s): 2.25 | learning rate: 1.242E-04 | global batch size: 512 | lm loss: 2.015730E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.974 | TFLOPs: 23.47 | +63: iteration 33610/ 73814 | consumed samples: 17208320 | consumed tokens: 35242639360 | elapsed time per iteration (s): 2.23 | learning rate: 1.241E-04 | global batch size: 512 | lm loss: 2.043301E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.608 | TFLOPs: 23.64 | +63: iteration 33620/ 73814 | consumed samples: 17213440 | consumed tokens: 35253125120 | elapsed time per iteration (s): 2.27 | learning rate: 1.241E-04 | global batch size: 512 | lm loss: 2.058821E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.871 | TFLOPs: 23.25 | +63: iteration 33630/ 73814 | consumed samples: 17218560 | consumed tokens: 35263610880 | elapsed time per iteration (s): 2.24 | learning rate: 1.241E-04 | global batch size: 512 | lm loss: 2.051472E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.637 | TFLOPs: 23.54 | +63: iteration 33640/ 73814 | consumed samples: 17223680 | consumed tokens: 35274096640 | elapsed time per iteration (s): 2.23 | learning rate: 1.240E-04 | global batch size: 512 | lm loss: 2.046070E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.398 | TFLOPs: 23.62 | +63: iteration 33650/ 73814 | consumed samples: 17228800 | consumed tokens: 35284582400 | elapsed time per iteration (s): 2.24 | learning rate: 1.240E-04 | global batch size: 512 | lm loss: 2.048352E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.287 | TFLOPs: 23.50 | +63: iteration 33660/ 73814 | consumed samples: 17233920 | consumed tokens: 35295068160 | elapsed time per iteration (s): 2.25 | learning rate: 1.239E-04 | global batch size: 512 | lm loss: 2.055497E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.234 | TFLOPs: 23.39 | +63: iteration 33670/ 73814 | consumed samples: 17239040 | consumed tokens: 35305553920 | elapsed time per iteration (s): 2.24 | learning rate: 1.239E-04 | global batch size: 512 | lm loss: 2.021095E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.718 | TFLOPs: 23.55 | +63: iteration 33680/ 73814 | consumed samples: 17244160 | consumed tokens: 35316039680 | elapsed time per iteration (s): 2.28 | learning rate: 1.239E-04 | global batch size: 512 | lm loss: 2.039943E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.594 | TFLOPs: 23.12 | +63: iteration 33690/ 73814 | consumed samples: 17249280 | consumed tokens: 35326525440 | elapsed time per iteration (s): 2.24 | learning rate: 1.238E-04 | global batch size: 512 | lm loss: 2.013319E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.839 | TFLOPs: 23.56 | +63: iteration 33700/ 73814 | consumed samples: 17254400 | consumed tokens: 35337011200 | elapsed time per iteration (s): 2.25 | learning rate: 1.238E-04 | global batch size: 512 | lm loss: 2.029306E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.788 | TFLOPs: 23.45 | +63: iteration 33710/ 73814 | consumed samples: 17259520 | consumed tokens: 35347496960 | elapsed time per iteration (s): 2.24 | learning rate: 1.237E-04 | global batch size: 512 | lm loss: 2.075398E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.640 | TFLOPs: 23.54 | +63: iteration 33720/ 73814 | consumed samples: 17264640 | consumed tokens: 35357982720 | elapsed time per iteration (s): 2.23 | learning rate: 1.237E-04 | global batch size: 512 | lm loss: 2.065694E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.991 | TFLOPs: 23.68 | +63: iteration 33730/ 73814 | consumed samples: 17269760 | consumed tokens: 35368468480 | elapsed time per iteration (s): 2.36 | learning rate: 1.237E-04 | global batch size: 512 | lm loss: 2.033953E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.845 | TFLOPs: 22.32 | +63: iteration 33740/ 73814 | consumed samples: 17274880 | consumed tokens: 35378954240 | elapsed time per iteration (s): 2.30 | learning rate: 1.236E-04 | global batch size: 512 | lm loss: 2.026245E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.802 | TFLOPs: 22.94 | +63: iteration 33750/ 73814 | consumed samples: 17280000 | consumed tokens: 35389440000 | elapsed time per iteration (s): 2.35 | learning rate: 1.236E-04 | global batch size: 512 | lm loss: 2.043839E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.716 | TFLOPs: 22.41 | +63: iteration 33760/ 73814 | consumed samples: 17285120 | consumed tokens: 35399925760 | elapsed time per iteration (s): 2.39 | learning rate: 1.236E-04 | global batch size: 512 | lm loss: 2.057186E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.811 | TFLOPs: 22.01 | +63: iteration 33770/ 73814 | consumed samples: 17290240 | consumed tokens: 35410411520 | elapsed time per iteration (s): 2.23 | learning rate: 1.235E-04 | global batch size: 512 | lm loss: 2.041526E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.708 | TFLOPs: 23.65 | +63: iteration 33780/ 73814 | consumed samples: 17295360 | consumed tokens: 35420897280 | elapsed time per iteration (s): 2.23 | learning rate: 1.235E-04 | global batch size: 512 | lm loss: 2.036709E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.613 | TFLOPs: 23.64 | +63: iteration 33790/ 73814 | consumed samples: 17300480 | consumed tokens: 35431383040 | elapsed time per iteration (s): 2.25 | learning rate: 1.234E-04 | global batch size: 512 | lm loss: 2.075194E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.275 | TFLOPs: 23.40 | +63: iteration 33800/ 73814 | consumed samples: 17305600 | consumed tokens: 35441868800 | elapsed time per iteration (s): 2.23 | learning rate: 1.234E-04 | global batch size: 512 | lm loss: 2.074942E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.606 | TFLOPs: 23.64 | +63: iteration 33810/ 73814 | consumed samples: 17310720 | consumed tokens: 35452354560 | elapsed time per iteration (s): 2.23 | learning rate: 1.234E-04 | global batch size: 512 | lm loss: 2.047930E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.777 | TFLOPs: 23.65 | +63: iteration 33820/ 73814 | consumed samples: 17315840 | consumed tokens: 35462840320 | elapsed time per iteration (s): 2.23 | learning rate: 1.233E-04 | global batch size: 512 | lm loss: 2.040021E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.526 | TFLOPs: 23.63 | +63: iteration 33830/ 73814 | consumed samples: 17320960 | consumed tokens: 35473326080 | elapsed time per iteration (s): 2.31 | learning rate: 1.233E-04 | global batch size: 512 | lm loss: 2.058144E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.711 | TFLOPs: 22.82 | +63: iteration 33840/ 73814 | consumed samples: 17326080 | consumed tokens: 35483811840 | elapsed time per iteration (s): 2.25 | learning rate: 1.232E-04 | global batch size: 512 | lm loss: 2.047142E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.321 | TFLOPs: 23.40 | +63: iteration 33850/ 73814 | consumed samples: 17331200 | consumed tokens: 35494297600 | elapsed time per iteration (s): 2.24 | learning rate: 1.232E-04 | global batch size: 512 | lm loss: 2.027233E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.320 | TFLOPs: 23.50 | +63: iteration 33860/ 73814 | consumed samples: 17336320 | consumed tokens: 35504783360 | elapsed time per iteration (s): 2.23 | learning rate: 1.232E-04 | global batch size: 512 | lm loss: 2.059863E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.445 | TFLOPs: 23.62 | +63: iteration 33870/ 73814 | consumed samples: 17341440 | consumed tokens: 35515269120 | elapsed time per iteration (s): 2.40 | learning rate: 1.231E-04 | global batch size: 512 | lm loss: 2.016863E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.526 | TFLOPs: 21.98 | +63: iteration 33880/ 73814 | consumed samples: 17346560 | consumed tokens: 35525754880 | elapsed time per iteration (s): 2.52 | learning rate: 1.231E-04 | global batch size: 512 | lm loss: 2.058435E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.868 | TFLOPs: 20.88 | +63: iteration 33890/ 73814 | consumed samples: 17351680 | consumed tokens: 35536240640 | elapsed time per iteration (s): 2.23 | learning rate: 1.231E-04 | global batch size: 512 | lm loss: 2.046452E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.705 | TFLOPs: 23.65 | +63: iteration 33900/ 73814 | consumed samples: 17356800 | consumed tokens: 35546726400 | elapsed time per iteration (s): 2.22 | learning rate: 1.230E-04 | global batch size: 512 | lm loss: 2.030614E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.266 | TFLOPs: 23.70 | +63: iteration 33910/ 73814 | consumed samples: 17361920 | consumed tokens: 35557212160 | elapsed time per iteration (s): 2.24 | learning rate: 1.230E-04 | global batch size: 512 | lm loss: 2.029181E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.715 | TFLOPs: 23.55 | +63: iteration 33920/ 73814 | consumed samples: 17367040 | consumed tokens: 35567697920 | elapsed time per iteration (s): 2.23 | learning rate: 1.229E-04 | global batch size: 512 | lm loss: 2.047230E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.949 | TFLOPs: 23.67 | +63: iteration 33930/ 73814 | consumed samples: 17372160 | consumed tokens: 35578183680 | elapsed time per iteration (s): 2.24 | learning rate: 1.229E-04 | global batch size: 512 | lm loss: 2.049951E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.763 | TFLOPs: 23.55 | +63: iteration 33940/ 73814 | consumed samples: 17377280 | consumed tokens: 35588669440 | elapsed time per iteration (s): 2.23 | learning rate: 1.229E-04 | global batch size: 512 | lm loss: 2.045703E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.923 | TFLOPs: 23.67 | +63: iteration 33950/ 73814 | consumed samples: 17382400 | consumed tokens: 35599155200 | elapsed time per iteration (s): 2.25 | learning rate: 1.228E-04 | global batch size: 512 | lm loss: 2.050433E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.511 | TFLOPs: 23.42 | +63: iteration 33960/ 73814 | consumed samples: 17387520 | consumed tokens: 35609640960 | elapsed time per iteration (s): 2.23 | learning rate: 1.228E-04 | global batch size: 512 | lm loss: 2.060445E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.664 | TFLOPs: 23.64 | +63: iteration 33970/ 73814 | consumed samples: 17392640 | consumed tokens: 35620126720 | elapsed time per iteration (s): 2.25 | learning rate: 1.227E-04 | global batch size: 512 | lm loss: 2.063087E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.418 | TFLOPs: 23.41 | +63: iteration 33980/ 73814 | consumed samples: 17397760 | consumed tokens: 35630612480 | elapsed time per iteration (s): 2.24 | learning rate: 1.227E-04 | global batch size: 512 | lm loss: 2.023381E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.864 | TFLOPs: 23.56 | +63: iteration 33990/ 73814 | consumed samples: 17402880 | consumed tokens: 35641098240 | elapsed time per iteration (s): 2.23 | learning rate: 1.227E-04 | global batch size: 512 | lm loss: 2.055587E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.097 | TFLOPs: 23.69 | + 0: [2022-12-02 09:18:20,620] [INFO] [logging.py:68:log_dist] [Rank 0] step=34000, skipped=0, lr=[0.0001226345196051246, 0.0001226345196051246, 0.0001226345196051246], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 34000/ 73814 | consumed samples: 17408000 | consumed tokens: 35651584000 | elapsed time per iteration (s): 2.30 | learning rate: 1.226E-04 | global batch size: 512 | lm loss: 2.023088E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.128 | TFLOPs: 22.87 | + 0: steps: 34000 loss: 1.9939 iter time (s): 2.263 samples/sec: 226.252 +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 34000 | lm loss value: 2.021611E+00 | lm loss PPL: 7.550479E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 34010/ 73814 | consumed samples: 17413120 | consumed tokens: 35662069760 | elapsed time per iteration (s): 2.32 | learning rate: 1.226E-04 | global batch size: 512 | lm loss: 2.047335E+00 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.922 | TFLOPs: 22.74 | +63: iteration 34020/ 73814 | consumed samples: 17418240 | consumed tokens: 35672555520 | elapsed time per iteration (s): 2.39 | learning rate: 1.226E-04 | global batch size: 512 | lm loss: 2.032996E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.871 | TFLOPs: 22.02 | +63: iteration 34030/ 73814 | consumed samples: 17423360 | consumed tokens: 35683041280 | elapsed time per iteration (s): 2.44 | learning rate: 1.225E-04 | global batch size: 512 | lm loss: 2.018421E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.557 | TFLOPs: 21.57 | +63: iteration 34040/ 73814 | consumed samples: 17428480 | consumed tokens: 35693527040 | elapsed time per iteration (s): 2.24 | learning rate: 1.225E-04 | global batch size: 512 | lm loss: 2.037178E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.839 | TFLOPs: 23.56 | +63: iteration 34050/ 73814 | consumed samples: 17433600 | consumed tokens: 35704012800 | elapsed time per iteration (s): 2.24 | learning rate: 1.224E-04 | global batch size: 512 | lm loss: 2.038939E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.263 | TFLOPs: 23.50 | +63: iteration 34060/ 73814 | consumed samples: 17438720 | consumed tokens: 35714498560 | elapsed time per iteration (s): 2.59 | learning rate: 1.224E-04 | global batch size: 512 | lm loss: 2.048897E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 197.999 | TFLOPs: 20.38 | +63: iteration 34070/ 73814 | consumed samples: 17443840 | consumed tokens: 35724984320 | elapsed time per iteration (s): 2.45 | learning rate: 1.224E-04 | global batch size: 512 | lm loss: 2.047845E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.657 | TFLOPs: 21.48 | +63: iteration 34080/ 73814 | consumed samples: 17448960 | consumed tokens: 35735470080 | elapsed time per iteration (s): 2.52 | learning rate: 1.223E-04 | global batch size: 512 | lm loss: 2.043340E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 203.528 | TFLOPs: 20.95 | +63: iteration 34090/ 73814 | consumed samples: 17454080 | consumed tokens: 35745955840 | elapsed time per iteration (s): 2.35 | learning rate: 1.223E-04 | global batch size: 512 | lm loss: 2.060762E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.532 | TFLOPs: 22.39 | +63: iteration 34100/ 73814 | consumed samples: 17459200 | consumed tokens: 35756441600 | elapsed time per iteration (s): 2.23 | learning rate: 1.223E-04 | global batch size: 512 | lm loss: 2.050496E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.567 | TFLOPs: 23.63 | +63: iteration 34110/ 73814 | consumed samples: 17464320 | consumed tokens: 35766927360 | elapsed time per iteration (s): 2.29 | learning rate: 1.222E-04 | global batch size: 512 | lm loss: 2.042519E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.205 | TFLOPs: 22.98 | +63: iteration 34120/ 73814 | consumed samples: 17469440 | consumed tokens: 35777413120 | elapsed time per iteration (s): 2.26 | learning rate: 1.222E-04 | global batch size: 512 | lm loss: 2.044778E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.252 | TFLOPs: 23.29 | +63: iteration 34130/ 73814 | consumed samples: 17474560 | consumed tokens: 35787898880 | elapsed time per iteration (s): 2.26 | learning rate: 1.221E-04 | global batch size: 512 | lm loss: 2.028586E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.299 | TFLOPs: 23.30 | +63: iteration 34140/ 73814 | consumed samples: 17479680 | consumed tokens: 35798384640 | elapsed time per iteration (s): 2.24 | learning rate: 1.221E-04 | global batch size: 512 | lm loss: 2.032835E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.851 | TFLOPs: 23.56 | +63: iteration 34150/ 73814 | consumed samples: 17484800 | consumed tokens: 35808870400 | elapsed time per iteration (s): 2.23 | learning rate: 1.221E-04 | global batch size: 512 | lm loss: 2.029333E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.661 | TFLOPs: 23.64 | +63: iteration 34160/ 73814 | consumed samples: 17489920 | consumed tokens: 35819356160 | elapsed time per iteration (s): 2.23 | learning rate: 1.220E-04 | global batch size: 512 | lm loss: 2.032141E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.747 | TFLOPs: 23.65 | +63: iteration 34170/ 73814 | consumed samples: 17495040 | consumed tokens: 35829841920 | elapsed time per iteration (s): 2.25 | learning rate: 1.220E-04 | global batch size: 512 | lm loss: 2.060109E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.480 | TFLOPs: 23.42 | +63: iteration 34180/ 73814 | consumed samples: 17500160 | consumed tokens: 35840327680 | elapsed time per iteration (s): 2.24 | learning rate: 1.219E-04 | global batch size: 512 | lm loss: 2.040648E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.381 | TFLOPs: 23.51 | +63: iteration 34190/ 73814 | consumed samples: 17505280 | consumed tokens: 35850813440 | elapsed time per iteration (s): 2.26 | learning rate: 1.219E-04 | global batch size: 512 | lm loss: 2.035231E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.812 | TFLOPs: 23.35 | +63: iteration 34200/ 73814 | consumed samples: 17510400 | consumed tokens: 35861299200 | elapsed time per iteration (s): 2.24 | learning rate: 1.219E-04 | global batch size: 512 | lm loss: 2.059285E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.478 | TFLOPs: 23.52 | +63: iteration 34210/ 73814 | consumed samples: 17515520 | consumed tokens: 35871784960 | elapsed time per iteration (s): 2.25 | learning rate: 1.218E-04 | global batch size: 512 | lm loss: 2.031074E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.794 | TFLOPs: 23.45 | +63: iteration 34220/ 73814 | consumed samples: 17520640 | consumed tokens: 35882270720 | elapsed time per iteration (s): 2.25 | learning rate: 1.218E-04 | global batch size: 512 | lm loss: 2.043375E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.971 | TFLOPs: 23.47 | +63: iteration 34230/ 73814 | consumed samples: 17525760 | consumed tokens: 35892756480 | elapsed time per iteration (s): 2.25 | learning rate: 1.218E-04 | global batch size: 512 | lm loss: 2.053063E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.296 | TFLOPs: 23.40 | +63: iteration 34240/ 73814 | consumed samples: 17530880 | consumed tokens: 35903242240 | elapsed time per iteration (s): 2.24 | learning rate: 1.217E-04 | global batch size: 512 | lm loss: 2.037251E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.971 | TFLOPs: 23.57 | +63: iteration 34250/ 73814 | consumed samples: 17536000 | consumed tokens: 35913728000 | elapsed time per iteration (s): 2.24 | learning rate: 1.217E-04 | global batch size: 512 | lm loss: 2.045013E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.807 | TFLOPs: 23.55 | +63: iteration 34260/ 73814 | consumed samples: 17541120 | consumed tokens: 35924213760 | elapsed time per iteration (s): 2.26 | learning rate: 1.216E-04 | global batch size: 512 | lm loss: 2.052479E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.214 | TFLOPs: 23.29 | +63: iteration 34270/ 73814 | consumed samples: 17546240 | consumed tokens: 35934699520 | elapsed time per iteration (s): 2.23 | learning rate: 1.216E-04 | global batch size: 512 | lm loss: 2.029315E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.657 | TFLOPs: 23.64 | +63: iteration 34280/ 73814 | consumed samples: 17551360 | consumed tokens: 35945185280 | elapsed time per iteration (s): 2.26 | learning rate: 1.216E-04 | global batch size: 512 | lm loss: 2.046946E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.338 | TFLOPs: 23.30 | +63: iteration 34290/ 73814 | consumed samples: 17556480 | consumed tokens: 35955671040 | elapsed time per iteration (s): 2.23 | learning rate: 1.215E-04 | global batch size: 512 | lm loss: 2.024603E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.806 | TFLOPs: 23.66 | +63: iteration 34300/ 73814 | consumed samples: 17561600 | consumed tokens: 35966156800 | elapsed time per iteration (s): 2.24 | learning rate: 1.215E-04 | global batch size: 512 | lm loss: 2.070257E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.839 | TFLOPs: 23.56 | +63: iteration 34310/ 73814 | consumed samples: 17566720 | consumed tokens: 35976642560 | elapsed time per iteration (s): 2.24 | learning rate: 1.214E-04 | global batch size: 512 | lm loss: 2.049710E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.524 | TFLOPs: 23.53 | +63: iteration 34320/ 73814 | consumed samples: 17571840 | consumed tokens: 35987128320 | elapsed time per iteration (s): 2.23 | learning rate: 1.214E-04 | global batch size: 512 | lm loss: 2.024590E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.879 | TFLOPs: 23.66 | +63: iteration 34330/ 73814 | consumed samples: 17576960 | consumed tokens: 35997614080 | elapsed time per iteration (s): 2.23 | learning rate: 1.214E-04 | global batch size: 512 | lm loss: 2.071472E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.970 | TFLOPs: 23.67 | +63: iteration 34340/ 73814 | consumed samples: 17582080 | consumed tokens: 36008099840 | elapsed time per iteration (s): 2.26 | learning rate: 1.213E-04 | global batch size: 512 | lm loss: 2.034235E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.135 | TFLOPs: 23.28 | +63: iteration 34350/ 73814 | consumed samples: 17587200 | consumed tokens: 36018585600 | elapsed time per iteration (s): 2.31 | learning rate: 1.213E-04 | global batch size: 512 | lm loss: 2.044242E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.314 | TFLOPs: 22.78 | +63: iteration 34360/ 73814 | consumed samples: 17592320 | consumed tokens: 36029071360 | elapsed time per iteration (s): 2.22 | learning rate: 1.213E-04 | global batch size: 512 | lm loss: 2.034681E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.337 | TFLOPs: 23.71 | +63: iteration 34370/ 73814 | consumed samples: 17597440 | consumed tokens: 36039557120 | elapsed time per iteration (s): 2.23 | learning rate: 1.212E-04 | global batch size: 512 | lm loss: 2.039783E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.518 | TFLOPs: 23.63 | +63: iteration 34380/ 73814 | consumed samples: 17602560 | consumed tokens: 36050042880 | elapsed time per iteration (s): 2.24 | learning rate: 1.212E-04 | global batch size: 512 | lm loss: 2.056887E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.751 | TFLOPs: 23.55 | +63: iteration 34390/ 73814 | consumed samples: 17607680 | consumed tokens: 36060528640 | elapsed time per iteration (s): 2.23 | learning rate: 1.211E-04 | global batch size: 512 | lm loss: 2.040491E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.848 | TFLOPs: 23.66 | +63: iteration 34400/ 73814 | consumed samples: 17612800 | consumed tokens: 36071014400 | elapsed time per iteration (s): 2.24 | learning rate: 1.211E-04 | global batch size: 512 | lm loss: 2.035044E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.073 | TFLOPs: 23.48 | +63: iteration 34410/ 73814 | consumed samples: 17617920 | consumed tokens: 36081500160 | elapsed time per iteration (s): 2.44 | learning rate: 1.211E-04 | global batch size: 512 | lm loss: 2.036069E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.079 | TFLOPs: 21.63 | +63: iteration 34420/ 73814 | consumed samples: 17623040 | consumed tokens: 36091985920 | elapsed time per iteration (s): 2.26 | learning rate: 1.210E-04 | global batch size: 512 | lm loss: 2.044672E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.430 | TFLOPs: 23.31 | +63: iteration 34430/ 73814 | consumed samples: 17628160 | consumed tokens: 36102471680 | elapsed time per iteration (s): 2.26 | learning rate: 1.210E-04 | global batch size: 512 | lm loss: 2.046190E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.689 | TFLOPs: 23.34 | +63: iteration 34440/ 73814 | consumed samples: 17633280 | consumed tokens: 36112957440 | elapsed time per iteration (s): 2.24 | learning rate: 1.209E-04 | global batch size: 512 | lm loss: 2.015198E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.044 | TFLOPs: 23.58 | +63: iteration 34450/ 73814 | consumed samples: 17638400 | consumed tokens: 36123443200 | elapsed time per iteration (s): 2.32 | learning rate: 1.209E-04 | global batch size: 512 | lm loss: 2.053060E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.833 | TFLOPs: 22.73 | +63: iteration 34460/ 73814 | consumed samples: 17643520 | consumed tokens: 36133928960 | elapsed time per iteration (s): 2.23 | learning rate: 1.209E-04 | global batch size: 512 | lm loss: 2.027059E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.979 | TFLOPs: 23.68 | +63: iteration 34470/ 73814 | consumed samples: 17648640 | consumed tokens: 36144414720 | elapsed time per iteration (s): 2.27 | learning rate: 1.208E-04 | global batch size: 512 | lm loss: 2.017456E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.344 | TFLOPs: 23.20 | +63: iteration 34480/ 73814 | consumed samples: 17653760 | consumed tokens: 36154900480 | elapsed time per iteration (s): 2.26 | learning rate: 1.208E-04 | global batch size: 512 | lm loss: 2.044899E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.727 | TFLOPs: 23.34 | +63: iteration 34490/ 73814 | consumed samples: 17658880 | consumed tokens: 36165386240 | elapsed time per iteration (s): 2.24 | learning rate: 1.208E-04 | global batch size: 512 | lm loss: 2.019361E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.069 | TFLOPs: 23.48 | +63: iteration 34500/ 73814 | consumed samples: 17664000 | consumed tokens: 36175872000 | elapsed time per iteration (s): 2.24 | learning rate: 1.207E-04 | global batch size: 512 | lm loss: 2.014425E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.875 | TFLOPs: 23.56 | +63: iteration 34510/ 73814 | consumed samples: 17669120 | consumed tokens: 36186357760 | elapsed time per iteration (s): 2.22 | learning rate: 1.207E-04 | global batch size: 512 | lm loss: 2.022927E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.171 | TFLOPs: 23.70 | +63: iteration 34520/ 73814 | consumed samples: 17674240 | consumed tokens: 36196843520 | elapsed time per iteration (s): 2.24 | learning rate: 1.206E-04 | global batch size: 512 | lm loss: 2.036407E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.869 | TFLOPs: 23.56 | +63: iteration 34530/ 73814 | consumed samples: 17679360 | consumed tokens: 36207329280 | elapsed time per iteration (s): 2.24 | learning rate: 1.206E-04 | global batch size: 512 | lm loss: 2.028495E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.631 | TFLOPs: 23.54 | +63: iteration 34540/ 73814 | consumed samples: 17684480 | consumed tokens: 36217815040 | elapsed time per iteration (s): 2.25 | learning rate: 1.206E-04 | global batch size: 512 | lm loss: 2.013992E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.965 | TFLOPs: 23.47 | +63: iteration 34550/ 73814 | consumed samples: 17689600 | consumed tokens: 36228300800 | elapsed time per iteration (s): 2.23 | learning rate: 1.205E-04 | global batch size: 512 | lm loss: 2.043060E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.720 | TFLOPs: 23.65 | +63: iteration 34560/ 73814 | consumed samples: 17694720 | consumed tokens: 36238786560 | elapsed time per iteration (s): 2.23 | learning rate: 1.205E-04 | global batch size: 512 | lm loss: 2.040206E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.429 | TFLOPs: 23.62 | +63: iteration 34570/ 73814 | consumed samples: 17699840 | consumed tokens: 36249272320 | elapsed time per iteration (s): 2.22 | learning rate: 1.204E-04 | global batch size: 512 | lm loss: 2.036624E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.220 | TFLOPs: 23.70 | +63: iteration 34580/ 73814 | consumed samples: 17704960 | consumed tokens: 36259758080 | elapsed time per iteration (s): 2.23 | learning rate: 1.204E-04 | global batch size: 512 | lm loss: 2.034756E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.857 | TFLOPs: 23.66 | +63: iteration 34590/ 73814 | consumed samples: 17710080 | consumed tokens: 36270243840 | elapsed time per iteration (s): 2.24 | learning rate: 1.204E-04 | global batch size: 512 | lm loss: 2.043449E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.441 | TFLOPs: 23.52 | +63: iteration 34600/ 73814 | consumed samples: 17715200 | consumed tokens: 36280729600 | elapsed time per iteration (s): 2.23 | learning rate: 1.203E-04 | global batch size: 512 | lm loss: 2.036459E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.411 | TFLOPs: 23.62 | +63: iteration 34610/ 73814 | consumed samples: 17720320 | consumed tokens: 36291215360 | elapsed time per iteration (s): 2.24 | learning rate: 1.203E-04 | global batch size: 512 | lm loss: 2.024516E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.986 | TFLOPs: 23.57 | +63: iteration 34620/ 73814 | consumed samples: 17725440 | consumed tokens: 36301701120 | elapsed time per iteration (s): 2.30 | learning rate: 1.203E-04 | global batch size: 512 | lm loss: 2.044102E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.711 | TFLOPs: 22.93 | +63: iteration 34630/ 73814 | consumed samples: 17730560 | consumed tokens: 36312186880 | elapsed time per iteration (s): 2.27 | learning rate: 1.202E-04 | global batch size: 512 | lm loss: 2.038307E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.866 | TFLOPs: 23.25 | +63: iteration 34640/ 73814 | consumed samples: 17735680 | consumed tokens: 36322672640 | elapsed time per iteration (s): 2.25 | learning rate: 1.202E-04 | global batch size: 512 | lm loss: 2.057496E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.146 | TFLOPs: 23.38 | +63: iteration 34650/ 73814 | consumed samples: 17740800 | consumed tokens: 36333158400 | elapsed time per iteration (s): 2.23 | learning rate: 1.201E-04 | global batch size: 512 | lm loss: 2.054949E+00 | grad norm: 0.397 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.602 | TFLOPs: 23.64 | +63: iteration 34660/ 73814 | consumed samples: 17745920 | consumed tokens: 36343644160 | elapsed time per iteration (s): 2.25 | learning rate: 1.201E-04 | global batch size: 512 | lm loss: 2.829857E+00 | grad norm: 3.949 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.484 | TFLOPs: 23.42 | +63: iteration 34670/ 73814 | consumed samples: 17751040 | consumed tokens: 36354129920 | elapsed time per iteration (s): 2.51 | learning rate: 1.201E-04 | global batch size: 512 | lm loss: 2.215329E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 204.229 | TFLOPs: 21.02 | +63: iteration 34680/ 73814 | consumed samples: 17756160 | consumed tokens: 36364615680 | elapsed time per iteration (s): 2.23 | learning rate: 1.200E-04 | global batch size: 512 | lm loss: 2.080200E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.163 | TFLOPs: 23.59 | +63: iteration 34690/ 73814 | consumed samples: 17761280 | consumed tokens: 36375101440 | elapsed time per iteration (s): 2.24 | learning rate: 1.200E-04 | global batch size: 512 | lm loss: 2.071945E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.249 | TFLOPs: 23.50 | +63: iteration 34700/ 73814 | consumed samples: 17766400 | consumed tokens: 36385587200 | elapsed time per iteration (s): 2.22 | learning rate: 1.199E-04 | global batch size: 512 | lm loss: 2.055036E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.508 | TFLOPs: 23.73 | +63: iteration 34710/ 73814 | consumed samples: 17771520 | consumed tokens: 36396072960 | elapsed time per iteration (s): 2.23 | learning rate: 1.199E-04 | global batch size: 512 | lm loss: 2.065510E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.644 | TFLOPs: 23.64 | +63: iteration 34720/ 73814 | consumed samples: 17776640 | consumed tokens: 36406558720 | elapsed time per iteration (s): 2.25 | learning rate: 1.199E-04 | global batch size: 512 | lm loss: 2.046408E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.746 | TFLOPs: 23.45 | +63: iteration 34730/ 73814 | consumed samples: 17781760 | consumed tokens: 36417044480 | elapsed time per iteration (s): 2.27 | learning rate: 1.198E-04 | global batch size: 512 | lm loss: 2.046820E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.882 | TFLOPs: 23.25 | +63: iteration 34740/ 73814 | consumed samples: 17786880 | consumed tokens: 36427530240 | elapsed time per iteration (s): 2.26 | learning rate: 1.198E-04 | global batch size: 512 | lm loss: 2.069579E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.321 | TFLOPs: 23.30 | +63: iteration 34750/ 73814 | consumed samples: 17792000 | consumed tokens: 36438016000 | elapsed time per iteration (s): 2.24 | learning rate: 1.198E-04 | global batch size: 512 | lm loss: 2.058438E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.707 | TFLOPs: 23.54 | +63: iteration 34760/ 73814 | consumed samples: 17797120 | consumed tokens: 36448501760 | elapsed time per iteration (s): 2.26 | learning rate: 1.197E-04 | global batch size: 512 | lm loss: 2.066296E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.036 | TFLOPs: 23.37 | +63: iteration 34770/ 73814 | consumed samples: 17802240 | consumed tokens: 36458987520 | elapsed time per iteration (s): 2.26 | learning rate: 1.197E-04 | global batch size: 512 | lm loss: 2.029027E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.138 | TFLOPs: 23.28 | +63: iteration 34780/ 73814 | consumed samples: 17807360 | consumed tokens: 36469473280 | elapsed time per iteration (s): 2.24 | learning rate: 1.196E-04 | global batch size: 512 | lm loss: 2.037380E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.839 | TFLOPs: 23.56 | +63: iteration 34790/ 73814 | consumed samples: 17812480 | consumed tokens: 36479959040 | elapsed time per iteration (s): 2.23 | learning rate: 1.196E-04 | global batch size: 512 | lm loss: 2.053875E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.875 | TFLOPs: 23.66 | +63: iteration 34800/ 73814 | consumed samples: 17817600 | consumed tokens: 36490444800 | elapsed time per iteration (s): 2.23 | learning rate: 1.196E-04 | global batch size: 512 | lm loss: 2.044474E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.856 | TFLOPs: 23.66 | +63: iteration 34810/ 73814 | consumed samples: 17822720 | consumed tokens: 36500930560 | elapsed time per iteration (s): 2.23 | learning rate: 1.195E-04 | global batch size: 512 | lm loss: 2.050163E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.104 | TFLOPs: 23.69 | +63: iteration 34820/ 73814 | consumed samples: 17827840 | consumed tokens: 36511416320 | elapsed time per iteration (s): 2.33 | learning rate: 1.195E-04 | global batch size: 512 | lm loss: 2.045284E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.470 | TFLOPs: 22.59 | +63: iteration 34830/ 73814 | consumed samples: 17832960 | consumed tokens: 36521902080 | elapsed time per iteration (s): 2.24 | learning rate: 1.194E-04 | global batch size: 512 | lm loss: 2.030813E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.170 | TFLOPs: 23.49 | +63: iteration 34840/ 73814 | consumed samples: 17838080 | consumed tokens: 36532387840 | elapsed time per iteration (s): 2.26 | learning rate: 1.194E-04 | global batch size: 512 | lm loss: 2.053895E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.238 | TFLOPs: 23.29 | +63: iteration 34850/ 73814 | consumed samples: 17843200 | consumed tokens: 36542873600 | elapsed time per iteration (s): 2.25 | learning rate: 1.194E-04 | global batch size: 512 | lm loss: 2.056881E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.258 | TFLOPs: 23.40 | +63: iteration 34860/ 73814 | consumed samples: 17848320 | consumed tokens: 36553359360 | elapsed time per iteration (s): 2.30 | learning rate: 1.193E-04 | global batch size: 512 | lm loss: 2.041315E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.482 | TFLOPs: 22.90 | +63: iteration 34870/ 73814 | consumed samples: 17853440 | consumed tokens: 36563845120 | elapsed time per iteration (s): 2.24 | learning rate: 1.193E-04 | global batch size: 512 | lm loss: 2.052899E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.194 | TFLOPs: 23.49 | +63: iteration 34880/ 73814 | consumed samples: 17858560 | consumed tokens: 36574330880 | elapsed time per iteration (s): 2.38 | learning rate: 1.193E-04 | global batch size: 512 | lm loss: 2.067680E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.160 | TFLOPs: 22.15 | +63: iteration 34890/ 73814 | consumed samples: 17863680 | consumed tokens: 36584816640 | elapsed time per iteration (s): 2.26 | learning rate: 1.192E-04 | global batch size: 512 | lm loss: 2.043738E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.995 | TFLOPs: 23.37 | +63: iteration 34900/ 73814 | consumed samples: 17868800 | consumed tokens: 36595302400 | elapsed time per iteration (s): 2.24 | learning rate: 1.192E-04 | global batch size: 512 | lm loss: 2.054518E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.777 | TFLOPs: 23.55 | +63: iteration 34910/ 73814 | consumed samples: 17873920 | consumed tokens: 36605788160 | elapsed time per iteration (s): 2.33 | learning rate: 1.191E-04 | global batch size: 512 | lm loss: 2.033784E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.505 | TFLOPs: 22.60 | +63: iteration 34920/ 73814 | consumed samples: 17879040 | consumed tokens: 36616273920 | elapsed time per iteration (s): 2.25 | learning rate: 1.191E-04 | global batch size: 512 | lm loss: 2.013994E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.776 | TFLOPs: 23.45 | +63: iteration 34930/ 73814 | consumed samples: 17884160 | consumed tokens: 36626759680 | elapsed time per iteration (s): 2.24 | learning rate: 1.191E-04 | global batch size: 512 | lm loss: 2.040882E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.163 | TFLOPs: 23.49 | +63: iteration 34940/ 73814 | consumed samples: 17889280 | consumed tokens: 36637245440 | elapsed time per iteration (s): 2.24 | learning rate: 1.190E-04 | global batch size: 512 | lm loss: 2.041783E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.586 | TFLOPs: 23.53 | +63: iteration 34950/ 73814 | consumed samples: 17894400 | consumed tokens: 36647731200 | elapsed time per iteration (s): 2.23 | learning rate: 1.190E-04 | global batch size: 512 | lm loss: 2.039835E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.200 | TFLOPs: 23.60 | +63: iteration 34960/ 73814 | consumed samples: 17899520 | consumed tokens: 36658216960 | elapsed time per iteration (s): 2.24 | learning rate: 1.189E-04 | global batch size: 512 | lm loss: 2.033005E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.664 | TFLOPs: 23.54 | +63: iteration 34970/ 73814 | consumed samples: 17904640 | consumed tokens: 36668702720 | elapsed time per iteration (s): 2.23 | learning rate: 1.189E-04 | global batch size: 512 | lm loss: 2.046382E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.442 | TFLOPs: 23.62 | +63: iteration 34980/ 73814 | consumed samples: 17909760 | consumed tokens: 36679188480 | elapsed time per iteration (s): 2.30 | learning rate: 1.189E-04 | global batch size: 512 | lm loss: 2.023248E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.695 | TFLOPs: 22.93 | +63: iteration 34990/ 73814 | consumed samples: 17914880 | consumed tokens: 36689674240 | elapsed time per iteration (s): 2.25 | learning rate: 1.188E-04 | global batch size: 512 | lm loss: 2.053457E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.813 | TFLOPs: 23.45 | +63: iteration 35000/ 73814 | consumed samples: 17920000 | consumed tokens: 36700160000 | elapsed time per iteration (s): 2.23 | learning rate: 1.188E-04 | global batch size: 512 | lm loss: 2.034695E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.856 | TFLOPs: 23.66 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 35000 | lm loss value: 2.010796E+00 | lm loss PPL: 7.469259E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 35010/ 73814 | consumed samples: 17925120 | consumed tokens: 36710645760 | elapsed time per iteration (s): 2.29 | learning rate: 1.188E-04 | global batch size: 512 | lm loss: 2.027762E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.300 | TFLOPs: 22.99 | +63: iteration 35020/ 73814 | consumed samples: 17930240 | consumed tokens: 36721131520 | elapsed time per iteration (s): 2.23 | learning rate: 1.187E-04 | global batch size: 512 | lm loss: 2.020426E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.813 | TFLOPs: 23.66 | +63: iteration 35030/ 73814 | consumed samples: 17935360 | consumed tokens: 36731617280 | elapsed time per iteration (s): 2.25 | learning rate: 1.187E-04 | global batch size: 512 | lm loss: 2.033645E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.278 | TFLOPs: 23.40 | +63: iteration 35040/ 73814 | consumed samples: 17940480 | consumed tokens: 36742103040 | elapsed time per iteration (s): 2.24 | learning rate: 1.186E-04 | global batch size: 512 | lm loss: 2.081082E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.075 | TFLOPs: 23.48 | +63: iteration 35050/ 73814 | consumed samples: 17945600 | consumed tokens: 36752588800 | elapsed time per iteration (s): 2.23 | learning rate: 1.186E-04 | global batch size: 512 | lm loss: 2.034458E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.203 | TFLOPs: 23.60 | +63: iteration 35060/ 73814 | consumed samples: 17950720 | consumed tokens: 36763074560 | elapsed time per iteration (s): 2.24 | learning rate: 1.186E-04 | global batch size: 512 | lm loss: 2.063474E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.322 | TFLOPs: 23.50 | +63: iteration 35070/ 73814 | consumed samples: 17955840 | consumed tokens: 36773560320 | elapsed time per iteration (s): 2.25 | learning rate: 1.185E-04 | global batch size: 512 | lm loss: 2.016944E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.024 | TFLOPs: 23.47 | +63: iteration 35080/ 73814 | consumed samples: 17960960 | consumed tokens: 36784046080 | elapsed time per iteration (s): 2.26 | learning rate: 1.185E-04 | global batch size: 512 | lm loss: 2.016275E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.167 | TFLOPs: 23.28 | +63: iteration 35090/ 73814 | consumed samples: 17966080 | consumed tokens: 36794531840 | elapsed time per iteration (s): 2.25 | learning rate: 1.184E-04 | global batch size: 512 | lm loss: 2.027447E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.137 | TFLOPs: 23.38 | +63: iteration 35100/ 73814 | consumed samples: 17971200 | consumed tokens: 36805017600 | elapsed time per iteration (s): 2.48 | learning rate: 1.184E-04 | global batch size: 512 | lm loss: 2.042529E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.070 | TFLOPs: 21.21 | +63: iteration 35110/ 73814 | consumed samples: 17976320 | consumed tokens: 36815503360 | elapsed time per iteration (s): 2.23 | learning rate: 1.184E-04 | global batch size: 512 | lm loss: 2.043262E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.985 | TFLOPs: 23.68 | +63: iteration 35120/ 73814 | consumed samples: 17981440 | consumed tokens: 36825989120 | elapsed time per iteration (s): 2.24 | learning rate: 1.183E-04 | global batch size: 512 | lm loss: 2.032276E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.784 | TFLOPs: 23.55 | +63: iteration 35130/ 73814 | consumed samples: 17986560 | consumed tokens: 36836474880 | elapsed time per iteration (s): 2.25 | learning rate: 1.183E-04 | global batch size: 512 | lm loss: 2.040804E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.185 | TFLOPs: 23.39 | +63: iteration 35140/ 73814 | consumed samples: 17991680 | consumed tokens: 36846960640 | elapsed time per iteration (s): 2.27 | learning rate: 1.183E-04 | global batch size: 512 | lm loss: 2.038745E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.967 | TFLOPs: 23.26 | +63: iteration 35150/ 73814 | consumed samples: 17996800 | consumed tokens: 36857446400 | elapsed time per iteration (s): 2.23 | learning rate: 1.182E-04 | global batch size: 512 | lm loss: 2.040299E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.838 | TFLOPs: 23.66 | +63: iteration 35160/ 73814 | consumed samples: 18001920 | consumed tokens: 36867932160 | elapsed time per iteration (s): 2.25 | learning rate: 1.182E-04 | global batch size: 512 | lm loss: 2.041322E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.129 | TFLOPs: 23.38 | +63: iteration 35170/ 73814 | consumed samples: 18007040 | consumed tokens: 36878417920 | elapsed time per iteration (s): 2.24 | learning rate: 1.181E-04 | global batch size: 512 | lm loss: 2.039612E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.753 | TFLOPs: 23.55 | +63: iteration 35180/ 73814 | consumed samples: 18012160 | consumed tokens: 36888903680 | elapsed time per iteration (s): 2.50 | learning rate: 1.181E-04 | global batch size: 512 | lm loss: 2.059260E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 204.535 | TFLOPs: 21.06 | +63: iteration 35190/ 73814 | consumed samples: 18017280 | consumed tokens: 36899389440 | elapsed time per iteration (s): 2.24 | learning rate: 1.181E-04 | global batch size: 512 | lm loss: 2.048375E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.453 | TFLOPs: 23.52 | +63: iteration 35200/ 73814 | consumed samples: 18022400 | consumed tokens: 36909875200 | elapsed time per iteration (s): 2.33 | learning rate: 1.180E-04 | global batch size: 512 | lm loss: 2.026473E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.070 | TFLOPs: 22.66 | +63: iteration 35210/ 73814 | consumed samples: 18027520 | consumed tokens: 36920360960 | elapsed time per iteration (s): 2.35 | learning rate: 1.180E-04 | global batch size: 512 | lm loss: 2.022053E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.997 | TFLOPs: 22.44 | +63: iteration 35220/ 73814 | consumed samples: 18032640 | consumed tokens: 36930846720 | elapsed time per iteration (s): 2.23 | learning rate: 1.179E-04 | global batch size: 512 | lm loss: 2.043227E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.755 | TFLOPs: 23.65 | +63: iteration 35230/ 73814 | consumed samples: 18037760 | consumed tokens: 36941332480 | elapsed time per iteration (s): 2.26 | learning rate: 1.179E-04 | global batch size: 512 | lm loss: 2.027750E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.986 | TFLOPs: 23.37 | +63: iteration 35240/ 73814 | consumed samples: 18042880 | consumed tokens: 36951818240 | elapsed time per iteration (s): 2.26 | learning rate: 1.179E-04 | global batch size: 512 | lm loss: 2.034421E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.497 | TFLOPs: 23.32 | +63: iteration 35250/ 73814 | consumed samples: 18048000 | consumed tokens: 36962304000 | elapsed time per iteration (s): 2.25 | learning rate: 1.178E-04 | global batch size: 512 | lm loss: 2.036694E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.663 | TFLOPs: 23.44 | +63: iteration 35260/ 73814 | consumed samples: 18053120 | consumed tokens: 36972789760 | elapsed time per iteration (s): 2.25 | learning rate: 1.178E-04 | global batch size: 512 | lm loss: 2.035729E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.481 | TFLOPs: 23.42 | +63: iteration 35270/ 73814 | consumed samples: 18058240 | consumed tokens: 36983275520 | elapsed time per iteration (s): 2.24 | learning rate: 1.178E-04 | global batch size: 512 | lm loss: 2.034175E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.148 | TFLOPs: 23.49 | +63: iteration 35280/ 73814 | consumed samples: 18063360 | consumed tokens: 36993761280 | elapsed time per iteration (s): 2.24 | learning rate: 1.177E-04 | global batch size: 512 | lm loss: 2.053025E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.841 | TFLOPs: 23.56 | +63: iteration 35290/ 73814 | consumed samples: 18068480 | consumed tokens: 37004247040 | elapsed time per iteration (s): 2.25 | learning rate: 1.177E-04 | global batch size: 512 | lm loss: 2.040025E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.880 | TFLOPs: 23.46 | +63: iteration 35300/ 73814 | consumed samples: 18073600 | consumed tokens: 37014732800 | elapsed time per iteration (s): 2.25 | learning rate: 1.176E-04 | global batch size: 512 | lm loss: 2.058095E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.147 | TFLOPs: 23.38 | +63: iteration 35310/ 73814 | consumed samples: 18078720 | consumed tokens: 37025218560 | elapsed time per iteration (s): 2.26 | learning rate: 1.176E-04 | global batch size: 512 | lm loss: 2.006970E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.049 | TFLOPs: 23.27 | +63: iteration 35320/ 73814 | consumed samples: 18083840 | consumed tokens: 37035704320 | elapsed time per iteration (s): 2.32 | learning rate: 1.176E-04 | global batch size: 512 | lm loss: 2.031362E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.053 | TFLOPs: 22.76 | +63: iteration 35330/ 73814 | consumed samples: 18088960 | consumed tokens: 37046190080 | elapsed time per iteration (s): 2.23 | learning rate: 1.175E-04 | global batch size: 512 | lm loss: 2.036029E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.226 | TFLOPs: 23.60 | +63: iteration 35340/ 73814 | consumed samples: 18094080 | consumed tokens: 37056675840 | elapsed time per iteration (s): 2.24 | learning rate: 1.175E-04 | global batch size: 512 | lm loss: 2.018560E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.876 | TFLOPs: 23.56 | +63: iteration 35350/ 73814 | consumed samples: 18099200 | consumed tokens: 37067161600 | elapsed time per iteration (s): 2.23 | learning rate: 1.174E-04 | global batch size: 512 | lm loss: 2.025149E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.389 | TFLOPs: 23.61 | +63: iteration 35360/ 73814 | consumed samples: 18104320 | consumed tokens: 37077647360 | elapsed time per iteration (s): 2.25 | learning rate: 1.174E-04 | global batch size: 512 | lm loss: 2.033850E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.801 | TFLOPs: 23.45 | +63: iteration 35370/ 73814 | consumed samples: 18109440 | consumed tokens: 37088133120 | elapsed time per iteration (s): 2.23 | learning rate: 1.174E-04 | global batch size: 512 | lm loss: 2.032241E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.045 | TFLOPs: 23.68 | +63: iteration 35380/ 73814 | consumed samples: 18114560 | consumed tokens: 37098618880 | elapsed time per iteration (s): 2.23 | learning rate: 1.173E-04 | global batch size: 512 | lm loss: 2.061475E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.385 | TFLOPs: 23.61 | +63: iteration 35390/ 73814 | consumed samples: 18119680 | consumed tokens: 37109104640 | elapsed time per iteration (s): 2.25 | learning rate: 1.173E-04 | global batch size: 512 | lm loss: 2.039803E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.745 | TFLOPs: 23.45 | +63: iteration 35400/ 73814 | consumed samples: 18124800 | consumed tokens: 37119590400 | elapsed time per iteration (s): 2.32 | learning rate: 1.173E-04 | global batch size: 512 | lm loss: 2.040221E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.390 | TFLOPs: 22.69 | +63: iteration 35410/ 73814 | consumed samples: 18129920 | consumed tokens: 37130076160 | elapsed time per iteration (s): 2.23 | learning rate: 1.172E-04 | global batch size: 512 | lm loss: 2.018851E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.613 | TFLOPs: 23.64 | +63: iteration 35420/ 73814 | consumed samples: 18135040 | consumed tokens: 37140561920 | elapsed time per iteration (s): 2.27 | learning rate: 1.172E-04 | global batch size: 512 | lm loss: 2.045136E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.208 | TFLOPs: 23.18 | +63: iteration 35430/ 73814 | consumed samples: 18140160 | consumed tokens: 37151047680 | elapsed time per iteration (s): 2.25 | learning rate: 1.171E-04 | global batch size: 512 | lm loss: 2.034772E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.456 | TFLOPs: 23.42 | +63: iteration 35440/ 73814 | consumed samples: 18145280 | consumed tokens: 37161533440 | elapsed time per iteration (s): 2.23 | learning rate: 1.171E-04 | global batch size: 512 | lm loss: 2.045493E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.325 | TFLOPs: 23.61 | +63: iteration 35450/ 73814 | consumed samples: 18150400 | consumed tokens: 37172019200 | elapsed time per iteration (s): 2.56 | learning rate: 1.171E-04 | global batch size: 512 | lm loss: 2.012455E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.822 | TFLOPs: 20.57 | +63: iteration 35460/ 73814 | consumed samples: 18155520 | consumed tokens: 37182504960 | elapsed time per iteration (s): 2.41 | learning rate: 1.170E-04 | global batch size: 512 | lm loss: 2.042160E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.758 | TFLOPs: 21.90 | +63: iteration 35470/ 73814 | consumed samples: 18160640 | consumed tokens: 37192990720 | elapsed time per iteration (s): 2.30 | learning rate: 1.170E-04 | global batch size: 512 | lm loss: 2.024117E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.762 | TFLOPs: 22.93 | +63: iteration 35480/ 73814 | consumed samples: 18165760 | consumed tokens: 37203476480 | elapsed time per iteration (s): 2.35 | learning rate: 1.169E-04 | global batch size: 512 | lm loss: 2.038367E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.558 | TFLOPs: 22.40 | +63: iteration 35490/ 73814 | consumed samples: 18170880 | consumed tokens: 37213962240 | elapsed time per iteration (s): 2.23 | learning rate: 1.169E-04 | global batch size: 512 | lm loss: 2.030970E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.222 | TFLOPs: 23.60 | +63: iteration 35500/ 73814 | consumed samples: 18176000 | consumed tokens: 37224448000 | elapsed time per iteration (s): 2.22 | learning rate: 1.169E-04 | global batch size: 512 | lm loss: 2.024412E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.341 | TFLOPs: 23.71 | +63: iteration 35510/ 73814 | consumed samples: 18181120 | consumed tokens: 37234933760 | elapsed time per iteration (s): 2.55 | learning rate: 1.168E-04 | global batch size: 512 | lm loss: 2.046230E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.518 | TFLOPs: 20.64 | +63: iteration 35520/ 73814 | consumed samples: 18186240 | consumed tokens: 37245419520 | elapsed time per iteration (s): 2.23 | learning rate: 1.168E-04 | global batch size: 512 | lm loss: 2.022388E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.393 | TFLOPs: 23.61 | +63: iteration 35530/ 73814 | consumed samples: 18191360 | consumed tokens: 37255905280 | elapsed time per iteration (s): 2.22 | learning rate: 1.168E-04 | global batch size: 512 | lm loss: 2.023384E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.261 | TFLOPs: 23.70 | +63: iteration 35540/ 73814 | consumed samples: 18196480 | consumed tokens: 37266391040 | elapsed time per iteration (s): 2.25 | learning rate: 1.167E-04 | global batch size: 512 | lm loss: 2.032611E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.670 | TFLOPs: 23.44 | +63: iteration 35550/ 73814 | consumed samples: 18201600 | consumed tokens: 37276876800 | elapsed time per iteration (s): 2.33 | learning rate: 1.167E-04 | global batch size: 512 | lm loss: 2.020182E+00 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.777 | TFLOPs: 22.62 | +63: iteration 35560/ 73814 | consumed samples: 18206720 | consumed tokens: 37287362560 | elapsed time per iteration (s): 2.26 | learning rate: 1.166E-04 | global batch size: 512 | lm loss: 2.012963E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.609 | TFLOPs: 23.33 | +63: iteration 35570/ 73814 | consumed samples: 18211840 | consumed tokens: 37297848320 | elapsed time per iteration (s): 2.24 | learning rate: 1.166E-04 | global batch size: 512 | lm loss: 2.031936E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.434 | TFLOPs: 23.52 | +63: iteration 35580/ 73814 | consumed samples: 18216960 | consumed tokens: 37308334080 | elapsed time per iteration (s): 2.23 | learning rate: 1.166E-04 | global batch size: 512 | lm loss: 2.041417E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.717 | TFLOPs: 23.65 | +63: iteration 35590/ 73814 | consumed samples: 18222080 | consumed tokens: 37318819840 | elapsed time per iteration (s): 2.27 | learning rate: 1.165E-04 | global batch size: 512 | lm loss: 2.029642E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.917 | TFLOPs: 23.26 | +63: iteration 35600/ 73814 | consumed samples: 18227200 | consumed tokens: 37329305600 | elapsed time per iteration (s): 2.55 | learning rate: 1.165E-04 | global batch size: 512 | lm loss: 2.031803E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.404 | TFLOPs: 20.63 | +63: iteration 35610/ 73814 | consumed samples: 18232320 | consumed tokens: 37339791360 | elapsed time per iteration (s): 2.24 | learning rate: 1.164E-04 | global batch size: 512 | lm loss: 2.047256E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.130 | TFLOPs: 23.48 | +63: iteration 35620/ 73814 | consumed samples: 18237440 | consumed tokens: 37350277120 | elapsed time per iteration (s): 2.25 | learning rate: 1.164E-04 | global batch size: 512 | lm loss: 2.064578E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.197 | TFLOPs: 23.39 | +63: iteration 35630/ 73814 | consumed samples: 18242560 | consumed tokens: 37360762880 | elapsed time per iteration (s): 2.25 | learning rate: 1.164E-04 | global batch size: 512 | lm loss: 2.025708E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.300 | TFLOPs: 23.40 | +63: iteration 35640/ 73814 | consumed samples: 18247680 | consumed tokens: 37371248640 | elapsed time per iteration (s): 2.23 | learning rate: 1.163E-04 | global batch size: 512 | lm loss: 2.037094E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.155 | TFLOPs: 23.59 | +63: iteration 35650/ 73814 | consumed samples: 18252800 | consumed tokens: 37381734400 | elapsed time per iteration (s): 2.27 | learning rate: 1.163E-04 | global batch size: 512 | lm loss: 2.040329E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.816 | TFLOPs: 23.25 | +63: iteration 35660/ 73814 | consumed samples: 18257920 | consumed tokens: 37392220160 | elapsed time per iteration (s): 2.25 | learning rate: 1.162E-04 | global batch size: 512 | lm loss: 2.027333E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.123 | TFLOPs: 23.38 | +63: iteration 35670/ 73814 | consumed samples: 18263040 | consumed tokens: 37402705920 | elapsed time per iteration (s): 2.23 | learning rate: 1.162E-04 | global batch size: 512 | lm loss: 2.025770E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.921 | TFLOPs: 23.67 | +63: iteration 35680/ 73814 | consumed samples: 18268160 | consumed tokens: 37413191680 | elapsed time per iteration (s): 2.26 | learning rate: 1.162E-04 | global batch size: 512 | lm loss: 2.007510E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.784 | TFLOPs: 23.35 | +63: iteration 35690/ 73814 | consumed samples: 18273280 | consumed tokens: 37423677440 | elapsed time per iteration (s): 2.25 | learning rate: 1.161E-04 | global batch size: 512 | lm loss: 2.041160E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.809 | TFLOPs: 23.45 | +63: iteration 35700/ 73814 | consumed samples: 18278400 | consumed tokens: 37434163200 | elapsed time per iteration (s): 2.24 | learning rate: 1.161E-04 | global batch size: 512 | lm loss: 2.047740E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.209 | TFLOPs: 23.49 | +63: iteration 35710/ 73814 | consumed samples: 18283520 | consumed tokens: 37444648960 | elapsed time per iteration (s): 2.23 | learning rate: 1.161E-04 | global batch size: 512 | lm loss: 2.024193E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.823 | TFLOPs: 23.66 | +63: iteration 35720/ 73814 | consumed samples: 18288640 | consumed tokens: 37455134720 | elapsed time per iteration (s): 2.32 | learning rate: 1.160E-04 | global batch size: 512 | lm loss: 2.036722E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.805 | TFLOPs: 22.73 | +63: iteration 35730/ 73814 | consumed samples: 18293760 | consumed tokens: 37465620480 | elapsed time per iteration (s): 2.28 | learning rate: 1.160E-04 | global batch size: 512 | lm loss: 2.048512E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.987 | TFLOPs: 23.16 | +63: iteration 35740/ 73814 | consumed samples: 18298880 | consumed tokens: 37476106240 | elapsed time per iteration (s): 2.27 | learning rate: 1.159E-04 | global batch size: 512 | lm loss: 2.022009E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.608 | TFLOPs: 23.23 | +63: iteration 35750/ 73814 | consumed samples: 18304000 | consumed tokens: 37486592000 | elapsed time per iteration (s): 2.42 | learning rate: 1.159E-04 | global batch size: 512 | lm loss: 2.034716E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.894 | TFLOPs: 21.81 | +63: iteration 35760/ 73814 | consumed samples: 18309120 | consumed tokens: 37497077760 | elapsed time per iteration (s): 2.27 | learning rate: 1.159E-04 | global batch size: 512 | lm loss: 2.015482E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.481 | TFLOPs: 23.21 | +63: iteration 35770/ 73814 | consumed samples: 18314240 | consumed tokens: 37507563520 | elapsed time per iteration (s): 2.25 | learning rate: 1.158E-04 | global batch size: 512 | lm loss: 2.038434E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.417 | TFLOPs: 23.41 | +63: iteration 35780/ 73814 | consumed samples: 18319360 | consumed tokens: 37518049280 | elapsed time per iteration (s): 2.44 | learning rate: 1.158E-04 | global batch size: 512 | lm loss: 2.025514E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.106 | TFLOPs: 21.63 | +63: iteration 35790/ 73814 | consumed samples: 18324480 | consumed tokens: 37528535040 | elapsed time per iteration (s): 2.66 | learning rate: 1.157E-04 | global batch size: 512 | lm loss: 2.014611E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 192.657 | TFLOPs: 19.83 | +63: iteration 35800/ 73814 | consumed samples: 18329600 | consumed tokens: 37539020800 | elapsed time per iteration (s): 2.73 | learning rate: 1.157E-04 | global batch size: 512 | lm loss: 2.023724E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 187.601 | TFLOPs: 19.31 | +63: iteration 35810/ 73814 | consumed samples: 18334720 | consumed tokens: 37549506560 | elapsed time per iteration (s): 2.32 | learning rate: 1.157E-04 | global batch size: 512 | lm loss: 2.005192E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.303 | TFLOPs: 22.68 | +63: iteration 35820/ 73814 | consumed samples: 18339840 | consumed tokens: 37559992320 | elapsed time per iteration (s): 2.27 | learning rate: 1.156E-04 | global batch size: 512 | lm loss: 2.041898E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.523 | TFLOPs: 23.22 | +63: iteration 35830/ 73814 | consumed samples: 18344960 | consumed tokens: 37570478080 | elapsed time per iteration (s): 2.36 | learning rate: 1.156E-04 | global batch size: 512 | lm loss: 2.022577E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.172 | TFLOPs: 22.36 | +63: iteration 35840/ 73814 | consumed samples: 18350080 | consumed tokens: 37580963840 | elapsed time per iteration (s): 2.47 | learning rate: 1.156E-04 | global batch size: 512 | lm loss: 2.034327E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 207.698 | TFLOPs: 21.38 | +63: iteration 35850/ 73814 | consumed samples: 18355200 | consumed tokens: 37591449600 | elapsed time per iteration (s): 2.25 | learning rate: 1.155E-04 | global batch size: 512 | lm loss: 2.023413E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.263 | TFLOPs: 23.40 | +63: iteration 35860/ 73814 | consumed samples: 18360320 | consumed tokens: 37601935360 | elapsed time per iteration (s): 2.26 | learning rate: 1.155E-04 | global batch size: 512 | lm loss: 2.047982E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.905 | TFLOPs: 23.36 | +63: iteration 35870/ 73814 | consumed samples: 18365440 | consumed tokens: 37612421120 | elapsed time per iteration (s): 2.25 | learning rate: 1.154E-04 | global batch size: 512 | lm loss: 2.053517E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.068 | TFLOPs: 23.38 | +63: iteration 35880/ 73814 | consumed samples: 18370560 | consumed tokens: 37622906880 | elapsed time per iteration (s): 2.23 | learning rate: 1.154E-04 | global batch size: 512 | lm loss: 2.026779E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.736 | TFLOPs: 23.65 | +63: iteration 35890/ 73814 | consumed samples: 18375680 | consumed tokens: 37633392640 | elapsed time per iteration (s): 2.23 | learning rate: 1.154E-04 | global batch size: 512 | lm loss: 2.027826E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.137 | TFLOPs: 23.59 | +63: iteration 35900/ 73814 | consumed samples: 18380800 | consumed tokens: 37643878400 | elapsed time per iteration (s): 2.23 | learning rate: 1.153E-04 | global batch size: 512 | lm loss: 2.029072E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.532 | TFLOPs: 23.63 | +63: iteration 35910/ 73814 | consumed samples: 18385920 | consumed tokens: 37654364160 | elapsed time per iteration (s): 2.27 | learning rate: 1.153E-04 | global batch size: 512 | lm loss: 2.031416E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.721 | TFLOPs: 23.24 | +63: iteration 35920/ 73814 | consumed samples: 18391040 | consumed tokens: 37664849920 | elapsed time per iteration (s): 2.26 | learning rate: 1.152E-04 | global batch size: 512 | lm loss: 2.050149E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.016 | TFLOPs: 23.37 | +63: iteration 35930/ 73814 | consumed samples: 18396160 | consumed tokens: 37675335680 | elapsed time per iteration (s): 2.27 | learning rate: 1.152E-04 | global batch size: 512 | lm loss: 2.045012E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.635 | TFLOPs: 23.23 | +63: iteration 35940/ 73814 | consumed samples: 18401280 | consumed tokens: 37685821440 | elapsed time per iteration (s): 2.35 | learning rate: 1.152E-04 | global batch size: 512 | lm loss: 2.021280E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.286 | TFLOPs: 22.47 | +63: iteration 35950/ 73814 | consumed samples: 18406400 | consumed tokens: 37696307200 | elapsed time per iteration (s): 2.34 | learning rate: 1.151E-04 | global batch size: 512 | lm loss: 2.031266E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.088 | TFLOPs: 22.55 | +63: iteration 35960/ 73814 | consumed samples: 18411520 | consumed tokens: 37706792960 | elapsed time per iteration (s): 2.23 | learning rate: 1.151E-04 | global batch size: 512 | lm loss: 2.037663E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.947 | TFLOPs: 23.67 | +63: iteration 35970/ 73814 | consumed samples: 18416640 | consumed tokens: 37717278720 | elapsed time per iteration (s): 2.23 | learning rate: 1.151E-04 | global batch size: 512 | lm loss: 2.011799E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.606 | TFLOPs: 23.64 | +63: iteration 35980/ 73814 | consumed samples: 18421760 | consumed tokens: 37727764480 | elapsed time per iteration (s): 2.22 | learning rate: 1.150E-04 | global batch size: 512 | lm loss: 2.023564E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.201 | TFLOPs: 23.70 | +63: iteration 35990/ 73814 | consumed samples: 18426880 | consumed tokens: 37738250240 | elapsed time per iteration (s): 2.25 | learning rate: 1.150E-04 | global batch size: 512 | lm loss: 2.036790E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.777 | TFLOPs: 23.45 | + 0: [2022-12-02 10:34:19,034] [INFO] [logging.py:68:log_dist] [Rank 0] step=36000, skipped=0, lr=[0.00011493560373688839, 0.00011493560373688839, 0.00011493560373688839], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] + 0: steps: 36000 loss: 1.9966 iter time (s): 2.277 samples/sec: 224.894 +63: iteration 36000/ 73814 | consumed samples: 18432000 | consumed tokens: 37748736000 | elapsed time per iteration (s): 2.66 | learning rate: 1.149E-04 | global batch size: 512 | lm loss: 2.036935E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 192.695 | TFLOPs: 19.84 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 36000 | lm loss value: 1.954634E+00 | lm loss PPL: 7.061334E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 36010/ 73814 | consumed samples: 18437120 | consumed tokens: 37759221760 | elapsed time per iteration (s): 2.28 | learning rate: 1.149E-04 | global batch size: 512 | lm loss: 2.027423E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.227 | TFLOPs: 23.08 | +63: iteration 36020/ 73814 | consumed samples: 18442240 | consumed tokens: 37769707520 | elapsed time per iteration (s): 2.23 | learning rate: 1.149E-04 | global batch size: 512 | lm loss: 2.050088E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.990 | TFLOPs: 23.68 | +63: iteration 36030/ 73814 | consumed samples: 18447360 | consumed tokens: 37780193280 | elapsed time per iteration (s): 2.25 | learning rate: 1.148E-04 | global batch size: 512 | lm loss: 2.000519E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.569 | TFLOPs: 23.43 | +63: iteration 36040/ 73814 | consumed samples: 18452480 | consumed tokens: 37790679040 | elapsed time per iteration (s): 2.23 | learning rate: 1.148E-04 | global batch size: 512 | lm loss: 2.050473E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.420 | TFLOPs: 23.62 | +63: iteration 36050/ 73814 | consumed samples: 18457600 | consumed tokens: 37801164800 | elapsed time per iteration (s): 2.23 | learning rate: 1.147E-04 | global batch size: 512 | lm loss: 2.032213E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.729 | TFLOPs: 23.65 | +63: iteration 36060/ 73814 | consumed samples: 18462720 | consumed tokens: 37811650560 | elapsed time per iteration (s): 2.48 | learning rate: 1.147E-04 | global batch size: 512 | lm loss: 2.041056E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.705 | TFLOPs: 21.28 | +63: iteration 36070/ 73814 | consumed samples: 18467840 | consumed tokens: 37822136320 | elapsed time per iteration (s): 2.24 | learning rate: 1.147E-04 | global batch size: 512 | lm loss: 2.030718E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.522 | TFLOPs: 23.53 | +63: iteration 36080/ 73814 | consumed samples: 18472960 | consumed tokens: 37832622080 | elapsed time per iteration (s): 2.23 | learning rate: 1.146E-04 | global batch size: 512 | lm loss: 2.018700E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.370 | TFLOPs: 23.61 | +63: iteration 36090/ 73814 | consumed samples: 18478080 | consumed tokens: 37843107840 | elapsed time per iteration (s): 2.25 | learning rate: 1.146E-04 | global batch size: 512 | lm loss: 2.045583E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.815 | TFLOPs: 23.45 | +63: iteration 36100/ 73814 | consumed samples: 18483200 | consumed tokens: 37853593600 | elapsed time per iteration (s): 2.28 | learning rate: 1.145E-04 | global batch size: 512 | lm loss: 2.011678E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.646 | TFLOPs: 23.13 | +63: iteration 36110/ 73814 | consumed samples: 18488320 | consumed tokens: 37864079360 | elapsed time per iteration (s): 2.26 | learning rate: 1.145E-04 | global batch size: 512 | lm loss: 2.042148E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.276 | TFLOPs: 23.29 | +63: iteration 36120/ 73814 | consumed samples: 18493440 | consumed tokens: 37874565120 | elapsed time per iteration (s): 2.35 | learning rate: 1.145E-04 | global batch size: 512 | lm loss: 2.030909E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.604 | TFLOPs: 22.40 | +63: iteration 36130/ 73814 | consumed samples: 18498560 | consumed tokens: 37885050880 | elapsed time per iteration (s): 2.25 | learning rate: 1.144E-04 | global batch size: 512 | lm loss: 2.021983E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.601 | TFLOPs: 23.43 | +63: iteration 36140/ 73814 | consumed samples: 18503680 | consumed tokens: 37895536640 | elapsed time per iteration (s): 2.23 | learning rate: 1.144E-04 | global batch size: 512 | lm loss: 2.021955E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.905 | TFLOPs: 23.67 | +63: iteration 36150/ 73814 | consumed samples: 18508800 | consumed tokens: 37906022400 | elapsed time per iteration (s): 2.25 | learning rate: 1.144E-04 | global batch size: 512 | lm loss: 2.028267E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.830 | TFLOPs: 23.45 | +63: iteration 36160/ 73814 | consumed samples: 18513920 | consumed tokens: 37916508160 | elapsed time per iteration (s): 2.23 | learning rate: 1.143E-04 | global batch size: 512 | lm loss: 2.017106E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.759 | TFLOPs: 23.65 | +63: iteration 36170/ 73814 | consumed samples: 18519040 | consumed tokens: 37926993920 | elapsed time per iteration (s): 2.26 | learning rate: 1.143E-04 | global batch size: 512 | lm loss: 2.015142E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.006 | TFLOPs: 23.37 | +63: iteration 36180/ 73814 | consumed samples: 18524160 | consumed tokens: 37937479680 | elapsed time per iteration (s): 2.30 | learning rate: 1.142E-04 | global batch size: 512 | lm loss: 2.033810E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.859 | TFLOPs: 22.94 | +63: iteration 36190/ 73814 | consumed samples: 18529280 | consumed tokens: 37947965440 | elapsed time per iteration (s): 2.23 | learning rate: 1.142E-04 | global batch size: 512 | lm loss: 2.032969E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.861 | TFLOPs: 23.66 | +63: iteration 36200/ 73814 | consumed samples: 18534400 | consumed tokens: 37958451200 | elapsed time per iteration (s): 61.12 | learning rate: 1.142E-04 | global batch size: 512 | lm loss: 2.024232E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 8.377 | TFLOPs: 0.86 | +63: iteration 36210/ 73814 | consumed samples: 18539520 | consumed tokens: 37968936960 | elapsed time per iteration (s): 2.22 | learning rate: 1.141E-04 | global batch size: 512 | lm loss: 2.012556E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.152 | TFLOPs: 23.69 | +63: iteration 36220/ 73814 | consumed samples: 18544640 | consumed tokens: 37979422720 | elapsed time per iteration (s): 2.25 | learning rate: 1.141E-04 | global batch size: 512 | lm loss: 2.008111E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.571 | TFLOPs: 23.43 | +63: iteration 36230/ 73814 | consumed samples: 18549760 | consumed tokens: 37989908480 | elapsed time per iteration (s): 2.23 | learning rate: 1.140E-04 | global batch size: 512 | lm loss: 2.022598E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.859 | TFLOPs: 23.66 | +63: iteration 36240/ 73814 | consumed samples: 18554880 | consumed tokens: 38000394240 | elapsed time per iteration (s): 2.23 | learning rate: 1.140E-04 | global batch size: 512 | lm loss: 2.047871E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.002 | TFLOPs: 23.68 | +63: iteration 36250/ 73814 | consumed samples: 18560000 | consumed tokens: 38010880000 | elapsed time per iteration (s): 2.24 | learning rate: 1.140E-04 | global batch size: 512 | lm loss: 2.027094E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.294 | TFLOPs: 23.50 | +63: iteration 36260/ 73814 | consumed samples: 18565120 | consumed tokens: 38021365760 | elapsed time per iteration (s): 6.89 | learning rate: 1.139E-04 | global batch size: 512 | lm loss: 2.024682E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 74.290 | TFLOPs: 7.65 | +63: iteration 36270/ 73814 | consumed samples: 18570240 | consumed tokens: 38031851520 | elapsed time per iteration (s): 2.25 | learning rate: 1.139E-04 | global batch size: 512 | lm loss: 2.045372E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.862 | TFLOPs: 23.46 | +63: iteration 36280/ 73814 | consumed samples: 18575360 | consumed tokens: 38042337280 | elapsed time per iteration (s): 2.24 | learning rate: 1.139E-04 | global batch size: 512 | lm loss: 2.037572E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.088 | TFLOPs: 23.48 | +63: iteration 36290/ 73814 | consumed samples: 18580480 | consumed tokens: 38052823040 | elapsed time per iteration (s): 2.24 | learning rate: 1.138E-04 | global batch size: 512 | lm loss: 2.028687E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.656 | TFLOPs: 23.54 | +63: iteration 36300/ 73814 | consumed samples: 18585600 | consumed tokens: 38063308800 | elapsed time per iteration (s): 2.25 | learning rate: 1.138E-04 | global batch size: 512 | lm loss: 2.020513E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.977 | TFLOPs: 23.47 | +63: iteration 36310/ 73814 | consumed samples: 18590720 | consumed tokens: 38073794560 | elapsed time per iteration (s): 2.44 | learning rate: 1.137E-04 | global batch size: 512 | lm loss: 2.006904E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.100 | TFLOPs: 21.63 | +63: iteration 36320/ 73814 | consumed samples: 18595840 | consumed tokens: 38084280320 | elapsed time per iteration (s): 2.25 | learning rate: 1.137E-04 | global batch size: 512 | lm loss: 2.036441E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.861 | TFLOPs: 23.46 | +63: iteration 36330/ 73814 | consumed samples: 18600960 | consumed tokens: 38094766080 | elapsed time per iteration (s): 2.24 | learning rate: 1.137E-04 | global batch size: 512 | lm loss: 2.025052E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.360 | TFLOPs: 23.51 | +63: iteration 36340/ 73814 | consumed samples: 18606080 | consumed tokens: 38105251840 | elapsed time per iteration (s): 2.32 | learning rate: 1.136E-04 | global batch size: 512 | lm loss: 2.025598E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.647 | TFLOPs: 22.71 | +63: iteration 36350/ 73814 | consumed samples: 18611200 | consumed tokens: 38115737600 | elapsed time per iteration (s): 2.23 | learning rate: 1.136E-04 | global batch size: 512 | lm loss: 2.024075E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.084 | TFLOPs: 23.69 | +63: iteration 36360/ 73814 | consumed samples: 18616320 | consumed tokens: 38126223360 | elapsed time per iteration (s): 2.24 | learning rate: 1.135E-04 | global batch size: 512 | lm loss: 2.012056E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.236 | TFLOPs: 23.50 | +63: iteration 36370/ 73814 | consumed samples: 18621440 | consumed tokens: 38136709120 | elapsed time per iteration (s): 2.23 | learning rate: 1.135E-04 | global batch size: 512 | lm loss: 2.041366E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.636 | TFLOPs: 23.64 | +63: iteration 36380/ 73814 | consumed samples: 18626560 | consumed tokens: 38147194880 | elapsed time per iteration (s): 2.25 | learning rate: 1.135E-04 | global batch size: 512 | lm loss: 2.027896E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.579 | TFLOPs: 23.43 | +63: iteration 36390/ 73814 | consumed samples: 18631680 | consumed tokens: 38157680640 | elapsed time per iteration (s): 2.25 | learning rate: 1.134E-04 | global batch size: 512 | lm loss: 2.016675E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.835 | TFLOPs: 23.45 | +63: iteration 36400/ 73814 | consumed samples: 18636800 | consumed tokens: 38168166400 | elapsed time per iteration (s): 2.24 | learning rate: 1.134E-04 | global batch size: 512 | lm loss: 2.032395E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.308 | TFLOPs: 23.50 | +63: iteration 36410/ 73814 | consumed samples: 18641920 | consumed tokens: 38178652160 | elapsed time per iteration (s): 2.30 | learning rate: 1.134E-04 | global batch size: 512 | lm loss: 2.027685E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.052 | TFLOPs: 22.96 | +63: iteration 36420/ 73814 | consumed samples: 18647040 | consumed tokens: 38189137920 | elapsed time per iteration (s): 2.23 | learning rate: 1.133E-04 | global batch size: 512 | lm loss: 2.049963E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.756 | TFLOPs: 23.65 | +63: iteration 36430/ 73814 | consumed samples: 18652160 | consumed tokens: 38199623680 | elapsed time per iteration (s): 2.24 | learning rate: 1.133E-04 | global batch size: 512 | lm loss: 2.037195E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.904 | TFLOPs: 23.56 | +63: iteration 36440/ 73814 | consumed samples: 18657280 | consumed tokens: 38210109440 | elapsed time per iteration (s): 2.25 | learning rate: 1.132E-04 | global batch size: 512 | lm loss: 2.025611E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.026 | TFLOPs: 23.47 | +63: iteration 36450/ 73814 | consumed samples: 18662400 | consumed tokens: 38220595200 | elapsed time per iteration (s): 2.23 | learning rate: 1.132E-04 | global batch size: 512 | lm loss: 2.031882E+00 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.746 | TFLOPs: 23.65 | +63: iteration 36460/ 73814 | consumed samples: 18667520 | consumed tokens: 38231080960 | elapsed time per iteration (s): 2.25 | learning rate: 1.132E-04 | global batch size: 512 | lm loss: 1.998414E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.493 | TFLOPs: 23.42 | +63: iteration 36470/ 73814 | consumed samples: 18672640 | consumed tokens: 38241566720 | elapsed time per iteration (s): 2.23 | learning rate: 1.131E-04 | global batch size: 512 | lm loss: 2.050763E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.906 | TFLOPs: 23.67 | +63: iteration 36480/ 73814 | consumed samples: 18677760 | consumed tokens: 38252052480 | elapsed time per iteration (s): 2.25 | learning rate: 1.131E-04 | global batch size: 512 | lm loss: 2.026808E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.516 | TFLOPs: 23.42 | +63: iteration 36490/ 73814 | consumed samples: 18682880 | consumed tokens: 38262538240 | elapsed time per iteration (s): 2.23 | learning rate: 1.130E-04 | global batch size: 512 | lm loss: 2.033763E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.775 | TFLOPs: 23.65 | +63: iteration 36500/ 73814 | consumed samples: 18688000 | consumed tokens: 38273024000 | elapsed time per iteration (s): 2.24 | learning rate: 1.130E-04 | global batch size: 512 | lm loss: 2.026585E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.397 | TFLOPs: 23.51 | +63: iteration 36510/ 73814 | consumed samples: 18693120 | consumed tokens: 38283509760 | elapsed time per iteration (s): 2.25 | learning rate: 1.130E-04 | global batch size: 512 | lm loss: 2.017223E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.040 | TFLOPs: 23.48 | +63: iteration 36520/ 73814 | consumed samples: 18698240 | consumed tokens: 38293995520 | elapsed time per iteration (s): 2.23 | learning rate: 1.129E-04 | global batch size: 512 | lm loss: 2.027327E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.068 | TFLOPs: 23.68 | +63: iteration 36530/ 73814 | consumed samples: 18703360 | consumed tokens: 38304481280 | elapsed time per iteration (s): 2.41 | learning rate: 1.129E-04 | global batch size: 512 | lm loss: 2.042555E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.374 | TFLOPs: 21.86 | +63: iteration 36540/ 73814 | consumed samples: 18708480 | consumed tokens: 38314967040 | elapsed time per iteration (s): 2.25 | learning rate: 1.128E-04 | global batch size: 512 | lm loss: 2.040315E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.913 | TFLOPs: 23.46 | +63: iteration 36550/ 73814 | consumed samples: 18713600 | consumed tokens: 38325452800 | elapsed time per iteration (s): 2.24 | learning rate: 1.128E-04 | global batch size: 512 | lm loss: 2.028302E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.957 | TFLOPs: 23.57 | +63: iteration 36560/ 73814 | consumed samples: 18718720 | consumed tokens: 38335938560 | elapsed time per iteration (s): 2.23 | learning rate: 1.128E-04 | global batch size: 512 | lm loss: 2.017237E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.737 | TFLOPs: 23.65 | +63: iteration 36570/ 73814 | consumed samples: 18723840 | consumed tokens: 38346424320 | elapsed time per iteration (s): 2.23 | learning rate: 1.127E-04 | global batch size: 512 | lm loss: 2.025471E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.686 | TFLOPs: 23.65 | +63: iteration 36580/ 73814 | consumed samples: 18728960 | consumed tokens: 38356910080 | elapsed time per iteration (s): 2.24 | learning rate: 1.127E-04 | global batch size: 512 | lm loss: 2.008603E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.530 | TFLOPs: 23.53 | +63: iteration 36590/ 73814 | consumed samples: 18734080 | consumed tokens: 38367395840 | elapsed time per iteration (s): 2.24 | learning rate: 1.127E-04 | global batch size: 512 | lm loss: 2.029352E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.773 | TFLOPs: 23.55 | +63: iteration 36600/ 73814 | consumed samples: 18739200 | consumed tokens: 38377881600 | elapsed time per iteration (s): 2.23 | learning rate: 1.126E-04 | global batch size: 512 | lm loss: 2.020065E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.246 | TFLOPs: 23.60 | +63: iteration 36610/ 73814 | consumed samples: 18744320 | consumed tokens: 38388367360 | elapsed time per iteration (s): 2.54 | learning rate: 1.126E-04 | global batch size: 512 | lm loss: 2.017740E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.502 | TFLOPs: 20.74 | +63: iteration 36620/ 73814 | consumed samples: 18749440 | consumed tokens: 38398853120 | elapsed time per iteration (s): 2.23 | learning rate: 1.125E-04 | global batch size: 512 | lm loss: 2.003321E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.947 | TFLOPs: 23.67 | +63: iteration 36630/ 73814 | consumed samples: 18754560 | consumed tokens: 38409338880 | elapsed time per iteration (s): 2.27 | learning rate: 1.125E-04 | global batch size: 512 | lm loss: 2.007100E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.669 | TFLOPs: 23.23 | +63: iteration 36640/ 73814 | consumed samples: 18759680 | consumed tokens: 38419824640 | elapsed time per iteration (s): 2.34 | learning rate: 1.125E-04 | global batch size: 512 | lm loss: 2.017236E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.076 | TFLOPs: 22.55 | +63: iteration 36650/ 73814 | consumed samples: 18764800 | consumed tokens: 38430310400 | elapsed time per iteration (s): 2.24 | learning rate: 1.124E-04 | global batch size: 512 | lm loss: 2.020344E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.752 | TFLOPs: 23.55 | +63: iteration 36660/ 73814 | consumed samples: 18769920 | consumed tokens: 38440796160 | elapsed time per iteration (s): 2.25 | learning rate: 1.124E-04 | global batch size: 512 | lm loss: 2.003008E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.230 | TFLOPs: 23.39 | +63: iteration 36670/ 73814 | consumed samples: 18775040 | consumed tokens: 38451281920 | elapsed time per iteration (s): 2.25 | learning rate: 1.123E-04 | global batch size: 512 | lm loss: 2.032345E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.733 | TFLOPs: 23.44 | +63: iteration 36680/ 73814 | consumed samples: 18780160 | consumed tokens: 38461767680 | elapsed time per iteration (s): 2.24 | learning rate: 1.123E-04 | global batch size: 512 | lm loss: 2.034893E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.350 | TFLOPs: 23.51 | +63: iteration 36690/ 73814 | consumed samples: 18785280 | consumed tokens: 38472253440 | elapsed time per iteration (s): 2.23 | learning rate: 1.123E-04 | global batch size: 512 | lm loss: 2.037015E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.484 | TFLOPs: 23.62 | +63: iteration 36700/ 73814 | consumed samples: 18790400 | consumed tokens: 38482739200 | elapsed time per iteration (s): 2.24 | learning rate: 1.122E-04 | global batch size: 512 | lm loss: 2.011526E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.826 | TFLOPs: 23.56 | +63: iteration 36710/ 73814 | consumed samples: 18795520 | consumed tokens: 38493224960 | elapsed time per iteration (s): 2.23 | learning rate: 1.122E-04 | global batch size: 512 | lm loss: 2.027064E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.485 | TFLOPs: 23.62 | +63: iteration 36720/ 73814 | consumed samples: 18800640 | consumed tokens: 38503710720 | elapsed time per iteration (s): 2.25 | learning rate: 1.122E-04 | global batch size: 512 | lm loss: 2.024047E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.802 | TFLOPs: 23.45 | +63: iteration 36730/ 73814 | consumed samples: 18805760 | consumed tokens: 38514196480 | elapsed time per iteration (s): 2.24 | learning rate: 1.121E-04 | global batch size: 512 | lm loss: 2.020590E+00 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.507 | TFLOPs: 23.52 | +63: iteration 36740/ 73814 | consumed samples: 18810880 | consumed tokens: 38524682240 | elapsed time per iteration (s): 2.29 | learning rate: 1.121E-04 | global batch size: 512 | lm loss: 2.022509E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.689 | TFLOPs: 23.03 | +63: iteration 36750/ 73814 | consumed samples: 18816000 | consumed tokens: 38535168000 | elapsed time per iteration (s): 2.25 | learning rate: 1.120E-04 | global batch size: 512 | lm loss: 2.025305E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.647 | TFLOPs: 23.44 | +63: iteration 36760/ 73814 | consumed samples: 18821120 | consumed tokens: 38545653760 | elapsed time per iteration (s): 2.23 | learning rate: 1.120E-04 | global batch size: 512 | lm loss: 2.019665E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.869 | TFLOPs: 23.66 | +63: iteration 36770/ 73814 | consumed samples: 18826240 | consumed tokens: 38556139520 | elapsed time per iteration (s): 2.23 | learning rate: 1.120E-04 | global batch size: 512 | lm loss: 2.008789E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.118 | TFLOPs: 23.59 | +63: iteration 36780/ 73814 | consumed samples: 18831360 | consumed tokens: 38566625280 | elapsed time per iteration (s): 2.26 | learning rate: 1.119E-04 | global batch size: 512 | lm loss: 2.031100E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.946 | TFLOPs: 23.36 | +63: iteration 36790/ 73814 | consumed samples: 18836480 | consumed tokens: 38577111040 | elapsed time per iteration (s): 2.23 | learning rate: 1.119E-04 | global batch size: 512 | lm loss: 2.022946E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.916 | TFLOPs: 23.67 | +63: iteration 36800/ 73814 | consumed samples: 18841600 | consumed tokens: 38587596800 | elapsed time per iteration (s): 2.25 | learning rate: 1.118E-04 | global batch size: 512 | lm loss: 2.003535E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.258 | TFLOPs: 23.40 | +63: iteration 36810/ 73814 | consumed samples: 18846720 | consumed tokens: 38598082560 | elapsed time per iteration (s): 2.23 | learning rate: 1.118E-04 | global batch size: 512 | lm loss: 2.010978E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.740 | TFLOPs: 23.65 | +63: iteration 36820/ 73814 | consumed samples: 18851840 | consumed tokens: 38608568320 | elapsed time per iteration (s): 2.23 | learning rate: 1.118E-04 | global batch size: 512 | lm loss: 2.029911E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.972 | TFLOPs: 23.67 | +63: iteration 36830/ 73814 | consumed samples: 18856960 | consumed tokens: 38619054080 | elapsed time per iteration (s): 2.23 | learning rate: 1.117E-04 | global batch size: 512 | lm loss: 2.001102E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.702 | TFLOPs: 23.65 | +63: iteration 36840/ 73814 | consumed samples: 18862080 | consumed tokens: 38629539840 | elapsed time per iteration (s): 2.29 | learning rate: 1.117E-04 | global batch size: 512 | lm loss: 2.012670E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.700 | TFLOPs: 23.03 | +63: iteration 36850/ 73814 | consumed samples: 18867200 | consumed tokens: 38640025600 | elapsed time per iteration (s): 2.24 | learning rate: 1.116E-04 | global batch size: 512 | lm loss: 2.017865E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.679 | TFLOPs: 23.54 | +63: iteration 36860/ 73814 | consumed samples: 18872320 | consumed tokens: 38650511360 | elapsed time per iteration (s): 2.24 | learning rate: 1.116E-04 | global batch size: 512 | lm loss: 2.033617E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.553 | TFLOPs: 23.53 | +63: iteration 36870/ 73814 | consumed samples: 18877440 | consumed tokens: 38660997120 | elapsed time per iteration (s): 2.22 | learning rate: 1.116E-04 | global batch size: 512 | lm loss: 2.024196E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.182 | TFLOPs: 23.70 | +63: iteration 36880/ 73814 | consumed samples: 18882560 | consumed tokens: 38671482880 | elapsed time per iteration (s): 2.40 | learning rate: 1.115E-04 | global batch size: 512 | lm loss: 2.048449E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.338 | TFLOPs: 21.96 | +63: iteration 36890/ 73814 | consumed samples: 18887680 | consumed tokens: 38681968640 | elapsed time per iteration (s): 2.46 | learning rate: 1.115E-04 | global batch size: 512 | lm loss: 2.034945E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.009 | TFLOPs: 21.41 | +63: iteration 36900/ 73814 | consumed samples: 18892800 | consumed tokens: 38692454400 | elapsed time per iteration (s): 2.24 | learning rate: 1.115E-04 | global batch size: 512 | lm loss: 1.996305E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.888 | TFLOPs: 23.56 | +63: iteration 36910/ 73814 | consumed samples: 18897920 | consumed tokens: 38702940160 | elapsed time per iteration (s): 2.32 | learning rate: 1.114E-04 | global batch size: 512 | lm loss: 2.042922E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.957 | TFLOPs: 22.75 | +63: iteration 36920/ 73814 | consumed samples: 18903040 | consumed tokens: 38713425920 | elapsed time per iteration (s): 2.37 | learning rate: 1.114E-04 | global batch size: 512 | lm loss: 2.040732E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.223 | TFLOPs: 22.26 | +63: iteration 36930/ 73814 | consumed samples: 18908160 | consumed tokens: 38723911680 | elapsed time per iteration (s): 2.23 | learning rate: 1.113E-04 | global batch size: 512 | lm loss: 2.028584E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.599 | TFLOPs: 23.64 | +63: iteration 36940/ 73814 | consumed samples: 18913280 | consumed tokens: 38734397440 | elapsed time per iteration (s): 2.22 | learning rate: 1.113E-04 | global batch size: 512 | lm loss: 2.029734E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.291 | TFLOPs: 23.71 | +63: iteration 36950/ 73814 | consumed samples: 18918400 | consumed tokens: 38744883200 | elapsed time per iteration (s): 2.23 | learning rate: 1.113E-04 | global batch size: 512 | lm loss: 2.037789E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.632 | TFLOPs: 23.64 | +63: iteration 36960/ 73814 | consumed samples: 18923520 | consumed tokens: 38755368960 | elapsed time per iteration (s): 2.23 | learning rate: 1.112E-04 | global batch size: 512 | lm loss: 2.031073E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.589 | TFLOPs: 23.64 | +63: iteration 36970/ 73814 | consumed samples: 18928640 | consumed tokens: 38765854720 | elapsed time per iteration (s): 2.24 | learning rate: 1.112E-04 | global batch size: 512 | lm loss: 2.029432E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.073 | TFLOPs: 23.48 | +63: iteration 36980/ 73814 | consumed samples: 18933760 | consumed tokens: 38776340480 | elapsed time per iteration (s): 2.32 | learning rate: 1.111E-04 | global batch size: 512 | lm loss: 2.021142E+00 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.238 | TFLOPs: 22.67 | +63: iteration 36990/ 73814 | consumed samples: 18938880 | consumed tokens: 38786826240 | elapsed time per iteration (s): 2.24 | learning rate: 1.111E-04 | global batch size: 512 | lm loss: 2.038243E+00 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.016 | TFLOPs: 23.58 | +63: iteration 37000/ 73814 | consumed samples: 18944000 | consumed tokens: 38797312000 | elapsed time per iteration (s): 2.23 | learning rate: 1.111E-04 | global batch size: 512 | lm loss: 2.005494E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.517 | TFLOPs: 23.63 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 37000 | lm loss value: 2.019217E+00 | lm loss PPL: 7.532427E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 37010/ 73814 | consumed samples: 18949120 | consumed tokens: 38807797760 | elapsed time per iteration (s): 2.31 | learning rate: 1.110E-04 | global batch size: 512 | lm loss: 2.014539E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.424 | TFLOPs: 22.79 | +63: iteration 37020/ 73814 | consumed samples: 18954240 | consumed tokens: 38818283520 | elapsed time per iteration (s): 2.32 | learning rate: 1.110E-04 | global batch size: 512 | lm loss: 2.023771E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.771 | TFLOPs: 22.73 | +63: iteration 37030/ 73814 | consumed samples: 18959360 | consumed tokens: 38828769280 | elapsed time per iteration (s): 2.62 | learning rate: 1.110E-04 | global batch size: 512 | lm loss: 2.038805E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 195.493 | TFLOPs: 20.13 | +63: iteration 37040/ 73814 | consumed samples: 18964480 | consumed tokens: 38839255040 | elapsed time per iteration (s): 2.27 | learning rate: 1.109E-04 | global batch size: 512 | lm loss: 2.011746E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.998 | TFLOPs: 23.27 | +63: iteration 37050/ 73814 | consumed samples: 18969600 | consumed tokens: 38849740800 | elapsed time per iteration (s): 2.23 | learning rate: 1.109E-04 | global batch size: 512 | lm loss: 2.042494E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.017 | TFLOPs: 23.68 | +63: iteration 37060/ 73814 | consumed samples: 18974720 | consumed tokens: 38860226560 | elapsed time per iteration (s): 2.25 | learning rate: 1.108E-04 | global batch size: 512 | lm loss: 2.016455E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.548 | TFLOPs: 23.42 | +63: iteration 37070/ 73814 | consumed samples: 18979840 | consumed tokens: 38870712320 | elapsed time per iteration (s): 2.23 | learning rate: 1.108E-04 | global batch size: 512 | lm loss: 2.032961E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.214 | TFLOPs: 23.60 | +63: iteration 37080/ 73814 | consumed samples: 18984960 | consumed tokens: 38881198080 | elapsed time per iteration (s): 2.23 | learning rate: 1.108E-04 | global batch size: 512 | lm loss: 2.007346E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.646 | TFLOPs: 23.64 | +63: iteration 37090/ 73814 | consumed samples: 18990080 | consumed tokens: 38891683840 | elapsed time per iteration (s): 2.23 | learning rate: 1.107E-04 | global batch size: 512 | lm loss: 2.029106E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.591 | TFLOPs: 23.64 | +63: iteration 37100/ 73814 | consumed samples: 18995200 | consumed tokens: 38902169600 | elapsed time per iteration (s): 2.24 | learning rate: 1.107E-04 | global batch size: 512 | lm loss: 1.984039E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.521 | TFLOPs: 23.53 | +63: iteration 37110/ 73814 | consumed samples: 19000320 | consumed tokens: 38912655360 | elapsed time per iteration (s): 2.24 | learning rate: 1.106E-04 | global batch size: 512 | lm loss: 2.008929E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.073 | TFLOPs: 23.58 | +63: iteration 37120/ 73814 | consumed samples: 19005440 | consumed tokens: 38923141120 | elapsed time per iteration (s): 2.23 | learning rate: 1.106E-04 | global batch size: 512 | lm loss: 2.029597E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.581 | TFLOPs: 23.63 | +63: iteration 37130/ 73814 | consumed samples: 19010560 | consumed tokens: 38933626880 | elapsed time per iteration (s): 2.22 | learning rate: 1.106E-04 | global batch size: 512 | lm loss: 2.023648E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.178 | TFLOPs: 23.70 | +63: iteration 37140/ 73814 | consumed samples: 19015680 | consumed tokens: 38944112640 | elapsed time per iteration (s): 2.25 | learning rate: 1.105E-04 | global batch size: 512 | lm loss: 2.011104E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.879 | TFLOPs: 23.46 | +63: iteration 37150/ 73814 | consumed samples: 19020800 | consumed tokens: 38954598400 | elapsed time per iteration (s): 2.25 | learning rate: 1.105E-04 | global batch size: 512 | lm loss: 2.030816E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.053 | TFLOPs: 23.48 | +63: iteration 37160/ 73814 | consumed samples: 19025920 | consumed tokens: 38965084160 | elapsed time per iteration (s): 2.40 | learning rate: 1.104E-04 | global batch size: 512 | lm loss: 2.021111E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.776 | TFLOPs: 22.01 | +63: iteration 37170/ 73814 | consumed samples: 19031040 | consumed tokens: 38975569920 | elapsed time per iteration (s): 2.33 | learning rate: 1.104E-04 | global batch size: 512 | lm loss: 2.031857E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.312 | TFLOPs: 22.58 | +63: iteration 37180/ 73814 | consumed samples: 19036160 | consumed tokens: 38986055680 | elapsed time per iteration (s): 2.40 | learning rate: 1.104E-04 | global batch size: 512 | lm loss: 2.017393E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.166 | TFLOPs: 21.94 | +63: iteration 37190/ 73814 | consumed samples: 19041280 | consumed tokens: 38996541440 | elapsed time per iteration (s): 2.34 | learning rate: 1.103E-04 | global batch size: 512 | lm loss: 2.005987E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.512 | TFLOPs: 22.49 | +63: iteration 37200/ 73814 | consumed samples: 19046400 | consumed tokens: 39007027200 | elapsed time per iteration (s): 2.34 | learning rate: 1.103E-04 | global batch size: 512 | lm loss: 2.024974E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.552 | TFLOPs: 22.50 | +63: iteration 37210/ 73814 | consumed samples: 19051520 | consumed tokens: 39017512960 | elapsed time per iteration (s): 2.40 | learning rate: 1.103E-04 | global batch size: 512 | lm loss: 2.028001E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.387 | TFLOPs: 21.97 | +63: iteration 37220/ 73814 | consumed samples: 19056640 | consumed tokens: 39027998720 | elapsed time per iteration (s): 2.63 | learning rate: 1.102E-04 | global batch size: 512 | lm loss: 2.022736E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 194.407 | TFLOPs: 20.01 | +63: iteration 37230/ 73814 | consumed samples: 19061760 | consumed tokens: 39038484480 | elapsed time per iteration (s): 2.64 | learning rate: 1.102E-04 | global batch size: 512 | lm loss: 2.020454E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 194.021 | TFLOPs: 19.97 | +63: iteration 37240/ 73814 | consumed samples: 19066880 | consumed tokens: 39048970240 | elapsed time per iteration (s): 2.40 | learning rate: 1.101E-04 | global batch size: 512 | lm loss: 2.018921E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.460 | TFLOPs: 21.97 | +63: iteration 37250/ 73814 | consumed samples: 19072000 | consumed tokens: 39059456000 | elapsed time per iteration (s): 2.25 | learning rate: 1.101E-04 | global batch size: 512 | lm loss: 2.044525E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.765 | TFLOPs: 23.45 | +63: iteration 37260/ 73814 | consumed samples: 19077120 | consumed tokens: 39069941760 | elapsed time per iteration (s): 2.39 | learning rate: 1.101E-04 | global batch size: 512 | lm loss: 2.023133E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.509 | TFLOPs: 22.08 | +63: iteration 37270/ 73814 | consumed samples: 19082240 | consumed tokens: 39080427520 | elapsed time per iteration (s): 2.30 | learning rate: 1.100E-04 | global batch size: 512 | lm loss: 2.020824E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.748 | TFLOPs: 22.93 | +63: iteration 37280/ 73814 | consumed samples: 19087360 | consumed tokens: 39090913280 | elapsed time per iteration (s): 2.30 | learning rate: 1.100E-04 | global batch size: 512 | lm loss: 2.024767E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.841 | TFLOPs: 22.94 | +63: iteration 37290/ 73814 | consumed samples: 19092480 | consumed tokens: 39101399040 | elapsed time per iteration (s): 2.22 | learning rate: 1.099E-04 | global batch size: 512 | lm loss: 2.015141E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.586 | TFLOPs: 23.74 | +63: iteration 37300/ 73814 | consumed samples: 19097600 | consumed tokens: 39111884800 | elapsed time per iteration (s): 2.24 | learning rate: 1.099E-04 | global batch size: 512 | lm loss: 2.028984E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.503 | TFLOPs: 23.52 | +63: iteration 37310/ 73814 | consumed samples: 19102720 | consumed tokens: 39122370560 | elapsed time per iteration (s): 2.26 | learning rate: 1.099E-04 | global batch size: 512 | lm loss: 2.041739E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.685 | TFLOPs: 23.34 | +63: iteration 37320/ 73814 | consumed samples: 19107840 | consumed tokens: 39132856320 | elapsed time per iteration (s): 2.27 | learning rate: 1.098E-04 | global batch size: 512 | lm loss: 1.988568E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.184 | TFLOPs: 23.18 | +63: iteration 37330/ 73814 | consumed samples: 19112960 | consumed tokens: 39143342080 | elapsed time per iteration (s): 2.23 | learning rate: 1.098E-04 | global batch size: 512 | lm loss: 2.014624E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.740 | TFLOPs: 23.65 | +63: iteration 37340/ 73814 | consumed samples: 19118080 | consumed tokens: 39153827840 | elapsed time per iteration (s): 2.25 | learning rate: 1.098E-04 | global batch size: 512 | lm loss: 2.027351E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.294 | TFLOPs: 23.40 | +63: iteration 37350/ 73814 | consumed samples: 19123200 | consumed tokens: 39164313600 | elapsed time per iteration (s): 2.23 | learning rate: 1.097E-04 | global batch size: 512 | lm loss: 2.035469E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.739 | TFLOPs: 23.65 | +63: iteration 37360/ 73814 | consumed samples: 19128320 | consumed tokens: 39174799360 | elapsed time per iteration (s): 2.25 | learning rate: 1.097E-04 | global batch size: 512 | lm loss: 2.037967E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.877 | TFLOPs: 23.46 | +63: iteration 37370/ 73814 | consumed samples: 19133440 | consumed tokens: 39185285120 | elapsed time per iteration (s): 2.29 | learning rate: 1.096E-04 | global batch size: 512 | lm loss: 2.039020E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.242 | TFLOPs: 22.98 | +63: iteration 37380/ 73814 | consumed samples: 19138560 | consumed tokens: 39195770880 | elapsed time per iteration (s): 2.24 | learning rate: 1.096E-04 | global batch size: 512 | lm loss: 2.038686E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.979 | TFLOPs: 23.57 | +63: iteration 37390/ 73814 | consumed samples: 19143680 | consumed tokens: 39206256640 | elapsed time per iteration (s): 2.33 | learning rate: 1.096E-04 | global batch size: 512 | lm loss: 2.019074E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.311 | TFLOPs: 22.58 | +63: iteration 37400/ 73814 | consumed samples: 19148800 | consumed tokens: 39216742400 | elapsed time per iteration (s): 2.26 | learning rate: 1.095E-04 | global batch size: 512 | lm loss: 2.028775E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.115 | TFLOPs: 23.28 | +63: iteration 37410/ 73814 | consumed samples: 19153920 | consumed tokens: 39227228160 | elapsed time per iteration (s): 2.25 | learning rate: 1.095E-04 | global batch size: 512 | lm loss: 2.021769E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.577 | TFLOPs: 23.43 | +63: iteration 37420/ 73814 | consumed samples: 19159040 | consumed tokens: 39237713920 | elapsed time per iteration (s): 2.25 | learning rate: 1.094E-04 | global batch size: 512 | lm loss: 2.016609E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.615 | TFLOPs: 23.43 | +63: iteration 37430/ 73814 | consumed samples: 19164160 | consumed tokens: 39248199680 | elapsed time per iteration (s): 2.24 | learning rate: 1.094E-04 | global batch size: 512 | lm loss: 2.028498E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.321 | TFLOPs: 23.50 | +63: iteration 37440/ 73814 | consumed samples: 19169280 | consumed tokens: 39258685440 | elapsed time per iteration (s): 2.34 | learning rate: 1.094E-04 | global batch size: 512 | lm loss: 2.030692E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.896 | TFLOPs: 22.53 | +63: iteration 37450/ 73814 | consumed samples: 19174400 | consumed tokens: 39269171200 | elapsed time per iteration (s): 2.22 | learning rate: 1.093E-04 | global batch size: 512 | lm loss: 2.025567E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.116 | TFLOPs: 23.69 | +63: iteration 37460/ 73814 | consumed samples: 19179520 | consumed tokens: 39279656960 | elapsed time per iteration (s): 2.31 | learning rate: 1.093E-04 | global batch size: 512 | lm loss: 2.032284E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.311 | TFLOPs: 22.78 | +63: iteration 37470/ 73814 | consumed samples: 19184640 | consumed tokens: 39290142720 | elapsed time per iteration (s): 2.25 | learning rate: 1.093E-04 | global batch size: 512 | lm loss: 2.014541E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.888 | TFLOPs: 23.46 | +63: iteration 37480/ 73814 | consumed samples: 19189760 | consumed tokens: 39300628480 | elapsed time per iteration (s): 2.23 | learning rate: 1.092E-04 | global batch size: 512 | lm loss: 2.026283E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.888 | TFLOPs: 23.67 | +63: iteration 37490/ 73814 | consumed samples: 19194880 | consumed tokens: 39311114240 | elapsed time per iteration (s): 2.24 | learning rate: 1.092E-04 | global batch size: 512 | lm loss: 2.032680E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.938 | TFLOPs: 23.57 | +63: iteration 37500/ 73814 | consumed samples: 19200000 | consumed tokens: 39321600000 | elapsed time per iteration (s): 2.39 | learning rate: 1.091E-04 | global batch size: 512 | lm loss: 2.026650E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.345 | TFLOPs: 22.07 | +63: iteration 37510/ 73814 | consumed samples: 19205120 | consumed tokens: 39332085760 | elapsed time per iteration (s): 2.24 | learning rate: 1.091E-04 | global batch size: 512 | lm loss: 2.034978E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.609 | TFLOPs: 23.53 | +63: iteration 37520/ 73814 | consumed samples: 19210240 | consumed tokens: 39342571520 | elapsed time per iteration (s): 2.24 | learning rate: 1.091E-04 | global batch size: 512 | lm loss: 2.011121E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.076 | TFLOPs: 23.58 | +63: iteration 37530/ 73814 | consumed samples: 19215360 | consumed tokens: 39353057280 | elapsed time per iteration (s): 2.25 | learning rate: 1.090E-04 | global batch size: 512 | lm loss: 2.001995E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.932 | TFLOPs: 23.46 | +63: iteration 37540/ 73814 | consumed samples: 19220480 | consumed tokens: 39363543040 | elapsed time per iteration (s): 2.33 | learning rate: 1.090E-04 | global batch size: 512 | lm loss: 2.027197E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.456 | TFLOPs: 22.59 | +63: iteration 37550/ 73814 | consumed samples: 19225600 | consumed tokens: 39374028800 | elapsed time per iteration (s): 2.26 | learning rate: 1.089E-04 | global batch size: 512 | lm loss: 2.020558E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.498 | TFLOPs: 23.32 | +63: iteration 37560/ 73814 | consumed samples: 19230720 | consumed tokens: 39384514560 | elapsed time per iteration (s): 2.24 | learning rate: 1.089E-04 | global batch size: 512 | lm loss: 2.032630E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.599 | TFLOPs: 23.53 | +63: iteration 37570/ 73814 | consumed samples: 19235840 | consumed tokens: 39395000320 | elapsed time per iteration (s): 2.24 | learning rate: 1.089E-04 | global batch size: 512 | lm loss: 2.020462E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.394 | TFLOPs: 23.51 | +63: iteration 37580/ 73814 | consumed samples: 19240960 | consumed tokens: 39405486080 | elapsed time per iteration (s): 2.23 | learning rate: 1.088E-04 | global batch size: 512 | lm loss: 2.030066E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.017 | TFLOPs: 23.68 | +63: iteration 37590/ 73814 | consumed samples: 19246080 | consumed tokens: 39415971840 | elapsed time per iteration (s): 2.24 | learning rate: 1.088E-04 | global batch size: 512 | lm loss: 2.026388E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.690 | TFLOPs: 23.54 | +63: iteration 37600/ 73814 | consumed samples: 19251200 | consumed tokens: 39426457600 | elapsed time per iteration (s): 2.23 | learning rate: 1.087E-04 | global batch size: 512 | lm loss: 2.027453E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.693 | TFLOPs: 23.65 | +63: iteration 37610/ 73814 | consumed samples: 19256320 | consumed tokens: 39436943360 | elapsed time per iteration (s): 2.23 | learning rate: 1.087E-04 | global batch size: 512 | lm loss: 2.020661E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.702 | TFLOPs: 23.65 | +63: iteration 37620/ 73814 | consumed samples: 19261440 | consumed tokens: 39447429120 | elapsed time per iteration (s): 2.23 | learning rate: 1.087E-04 | global batch size: 512 | lm loss: 2.037330E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.233 | TFLOPs: 23.60 | +63: iteration 37630/ 73814 | consumed samples: 19266560 | consumed tokens: 39457914880 | elapsed time per iteration (s): 2.23 | learning rate: 1.086E-04 | global batch size: 512 | lm loss: 2.011967E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.989 | TFLOPs: 23.68 | +63: iteration 37640/ 73814 | consumed samples: 19271680 | consumed tokens: 39468400640 | elapsed time per iteration (s): 2.23 | learning rate: 1.086E-04 | global batch size: 512 | lm loss: 2.010263E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.162 | TFLOPs: 23.59 | +63: iteration 37650/ 73814 | consumed samples: 19276800 | consumed tokens: 39478886400 | elapsed time per iteration (s): 2.23 | learning rate: 1.086E-04 | global batch size: 512 | lm loss: 2.009319E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.423 | TFLOPs: 23.62 | +63: iteration 37660/ 73814 | consumed samples: 19281920 | consumed tokens: 39489372160 | elapsed time per iteration (s): 2.24 | learning rate: 1.085E-04 | global batch size: 512 | lm loss: 2.008181E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.980 | TFLOPs: 23.57 | +63: iteration 37670/ 73814 | consumed samples: 19287040 | consumed tokens: 39499857920 | elapsed time per iteration (s): 2.24 | learning rate: 1.085E-04 | global batch size: 512 | lm loss: 2.003301E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.099 | TFLOPs: 23.48 | +63: iteration 37680/ 73814 | consumed samples: 19292160 | consumed tokens: 39510343680 | elapsed time per iteration (s): 2.23 | learning rate: 1.084E-04 | global batch size: 512 | lm loss: 2.012787E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.740 | TFLOPs: 23.65 | +63: iteration 37690/ 73814 | consumed samples: 19297280 | consumed tokens: 39520829440 | elapsed time per iteration (s): 2.24 | learning rate: 1.084E-04 | global batch size: 512 | lm loss: 2.014515E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.147 | TFLOPs: 23.49 | +63: iteration 37700/ 73814 | consumed samples: 19302400 | consumed tokens: 39531315200 | elapsed time per iteration (s): 2.29 | learning rate: 1.084E-04 | global batch size: 512 | lm loss: 2.029884E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.338 | TFLOPs: 22.99 | +63: iteration 37710/ 73814 | consumed samples: 19307520 | consumed tokens: 39541800960 | elapsed time per iteration (s): 2.25 | learning rate: 1.083E-04 | global batch size: 512 | lm loss: 2.015195E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.948 | TFLOPs: 23.47 | +63: iteration 37720/ 73814 | consumed samples: 19312640 | consumed tokens: 39552286720 | elapsed time per iteration (s): 2.23 | learning rate: 1.083E-04 | global batch size: 512 | lm loss: 2.043845E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.456 | TFLOPs: 23.62 | +63: iteration 37730/ 73814 | consumed samples: 19317760 | consumed tokens: 39562772480 | elapsed time per iteration (s): 2.24 | learning rate: 1.082E-04 | global batch size: 512 | lm loss: 2.030227E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.764 | TFLOPs: 23.55 | +63: iteration 37740/ 73814 | consumed samples: 19322880 | consumed tokens: 39573258240 | elapsed time per iteration (s): 2.24 | learning rate: 1.082E-04 | global batch size: 512 | lm loss: 2.020998E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.175 | TFLOPs: 23.49 | +63: iteration 37750/ 73814 | consumed samples: 19328000 | consumed tokens: 39583744000 | elapsed time per iteration (s): 2.26 | learning rate: 1.082E-04 | global batch size: 512 | lm loss: 1.996065E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.072 | TFLOPs: 23.27 | +63: iteration 37760/ 73814 | consumed samples: 19333120 | consumed tokens: 39594229760 | elapsed time per iteration (s): 2.23 | learning rate: 1.081E-04 | global batch size: 512 | lm loss: 2.008961E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.109 | TFLOPs: 23.69 | +63: iteration 37770/ 73814 | consumed samples: 19338240 | consumed tokens: 39604715520 | elapsed time per iteration (s): 2.23 | learning rate: 1.081E-04 | global batch size: 512 | lm loss: 2.019313E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.628 | TFLOPs: 23.64 | +63: iteration 37780/ 73814 | consumed samples: 19343360 | consumed tokens: 39615201280 | elapsed time per iteration (s): 2.25 | learning rate: 1.081E-04 | global batch size: 512 | lm loss: 2.011727E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.014 | TFLOPs: 23.47 | +63: iteration 37790/ 73814 | consumed samples: 19348480 | consumed tokens: 39625687040 | elapsed time per iteration (s): 2.24 | learning rate: 1.080E-04 | global batch size: 512 | lm loss: 2.006116E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.482 | TFLOPs: 23.52 | +63: iteration 37800/ 73814 | consumed samples: 19353600 | consumed tokens: 39636172800 | elapsed time per iteration (s): 2.24 | learning rate: 1.080E-04 | global batch size: 512 | lm loss: 2.002837E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.978 | TFLOPs: 23.57 | +63: iteration 37810/ 73814 | consumed samples: 19358720 | consumed tokens: 39646658560 | elapsed time per iteration (s): 2.27 | learning rate: 1.079E-04 | global batch size: 512 | lm loss: 2.003775E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.254 | TFLOPs: 23.19 | +63: iteration 37820/ 73814 | consumed samples: 19363840 | consumed tokens: 39657144320 | elapsed time per iteration (s): 2.28 | learning rate: 1.079E-04 | global batch size: 512 | lm loss: 2.011594E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.547 | TFLOPs: 23.12 | +63: iteration 37830/ 73814 | consumed samples: 19368960 | consumed tokens: 39667630080 | elapsed time per iteration (s): 2.33 | learning rate: 1.079E-04 | global batch size: 512 | lm loss: 2.012041E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.694 | TFLOPs: 22.62 | +63: iteration 37840/ 73814 | consumed samples: 19374080 | consumed tokens: 39678115840 | elapsed time per iteration (s): 2.38 | learning rate: 1.078E-04 | global batch size: 512 | lm loss: 2.008554E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.527 | TFLOPs: 22.19 | +63: iteration 37850/ 73814 | consumed samples: 19379200 | consumed tokens: 39688601600 | elapsed time per iteration (s): 2.34 | learning rate: 1.078E-04 | global batch size: 512 | lm loss: 1.991363E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.206 | TFLOPs: 22.57 | +63: iteration 37860/ 73814 | consumed samples: 19384320 | consumed tokens: 39699087360 | elapsed time per iteration (s): 2.25 | learning rate: 1.077E-04 | global batch size: 512 | lm loss: 1.988809E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.712 | TFLOPs: 23.44 | +63: iteration 37870/ 73814 | consumed samples: 19389440 | consumed tokens: 39709573120 | elapsed time per iteration (s): 2.25 | learning rate: 1.077E-04 | global batch size: 512 | lm loss: 2.019832E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.730 | TFLOPs: 23.44 | +63: iteration 37880/ 73814 | consumed samples: 19394560 | consumed tokens: 39720058880 | elapsed time per iteration (s): 2.23 | learning rate: 1.077E-04 | global batch size: 512 | lm loss: 2.044324E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.715 | TFLOPs: 23.65 | +63: iteration 37890/ 73814 | consumed samples: 19399680 | consumed tokens: 39730544640 | elapsed time per iteration (s): 2.27 | learning rate: 1.076E-04 | global batch size: 512 | lm loss: 2.012782E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.492 | TFLOPs: 23.21 | +63: iteration 37900/ 73814 | consumed samples: 19404800 | consumed tokens: 39741030400 | elapsed time per iteration (s): 2.36 | learning rate: 1.076E-04 | global batch size: 512 | lm loss: 2.032195E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.927 | TFLOPs: 22.33 | +63: iteration 37910/ 73814 | consumed samples: 19409920 | consumed tokens: 39751516160 | elapsed time per iteration (s): 2.23 | learning rate: 1.075E-04 | global batch size: 512 | lm loss: 2.027340E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.087 | TFLOPs: 23.58 | +63: iteration 37920/ 73814 | consumed samples: 19415040 | consumed tokens: 39762001920 | elapsed time per iteration (s): 2.25 | learning rate: 1.075E-04 | global batch size: 512 | lm loss: 2.018487E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.240 | TFLOPs: 23.39 | +63: iteration 37930/ 73814 | consumed samples: 19420160 | consumed tokens: 39772487680 | elapsed time per iteration (s): 2.25 | learning rate: 1.075E-04 | global batch size: 512 | lm loss: 2.026839E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.147 | TFLOPs: 23.38 | +63: iteration 37940/ 73814 | consumed samples: 19425280 | consumed tokens: 39782973440 | elapsed time per iteration (s): 2.24 | learning rate: 1.074E-04 | global batch size: 512 | lm loss: 2.004864E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.317 | TFLOPs: 23.50 | +63: iteration 37950/ 73814 | consumed samples: 19430400 | consumed tokens: 39793459200 | elapsed time per iteration (s): 2.23 | learning rate: 1.074E-04 | global batch size: 512 | lm loss: 2.002809E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.696 | TFLOPs: 23.65 | +63: iteration 37960/ 73814 | consumed samples: 19435520 | consumed tokens: 39803944960 | elapsed time per iteration (s): 2.23 | learning rate: 1.074E-04 | global batch size: 512 | lm loss: 2.025873E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.538 | TFLOPs: 23.63 | +63: iteration 37970/ 73814 | consumed samples: 19440640 | consumed tokens: 39814430720 | elapsed time per iteration (s): 2.26 | learning rate: 1.073E-04 | global batch size: 512 | lm loss: 2.014225E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.754 | TFLOPs: 23.34 | +63: iteration 37980/ 73814 | consumed samples: 19445760 | consumed tokens: 39824916480 | elapsed time per iteration (s): 2.35 | learning rate: 1.073E-04 | global batch size: 512 | lm loss: 2.006488E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.553 | TFLOPs: 22.40 | +63: iteration 37990/ 73814 | consumed samples: 19450880 | consumed tokens: 39835402240 | elapsed time per iteration (s): 2.23 | learning rate: 1.072E-04 | global batch size: 512 | lm loss: 2.013420E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.482 | TFLOPs: 23.62 | + 0: [2022-12-02 12:00:32,279] [INFO] [logging.py:68:log_dist] [Rank 0] step=38000, skipped=0, lr=[0.00010720022255371527, 0.00010720022255371527, 0.00010720022255371527], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 38000/ 73814 | consumed samples: 19456000 | consumed tokens: 39845888000 | elapsed time per iteration (s): 2.23 | learning rate: 1.072E-04 | global batch size: 512 | lm loss: 2.010639E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.653 | TFLOPs: 23.64 | + 0: steps: 38000 loss: 1.9682 iter time (s): 2.584 samples/sec: 198.161 +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 38000 | lm loss value: 2.001432E+00 | lm loss PPL: 7.399644E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 38010/ 73814 | consumed samples: 19461120 | consumed tokens: 39856373760 | elapsed time per iteration (s): 2.28 | learning rate: 1.072E-04 | global batch size: 512 | lm loss: 2.022785E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.328 | TFLOPs: 23.09 | +63: iteration 38020/ 73814 | consumed samples: 19466240 | consumed tokens: 39866859520 | elapsed time per iteration (s): 2.26 | learning rate: 1.071E-04 | global batch size: 512 | lm loss: 1.998469E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.442 | TFLOPs: 23.31 | +63: iteration 38030/ 73814 | consumed samples: 19471360 | consumed tokens: 39877345280 | elapsed time per iteration (s): 2.23 | learning rate: 1.071E-04 | global batch size: 512 | lm loss: 1.984449E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.419 | TFLOPs: 23.62 | +63: iteration 38040/ 73814 | consumed samples: 19476480 | consumed tokens: 39887831040 | elapsed time per iteration (s): 2.24 | learning rate: 1.070E-04 | global batch size: 512 | lm loss: 2.004330E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.304 | TFLOPs: 23.50 | +63: iteration 38050/ 73814 | consumed samples: 19481600 | consumed tokens: 39898316800 | elapsed time per iteration (s): 2.23 | learning rate: 1.070E-04 | global batch size: 512 | lm loss: 1.991828E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.468 | TFLOPs: 23.62 | +63: iteration 38060/ 73814 | consumed samples: 19486720 | consumed tokens: 39908802560 | elapsed time per iteration (s): 2.28 | learning rate: 1.070E-04 | global batch size: 512 | lm loss: 1.982787E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.926 | TFLOPs: 23.16 | +63: iteration 38070/ 73814 | consumed samples: 19491840 | consumed tokens: 39919288320 | elapsed time per iteration (s): 2.25 | learning rate: 1.069E-04 | global batch size: 512 | lm loss: 2.019898E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.879 | TFLOPs: 23.46 | +63: iteration 38080/ 73814 | consumed samples: 19496960 | consumed tokens: 39929774080 | elapsed time per iteration (s): 2.23 | learning rate: 1.069E-04 | global batch size: 512 | lm loss: 2.020245E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.160 | TFLOPs: 23.59 | +63: iteration 38090/ 73814 | consumed samples: 19502080 | consumed tokens: 39940259840 | elapsed time per iteration (s): 2.27 | learning rate: 1.069E-04 | global batch size: 512 | lm loss: 2.047102E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.756 | TFLOPs: 23.24 | +63: iteration 38100/ 73814 | consumed samples: 19507200 | consumed tokens: 39950745600 | elapsed time per iteration (s): 2.23 | learning rate: 1.068E-04 | global batch size: 512 | lm loss: 2.037952E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.630 | TFLOPs: 23.64 | +63: iteration 38110/ 73814 | consumed samples: 19512320 | consumed tokens: 39961231360 | elapsed time per iteration (s): 2.23 | learning rate: 1.068E-04 | global batch size: 512 | lm loss: 2.028048E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.840 | TFLOPs: 23.66 | +63: iteration 38120/ 73814 | consumed samples: 19517440 | consumed tokens: 39971717120 | elapsed time per iteration (s): 2.23 | learning rate: 1.067E-04 | global batch size: 512 | lm loss: 2.017569E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.262 | TFLOPs: 23.60 | +63: iteration 38130/ 73814 | consumed samples: 19522560 | consumed tokens: 39982202880 | elapsed time per iteration (s): 2.28 | learning rate: 1.067E-04 | global batch size: 512 | lm loss: 2.011850E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.131 | TFLOPs: 23.07 | +63: iteration 38140/ 73814 | consumed samples: 19527680 | consumed tokens: 39992688640 | elapsed time per iteration (s): 2.23 | learning rate: 1.067E-04 | global batch size: 512 | lm loss: 2.012773E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.789 | TFLOPs: 23.66 | +63: iteration 38150/ 73814 | consumed samples: 19532800 | consumed tokens: 40003174400 | elapsed time per iteration (s): 2.23 | learning rate: 1.066E-04 | global batch size: 512 | lm loss: 2.035100E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.902 | TFLOPs: 23.67 | +63: iteration 38160/ 73814 | consumed samples: 19537920 | consumed tokens: 40013660160 | elapsed time per iteration (s): 2.22 | learning rate: 1.066E-04 | global batch size: 512 | lm loss: 2.040051E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.117 | TFLOPs: 23.69 | +63: iteration 38170/ 73814 | consumed samples: 19543040 | consumed tokens: 40024145920 | elapsed time per iteration (s): 2.23 | learning rate: 1.065E-04 | global batch size: 512 | lm loss: 2.017437E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.021 | TFLOPs: 23.68 | +63: iteration 38180/ 73814 | consumed samples: 19548160 | consumed tokens: 40034631680 | elapsed time per iteration (s): 2.24 | learning rate: 1.065E-04 | global batch size: 512 | lm loss: 2.016266E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.998 | TFLOPs: 23.57 | +63: iteration 38190/ 73814 | consumed samples: 19553280 | consumed tokens: 40045117440 | elapsed time per iteration (s): 2.24 | learning rate: 1.065E-04 | global batch size: 512 | lm loss: 2.020439E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.538 | TFLOPs: 23.53 | +63: iteration 38200/ 73814 | consumed samples: 19558400 | consumed tokens: 40055603200 | elapsed time per iteration (s): 2.22 | learning rate: 1.064E-04 | global batch size: 512 | lm loss: 2.006833E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.140 | TFLOPs: 23.69 | +63: iteration 38210/ 73814 | consumed samples: 19563520 | consumed tokens: 40066088960 | elapsed time per iteration (s): 2.24 | learning rate: 1.064E-04 | global batch size: 512 | lm loss: 2.020718E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.342 | TFLOPs: 23.51 | +63: iteration 38220/ 73814 | consumed samples: 19568640 | consumed tokens: 40076574720 | elapsed time per iteration (s): 2.23 | learning rate: 1.063E-04 | global batch size: 512 | lm loss: 2.013840E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.947 | TFLOPs: 23.67 | +63: iteration 38230/ 73814 | consumed samples: 19573760 | consumed tokens: 40087060480 | elapsed time per iteration (s): 2.24 | learning rate: 1.063E-04 | global batch size: 512 | lm loss: 2.033272E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.127 | TFLOPs: 23.48 | +63: iteration 38240/ 73814 | consumed samples: 19578880 | consumed tokens: 40097546240 | elapsed time per iteration (s): 2.24 | learning rate: 1.063E-04 | global batch size: 512 | lm loss: 2.004796E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.539 | TFLOPs: 23.53 | +63: iteration 38250/ 73814 | consumed samples: 19584000 | consumed tokens: 40108032000 | elapsed time per iteration (s): 2.28 | learning rate: 1.062E-04 | global batch size: 512 | lm loss: 2.020836E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.360 | TFLOPs: 23.10 | +63: iteration 38260/ 73814 | consumed samples: 19589120 | consumed tokens: 40118517760 | elapsed time per iteration (s): 2.22 | learning rate: 1.062E-04 | global batch size: 512 | lm loss: 1.998814E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.183 | TFLOPs: 23.70 | +63: iteration 38270/ 73814 | consumed samples: 19594240 | consumed tokens: 40129003520 | elapsed time per iteration (s): 2.23 | learning rate: 1.062E-04 | global batch size: 512 | lm loss: 2.005022E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.952 | TFLOPs: 23.67 | +63: iteration 38280/ 73814 | consumed samples: 19599360 | consumed tokens: 40139489280 | elapsed time per iteration (s): 2.24 | learning rate: 1.061E-04 | global batch size: 512 | lm loss: 2.028524E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.982 | TFLOPs: 23.57 | +63: iteration 38290/ 73814 | consumed samples: 19604480 | consumed tokens: 40149975040 | elapsed time per iteration (s): 2.23 | learning rate: 1.061E-04 | global batch size: 512 | lm loss: 2.017129E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.782 | TFLOPs: 23.65 | +63: iteration 38300/ 73814 | consumed samples: 19609600 | consumed tokens: 40160460800 | elapsed time per iteration (s): 2.22 | learning rate: 1.060E-04 | global batch size: 512 | lm loss: 2.003950E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.462 | TFLOPs: 23.72 | +63: iteration 38310/ 73814 | consumed samples: 19614720 | consumed tokens: 40170946560 | elapsed time per iteration (s): 2.23 | learning rate: 1.060E-04 | global batch size: 512 | lm loss: 2.019404E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.924 | TFLOPs: 23.67 | +63: iteration 38320/ 73814 | consumed samples: 19619840 | consumed tokens: 40181432320 | elapsed time per iteration (s): 2.23 | learning rate: 1.060E-04 | global batch size: 512 | lm loss: 2.004123E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.482 | TFLOPs: 23.62 | +63: iteration 38330/ 73814 | consumed samples: 19624960 | consumed tokens: 40191918080 | elapsed time per iteration (s): 2.40 | learning rate: 1.059E-04 | global batch size: 512 | lm loss: 2.029043E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.554 | TFLOPs: 21.98 | +63: iteration 38340/ 73814 | consumed samples: 19630080 | consumed tokens: 40202403840 | elapsed time per iteration (s): 2.29 | learning rate: 1.059E-04 | global batch size: 512 | lm loss: 2.025316E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.567 | TFLOPs: 23.02 | +63: iteration 38350/ 73814 | consumed samples: 19635200 | consumed tokens: 40212889600 | elapsed time per iteration (s): 2.24 | learning rate: 1.058E-04 | global batch size: 512 | lm loss: 2.024315E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.347 | TFLOPs: 23.51 | +63: iteration 38360/ 73814 | consumed samples: 19640320 | consumed tokens: 40223375360 | elapsed time per iteration (s): 2.39 | learning rate: 1.058E-04 | global batch size: 512 | lm loss: 2.018600E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.319 | TFLOPs: 22.06 | +63: iteration 38370/ 73814 | consumed samples: 19645440 | consumed tokens: 40233861120 | elapsed time per iteration (s): 2.28 | learning rate: 1.058E-04 | global batch size: 512 | lm loss: 2.012326E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.238 | TFLOPs: 23.08 | +63: iteration 38380/ 73814 | consumed samples: 19650560 | consumed tokens: 40244346880 | elapsed time per iteration (s): 2.26 | learning rate: 1.057E-04 | global batch size: 512 | lm loss: 2.004865E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.938 | TFLOPs: 23.36 | +63: iteration 38390/ 73814 | consumed samples: 19655680 | consumed tokens: 40254832640 | elapsed time per iteration (s): 2.28 | learning rate: 1.057E-04 | global batch size: 512 | lm loss: 2.005515E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.659 | TFLOPs: 23.13 | +63: iteration 38400/ 73814 | consumed samples: 19660800 | consumed tokens: 40265318400 | elapsed time per iteration (s): 2.23 | learning rate: 1.057E-04 | global batch size: 512 | lm loss: 1.993526E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.707 | TFLOPs: 23.65 | +63: iteration 38410/ 73814 | consumed samples: 19665920 | consumed tokens: 40275804160 | elapsed time per iteration (s): 2.22 | learning rate: 1.056E-04 | global batch size: 512 | lm loss: 2.009236E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.384 | TFLOPs: 23.72 | +63: iteration 38420/ 73814 | consumed samples: 19671040 | consumed tokens: 40286289920 | elapsed time per iteration (s): 2.23 | learning rate: 1.056E-04 | global batch size: 512 | lm loss: 2.027721E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.092 | TFLOPs: 23.69 | +63: iteration 38430/ 73814 | consumed samples: 19676160 | consumed tokens: 40296775680 | elapsed time per iteration (s): 2.23 | learning rate: 1.055E-04 | global batch size: 512 | lm loss: 2.026441E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.911 | TFLOPs: 23.67 | +63: iteration 38440/ 73814 | consumed samples: 19681280 | consumed tokens: 40307261440 | elapsed time per iteration (s): 2.24 | learning rate: 1.055E-04 | global batch size: 512 | lm loss: 2.004701E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.139 | TFLOPs: 23.49 | +63: iteration 38450/ 73814 | consumed samples: 19686400 | consumed tokens: 40317747200 | elapsed time per iteration (s): 2.25 | learning rate: 1.055E-04 | global batch size: 512 | lm loss: 2.002673E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.247 | TFLOPs: 23.39 | +63: iteration 38460/ 73814 | consumed samples: 19691520 | consumed tokens: 40328232960 | elapsed time per iteration (s): 2.24 | learning rate: 1.054E-04 | global batch size: 512 | lm loss: 2.000763E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.012 | TFLOPs: 23.58 | +63: iteration 38470/ 73814 | consumed samples: 19696640 | consumed tokens: 40338718720 | elapsed time per iteration (s): 2.25 | learning rate: 1.054E-04 | global batch size: 512 | lm loss: 1.986161E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.998 | TFLOPs: 23.47 | +63: iteration 38480/ 73814 | consumed samples: 19701760 | consumed tokens: 40349204480 | elapsed time per iteration (s): 2.25 | learning rate: 1.053E-04 | global batch size: 512 | lm loss: 2.019182E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.033 | TFLOPs: 23.47 | +63: iteration 38490/ 73814 | consumed samples: 19706880 | consumed tokens: 40359690240 | elapsed time per iteration (s): 2.24 | learning rate: 1.053E-04 | global batch size: 512 | lm loss: 2.024874E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.662 | TFLOPs: 23.54 | +63: iteration 38500/ 73814 | consumed samples: 19712000 | consumed tokens: 40370176000 | elapsed time per iteration (s): 2.26 | learning rate: 1.053E-04 | global batch size: 512 | lm loss: 1.999850E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.827 | TFLOPs: 23.35 | +63: iteration 38510/ 73814 | consumed samples: 19717120 | consumed tokens: 40380661760 | elapsed time per iteration (s): 2.22 | learning rate: 1.052E-04 | global batch size: 512 | lm loss: 2.002631E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.315 | TFLOPs: 23.71 | +63: iteration 38520/ 73814 | consumed samples: 19722240 | consumed tokens: 40391147520 | elapsed time per iteration (s): 2.22 | learning rate: 1.052E-04 | global batch size: 512 | lm loss: 2.039082E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.275 | TFLOPs: 23.71 | +63: iteration 38530/ 73814 | consumed samples: 19727360 | consumed tokens: 40401633280 | elapsed time per iteration (s): 2.23 | learning rate: 1.052E-04 | global batch size: 512 | lm loss: 2.004976E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.735 | TFLOPs: 23.65 | +63: iteration 38540/ 73814 | consumed samples: 19732480 | consumed tokens: 40412119040 | elapsed time per iteration (s): 2.25 | learning rate: 1.051E-04 | global batch size: 512 | lm loss: 2.007264E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.809 | TFLOPs: 23.45 | +63: iteration 38550/ 73814 | consumed samples: 19737600 | consumed tokens: 40422604800 | elapsed time per iteration (s): 2.24 | learning rate: 1.051E-04 | global batch size: 512 | lm loss: 2.014836E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.374 | TFLOPs: 23.51 | +63: iteration 38560/ 73814 | consumed samples: 19742720 | consumed tokens: 40433090560 | elapsed time per iteration (s): 2.39 | learning rate: 1.050E-04 | global batch size: 512 | lm loss: 2.040506E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.812 | TFLOPs: 22.01 | +63: iteration 38570/ 73814 | consumed samples: 19747840 | consumed tokens: 40443576320 | elapsed time per iteration (s): 2.23 | learning rate: 1.050E-04 | global batch size: 512 | lm loss: 1.988490E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.067 | TFLOPs: 23.68 | +63: iteration 38580/ 73814 | consumed samples: 19752960 | consumed tokens: 40454062080 | elapsed time per iteration (s): 2.27 | learning rate: 1.050E-04 | global batch size: 512 | lm loss: 1.999521E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.903 | TFLOPs: 23.26 | +63: iteration 38590/ 73814 | consumed samples: 19758080 | consumed tokens: 40464547840 | elapsed time per iteration (s): 2.31 | learning rate: 1.049E-04 | global batch size: 512 | lm loss: 2.007405E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.182 | TFLOPs: 22.77 | +63: iteration 38600/ 73814 | consumed samples: 19763200 | consumed tokens: 40475033600 | elapsed time per iteration (s): 2.38 | learning rate: 1.049E-04 | global batch size: 512 | lm loss: 2.012466E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.121 | TFLOPs: 22.15 | +63: iteration 38610/ 73814 | consumed samples: 19768320 | consumed tokens: 40485519360 | elapsed time per iteration (s): 2.52 | learning rate: 1.048E-04 | global batch size: 512 | lm loss: 2.027291E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 203.382 | TFLOPs: 20.94 | +63: iteration 38620/ 73814 | consumed samples: 19773440 | consumed tokens: 40496005120 | elapsed time per iteration (s): 2.24 | learning rate: 1.048E-04 | global batch size: 512 | lm loss: 1.994226E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.580 | TFLOPs: 23.53 | +63: iteration 38630/ 73814 | consumed samples: 19778560 | consumed tokens: 40506490880 | elapsed time per iteration (s): 2.23 | learning rate: 1.048E-04 | global batch size: 512 | lm loss: 2.021887E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.579 | TFLOPs: 23.63 | +63: iteration 38640/ 73814 | consumed samples: 19783680 | consumed tokens: 40516976640 | elapsed time per iteration (s): 2.42 | learning rate: 1.047E-04 | global batch size: 512 | lm loss: 2.018859E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.780 | TFLOPs: 21.80 | +63: iteration 38650/ 73814 | consumed samples: 19788800 | consumed tokens: 40527462400 | elapsed time per iteration (s): 2.23 | learning rate: 1.047E-04 | global batch size: 512 | lm loss: 2.025572E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.790 | TFLOPs: 23.66 | +63: iteration 38660/ 73814 | consumed samples: 19793920 | consumed tokens: 40537948160 | elapsed time per iteration (s): 2.26 | learning rate: 1.046E-04 | global batch size: 512 | lm loss: 2.007494E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.206 | TFLOPs: 23.29 | +63: iteration 38670/ 73814 | consumed samples: 19799040 | consumed tokens: 40548433920 | elapsed time per iteration (s): 2.24 | learning rate: 1.046E-04 | global batch size: 512 | lm loss: 2.024991E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.962 | TFLOPs: 23.57 | +63: iteration 38680/ 73814 | consumed samples: 19804160 | consumed tokens: 40558919680 | elapsed time per iteration (s): 2.23 | learning rate: 1.046E-04 | global batch size: 512 | lm loss: 2.007325E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.683 | TFLOPs: 23.64 | +63: iteration 38690/ 73814 | consumed samples: 19809280 | consumed tokens: 40569405440 | elapsed time per iteration (s): 2.23 | learning rate: 1.045E-04 | global batch size: 512 | lm loss: 2.019668E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.919 | TFLOPs: 23.67 | +63: iteration 38700/ 73814 | consumed samples: 19814400 | consumed tokens: 40579891200 | elapsed time per iteration (s): 2.45 | learning rate: 1.045E-04 | global batch size: 512 | lm loss: 2.011996E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.007 | TFLOPs: 21.52 | +63: iteration 38710/ 73814 | consumed samples: 19819520 | consumed tokens: 40590376960 | elapsed time per iteration (s): 2.23 | learning rate: 1.045E-04 | global batch size: 512 | lm loss: 2.006597E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.748 | TFLOPs: 23.65 | +63: iteration 38720/ 73814 | consumed samples: 19824640 | consumed tokens: 40600862720 | elapsed time per iteration (s): 2.23 | learning rate: 1.044E-04 | global batch size: 512 | lm loss: 1.996606E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.985 | TFLOPs: 23.68 | +63: iteration 38730/ 73814 | consumed samples: 19829760 | consumed tokens: 40611348480 | elapsed time per iteration (s): 2.23 | learning rate: 1.044E-04 | global batch size: 512 | lm loss: 2.019252E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.041 | TFLOPs: 23.68 | +63: iteration 38740/ 73814 | consumed samples: 19834880 | consumed tokens: 40621834240 | elapsed time per iteration (s): 2.25 | learning rate: 1.043E-04 | global batch size: 512 | lm loss: 1.994566E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.044 | TFLOPs: 23.48 | +63: iteration 38750/ 73814 | consumed samples: 19840000 | consumed tokens: 40632320000 | elapsed time per iteration (s): 2.48 | learning rate: 1.043E-04 | global batch size: 512 | lm loss: 1.998994E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.077 | TFLOPs: 21.21 | +63: iteration 38760/ 73814 | consumed samples: 19845120 | consumed tokens: 40642805760 | elapsed time per iteration (s): 2.32 | learning rate: 1.043E-04 | global batch size: 512 | lm loss: 2.011633E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.817 | TFLOPs: 22.73 | +63: iteration 38770/ 73814 | consumed samples: 19850240 | consumed tokens: 40653291520 | elapsed time per iteration (s): 2.24 | learning rate: 1.042E-04 | global batch size: 512 | lm loss: 2.020134E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.152 | TFLOPs: 23.49 | +63: iteration 38780/ 73814 | consumed samples: 19855360 | consumed tokens: 40663777280 | elapsed time per iteration (s): 2.23 | learning rate: 1.042E-04 | global batch size: 512 | lm loss: 2.024717E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.161 | TFLOPs: 23.59 | +63: iteration 38790/ 73814 | consumed samples: 19860480 | consumed tokens: 40674263040 | elapsed time per iteration (s): 2.30 | learning rate: 1.041E-04 | global batch size: 512 | lm loss: 2.009478E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.666 | TFLOPs: 22.92 | +63: iteration 38800/ 73814 | consumed samples: 19865600 | consumed tokens: 40684748800 | elapsed time per iteration (s): 2.25 | learning rate: 1.041E-04 | global batch size: 512 | lm loss: 2.008575E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.404 | TFLOPs: 23.41 | +63: iteration 38810/ 73814 | consumed samples: 19870720 | consumed tokens: 40695234560 | elapsed time per iteration (s): 2.23 | learning rate: 1.041E-04 | global batch size: 512 | lm loss: 2.012928E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.764 | TFLOPs: 23.65 | +63: iteration 38820/ 73814 | consumed samples: 19875840 | consumed tokens: 40705720320 | elapsed time per iteration (s): 2.23 | learning rate: 1.040E-04 | global batch size: 512 | lm loss: 2.003367E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.059 | TFLOPs: 23.68 | +63: iteration 38830/ 73814 | consumed samples: 19880960 | consumed tokens: 40716206080 | elapsed time per iteration (s): 2.23 | learning rate: 1.040E-04 | global batch size: 512 | lm loss: 1.994633E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.324 | TFLOPs: 23.61 | +63: iteration 38840/ 73814 | consumed samples: 19886080 | consumed tokens: 40726691840 | elapsed time per iteration (s): 2.22 | learning rate: 1.040E-04 | global batch size: 512 | lm loss: 2.009316E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.131 | TFLOPs: 23.69 | +63: iteration 38850/ 73814 | consumed samples: 19891200 | consumed tokens: 40737177600 | elapsed time per iteration (s): 2.23 | learning rate: 1.039E-04 | global batch size: 512 | lm loss: 2.026482E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.680 | TFLOPs: 23.64 | +63: iteration 38860/ 73814 | consumed samples: 19896320 | consumed tokens: 40747663360 | elapsed time per iteration (s): 2.22 | learning rate: 1.039E-04 | global batch size: 512 | lm loss: 1.997668E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.530 | TFLOPs: 23.73 | +63: iteration 38870/ 73814 | consumed samples: 19901440 | consumed tokens: 40758149120 | elapsed time per iteration (s): 2.23 | learning rate: 1.038E-04 | global batch size: 512 | lm loss: 1.997100E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.730 | TFLOPs: 23.65 | +63: iteration 38880/ 73814 | consumed samples: 19906560 | consumed tokens: 40768634880 | elapsed time per iteration (s): 2.42 | learning rate: 1.038E-04 | global batch size: 512 | lm loss: 2.022183E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.433 | TFLOPs: 21.77 | +63: iteration 38890/ 73814 | consumed samples: 19911680 | consumed tokens: 40779120640 | elapsed time per iteration (s): 2.26 | learning rate: 1.038E-04 | global batch size: 512 | lm loss: 2.034320E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.171 | TFLOPs: 23.28 | +63: iteration 38900/ 73814 | consumed samples: 19916800 | consumed tokens: 40789606400 | elapsed time per iteration (s): 2.42 | learning rate: 1.037E-04 | global batch size: 512 | lm loss: 2.002167E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.669 | TFLOPs: 21.79 | +63: iteration 38910/ 73814 | consumed samples: 19921920 | consumed tokens: 40800092160 | elapsed time per iteration (s): 4.42 | learning rate: 1.037E-04 | global batch size: 512 | lm loss: 2.002620E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 115.857 | TFLOPs: 11.93 | +63: iteration 38920/ 73814 | consumed samples: 19927040 | consumed tokens: 40810577920 | elapsed time per iteration (s): 2.30 | learning rate: 1.036E-04 | global batch size: 512 | lm loss: 1.995474E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.366 | TFLOPs: 22.89 | +63: iteration 38930/ 73814 | consumed samples: 19932160 | consumed tokens: 40821063680 | elapsed time per iteration (s): 2.57 | learning rate: 1.036E-04 | global batch size: 512 | lm loss: 1.999519E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.927 | TFLOPs: 20.48 | +63: iteration 38940/ 73814 | consumed samples: 19937280 | consumed tokens: 40831549440 | elapsed time per iteration (s): 2.68 | learning rate: 1.036E-04 | global batch size: 512 | lm loss: 2.029306E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 191.085 | TFLOPs: 19.67 | +63: iteration 38950/ 73814 | consumed samples: 19942400 | consumed tokens: 40842035200 | elapsed time per iteration (s): 2.45 | learning rate: 1.035E-04 | global batch size: 512 | lm loss: 1.994845E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.169 | TFLOPs: 21.53 | +63: iteration 38960/ 73814 | consumed samples: 19947520 | consumed tokens: 40852520960 | elapsed time per iteration (s): 2.29 | learning rate: 1.035E-04 | global batch size: 512 | lm loss: 2.017513E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.993 | TFLOPs: 23.06 | +63: iteration 38970/ 73814 | consumed samples: 19952640 | consumed tokens: 40863006720 | elapsed time per iteration (s): 2.66 | learning rate: 1.035E-04 | global batch size: 512 | lm loss: 2.005376E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 192.285 | TFLOPs: 19.79 | +63: iteration 38980/ 73814 | consumed samples: 19957760 | consumed tokens: 40873492480 | elapsed time per iteration (s): 2.34 | learning rate: 1.034E-04 | global batch size: 512 | lm loss: 2.021166E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.091 | TFLOPs: 22.55 | +63: iteration 38990/ 73814 | consumed samples: 19962880 | consumed tokens: 40883978240 | elapsed time per iteration (s): 2.29 | learning rate: 1.034E-04 | global batch size: 512 | lm loss: 2.014668E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.992 | TFLOPs: 23.06 | +63: iteration 39000/ 73814 | consumed samples: 19968000 | consumed tokens: 40894464000 | elapsed time per iteration (s): 2.25 | learning rate: 1.033E-04 | global batch size: 512 | lm loss: 1.992418E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.060 | TFLOPs: 23.37 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 39000 | lm loss value: 2.008158E+00 | lm loss PPL: 7.449586E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 39010/ 73814 | consumed samples: 19973120 | consumed tokens: 40904949760 | elapsed time per iteration (s): 2.29 | learning rate: 1.033E-04 | global batch size: 512 | lm loss: 2.020651E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.312 | TFLOPs: 22.99 | +63: iteration 39020/ 73814 | consumed samples: 19978240 | consumed tokens: 40915435520 | elapsed time per iteration (s): 2.24 | learning rate: 1.033E-04 | global batch size: 512 | lm loss: 2.025120E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.205 | TFLOPs: 23.49 | +63: iteration 39030/ 73814 | consumed samples: 19983360 | consumed tokens: 40925921280 | elapsed time per iteration (s): 2.23 | learning rate: 1.032E-04 | global batch size: 512 | lm loss: 2.000152E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.006 | TFLOPs: 23.68 | +63: iteration 39040/ 73814 | consumed samples: 19988480 | consumed tokens: 40936407040 | elapsed time per iteration (s): 2.25 | learning rate: 1.032E-04 | global batch size: 512 | lm loss: 1.993711E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.823 | TFLOPs: 23.45 | +63: iteration 39050/ 73814 | consumed samples: 19993600 | consumed tokens: 40946892800 | elapsed time per iteration (s): 2.24 | learning rate: 1.031E-04 | global batch size: 512 | lm loss: 2.020287E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.761 | TFLOPs: 23.55 | +63: iteration 39060/ 73814 | consumed samples: 19998720 | consumed tokens: 40957378560 | elapsed time per iteration (s): 2.24 | learning rate: 1.031E-04 | global batch size: 512 | lm loss: 2.013586E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.391 | TFLOPs: 23.51 | +63: iteration 39070/ 73814 | consumed samples: 20003840 | consumed tokens: 40967864320 | elapsed time per iteration (s): 2.26 | learning rate: 1.031E-04 | global batch size: 512 | lm loss: 2.011186E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.804 | TFLOPs: 23.35 | +63: iteration 39080/ 73814 | consumed samples: 20008960 | consumed tokens: 40978350080 | elapsed time per iteration (s): 2.39 | learning rate: 1.030E-04 | global batch size: 512 | lm loss: 2.016851E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.541 | TFLOPs: 22.09 | +63: iteration 39090/ 73814 | consumed samples: 20014080 | consumed tokens: 40988835840 | elapsed time per iteration (s): 2.24 | learning rate: 1.030E-04 | global batch size: 512 | lm loss: 2.024199E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.609 | TFLOPs: 23.53 | +63: iteration 39100/ 73814 | consumed samples: 20019200 | consumed tokens: 40999321600 | elapsed time per iteration (s): 2.24 | learning rate: 1.030E-04 | global batch size: 512 | lm loss: 2.011460E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.302 | TFLOPs: 23.50 | +63: iteration 39110/ 73814 | consumed samples: 20024320 | consumed tokens: 41009807360 | elapsed time per iteration (s): 2.26 | learning rate: 1.029E-04 | global batch size: 512 | lm loss: 2.015477E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.764 | TFLOPs: 23.34 | +63: iteration 39120/ 73814 | consumed samples: 20029440 | consumed tokens: 41020293120 | elapsed time per iteration (s): 2.25 | learning rate: 1.029E-04 | global batch size: 512 | lm loss: 1.996274E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.569 | TFLOPs: 23.43 | +63: iteration 39130/ 73814 | consumed samples: 20034560 | consumed tokens: 41030778880 | elapsed time per iteration (s): 2.22 | learning rate: 1.028E-04 | global batch size: 512 | lm loss: 2.016540E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.275 | TFLOPs: 23.71 | +63: iteration 39140/ 73814 | consumed samples: 20039680 | consumed tokens: 41041264640 | elapsed time per iteration (s): 2.23 | learning rate: 1.028E-04 | global batch size: 512 | lm loss: 2.005380E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.702 | TFLOPs: 23.65 | +63: iteration 39150/ 73814 | consumed samples: 20044800 | consumed tokens: 41051750400 | elapsed time per iteration (s): 2.33 | learning rate: 1.028E-04 | global batch size: 512 | lm loss: 1.994496E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.421 | TFLOPs: 22.59 | +63: iteration 39160/ 73814 | consumed samples: 20049920 | consumed tokens: 41062236160 | elapsed time per iteration (s): 2.22 | learning rate: 1.027E-04 | global batch size: 512 | lm loss: 1.998611E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.213 | TFLOPs: 23.70 | +63: iteration 39170/ 73814 | consumed samples: 20055040 | consumed tokens: 41072721920 | elapsed time per iteration (s): 2.40 | learning rate: 1.027E-04 | global batch size: 512 | lm loss: 2.008698E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.901 | TFLOPs: 21.92 | +63: iteration 39180/ 73814 | consumed samples: 20060160 | consumed tokens: 41083207680 | elapsed time per iteration (s): 2.36 | learning rate: 1.026E-04 | global batch size: 512 | lm loss: 1.999467E+00 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.873 | TFLOPs: 22.33 | +63: iteration 39190/ 73814 | consumed samples: 20065280 | consumed tokens: 41093693440 | elapsed time per iteration (s): 2.23 | learning rate: 1.026E-04 | global batch size: 512 | lm loss: 1.998647E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.100 | TFLOPs: 23.69 | +63: iteration 39200/ 73814 | consumed samples: 20070400 | consumed tokens: 41104179200 | elapsed time per iteration (s): 2.23 | learning rate: 1.026E-04 | global batch size: 512 | lm loss: 2.005437E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.992 | TFLOPs: 23.68 | +63: iteration 39210/ 73814 | consumed samples: 20075520 | consumed tokens: 41114664960 | elapsed time per iteration (s): 2.45 | learning rate: 1.025E-04 | global batch size: 512 | lm loss: 1.996532E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.576 | TFLOPs: 21.47 | +63: iteration 39220/ 73814 | consumed samples: 20080640 | consumed tokens: 41125150720 | elapsed time per iteration (s): 2.27 | learning rate: 1.025E-04 | global batch size: 512 | lm loss: 2.004888E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.988 | TFLOPs: 23.26 | +63: iteration 39230/ 73814 | consumed samples: 20085760 | consumed tokens: 41135636480 | elapsed time per iteration (s): 2.23 | learning rate: 1.024E-04 | global batch size: 512 | lm loss: 2.018526E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.528 | TFLOPs: 23.63 | +63: iteration 39240/ 73814 | consumed samples: 20090880 | consumed tokens: 41146122240 | elapsed time per iteration (s): 2.40 | learning rate: 1.024E-04 | global batch size: 512 | lm loss: 2.009765E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.982 | TFLOPs: 21.93 | +63: iteration 39250/ 73814 | consumed samples: 20096000 | consumed tokens: 41156608000 | elapsed time per iteration (s): 2.28 | learning rate: 1.024E-04 | global batch size: 512 | lm loss: 2.032931E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.609 | TFLOPs: 23.12 | +63: iteration 39260/ 73814 | consumed samples: 20101120 | consumed tokens: 41167093760 | elapsed time per iteration (s): 2.25 | learning rate: 1.023E-04 | global batch size: 512 | lm loss: 2.002738E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.572 | TFLOPs: 23.43 | +63: iteration 39270/ 73814 | consumed samples: 20106240 | consumed tokens: 41177579520 | elapsed time per iteration (s): 2.28 | learning rate: 1.023E-04 | global batch size: 512 | lm loss: 1.993633E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.298 | TFLOPs: 23.09 | +63: iteration 39280/ 73814 | consumed samples: 20111360 | consumed tokens: 41188065280 | elapsed time per iteration (s): 2.24 | learning rate: 1.023E-04 | global batch size: 512 | lm loss: 2.010250E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.860 | TFLOPs: 23.56 | +63: iteration 39290/ 73814 | consumed samples: 20116480 | consumed tokens: 41198551040 | elapsed time per iteration (s): 2.25 | learning rate: 1.022E-04 | global batch size: 512 | lm loss: 1.999661E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.635 | TFLOPs: 23.43 | +63: iteration 39300/ 73814 | consumed samples: 20121600 | consumed tokens: 41209036800 | elapsed time per iteration (s): 2.25 | learning rate: 1.022E-04 | global batch size: 512 | lm loss: 2.032196E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.450 | TFLOPs: 23.41 | +63: iteration 39310/ 73814 | consumed samples: 20126720 | consumed tokens: 41219522560 | elapsed time per iteration (s): 2.24 | learning rate: 1.021E-04 | global batch size: 512 | lm loss: 2.002788E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.896 | TFLOPs: 23.56 | +63: iteration 39320/ 73814 | consumed samples: 20131840 | consumed tokens: 41230008320 | elapsed time per iteration (s): 2.25 | learning rate: 1.021E-04 | global batch size: 512 | lm loss: 1.997159E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.050 | TFLOPs: 23.48 | +63: iteration 39330/ 73814 | consumed samples: 20136960 | consumed tokens: 41240494080 | elapsed time per iteration (s): 2.23 | learning rate: 1.021E-04 | global batch size: 512 | lm loss: 2.014143E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.316 | TFLOPs: 23.61 | +63: iteration 39340/ 73814 | consumed samples: 20142080 | consumed tokens: 41250979840 | elapsed time per iteration (s): 2.30 | learning rate: 1.020E-04 | global batch size: 512 | lm loss: 2.012498E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.376 | TFLOPs: 22.89 | +63: iteration 39350/ 73814 | consumed samples: 20147200 | consumed tokens: 41261465600 | elapsed time per iteration (s): 2.23 | learning rate: 1.020E-04 | global batch size: 512 | lm loss: 2.003753E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.982 | TFLOPs: 23.68 | +63: iteration 39360/ 73814 | consumed samples: 20152320 | consumed tokens: 41271951360 | elapsed time per iteration (s): 2.23 | learning rate: 1.019E-04 | global batch size: 512 | lm loss: 2.011197E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.204 | TFLOPs: 23.60 | +63: iteration 39370/ 73814 | consumed samples: 20157440 | consumed tokens: 41282437120 | elapsed time per iteration (s): 2.25 | learning rate: 1.019E-04 | global batch size: 512 | lm loss: 2.009130E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.054 | TFLOPs: 23.48 | +63: iteration 39380/ 73814 | consumed samples: 20162560 | consumed tokens: 41292922880 | elapsed time per iteration (s): 2.25 | learning rate: 1.019E-04 | global batch size: 512 | lm loss: 2.027899E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.589 | TFLOPs: 23.43 | +63: iteration 39390/ 73814 | consumed samples: 20167680 | consumed tokens: 41303408640 | elapsed time per iteration (s): 2.24 | learning rate: 1.018E-04 | global batch size: 512 | lm loss: 2.019197E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.029 | TFLOPs: 23.58 | +63: iteration 39400/ 73814 | consumed samples: 20172800 | consumed tokens: 41313894400 | elapsed time per iteration (s): 2.23 | learning rate: 1.018E-04 | global batch size: 512 | lm loss: 2.012211E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.918 | TFLOPs: 23.67 | +63: iteration 39410/ 73814 | consumed samples: 20177920 | consumed tokens: 41324380160 | elapsed time per iteration (s): 2.31 | learning rate: 1.018E-04 | global batch size: 512 | lm loss: 2.010450E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.840 | TFLOPs: 22.84 | +63: iteration 39420/ 73814 | consumed samples: 20183040 | consumed tokens: 41334865920 | elapsed time per iteration (s): 2.23 | learning rate: 1.017E-04 | global batch size: 512 | lm loss: 2.002308E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.798 | TFLOPs: 23.66 | +63: iteration 39430/ 73814 | consumed samples: 20188160 | consumed tokens: 41345351680 | elapsed time per iteration (s): 2.24 | learning rate: 1.017E-04 | global batch size: 512 | lm loss: 2.015046E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.691 | TFLOPs: 23.54 | +63: iteration 39440/ 73814 | consumed samples: 20193280 | consumed tokens: 41355837440 | elapsed time per iteration (s): 2.24 | learning rate: 1.016E-04 | global batch size: 512 | lm loss: 2.014597E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.364 | TFLOPs: 23.51 | +63: iteration 39450/ 73814 | consumed samples: 20198400 | consumed tokens: 41366323200 | elapsed time per iteration (s): 2.23 | learning rate: 1.016E-04 | global batch size: 512 | lm loss: 1.981023E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.909 | TFLOPs: 23.67 | +63: iteration 39460/ 73814 | consumed samples: 20203520 | consumed tokens: 41376808960 | elapsed time per iteration (s): 2.24 | learning rate: 1.016E-04 | global batch size: 512 | lm loss: 2.007751E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.069 | TFLOPs: 23.58 | +63: iteration 39470/ 73814 | consumed samples: 20208640 | consumed tokens: 41387294720 | elapsed time per iteration (s): 2.24 | learning rate: 1.015E-04 | global batch size: 512 | lm loss: 1.997946E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.683 | TFLOPs: 23.54 | +63: iteration 39480/ 73814 | consumed samples: 20213760 | consumed tokens: 41397780480 | elapsed time per iteration (s): 2.24 | learning rate: 1.015E-04 | global batch size: 512 | lm loss: 1.996368E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.354 | TFLOPs: 23.51 | +63: iteration 39490/ 73814 | consumed samples: 20218880 | consumed tokens: 41408266240 | elapsed time per iteration (s): 2.23 | learning rate: 1.014E-04 | global batch size: 512 | lm loss: 2.001321E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.458 | TFLOPs: 23.62 | +63: iteration 39500/ 73814 | consumed samples: 20224000 | consumed tokens: 41418752000 | elapsed time per iteration (s): 2.22 | learning rate: 1.014E-04 | global batch size: 512 | lm loss: 2.008534E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.198 | TFLOPs: 23.70 | +63: iteration 39510/ 73814 | consumed samples: 20229120 | consumed tokens: 41429237760 | elapsed time per iteration (s): 2.23 | learning rate: 1.014E-04 | global batch size: 512 | lm loss: 1.987154E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.909 | TFLOPs: 23.67 | +63: iteration 39520/ 73814 | consumed samples: 20234240 | consumed tokens: 41439723520 | elapsed time per iteration (s): 2.23 | learning rate: 1.013E-04 | global batch size: 512 | lm loss: 2.007630E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.324 | TFLOPs: 23.61 | +63: iteration 39530/ 73814 | consumed samples: 20239360 | consumed tokens: 41450209280 | elapsed time per iteration (s): 2.24 | learning rate: 1.013E-04 | global batch size: 512 | lm loss: 1.985476E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.748 | TFLOPs: 23.55 | +63: iteration 39540/ 73814 | consumed samples: 20244480 | consumed tokens: 41460695040 | elapsed time per iteration (s): 2.23 | learning rate: 1.013E-04 | global batch size: 512 | lm loss: 1.990938E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.800 | TFLOPs: 23.66 | +63: iteration 39550/ 73814 | consumed samples: 20249600 | consumed tokens: 41471180800 | elapsed time per iteration (s): 2.44 | learning rate: 1.012E-04 | global batch size: 512 | lm loss: 2.003914E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.198 | TFLOPs: 21.64 | +63: iteration 39560/ 73814 | consumed samples: 20254720 | consumed tokens: 41481666560 | elapsed time per iteration (s): 2.25 | learning rate: 1.012E-04 | global batch size: 512 | lm loss: 1.998207E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.848 | TFLOPs: 23.46 | +63: iteration 39570/ 73814 | consumed samples: 20259840 | consumed tokens: 41492152320 | elapsed time per iteration (s): 2.23 | learning rate: 1.011E-04 | global batch size: 512 | lm loss: 2.008170E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.925 | TFLOPs: 23.67 | +63: iteration 39580/ 73814 | consumed samples: 20264960 | consumed tokens: 41502638080 | elapsed time per iteration (s): 2.23 | learning rate: 1.011E-04 | global batch size: 512 | lm loss: 2.006172E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.283 | TFLOPs: 23.60 | +63: iteration 39590/ 73814 | consumed samples: 20270080 | consumed tokens: 41513123840 | elapsed time per iteration (s): 2.23 | learning rate: 1.011E-04 | global batch size: 512 | lm loss: 2.016922E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.390 | TFLOPs: 23.61 | +63: iteration 39600/ 73814 | consumed samples: 20275200 | consumed tokens: 41523609600 | elapsed time per iteration (s): 2.24 | learning rate: 1.010E-04 | global batch size: 512 | lm loss: 1.996249E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.320 | TFLOPs: 23.50 | +63: iteration 39610/ 73814 | consumed samples: 20280320 | consumed tokens: 41534095360 | elapsed time per iteration (s): 2.36 | learning rate: 1.010E-04 | global batch size: 512 | lm loss: 2.009051E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.698 | TFLOPs: 22.31 | +63: iteration 39620/ 73814 | consumed samples: 20285440 | consumed tokens: 41544581120 | elapsed time per iteration (s): 2.23 | learning rate: 1.009E-04 | global batch size: 512 | lm loss: 2.020468E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.175 | TFLOPs: 23.59 | +63: iteration 39630/ 73814 | consumed samples: 20290560 | consumed tokens: 41555066880 | elapsed time per iteration (s): 2.23 | learning rate: 1.009E-04 | global batch size: 512 | lm loss: 1.999275E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.004 | TFLOPs: 23.68 | +63: iteration 39640/ 73814 | consumed samples: 20295680 | consumed tokens: 41565552640 | elapsed time per iteration (s): 2.24 | learning rate: 1.009E-04 | global batch size: 512 | lm loss: 2.015351E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.061 | TFLOPs: 23.58 | +63: iteration 39650/ 73814 | consumed samples: 20300800 | consumed tokens: 41576038400 | elapsed time per iteration (s): 2.24 | learning rate: 1.008E-04 | global batch size: 512 | lm loss: 2.002511E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.123 | TFLOPs: 23.48 | +63: iteration 39660/ 73814 | consumed samples: 20305920 | consumed tokens: 41586524160 | elapsed time per iteration (s): 2.22 | learning rate: 1.008E-04 | global batch size: 512 | lm loss: 2.012754E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.367 | TFLOPs: 23.72 | +63: iteration 39670/ 73814 | consumed samples: 20311040 | consumed tokens: 41597009920 | elapsed time per iteration (s): 2.23 | learning rate: 1.008E-04 | global batch size: 512 | lm loss: 2.024163E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.040 | TFLOPs: 23.68 | +63: iteration 39680/ 73814 | consumed samples: 20316160 | consumed tokens: 41607495680 | elapsed time per iteration (s): 2.23 | learning rate: 1.007E-04 | global batch size: 512 | lm loss: 1.998868E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.946 | TFLOPs: 23.67 | +63: iteration 39690/ 73814 | consumed samples: 20321280 | consumed tokens: 41617981440 | elapsed time per iteration (s): 2.31 | learning rate: 1.007E-04 | global batch size: 512 | lm loss: 2.012947E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.268 | TFLOPs: 22.78 | +63: iteration 39700/ 73814 | consumed samples: 20326400 | consumed tokens: 41628467200 | elapsed time per iteration (s): 2.23 | learning rate: 1.006E-04 | global batch size: 512 | lm loss: 1.984805E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.694 | TFLOPs: 23.65 | +63: iteration 39710/ 73814 | consumed samples: 20331520 | consumed tokens: 41638952960 | elapsed time per iteration (s): 2.25 | learning rate: 1.006E-04 | global batch size: 512 | lm loss: 2.014843E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.039 | TFLOPs: 23.48 | +63: iteration 39720/ 73814 | consumed samples: 20336640 | consumed tokens: 41649438720 | elapsed time per iteration (s): 2.23 | learning rate: 1.006E-04 | global batch size: 512 | lm loss: 2.000544E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.952 | TFLOPs: 23.67 | +63: iteration 39730/ 73814 | consumed samples: 20341760 | consumed tokens: 41659924480 | elapsed time per iteration (s): 2.23 | learning rate: 1.005E-04 | global batch size: 512 | lm loss: 2.023591E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.611 | TFLOPs: 23.64 | +63: iteration 39740/ 73814 | consumed samples: 20346880 | consumed tokens: 41670410240 | elapsed time per iteration (s): 2.29 | learning rate: 1.005E-04 | global batch size: 512 | lm loss: 2.022496E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.717 | TFLOPs: 23.03 | +63: iteration 39750/ 73814 | consumed samples: 20352000 | consumed tokens: 41680896000 | elapsed time per iteration (s): 2.26 | learning rate: 1.004E-04 | global batch size: 512 | lm loss: 1.985043E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.701 | TFLOPs: 23.34 | +63: iteration 39760/ 73814 | consumed samples: 20357120 | consumed tokens: 41691381760 | elapsed time per iteration (s): 2.25 | learning rate: 1.004E-04 | global batch size: 512 | lm loss: 1.983818E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.443 | TFLOPs: 23.41 | +63: iteration 39770/ 73814 | consumed samples: 20362240 | consumed tokens: 41701867520 | elapsed time per iteration (s): 2.24 | learning rate: 1.004E-04 | global batch size: 512 | lm loss: 2.015133E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.779 | TFLOPs: 23.55 | +63: iteration 39780/ 73814 | consumed samples: 20367360 | consumed tokens: 41712353280 | elapsed time per iteration (s): 2.26 | learning rate: 1.003E-04 | global batch size: 512 | lm loss: 1.976135E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.092 | TFLOPs: 23.28 | +63: iteration 39790/ 73814 | consumed samples: 20372480 | consumed tokens: 41722839040 | elapsed time per iteration (s): 2.24 | learning rate: 1.003E-04 | global batch size: 512 | lm loss: 2.000998E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.347 | TFLOPs: 23.51 | +63: iteration 39800/ 73814 | consumed samples: 20377600 | consumed tokens: 41733324800 | elapsed time per iteration (s): 2.25 | learning rate: 1.003E-04 | global batch size: 512 | lm loss: 1.986958E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.655 | TFLOPs: 23.44 | +63: iteration 39810/ 73814 | consumed samples: 20382720 | consumed tokens: 41743810560 | elapsed time per iteration (s): 2.24 | learning rate: 1.002E-04 | global batch size: 512 | lm loss: 1.998575E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.395 | TFLOPs: 23.51 | +63: iteration 39820/ 73814 | consumed samples: 20387840 | consumed tokens: 41754296320 | elapsed time per iteration (s): 2.23 | learning rate: 1.002E-04 | global batch size: 512 | lm loss: 2.003189E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.191 | TFLOPs: 23.59 | +63: iteration 39830/ 73814 | consumed samples: 20392960 | consumed tokens: 41764782080 | elapsed time per iteration (s): 2.23 | learning rate: 1.001E-04 | global batch size: 512 | lm loss: 2.022030E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.754 | TFLOPs: 23.65 | +63: iteration 39840/ 73814 | consumed samples: 20398080 | consumed tokens: 41775267840 | elapsed time per iteration (s): 2.23 | learning rate: 1.001E-04 | global batch size: 512 | lm loss: 2.016853E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.105 | TFLOPs: 23.59 | +63: iteration 39850/ 73814 | consumed samples: 20403200 | consumed tokens: 41785753600 | elapsed time per iteration (s): 2.23 | learning rate: 1.001E-04 | global batch size: 512 | lm loss: 1.992391E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.725 | TFLOPs: 23.65 | +63: iteration 39860/ 73814 | consumed samples: 20408320 | consumed tokens: 41796239360 | elapsed time per iteration (s): 2.24 | learning rate: 1.000E-04 | global batch size: 512 | lm loss: 1.985093E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.105 | TFLOPs: 23.48 | +63: iteration 39870/ 73814 | consumed samples: 20413440 | consumed tokens: 41806725120 | elapsed time per iteration (s): 2.24 | learning rate: 9.999E-05 | global batch size: 512 | lm loss: 2.024060E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.736 | TFLOPs: 23.55 | +63: iteration 39880/ 73814 | consumed samples: 20418560 | consumed tokens: 41817210880 | elapsed time per iteration (s): 2.23 | learning rate: 9.995E-05 | global batch size: 512 | lm loss: 2.007735E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.721 | TFLOPs: 23.65 | +63: iteration 39890/ 73814 | consumed samples: 20423680 | consumed tokens: 41827696640 | elapsed time per iteration (s): 2.26 | learning rate: 9.991E-05 | global batch size: 512 | lm loss: 1.984290E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.519 | TFLOPs: 23.32 | +63: iteration 39900/ 73814 | consumed samples: 20428800 | consumed tokens: 41838182400 | elapsed time per iteration (s): 2.23 | learning rate: 9.987E-05 | global batch size: 512 | lm loss: 1.994857E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.921 | TFLOPs: 23.67 | +63: iteration 39910/ 73814 | consumed samples: 20433920 | consumed tokens: 41848668160 | elapsed time per iteration (s): 2.23 | learning rate: 9.983E-05 | global batch size: 512 | lm loss: 2.002385E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.100 | TFLOPs: 23.69 | +63: iteration 39920/ 73814 | consumed samples: 20439040 | consumed tokens: 41859153920 | elapsed time per iteration (s): 2.23 | learning rate: 9.979E-05 | global batch size: 512 | lm loss: 2.006744E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.787 | TFLOPs: 23.66 | +63: iteration 39930/ 73814 | consumed samples: 20444160 | consumed tokens: 41869639680 | elapsed time per iteration (s): 2.22 | learning rate: 9.975E-05 | global batch size: 512 | lm loss: 2.014095E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.159 | TFLOPs: 23.69 | +63: iteration 39940/ 73814 | consumed samples: 20449280 | consumed tokens: 41880125440 | elapsed time per iteration (s): 2.24 | learning rate: 9.972E-05 | global batch size: 512 | lm loss: 2.006454E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.068 | TFLOPs: 23.58 | +63: iteration 39950/ 73814 | consumed samples: 20454400 | consumed tokens: 41890611200 | elapsed time per iteration (s): 2.24 | learning rate: 9.968E-05 | global batch size: 512 | lm loss: 2.001588E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.665 | TFLOPs: 23.54 | +63: iteration 39960/ 73814 | consumed samples: 20459520 | consumed tokens: 41901096960 | elapsed time per iteration (s): 2.30 | learning rate: 9.964E-05 | global batch size: 512 | lm loss: 1.999660E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.723 | TFLOPs: 22.93 | +63: iteration 39970/ 73814 | consumed samples: 20464640 | consumed tokens: 41911582720 | elapsed time per iteration (s): 2.23 | learning rate: 9.960E-05 | global batch size: 512 | lm loss: 2.003876E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.553 | TFLOPs: 23.63 | +63: iteration 39980/ 73814 | consumed samples: 20469760 | consumed tokens: 41922068480 | elapsed time per iteration (s): 2.22 | learning rate: 9.956E-05 | global batch size: 512 | lm loss: 1.983067E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.118 | TFLOPs: 23.69 | +63: iteration 39990/ 73814 | consumed samples: 20474880 | consumed tokens: 41932554240 | elapsed time per iteration (s): 2.24 | learning rate: 9.952E-05 | global batch size: 512 | lm loss: 2.000458E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.174 | TFLOPs: 23.49 | + 0: [2022-12-02 13:16:25,862] [INFO] [logging.py:68:log_dist] [Rank 0] step=40000, skipped=0, lr=[9.9485526735854e-05, 9.9485526735854e-05, 9.9485526735854e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] + 0: steps: 40000 loss: 2.0052 iter time (s): 2.274 samples/sec: 225.151 +63: iteration 40000/ 73814 | consumed samples: 20480000 | consumed tokens: 41943040000 | elapsed time per iteration (s): 2.25 | learning rate: 9.949E-05 | global batch size: 512 | lm loss: 2.011417E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.905 | TFLOPs: 23.46 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 40000 | lm loss value: 1.980313E+00 | lm loss PPL: 7.245007E+00 | +63: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 40000 to checkpoints_3b977boscar + 0: [2022-12-02 13:16:26,704] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step40000 is begin to save! +32: [2022-12-02 13:16:26,758] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_21-model_00-model_states.pt... + 0: [2022-12-02 13:16:26,759] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_01-model_00-model_states.pt... +32: [2022-12-02 13:16:27,211] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_21-model_00-model_states.pt. +32: [2022-12-02 13:16:27,212] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_22-model_00-model_states.pt... + 0: [2022-12-02 13:16:27,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_01-model_00-model_states.pt. + 0: [2022-12-02 13:16:27,259] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_03-model_00-model_states.pt... +32: [2022-12-02 13:16:27,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_22-model_00-model_states.pt. +32: [2022-12-02 13:16:27,450] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_23-model_00-model_states.pt... + 0: [2022-12-02 13:16:27,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_03-model_00-model_states.pt. + 0: [2022-12-02 13:16:27,475] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_04-model_00-model_states.pt... +32: [2022-12-02 13:16:27,688] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_23-model_00-model_states.pt. +32: [2022-12-02 13:16:27,688] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_24-model_00-model_states.pt... + 0: [2022-12-02 13:16:27,697] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_04-model_00-model_states.pt. + 0: [2022-12-02 13:16:27,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_05-model_00-model_states.pt... + 0: [2022-12-02 13:16:27,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_05-model_00-model_states.pt. + 0: [2022-12-02 13:16:27,918] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_06-model_00-model_states.pt... +32: [2022-12-02 13:16:27,928] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_24-model_00-model_states.pt. +32: [2022-12-02 13:16:27,928] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_25-model_00-model_states.pt... + 0: [2022-12-02 13:16:28,141] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_06-model_00-model_states.pt. + 0: [2022-12-02 13:16:28,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_07-model_00-model_states.pt... +32: [2022-12-02 13:16:28,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_25-model_00-model_states.pt. +32: [2022-12-02 13:16:28,168] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_26-model_00-model_states.pt... + 0: [2022-12-02 13:16:28,367] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_07-model_00-model_states.pt. + 0: [2022-12-02 13:16:28,368] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_08-model_00-model_states.pt... +32: [2022-12-02 13:16:28,402] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_26-model_00-model_states.pt. +32: [2022-12-02 13:16:28,402] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_27-model_00-model_states.pt... + 0: [2022-12-02 13:16:28,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_08-model_00-model_states.pt. + 0: [2022-12-02 13:16:28,588] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_09-model_00-model_states.pt... +32: [2022-12-02 13:16:28,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_27-model_00-model_states.pt. +32: [2022-12-02 13:16:28,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_28-model_00-model_states.pt... + 0: [2022-12-02 13:16:28,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_09-model_00-model_states.pt. + 0: [2022-12-02 13:16:28,810] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_10-model_00-model_states.pt... +32: [2022-12-02 13:16:28,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_28-model_00-model_states.pt. +32: [2022-12-02 13:16:28,864] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_29-model_00-model_states.pt... + 0: [2022-12-02 13:16:29,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_10-model_00-model_states.pt. + 0: [2022-12-02 13:16:29,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_11-model_00-model_states.pt... +32: [2022-12-02 13:16:29,092] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_29-model_00-model_states.pt. +32: [2022-12-02 13:16:29,093] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_30-model_00-model_states.pt... + 0: [2022-12-02 13:16:29,252] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_11-model_00-model_states.pt. + 0: [2022-12-02 13:16:29,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_12-model_00-model_states.pt... +32: [2022-12-02 13:16:29,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_30-model_00-model_states.pt. +32: [2022-12-02 13:16:29,326] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_31-model_00-model_states.pt... + 0: [2022-12-02 13:16:29,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_12-model_00-model_states.pt. + 0: [2022-12-02 13:16:29,477] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_13-model_00-model_states.pt... +32: [2022-12-02 13:16:29,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_31-model_00-model_states.pt. +32: [2022-12-02 13:16:29,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_32-model_00-model_states.pt... + 0: [2022-12-02 13:16:29,702] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_13-model_00-model_states.pt. + 0: [2022-12-02 13:16:29,703] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_14-model_00-model_states.pt... +32: [2022-12-02 13:16:29,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_32-model_00-model_states.pt. +32: [2022-12-02 13:16:29,788] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_33-model_00-model_states.pt... + 0: [2022-12-02 13:16:29,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 13:16:29,923] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_15-model_00-model_states.pt... + 0: [2022-12-02 13:16:30,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_15-model_00-model_states.pt. + 0: [2022-12-02 13:16:30,149] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_16-model_00-model_states.pt... +32: [2022-12-02 13:16:30,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_33-model_00-model_states.pt. +32: [2022-12-02 13:16:30,230] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_34-model_00-model_states.pt... + 0: [2022-12-02 13:16:30,370] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_16-model_00-model_states.pt. + 0: [2022-12-02 13:16:30,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_17-model_00-model_states.pt... + 0: [2022-12-02 13:16:30,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_17-model_00-model_states.pt. + 0: [2022-12-02 13:16:30,589] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_18-model_00-model_states.pt... +32: [2022-12-02 13:16:30,669] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_34-model_00-model_states.pt. +32: [2022-12-02 13:16:30,670] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_35-model_00-model_states.pt... + 0: [2022-12-02 13:16:30,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_18-model_00-model_states.pt. + 0: [2022-12-02 13:16:30,815] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_19-model_00-model_states.pt... + 0: [2022-12-02 13:16:31,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_19-model_00-model_states.pt. + 0: [2022-12-02 13:16:31,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_20-model_00-model_states.pt... +32: [2022-12-02 13:16:31,109] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_35-model_00-model_states.pt. +32: [2022-12-02 13:16:31,110] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_36-model_00-model_states.pt... + 0: [2022-12-02 13:16:31,255] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_20-model_00-model_states.pt. + 0: [2022-12-02 13:16:31,256] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_3b977boscar/global_step40000/mp_rank_00_model_states.pt + 0: [2022-12-02 13:16:31,256] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/mp_rank_00_model_states.pt... + 0: [2022-12-02 13:16:31,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/mp_rank_00_model_states.pt. +32: [2022-12-02 13:16:31,404] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_36-model_00-model_states.pt. +32: [2022-12-02 13:16:31,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_37-model_00-model_states.pt... +32: [2022-12-02 13:16:31,639] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_37-model_00-model_states.pt. +32: [2022-12-02 13:16:31,639] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_38-model_00-model_states.pt... +32: [2022-12-02 13:16:31,881] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_38-model_00-model_states.pt. +32: [2022-12-02 13:16:31,882] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/layer_40-model_00-model_states.pt... +32: [2022-12-02 13:16:31,886] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/layer_40-model_00-model_states.pt. +32: [2022-12-02 13:16:31,887] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/mp_rank_01_model_states.pt... +32: [2022-12-02 13:16:31,899] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/mp_rank_01_model_states.pt. +32: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt... +32: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt... +32: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt... +54: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt... +54: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt... +54: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt... +54: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt... +54: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt... +56: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt... +56: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt... +56: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt... +56: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt... +56: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt... +52: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt... +52: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt... +52: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt... +52: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt... +52: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt... +61: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt... +61: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt... +61: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt... +61: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt... +61: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt... +63: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt... +63: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt... +63: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt... +63: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt... +63: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt... +53: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt... +53: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt... +53: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt... +53: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt... +53: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt... +33: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt... +33: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt... +33: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt... +33: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt... +33: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt... +59: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt... +59: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt... +59: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt... +59: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt... +59: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt... +62: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt... +62: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt... +62: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt... +62: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt... +62: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt... +58: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt... +58: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt... +58: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt... +58: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt... +58: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt... +38: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt... +38: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt... +44: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt... +44: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt... +48: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt... +48: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt... +48: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt... +48: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt... +48: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt... +34: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt... +34: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt... +34: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt... +34: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt... +34: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt... +43: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt... +43: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt... +43: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt... +36: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt... +36: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt... +36: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt... +36: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt... +36: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt... +35: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt... +35: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt... +35: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt... +35: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt... +35: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt... +50: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt... +50: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt... +50: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt... +50: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt... +50: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt... +32: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt... +32: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt... +32: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt... +32: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt... +51: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt... +51: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt... +51: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt... +51: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt... +51: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt... +60: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt... +60: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt... +60: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt... +60: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt... +60: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt... +49: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt... +49: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt... +49: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt... +49: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt... +49: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt... +46: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt... +46: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt... +46: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt... +46: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt... +46: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt... +41: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt... +41: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt... +41: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt... +41: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt... +41: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt... +55: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt... +55: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt... +55: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt... +55: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt... +55: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt... +47: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt... +47: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt... +47: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt... +47: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt... +47: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt... +45: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt... +45: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt... +45: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt... +45: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt... +45: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt... +37: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt... +37: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt... +37: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt... +40: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt... +40: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt... +40: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt... +40: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt... +40: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt... +42: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt... +42: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt... +42: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt... +42: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt... +42: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt... +57: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt... +57: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt... +57: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt... +57: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt... +57: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt... +54: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt... +54: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt... +56: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt... +56: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt... +52: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt... +61: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt... +61: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt... +61: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt... +63: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt... +63: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt... +53: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt... +53: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt... +53: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt... +33: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt... +33: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt... +33: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt... +59: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt... +59: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt... +59: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt... +62: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt... +62: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt... +58: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt... +58: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt... +58: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt... +38: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt... +38: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt... +38: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt... +38: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt... +44: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt... +44: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt... +44: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt... +44: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt... +48: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt... +48: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt... +48: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt... +34: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt... +34: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt... +43: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt... +43: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt... +43: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt... +43: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt... +36: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt... +35: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt... +35: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt... +50: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt... +32: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt... +51: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt... +60: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt... +60: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt... +60: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt... +49: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt... +46: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt... +46: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt... +41: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt... +55: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt... +55: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt... +47: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt... +45: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt... +37: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt... +40: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt... +42: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt... +42: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt... +42: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt... +57: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt... +57: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt... +54: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt... +52: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt... +52: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt... +63: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt... +62: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt... +38: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt... +44: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt... +34: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt... +43: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt... +36: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt... +35: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt... +39: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt... +39: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt... +39: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt... +39: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt... +39: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt... +50: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt... +50: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt... +51: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt... +51: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt... + 4: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +49: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt... +49: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt... +46: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt... +41: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt... +41: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt... +55: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt... +47: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt... +47: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt... +45: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt... +45: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt... +37: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt... +37: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt... +37: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt... +40: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt... +40: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt... +57: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt... + 0: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 7: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +19: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +20: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +56: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt... +15: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... + 1: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +11: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... + 5: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... + 5: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +10: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +28: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +22: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +12: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +18: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +18: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +38: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt... +26: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +44: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt... + 9: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... +36: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt... + 2: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +39: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt... +39: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt... +39: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt... +25: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... + 4: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 6: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +13: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +31: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... + 3: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +27: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... + 8: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... +16: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +14: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +17: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +29: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +24: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +23: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +37: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt... +21: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... + 0: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 7: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +19: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +20: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +15: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... + 1: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +11: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... + 5: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +10: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +28: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +22: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +12: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +18: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +26: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +26: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... + 9: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 2: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +25: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... + 4: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 6: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +13: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +31: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... + 3: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +27: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +27: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... + 8: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... + 8: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... +16: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +14: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +17: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +29: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +30: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +24: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +23: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +21: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... + 0: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 7: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +19: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +20: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +15: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... + 1: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +11: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 5: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +10: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +28: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +22: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +12: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +18: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +26: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... + 9: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 2: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +25: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... + 4: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 6: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +13: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +31: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... + 3: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +27: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... + 8: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... +16: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +14: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +17: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +29: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +30: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +24: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +23: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +23: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... + 0: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 7: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +19: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... + 1: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +11: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... + 5: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +10: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +28: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +22: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +12: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +18: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +26: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... + 2: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +25: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... + 4: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 6: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +13: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +31: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +27: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... + 8: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... +16: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +17: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +29: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +30: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +23: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +21: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... + 0: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 7: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +19: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +11: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +10: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +28: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +18: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... + 2: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 4: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 6: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +13: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +31: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +16: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +14: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +29: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +30: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +24: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +21: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... + 0: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 7: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +11: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +10: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... + 2: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 4: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 6: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +13: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +31: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +17: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +30: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +24: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... + 0: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 7: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +11: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +10: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +31: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +17: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +29: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +30: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... + 7: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +29: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +30: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +29: [2022-12-02 13:16:32,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +32: [2022-12-02 13:16:32,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt. +32: [2022-12-02 13:16:32,173] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt +32: [2022-12-02 13:16:32,173] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 0: [2022-12-02 13:16:32,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-12-02 13:16:32,179] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-12-02 13:16:32,179] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 0: [2022-12-02 13:16:32,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-12-02 13:16:32,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. + 0: [2022-12-02 13:16:32,179] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-12-02 13:16:32,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-12-02 13:16:32,179] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 0: [2022-12-02 13:16:32,179] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-12-02 13:16:32,179] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 0: [2022-12-02 13:16:32,182] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-12-02 13:16:32,182] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-12-02 13:16:32,182] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +32: [2022-12-02 13:16:32,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt. +32: [2022-12-02 13:16:32,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt. +32: [2022-12-02 13:16:32,186] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt +32: [2022-12-02 13:16:32,186] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt +32: [2022-12-02 13:16:32,186] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +32: [2022-12-02 13:16:32,186] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +32: [2022-12-02 13:16:32,188] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt. +32: [2022-12-02 13:16:32,188] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt. +32: [2022-12-02 13:16:32,188] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt +32: [2022-12-02 13:16:32,188] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt +32: [2022-12-02 13:16:32,188] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +32: [2022-12-02 13:16:32,188] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +32: [2022-12-02 13:16:32,214] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt. +32: [2022-12-02 13:16:32,214] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt. +32: [2022-12-02 13:16:32,214] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt. +32: [2022-12-02 13:16:32,214] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt +32: [2022-12-02 13:16:32,214] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt +32: [2022-12-02 13:16:32,214] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +32: [2022-12-02 13:16:32,214] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +32: [2022-12-02 13:16:32,214] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt +32: [2022-12-02 13:16:32,214] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 0: [2022-12-02 13:16:32,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-12-02 13:16:32,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-12-02 13:16:32,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 0: [2022-12-02 13:16:32,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-12-02 13:16:32,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-12-02 13:16:32,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 0: [2022-12-02 13:16:32,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-12-02 13:16:32,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-12-02 13:16:32,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +49: [2022-12-02 13:16:32,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt. +49: [2022-12-02 13:16:32,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt. +49: [2022-12-02 13:16:32,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt +49: [2022-12-02 13:16:32,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt +49: [2022-12-02 13:16:32,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +49: [2022-12-02 13:16:32,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +49: [2022-12-02 13:16:32,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt. +49: [2022-12-02 13:16:32,291] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt +49: [2022-12-02 13:16:32,291] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +49: [2022-12-02 13:16:32,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt. +49: [2022-12-02 13:16:32,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt. +49: [2022-12-02 13:16:32,291] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt +49: [2022-12-02 13:16:32,291] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt +49: [2022-12-02 13:16:32,291] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +49: [2022-12-02 13:16:32,291] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +33: [2022-12-02 13:16:32,292] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt. +33: [2022-12-02 13:16:32,292] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt +33: [2022-12-02 13:16:32,292] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +33: [2022-12-02 13:16:32,292] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt. +33: [2022-12-02 13:16:32,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt +33: [2022-12-02 13:16:32,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +33: [2022-12-02 13:16:32,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt. +33: [2022-12-02 13:16:32,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt +33: [2022-12-02 13:16:32,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +33: [2022-12-02 13:16:32,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt. +33: [2022-12-02 13:16:32,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt +33: [2022-12-02 13:16:32,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +33: [2022-12-02 13:16:32,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt. +33: [2022-12-02 13:16:32,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt. +33: [2022-12-02 13:16:32,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt +33: [2022-12-02 13:16:32,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt +33: [2022-12-02 13:16:32,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +33: [2022-12-02 13:16:32,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +51: [2022-12-02 13:16:32,326] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt. +51: [2022-12-02 13:16:32,326] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt. +51: [2022-12-02 13:16:32,326] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt. +51: [2022-12-02 13:16:32,326] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt. +51: [2022-12-02 13:16:32,326] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt. +51: [2022-12-02 13:16:32,326] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt. +51: [2022-12-02 13:16:32,326] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt. +51: [2022-12-02 13:16:32,326] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt +51: [2022-12-02 13:16:32,326] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt +51: [2022-12-02 13:16:32,326] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt +51: [2022-12-02 13:16:32,326] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt +51: [2022-12-02 13:16:32,326] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt. +51: [2022-12-02 13:16:32,326] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt +51: [2022-12-02 13:16:32,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +51: [2022-12-02 13:16:32,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +51: [2022-12-02 13:16:32,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +51: [2022-12-02 13:16:32,326] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt +51: [2022-12-02 13:16:32,326] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt +51: [2022-12-02 13:16:32,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +51: [2022-12-02 13:16:32,326] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt +51: [2022-12-02 13:16:32,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +51: [2022-12-02 13:16:32,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +51: [2022-12-02 13:16:32,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +51: [2022-12-02 13:16:32,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +49: [2022-12-02 13:16:32,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt. +49: [2022-12-02 13:16:32,328] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt +49: [2022-12-02 13:16:32,328] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +48: [2022-12-02 13:16:32,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt. +48: [2022-12-02 13:16:32,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt +48: [2022-12-02 13:16:32,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +48: [2022-12-02 13:16:32,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt. +48: [2022-12-02 13:16:32,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt +48: [2022-12-02 13:16:32,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +48: [2022-12-02 13:16:32,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt. +48: [2022-12-02 13:16:32,335] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt +48: [2022-12-02 13:16:32,335] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +48: [2022-12-02 13:16:32,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt. +48: [2022-12-02 13:16:32,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt +48: [2022-12-02 13:16:32,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +48: [2022-12-02 13:16:32,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt. +48: [2022-12-02 13:16:32,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt +48: [2022-12-02 13:16:32,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 0: [2022-12-02 13:16:32,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-12-02 13:16:32,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +49: [2022-12-02 13:16:32,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt. +49: [2022-12-02 13:16:32,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt +49: [2022-12-02 13:16:32,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +49: [2022-12-02 13:16:32,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt. +49: [2022-12-02 13:16:32,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt +49: [2022-12-02 13:16:32,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +13: [2022-12-02 13:16:32,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-12-02 13:16:32,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-12-02 13:16:32,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-12-02 13:16:32,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-12-02 13:16:32,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-12-02 13:16:32,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-12-02 13:16:32,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-12-02 13:16:32,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-12-02 13:16:32,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-12-02 13:16:32,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-12-02 13:16:32,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-12-02 13:16:32,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-12-02 13:16:32,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-12-02 13:16:32,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-12-02 13:16:32,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-12-02 13:16:32,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +13: [2022-12-02 13:16:32,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +13: [2022-12-02 13:16:32,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-12-02 13:16:32,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +13: [2022-12-02 13:16:32,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +13: [2022-12-02 13:16:32,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +13: [2022-12-02 13:16:32,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +13: [2022-12-02 13:16:32,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +13: [2022-12-02 13:16:32,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +48: [2022-12-02 13:16:32,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt. +48: [2022-12-02 13:16:32,346] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt +48: [2022-12-02 13:16:32,346] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +48: [2022-12-02 13:16:32,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt. +48: [2022-12-02 13:16:32,346] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt +48: [2022-12-02 13:16:32,346] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +48: [2022-12-02 13:16:32,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt. +48: [2022-12-02 13:16:32,347] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt +48: [2022-12-02 13:16:32,347] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +25: [2022-12-02 13:16:32,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +53: [2022-12-02 13:16:32,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt. +53: [2022-12-02 13:16:32,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt. +53: [2022-12-02 13:16:32,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt. +53: [2022-12-02 13:16:32,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt. +53: [2022-12-02 13:16:32,352] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt +53: [2022-12-02 13:16:32,352] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt +53: [2022-12-02 13:16:32,352] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt +53: [2022-12-02 13:16:32,352] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt +53: [2022-12-02 13:16:32,352] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +53: [2022-12-02 13:16:32,352] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +53: [2022-12-02 13:16:32,352] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +53: [2022-12-02 13:16:32,352] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +53: [2022-12-02 13:16:32,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt. +53: [2022-12-02 13:16:32,355] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt +53: [2022-12-02 13:16:32,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +25: [2022-12-02 13:16:32,350] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-12-02 13:16:32,350] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +25: [2022-12-02 13:16:32,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-12-02 13:16:32,350] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +53: [2022-12-02 13:16:32,356] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt. +25: [2022-12-02 13:16:32,350] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +53: [2022-12-02 13:16:32,356] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt +25: [2022-12-02 13:16:32,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +53: [2022-12-02 13:16:32,356] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +25: [2022-12-02 13:16:32,350] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-12-02 13:16:32,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +53: [2022-12-02 13:16:32,357] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt. +53: [2022-12-02 13:16:32,357] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt +53: [2022-12-02 13:16:32,357] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +53: [2022-12-02 13:16:32,357] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt. +53: [2022-12-02 13:16:32,357] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt +53: [2022-12-02 13:16:32,357] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +25: [2022-12-02 13:16:32,358] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-12-02 13:16:32,358] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-12-02 13:16:32,358] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-12-02 13:16:32,358] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-12-02 13:16:32,358] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-12-02 13:16:32,358] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-12-02 13:16:32,358] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +25: [2022-12-02 13:16:32,358] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +25: [2022-12-02 13:16:32,358] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +38: [2022-12-02 13:16:32,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt. +38: [2022-12-02 13:16:32,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt. +38: [2022-12-02 13:16:32,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt. +38: [2022-12-02 13:16:32,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt. +38: [2022-12-02 13:16:32,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt. +38: [2022-12-02 13:16:32,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt. +38: [2022-12-02 13:16:32,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt. +38: [2022-12-02 13:16:32,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt. +38: [2022-12-02 13:16:32,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt +38: [2022-12-02 13:16:32,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt +38: [2022-12-02 13:16:32,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt +38: [2022-12-02 13:16:32,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt +38: [2022-12-02 13:16:32,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt +38: [2022-12-02 13:16:32,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt +38: [2022-12-02 13:16:32,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +38: [2022-12-02 13:16:32,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +38: [2022-12-02 13:16:32,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +38: [2022-12-02 13:16:32,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +38: [2022-12-02 13:16:32,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +38: [2022-12-02 13:16:32,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt +38: [2022-12-02 13:16:32,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt +38: [2022-12-02 13:16:32,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +38: [2022-12-02 13:16:32,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +38: [2022-12-02 13:16:32,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +21: [2022-12-02 13:16:32,365] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-12-02 13:16:32,365] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-12-02 13:16:32,365] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-12-02 13:16:32,365] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-12-02 13:16:32,365] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-12-02 13:16:32,365] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-12-02 13:16:32,365] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-12-02 13:16:32,365] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-12-02 13:16:32,365] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-12-02 13:16:32,365] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +21: [2022-12-02 13:16:32,365] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +21: [2022-12-02 13:16:32,365] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +21: [2022-12-02 13:16:32,365] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-12-02 13:16:32,365] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +21: [2022-12-02 13:16:32,365] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +21: [2022-12-02 13:16:32,374] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-12-02 13:16:32,374] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-12-02 13:16:32,374] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +36: [2022-12-02 13:16:32,375] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt. +36: [2022-12-02 13:16:32,375] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt. +36: [2022-12-02 13:16:32,375] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt. +36: [2022-12-02 13:16:32,375] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt. +36: [2022-12-02 13:16:32,375] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt. +36: [2022-12-02 13:16:32,375] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt. +36: [2022-12-02 13:16:32,375] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt. +36: [2022-12-02 13:16:32,375] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt +36: [2022-12-02 13:16:32,375] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt +36: [2022-12-02 13:16:32,375] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt +36: [2022-12-02 13:16:32,375] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt +36: [2022-12-02 13:16:32,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +36: [2022-12-02 13:16:32,375] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt +36: [2022-12-02 13:16:32,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +36: [2022-12-02 13:16:32,375] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt +36: [2022-12-02 13:16:32,375] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt +36: [2022-12-02 13:16:32,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +36: [2022-12-02 13:16:32,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +36: [2022-12-02 13:16:32,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +36: [2022-12-02 13:16:32,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +36: [2022-12-02 13:16:32,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +36: [2022-12-02 13:16:32,375] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt. +36: [2022-12-02 13:16:32,375] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt +36: [2022-12-02 13:16:32,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +21: [2022-12-02 13:16:32,385] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-12-02 13:16:32,385] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-12-02 13:16:32,385] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 2: [2022-12-02 13:16:32,399] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 2: [2022-12-02 13:16:32,399] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-12-02 13:16:32,399] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 2: [2022-12-02 13:16:32,399] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-12-02 13:16:32,399] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 2: [2022-12-02 13:16:32,399] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 2: [2022-12-02 13:16:32,399] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-12-02 13:16:32,399] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-12-02 13:16:32,399] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-12-02 13:16:32,399] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-12-02 13:16:32,399] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 2: [2022-12-02 13:16:32,399] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 4: [2022-12-02 13:16:32,400] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-12-02 13:16:32,400] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-12-02 13:16:32,400] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 4: [2022-12-02 13:16:32,401] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-12-02 13:16:32,401] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-12-02 13:16:32,401] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 4: [2022-12-02 13:16:32,401] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-12-02 13:16:32,401] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-12-02 13:16:32,402] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 4: [2022-12-02 13:16:32,402] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-12-02 13:16:32,402] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-12-02 13:16:32,402] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 4: [2022-12-02 13:16:32,403] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-12-02 13:16:32,403] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-12-02 13:16:32,403] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +19: [2022-12-02 13:16:32,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-12-02 13:16:32,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-12-02 13:16:32,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +55: [2022-12-02 13:16:32,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt. +55: [2022-12-02 13:16:32,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt. +55: [2022-12-02 13:16:32,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt. +55: [2022-12-02 13:16:32,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt. +55: [2022-12-02 13:16:32,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt. + 2: [2022-12-02 13:16:32,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-12-02 13:16:32,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-12-02 13:16:32,406] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-12-02 13:16:32,406] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +17: [2022-12-02 13:16:32,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-12-02 13:16:32,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-12-02 13:16:32,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +55: [2022-12-02 13:16:32,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt. +17: [2022-12-02 13:16:32,406] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-12-02 13:16:32,406] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +55: [2022-12-02 13:16:32,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt +55: [2022-12-02 13:16:32,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt +55: [2022-12-02 13:16:32,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt +17: [2022-12-02 13:16:32,406] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-12-02 13:16:32,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +55: [2022-12-02 13:16:32,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt +55: [2022-12-02 13:16:32,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt +55: [2022-12-02 13:16:32,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt +55: [2022-12-02 13:16:32,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +55: [2022-12-02 13:16:32,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +17: [2022-12-02 13:16:32,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +55: [2022-12-02 13:16:32,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +17: [2022-12-02 13:16:32,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +55: [2022-12-02 13:16:32,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +55: [2022-12-02 13:16:32,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 2: [2022-12-02 13:16:32,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 2: [2022-12-02 13:16:32,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +55: [2022-12-02 13:16:32,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +55: [2022-12-02 13:16:32,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt. +55: [2022-12-02 13:16:32,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt. +55: [2022-12-02 13:16:32,406] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt +55: [2022-12-02 13:16:32,406] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt +55: [2022-12-02 13:16:32,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +55: [2022-12-02 13:16:32,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 2: [2022-12-02 13:16:32,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-12-02 13:16:32,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-12-02 13:16:32,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-12-02 13:16:32,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-12-02 13:16:32,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 2: [2022-12-02 13:16:32,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +17: [2022-12-02 13:16:32,408] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-12-02 13:16:32,409] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-12-02 13:16:32,409] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +19: [2022-12-02 13:16:32,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-12-02 13:16:32,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-12-02 13:16:32,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-12-02 13:16:32,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +19: [2022-12-02 13:16:32,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +19: [2022-12-02 13:16:32,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +19: [2022-12-02 13:16:32,408] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-12-02 13:16:32,408] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +17: [2022-12-02 13:16:32,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +19: [2022-12-02 13:16:32,408] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-12-02 13:16:32,408] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-12-02 13:16:32,408] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +19: [2022-12-02 13:16:32,408] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +31: [2022-12-02 13:16:32,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-12-02 13:16:32,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-12-02 13:16:32,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +31: [2022-12-02 13:16:32,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-12-02 13:16:32,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-12-02 13:16:32,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-12-02 13:16:32,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-12-02 13:16:32,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-12-02 13:16:32,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +31: [2022-12-02 13:16:32,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +17: [2022-12-02 13:16:32,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +31: [2022-12-02 13:16:32,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +17: [2022-12-02 13:16:32,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +31: [2022-12-02 13:16:32,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +31: [2022-12-02 13:16:32,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-12-02 13:16:32,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +20: [2022-12-02 13:16:32,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-12-02 13:16:32,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +31: [2022-12-02 13:16:32,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-12-02 13:16:32,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-12-02 13:16:32,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-12-02 13:16:32,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-12-02 13:16:32,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +31: [2022-12-02 13:16:32,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +31: [2022-12-02 13:16:32,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +20: [2022-12-02 13:16:32,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-12-02 13:16:32,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-12-02 13:16:32,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +20: [2022-12-02 13:16:32,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +20: [2022-12-02 13:16:32,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +17: [2022-12-02 13:16:32,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-12-02 13:16:32,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-12-02 13:16:32,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-12-02 13:16:32,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-12-02 13:16:32,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +17: [2022-12-02 13:16:32,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-12-02 13:16:32,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-12-02 13:16:32,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +17: [2022-12-02 13:16:32,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +20: [2022-12-02 13:16:32,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-12-02 13:16:32,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-12-02 13:16:32,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +20: [2022-12-02 13:16:32,416] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-12-02 13:16:32,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +11: [2022-12-02 13:16:32,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-12-02 13:16:32,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-12-02 13:16:32,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-12-02 13:16:32,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-12-02 13:16:32,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-12-02 13:16:32,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-12-02 13:16:32,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-12-02 13:16:32,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-12-02 13:16:32,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-12-02 13:16:32,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-12-02 13:16:32,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-12-02 13:16:32,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-12-02 13:16:32,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-12-02 13:16:32,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +11: [2022-12-02 13:16:32,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-12-02 13:16:32,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +11: [2022-12-02 13:16:32,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-12-02 13:16:32,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-12-02 13:16:32,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +11: [2022-12-02 13:16:32,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +11: [2022-12-02 13:16:32,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +11: [2022-12-02 13:16:32,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +11: [2022-12-02 13:16:32,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +11: [2022-12-02 13:16:32,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +18: [2022-12-02 13:16:32,420] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-12-02 13:16:32,420] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-12-02 13:16:32,420] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-12-02 13:16:32,420] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-12-02 13:16:32,420] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-12-02 13:16:32,420] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-12-02 13:16:32,420] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-12-02 13:16:32,420] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-12-02 13:16:32,420] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-12-02 13:16:32,420] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-12-02 13:16:32,420] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-12-02 13:16:32,420] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-12-02 13:16:32,420] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-12-02 13:16:32,420] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-12-02 13:16:32,421] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-12-02 13:16:32,421] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-12-02 13:16:32,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +18: [2022-12-02 13:16:32,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +18: [2022-12-02 13:16:32,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +18: [2022-12-02 13:16:32,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +18: [2022-12-02 13:16:32,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +18: [2022-12-02 13:16:32,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +18: [2022-12-02 13:16:32,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 1: [2022-12-02 13:16:32,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +18: [2022-12-02 13:16:32,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 1: [2022-12-02 13:16:32,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-12-02 13:16:32,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-12-02 13:16:32,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-12-02 13:16:32,421] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-12-02 13:16:32,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-12-02 13:16:32,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 1: [2022-12-02 13:16:32,421] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-12-02 13:16:32,421] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-12-02 13:16:32,421] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-12-02 13:16:32,421] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-12-02 13:16:32,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 1: [2022-12-02 13:16:32,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 1: [2022-12-02 13:16:32,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 1: [2022-12-02 13:16:32,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +34: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt. +34: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt. +34: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt. +34: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt. +34: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt. +34: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt. +34: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt. +34: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt. +34: [2022-12-02 13:16:32,422] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt +34: [2022-12-02 13:16:32,422] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt +34: [2022-12-02 13:16:32,422] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt +34: [2022-12-02 13:16:32,422] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt +34: [2022-12-02 13:16:32,422] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt +34: [2022-12-02 13:16:32,422] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt +34: [2022-12-02 13:16:32,422] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt +34: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +34: [2022-12-02 13:16:32,422] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt +34: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +34: [2022-12-02 13:16:32,423] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +34: [2022-12-02 13:16:32,423] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +34: [2022-12-02 13:16:32,423] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +34: [2022-12-02 13:16:32,423] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +34: [2022-12-02 13:16:32,423] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +34: [2022-12-02 13:16:32,423] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +59: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt. +59: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt. +59: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt. +59: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt. +59: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt. +21: [2022-12-02 13:16:32,424] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-12-02 13:16:32,424] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-12-02 13:16:32,424] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +59: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt. +59: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt. +59: [2022-12-02 13:16:32,422] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt +59: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt. +59: [2022-12-02 13:16:32,422] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt +59: [2022-12-02 13:16:32,422] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt +59: [2022-12-02 13:16:32,422] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt +59: [2022-12-02 13:16:32,422] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt +59: [2022-12-02 13:16:32,422] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt +59: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +59: [2022-12-02 13:16:32,422] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt +59: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +59: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +59: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +59: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +59: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +59: [2022-12-02 13:16:32,422] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt +59: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +59: [2022-12-02 13:16:32,422] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +27: [2022-12-02 13:16:32,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-12-02 13:16:32,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-12-02 13:16:32,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-12-02 13:16:32,425] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-12-02 13:16:32,425] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-12-02 13:16:32,425] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-12-02 13:16:32,425] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +27: [2022-12-02 13:16:32,425] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +27: [2022-12-02 13:16:32,425] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +27: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-12-02 13:16:32,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +43: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt. +43: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt. +43: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt. +43: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt. +43: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt. +43: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt. +43: [2022-12-02 13:16:32,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt +43: [2022-12-02 13:16:32,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt +43: [2022-12-02 13:16:32,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt +43: [2022-12-02 13:16:32,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt +43: [2022-12-02 13:16:32,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt +43: [2022-12-02 13:16:32,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt +43: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +43: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +43: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +43: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 3: [2022-12-02 13:16:32,423] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-12-02 13:16:32,423] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-12-02 13:16:32,423] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-12-02 13:16:32,423] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +43: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +43: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +10: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +43: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt. +10: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-12-02 13:16:32,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +43: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt. +10: [2022-12-02 13:16:32,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-12-02 13:16:32,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-12-02 13:16:32,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +43: [2022-12-02 13:16:32,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt +10: [2022-12-02 13:16:32,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-12-02 13:16:32,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-12-02 13:16:32,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-12-02 13:16:32,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +43: [2022-12-02 13:16:32,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt +10: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +10: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +10: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +10: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +43: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +10: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +43: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +10: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +10: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +10: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +27: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-12-02 13:16:32,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +22: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +22: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-12-02 13:16:32,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-12-02 13:16:32,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-12-02 13:16:32,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-12-02 13:16:32,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-12-02 13:16:32,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +22: [2022-12-02 13:16:32,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-12-02 13:16:32,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-12-02 13:16:32,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +22: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +22: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +22: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +22: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +22: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +22: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +22: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +27: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-12-02 13:16:32,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt + 3: [2022-12-02 13:16:32,423] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-12-02 13:16:32,423] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +27: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 3: [2022-12-02 13:16:32,423] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-12-02 13:16:32,423] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-12-02 13:16:32,423] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 3: [2022-12-02 13:16:32,423] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 3: [2022-12-02 13:16:32,423] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 3: [2022-12-02 13:16:32,423] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +27: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. + 3: [2022-12-02 13:16:32,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-12-02 13:16:32,425] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +27: [2022-12-02 13:16:32,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-12-02 13:16:32,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt + 3: [2022-12-02 13:16:32,425] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 3: [2022-12-02 13:16:32,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-12-02 13:16:32,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +27: [2022-12-02 13:16:32,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +27: [2022-12-02 13:16:32,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 3: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 3: [2022-12-02 13:16:32,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-12-02 13:16:32,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +23: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-12-02 13:16:32,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +23: [2022-12-02 13:16:32,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 3: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-12-02 13:16:32,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-12-02 13:16:32,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +23: [2022-12-02 13:16:32,431] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-12-02 13:16:32,431] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-12-02 13:16:32,431] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-12-02 13:16:32,431] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +23: [2022-12-02 13:16:32,431] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-12-02 13:16:32,431] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 9: [2022-12-02 13:16:32,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-12-02 13:16:32,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-12-02 13:16:32,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-12-02 13:16:32,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-12-02 13:16:32,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-12-02 13:16:32,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-12-02 13:16:32,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-12-02 13:16:32,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-12-02 13:16:32,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-12-02 13:16:32,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-12-02 13:16:32,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-12-02 13:16:32,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-12-02 13:16:32,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-12-02 13:16:32,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-12-02 13:16:32,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-12-02 13:16:32,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-12-02 13:16:32,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 9: [2022-12-02 13:16:32,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 9: [2022-12-02 13:16:32,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 9: [2022-12-02 13:16:32,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 9: [2022-12-02 13:16:32,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 9: [2022-12-02 13:16:32,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 9: [2022-12-02 13:16:32,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 9: [2022-12-02 13:16:32,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +39: [2022-12-02 13:16:32,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt. +39: [2022-12-02 13:16:32,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt. +39: [2022-12-02 13:16:32,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt. +39: [2022-12-02 13:16:32,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt. +39: [2022-12-02 13:16:32,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt. +39: [2022-12-02 13:16:32,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt. +39: [2022-12-02 13:16:32,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt. +39: [2022-12-02 13:16:32,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt. +39: [2022-12-02 13:16:32,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt +39: [2022-12-02 13:16:32,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt +39: [2022-12-02 13:16:32,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt +39: [2022-12-02 13:16:32,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt +39: [2022-12-02 13:16:32,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +39: [2022-12-02 13:16:32,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt +39: [2022-12-02 13:16:32,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt +39: [2022-12-02 13:16:32,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +39: [2022-12-02 13:16:32,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +39: [2022-12-02 13:16:32,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt +39: [2022-12-02 13:16:32,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +39: [2022-12-02 13:16:32,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt +39: [2022-12-02 13:16:32,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +39: [2022-12-02 13:16:32,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +39: [2022-12-02 13:16:32,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +39: [2022-12-02 13:16:32,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +47: [2022-12-02 13:16:32,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt. +47: [2022-12-02 13:16:32,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt. +47: [2022-12-02 13:16:32,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt. +47: [2022-12-02 13:16:32,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt. +47: [2022-12-02 13:16:32,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt. +47: [2022-12-02 13:16:32,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt. +47: [2022-12-02 13:16:32,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt. +47: [2022-12-02 13:16:32,434] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt +47: [2022-12-02 13:16:32,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt. +47: [2022-12-02 13:16:32,434] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt +47: [2022-12-02 13:16:32,434] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +47: [2022-12-02 13:16:32,434] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt +47: [2022-12-02 13:16:32,434] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt +47: [2022-12-02 13:16:32,434] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt +47: [2022-12-02 13:16:32,434] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +47: [2022-12-02 13:16:32,434] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt +47: [2022-12-02 13:16:32,434] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt +47: [2022-12-02 13:16:32,434] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt +47: [2022-12-02 13:16:32,434] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +47: [2022-12-02 13:16:32,434] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +47: [2022-12-02 13:16:32,434] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +47: [2022-12-02 13:16:32,434] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +47: [2022-12-02 13:16:32,434] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +47: [2022-12-02 13:16:32,434] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 1: [2022-12-02 13:16:32,435] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 4: [2022-12-02 13:16:32,437] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-12-02 13:16:32,437] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-12-02 13:16:32,437] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-12-02 13:16:32,437] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-12-02 13:16:32,437] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-12-02 13:16:32,437] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 4: [2022-12-02 13:16:32,437] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 4: [2022-12-02 13:16:32,437] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-12-02 13:16:32,437] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 1: [2022-12-02 13:16:32,435] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-12-02 13:16:32,435] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-12-02 13:16:32,435] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-12-02 13:16:32,435] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-12-02 13:16:32,435] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-12-02 13:16:32,435] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 1: [2022-12-02 13:16:32,435] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 1: [2022-12-02 13:16:32,435] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +60: [2022-12-02 13:16:32,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt. +60: [2022-12-02 13:16:32,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt. +60: [2022-12-02 13:16:32,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt. +60: [2022-12-02 13:16:32,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt. +60: [2022-12-02 13:16:32,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt. +60: [2022-12-02 13:16:32,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt. +60: [2022-12-02 13:16:32,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt. +60: [2022-12-02 13:16:32,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt. +60: [2022-12-02 13:16:32,440] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt +60: [2022-12-02 13:16:32,440] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt +60: [2022-12-02 13:16:32,441] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt +60: [2022-12-02 13:16:32,441] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt +60: [2022-12-02 13:16:32,441] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt +60: [2022-12-02 13:16:32,441] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt +60: [2022-12-02 13:16:32,441] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt +60: [2022-12-02 13:16:32,441] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt +60: [2022-12-02 13:16:32,441] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +60: [2022-12-02 13:16:32,441] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +60: [2022-12-02 13:16:32,441] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +60: [2022-12-02 13:16:32,441] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +60: [2022-12-02 13:16:32,441] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +60: [2022-12-02 13:16:32,441] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +60: [2022-12-02 13:16:32,441] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +60: [2022-12-02 13:16:32,441] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +54: [2022-12-02 13:16:32,441] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt. +54: [2022-12-02 13:16:32,441] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt. +54: [2022-12-02 13:16:32,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt. +54: [2022-12-02 13:16:32,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt. +54: [2022-12-02 13:16:32,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt. +54: [2022-12-02 13:16:32,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt. +54: [2022-12-02 13:16:32,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt. +54: [2022-12-02 13:16:32,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt. +54: [2022-12-02 13:16:32,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt +54: [2022-12-02 13:16:32,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt +54: [2022-12-02 13:16:32,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt +54: [2022-12-02 13:16:32,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt +54: [2022-12-02 13:16:32,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt +54: [2022-12-02 13:16:32,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt +54: [2022-12-02 13:16:32,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt +54: [2022-12-02 13:16:32,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt +54: [2022-12-02 13:16:32,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +54: [2022-12-02 13:16:32,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +54: [2022-12-02 13:16:32,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +54: [2022-12-02 13:16:32,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +54: [2022-12-02 13:16:32,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +54: [2022-12-02 13:16:32,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +54: [2022-12-02 13:16:32,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +54: [2022-12-02 13:16:32,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +45: [2022-12-02 13:16:32,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt. +45: [2022-12-02 13:16:32,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt. +45: [2022-12-02 13:16:32,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt. +45: [2022-12-02 13:16:32,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt. +45: [2022-12-02 13:16:32,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt. +45: [2022-12-02 13:16:32,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt. +45: [2022-12-02 13:16:32,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt. +45: [2022-12-02 13:16:32,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt. +45: [2022-12-02 13:16:32,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt +45: [2022-12-02 13:16:32,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt +45: [2022-12-02 13:16:32,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt +45: [2022-12-02 13:16:32,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt +45: [2022-12-02 13:16:32,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt +45: [2022-12-02 13:16:32,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt +45: [2022-12-02 13:16:32,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt +45: [2022-12-02 13:16:32,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt +45: [2022-12-02 13:16:32,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +45: [2022-12-02 13:16:32,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +45: [2022-12-02 13:16:32,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +45: [2022-12-02 13:16:32,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +45: [2022-12-02 13:16:32,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +45: [2022-12-02 13:16:32,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +45: [2022-12-02 13:16:32,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +45: [2022-12-02 13:16:32,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +37: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt. +37: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt. +37: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt. +37: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt. +37: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt. +37: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt. +37: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt. +37: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt. +37: [2022-12-02 13:16:32,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt +37: [2022-12-02 13:16:32,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt +37: [2022-12-02 13:16:32,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt +37: [2022-12-02 13:16:32,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt +37: [2022-12-02 13:16:32,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt +37: [2022-12-02 13:16:32,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt +37: [2022-12-02 13:16:32,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt +37: [2022-12-02 13:16:32,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt +37: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +37: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +37: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +37: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +37: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +37: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +37: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +37: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +63: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt. +63: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt. +63: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt. +63: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt. +63: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt. +63: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt. +63: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt. +63: [2022-12-02 13:16:32,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt. +63: [2022-12-02 13:16:32,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt +63: [2022-12-02 13:16:32,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt +63: [2022-12-02 13:16:32,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt +63: [2022-12-02 13:16:32,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt +63: [2022-12-02 13:16:32,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt +63: [2022-12-02 13:16:32,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt +63: [2022-12-02 13:16:32,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt +63: [2022-12-02 13:16:32,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +63: [2022-12-02 13:16:32,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +63: [2022-12-02 13:16:32,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt +63: [2022-12-02 13:16:32,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +63: [2022-12-02 13:16:32,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +63: [2022-12-02 13:16:32,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +63: [2022-12-02 13:16:32,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +63: [2022-12-02 13:16:32,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +63: [2022-12-02 13:16:32,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +15: [2022-12-02 13:16:32,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-12-02 13:16:32,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-12-02 13:16:32,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-12-02 13:16:32,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-12-02 13:16:32,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-12-02 13:16:32,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-12-02 13:16:32,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-12-02 13:16:32,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-12-02 13:16:32,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-12-02 13:16:32,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-12-02 13:16:32,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-12-02 13:16:32,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +15: [2022-12-02 13:16:32,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-12-02 13:16:32,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +15: [2022-12-02 13:16:32,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-12-02 13:16:32,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +15: [2022-12-02 13:16:32,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-12-02 13:16:32,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +15: [2022-12-02 13:16:32,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +15: [2022-12-02 13:16:32,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +15: [2022-12-02 13:16:32,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +33: [2022-12-02 13:16:32,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt. +33: [2022-12-02 13:16:32,451] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt +33: [2022-12-02 13:16:32,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +33: [2022-12-02 13:16:32,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt. +33: [2022-12-02 13:16:32,451] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt +33: [2022-12-02 13:16:32,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 7: [2022-12-02 13:16:32,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-12-02 13:16:32,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-12-02 13:16:32,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-12-02 13:16:32,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-12-02 13:16:32,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-12-02 13:16:32,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-12-02 13:16:32,452] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-12-02 13:16:32,452] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-12-02 13:16:32,452] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-12-02 13:16:32,452] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-12-02 13:16:32,452] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-12-02 13:16:32,452] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-12-02 13:16:32,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 7: [2022-12-02 13:16:32,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 7: [2022-12-02 13:16:32,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 7: [2022-12-02 13:16:32,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 7: [2022-12-02 13:16:32,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 7: [2022-12-02 13:16:32,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-12-02 13:16:32,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 7: [2022-12-02 13:16:32,452] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-12-02 13:16:32,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +15: [2022-12-02 13:16:32,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-12-02 13:16:32,453] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-12-02 13:16:32,453] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 7: [2022-12-02 13:16:32,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-12-02 13:16:32,453] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-12-02 13:16:32,453] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +16: [2022-12-02 13:16:32,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-12-02 13:16:32,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-12-02 13:16:32,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-12-02 13:16:32,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-12-02 13:16:32,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-12-02 13:16:32,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-12-02 13:16:32,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-12-02 13:16:32,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-12-02 13:16:32,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-12-02 13:16:32,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-12-02 13:16:32,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-12-02 13:16:32,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +16: [2022-12-02 13:16:32,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +16: [2022-12-02 13:16:32,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +16: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +16: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +16: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +16: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +57: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt. +57: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt. +57: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt. +57: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt. +57: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt. +57: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt. +57: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt. +57: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt. +57: [2022-12-02 13:16:32,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt +57: [2022-12-02 13:16:32,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt +57: [2022-12-02 13:16:32,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt +57: [2022-12-02 13:16:32,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt +57: [2022-12-02 13:16:32,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt +57: [2022-12-02 13:16:32,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt +57: [2022-12-02 13:16:32,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt +57: [2022-12-02 13:16:32,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt +57: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +57: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +57: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +57: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +57: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +57: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +57: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +57: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +26: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-12-02 13:16:32,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-12-02 13:16:32,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-12-02 13:16:32,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-12-02 13:16:32,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-12-02 13:16:32,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-12-02 13:16:32,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +26: [2022-12-02 13:16:32,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +26: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +26: [2022-12-02 13:16:32,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +26: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +26: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +26: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +26: [2022-12-02 13:16:32,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +56: [2022-12-02 13:16:32,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt. +56: [2022-12-02 13:16:32,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt. +56: [2022-12-02 13:16:32,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt. +56: [2022-12-02 13:16:32,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt. +56: [2022-12-02 13:16:32,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt. +56: [2022-12-02 13:16:32,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt. +56: [2022-12-02 13:16:32,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt. +56: [2022-12-02 13:16:32,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt. +56: [2022-12-02 13:16:32,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt +56: [2022-12-02 13:16:32,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt +56: [2022-12-02 13:16:32,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt +56: [2022-12-02 13:16:32,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt +56: [2022-12-02 13:16:32,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt +56: [2022-12-02 13:16:32,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt +56: [2022-12-02 13:16:32,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +56: [2022-12-02 13:16:32,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +56: [2022-12-02 13:16:32,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +56: [2022-12-02 13:16:32,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt +56: [2022-12-02 13:16:32,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +56: [2022-12-02 13:16:32,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt +56: [2022-12-02 13:16:32,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +56: [2022-12-02 13:16:32,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +56: [2022-12-02 13:16:32,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +56: [2022-12-02 13:16:32,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +30: [2022-12-02 13:16:32,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-12-02 13:16:32,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-12-02 13:16:32,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-12-02 13:16:32,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. + 5: [2022-12-02 13:16:32,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-12-02 13:16:32,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-12-02 13:16:32,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-12-02 13:16:32,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-12-02 13:16:32,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-12-02 13:16:32,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-12-02 13:16:32,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-12-02 13:16:32,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 5: [2022-12-02 13:16:32,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 5: [2022-12-02 13:16:32,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-12-02 13:16:32,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 5: [2022-12-02 13:16:32,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +30: [2022-12-02 13:16:32,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-12-02 13:16:32,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-12-02 13:16:32,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +58: [2022-12-02 13:16:32,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt. +58: [2022-12-02 13:16:32,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt. +58: [2022-12-02 13:16:32,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt. +58: [2022-12-02 13:16:32,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt. +58: [2022-12-02 13:16:32,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt. +30: [2022-12-02 13:16:32,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-12-02 13:16:32,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-12-02 13:16:32,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-12-02 13:16:32,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +30: [2022-12-02 13:16:32,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +30: [2022-12-02 13:16:32,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +30: [2022-12-02 13:16:32,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +58: [2022-12-02 13:16:32,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt. +58: [2022-12-02 13:16:32,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt. +30: [2022-12-02 13:16:32,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +58: [2022-12-02 13:16:32,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt. +58: [2022-12-02 13:16:32,459] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt +58: [2022-12-02 13:16:32,459] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt +58: [2022-12-02 13:16:32,459] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt +58: [2022-12-02 13:16:32,459] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt +58: [2022-12-02 13:16:32,459] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt +58: [2022-12-02 13:16:32,459] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt +58: [2022-12-02 13:16:32,459] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt +58: [2022-12-02 13:16:32,459] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +58: [2022-12-02 13:16:32,459] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +58: [2022-12-02 13:16:32,459] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt +58: [2022-12-02 13:16:32,459] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +58: [2022-12-02 13:16:32,459] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +58: [2022-12-02 13:16:32,459] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +58: [2022-12-02 13:16:32,459] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +58: [2022-12-02 13:16:32,459] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +58: [2022-12-02 13:16:32,459] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 5: [2022-12-02 13:16:32,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-12-02 13:16:32,462] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-12-02 13:16:32,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 5: [2022-12-02 13:16:32,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-12-02 13:16:32,462] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-12-02 13:16:32,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 5: [2022-12-02 13:16:32,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-12-02 13:16:32,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-12-02 13:16:32,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +44: [2022-12-02 13:16:32,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt. +44: [2022-12-02 13:16:32,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt. +44: [2022-12-02 13:16:32,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt. +44: [2022-12-02 13:16:32,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt. +44: [2022-12-02 13:16:32,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt. +44: [2022-12-02 13:16:32,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt. +44: [2022-12-02 13:16:32,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt. +44: [2022-12-02 13:16:32,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt. +44: [2022-12-02 13:16:32,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt +44: [2022-12-02 13:16:32,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt +44: [2022-12-02 13:16:32,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt +44: [2022-12-02 13:16:32,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt +44: [2022-12-02 13:16:32,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt +44: [2022-12-02 13:16:32,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt +44: [2022-12-02 13:16:32,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +44: [2022-12-02 13:16:32,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt +44: [2022-12-02 13:16:32,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt +44: [2022-12-02 13:16:32,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +44: [2022-12-02 13:16:32,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +44: [2022-12-02 13:16:32,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +44: [2022-12-02 13:16:32,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +44: [2022-12-02 13:16:32,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +44: [2022-12-02 13:16:32,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +44: [2022-12-02 13:16:32,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 5: [2022-12-02 13:16:32,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-12-02 13:16:32,467] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-12-02 13:16:32,467] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 8: [2022-12-02 13:16:32,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-12-02 13:16:32,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-12-02 13:16:32,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. +23: [2022-12-02 13:16:32,470] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-12-02 13:16:32,470] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-12-02 13:16:32,470] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 6: [2022-12-02 13:16:32,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-12-02 13:16:32,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-12-02 13:16:32,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-12-02 13:16:32,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-12-02 13:16:32,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-12-02 13:16:32,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-12-02 13:16:32,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-12-02 13:16:32,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-12-02 13:16:32,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-12-02 13:16:32,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +16: [2022-12-02 13:16:32,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. + 6: [2022-12-02 13:16:32,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-12-02 13:16:32,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-12-02 13:16:32,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +16: [2022-12-02 13:16:32,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt + 6: [2022-12-02 13:16:32,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 6: [2022-12-02 13:16:32,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 6: [2022-12-02 13:16:32,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-12-02 13:16:32,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-12-02 13:16:32,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +16: [2022-12-02 13:16:32,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 6: [2022-12-02 13:16:32,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 6: [2022-12-02 13:16:32,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 6: [2022-12-02 13:16:32,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 6: [2022-12-02 13:16:32,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 6: [2022-12-02 13:16:32,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 6: [2022-12-02 13:16:32,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +42: [2022-12-02 13:16:32,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt. +42: [2022-12-02 13:16:32,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt. +42: [2022-12-02 13:16:32,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt. +42: [2022-12-02 13:16:32,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt. +42: [2022-12-02 13:16:32,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt +42: [2022-12-02 13:16:32,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt. +42: [2022-12-02 13:16:32,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt. +42: [2022-12-02 13:16:32,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt. +42: [2022-12-02 13:16:32,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt +42: [2022-12-02 13:16:32,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt. +42: [2022-12-02 13:16:32,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +42: [2022-12-02 13:16:32,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt +42: [2022-12-02 13:16:32,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt +42: [2022-12-02 13:16:32,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +42: [2022-12-02 13:16:32,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt +42: [2022-12-02 13:16:32,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt +42: [2022-12-02 13:16:32,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt +42: [2022-12-02 13:16:32,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt +42: [2022-12-02 13:16:32,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +42: [2022-12-02 13:16:32,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +42: [2022-12-02 13:16:32,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +42: [2022-12-02 13:16:32,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +42: [2022-12-02 13:16:32,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +42: [2022-12-02 13:16:32,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +62: [2022-12-02 13:16:32,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt. +62: [2022-12-02 13:16:32,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt. +62: [2022-12-02 13:16:32,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt. +62: [2022-12-02 13:16:32,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt. +62: [2022-12-02 13:16:32,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt +62: [2022-12-02 13:16:32,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt. +62: [2022-12-02 13:16:32,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +62: [2022-12-02 13:16:32,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt +62: [2022-12-02 13:16:32,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt +62: [2022-12-02 13:16:32,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt +62: [2022-12-02 13:16:32,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt. +62: [2022-12-02 13:16:32,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt. +62: [2022-12-02 13:16:32,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt +62: [2022-12-02 13:16:32,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +62: [2022-12-02 13:16:32,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +62: [2022-12-02 13:16:32,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +62: [2022-12-02 13:16:32,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +62: [2022-12-02 13:16:32,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt +62: [2022-12-02 13:16:32,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt +62: [2022-12-02 13:16:32,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +62: [2022-12-02 13:16:32,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +62: [2022-12-02 13:16:32,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt. +62: [2022-12-02 13:16:32,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt +62: [2022-12-02 13:16:32,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +52: [2022-12-02 13:16:32,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt. +52: [2022-12-02 13:16:32,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt. +52: [2022-12-02 13:16:32,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt. +52: [2022-12-02 13:16:32,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt. +52: [2022-12-02 13:16:32,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt. +52: [2022-12-02 13:16:32,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt. +52: [2022-12-02 13:16:32,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt. +52: [2022-12-02 13:16:32,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt +52: [2022-12-02 13:16:32,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt +52: [2022-12-02 13:16:32,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt +52: [2022-12-02 13:16:32,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt +52: [2022-12-02 13:16:32,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt +52: [2022-12-02 13:16:32,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt +52: [2022-12-02 13:16:32,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt +52: [2022-12-02 13:16:32,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +52: [2022-12-02 13:16:32,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +52: [2022-12-02 13:16:32,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +52: [2022-12-02 13:16:32,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt. +52: [2022-12-02 13:16:32,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +52: [2022-12-02 13:16:32,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +52: [2022-12-02 13:16:32,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +52: [2022-12-02 13:16:32,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +52: [2022-12-02 13:16:32,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt +52: [2022-12-02 13:16:32,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +46: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt. +46: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt. +46: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt. +46: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt. +46: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt. +46: [2022-12-02 13:16:32,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt +46: [2022-12-02 13:16:32,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt +46: [2022-12-02 13:16:32,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt +46: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +46: [2022-12-02 13:16:32,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt +46: [2022-12-02 13:16:32,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt +46: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +46: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +46: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +46: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +28: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-12-02 13:16:32,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-12-02 13:16:32,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-12-02 13:16:32,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-12-02 13:16:32,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-12-02 13:16:32,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-12-02 13:16:32,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +28: [2022-12-02 13:16:32,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-12-02 13:16:32,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +28: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +28: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +28: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +28: [2022-12-02 13:16:32,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +28: [2022-12-02 13:16:32,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +28: [2022-12-02 13:16:32,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +14: [2022-12-02 13:16:32,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-12-02 13:16:32,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-12-02 13:16:32,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-12-02 13:16:32,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +41: [2022-12-02 13:16:32,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt. +41: [2022-12-02 13:16:32,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt. +41: [2022-12-02 13:16:32,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt. +14: [2022-12-02 13:16:32,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-12-02 13:16:32,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-12-02 13:16:32,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-12-02 13:16:32,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-12-02 13:16:32,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +14: [2022-12-02 13:16:32,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +14: [2022-12-02 13:16:32,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +14: [2022-12-02 13:16:32,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +14: [2022-12-02 13:16:32,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-12-02 13:16:32,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-12-02 13:16:32,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +14: [2022-12-02 13:16:32,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-12-02 13:16:32,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-12-02 13:16:32,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-12-02 13:16:32,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-12-02 13:16:32,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +14: [2022-12-02 13:16:32,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-12-02 13:16:32,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-12-02 13:16:32,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +14: [2022-12-02 13:16:32,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +29: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-12-02 13:16:32,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-12-02 13:16:32,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +29: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +29: [2022-12-02 13:16:32,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-12-02 13:16:32,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-12-02 13:16:32,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-12-02 13:16:32,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +29: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +29: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +61: [2022-12-02 13:16:32,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt. +61: [2022-12-02 13:16:32,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt. +61: [2022-12-02 13:16:32,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt. +61: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt. +61: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt. +29: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +29: [2022-12-02 13:16:32,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +20: [2022-12-02 13:16:32,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-12-02 13:16:32,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-12-02 13:16:32,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +29: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-12-02 13:16:32,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +61: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt. +29: [2022-12-02 13:16:32,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +61: [2022-12-02 13:16:32,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt. +61: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt. +61: [2022-12-02 13:16:32,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt +61: [2022-12-02 13:16:32,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt +61: [2022-12-02 13:16:32,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt +61: [2022-12-02 13:16:32,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt +61: [2022-12-02 13:16:32,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt +61: [2022-12-02 13:16:32,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt +61: [2022-12-02 13:16:32,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt +61: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +61: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +61: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +61: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +61: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +61: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +61: [2022-12-02 13:16:32,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt +61: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +61: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +35: [2022-12-02 13:16:32,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt. +35: [2022-12-02 13:16:32,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt. +35: [2022-12-02 13:16:32,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt. +35: [2022-12-02 13:16:32,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt. +35: [2022-12-02 13:16:32,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt. +35: [2022-12-02 13:16:32,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt. +35: [2022-12-02 13:16:32,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt. +35: [2022-12-02 13:16:32,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt +35: [2022-12-02 13:16:32,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt +35: [2022-12-02 13:16:32,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt. +35: [2022-12-02 13:16:32,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt +35: [2022-12-02 13:16:32,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt +35: [2022-12-02 13:16:32,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt +35: [2022-12-02 13:16:32,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt +35: [2022-12-02 13:16:32,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt +35: [2022-12-02 13:16:32,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +35: [2022-12-02 13:16:32,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +35: [2022-12-02 13:16:32,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +35: [2022-12-02 13:16:32,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt +35: [2022-12-02 13:16:32,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +35: [2022-12-02 13:16:32,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +35: [2022-12-02 13:16:32,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +35: [2022-12-02 13:16:32,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +35: [2022-12-02 13:16:32,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +41: [2022-12-02 13:16:32,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt +41: [2022-12-02 13:16:32,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt +41: [2022-12-02 13:16:32,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt +41: [2022-12-02 13:16:32,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +41: [2022-12-02 13:16:32,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +41: [2022-12-02 13:16:32,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +41: [2022-12-02 13:16:32,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt. +41: [2022-12-02 13:16:32,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt +41: [2022-12-02 13:16:32,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +41: [2022-12-02 13:16:32,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt. +41: [2022-12-02 13:16:32,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt. +41: [2022-12-02 13:16:32,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt. +41: [2022-12-02 13:16:32,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt +41: [2022-12-02 13:16:32,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt +41: [2022-12-02 13:16:32,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt +41: [2022-12-02 13:16:32,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +41: [2022-12-02 13:16:32,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +41: [2022-12-02 13:16:32,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +12: [2022-12-02 13:16:32,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-12-02 13:16:32,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-12-02 13:16:32,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-12-02 13:16:32,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +12: [2022-12-02 13:16:32,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-12-02 13:16:32,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-12-02 13:16:32,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-12-02 13:16:32,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-12-02 13:16:32,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +12: [2022-12-02 13:16:32,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +12: [2022-12-02 13:16:32,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +12: [2022-12-02 13:16:32,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +12: [2022-12-02 13:16:32,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-12-02 13:16:32,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-12-02 13:16:32,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-12-02 13:16:32,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-12-02 13:16:32,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +12: [2022-12-02 13:16:32,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +41: [2022-12-02 13:16:32,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt. +41: [2022-12-02 13:16:32,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt +41: [2022-12-02 13:16:32,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +46: [2022-12-02 13:16:32,492] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt. +46: [2022-12-02 13:16:32,492] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt +46: [2022-12-02 13:16:32,492] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +46: [2022-12-02 13:16:32,492] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt. +46: [2022-12-02 13:16:32,492] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt +46: [2022-12-02 13:16:32,492] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 8: [2022-12-02 13:16:32,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-12-02 13:16:32,467] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-12-02 13:16:32,467] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-12-02 13:16:32,467] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-12-02 13:16:32,467] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-12-02 13:16:32,467] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 8: [2022-12-02 13:16:32,467] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 8: [2022-12-02 13:16:32,467] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 8: [2022-12-02 13:16:32,467] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 8: [2022-12-02 13:16:32,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-12-02 13:16:32,468] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-12-02 13:16:32,468] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 8: [2022-12-02 13:16:32,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-12-02 13:16:32,468] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-12-02 13:16:32,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-12-02 13:16:32,468] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 8: [2022-12-02 13:16:32,468] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-12-02 13:16:32,468] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 8: [2022-12-02 13:16:32,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-12-02 13:16:32,468] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-12-02 13:16:32,468] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +12: [2022-12-02 13:16:32,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-12-02 13:16:32,503] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-12-02 13:16:32,503] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +12: [2022-12-02 13:16:32,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-12-02 13:16:32,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-12-02 13:16:32,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +50: [2022-12-02 13:16:32,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt. +50: [2022-12-02 13:16:32,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt. +50: [2022-12-02 13:16:32,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt. +50: [2022-12-02 13:16:32,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt. +50: [2022-12-02 13:16:32,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt. +50: [2022-12-02 13:16:32,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt. +50: [2022-12-02 13:16:32,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt. +50: [2022-12-02 13:16:32,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt +50: [2022-12-02 13:16:32,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt +50: [2022-12-02 13:16:32,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt +50: [2022-12-02 13:16:32,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt +50: [2022-12-02 13:16:32,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt +50: [2022-12-02 13:16:32,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt +50: [2022-12-02 13:16:32,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt +50: [2022-12-02 13:16:32,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +50: [2022-12-02 13:16:32,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +50: [2022-12-02 13:16:32,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +50: [2022-12-02 13:16:32,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +50: [2022-12-02 13:16:32,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +50: [2022-12-02 13:16:32,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +50: [2022-12-02 13:16:32,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +50: [2022-12-02 13:16:32,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt. +50: [2022-12-02 13:16:32,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt +50: [2022-12-02 13:16:32,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +23: [2022-12-02 13:16:32,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-12-02 13:16:32,506] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-12-02 13:16:32,506] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +19: [2022-12-02 13:16:32,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-12-02 13:16:32,510] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-12-02 13:16:32,510] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +30: [2022-12-02 13:16:32,517] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-12-02 13:16:32,517] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-12-02 13:16:32,517] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +24: [2022-12-02 13:16:32,532] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-12-02 13:16:32,532] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-12-02 13:16:32,532] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-12-02 13:16:32,532] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-12-02 13:16:32,532] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-12-02 13:16:32,532] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-12-02 13:16:32,532] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-12-02 13:16:32,532] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-12-02 13:16:32,532] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +20: [2022-12-02 13:16:32,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +24: [2022-12-02 13:16:32,532] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +20: [2022-12-02 13:16:32,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +24: [2022-12-02 13:16:32,532] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-12-02 13:16:32,532] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +24: [2022-12-02 13:16:32,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +20: [2022-12-02 13:16:32,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +24: [2022-12-02 13:16:32,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +24: [2022-12-02 13:16:32,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +24: [2022-12-02 13:16:32,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +24: [2022-12-02 13:16:32,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-12-02 13:16:32,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +40: [2022-12-02 13:16:32,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt. +40: [2022-12-02 13:16:32,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt. +40: [2022-12-02 13:16:32,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt. +40: [2022-12-02 13:16:32,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt. +40: [2022-12-02 13:16:32,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt. +40: [2022-12-02 13:16:32,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt. +40: [2022-12-02 13:16:32,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt. +40: [2022-12-02 13:16:32,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt. +40: [2022-12-02 13:16:32,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt +40: [2022-12-02 13:16:32,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt +40: [2022-12-02 13:16:32,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt +40: [2022-12-02 13:16:32,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt +40: [2022-12-02 13:16:32,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt +40: [2022-12-02 13:16:32,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt +40: [2022-12-02 13:16:32,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt +40: [2022-12-02 13:16:32,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +40: [2022-12-02 13:16:32,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +40: [2022-12-02 13:16:32,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt +40: [2022-12-02 13:16:32,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +40: [2022-12-02 13:16:32,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +40: [2022-12-02 13:16:32,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +40: [2022-12-02 13:16:32,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +40: [2022-12-02 13:16:32,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +40: [2022-12-02 13:16:32,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +20: [2022-12-02 13:16:32,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-12-02 13:16:32,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-12-02 13:16:32,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +23: [2022-12-02 13:16:32,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +23: [2022-12-02 13:16:32,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-12-02 13:16:32,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +30: [2022-12-02 13:16:32,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-12-02 13:16:32,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-12-02 13:16:32,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +31: [2022-12-02 13:16:32,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-12-02 13:16:32,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-12-02 13:16:32,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +24: [2022-12-02 13:16:32,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-12-02 13:16:32,550] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-12-02 13:16:32,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +46: [2022-12-02 13:16:32,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt. +46: [2022-12-02 13:16:32,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt +46: [2022-12-02 13:16:32,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +19: [2022-12-02 13:16:32,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-12-02 13:16:32,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-12-02 13:16:32,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +19: [2022-12-02 13:16:32,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-12-02 13:16:32,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-12-02 13:16:32,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +23: [2022-12-02 13:16:32,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-12-02 13:16:32,575] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-12-02 13:16:32,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +20: [2022-12-02 13:16:32,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-12-02 13:16:32,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-12-02 13:16:32,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +24: [2022-12-02 13:16:32,587] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-12-02 13:16:32,587] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-12-02 13:16:32,587] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +25: [2022-12-02 13:16:32,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-12-02 13:16:32,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-12-02 13:16:32,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +25: [2022-12-02 13:16:32,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-12-02 13:16:32,604] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-12-02 13:16:32,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! +30: [2022-12-02 13:16:32,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-12-02 13:16:32,609] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step40000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-12-02 13:16:32,609] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step40000 is ready now! + 0: successfully saved checkpoint at iteration 40000 to checkpoints_3b977boscar +63: time (ms) | save-checkpoint: 6011.16 +63: iteration 40010/ 73814 | consumed samples: 20485120 | consumed tokens: 41953525760 | elapsed time per iteration (s): 2.88 | learning rate: 9.945E-05 | global batch size: 512 | lm loss: 1.987940E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 177.506 | TFLOPs: 18.27 | +63: iteration 40020/ 73814 | consumed samples: 20490240 | consumed tokens: 41964011520 | elapsed time per iteration (s): 2.25 | learning rate: 9.941E-05 | global batch size: 512 | lm loss: 1.994562E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.016 | TFLOPs: 23.47 | +63: iteration 40030/ 73814 | consumed samples: 20495360 | consumed tokens: 41974497280 | elapsed time per iteration (s): 2.23 | learning rate: 9.937E-05 | global batch size: 512 | lm loss: 1.998734E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.899 | TFLOPs: 23.67 | +63: iteration 40040/ 73814 | consumed samples: 20500480 | consumed tokens: 41984983040 | elapsed time per iteration (s): 2.46 | learning rate: 9.933E-05 | global batch size: 512 | lm loss: 1.990768E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.131 | TFLOPs: 21.43 | +63: iteration 40050/ 73814 | consumed samples: 20505600 | consumed tokens: 41995468800 | elapsed time per iteration (s): 2.34 | learning rate: 9.929E-05 | global batch size: 512 | lm loss: 2.032520E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.709 | TFLOPs: 22.52 | +63: iteration 40060/ 73814 | consumed samples: 20510720 | consumed tokens: 42005954560 | elapsed time per iteration (s): 2.24 | learning rate: 9.926E-05 | global batch size: 512 | lm loss: 1.999952E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.641 | TFLOPs: 23.54 | +63: iteration 40070/ 73814 | consumed samples: 20515840 | consumed tokens: 42016440320 | elapsed time per iteration (s): 2.33 | learning rate: 9.922E-05 | global batch size: 512 | lm loss: 2.005756E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.615 | TFLOPs: 22.61 | +63: iteration 40080/ 73814 | consumed samples: 20520960 | consumed tokens: 42026926080 | elapsed time per iteration (s): 2.23 | learning rate: 9.918E-05 | global batch size: 512 | lm loss: 1.993157E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.400 | TFLOPs: 23.62 | +63: iteration 40090/ 73814 | consumed samples: 20526080 | consumed tokens: 42037411840 | elapsed time per iteration (s): 2.22 | learning rate: 9.914E-05 | global batch size: 512 | lm loss: 1.995140E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.291 | TFLOPs: 23.71 | +63: iteration 40100/ 73814 | consumed samples: 20531200 | consumed tokens: 42047897600 | elapsed time per iteration (s): 2.24 | learning rate: 9.910E-05 | global batch size: 512 | lm loss: 1.993620E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.276 | TFLOPs: 23.50 | +63: iteration 40110/ 73814 | consumed samples: 20536320 | consumed tokens: 42058383360 | elapsed time per iteration (s): 2.24 | learning rate: 9.906E-05 | global batch size: 512 | lm loss: 2.026270E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.261 | TFLOPs: 23.50 | +63: iteration 40120/ 73814 | consumed samples: 20541440 | consumed tokens: 42068869120 | elapsed time per iteration (s): 2.24 | learning rate: 9.902E-05 | global batch size: 512 | lm loss: 2.009331E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.253 | TFLOPs: 23.50 | +63: iteration 40130/ 73814 | consumed samples: 20546560 | consumed tokens: 42079354880 | elapsed time per iteration (s): 2.23 | learning rate: 9.899E-05 | global batch size: 512 | lm loss: 2.014528E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.104 | TFLOPs: 23.69 | +63: iteration 40140/ 73814 | consumed samples: 20551680 | consumed tokens: 42089840640 | elapsed time per iteration (s): 2.22 | learning rate: 9.895E-05 | global batch size: 512 | lm loss: 2.002719E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.138 | TFLOPs: 23.69 | +63: iteration 40150/ 73814 | consumed samples: 20556800 | consumed tokens: 42100326400 | elapsed time per iteration (s): 2.27 | learning rate: 9.891E-05 | global batch size: 512 | lm loss: 2.026658E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.957 | TFLOPs: 23.26 | +63: iteration 40160/ 73814 | consumed samples: 20561920 | consumed tokens: 42110812160 | elapsed time per iteration (s): 2.25 | learning rate: 9.887E-05 | global batch size: 512 | lm loss: 2.016565E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.606 | TFLOPs: 23.43 | +63: iteration 40170/ 73814 | consumed samples: 20567040 | consumed tokens: 42121297920 | elapsed time per iteration (s): 2.26 | learning rate: 9.883E-05 | global batch size: 512 | lm loss: 1.984850E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.901 | TFLOPs: 23.36 | +63: iteration 40180/ 73814 | consumed samples: 20572160 | consumed tokens: 42131783680 | elapsed time per iteration (s): 2.25 | learning rate: 9.879E-05 | global batch size: 512 | lm loss: 2.010235E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.500 | TFLOPs: 23.42 | +63: iteration 40190/ 73814 | consumed samples: 20577280 | consumed tokens: 42142269440 | elapsed time per iteration (s): 2.29 | learning rate: 9.876E-05 | global batch size: 512 | lm loss: 1.998933E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.902 | TFLOPs: 23.05 | +63: iteration 40200/ 73814 | consumed samples: 20582400 | consumed tokens: 42152755200 | elapsed time per iteration (s): 2.24 | learning rate: 9.872E-05 | global batch size: 512 | lm loss: 1.994086E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.771 | TFLOPs: 23.55 | +63: iteration 40210/ 73814 | consumed samples: 20587520 | consumed tokens: 42163240960 | elapsed time per iteration (s): 2.26 | learning rate: 9.868E-05 | global batch size: 512 | lm loss: 1.996788E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.852 | TFLOPs: 23.35 | +63: iteration 40220/ 73814 | consumed samples: 20592640 | consumed tokens: 42173726720 | elapsed time per iteration (s): 2.23 | learning rate: 9.864E-05 | global batch size: 512 | lm loss: 1.979151E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.118 | TFLOPs: 23.59 | +63: iteration 40230/ 73814 | consumed samples: 20597760 | consumed tokens: 42184212480 | elapsed time per iteration (s): 2.23 | learning rate: 9.860E-05 | global batch size: 512 | lm loss: 2.001910E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.519 | TFLOPs: 23.63 | +63: iteration 40240/ 73814 | consumed samples: 20602880 | consumed tokens: 42194698240 | elapsed time per iteration (s): 2.24 | learning rate: 9.856E-05 | global batch size: 512 | lm loss: 2.005043E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.270 | TFLOPs: 23.50 | +63: iteration 40250/ 73814 | consumed samples: 20608000 | consumed tokens: 42205184000 | elapsed time per iteration (s): 2.23 | learning rate: 9.853E-05 | global batch size: 512 | lm loss: 1.998999E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.077 | TFLOPs: 23.69 | +63: iteration 40260/ 73814 | consumed samples: 20613120 | consumed tokens: 42215669760 | elapsed time per iteration (s): 2.28 | learning rate: 9.849E-05 | global batch size: 512 | lm loss: 2.011421E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.844 | TFLOPs: 23.15 | +63: iteration 40270/ 73814 | consumed samples: 20618240 | consumed tokens: 42226155520 | elapsed time per iteration (s): 2.23 | learning rate: 9.845E-05 | global batch size: 512 | lm loss: 1.998799E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.096 | TFLOPs: 23.69 | +63: iteration 40280/ 73814 | consumed samples: 20623360 | consumed tokens: 42236641280 | elapsed time per iteration (s): 2.23 | learning rate: 9.841E-05 | global batch size: 512 | lm loss: 2.003573E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.700 | TFLOPs: 23.65 | +63: iteration 40290/ 73814 | consumed samples: 20628480 | consumed tokens: 42247127040 | elapsed time per iteration (s): 2.33 | learning rate: 9.837E-05 | global batch size: 512 | lm loss: 2.007387E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.193 | TFLOPs: 22.67 | +63: iteration 40300/ 73814 | consumed samples: 20633600 | consumed tokens: 42257612800 | elapsed time per iteration (s): 2.25 | learning rate: 9.833E-05 | global batch size: 512 | lm loss: 1.999702E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.858 | TFLOPs: 23.46 | +63: iteration 40310/ 73814 | consumed samples: 20638720 | consumed tokens: 42268098560 | elapsed time per iteration (s): 2.39 | learning rate: 9.830E-05 | global batch size: 512 | lm loss: 2.016813E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.366 | TFLOPs: 22.07 | +63: iteration 40320/ 73814 | consumed samples: 20643840 | consumed tokens: 42278584320 | elapsed time per iteration (s): 2.24 | learning rate: 9.826E-05 | global batch size: 512 | lm loss: 1.994291E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.854 | TFLOPs: 23.56 | +63: iteration 40330/ 73814 | consumed samples: 20648960 | consumed tokens: 42289070080 | elapsed time per iteration (s): 2.23 | learning rate: 9.822E-05 | global batch size: 512 | lm loss: 1.983353E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.838 | TFLOPs: 23.66 | +63: iteration 40340/ 73814 | consumed samples: 20654080 | consumed tokens: 42299555840 | elapsed time per iteration (s): 2.30 | learning rate: 9.818E-05 | global batch size: 512 | lm loss: 1.995665E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.687 | TFLOPs: 22.92 | +63: iteration 40350/ 73814 | consumed samples: 20659200 | consumed tokens: 42310041600 | elapsed time per iteration (s): 2.26 | learning rate: 9.814E-05 | global batch size: 512 | lm loss: 1.998980E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.958 | TFLOPs: 23.36 | +63: iteration 40360/ 73814 | consumed samples: 20664320 | consumed tokens: 42320527360 | elapsed time per iteration (s): 2.23 | learning rate: 9.810E-05 | global batch size: 512 | lm loss: 1.986521E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.102 | TFLOPs: 23.69 | +63: iteration 40370/ 73814 | consumed samples: 20669440 | consumed tokens: 42331013120 | elapsed time per iteration (s): 2.24 | learning rate: 9.807E-05 | global batch size: 512 | lm loss: 1.998803E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.431 | TFLOPs: 23.52 | +63: iteration 40380/ 73814 | consumed samples: 20674560 | consumed tokens: 42341498880 | elapsed time per iteration (s): 2.23 | learning rate: 9.803E-05 | global batch size: 512 | lm loss: 2.024501E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.826 | TFLOPs: 23.66 | +63: iteration 40390/ 73814 | consumed samples: 20679680 | consumed tokens: 42351984640 | elapsed time per iteration (s): 2.27 | learning rate: 9.799E-05 | global batch size: 512 | lm loss: 2.009161E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.048 | TFLOPs: 23.27 | +63: iteration 40400/ 73814 | consumed samples: 20684800 | consumed tokens: 42362470400 | elapsed time per iteration (s): 2.22 | learning rate: 9.795E-05 | global batch size: 512 | lm loss: 2.027276E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.151 | TFLOPs: 23.69 | +63: iteration 40410/ 73814 | consumed samples: 20689920 | consumed tokens: 42372956160 | elapsed time per iteration (s): 2.40 | learning rate: 9.791E-05 | global batch size: 512 | lm loss: 2.017634E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.039 | TFLOPs: 21.93 | +63: iteration 40420/ 73814 | consumed samples: 20695040 | consumed tokens: 42383441920 | elapsed time per iteration (s): 2.27 | learning rate: 9.787E-05 | global batch size: 512 | lm loss: 2.005609E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.281 | TFLOPs: 23.19 | +63: iteration 40430/ 73814 | consumed samples: 20700160 | consumed tokens: 42393927680 | elapsed time per iteration (s): 2.23 | learning rate: 9.784E-05 | global batch size: 512 | lm loss: 1.995474E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.877 | TFLOPs: 23.66 | +63: iteration 40440/ 73814 | consumed samples: 20705280 | consumed tokens: 42404413440 | elapsed time per iteration (s): 2.23 | learning rate: 9.780E-05 | global batch size: 512 | lm loss: 1.997894E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.047 | TFLOPs: 23.68 | +63: iteration 40450/ 73814 | consumed samples: 20710400 | consumed tokens: 42414899200 | elapsed time per iteration (s): 2.23 | learning rate: 9.776E-05 | global batch size: 512 | lm loss: 2.017243E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.446 | TFLOPs: 23.62 | +63: iteration 40460/ 73814 | consumed samples: 20715520 | consumed tokens: 42425384960 | elapsed time per iteration (s): 2.34 | learning rate: 9.772E-05 | global batch size: 512 | lm loss: 1.995308E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.985 | TFLOPs: 22.54 | +63: iteration 40470/ 73814 | consumed samples: 20720640 | consumed tokens: 42435870720 | elapsed time per iteration (s): 2.28 | learning rate: 9.768E-05 | global batch size: 512 | lm loss: 1.993442E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.118 | TFLOPs: 23.07 | +63: iteration 40480/ 73814 | consumed samples: 20725760 | consumed tokens: 42446356480 | elapsed time per iteration (s): 2.24 | learning rate: 9.764E-05 | global batch size: 512 | lm loss: 2.006358E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.192 | TFLOPs: 23.49 | +63: iteration 40490/ 73814 | consumed samples: 20730880 | consumed tokens: 42456842240 | elapsed time per iteration (s): 4.26 | learning rate: 9.761E-05 | global batch size: 512 | lm loss: 1.999538E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 120.228 | TFLOPs: 12.38 | +63: iteration 40500/ 73814 | consumed samples: 20736000 | consumed tokens: 42467328000 | elapsed time per iteration (s): 2.25 | learning rate: 9.757E-05 | global batch size: 512 | lm loss: 2.001477E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.916 | TFLOPs: 23.46 | +63: iteration 40510/ 73814 | consumed samples: 20741120 | consumed tokens: 42477813760 | elapsed time per iteration (s): 2.32 | learning rate: 9.753E-05 | global batch size: 512 | lm loss: 1.996955E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.325 | TFLOPs: 22.68 | +63: iteration 40520/ 73814 | consumed samples: 20746240 | consumed tokens: 42488299520 | elapsed time per iteration (s): 2.23 | learning rate: 9.749E-05 | global batch size: 512 | lm loss: 1.980710E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.107 | TFLOPs: 23.69 | +63: iteration 40530/ 73814 | consumed samples: 20751360 | consumed tokens: 42498785280 | elapsed time per iteration (s): 2.23 | learning rate: 9.745E-05 | global batch size: 512 | lm loss: 2.000914E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.800 | TFLOPs: 23.66 | +63: iteration 40540/ 73814 | consumed samples: 20756480 | consumed tokens: 42509271040 | elapsed time per iteration (s): 2.24 | learning rate: 9.741E-05 | global batch size: 512 | lm loss: 1.981577E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.083 | TFLOPs: 23.48 | +63: iteration 40550/ 73814 | consumed samples: 20761600 | consumed tokens: 42519756800 | elapsed time per iteration (s): 2.23 | learning rate: 9.738E-05 | global batch size: 512 | lm loss: 1.998604E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.652 | TFLOPs: 23.64 | +63: iteration 40560/ 73814 | consumed samples: 20766720 | consumed tokens: 42530242560 | elapsed time per iteration (s): 2.23 | learning rate: 9.734E-05 | global batch size: 512 | lm loss: 2.016539E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.620 | TFLOPs: 23.64 | +63: iteration 40570/ 73814 | consumed samples: 20771840 | consumed tokens: 42540728320 | elapsed time per iteration (s): 2.24 | learning rate: 9.730E-05 | global batch size: 512 | lm loss: 1.985109E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.344 | TFLOPs: 23.51 | +63: iteration 40580/ 73814 | consumed samples: 20776960 | consumed tokens: 42551214080 | elapsed time per iteration (s): 2.39 | learning rate: 9.726E-05 | global batch size: 512 | lm loss: 1.981616E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.393 | TFLOPs: 22.07 | +63: iteration 40590/ 73814 | consumed samples: 20782080 | consumed tokens: 42561699840 | elapsed time per iteration (s): 2.29 | learning rate: 9.722E-05 | global batch size: 512 | lm loss: 1.999913E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.640 | TFLOPs: 23.02 | +63: iteration 40600/ 73814 | consumed samples: 20787200 | consumed tokens: 42572185600 | elapsed time per iteration (s): 2.33 | learning rate: 9.718E-05 | global batch size: 512 | lm loss: 1.997407E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.633 | TFLOPs: 22.61 | +63: iteration 40610/ 73814 | consumed samples: 20792320 | consumed tokens: 42582671360 | elapsed time per iteration (s): 2.52 | learning rate: 9.715E-05 | global batch size: 512 | lm loss: 1.998789E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 203.076 | TFLOPs: 20.91 | +63: iteration 40620/ 73814 | consumed samples: 20797440 | consumed tokens: 42593157120 | elapsed time per iteration (s): 2.24 | learning rate: 9.711E-05 | global batch size: 512 | lm loss: 1.980519E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.369 | TFLOPs: 23.51 | +63: iteration 40630/ 73814 | consumed samples: 20802560 | consumed tokens: 42603642880 | elapsed time per iteration (s): 2.50 | learning rate: 9.707E-05 | global batch size: 512 | lm loss: 1.997452E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 204.838 | TFLOPs: 21.09 | +63: iteration 40640/ 73814 | consumed samples: 20807680 | consumed tokens: 42614128640 | elapsed time per iteration (s): 2.58 | learning rate: 9.703E-05 | global batch size: 512 | lm loss: 2.010098E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.183 | TFLOPs: 20.40 | +63: iteration 40650/ 73814 | consumed samples: 20812800 | consumed tokens: 42624614400 | elapsed time per iteration (s): 2.87 | learning rate: 9.699E-05 | global batch size: 512 | lm loss: 2.001822E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 178.122 | TFLOPs: 18.34 | +63: iteration 40660/ 73814 | consumed samples: 20817920 | consumed tokens: 42635100160 | elapsed time per iteration (s): 2.74 | learning rate: 9.695E-05 | global batch size: 512 | lm loss: 1.975926E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 186.935 | TFLOPs: 19.24 | +63: iteration 40670/ 73814 | consumed samples: 20823040 | consumed tokens: 42645585920 | elapsed time per iteration (s): 2.46 | learning rate: 9.692E-05 | global batch size: 512 | lm loss: 1.977275E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.074 | TFLOPs: 21.42 | +63: iteration 40680/ 73814 | consumed samples: 20828160 | consumed tokens: 42656071680 | elapsed time per iteration (s): 2.48 | learning rate: 9.688E-05 | global batch size: 512 | lm loss: 2.005357E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.720 | TFLOPs: 21.28 | +63: iteration 40690/ 73814 | consumed samples: 20833280 | consumed tokens: 42666557440 | elapsed time per iteration (s): 2.37 | learning rate: 9.684E-05 | global batch size: 512 | lm loss: 1.985281E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.645 | TFLOPs: 22.20 | +63: iteration 40700/ 73814 | consumed samples: 20838400 | consumed tokens: 42677043200 | elapsed time per iteration (s): 2.31 | learning rate: 9.680E-05 | global batch size: 512 | lm loss: 2.010582E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.923 | TFLOPs: 22.85 | +63: iteration 40710/ 73814 | consumed samples: 20843520 | consumed tokens: 42687528960 | elapsed time per iteration (s): 2.25 | learning rate: 9.676E-05 | global batch size: 512 | lm loss: 1.981792E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.616 | TFLOPs: 23.43 | +63: iteration 40720/ 73814 | consumed samples: 20848640 | consumed tokens: 42698014720 | elapsed time per iteration (s): 2.23 | learning rate: 9.672E-05 | global batch size: 512 | lm loss: 1.999323E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.013 | TFLOPs: 23.68 | +63: iteration 40730/ 73814 | consumed samples: 20853760 | consumed tokens: 42708500480 | elapsed time per iteration (s): 2.24 | learning rate: 9.669E-05 | global batch size: 512 | lm loss: 2.016012E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.733 | TFLOPs: 23.55 | +63: iteration 40740/ 73814 | consumed samples: 20858880 | consumed tokens: 42718986240 | elapsed time per iteration (s): 2.25 | learning rate: 9.665E-05 | global batch size: 512 | lm loss: 1.987275E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.169 | TFLOPs: 23.39 | +63: iteration 40750/ 73814 | consumed samples: 20864000 | consumed tokens: 42729472000 | elapsed time per iteration (s): 2.23 | learning rate: 9.661E-05 | global batch size: 512 | lm loss: 1.988405E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.894 | TFLOPs: 23.67 | +63: iteration 40760/ 73814 | consumed samples: 20869120 | consumed tokens: 42739957760 | elapsed time per iteration (s): 2.23 | learning rate: 9.657E-05 | global batch size: 512 | lm loss: 2.009334E+00 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.499 | TFLOPs: 23.63 | +63: iteration 40770/ 73814 | consumed samples: 20874240 | consumed tokens: 42750443520 | elapsed time per iteration (s): 2.24 | learning rate: 9.653E-05 | global batch size: 512 | lm loss: 2.013394E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.122 | TFLOPs: 23.48 | +63: iteration 40780/ 73814 | consumed samples: 20879360 | consumed tokens: 42760929280 | elapsed time per iteration (s): 2.23 | learning rate: 9.649E-05 | global batch size: 512 | lm loss: 2.015082E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.916 | TFLOPs: 23.67 | +63: iteration 40790/ 73814 | consumed samples: 20884480 | consumed tokens: 42771415040 | elapsed time per iteration (s): 2.55 | learning rate: 9.646E-05 | global batch size: 512 | lm loss: 1.992918E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.555 | TFLOPs: 20.65 | +63: iteration 40800/ 73814 | consumed samples: 20889600 | consumed tokens: 42781900800 | elapsed time per iteration (s): 2.25 | learning rate: 9.642E-05 | global batch size: 512 | lm loss: 2.001102E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.059 | TFLOPs: 23.37 | +63: iteration 40810/ 73814 | consumed samples: 20894720 | consumed tokens: 42792386560 | elapsed time per iteration (s): 2.22 | learning rate: 9.638E-05 | global batch size: 512 | lm loss: 2.009712E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.515 | TFLOPs: 23.73 | +63: iteration 40820/ 73814 | consumed samples: 20899840 | consumed tokens: 42802872320 | elapsed time per iteration (s): 2.23 | learning rate: 9.634E-05 | global batch size: 512 | lm loss: 1.985346E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.727 | TFLOPs: 23.65 | +63: iteration 40830/ 73814 | consumed samples: 20904960 | consumed tokens: 42813358080 | elapsed time per iteration (s): 2.23 | learning rate: 9.630E-05 | global batch size: 512 | lm loss: 2.014160E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.289 | TFLOPs: 23.60 | +63: iteration 40840/ 73814 | consumed samples: 20910080 | consumed tokens: 42823843840 | elapsed time per iteration (s): 2.23 | learning rate: 9.627E-05 | global batch size: 512 | lm loss: 2.001236E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.421 | TFLOPs: 23.62 | +63: iteration 40850/ 73814 | consumed samples: 20915200 | consumed tokens: 42834329600 | elapsed time per iteration (s): 2.23 | learning rate: 9.623E-05 | global batch size: 512 | lm loss: 1.968908E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.632 | TFLOPs: 23.64 | +63: iteration 40860/ 73814 | consumed samples: 20920320 | consumed tokens: 42844815360 | elapsed time per iteration (s): 2.30 | learning rate: 9.619E-05 | global batch size: 512 | lm loss: 2.020047E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.533 | TFLOPs: 22.91 | +63: iteration 40870/ 73814 | consumed samples: 20925440 | consumed tokens: 42855301120 | elapsed time per iteration (s): 2.36 | learning rate: 9.615E-05 | global batch size: 512 | lm loss: 2.008141E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.173 | TFLOPs: 22.36 | +63: iteration 40880/ 73814 | consumed samples: 20930560 | consumed tokens: 42865786880 | elapsed time per iteration (s): 2.33 | learning rate: 9.611E-05 | global batch size: 512 | lm loss: 2.016975E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.436 | TFLOPs: 22.59 | +63: iteration 40890/ 73814 | consumed samples: 20935680 | consumed tokens: 42876272640 | elapsed time per iteration (s): 2.23 | learning rate: 9.607E-05 | global batch size: 512 | lm loss: 1.972599E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.607 | TFLOPs: 23.64 | +63: iteration 40900/ 73814 | consumed samples: 20940800 | consumed tokens: 42886758400 | elapsed time per iteration (s): 2.23 | learning rate: 9.604E-05 | global batch size: 512 | lm loss: 1.980848E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.005 | TFLOPs: 23.68 | +63: iteration 40910/ 73814 | consumed samples: 20945920 | consumed tokens: 42897244160 | elapsed time per iteration (s): 2.26 | learning rate: 9.600E-05 | global batch size: 512 | lm loss: 2.001053E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.324 | TFLOPs: 23.30 | +63: iteration 40920/ 73814 | consumed samples: 20951040 | consumed tokens: 42907729920 | elapsed time per iteration (s): 2.48 | learning rate: 9.596E-05 | global batch size: 512 | lm loss: 1.983488E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.405 | TFLOPs: 21.25 | +63: iteration 40930/ 73814 | consumed samples: 20956160 | consumed tokens: 42918215680 | elapsed time per iteration (s): 2.24 | learning rate: 9.592E-05 | global batch size: 512 | lm loss: 2.014838E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.569 | TFLOPs: 23.53 | +63: iteration 40940/ 73814 | consumed samples: 20961280 | consumed tokens: 42928701440 | elapsed time per iteration (s): 2.22 | learning rate: 9.588E-05 | global batch size: 512 | lm loss: 1.999858E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.539 | TFLOPs: 23.73 | +63: iteration 40950/ 73814 | consumed samples: 20966400 | consumed tokens: 42939187200 | elapsed time per iteration (s): 2.25 | learning rate: 9.584E-05 | global batch size: 512 | lm loss: 1.979016E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.587 | TFLOPs: 23.43 | +63: iteration 40960/ 73814 | consumed samples: 20971520 | consumed tokens: 42949672960 | elapsed time per iteration (s): 2.32 | learning rate: 9.581E-05 | global batch size: 512 | lm loss: 1.980503E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.119 | TFLOPs: 22.76 | +63: iteration 40970/ 73814 | consumed samples: 20976640 | consumed tokens: 42960158720 | elapsed time per iteration (s): 2.25 | learning rate: 9.577E-05 | global batch size: 512 | lm loss: 1.997428E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.161 | TFLOPs: 23.39 | +63: iteration 40980/ 73814 | consumed samples: 20981760 | consumed tokens: 42970644480 | elapsed time per iteration (s): 2.26 | learning rate: 9.573E-05 | global batch size: 512 | lm loss: 2.002820E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.452 | TFLOPs: 23.31 | +63: iteration 40990/ 73814 | consumed samples: 20986880 | consumed tokens: 42981130240 | elapsed time per iteration (s): 2.24 | learning rate: 9.569E-05 | global batch size: 512 | lm loss: 1.995324E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.956 | TFLOPs: 23.57 | +63: iteration 41000/ 73814 | consumed samples: 20992000 | consumed tokens: 42991616000 | elapsed time per iteration (s): 2.28 | learning rate: 9.565E-05 | global batch size: 512 | lm loss: 2.036347E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.645 | TFLOPs: 23.13 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 41000 | lm loss value: 1.832782E+00 | lm loss PPL: 6.251255E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 41010/ 73814 | consumed samples: 20997120 | consumed tokens: 43002101760 | elapsed time per iteration (s): 2.30 | learning rate: 9.562E-05 | global batch size: 512 | lm loss: 2.003314E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.230 | TFLOPs: 22.88 | +63: iteration 41020/ 73814 | consumed samples: 21002240 | consumed tokens: 43012587520 | elapsed time per iteration (s): 2.23 | learning rate: 9.558E-05 | global batch size: 512 | lm loss: 1.994511E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.417 | TFLOPs: 23.62 | +63: iteration 41030/ 73814 | consumed samples: 21007360 | consumed tokens: 43023073280 | elapsed time per iteration (s): 2.23 | learning rate: 9.554E-05 | global batch size: 512 | lm loss: 2.007015E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.001 | TFLOPs: 23.68 | +63: iteration 41040/ 73814 | consumed samples: 21012480 | consumed tokens: 43033559040 | elapsed time per iteration (s): 2.23 | learning rate: 9.550E-05 | global batch size: 512 | lm loss: 2.003477E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.969 | TFLOPs: 23.67 | +63: iteration 41050/ 73814 | consumed samples: 21017600 | consumed tokens: 43044044800 | elapsed time per iteration (s): 2.28 | learning rate: 9.546E-05 | global batch size: 512 | lm loss: 1.998528E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.376 | TFLOPs: 23.10 | +63: iteration 41060/ 73814 | consumed samples: 21022720 | consumed tokens: 43054530560 | elapsed time per iteration (s): 2.23 | learning rate: 9.542E-05 | global batch size: 512 | lm loss: 1.995995E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.227 | TFLOPs: 23.60 | +63: iteration 41070/ 73814 | consumed samples: 21027840 | consumed tokens: 43065016320 | elapsed time per iteration (s): 2.23 | learning rate: 9.539E-05 | global batch size: 512 | lm loss: 2.008853E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.502 | TFLOPs: 23.63 | +63: iteration 41080/ 73814 | consumed samples: 21032960 | consumed tokens: 43075502080 | elapsed time per iteration (s): 2.23 | learning rate: 9.535E-05 | global batch size: 512 | lm loss: 1.973066E+00 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.570 | TFLOPs: 23.63 | +63: iteration 41090/ 73814 | consumed samples: 21038080 | consumed tokens: 43085987840 | elapsed time per iteration (s): 2.25 | learning rate: 9.531E-05 | global batch size: 512 | lm loss: 1.983258E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.053 | TFLOPs: 23.37 | +63: iteration 41100/ 73814 | consumed samples: 21043200 | consumed tokens: 43096473600 | elapsed time per iteration (s): 2.23 | learning rate: 9.527E-05 | global batch size: 512 | lm loss: 2.010387E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.257 | TFLOPs: 23.60 | +63: iteration 41110/ 73814 | consumed samples: 21048320 | consumed tokens: 43106959360 | elapsed time per iteration (s): 2.26 | learning rate: 9.523E-05 | global batch size: 512 | lm loss: 1.982091E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.561 | TFLOPs: 23.32 | +63: iteration 41120/ 73814 | consumed samples: 21053440 | consumed tokens: 43117445120 | elapsed time per iteration (s): 2.31 | learning rate: 9.520E-05 | global batch size: 512 | lm loss: 2.009569E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.762 | TFLOPs: 22.83 | +63: iteration 41130/ 73814 | consumed samples: 21058560 | consumed tokens: 43127930880 | elapsed time per iteration (s): 2.23 | learning rate: 9.516E-05 | global batch size: 512 | lm loss: 2.040984E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.686 | TFLOPs: 23.65 | +63: iteration 41140/ 73814 | consumed samples: 21063680 | consumed tokens: 43138416640 | elapsed time per iteration (s): 2.25 | learning rate: 9.512E-05 | global batch size: 512 | lm loss: 2.009810E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.059 | TFLOPs: 23.37 | +63: iteration 41150/ 73814 | consumed samples: 21068800 | consumed tokens: 43148902400 | elapsed time per iteration (s): 2.27 | learning rate: 9.508E-05 | global batch size: 512 | lm loss: 2.006852E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.420 | TFLOPs: 23.21 | +63: iteration 41160/ 73814 | consumed samples: 21073920 | consumed tokens: 43159388160 | elapsed time per iteration (s): 2.23 | learning rate: 9.504E-05 | global batch size: 512 | lm loss: 1.994068E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.014 | TFLOPs: 23.68 | +63: iteration 41170/ 73814 | consumed samples: 21079040 | consumed tokens: 43169873920 | elapsed time per iteration (s): 2.32 | learning rate: 9.500E-05 | global batch size: 512 | lm loss: 2.000344E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.691 | TFLOPs: 22.72 | +63: iteration 41180/ 73814 | consumed samples: 21084160 | consumed tokens: 43180359680 | elapsed time per iteration (s): 2.22 | learning rate: 9.497E-05 | global batch size: 512 | lm loss: 2.009047E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.408 | TFLOPs: 23.72 | +63: iteration 41190/ 73814 | consumed samples: 21089280 | consumed tokens: 43190845440 | elapsed time per iteration (s): 2.45 | learning rate: 9.493E-05 | global batch size: 512 | lm loss: 1.992085E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.174 | TFLOPs: 21.53 | +63: iteration 41200/ 73814 | consumed samples: 21094400 | consumed tokens: 43201331200 | elapsed time per iteration (s): 2.23 | learning rate: 9.489E-05 | global batch size: 512 | lm loss: 2.012639E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.486 | TFLOPs: 23.62 | +63: iteration 41210/ 73814 | consumed samples: 21099520 | consumed tokens: 43211816960 | elapsed time per iteration (s): 2.22 | learning rate: 9.485E-05 | global batch size: 512 | lm loss: 2.004745E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.288 | TFLOPs: 23.71 | +63: iteration 41220/ 73814 | consumed samples: 21104640 | consumed tokens: 43222302720 | elapsed time per iteration (s): 2.25 | learning rate: 9.481E-05 | global batch size: 512 | lm loss: 1.979698E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.901 | TFLOPs: 23.46 | +63: iteration 41230/ 73814 | consumed samples: 21109760 | consumed tokens: 43232788480 | elapsed time per iteration (s): 2.23 | learning rate: 9.478E-05 | global batch size: 512 | lm loss: 1.991466E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.575 | TFLOPs: 23.63 | +63: iteration 41240/ 73814 | consumed samples: 21114880 | consumed tokens: 43243274240 | elapsed time per iteration (s): 2.25 | learning rate: 9.474E-05 | global batch size: 512 | lm loss: 2.004390E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.969 | TFLOPs: 23.47 | +63: iteration 41250/ 73814 | consumed samples: 21120000 | consumed tokens: 43253760000 | elapsed time per iteration (s): 2.26 | learning rate: 9.470E-05 | global batch size: 512 | lm loss: 1.990750E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.871 | TFLOPs: 23.36 | +63: iteration 41260/ 73814 | consumed samples: 21125120 | consumed tokens: 43264245760 | elapsed time per iteration (s): 2.28 | learning rate: 9.466E-05 | global batch size: 512 | lm loss: 2.009385E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.888 | TFLOPs: 23.15 | +63: iteration 41270/ 73814 | consumed samples: 21130240 | consumed tokens: 43274731520 | elapsed time per iteration (s): 2.25 | learning rate: 9.462E-05 | global batch size: 512 | lm loss: 1.983531E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.916 | TFLOPs: 23.46 | +63: iteration 41280/ 73814 | consumed samples: 21135360 | consumed tokens: 43285217280 | elapsed time per iteration (s): 2.23 | learning rate: 9.459E-05 | global batch size: 512 | lm loss: 2.013388E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.193 | TFLOPs: 23.59 | +63: iteration 41290/ 73814 | consumed samples: 21140480 | consumed tokens: 43295703040 | elapsed time per iteration (s): 2.25 | learning rate: 9.455E-05 | global batch size: 512 | lm loss: 1.999899E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.676 | TFLOPs: 23.44 | +63: iteration 41300/ 73814 | consumed samples: 21145600 | consumed tokens: 43306188800 | elapsed time per iteration (s): 2.34 | learning rate: 9.451E-05 | global batch size: 512 | lm loss: 1.977480E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.808 | TFLOPs: 22.53 | +63: iteration 41310/ 73814 | consumed samples: 21150720 | consumed tokens: 43316674560 | elapsed time per iteration (s): 2.33 | learning rate: 9.447E-05 | global batch size: 512 | lm loss: 1.998182E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.106 | TFLOPs: 22.66 | +63: iteration 41320/ 73814 | consumed samples: 21155840 | consumed tokens: 43327160320 | elapsed time per iteration (s): 4.15 | learning rate: 9.443E-05 | global batch size: 512 | lm loss: 1.979099E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 123.250 | TFLOPs: 12.69 | +63: iteration 41330/ 73814 | consumed samples: 21160960 | consumed tokens: 43337646080 | elapsed time per iteration (s): 2.24 | learning rate: 9.439E-05 | global batch size: 512 | lm loss: 2.014748E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.214 | TFLOPs: 23.49 | +63: iteration 41340/ 73814 | consumed samples: 21166080 | consumed tokens: 43348131840 | elapsed time per iteration (s): 2.24 | learning rate: 9.436E-05 | global batch size: 512 | lm loss: 1.988796E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.710 | TFLOPs: 23.54 | +63: iteration 41350/ 73814 | consumed samples: 21171200 | consumed tokens: 43358617600 | elapsed time per iteration (s): 2.24 | learning rate: 9.432E-05 | global batch size: 512 | lm loss: 1.985343E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.303 | TFLOPs: 23.50 | +63: iteration 41360/ 73814 | consumed samples: 21176320 | consumed tokens: 43369103360 | elapsed time per iteration (s): 2.23 | learning rate: 9.428E-05 | global batch size: 512 | lm loss: 1.991965E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.628 | TFLOPs: 23.64 | +63: iteration 41370/ 73814 | consumed samples: 21181440 | consumed tokens: 43379589120 | elapsed time per iteration (s): 2.26 | learning rate: 9.424E-05 | global batch size: 512 | lm loss: 1.992752E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.664 | TFLOPs: 23.33 | +63: iteration 41380/ 73814 | consumed samples: 21186560 | consumed tokens: 43390074880 | elapsed time per iteration (s): 2.31 | learning rate: 9.420E-05 | global batch size: 512 | lm loss: 1.989740E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.194 | TFLOPs: 22.77 | +63: iteration 41390/ 73814 | consumed samples: 21191680 | consumed tokens: 43400560640 | elapsed time per iteration (s): 2.27 | learning rate: 9.417E-05 | global batch size: 512 | lm loss: 1.990519E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.158 | TFLOPs: 23.18 | +63: iteration 41400/ 73814 | consumed samples: 21196800 | consumed tokens: 43411046400 | elapsed time per iteration (s): 2.25 | learning rate: 9.413E-05 | global batch size: 512 | lm loss: 1.999193E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.972 | TFLOPs: 23.47 | +63: iteration 41410/ 73814 | consumed samples: 21201920 | consumed tokens: 43421532160 | elapsed time per iteration (s): 2.33 | learning rate: 9.409E-05 | global batch size: 512 | lm loss: 2.006179E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.808 | TFLOPs: 22.63 | +63: iteration 41420/ 73814 | consumed samples: 21207040 | consumed tokens: 43432017920 | elapsed time per iteration (s): 2.24 | learning rate: 9.405E-05 | global batch size: 512 | lm loss: 1.998776E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.867 | TFLOPs: 23.56 | +63: iteration 41430/ 73814 | consumed samples: 21212160 | consumed tokens: 43442503680 | elapsed time per iteration (s): 2.27 | learning rate: 9.401E-05 | global batch size: 512 | lm loss: 1.992333E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.271 | TFLOPs: 23.19 | +63: iteration 41440/ 73814 | consumed samples: 21217280 | consumed tokens: 43452989440 | elapsed time per iteration (s): 2.25 | learning rate: 9.398E-05 | global batch size: 512 | lm loss: 1.964636E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.793 | TFLOPs: 23.45 | +63: iteration 41450/ 73814 | consumed samples: 21222400 | consumed tokens: 43463475200 | elapsed time per iteration (s): 2.25 | learning rate: 9.394E-05 | global batch size: 512 | lm loss: 1.994714E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.329 | TFLOPs: 23.40 | +63: iteration 41460/ 73814 | consumed samples: 21227520 | consumed tokens: 43473960960 | elapsed time per iteration (s): 2.23 | learning rate: 9.390E-05 | global batch size: 512 | lm loss: 1.996685E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.763 | TFLOPs: 23.65 | +63: iteration 41470/ 73814 | consumed samples: 21232640 | consumed tokens: 43484446720 | elapsed time per iteration (s): 2.25 | learning rate: 9.386E-05 | global batch size: 512 | lm loss: 1.995057E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.912 | TFLOPs: 23.46 | +63: iteration 41480/ 73814 | consumed samples: 21237760 | consumed tokens: 43494932480 | elapsed time per iteration (s): 2.25 | learning rate: 9.382E-05 | global batch size: 512 | lm loss: 2.004070E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.864 | TFLOPs: 23.46 | +63: iteration 41490/ 73814 | consumed samples: 21242880 | consumed tokens: 43505418240 | elapsed time per iteration (s): 2.23 | learning rate: 9.379E-05 | global batch size: 512 | lm loss: 2.004132E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.382 | TFLOPs: 23.61 | +63: iteration 41500/ 73814 | consumed samples: 21248000 | consumed tokens: 43515904000 | elapsed time per iteration (s): 2.24 | learning rate: 9.375E-05 | global batch size: 512 | lm loss: 1.984583E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.109 | TFLOPs: 23.48 | +63: iteration 41510/ 73814 | consumed samples: 21253120 | consumed tokens: 43526389760 | elapsed time per iteration (s): 2.23 | learning rate: 9.371E-05 | global batch size: 512 | lm loss: 2.003115E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.100 | TFLOPs: 23.69 | +63: iteration 41520/ 73814 | consumed samples: 21258240 | consumed tokens: 43536875520 | elapsed time per iteration (s): 2.23 | learning rate: 9.367E-05 | global batch size: 512 | lm loss: 2.008906E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.818 | TFLOPs: 23.66 | +63: iteration 41530/ 73814 | consumed samples: 21263360 | consumed tokens: 43547361280 | elapsed time per iteration (s): 2.25 | learning rate: 9.363E-05 | global batch size: 512 | lm loss: 1.976356E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.938 | TFLOPs: 23.47 | +63: iteration 41540/ 73814 | consumed samples: 21268480 | consumed tokens: 43557847040 | elapsed time per iteration (s): 2.24 | learning rate: 9.360E-05 | global batch size: 512 | lm loss: 2.009490E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.712 | TFLOPs: 23.54 | +63: iteration 41550/ 73814 | consumed samples: 21273600 | consumed tokens: 43568332800 | elapsed time per iteration (s): 2.23 | learning rate: 9.356E-05 | global batch size: 512 | lm loss: 1.985887E+00 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.098 | TFLOPs: 23.69 | +63: iteration 41560/ 73814 | consumed samples: 21278720 | consumed tokens: 43578818560 | elapsed time per iteration (s): 2.23 | learning rate: 9.352E-05 | global batch size: 512 | lm loss: 1.990701E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.641 | TFLOPs: 23.64 | +63: iteration 41570/ 73814 | consumed samples: 21283840 | consumed tokens: 43589304320 | elapsed time per iteration (s): 2.24 | learning rate: 9.348E-05 | global batch size: 512 | lm loss: 1.970676E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.477 | TFLOPs: 23.52 | +63: iteration 41580/ 73814 | consumed samples: 21288960 | consumed tokens: 43599790080 | elapsed time per iteration (s): 2.24 | learning rate: 9.344E-05 | global batch size: 512 | lm loss: 1.985746E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.403 | TFLOPs: 23.51 | +63: iteration 41590/ 73814 | consumed samples: 21294080 | consumed tokens: 43610275840 | elapsed time per iteration (s): 2.25 | learning rate: 9.341E-05 | global batch size: 512 | lm loss: 1.996790E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.817 | TFLOPs: 23.45 | +63: iteration 41600/ 73814 | consumed samples: 21299200 | consumed tokens: 43620761600 | elapsed time per iteration (s): 2.23 | learning rate: 9.337E-05 | global batch size: 512 | lm loss: 1.978391E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.085 | TFLOPs: 23.69 | +63: iteration 41610/ 73814 | consumed samples: 21304320 | consumed tokens: 43631247360 | elapsed time per iteration (s): 2.25 | learning rate: 9.333E-05 | global batch size: 512 | lm loss: 1.974725E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.199 | TFLOPs: 23.39 | +63: iteration 41620/ 73814 | consumed samples: 21309440 | consumed tokens: 43641733120 | elapsed time per iteration (s): 2.23 | learning rate: 9.329E-05 | global batch size: 512 | lm loss: 1.981678E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.884 | TFLOPs: 23.67 | +63: iteration 41630/ 73814 | consumed samples: 21314560 | consumed tokens: 43652218880 | elapsed time per iteration (s): 2.23 | learning rate: 9.325E-05 | global batch size: 512 | lm loss: 2.001249E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.506 | TFLOPs: 23.63 | +63: iteration 41640/ 73814 | consumed samples: 21319680 | consumed tokens: 43662704640 | elapsed time per iteration (s): 2.24 | learning rate: 9.321E-05 | global batch size: 512 | lm loss: 1.978114E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.155 | TFLOPs: 23.49 | +63: iteration 41650/ 73814 | consumed samples: 21324800 | consumed tokens: 43673190400 | elapsed time per iteration (s): 2.31 | learning rate: 9.318E-05 | global batch size: 512 | lm loss: 1.964407E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.722 | TFLOPs: 22.83 | +63: iteration 41660/ 73814 | consumed samples: 21329920 | consumed tokens: 43683676160 | elapsed time per iteration (s): 2.23 | learning rate: 9.314E-05 | global batch size: 512 | lm loss: 1.967489E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.185 | TFLOPs: 23.59 | +63: iteration 41670/ 73814 | consumed samples: 21335040 | consumed tokens: 43694161920 | elapsed time per iteration (s): 2.24 | learning rate: 9.310E-05 | global batch size: 512 | lm loss: 2.020113E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.150 | TFLOPs: 23.49 | +63: iteration 41680/ 73814 | consumed samples: 21340160 | consumed tokens: 43704647680 | elapsed time per iteration (s): 2.23 | learning rate: 9.306E-05 | global batch size: 512 | lm loss: 1.967582E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.534 | TFLOPs: 23.63 | +63: iteration 41690/ 73814 | consumed samples: 21345280 | consumed tokens: 43715133440 | elapsed time per iteration (s): 2.22 | learning rate: 9.302E-05 | global batch size: 512 | lm loss: 1.998160E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.187 | TFLOPs: 23.70 | +63: iteration 41700/ 73814 | consumed samples: 21350400 | consumed tokens: 43725619200 | elapsed time per iteration (s): 2.40 | learning rate: 9.299E-05 | global batch size: 512 | lm loss: 1.999553E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.918 | TFLOPs: 21.92 | +63: iteration 41710/ 73814 | consumed samples: 21355520 | consumed tokens: 43736104960 | elapsed time per iteration (s): 2.24 | learning rate: 9.295E-05 | global batch size: 512 | lm loss: 2.005446E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.251 | TFLOPs: 23.50 | +63: iteration 41720/ 73814 | consumed samples: 21360640 | consumed tokens: 43746590720 | elapsed time per iteration (s): 2.34 | learning rate: 9.291E-05 | global batch size: 512 | lm loss: 1.992903E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.938 | TFLOPs: 22.54 | +63: iteration 41730/ 73814 | consumed samples: 21365760 | consumed tokens: 43757076480 | elapsed time per iteration (s): 2.23 | learning rate: 9.287E-05 | global batch size: 512 | lm loss: 1.982897E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.251 | TFLOPs: 23.60 | +63: iteration 41740/ 73814 | consumed samples: 21370880 | consumed tokens: 43767562240 | elapsed time per iteration (s): 2.52 | learning rate: 9.283E-05 | global batch size: 512 | lm loss: 1.989207E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 203.437 | TFLOPs: 20.94 | +63: iteration 41750/ 73814 | consumed samples: 21376000 | consumed tokens: 43778048000 | elapsed time per iteration (s): 2.34 | learning rate: 9.280E-05 | global batch size: 512 | lm loss: 1.991045E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.130 | TFLOPs: 22.56 | +63: iteration 41760/ 73814 | consumed samples: 21381120 | consumed tokens: 43788533760 | elapsed time per iteration (s): 2.43 | learning rate: 9.276E-05 | global batch size: 512 | lm loss: 2.005239E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.847 | TFLOPs: 21.71 | +63: iteration 41770/ 73814 | consumed samples: 21386240 | consumed tokens: 43799019520 | elapsed time per iteration (s): 2.28 | learning rate: 9.272E-05 | global batch size: 512 | lm loss: 1.993422E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.412 | TFLOPs: 23.10 | +63: iteration 41780/ 73814 | consumed samples: 21391360 | consumed tokens: 43809505280 | elapsed time per iteration (s): 2.24 | learning rate: 9.268E-05 | global batch size: 512 | lm loss: 2.001925E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.219 | TFLOPs: 23.49 | +63: iteration 41790/ 73814 | consumed samples: 21396480 | consumed tokens: 43819991040 | elapsed time per iteration (s): 2.24 | learning rate: 9.265E-05 | global batch size: 512 | lm loss: 1.982668E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.522 | TFLOPs: 23.53 | +63: iteration 41800/ 73814 | consumed samples: 21401600 | consumed tokens: 43830476800 | elapsed time per iteration (s): 2.26 | learning rate: 9.261E-05 | global batch size: 512 | lm loss: 1.994062E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.278 | TFLOPs: 23.29 | +63: iteration 41810/ 73814 | consumed samples: 21406720 | consumed tokens: 43840962560 | elapsed time per iteration (s): 2.24 | learning rate: 9.257E-05 | global batch size: 512 | lm loss: 2.005546E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.524 | TFLOPs: 23.53 | +63: iteration 41820/ 73814 | consumed samples: 21411840 | consumed tokens: 43851448320 | elapsed time per iteration (s): 2.23 | learning rate: 9.253E-05 | global batch size: 512 | lm loss: 1.991032E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.479 | TFLOPs: 23.62 | +63: iteration 41830/ 73814 | consumed samples: 21416960 | consumed tokens: 43861934080 | elapsed time per iteration (s): 2.25 | learning rate: 9.249E-05 | global batch size: 512 | lm loss: 2.001617E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.878 | TFLOPs: 23.46 | +63: iteration 41840/ 73814 | consumed samples: 21422080 | consumed tokens: 43872419840 | elapsed time per iteration (s): 2.25 | learning rate: 9.246E-05 | global batch size: 512 | lm loss: 2.027126E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.033 | TFLOPs: 23.47 | +63: iteration 41850/ 73814 | consumed samples: 21427200 | consumed tokens: 43882905600 | elapsed time per iteration (s): 2.24 | learning rate: 9.242E-05 | global batch size: 512 | lm loss: 1.991348E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.723 | TFLOPs: 23.55 | +63: iteration 41860/ 73814 | consumed samples: 21432320 | consumed tokens: 43893391360 | elapsed time per iteration (s): 2.23 | learning rate: 9.238E-05 | global batch size: 512 | lm loss: 2.004144E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.617 | TFLOPs: 23.64 | +63: iteration 41870/ 73814 | consumed samples: 21437440 | consumed tokens: 43903877120 | elapsed time per iteration (s): 2.24 | learning rate: 9.234E-05 | global batch size: 512 | lm loss: 1.981774E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.750 | TFLOPs: 23.55 | +63: iteration 41880/ 73814 | consumed samples: 21442560 | consumed tokens: 43914362880 | elapsed time per iteration (s): 2.24 | learning rate: 9.230E-05 | global batch size: 512 | lm loss: 1.970384E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.131 | TFLOPs: 23.49 | +63: iteration 41890/ 73814 | consumed samples: 21447680 | consumed tokens: 43924848640 | elapsed time per iteration (s): 2.25 | learning rate: 9.227E-05 | global batch size: 512 | lm loss: 2.002812E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.735 | TFLOPs: 23.44 | +63: iteration 41900/ 73814 | consumed samples: 21452800 | consumed tokens: 43935334400 | elapsed time per iteration (s): 2.25 | learning rate: 9.223E-05 | global batch size: 512 | lm loss: 1.986122E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.699 | TFLOPs: 23.44 | +63: iteration 41910/ 73814 | consumed samples: 21457920 | consumed tokens: 43945820160 | elapsed time per iteration (s): 2.24 | learning rate: 9.219E-05 | global batch size: 512 | lm loss: 1.985447E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.135 | TFLOPs: 23.49 | +63: iteration 41920/ 73814 | consumed samples: 21463040 | consumed tokens: 43956305920 | elapsed time per iteration (s): 2.25 | learning rate: 9.215E-05 | global batch size: 512 | lm loss: 1.980608E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.679 | TFLOPs: 23.44 | +63: iteration 41930/ 73814 | consumed samples: 21468160 | consumed tokens: 43966791680 | elapsed time per iteration (s): 2.26 | learning rate: 9.211E-05 | global batch size: 512 | lm loss: 2.002534E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.780 | TFLOPs: 23.35 | +63: iteration 41940/ 73814 | consumed samples: 21473280 | consumed tokens: 43977277440 | elapsed time per iteration (s): 2.23 | learning rate: 9.208E-05 | global batch size: 512 | lm loss: 1.986496E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.136 | TFLOPs: 23.59 | +63: iteration 41950/ 73814 | consumed samples: 21478400 | consumed tokens: 43987763200 | elapsed time per iteration (s): 2.24 | learning rate: 9.204E-05 | global batch size: 512 | lm loss: 2.020482E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.314 | TFLOPs: 23.50 | +63: iteration 41960/ 73814 | consumed samples: 21483520 | consumed tokens: 43998248960 | elapsed time per iteration (s): 2.25 | learning rate: 9.200E-05 | global batch size: 512 | lm loss: 2.009247E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.629 | TFLOPs: 23.43 | +63: iteration 41970/ 73814 | consumed samples: 21488640 | consumed tokens: 44008734720 | elapsed time per iteration (s): 2.24 | learning rate: 9.196E-05 | global batch size: 512 | lm loss: 1.997429E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.185 | TFLOPs: 23.49 | +63: iteration 41980/ 73814 | consumed samples: 21493760 | consumed tokens: 44019220480 | elapsed time per iteration (s): 2.34 | learning rate: 9.192E-05 | global batch size: 512 | lm loss: 1.987071E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.898 | TFLOPs: 22.53 | +63: iteration 41990/ 73814 | consumed samples: 21498880 | consumed tokens: 44029706240 | elapsed time per iteration (s): 2.26 | learning rate: 9.189E-05 | global batch size: 512 | lm loss: 1.995717E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.843 | TFLOPs: 23.35 | + 0: [2022-12-02 14:33:00,931] [INFO] [logging.py:68:log_dist] [Rank 0] step=42000, skipped=0, lr=[9.184851413557101e-05, 9.184851413557101e-05, 9.184851413557101e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 42000/ 73814 | consumed samples: 21504000 | consumed tokens: 44040192000 | elapsed time per iteration (s): 2.23 | learning rate: 9.185E-05 | global batch size: 512 | lm loss: 2.010159E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.607 | TFLOPs: 23.64 | + 0: steps: 42000 loss: 1.9298 iter time (s): 2.292 samples/sec: 223.365 +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 42000 | lm loss value: 1.899558E+00 | lm loss PPL: 6.682941E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 42010/ 73814 | consumed samples: 21509120 | consumed tokens: 44050677760 | elapsed time per iteration (s): 2.49 | learning rate: 9.181E-05 | global batch size: 512 | lm loss: 1.998178E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.449 | TFLOPs: 21.15 | +63: iteration 42020/ 73814 | consumed samples: 21514240 | consumed tokens: 44061163520 | elapsed time per iteration (s): 2.23 | learning rate: 9.177E-05 | global batch size: 512 | lm loss: 2.000938E+00 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.237 | TFLOPs: 23.60 | +63: iteration 42030/ 73814 | consumed samples: 21519360 | consumed tokens: 44071649280 | elapsed time per iteration (s): 2.23 | learning rate: 9.173E-05 | global batch size: 512 | lm loss: 1.961331E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.421 | TFLOPs: 23.62 | +63: iteration 42040/ 73814 | consumed samples: 21524480 | consumed tokens: 44082135040 | elapsed time per iteration (s): 2.33 | learning rate: 9.170E-05 | global batch size: 512 | lm loss: 1.993166E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.110 | TFLOPs: 22.66 | +63: iteration 42050/ 73814 | consumed samples: 21529600 | consumed tokens: 44092620800 | elapsed time per iteration (s): 2.24 | learning rate: 9.166E-05 | global batch size: 512 | lm loss: 1.988753E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.812 | TFLOPs: 23.56 | +63: iteration 42060/ 73814 | consumed samples: 21534720 | consumed tokens: 44103106560 | elapsed time per iteration (s): 2.23 | learning rate: 9.162E-05 | global batch size: 512 | lm loss: 1.986101E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.588 | TFLOPs: 23.63 | +63: iteration 42070/ 73814 | consumed samples: 21539840 | consumed tokens: 44113592320 | elapsed time per iteration (s): 2.25 | learning rate: 9.158E-05 | global batch size: 512 | lm loss: 1.993720E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.169 | TFLOPs: 23.39 | +63: iteration 42080/ 73814 | consumed samples: 21544960 | consumed tokens: 44124078080 | elapsed time per iteration (s): 2.22 | learning rate: 9.155E-05 | global batch size: 512 | lm loss: 1.997276E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.224 | TFLOPs: 23.70 | +63: iteration 42090/ 73814 | consumed samples: 21550080 | consumed tokens: 44134563840 | elapsed time per iteration (s): 2.23 | learning rate: 9.151E-05 | global batch size: 512 | lm loss: 2.001203E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.211 | TFLOPs: 23.60 | +63: iteration 42100/ 73814 | consumed samples: 21555200 | consumed tokens: 44145049600 | elapsed time per iteration (s): 2.23 | learning rate: 9.147E-05 | global batch size: 512 | lm loss: 1.997481E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.973 | TFLOPs: 23.67 | +63: iteration 42110/ 73814 | consumed samples: 21560320 | consumed tokens: 44155535360 | elapsed time per iteration (s): 2.23 | learning rate: 9.143E-05 | global batch size: 512 | lm loss: 2.005563E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.293 | TFLOPs: 23.60 | +63: iteration 42120/ 73814 | consumed samples: 21565440 | consumed tokens: 44166021120 | elapsed time per iteration (s): 2.25 | learning rate: 9.139E-05 | global batch size: 512 | lm loss: 1.993853E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.354 | TFLOPs: 23.40 | +63: iteration 42130/ 73814 | consumed samples: 21570560 | consumed tokens: 44176506880 | elapsed time per iteration (s): 2.23 | learning rate: 9.136E-05 | global batch size: 512 | lm loss: 1.987989E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.499 | TFLOPs: 23.63 | +63: iteration 42140/ 73814 | consumed samples: 21575680 | consumed tokens: 44186992640 | elapsed time per iteration (s): 2.23 | learning rate: 9.132E-05 | global batch size: 512 | lm loss: 1.972581E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.787 | TFLOPs: 23.66 | +63: iteration 42150/ 73814 | consumed samples: 21580800 | consumed tokens: 44197478400 | elapsed time per iteration (s): 2.33 | learning rate: 9.128E-05 | global batch size: 512 | lm loss: 1.995667E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.640 | TFLOPs: 22.61 | +63: iteration 42160/ 73814 | consumed samples: 21585920 | consumed tokens: 44207964160 | elapsed time per iteration (s): 2.47 | learning rate: 9.124E-05 | global batch size: 512 | lm loss: 1.970538E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 207.647 | TFLOPs: 21.38 | +63: iteration 42170/ 73814 | consumed samples: 21591040 | consumed tokens: 44218449920 | elapsed time per iteration (s): 2.25 | learning rate: 9.120E-05 | global batch size: 512 | lm loss: 1.977202E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.255 | TFLOPs: 23.39 | +63: iteration 42180/ 73814 | consumed samples: 21596160 | consumed tokens: 44228935680 | elapsed time per iteration (s): 2.23 | learning rate: 9.117E-05 | global batch size: 512 | lm loss: 1.998768E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.601 | TFLOPs: 23.64 | +63: iteration 42190/ 73814 | consumed samples: 21601280 | consumed tokens: 44239421440 | elapsed time per iteration (s): 2.25 | learning rate: 9.113E-05 | global batch size: 512 | lm loss: 1.989247E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.076 | TFLOPs: 23.38 | +63: iteration 42200/ 73814 | consumed samples: 21606400 | consumed tokens: 44249907200 | elapsed time per iteration (s): 2.25 | learning rate: 9.109E-05 | global batch size: 512 | lm loss: 2.008535E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.057 | TFLOPs: 23.48 | +63: iteration 42210/ 73814 | consumed samples: 21611520 | consumed tokens: 44260392960 | elapsed time per iteration (s): 2.24 | learning rate: 9.105E-05 | global batch size: 512 | lm loss: 1.990526E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.129 | TFLOPs: 23.48 | +63: iteration 42220/ 73814 | consumed samples: 21616640 | consumed tokens: 44270878720 | elapsed time per iteration (s): 2.26 | learning rate: 9.102E-05 | global batch size: 512 | lm loss: 1.976816E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.722 | TFLOPs: 23.34 | +63: iteration 42230/ 73814 | consumed samples: 21621760 | consumed tokens: 44281364480 | elapsed time per iteration (s): 2.25 | learning rate: 9.098E-05 | global batch size: 512 | lm loss: 2.007671E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.720 | TFLOPs: 23.44 | +63: iteration 42240/ 73814 | consumed samples: 21626880 | consumed tokens: 44291850240 | elapsed time per iteration (s): 2.24 | learning rate: 9.094E-05 | global batch size: 512 | lm loss: 1.978025E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.489 | TFLOPs: 23.52 | +63: iteration 42250/ 73814 | consumed samples: 21632000 | consumed tokens: 44302336000 | elapsed time per iteration (s): 2.25 | learning rate: 9.090E-05 | global batch size: 512 | lm loss: 2.013263E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.006 | TFLOPs: 23.47 | +63: iteration 42260/ 73814 | consumed samples: 21637120 | consumed tokens: 44312821760 | elapsed time per iteration (s): 2.23 | learning rate: 9.086E-05 | global batch size: 512 | lm loss: 2.009177E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.511 | TFLOPs: 23.63 | +63: iteration 42270/ 73814 | consumed samples: 21642240 | consumed tokens: 44323307520 | elapsed time per iteration (s): 2.25 | learning rate: 9.083E-05 | global batch size: 512 | lm loss: 1.991051E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.184 | TFLOPs: 23.39 | +63: iteration 42280/ 73814 | consumed samples: 21647360 | consumed tokens: 44333793280 | elapsed time per iteration (s): 2.28 | learning rate: 9.079E-05 | global batch size: 512 | lm loss: 1.972211E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.794 | TFLOPs: 23.14 | +63: iteration 42290/ 73814 | consumed samples: 21652480 | consumed tokens: 44344279040 | elapsed time per iteration (s): 2.25 | learning rate: 9.075E-05 | global batch size: 512 | lm loss: 1.985032E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.166 | TFLOPs: 23.39 | +63: iteration 42300/ 73814 | consumed samples: 21657600 | consumed tokens: 44354764800 | elapsed time per iteration (s): 2.27 | learning rate: 9.071E-05 | global batch size: 512 | lm loss: 1.974874E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.047 | TFLOPs: 23.27 | +63: iteration 42310/ 73814 | consumed samples: 21662720 | consumed tokens: 44365250560 | elapsed time per iteration (s): 2.50 | learning rate: 9.068E-05 | global batch size: 512 | lm loss: 1.988306E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.206 | TFLOPs: 21.12 | +63: iteration 42320/ 73814 | consumed samples: 21667840 | consumed tokens: 44375736320 | elapsed time per iteration (s): 2.44 | learning rate: 9.064E-05 | global batch size: 512 | lm loss: 1.986805E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.466 | TFLOPs: 21.56 | +63: iteration 42330/ 73814 | consumed samples: 21672960 | consumed tokens: 44386222080 | elapsed time per iteration (s): 2.32 | learning rate: 9.060E-05 | global batch size: 512 | lm loss: 1.987441E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.953 | TFLOPs: 22.75 | +63: iteration 42340/ 73814 | consumed samples: 21678080 | consumed tokens: 44396707840 | elapsed time per iteration (s): 2.48 | learning rate: 9.056E-05 | global batch size: 512 | lm loss: 1.993486E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.184 | TFLOPs: 21.23 | +63: iteration 42350/ 73814 | consumed samples: 21683200 | consumed tokens: 44407193600 | elapsed time per iteration (s): 2.72 | learning rate: 9.052E-05 | global batch size: 512 | lm loss: 1.996660E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 187.901 | TFLOPs: 19.34 | +63: iteration 42360/ 73814 | consumed samples: 21688320 | consumed tokens: 44417679360 | elapsed time per iteration (s): 2.92 | learning rate: 9.049E-05 | global batch size: 512 | lm loss: 1.991330E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 175.229 | TFLOPs: 18.04 | +63: iteration 42370/ 73814 | consumed samples: 21693440 | consumed tokens: 44428165120 | elapsed time per iteration (s): 2.26 | learning rate: 9.045E-05 | global batch size: 512 | lm loss: 1.998187E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.388 | TFLOPs: 23.31 | +63: iteration 42380/ 73814 | consumed samples: 21698560 | consumed tokens: 44438650880 | elapsed time per iteration (s): 2.25 | learning rate: 9.041E-05 | global batch size: 512 | lm loss: 1.987288E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.055 | TFLOPs: 23.48 | +63: iteration 42390/ 73814 | consumed samples: 21703680 | consumed tokens: 44449136640 | elapsed time per iteration (s): 2.31 | learning rate: 9.037E-05 | global batch size: 512 | lm loss: 1.977004E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.831 | TFLOPs: 22.84 | +63: iteration 42400/ 73814 | consumed samples: 21708800 | consumed tokens: 44459622400 | elapsed time per iteration (s): 2.37 | learning rate: 9.034E-05 | global batch size: 512 | lm loss: 1.977456E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.950 | TFLOPs: 22.23 | +63: iteration 42410/ 73814 | consumed samples: 21713920 | consumed tokens: 44470108160 | elapsed time per iteration (s): 2.23 | learning rate: 9.030E-05 | global batch size: 512 | lm loss: 2.001092E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.338 | TFLOPs: 23.61 | +63: iteration 42420/ 73814 | consumed samples: 21719040 | consumed tokens: 44480593920 | elapsed time per iteration (s): 2.24 | learning rate: 9.026E-05 | global batch size: 512 | lm loss: 1.973683E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.512 | TFLOPs: 23.52 | +63: iteration 42430/ 73814 | consumed samples: 21724160 | consumed tokens: 44491079680 | elapsed time per iteration (s): 2.24 | learning rate: 9.022E-05 | global batch size: 512 | lm loss: 1.981456E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.506 | TFLOPs: 23.52 | +63: iteration 42440/ 73814 | consumed samples: 21729280 | consumed tokens: 44501565440 | elapsed time per iteration (s): 2.23 | learning rate: 9.018E-05 | global batch size: 512 | lm loss: 2.002334E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.950 | TFLOPs: 23.67 | +63: iteration 42450/ 73814 | consumed samples: 21734400 | consumed tokens: 44512051200 | elapsed time per iteration (s): 2.25 | learning rate: 9.015E-05 | global batch size: 512 | lm loss: 2.010716E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.734 | TFLOPs: 23.44 | +63: iteration 42460/ 73814 | consumed samples: 21739520 | consumed tokens: 44522536960 | elapsed time per iteration (s): 2.29 | learning rate: 9.011E-05 | global batch size: 512 | lm loss: 1.988136E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.633 | TFLOPs: 23.02 | +63: iteration 42470/ 73814 | consumed samples: 21744640 | consumed tokens: 44533022720 | elapsed time per iteration (s): 2.23 | learning rate: 9.007E-05 | global batch size: 512 | lm loss: 1.995994E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.649 | TFLOPs: 23.64 | +63: iteration 42480/ 73814 | consumed samples: 21749760 | consumed tokens: 44543508480 | elapsed time per iteration (s): 2.25 | learning rate: 9.003E-05 | global batch size: 512 | lm loss: 1.980758E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.143 | TFLOPs: 23.38 | +63: iteration 42490/ 73814 | consumed samples: 21754880 | consumed tokens: 44553994240 | elapsed time per iteration (s): 2.22 | learning rate: 9.000E-05 | global batch size: 512 | lm loss: 1.978015E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.326 | TFLOPs: 23.71 | +63: iteration 42500/ 73814 | consumed samples: 21760000 | consumed tokens: 44564480000 | elapsed time per iteration (s): 2.46 | learning rate: 8.996E-05 | global batch size: 512 | lm loss: 1.982133E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 207.891 | TFLOPs: 21.40 | +63: iteration 42510/ 73814 | consumed samples: 21765120 | consumed tokens: 44574965760 | elapsed time per iteration (s): 2.26 | learning rate: 8.992E-05 | global batch size: 512 | lm loss: 1.978966E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.708 | TFLOPs: 23.34 | +63: iteration 42520/ 73814 | consumed samples: 21770240 | consumed tokens: 44585451520 | elapsed time per iteration (s): 2.24 | learning rate: 8.988E-05 | global batch size: 512 | lm loss: 1.983098E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.671 | TFLOPs: 23.54 | +63: iteration 42530/ 73814 | consumed samples: 21775360 | consumed tokens: 44595937280 | elapsed time per iteration (s): 2.23 | learning rate: 8.984E-05 | global batch size: 512 | lm loss: 1.982738E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.765 | TFLOPs: 23.65 | +63: iteration 42540/ 73814 | consumed samples: 21780480 | consumed tokens: 44606423040 | elapsed time per iteration (s): 2.24 | learning rate: 8.981E-05 | global batch size: 512 | lm loss: 1.987034E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.838 | TFLOPs: 23.56 | +63: iteration 42550/ 73814 | consumed samples: 21785600 | consumed tokens: 44616908800 | elapsed time per iteration (s): 2.23 | learning rate: 8.977E-05 | global batch size: 512 | lm loss: 1.992823E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.473 | TFLOPs: 23.62 | +63: iteration 42560/ 73814 | consumed samples: 21790720 | consumed tokens: 44627394560 | elapsed time per iteration (s): 2.32 | learning rate: 8.973E-05 | global batch size: 512 | lm loss: 1.988053E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.720 | TFLOPs: 22.72 | +63: iteration 42570/ 73814 | consumed samples: 21795840 | consumed tokens: 44637880320 | elapsed time per iteration (s): 2.23 | learning rate: 8.969E-05 | global batch size: 512 | lm loss: 1.985340E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.068 | TFLOPs: 23.68 | +63: iteration 42580/ 73814 | consumed samples: 21800960 | consumed tokens: 44648366080 | elapsed time per iteration (s): 2.34 | learning rate: 8.966E-05 | global batch size: 512 | lm loss: 1.995010E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.232 | TFLOPs: 22.57 | +63: iteration 42590/ 73814 | consumed samples: 21806080 | consumed tokens: 44658851840 | elapsed time per iteration (s): 2.23 | learning rate: 8.962E-05 | global batch size: 512 | lm loss: 1.996506E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.832 | TFLOPs: 23.66 | +63: iteration 42600/ 73814 | consumed samples: 21811200 | consumed tokens: 44669337600 | elapsed time per iteration (s): 2.25 | learning rate: 8.958E-05 | global batch size: 512 | lm loss: 1.997453E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.719 | TFLOPs: 23.44 | +63: iteration 42610/ 73814 | consumed samples: 21816320 | consumed tokens: 44679823360 | elapsed time per iteration (s): 2.24 | learning rate: 8.954E-05 | global batch size: 512 | lm loss: 1.990902E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.415 | TFLOPs: 23.51 | +63: iteration 42620/ 73814 | consumed samples: 21821440 | consumed tokens: 44690309120 | elapsed time per iteration (s): 2.22 | learning rate: 8.951E-05 | global batch size: 512 | lm loss: 1.991985E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.145 | TFLOPs: 23.69 | +63: iteration 42630/ 73814 | consumed samples: 21826560 | consumed tokens: 44700794880 | elapsed time per iteration (s): 2.30 | learning rate: 8.947E-05 | global batch size: 512 | lm loss: 1.963894E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.229 | TFLOPs: 22.88 | +63: iteration 42640/ 73814 | consumed samples: 21831680 | consumed tokens: 44711280640 | elapsed time per iteration (s): 2.28 | learning rate: 8.943E-05 | global batch size: 512 | lm loss: 1.967216E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.463 | TFLOPs: 23.11 | +63: iteration 42650/ 73814 | consumed samples: 21836800 | consumed tokens: 44721766400 | elapsed time per iteration (s): 2.23 | learning rate: 8.939E-05 | global batch size: 512 | lm loss: 1.995402E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.953 | TFLOPs: 23.67 | +63: iteration 42660/ 73814 | consumed samples: 21841920 | consumed tokens: 44732252160 | elapsed time per iteration (s): 2.48 | learning rate: 8.935E-05 | global batch size: 512 | lm loss: 1.987144E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.655 | TFLOPs: 21.27 | +63: iteration 42670/ 73814 | consumed samples: 21847040 | consumed tokens: 44742737920 | elapsed time per iteration (s): 2.27 | learning rate: 8.932E-05 | global batch size: 512 | lm loss: 2.017753E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.435 | TFLOPs: 23.21 | +63: iteration 42680/ 73814 | consumed samples: 21852160 | consumed tokens: 44753223680 | elapsed time per iteration (s): 2.25 | learning rate: 8.928E-05 | global batch size: 512 | lm loss: 1.981126E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.327 | TFLOPs: 23.40 | +63: iteration 42690/ 73814 | consumed samples: 21857280 | consumed tokens: 44763709440 | elapsed time per iteration (s): 2.24 | learning rate: 8.924E-05 | global batch size: 512 | lm loss: 1.962945E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.678 | TFLOPs: 23.54 | +63: iteration 42700/ 73814 | consumed samples: 21862400 | consumed tokens: 44774195200 | elapsed time per iteration (s): 2.24 | learning rate: 8.920E-05 | global batch size: 512 | lm loss: 1.955215E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.300 | TFLOPs: 23.50 | +63: iteration 42710/ 73814 | consumed samples: 21867520 | consumed tokens: 44784680960 | elapsed time per iteration (s): 2.25 | learning rate: 8.917E-05 | global batch size: 512 | lm loss: 1.997839E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.037 | TFLOPs: 23.48 | +63: iteration 42720/ 73814 | consumed samples: 21872640 | consumed tokens: 44795166720 | elapsed time per iteration (s): 2.23 | learning rate: 8.913E-05 | global batch size: 512 | lm loss: 1.972150E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.881 | TFLOPs: 23.67 | +63: iteration 42730/ 73814 | consumed samples: 21877760 | consumed tokens: 44805652480 | elapsed time per iteration (s): 2.26 | learning rate: 8.909E-05 | global batch size: 512 | lm loss: 1.996003E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.820 | TFLOPs: 23.35 | +63: iteration 42740/ 73814 | consumed samples: 21882880 | consumed tokens: 44816138240 | elapsed time per iteration (s): 2.23 | learning rate: 8.905E-05 | global batch size: 512 | lm loss: 1.991413E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.377 | TFLOPs: 23.61 | +63: iteration 42750/ 73814 | consumed samples: 21888000 | consumed tokens: 44826624000 | elapsed time per iteration (s): 2.23 | learning rate: 8.902E-05 | global batch size: 512 | lm loss: 1.977123E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.755 | TFLOPs: 23.65 | +63: iteration 42760/ 73814 | consumed samples: 21893120 | consumed tokens: 44837109760 | elapsed time per iteration (s): 2.23 | learning rate: 8.898E-05 | global batch size: 512 | lm loss: 1.984303E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.982 | TFLOPs: 23.68 | +63: iteration 42770/ 73814 | consumed samples: 21898240 | consumed tokens: 44847595520 | elapsed time per iteration (s): 2.25 | learning rate: 8.894E-05 | global batch size: 512 | lm loss: 1.958914E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.618 | TFLOPs: 23.43 | +63: iteration 42780/ 73814 | consumed samples: 21903360 | consumed tokens: 44858081280 | elapsed time per iteration (s): 2.23 | learning rate: 8.890E-05 | global batch size: 512 | lm loss: 1.980560E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.091 | TFLOPs: 23.69 | +63: iteration 42790/ 73814 | consumed samples: 21908480 | consumed tokens: 44868567040 | elapsed time per iteration (s): 2.23 | learning rate: 8.887E-05 | global batch size: 512 | lm loss: 1.976785E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.540 | TFLOPs: 23.63 | +63: iteration 42800/ 73814 | consumed samples: 21913600 | consumed tokens: 44879052800 | elapsed time per iteration (s): 2.23 | learning rate: 8.883E-05 | global batch size: 512 | lm loss: 1.982976E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.084 | TFLOPs: 23.58 | +63: iteration 42810/ 73814 | consumed samples: 21918720 | consumed tokens: 44889538560 | elapsed time per iteration (s): 2.26 | learning rate: 8.879E-05 | global batch size: 512 | lm loss: 1.994902E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.709 | TFLOPs: 23.34 | +63: iteration 42820/ 73814 | consumed samples: 21923840 | consumed tokens: 44900024320 | elapsed time per iteration (s): 2.24 | learning rate: 8.875E-05 | global batch size: 512 | lm loss: 1.984361E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.990 | TFLOPs: 23.57 | +63: iteration 42830/ 73814 | consumed samples: 21928960 | consumed tokens: 44910510080 | elapsed time per iteration (s): 2.30 | learning rate: 8.872E-05 | global batch size: 512 | lm loss: 1.981043E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.656 | TFLOPs: 22.92 | +63: iteration 42840/ 73814 | consumed samples: 21934080 | consumed tokens: 44920995840 | elapsed time per iteration (s): 2.24 | learning rate: 8.868E-05 | global batch size: 512 | lm loss: 2.000714E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.284 | TFLOPs: 23.50 | +63: iteration 42850/ 73814 | consumed samples: 21939200 | consumed tokens: 44931481600 | elapsed time per iteration (s): 2.25 | learning rate: 8.864E-05 | global batch size: 512 | lm loss: 1.989943E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.573 | TFLOPs: 23.43 | +63: iteration 42860/ 73814 | consumed samples: 21944320 | consumed tokens: 44941967360 | elapsed time per iteration (s): 2.55 | learning rate: 8.860E-05 | global batch size: 512 | lm loss: 1.971277E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.501 | TFLOPs: 20.64 | +63: iteration 42870/ 73814 | consumed samples: 21949440 | consumed tokens: 44952453120 | elapsed time per iteration (s): 2.23 | learning rate: 8.856E-05 | global batch size: 512 | lm loss: 1.970961E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.184 | TFLOPs: 23.59 | +63: iteration 42880/ 73814 | consumed samples: 21954560 | consumed tokens: 44962938880 | elapsed time per iteration (s): 2.23 | learning rate: 8.853E-05 | global batch size: 512 | lm loss: 1.984479E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.862 | TFLOPs: 23.66 | +63: iteration 42890/ 73814 | consumed samples: 21959680 | consumed tokens: 44973424640 | elapsed time per iteration (s): 2.26 | learning rate: 8.849E-05 | global batch size: 512 | lm loss: 1.996826E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.521 | TFLOPs: 23.32 | +63: iteration 42900/ 73814 | consumed samples: 21964800 | consumed tokens: 44983910400 | elapsed time per iteration (s): 2.23 | learning rate: 8.845E-05 | global batch size: 512 | lm loss: 1.972790E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.283 | TFLOPs: 23.60 | +63: iteration 42910/ 73814 | consumed samples: 21969920 | consumed tokens: 44994396160 | elapsed time per iteration (s): 2.25 | learning rate: 8.841E-05 | global batch size: 512 | lm loss: 1.977285E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.859 | TFLOPs: 23.46 | +63: iteration 42920/ 73814 | consumed samples: 21975040 | consumed tokens: 45004881920 | elapsed time per iteration (s): 2.23 | learning rate: 8.838E-05 | global batch size: 512 | lm loss: 1.990300E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.950 | TFLOPs: 23.67 | +63: iteration 42930/ 73814 | consumed samples: 21980160 | consumed tokens: 45015367680 | elapsed time per iteration (s): 2.23 | learning rate: 8.834E-05 | global batch size: 512 | lm loss: 1.962934E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.156 | TFLOPs: 23.59 | +63: iteration 42940/ 73814 | consumed samples: 21985280 | consumed tokens: 45025853440 | elapsed time per iteration (s): 2.23 | learning rate: 8.830E-05 | global batch size: 512 | lm loss: 1.975752E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.488 | TFLOPs: 23.62 | +63: iteration 42950/ 73814 | consumed samples: 21990400 | consumed tokens: 45036339200 | elapsed time per iteration (s): 2.23 | learning rate: 8.826E-05 | global batch size: 512 | lm loss: 1.989213E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.626 | TFLOPs: 23.64 | +63: iteration 42960/ 73814 | consumed samples: 21995520 | consumed tokens: 45046824960 | elapsed time per iteration (s): 2.23 | learning rate: 8.823E-05 | global batch size: 512 | lm loss: 1.973276E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.342 | TFLOPs: 23.61 | +63: iteration 42970/ 73814 | consumed samples: 22000640 | consumed tokens: 45057310720 | elapsed time per iteration (s): 2.28 | learning rate: 8.819E-05 | global batch size: 512 | lm loss: 1.971540E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.901 | TFLOPs: 23.15 | +63: iteration 42980/ 73814 | consumed samples: 22005760 | consumed tokens: 45067796480 | elapsed time per iteration (s): 2.25 | learning rate: 8.815E-05 | global batch size: 512 | lm loss: 1.965216E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.621 | TFLOPs: 23.43 | +63: iteration 42990/ 73814 | consumed samples: 22010880 | consumed tokens: 45078282240 | elapsed time per iteration (s): 2.23 | learning rate: 8.811E-05 | global batch size: 512 | lm loss: 1.971920E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.226 | TFLOPs: 23.60 | +63: iteration 43000/ 73814 | consumed samples: 22016000 | consumed tokens: 45088768000 | elapsed time per iteration (s): 2.24 | learning rate: 8.808E-05 | global batch size: 512 | lm loss: 1.990535E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.469 | TFLOPs: 23.52 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 43000 | lm loss value: 1.920297E+00 | lm loss PPL: 6.822982E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 43010/ 73814 | consumed samples: 22021120 | consumed tokens: 45099253760 | elapsed time per iteration (s): 2.38 | learning rate: 8.804E-05 | global batch size: 512 | lm loss: 2.005721E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.710 | TFLOPs: 22.10 | +63: iteration 43020/ 73814 | consumed samples: 22026240 | consumed tokens: 45109739520 | elapsed time per iteration (s): 2.30 | learning rate: 8.800E-05 | global batch size: 512 | lm loss: 1.985391E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.265 | TFLOPs: 22.88 | +63: iteration 43030/ 73814 | consumed samples: 22031360 | consumed tokens: 45120225280 | elapsed time per iteration (s): 2.23 | learning rate: 8.796E-05 | global batch size: 512 | lm loss: 1.980413E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.934 | TFLOPs: 23.67 | +63: iteration 43040/ 73814 | consumed samples: 22036480 | consumed tokens: 45130711040 | elapsed time per iteration (s): 2.24 | learning rate: 8.793E-05 | global batch size: 512 | lm loss: 1.973812E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.384 | TFLOPs: 23.51 | +63: iteration 43050/ 73814 | consumed samples: 22041600 | consumed tokens: 45141196800 | elapsed time per iteration (s): 2.28 | learning rate: 8.789E-05 | global batch size: 512 | lm loss: 1.994486E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.817 | TFLOPs: 23.14 | +63: iteration 43060/ 73814 | consumed samples: 22046720 | consumed tokens: 45151682560 | elapsed time per iteration (s): 2.32 | learning rate: 8.785E-05 | global batch size: 512 | lm loss: 1.972906E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.633 | TFLOPs: 22.71 | +63: iteration 43070/ 73814 | consumed samples: 22051840 | consumed tokens: 45162168320 | elapsed time per iteration (s): 2.24 | learning rate: 8.781E-05 | global batch size: 512 | lm loss: 1.988726E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.167 | TFLOPs: 23.49 | +63: iteration 43080/ 73814 | consumed samples: 22056960 | consumed tokens: 45172654080 | elapsed time per iteration (s): 2.28 | learning rate: 8.778E-05 | global batch size: 512 | lm loss: 1.989906E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.468 | TFLOPs: 23.11 | +63: iteration 43090/ 73814 | consumed samples: 22062080 | consumed tokens: 45183139840 | elapsed time per iteration (s): 2.28 | learning rate: 8.774E-05 | global batch size: 512 | lm loss: 1.990729E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.821 | TFLOPs: 23.14 | +63: iteration 43100/ 73814 | consumed samples: 22067200 | consumed tokens: 45193625600 | elapsed time per iteration (s): 2.27 | learning rate: 8.770E-05 | global batch size: 512 | lm loss: 2.008377E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.367 | TFLOPs: 23.20 | +63: iteration 43110/ 73814 | consumed samples: 22072320 | consumed tokens: 45204111360 | elapsed time per iteration (s): 2.23 | learning rate: 8.766E-05 | global batch size: 512 | lm loss: 2.000484E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.943 | TFLOPs: 23.67 | +63: iteration 43120/ 73814 | consumed samples: 22077440 | consumed tokens: 45214597120 | elapsed time per iteration (s): 2.24 | learning rate: 8.763E-05 | global batch size: 512 | lm loss: 1.981818E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.304 | TFLOPs: 23.50 | +63: iteration 43130/ 73814 | consumed samples: 22082560 | consumed tokens: 45225082880 | elapsed time per iteration (s): 2.52 | learning rate: 8.759E-05 | global batch size: 512 | lm loss: 2.011371E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 203.154 | TFLOPs: 20.91 | +63: iteration 43140/ 73814 | consumed samples: 22087680 | consumed tokens: 45235568640 | elapsed time per iteration (s): 2.24 | learning rate: 8.755E-05 | global batch size: 512 | lm loss: 1.955879E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.191 | TFLOPs: 23.49 | +63: iteration 43150/ 73814 | consumed samples: 22092800 | consumed tokens: 45246054400 | elapsed time per iteration (s): 2.23 | learning rate: 8.751E-05 | global batch size: 512 | lm loss: 2.011175E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.827 | TFLOPs: 23.66 | +63: iteration 43160/ 73814 | consumed samples: 22097920 | consumed tokens: 45256540160 | elapsed time per iteration (s): 2.34 | learning rate: 8.748E-05 | global batch size: 512 | lm loss: 1.998760E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.200 | TFLOPs: 22.57 | +63: iteration 43170/ 73814 | consumed samples: 22103040 | consumed tokens: 45267025920 | elapsed time per iteration (s): 2.24 | learning rate: 8.744E-05 | global batch size: 512 | lm loss: 1.974368E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.291 | TFLOPs: 23.50 | +63: iteration 43180/ 73814 | consumed samples: 22108160 | consumed tokens: 45277511680 | elapsed time per iteration (s): 2.22 | learning rate: 8.740E-05 | global batch size: 512 | lm loss: 1.974895E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.285 | TFLOPs: 23.71 | +63: iteration 43190/ 73814 | consumed samples: 22113280 | consumed tokens: 45287997440 | elapsed time per iteration (s): 2.25 | learning rate: 8.736E-05 | global batch size: 512 | lm loss: 2.004816E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.091 | TFLOPs: 23.38 | +63: iteration 43200/ 73814 | consumed samples: 22118400 | consumed tokens: 45298483200 | elapsed time per iteration (s): 2.23 | learning rate: 8.733E-05 | global batch size: 512 | lm loss: 1.963581E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.941 | TFLOPs: 23.67 | +63: iteration 43210/ 73814 | consumed samples: 22123520 | consumed tokens: 45308968960 | elapsed time per iteration (s): 2.26 | learning rate: 8.729E-05 | global batch size: 512 | lm loss: 1.980948E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.750 | TFLOPs: 23.34 | +63: iteration 43220/ 73814 | consumed samples: 22128640 | consumed tokens: 45319454720 | elapsed time per iteration (s): 2.23 | learning rate: 8.725E-05 | global batch size: 512 | lm loss: 1.984621E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.994 | TFLOPs: 23.68 | +63: iteration 43230/ 73814 | consumed samples: 22133760 | consumed tokens: 45329940480 | elapsed time per iteration (s): 2.24 | learning rate: 8.721E-05 | global batch size: 512 | lm loss: 1.975009E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.712 | TFLOPs: 23.54 | +63: iteration 43240/ 73814 | consumed samples: 22138880 | consumed tokens: 45340426240 | elapsed time per iteration (s): 2.26 | learning rate: 8.718E-05 | global batch size: 512 | lm loss: 1.987814E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.924 | TFLOPs: 23.36 | +63: iteration 43250/ 73814 | consumed samples: 22144000 | consumed tokens: 45350912000 | elapsed time per iteration (s): 2.24 | learning rate: 8.714E-05 | global batch size: 512 | lm loss: 1.966245E+00 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.801 | TFLOPs: 23.55 | +63: iteration 43260/ 73814 | consumed samples: 22149120 | consumed tokens: 45361397760 | elapsed time per iteration (s): 2.25 | learning rate: 8.710E-05 | global batch size: 512 | lm loss: 1.996599E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.553 | TFLOPs: 23.43 | +63: iteration 43270/ 73814 | consumed samples: 22154240 | consumed tokens: 45371883520 | elapsed time per iteration (s): 2.24 | learning rate: 8.707E-05 | global batch size: 512 | lm loss: 1.983535E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.990 | TFLOPs: 23.57 | +63: iteration 43280/ 73814 | consumed samples: 22159360 | consumed tokens: 45382369280 | elapsed time per iteration (s): 2.23 | learning rate: 8.703E-05 | global batch size: 512 | lm loss: 1.972826E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.582 | TFLOPs: 23.63 | +63: iteration 43290/ 73814 | consumed samples: 22164480 | consumed tokens: 45392855040 | elapsed time per iteration (s): 2.25 | learning rate: 8.699E-05 | global batch size: 512 | lm loss: 1.980362E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.244 | TFLOPs: 23.39 | +63: iteration 43300/ 73814 | consumed samples: 22169600 | consumed tokens: 45403340800 | elapsed time per iteration (s): 2.24 | learning rate: 8.695E-05 | global batch size: 512 | lm loss: 1.970633E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.802 | TFLOPs: 23.55 | +63: iteration 43310/ 73814 | consumed samples: 22174720 | consumed tokens: 45413826560 | elapsed time per iteration (s): 2.22 | learning rate: 8.692E-05 | global batch size: 512 | lm loss: 2.016230E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.219 | TFLOPs: 23.70 | +63: iteration 43320/ 73814 | consumed samples: 22179840 | consumed tokens: 45424312320 | elapsed time per iteration (s): 2.24 | learning rate: 8.688E-05 | global batch size: 512 | lm loss: 1.980048E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.815 | TFLOPs: 23.56 | +63: iteration 43330/ 73814 | consumed samples: 22184960 | consumed tokens: 45434798080 | elapsed time per iteration (s): 2.23 | learning rate: 8.684E-05 | global batch size: 512 | lm loss: 2.005071E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.715 | TFLOPs: 23.65 | +63: iteration 43340/ 73814 | consumed samples: 22190080 | consumed tokens: 45445283840 | elapsed time per iteration (s): 2.22 | learning rate: 8.680E-05 | global batch size: 512 | lm loss: 1.995239E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.283 | TFLOPs: 23.71 | +63: iteration 43350/ 73814 | consumed samples: 22195200 | consumed tokens: 45455769600 | elapsed time per iteration (s): 2.30 | learning rate: 8.677E-05 | global batch size: 512 | lm loss: 2.014344E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.947 | TFLOPs: 22.95 | +63: iteration 43360/ 73814 | consumed samples: 22200320 | consumed tokens: 45466255360 | elapsed time per iteration (s): 2.25 | learning rate: 8.673E-05 | global batch size: 512 | lm loss: 2.000315E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.976 | TFLOPs: 23.47 | +63: iteration 43370/ 73814 | consumed samples: 22205440 | consumed tokens: 45476741120 | elapsed time per iteration (s): 2.31 | learning rate: 8.669E-05 | global batch size: 512 | lm loss: 1.979753E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.798 | TFLOPs: 22.83 | +63: iteration 43380/ 73814 | consumed samples: 22210560 | consumed tokens: 45487226880 | elapsed time per iteration (s): 2.23 | learning rate: 8.665E-05 | global batch size: 512 | lm loss: 1.998636E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.017 | TFLOPs: 23.68 | +63: iteration 43390/ 73814 | consumed samples: 22215680 | consumed tokens: 45497712640 | elapsed time per iteration (s): 2.25 | learning rate: 8.662E-05 | global batch size: 512 | lm loss: 1.973523E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.166 | TFLOPs: 23.39 | +63: iteration 43400/ 73814 | consumed samples: 22220800 | consumed tokens: 45508198400 | elapsed time per iteration (s): 2.26 | learning rate: 8.658E-05 | global batch size: 512 | lm loss: 1.969843E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.804 | TFLOPs: 23.35 | +63: iteration 43410/ 73814 | consumed samples: 22225920 | consumed tokens: 45518684160 | elapsed time per iteration (s): 2.23 | learning rate: 8.654E-05 | global batch size: 512 | lm loss: 1.981272E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.862 | TFLOPs: 23.66 | +63: iteration 43420/ 73814 | consumed samples: 22231040 | consumed tokens: 45529169920 | elapsed time per iteration (s): 2.35 | learning rate: 8.650E-05 | global batch size: 512 | lm loss: 1.991988E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.063 | TFLOPs: 22.45 | +63: iteration 43430/ 73814 | consumed samples: 22236160 | consumed tokens: 45539655680 | elapsed time per iteration (s): 2.25 | learning rate: 8.647E-05 | global batch size: 512 | lm loss: 1.977346E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.145 | TFLOPs: 23.38 | +63: iteration 43440/ 73814 | consumed samples: 22241280 | consumed tokens: 45550141440 | elapsed time per iteration (s): 2.27 | learning rate: 8.643E-05 | global batch size: 512 | lm loss: 2.011354E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.926 | TFLOPs: 23.26 | +63: iteration 43450/ 73814 | consumed samples: 22246400 | consumed tokens: 45560627200 | elapsed time per iteration (s): 2.33 | learning rate: 8.639E-05 | global batch size: 512 | lm loss: 1.986229E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.791 | TFLOPs: 22.63 | +63: iteration 43460/ 73814 | consumed samples: 22251520 | consumed tokens: 45571112960 | elapsed time per iteration (s): 2.31 | learning rate: 8.636E-05 | global batch size: 512 | lm loss: 1.966368E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.656 | TFLOPs: 22.82 | +63: iteration 43470/ 73814 | consumed samples: 22256640 | consumed tokens: 45581598720 | elapsed time per iteration (s): 2.25 | learning rate: 8.632E-05 | global batch size: 512 | lm loss: 1.991724E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.617 | TFLOPs: 23.43 | +63: iteration 43480/ 73814 | consumed samples: 22261760 | consumed tokens: 45592084480 | elapsed time per iteration (s): 2.25 | learning rate: 8.628E-05 | global batch size: 512 | lm loss: 1.993455E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.936 | TFLOPs: 23.46 | +63: iteration 43490/ 73814 | consumed samples: 22266880 | consumed tokens: 45602570240 | elapsed time per iteration (s): 2.26 | learning rate: 8.624E-05 | global batch size: 512 | lm loss: 2.003802E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.607 | TFLOPs: 23.33 | +63: iteration 43500/ 73814 | consumed samples: 22272000 | consumed tokens: 45613056000 | elapsed time per iteration (s): 2.24 | learning rate: 8.621E-05 | global batch size: 512 | lm loss: 1.971379E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.751 | TFLOPs: 23.55 | +63: iteration 43510/ 73814 | consumed samples: 22277120 | consumed tokens: 45623541760 | elapsed time per iteration (s): 2.45 | learning rate: 8.617E-05 | global batch size: 512 | lm loss: 1.975755E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.920 | TFLOPs: 21.51 | +63: iteration 43520/ 73814 | consumed samples: 22282240 | consumed tokens: 45634027520 | elapsed time per iteration (s): 2.24 | learning rate: 8.613E-05 | global batch size: 512 | lm loss: 1.988328E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.249 | TFLOPs: 23.50 | +63: iteration 43530/ 73814 | consumed samples: 22287360 | consumed tokens: 45644513280 | elapsed time per iteration (s): 2.34 | learning rate: 8.609E-05 | global batch size: 512 | lm loss: 2.007372E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.725 | TFLOPs: 22.52 | +63: iteration 43540/ 73814 | consumed samples: 22292480 | consumed tokens: 45654999040 | elapsed time per iteration (s): 2.23 | learning rate: 8.606E-05 | global batch size: 512 | lm loss: 1.981494E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.514 | TFLOPs: 23.63 | +63: iteration 43550/ 73814 | consumed samples: 22297600 | consumed tokens: 45665484800 | elapsed time per iteration (s): 2.26 | learning rate: 8.602E-05 | global batch size: 512 | lm loss: 1.983153E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.805 | TFLOPs: 23.35 | +63: iteration 43560/ 73814 | consumed samples: 22302720 | consumed tokens: 45675970560 | elapsed time per iteration (s): 2.23 | learning rate: 8.598E-05 | global batch size: 512 | lm loss: 1.968339E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.779 | TFLOPs: 23.65 | +63: iteration 43570/ 73814 | consumed samples: 22307840 | consumed tokens: 45686456320 | elapsed time per iteration (s): 2.26 | learning rate: 8.594E-05 | global batch size: 512 | lm loss: 1.969061E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.543 | TFLOPs: 23.32 | +63: iteration 43580/ 73814 | consumed samples: 22312960 | consumed tokens: 45696942080 | elapsed time per iteration (s): 2.25 | learning rate: 8.591E-05 | global batch size: 512 | lm loss: 1.990396E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.834 | TFLOPs: 23.45 | +63: iteration 43590/ 73814 | consumed samples: 22318080 | consumed tokens: 45707427840 | elapsed time per iteration (s): 2.23 | learning rate: 8.587E-05 | global batch size: 512 | lm loss: 1.976874E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.384 | TFLOPs: 23.61 | +63: iteration 43600/ 73814 | consumed samples: 22323200 | consumed tokens: 45717913600 | elapsed time per iteration (s): 2.24 | learning rate: 8.583E-05 | global batch size: 512 | lm loss: 1.979979E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.619 | TFLOPs: 23.54 | +63: iteration 43610/ 73814 | consumed samples: 22328320 | consumed tokens: 45728399360 | elapsed time per iteration (s): 2.25 | learning rate: 8.580E-05 | global batch size: 512 | lm loss: 1.954458E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.160 | TFLOPs: 23.39 | +63: iteration 43620/ 73814 | consumed samples: 22333440 | consumed tokens: 45738885120 | elapsed time per iteration (s): 2.23 | learning rate: 8.576E-05 | global batch size: 512 | lm loss: 1.975726E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.955 | TFLOPs: 23.67 | +63: iteration 43630/ 73814 | consumed samples: 22338560 | consumed tokens: 45749370880 | elapsed time per iteration (s): 2.24 | learning rate: 8.572E-05 | global batch size: 512 | lm loss: 1.979257E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.818 | TFLOPs: 23.56 | +63: iteration 43640/ 73814 | consumed samples: 22343680 | consumed tokens: 45759856640 | elapsed time per iteration (s): 2.25 | learning rate: 8.568E-05 | global batch size: 512 | lm loss: 1.994789E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.242 | TFLOPs: 23.39 | +63: iteration 43650/ 73814 | consumed samples: 22348800 | consumed tokens: 45770342400 | elapsed time per iteration (s): 2.26 | learning rate: 8.565E-05 | global batch size: 512 | lm loss: 1.952231E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.973 | TFLOPs: 23.37 | +63: iteration 43660/ 73814 | consumed samples: 22353920 | consumed tokens: 45780828160 | elapsed time per iteration (s): 2.24 | learning rate: 8.561E-05 | global batch size: 512 | lm loss: 1.994465E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.572 | TFLOPs: 23.53 | +63: iteration 43670/ 73814 | consumed samples: 22359040 | consumed tokens: 45791313920 | elapsed time per iteration (s): 2.27 | learning rate: 8.557E-05 | global batch size: 512 | lm loss: 1.981575E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.525 | TFLOPs: 23.22 | +63: iteration 43680/ 73814 | consumed samples: 22364160 | consumed tokens: 45801799680 | elapsed time per iteration (s): 2.28 | learning rate: 8.553E-05 | global batch size: 512 | lm loss: 1.977209E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.937 | TFLOPs: 23.16 | +63: iteration 43690/ 73814 | consumed samples: 22369280 | consumed tokens: 45812285440 | elapsed time per iteration (s): 2.22 | learning rate: 8.550E-05 | global batch size: 512 | lm loss: 1.970240E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.363 | TFLOPs: 23.71 | +63: iteration 43700/ 73814 | consumed samples: 22374400 | consumed tokens: 45822771200 | elapsed time per iteration (s): 2.23 | learning rate: 8.546E-05 | global batch size: 512 | lm loss: 1.977566E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.398 | TFLOPs: 23.62 | +63: iteration 43710/ 73814 | consumed samples: 22379520 | consumed tokens: 45833256960 | elapsed time per iteration (s): 2.33 | learning rate: 8.542E-05 | global batch size: 512 | lm loss: 1.998663E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.431 | TFLOPs: 22.59 | +63: iteration 43720/ 73814 | consumed samples: 22384640 | consumed tokens: 45843742720 | elapsed time per iteration (s): 2.40 | learning rate: 8.539E-05 | global batch size: 512 | lm loss: 1.987071E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.473 | TFLOPs: 21.98 | +63: iteration 43730/ 73814 | consumed samples: 22389760 | consumed tokens: 45854228480 | elapsed time per iteration (s): 2.33 | learning rate: 8.535E-05 | global batch size: 512 | lm loss: 1.990971E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.845 | TFLOPs: 22.63 | +63: iteration 43740/ 73814 | consumed samples: 22394880 | consumed tokens: 45864714240 | elapsed time per iteration (s): 2.23 | learning rate: 8.531E-05 | global batch size: 512 | lm loss: 1.985494E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.242 | TFLOPs: 23.60 | +63: iteration 43750/ 73814 | consumed samples: 22400000 | consumed tokens: 45875200000 | elapsed time per iteration (s): 2.23 | learning rate: 8.527E-05 | global batch size: 512 | lm loss: 1.979621E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.627 | TFLOPs: 23.64 | +63: iteration 43760/ 73814 | consumed samples: 22405120 | consumed tokens: 45885685760 | elapsed time per iteration (s): 2.40 | learning rate: 8.524E-05 | global batch size: 512 | lm loss: 1.965363E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.053 | TFLOPs: 21.93 | +63: iteration 43770/ 73814 | consumed samples: 22410240 | consumed tokens: 45896171520 | elapsed time per iteration (s): 2.27 | learning rate: 8.520E-05 | global batch size: 512 | lm loss: 1.975629E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.263 | TFLOPs: 23.19 | +63: iteration 43780/ 73814 | consumed samples: 22415360 | consumed tokens: 45906657280 | elapsed time per iteration (s): 2.24 | learning rate: 8.516E-05 | global batch size: 512 | lm loss: 1.984589E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.349 | TFLOPs: 23.51 | +63: iteration 43790/ 73814 | consumed samples: 22420480 | consumed tokens: 45917143040 | elapsed time per iteration (s): 2.23 | learning rate: 8.513E-05 | global batch size: 512 | lm loss: 1.962901E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.813 | TFLOPs: 23.66 | +63: iteration 43800/ 73814 | consumed samples: 22425600 | consumed tokens: 45927628800 | elapsed time per iteration (s): 2.23 | learning rate: 8.509E-05 | global batch size: 512 | lm loss: 1.989257E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.070 | TFLOPs: 23.68 | +63: iteration 43810/ 73814 | consumed samples: 22430720 | consumed tokens: 45938114560 | elapsed time per iteration (s): 2.24 | learning rate: 8.505E-05 | global batch size: 512 | lm loss: 2.000330E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.390 | TFLOPs: 23.51 | +63: iteration 43820/ 73814 | consumed samples: 22435840 | consumed tokens: 45948600320 | elapsed time per iteration (s): 2.22 | learning rate: 8.501E-05 | global batch size: 512 | lm loss: 1.983839E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.434 | TFLOPs: 23.72 | +63: iteration 43830/ 73814 | consumed samples: 22440960 | consumed tokens: 45959086080 | elapsed time per iteration (s): 2.23 | learning rate: 8.498E-05 | global batch size: 512 | lm loss: 1.981900E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.999 | TFLOPs: 23.68 | +63: iteration 43840/ 73814 | consumed samples: 22446080 | consumed tokens: 45969571840 | elapsed time per iteration (s): 2.23 | learning rate: 8.494E-05 | global batch size: 512 | lm loss: 1.977933E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.923 | TFLOPs: 23.67 | +63: iteration 43850/ 73814 | consumed samples: 22451200 | consumed tokens: 45980057600 | elapsed time per iteration (s): 2.24 | learning rate: 8.490E-05 | global batch size: 512 | lm loss: 1.987374E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.721 | TFLOPs: 23.55 | +63: iteration 43860/ 73814 | consumed samples: 22456320 | consumed tokens: 45990543360 | elapsed time per iteration (s): 2.25 | learning rate: 8.487E-05 | global batch size: 512 | lm loss: 1.977691E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.081 | TFLOPs: 23.38 | +63: iteration 43870/ 73814 | consumed samples: 22461440 | consumed tokens: 46001029120 | elapsed time per iteration (s): 2.34 | learning rate: 8.483E-05 | global batch size: 512 | lm loss: 1.966163E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.754 | TFLOPs: 22.52 | +63: iteration 43880/ 73814 | consumed samples: 22466560 | consumed tokens: 46011514880 | elapsed time per iteration (s): 2.23 | learning rate: 8.479E-05 | global batch size: 512 | lm loss: 1.990767E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.220 | TFLOPs: 23.60 | +63: iteration 43890/ 73814 | consumed samples: 22471680 | consumed tokens: 46022000640 | elapsed time per iteration (s): 2.26 | learning rate: 8.475E-05 | global batch size: 512 | lm loss: 1.980639E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.994 | TFLOPs: 23.37 | +63: iteration 43900/ 73814 | consumed samples: 22476800 | consumed tokens: 46032486400 | elapsed time per iteration (s): 2.24 | learning rate: 8.472E-05 | global batch size: 512 | lm loss: 1.971953E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.371 | TFLOPs: 23.51 | +63: iteration 43910/ 73814 | consumed samples: 22481920 | consumed tokens: 46042972160 | elapsed time per iteration (s): 2.23 | learning rate: 8.468E-05 | global batch size: 512 | lm loss: 1.978473E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.216 | TFLOPs: 23.60 | +63: iteration 43920/ 73814 | consumed samples: 22487040 | consumed tokens: 46053457920 | elapsed time per iteration (s): 2.24 | learning rate: 8.464E-05 | global batch size: 512 | lm loss: 1.965545E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.009 | TFLOPs: 23.58 | +63: iteration 43930/ 73814 | consumed samples: 22492160 | consumed tokens: 46063943680 | elapsed time per iteration (s): 2.26 | learning rate: 8.461E-05 | global batch size: 512 | lm loss: 1.985764E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.787 | TFLOPs: 23.35 | +63: iteration 43940/ 73814 | consumed samples: 22497280 | consumed tokens: 46074429440 | elapsed time per iteration (s): 2.23 | learning rate: 8.457E-05 | global batch size: 512 | lm loss: 1.980877E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.681 | TFLOPs: 23.64 | +63: iteration 43950/ 73814 | consumed samples: 22502400 | consumed tokens: 46084915200 | elapsed time per iteration (s): 2.25 | learning rate: 8.453E-05 | global batch size: 512 | lm loss: 1.961663E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.142 | TFLOPs: 23.38 | +63: iteration 43960/ 73814 | consumed samples: 22507520 | consumed tokens: 46095400960 | elapsed time per iteration (s): 2.23 | learning rate: 8.449E-05 | global batch size: 512 | lm loss: 1.964972E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.564 | TFLOPs: 23.63 | +63: iteration 43970/ 73814 | consumed samples: 22512640 | consumed tokens: 46105886720 | elapsed time per iteration (s): 2.44 | learning rate: 8.446E-05 | global batch size: 512 | lm loss: 1.977343E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.754 | TFLOPs: 21.59 | +63: iteration 43980/ 73814 | consumed samples: 22517760 | consumed tokens: 46116372480 | elapsed time per iteration (s): 2.23 | learning rate: 8.442E-05 | global batch size: 512 | lm loss: 1.974029E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.844 | TFLOPs: 23.66 | +63: iteration 43990/ 73814 | consumed samples: 22522880 | consumed tokens: 46126858240 | elapsed time per iteration (s): 2.23 | learning rate: 8.438E-05 | global batch size: 512 | lm loss: 1.997085E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.799 | TFLOPs: 23.66 | + 0: [2022-12-02 15:48:45,685] [INFO] [logging.py:68:log_dist] [Rank 0] step=44000, skipped=0, lr=[8.434560866460889e-05, 8.434560866460889e-05, 8.434560866460889e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] + 0: steps: 44000 loss: 2.0270 iter time (s): 2.269 samples/sec: 225.623 +63: iteration 44000/ 73814 | consumed samples: 22528000 | consumed tokens: 46137344000 | elapsed time per iteration (s): 2.32 | learning rate: 8.435E-05 | global batch size: 512 | lm loss: 1.995060E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.547 | TFLOPs: 22.70 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 44000 | lm loss value: 1.976559E+00 | lm loss PPL: 7.217862E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 44010/ 73814 | consumed samples: 22533120 | consumed tokens: 46147829760 | elapsed time per iteration (s): 2.33 | learning rate: 8.431E-05 | global batch size: 512 | lm loss: 1.976779E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.158 | TFLOPs: 22.66 | +63: iteration 44020/ 73814 | consumed samples: 22538240 | consumed tokens: 46158315520 | elapsed time per iteration (s): 2.43 | learning rate: 8.427E-05 | global batch size: 512 | lm loss: 1.982398E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.354 | TFLOPs: 21.65 | +63: iteration 44030/ 73814 | consumed samples: 22543360 | consumed tokens: 46168801280 | elapsed time per iteration (s): 2.41 | learning rate: 8.423E-05 | global batch size: 512 | lm loss: 1.979009E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.073 | TFLOPs: 21.83 | +63: iteration 44040/ 73814 | consumed samples: 22548480 | consumed tokens: 46179287040 | elapsed time per iteration (s): 2.24 | learning rate: 8.420E-05 | global batch size: 512 | lm loss: 2.006385E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.485 | TFLOPs: 23.52 | +63: iteration 44050/ 73814 | consumed samples: 22553600 | consumed tokens: 46189772800 | elapsed time per iteration (s): 2.45 | learning rate: 8.416E-05 | global batch size: 512 | lm loss: 1.988495E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.287 | TFLOPs: 21.55 | +63: iteration 44060/ 73814 | consumed samples: 22558720 | consumed tokens: 46200258560 | elapsed time per iteration (s): 2.51 | learning rate: 8.412E-05 | global batch size: 512 | lm loss: 1.964112E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 203.670 | TFLOPs: 20.97 | +63: iteration 44070/ 73814 | consumed samples: 22563840 | consumed tokens: 46210744320 | elapsed time per iteration (s): 2.60 | learning rate: 8.409E-05 | global batch size: 512 | lm loss: 1.979812E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 196.678 | TFLOPs: 20.25 | +63: iteration 44080/ 73814 | consumed samples: 22568960 | consumed tokens: 46221230080 | elapsed time per iteration (s): 2.58 | learning rate: 8.405E-05 | global batch size: 512 | lm loss: 1.989861E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.786 | TFLOPs: 20.46 | +63: iteration 44090/ 73814 | consumed samples: 22574080 | consumed tokens: 46231715840 | elapsed time per iteration (s): 2.25 | learning rate: 8.401E-05 | global batch size: 512 | lm loss: 2.001482E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.024 | TFLOPs: 23.47 | +63: iteration 44100/ 73814 | consumed samples: 22579200 | consumed tokens: 46242201600 | elapsed time per iteration (s): 2.34 | learning rate: 8.397E-05 | global batch size: 512 | lm loss: 2.015011E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.842 | TFLOPs: 22.53 | +63: iteration 44110/ 73814 | consumed samples: 22584320 | consumed tokens: 46252687360 | elapsed time per iteration (s): 2.52 | learning rate: 8.394E-05 | global batch size: 512 | lm loss: 2.270020E+00 | grad norm: 2.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 203.573 | TFLOPs: 20.96 | +63: iteration 44120/ 73814 | consumed samples: 22589440 | consumed tokens: 46263173120 | elapsed time per iteration (s): 2.29 | learning rate: 8.390E-05 | global batch size: 512 | lm loss: 2.181787E+00 | grad norm: 0.873 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.011 | TFLOPs: 23.06 | +63: iteration 44130/ 73814 | consumed samples: 22594560 | consumed tokens: 46273658880 | elapsed time per iteration (s): 2.28 | learning rate: 8.386E-05 | global batch size: 512 | lm loss: 2.042540E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.772 | TFLOPs: 23.14 | +63: iteration 44140/ 73814 | consumed samples: 22599680 | consumed tokens: 46284144640 | elapsed time per iteration (s): 2.22 | learning rate: 8.383E-05 | global batch size: 512 | lm loss: 2.009988E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.183 | TFLOPs: 23.70 | +63: iteration 44150/ 73814 | consumed samples: 22604800 | consumed tokens: 46294630400 | elapsed time per iteration (s): 2.23 | learning rate: 8.379E-05 | global batch size: 512 | lm loss: 1.977269E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.584 | TFLOPs: 23.63 | +63: iteration 44160/ 73814 | consumed samples: 22609920 | consumed tokens: 46305116160 | elapsed time per iteration (s): 2.55 | learning rate: 8.375E-05 | global batch size: 512 | lm loss: 1.987743E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.523 | TFLOPs: 20.64 | +63: iteration 44170/ 73814 | consumed samples: 22615040 | consumed tokens: 46315601920 | elapsed time per iteration (s): 2.24 | learning rate: 8.372E-05 | global batch size: 512 | lm loss: 1.982616E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.012 | TFLOPs: 23.58 | +63: iteration 44180/ 73814 | consumed samples: 22620160 | consumed tokens: 46326087680 | elapsed time per iteration (s): 2.23 | learning rate: 8.368E-05 | global batch size: 512 | lm loss: 1.994889E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.209 | TFLOPs: 23.60 | +63: iteration 44190/ 73814 | consumed samples: 22625280 | consumed tokens: 46336573440 | elapsed time per iteration (s): 2.23 | learning rate: 8.364E-05 | global batch size: 512 | lm loss: 1.985097E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.700 | TFLOPs: 23.65 | +63: iteration 44200/ 73814 | consumed samples: 22630400 | consumed tokens: 46347059200 | elapsed time per iteration (s): 2.24 | learning rate: 8.360E-05 | global batch size: 512 | lm loss: 1.980197E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.286 | TFLOPs: 23.50 | +63: iteration 44210/ 73814 | consumed samples: 22635520 | consumed tokens: 46357544960 | elapsed time per iteration (s): 2.24 | learning rate: 8.357E-05 | global batch size: 512 | lm loss: 1.991425E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.188 | TFLOPs: 23.49 | +63: iteration 44220/ 73814 | consumed samples: 22640640 | consumed tokens: 46368030720 | elapsed time per iteration (s): 2.42 | learning rate: 8.353E-05 | global batch size: 512 | lm loss: 1.984185E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.582 | TFLOPs: 21.78 | +63: iteration 44230/ 73814 | consumed samples: 22645760 | consumed tokens: 46378516480 | elapsed time per iteration (s): 2.23 | learning rate: 8.349E-05 | global batch size: 512 | lm loss: 1.979561E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.167 | TFLOPs: 23.59 | +63: iteration 44240/ 73814 | consumed samples: 22650880 | consumed tokens: 46389002240 | elapsed time per iteration (s): 2.32 | learning rate: 8.346E-05 | global batch size: 512 | lm loss: 1.977106E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.784 | TFLOPs: 22.73 | +63: iteration 44250/ 73814 | consumed samples: 22656000 | consumed tokens: 46399488000 | elapsed time per iteration (s): 2.27 | learning rate: 8.342E-05 | global batch size: 512 | lm loss: 1.988865E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.031 | TFLOPs: 23.27 | +63: iteration 44260/ 73814 | consumed samples: 22661120 | consumed tokens: 46409973760 | elapsed time per iteration (s): 2.23 | learning rate: 8.338E-05 | global batch size: 512 | lm loss: 1.984906E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.901 | TFLOPs: 23.67 | +63: iteration 44270/ 73814 | consumed samples: 22666240 | consumed tokens: 46420459520 | elapsed time per iteration (s): 2.23 | learning rate: 8.335E-05 | global batch size: 512 | lm loss: 2.010806E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.993 | TFLOPs: 23.68 | +63: iteration 44280/ 73814 | consumed samples: 22671360 | consumed tokens: 46430945280 | elapsed time per iteration (s): 2.31 | learning rate: 8.331E-05 | global batch size: 512 | lm loss: 1.983863E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.471 | TFLOPs: 22.80 | +63: iteration 44290/ 73814 | consumed samples: 22676480 | consumed tokens: 46441431040 | elapsed time per iteration (s): 2.24 | learning rate: 8.327E-05 | global batch size: 512 | lm loss: 1.968769E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.219 | TFLOPs: 23.49 | +63: iteration 44300/ 73814 | consumed samples: 22681600 | consumed tokens: 46451916800 | elapsed time per iteration (s): 2.25 | learning rate: 8.324E-05 | global batch size: 512 | lm loss: 1.978390E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.622 | TFLOPs: 23.43 | +63: iteration 44310/ 73814 | consumed samples: 22686720 | consumed tokens: 46462402560 | elapsed time per iteration (s): 2.23 | learning rate: 8.320E-05 | global batch size: 512 | lm loss: 2.015514E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.785 | TFLOPs: 23.66 | +63: iteration 44320/ 73814 | consumed samples: 22691840 | consumed tokens: 46472888320 | elapsed time per iteration (s): 2.25 | learning rate: 8.316E-05 | global batch size: 512 | lm loss: 1.980395E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.025 | TFLOPs: 23.47 | +63: iteration 44330/ 73814 | consumed samples: 22696960 | consumed tokens: 46483374080 | elapsed time per iteration (s): 2.25 | learning rate: 8.312E-05 | global batch size: 512 | lm loss: 1.989006E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.287 | TFLOPs: 23.40 | +63: iteration 44340/ 73814 | consumed samples: 22702080 | consumed tokens: 46493859840 | elapsed time per iteration (s): 2.25 | learning rate: 8.309E-05 | global batch size: 512 | lm loss: 1.978136E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.380 | TFLOPs: 23.41 | +63: iteration 44350/ 73814 | consumed samples: 22707200 | consumed tokens: 46504345600 | elapsed time per iteration (s): 2.37 | learning rate: 8.305E-05 | global batch size: 512 | lm loss: 1.966333E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.874 | TFLOPs: 22.22 | +63: iteration 44360/ 73814 | consumed samples: 22712320 | consumed tokens: 46514831360 | elapsed time per iteration (s): 2.24 | learning rate: 8.301E-05 | global batch size: 512 | lm loss: 1.984274E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.452 | TFLOPs: 23.52 | +63: iteration 44370/ 73814 | consumed samples: 22717440 | consumed tokens: 46525317120 | elapsed time per iteration (s): 2.23 | learning rate: 8.298E-05 | global batch size: 512 | lm loss: 1.984381E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.823 | TFLOPs: 23.66 | +63: iteration 44380/ 73814 | consumed samples: 22722560 | consumed tokens: 46535802880 | elapsed time per iteration (s): 2.40 | learning rate: 8.294E-05 | global batch size: 512 | lm loss: 1.972244E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.961 | TFLOPs: 21.92 | +63: iteration 44390/ 73814 | consumed samples: 22727680 | consumed tokens: 46546288640 | elapsed time per iteration (s): 2.37 | learning rate: 8.290E-05 | global batch size: 512 | lm loss: 1.995735E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.660 | TFLOPs: 22.20 | +63: iteration 44400/ 73814 | consumed samples: 22732800 | consumed tokens: 46556774400 | elapsed time per iteration (s): 2.33 | learning rate: 8.287E-05 | global batch size: 512 | lm loss: 1.985114E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.635 | TFLOPs: 22.61 | +63: iteration 44410/ 73814 | consumed samples: 22737920 | consumed tokens: 46567260160 | elapsed time per iteration (s): 2.27 | learning rate: 8.283E-05 | global batch size: 512 | lm loss: 1.971790E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.795 | TFLOPs: 23.24 | +63: iteration 44420/ 73814 | consumed samples: 22743040 | consumed tokens: 46577745920 | elapsed time per iteration (s): 2.23 | learning rate: 8.279E-05 | global batch size: 512 | lm loss: 1.987322E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.824 | TFLOPs: 23.66 | +63: iteration 44430/ 73814 | consumed samples: 22748160 | consumed tokens: 46588231680 | elapsed time per iteration (s): 2.34 | learning rate: 8.276E-05 | global batch size: 512 | lm loss: 2.008823E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.027 | TFLOPs: 22.55 | +63: iteration 44440/ 73814 | consumed samples: 22753280 | consumed tokens: 46598717440 | elapsed time per iteration (s): 2.24 | learning rate: 8.272E-05 | global batch size: 512 | lm loss: 1.971791E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.516 | TFLOPs: 23.52 | +63: iteration 44450/ 73814 | consumed samples: 22758400 | consumed tokens: 46609203200 | elapsed time per iteration (s): 2.23 | learning rate: 8.268E-05 | global batch size: 512 | lm loss: 1.971365E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.764 | TFLOPs: 23.65 | +63: iteration 44460/ 73814 | consumed samples: 22763520 | consumed tokens: 46619688960 | elapsed time per iteration (s): 2.22 | learning rate: 8.264E-05 | global batch size: 512 | lm loss: 1.971617E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.278 | TFLOPs: 23.71 | +63: iteration 44470/ 73814 | consumed samples: 22768640 | consumed tokens: 46630174720 | elapsed time per iteration (s): 2.24 | learning rate: 8.261E-05 | global batch size: 512 | lm loss: 1.957283E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.348 | TFLOPs: 23.51 | +63: iteration 44480/ 73814 | consumed samples: 22773760 | consumed tokens: 46640660480 | elapsed time per iteration (s): 2.23 | learning rate: 8.257E-05 | global batch size: 512 | lm loss: 1.976410E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.662 | TFLOPs: 23.64 | +63: iteration 44490/ 73814 | consumed samples: 22778880 | consumed tokens: 46651146240 | elapsed time per iteration (s): 2.23 | learning rate: 8.253E-05 | global batch size: 512 | lm loss: 1.976104E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.025 | TFLOPs: 23.68 | +63: iteration 44500/ 73814 | consumed samples: 22784000 | consumed tokens: 46661632000 | elapsed time per iteration (s): 2.25 | learning rate: 8.250E-05 | global batch size: 512 | lm loss: 1.990657E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.588 | TFLOPs: 23.43 | +63: iteration 44510/ 73814 | consumed samples: 22789120 | consumed tokens: 46672117760 | elapsed time per iteration (s): 2.23 | learning rate: 8.246E-05 | global batch size: 512 | lm loss: 2.001694E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.925 | TFLOPs: 23.67 | +63: iteration 44520/ 73814 | consumed samples: 22794240 | consumed tokens: 46682603520 | elapsed time per iteration (s): 2.24 | learning rate: 8.242E-05 | global batch size: 512 | lm loss: 1.960568E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.453 | TFLOPs: 23.52 | +63: iteration 44530/ 73814 | consumed samples: 22799360 | consumed tokens: 46693089280 | elapsed time per iteration (s): 2.32 | learning rate: 8.239E-05 | global batch size: 512 | lm loss: 1.971431E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.326 | TFLOPs: 22.68 | +63: iteration 44540/ 73814 | consumed samples: 22804480 | consumed tokens: 46703575040 | elapsed time per iteration (s): 2.40 | learning rate: 8.235E-05 | global batch size: 512 | lm loss: 1.997485E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.476 | TFLOPs: 21.98 | +63: iteration 44550/ 73814 | consumed samples: 22809600 | consumed tokens: 46714060800 | elapsed time per iteration (s): 2.35 | learning rate: 8.231E-05 | global batch size: 512 | lm loss: 1.977753E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.514 | TFLOPs: 22.39 | +63: iteration 44560/ 73814 | consumed samples: 22814720 | consumed tokens: 46724546560 | elapsed time per iteration (s): 2.24 | learning rate: 8.228E-05 | global batch size: 512 | lm loss: 1.977618E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.705 | TFLOPs: 23.54 | +63: iteration 44570/ 73814 | consumed samples: 22819840 | consumed tokens: 46735032320 | elapsed time per iteration (s): 2.42 | learning rate: 8.224E-05 | global batch size: 512 | lm loss: 1.994270E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.858 | TFLOPs: 21.81 | +63: iteration 44580/ 73814 | consumed samples: 22824960 | consumed tokens: 46745518080 | elapsed time per iteration (s): 2.30 | learning rate: 8.220E-05 | global batch size: 512 | lm loss: 1.961381E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.806 | TFLOPs: 22.94 | +63: iteration 44590/ 73814 | consumed samples: 22830080 | consumed tokens: 46756003840 | elapsed time per iteration (s): 2.24 | learning rate: 8.217E-05 | global batch size: 512 | lm loss: 1.985575E+00 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.980 | TFLOPs: 23.57 | +63: iteration 44600/ 73814 | consumed samples: 22835200 | consumed tokens: 46766489600 | elapsed time per iteration (s): 2.23 | learning rate: 8.213E-05 | global batch size: 512 | lm loss: 1.977129E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.871 | TFLOPs: 23.66 | +63: iteration 44610/ 73814 | consumed samples: 22840320 | consumed tokens: 46776975360 | elapsed time per iteration (s): 2.23 | learning rate: 8.209E-05 | global batch size: 512 | lm loss: 1.977706E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.108 | TFLOPs: 23.59 | +63: iteration 44620/ 73814 | consumed samples: 22845440 | consumed tokens: 46787461120 | elapsed time per iteration (s): 2.24 | learning rate: 8.206E-05 | global batch size: 512 | lm loss: 1.967510E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.940 | TFLOPs: 23.57 | +63: iteration 44630/ 73814 | consumed samples: 22850560 | consumed tokens: 46797946880 | elapsed time per iteration (s): 2.23 | learning rate: 8.202E-05 | global batch size: 512 | lm loss: 2.011527E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.578 | TFLOPs: 23.63 | +63: iteration 44640/ 73814 | consumed samples: 22855680 | consumed tokens: 46808432640 | elapsed time per iteration (s): 2.23 | learning rate: 8.198E-05 | global batch size: 512 | lm loss: 1.964674E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.828 | TFLOPs: 23.66 | +63: iteration 44650/ 73814 | consumed samples: 22860800 | consumed tokens: 46818918400 | elapsed time per iteration (s): 2.26 | learning rate: 8.195E-05 | global batch size: 512 | lm loss: 1.993255E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.241 | TFLOPs: 23.29 | +63: iteration 44660/ 73814 | consumed samples: 22865920 | consumed tokens: 46829404160 | elapsed time per iteration (s): 2.23 | learning rate: 8.191E-05 | global batch size: 512 | lm loss: 1.966417E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.747 | TFLOPs: 23.65 | +63: iteration 44670/ 73814 | consumed samples: 22871040 | consumed tokens: 46839889920 | elapsed time per iteration (s): 2.26 | learning rate: 8.187E-05 | global batch size: 512 | lm loss: 1.974360E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.115 | TFLOPs: 23.28 | +63: iteration 44680/ 73814 | consumed samples: 22876160 | consumed tokens: 46850375680 | elapsed time per iteration (s): 2.24 | learning rate: 8.184E-05 | global batch size: 512 | lm loss: 1.956405E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.917 | TFLOPs: 23.57 | +63: iteration 44690/ 73814 | consumed samples: 22881280 | consumed tokens: 46860861440 | elapsed time per iteration (s): 2.32 | learning rate: 8.180E-05 | global batch size: 512 | lm loss: 1.962012E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.320 | TFLOPs: 22.68 | +63: iteration 44700/ 73814 | consumed samples: 22886400 | consumed tokens: 46871347200 | elapsed time per iteration (s): 2.23 | learning rate: 8.176E-05 | global batch size: 512 | lm loss: 2.007520E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.134 | TFLOPs: 23.59 | +63: iteration 44710/ 73814 | consumed samples: 22891520 | consumed tokens: 46881832960 | elapsed time per iteration (s): 2.23 | learning rate: 8.172E-05 | global batch size: 512 | lm loss: 1.974744E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.923 | TFLOPs: 23.67 | +63: iteration 44720/ 73814 | consumed samples: 22896640 | consumed tokens: 46892318720 | elapsed time per iteration (s): 2.29 | learning rate: 8.169E-05 | global batch size: 512 | lm loss: 1.951863E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.659 | TFLOPs: 23.02 | +63: iteration 44730/ 73814 | consumed samples: 22901760 | consumed tokens: 46902804480 | elapsed time per iteration (s): 2.26 | learning rate: 8.165E-05 | global batch size: 512 | lm loss: 1.993672E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.785 | TFLOPs: 23.35 | +63: iteration 44740/ 73814 | consumed samples: 22906880 | consumed tokens: 46913290240 | elapsed time per iteration (s): 2.26 | learning rate: 8.161E-05 | global batch size: 512 | lm loss: 1.971560E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.645 | TFLOPs: 23.33 | +63: iteration 44750/ 73814 | consumed samples: 22912000 | consumed tokens: 46923776000 | elapsed time per iteration (s): 2.24 | learning rate: 8.158E-05 | global batch size: 512 | lm loss: 1.966554E+00 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.384 | TFLOPs: 23.51 | +63: iteration 44760/ 73814 | consumed samples: 22917120 | consumed tokens: 46934261760 | elapsed time per iteration (s): 2.24 | learning rate: 8.154E-05 | global batch size: 512 | lm loss: 1.953351E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.904 | TFLOPs: 23.56 | +63: iteration 44770/ 73814 | consumed samples: 22922240 | consumed tokens: 46944747520 | elapsed time per iteration (s): 2.24 | learning rate: 8.150E-05 | global batch size: 512 | lm loss: 1.971231E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.566 | TFLOPs: 23.53 | +63: iteration 44780/ 73814 | consumed samples: 22927360 | consumed tokens: 46955233280 | elapsed time per iteration (s): 2.23 | learning rate: 8.147E-05 | global batch size: 512 | lm loss: 1.981709E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.554 | TFLOPs: 23.63 | +63: iteration 44790/ 73814 | consumed samples: 22932480 | consumed tokens: 46965719040 | elapsed time per iteration (s): 2.23 | learning rate: 8.143E-05 | global batch size: 512 | lm loss: 1.957362E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.985 | TFLOPs: 23.68 | +63: iteration 44800/ 73814 | consumed samples: 22937600 | consumed tokens: 46976204800 | elapsed time per iteration (s): 2.24 | learning rate: 8.139E-05 | global batch size: 512 | lm loss: 1.976576E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.405 | TFLOPs: 23.51 | +63: iteration 44810/ 73814 | consumed samples: 22942720 | consumed tokens: 46986690560 | elapsed time per iteration (s): 2.24 | learning rate: 8.136E-05 | global batch size: 512 | lm loss: 1.967757E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.442 | TFLOPs: 23.52 | +63: iteration 44820/ 73814 | consumed samples: 22947840 | consumed tokens: 46997176320 | elapsed time per iteration (s): 2.29 | learning rate: 8.132E-05 | global batch size: 512 | lm loss: 1.984340E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.621 | TFLOPs: 23.02 | +63: iteration 44830/ 73814 | consumed samples: 22952960 | consumed tokens: 47007662080 | elapsed time per iteration (s): 2.26 | learning rate: 8.128E-05 | global batch size: 512 | lm loss: 1.969665E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.292 | TFLOPs: 23.30 | +63: iteration 44840/ 73814 | consumed samples: 22958080 | consumed tokens: 47018147840 | elapsed time per iteration (s): 2.53 | learning rate: 8.125E-05 | global batch size: 512 | lm loss: 1.973152E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.462 | TFLOPs: 20.84 | +63: iteration 44850/ 73814 | consumed samples: 22963200 | consumed tokens: 47028633600 | elapsed time per iteration (s): 2.23 | learning rate: 8.121E-05 | global batch size: 512 | lm loss: 1.963202E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.397 | TFLOPs: 23.62 | +63: iteration 44860/ 73814 | consumed samples: 22968320 | consumed tokens: 47039119360 | elapsed time per iteration (s): 2.22 | learning rate: 8.117E-05 | global batch size: 512 | lm loss: 1.980609E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.200 | TFLOPs: 23.70 | +63: iteration 44870/ 73814 | consumed samples: 22973440 | consumed tokens: 47049605120 | elapsed time per iteration (s): 2.23 | learning rate: 8.114E-05 | global batch size: 512 | lm loss: 1.974146E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.240 | TFLOPs: 23.60 | +63: iteration 44880/ 73814 | consumed samples: 22978560 | consumed tokens: 47060090880 | elapsed time per iteration (s): 2.33 | learning rate: 8.110E-05 | global batch size: 512 | lm loss: 1.958710E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.658 | TFLOPs: 22.61 | +63: iteration 44890/ 73814 | consumed samples: 22983680 | consumed tokens: 47070576640 | elapsed time per iteration (s): 2.24 | learning rate: 8.106E-05 | global batch size: 512 | lm loss: 1.982057E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.211 | TFLOPs: 23.49 | +63: iteration 44900/ 73814 | consumed samples: 22988800 | consumed tokens: 47081062400 | elapsed time per iteration (s): 2.26 | learning rate: 8.103E-05 | global batch size: 512 | lm loss: 1.985266E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.006 | TFLOPs: 23.37 | +63: iteration 44910/ 73814 | consumed samples: 22993920 | consumed tokens: 47091548160 | elapsed time per iteration (s): 2.23 | learning rate: 8.099E-05 | global batch size: 512 | lm loss: 1.979685E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.806 | TFLOPs: 23.66 | +63: iteration 44920/ 73814 | consumed samples: 22999040 | consumed tokens: 47102033920 | elapsed time per iteration (s): 2.23 | learning rate: 8.095E-05 | global batch size: 512 | lm loss: 1.959872E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.832 | TFLOPs: 23.66 | +63: iteration 44930/ 73814 | consumed samples: 23004160 | consumed tokens: 47112519680 | elapsed time per iteration (s): 2.25 | learning rate: 8.092E-05 | global batch size: 512 | lm loss: 1.943898E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.336 | TFLOPs: 23.40 | +63: iteration 44940/ 73814 | consumed samples: 23009280 | consumed tokens: 47123005440 | elapsed time per iteration (s): 2.25 | learning rate: 8.088E-05 | global batch size: 512 | lm loss: 1.970838E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.711 | TFLOPs: 23.44 | +63: iteration 44950/ 73814 | consumed samples: 23014400 | consumed tokens: 47133491200 | elapsed time per iteration (s): 2.37 | learning rate: 8.084E-05 | global batch size: 512 | lm loss: 1.971795E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.986 | TFLOPs: 22.23 | +63: iteration 44960/ 73814 | consumed samples: 23019520 | consumed tokens: 47143976960 | elapsed time per iteration (s): 2.24 | learning rate: 8.081E-05 | global batch size: 512 | lm loss: 1.966018E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.051 | TFLOPs: 23.58 | +63: iteration 44970/ 73814 | consumed samples: 23024640 | consumed tokens: 47154462720 | elapsed time per iteration (s): 2.46 | learning rate: 8.077E-05 | global batch size: 512 | lm loss: 1.954414E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.471 | TFLOPs: 21.46 | +63: iteration 44980/ 73814 | consumed samples: 23029760 | consumed tokens: 47164948480 | elapsed time per iteration (s): 2.24 | learning rate: 8.073E-05 | global batch size: 512 | lm loss: 1.977318E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.209 | TFLOPs: 23.49 | +63: iteration 44990/ 73814 | consumed samples: 23034880 | consumed tokens: 47175434240 | elapsed time per iteration (s): 2.24 | learning rate: 8.070E-05 | global batch size: 512 | lm loss: 1.971679E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.890 | TFLOPs: 23.56 | +63: iteration 45000/ 73814 | consumed samples: 23040000 | consumed tokens: 47185920000 | elapsed time per iteration (s): 2.26 | learning rate: 8.066E-05 | global batch size: 512 | lm loss: 1.991494E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.588 | TFLOPs: 23.33 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 45000 | lm loss value: 1.985890E+00 | lm loss PPL: 7.285531E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 45010/ 73814 | consumed samples: 23045120 | consumed tokens: 47196405760 | elapsed time per iteration (s): 2.29 | learning rate: 8.063E-05 | global batch size: 512 | lm loss: 1.995732E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.952 | TFLOPs: 23.05 | +63: iteration 45020/ 73814 | consumed samples: 23050240 | consumed tokens: 47206891520 | elapsed time per iteration (s): 2.23 | learning rate: 8.059E-05 | global batch size: 512 | lm loss: 1.980183E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.085 | TFLOPs: 23.69 | +63: iteration 45030/ 73814 | consumed samples: 23055360 | consumed tokens: 47217377280 | elapsed time per iteration (s): 2.25 | learning rate: 8.055E-05 | global batch size: 512 | lm loss: 1.988080E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.132 | TFLOPs: 23.38 | +63: iteration 45040/ 73814 | consumed samples: 23060480 | consumed tokens: 47227863040 | elapsed time per iteration (s): 2.25 | learning rate: 8.052E-05 | global batch size: 512 | lm loss: 1.986599E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.847 | TFLOPs: 23.46 | +63: iteration 45050/ 73814 | consumed samples: 23065600 | consumed tokens: 47238348800 | elapsed time per iteration (s): 2.24 | learning rate: 8.048E-05 | global batch size: 512 | lm loss: 1.964380E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.383 | TFLOPs: 23.51 | +63: iteration 45060/ 73814 | consumed samples: 23070720 | consumed tokens: 47248834560 | elapsed time per iteration (s): 2.23 | learning rate: 8.044E-05 | global batch size: 512 | lm loss: 1.970192E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.411 | TFLOPs: 23.62 | +63: iteration 45070/ 73814 | consumed samples: 23075840 | consumed tokens: 47259320320 | elapsed time per iteration (s): 2.23 | learning rate: 8.041E-05 | global batch size: 512 | lm loss: 1.979650E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.474 | TFLOPs: 23.62 | +63: iteration 45080/ 73814 | consumed samples: 23080960 | consumed tokens: 47269806080 | elapsed time per iteration (s): 2.22 | learning rate: 8.037E-05 | global batch size: 512 | lm loss: 1.988449E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.241 | TFLOPs: 23.70 | +63: iteration 45090/ 73814 | consumed samples: 23086080 | consumed tokens: 47280291840 | elapsed time per iteration (s): 2.23 | learning rate: 8.033E-05 | global batch size: 512 | lm loss: 1.960616E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.928 | TFLOPs: 23.67 | +63: iteration 45100/ 73814 | consumed samples: 23091200 | consumed tokens: 47290777600 | elapsed time per iteration (s): 2.24 | learning rate: 8.030E-05 | global batch size: 512 | lm loss: 1.962213E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.051 | TFLOPs: 23.58 | +63: iteration 45110/ 73814 | consumed samples: 23096320 | consumed tokens: 47301263360 | elapsed time per iteration (s): 2.23 | learning rate: 8.026E-05 | global batch size: 512 | lm loss: 1.967699E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.747 | TFLOPs: 23.65 | +63: iteration 45120/ 73814 | consumed samples: 23101440 | consumed tokens: 47311749120 | elapsed time per iteration (s): 2.23 | learning rate: 8.022E-05 | global batch size: 512 | lm loss: 1.973415E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.593 | TFLOPs: 23.64 | +63: iteration 45130/ 73814 | consumed samples: 23106560 | consumed tokens: 47322234880 | elapsed time per iteration (s): 2.43 | learning rate: 8.019E-05 | global batch size: 512 | lm loss: 1.956176E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.711 | TFLOPs: 21.69 | +63: iteration 45140/ 73814 | consumed samples: 23111680 | consumed tokens: 47332720640 | elapsed time per iteration (s): 2.29 | learning rate: 8.015E-05 | global batch size: 512 | lm loss: 1.986142E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.829 | TFLOPs: 23.04 | +63: iteration 45150/ 73814 | consumed samples: 23116800 | consumed tokens: 47343206400 | elapsed time per iteration (s): 2.29 | learning rate: 8.011E-05 | global batch size: 512 | lm loss: 1.978270E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.290 | TFLOPs: 22.99 | +63: iteration 45160/ 73814 | consumed samples: 23121920 | consumed tokens: 47353692160 | elapsed time per iteration (s): 2.23 | learning rate: 8.008E-05 | global batch size: 512 | lm loss: 1.960686E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.852 | TFLOPs: 23.66 | +63: iteration 45170/ 73814 | consumed samples: 23127040 | consumed tokens: 47364177920 | elapsed time per iteration (s): 2.24 | learning rate: 8.004E-05 | global batch size: 512 | lm loss: 1.990173E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.354 | TFLOPs: 23.51 | +63: iteration 45180/ 73814 | consumed samples: 23132160 | consumed tokens: 47374663680 | elapsed time per iteration (s): 2.34 | learning rate: 8.000E-05 | global batch size: 512 | lm loss: 1.988394E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.713 | TFLOPs: 22.52 | +63: iteration 45190/ 73814 | consumed samples: 23137280 | consumed tokens: 47385149440 | elapsed time per iteration (s): 2.23 | learning rate: 7.997E-05 | global batch size: 512 | lm loss: 1.968361E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.527 | TFLOPs: 23.63 | +63: iteration 45200/ 73814 | consumed samples: 23142400 | consumed tokens: 47395635200 | elapsed time per iteration (s): 2.29 | learning rate: 7.993E-05 | global batch size: 512 | lm loss: 2.007596E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.613 | TFLOPs: 23.02 | +63: iteration 45210/ 73814 | consumed samples: 23147520 | consumed tokens: 47406120960 | elapsed time per iteration (s): 2.23 | learning rate: 7.989E-05 | global batch size: 512 | lm loss: 1.989660E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.704 | TFLOPs: 23.65 | +63: iteration 45220/ 73814 | consumed samples: 23152640 | consumed tokens: 47416606720 | elapsed time per iteration (s): 2.35 | learning rate: 7.986E-05 | global batch size: 512 | lm loss: 1.988266E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.004 | TFLOPs: 22.44 | +63: iteration 45230/ 73814 | consumed samples: 23157760 | consumed tokens: 47427092480 | elapsed time per iteration (s): 2.24 | learning rate: 7.982E-05 | global batch size: 512 | lm loss: 1.954073E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.044 | TFLOPs: 23.58 | +63: iteration 45240/ 73814 | consumed samples: 23162880 | consumed tokens: 47437578240 | elapsed time per iteration (s): 2.33 | learning rate: 7.979E-05 | global batch size: 512 | lm loss: 1.984598E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.697 | TFLOPs: 22.62 | +63: iteration 45250/ 73814 | consumed samples: 23168000 | consumed tokens: 47448064000 | elapsed time per iteration (s): 2.25 | learning rate: 7.975E-05 | global batch size: 512 | lm loss: 1.972239E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.108 | TFLOPs: 23.38 | +63: iteration 45260/ 73814 | consumed samples: 23173120 | consumed tokens: 47458549760 | elapsed time per iteration (s): 2.22 | learning rate: 7.971E-05 | global batch size: 512 | lm loss: 1.955233E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.393 | TFLOPs: 23.72 | +63: iteration 45270/ 73814 | consumed samples: 23178240 | consumed tokens: 47469035520 | elapsed time per iteration (s): 2.23 | learning rate: 7.968E-05 | global batch size: 512 | lm loss: 1.970922E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.844 | TFLOPs: 23.66 | +63: iteration 45280/ 73814 | consumed samples: 23183360 | consumed tokens: 47479521280 | elapsed time per iteration (s): 2.25 | learning rate: 7.964E-05 | global batch size: 512 | lm loss: 1.983150E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.870 | TFLOPs: 23.46 | +63: iteration 45290/ 73814 | consumed samples: 23188480 | consumed tokens: 47490007040 | elapsed time per iteration (s): 2.23 | learning rate: 7.960E-05 | global batch size: 512 | lm loss: 1.984569E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.640 | TFLOPs: 23.64 | +63: iteration 45300/ 73814 | consumed samples: 23193600 | consumed tokens: 47500492800 | elapsed time per iteration (s): 2.24 | learning rate: 7.957E-05 | global batch size: 512 | lm loss: 1.950756E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.061 | TFLOPs: 23.58 | +63: iteration 45310/ 73814 | consumed samples: 23198720 | consumed tokens: 47510978560 | elapsed time per iteration (s): 2.24 | learning rate: 7.953E-05 | global batch size: 512 | lm loss: 1.958675E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.072 | TFLOPs: 23.58 | +63: iteration 45320/ 73814 | consumed samples: 23203840 | consumed tokens: 47521464320 | elapsed time per iteration (s): 2.26 | learning rate: 7.949E-05 | global batch size: 512 | lm loss: 1.956735E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.225 | TFLOPs: 23.29 | +63: iteration 45330/ 73814 | consumed samples: 23208960 | consumed tokens: 47531950080 | elapsed time per iteration (s): 2.23 | learning rate: 7.946E-05 | global batch size: 512 | lm loss: 1.964936E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.233 | TFLOPs: 23.60 | +63: iteration 45340/ 73814 | consumed samples: 23214080 | consumed tokens: 47542435840 | elapsed time per iteration (s): 2.25 | learning rate: 7.942E-05 | global batch size: 512 | lm loss: 1.973851E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.244 | TFLOPs: 23.39 | +63: iteration 45350/ 73814 | consumed samples: 23219200 | consumed tokens: 47552921600 | elapsed time per iteration (s): 2.23 | learning rate: 7.938E-05 | global batch size: 512 | lm loss: 1.983966E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.732 | TFLOPs: 23.65 | +63: iteration 45360/ 73814 | consumed samples: 23224320 | consumed tokens: 47563407360 | elapsed time per iteration (s): 2.24 | learning rate: 7.935E-05 | global batch size: 512 | lm loss: 1.995295E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.848 | TFLOPs: 23.56 | +63: iteration 45370/ 73814 | consumed samples: 23229440 | consumed tokens: 47573893120 | elapsed time per iteration (s): 2.22 | learning rate: 7.931E-05 | global batch size: 512 | lm loss: 1.966803E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.247 | TFLOPs: 23.70 | +63: iteration 45380/ 73814 | consumed samples: 23234560 | consumed tokens: 47584378880 | elapsed time per iteration (s): 2.25 | learning rate: 7.928E-05 | global batch size: 512 | lm loss: 1.969763E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.044 | TFLOPs: 23.48 | +63: iteration 45390/ 73814 | consumed samples: 23239680 | consumed tokens: 47594864640 | elapsed time per iteration (s): 2.22 | learning rate: 7.924E-05 | global batch size: 512 | lm loss: 1.959368E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.126 | TFLOPs: 23.69 | +63: iteration 45400/ 73814 | consumed samples: 23244800 | consumed tokens: 47605350400 | elapsed time per iteration (s): 2.24 | learning rate: 7.920E-05 | global batch size: 512 | lm loss: 1.969192E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.172 | TFLOPs: 23.49 | +63: iteration 45410/ 73814 | consumed samples: 23249920 | consumed tokens: 47615836160 | elapsed time per iteration (s): 2.23 | learning rate: 7.917E-05 | global batch size: 512 | lm loss: 1.960945E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.853 | TFLOPs: 23.66 | +63: iteration 45420/ 73814 | consumed samples: 23255040 | consumed tokens: 47626321920 | elapsed time per iteration (s): 2.31 | learning rate: 7.913E-05 | global batch size: 512 | lm loss: 1.965079E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.489 | TFLOPs: 22.80 | +63: iteration 45430/ 73814 | consumed samples: 23260160 | consumed tokens: 47636807680 | elapsed time per iteration (s): 2.27 | learning rate: 7.909E-05 | global batch size: 512 | lm loss: 1.957121E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.754 | TFLOPs: 23.24 | +63: iteration 45440/ 73814 | consumed samples: 23265280 | consumed tokens: 47647293440 | elapsed time per iteration (s): 2.40 | learning rate: 7.906E-05 | global batch size: 512 | lm loss: 1.944265E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.179 | TFLOPs: 21.95 | +63: iteration 45450/ 73814 | consumed samples: 23270400 | consumed tokens: 47657779200 | elapsed time per iteration (s): 2.34 | learning rate: 7.902E-05 | global batch size: 512 | lm loss: 1.947760E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.340 | TFLOPs: 22.48 | +63: iteration 45460/ 73814 | consumed samples: 23275520 | consumed tokens: 47668264960 | elapsed time per iteration (s): 2.25 | learning rate: 7.899E-05 | global batch size: 512 | lm loss: 1.942690E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.831 | TFLOPs: 23.45 | +63: iteration 45470/ 73814 | consumed samples: 23280640 | consumed tokens: 47678750720 | elapsed time per iteration (s): 2.42 | learning rate: 7.895E-05 | global batch size: 512 | lm loss: 1.971024E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.733 | TFLOPs: 21.80 | +63: iteration 45480/ 73814 | consumed samples: 23285760 | consumed tokens: 47689236480 | elapsed time per iteration (s): 2.24 | learning rate: 7.891E-05 | global batch size: 512 | lm loss: 1.969312E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.000 | TFLOPs: 23.57 | +63: iteration 45490/ 73814 | consumed samples: 23290880 | consumed tokens: 47699722240 | elapsed time per iteration (s): 2.23 | learning rate: 7.888E-05 | global batch size: 512 | lm loss: 1.984119E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.001 | TFLOPs: 23.68 | +63: iteration 45500/ 73814 | consumed samples: 23296000 | consumed tokens: 47710208000 | elapsed time per iteration (s): 2.23 | learning rate: 7.884E-05 | global batch size: 512 | lm loss: 1.976276E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.258 | TFLOPs: 23.60 | +63: iteration 45510/ 73814 | consumed samples: 23301120 | consumed tokens: 47720693760 | elapsed time per iteration (s): 2.25 | learning rate: 7.880E-05 | global batch size: 512 | lm loss: 1.960039E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.208 | TFLOPs: 23.39 | +63: iteration 45520/ 73814 | consumed samples: 23306240 | consumed tokens: 47731179520 | elapsed time per iteration (s): 2.24 | learning rate: 7.877E-05 | global batch size: 512 | lm loss: 1.950686E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.745 | TFLOPs: 23.55 | +63: iteration 45530/ 73814 | consumed samples: 23311360 | consumed tokens: 47741665280 | elapsed time per iteration (s): 2.24 | learning rate: 7.873E-05 | global batch size: 512 | lm loss: 1.973106E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.079 | TFLOPs: 23.48 | +63: iteration 45540/ 73814 | consumed samples: 23316480 | consumed tokens: 47752151040 | elapsed time per iteration (s): 2.24 | learning rate: 7.869E-05 | global batch size: 512 | lm loss: 1.975756E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.664 | TFLOPs: 23.54 | +63: iteration 45550/ 73814 | consumed samples: 23321600 | consumed tokens: 47762636800 | elapsed time per iteration (s): 2.24 | learning rate: 7.866E-05 | global batch size: 512 | lm loss: 1.964211E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.063 | TFLOPs: 23.48 | +63: iteration 45560/ 73814 | consumed samples: 23326720 | consumed tokens: 47773122560 | elapsed time per iteration (s): 2.23 | learning rate: 7.862E-05 | global batch size: 512 | lm loss: 1.950033E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.596 | TFLOPs: 23.64 | +63: iteration 45570/ 73814 | consumed samples: 23331840 | consumed tokens: 47783608320 | elapsed time per iteration (s): 2.24 | learning rate: 7.859E-05 | global batch size: 512 | lm loss: 1.968061E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.099 | TFLOPs: 23.48 | +63: iteration 45580/ 73814 | consumed samples: 23336960 | consumed tokens: 47794094080 | elapsed time per iteration (s): 2.48 | learning rate: 7.855E-05 | global batch size: 512 | lm loss: 1.973158E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.808 | TFLOPs: 21.29 | +63: iteration 45590/ 73814 | consumed samples: 23342080 | consumed tokens: 47804579840 | elapsed time per iteration (s): 2.38 | learning rate: 7.851E-05 | global batch size: 512 | lm loss: 1.955408E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.567 | TFLOPs: 22.19 | +63: iteration 45600/ 73814 | consumed samples: 23347200 | consumed tokens: 47815065600 | elapsed time per iteration (s): 2.24 | learning rate: 7.848E-05 | global batch size: 512 | lm loss: 1.970396E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.169 | TFLOPs: 23.49 | +63: iteration 45610/ 73814 | consumed samples: 23352320 | consumed tokens: 47825551360 | elapsed time per iteration (s): 2.25 | learning rate: 7.844E-05 | global batch size: 512 | lm loss: 1.978804E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.485 | TFLOPs: 23.42 | +63: iteration 45620/ 73814 | consumed samples: 23357440 | consumed tokens: 47836037120 | elapsed time per iteration (s): 2.23 | learning rate: 7.840E-05 | global batch size: 512 | lm loss: 1.974089E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.463 | TFLOPs: 23.62 | +63: iteration 45630/ 73814 | consumed samples: 23362560 | consumed tokens: 47846522880 | elapsed time per iteration (s): 2.27 | learning rate: 7.837E-05 | global batch size: 512 | lm loss: 1.983704E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.779 | TFLOPs: 23.24 | +63: iteration 45640/ 73814 | consumed samples: 23367680 | consumed tokens: 47857008640 | elapsed time per iteration (s): 2.24 | learning rate: 7.833E-05 | global batch size: 512 | lm loss: 1.976292E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.563 | TFLOPs: 23.53 | +63: iteration 45650/ 73814 | consumed samples: 23372800 | consumed tokens: 47867494400 | elapsed time per iteration (s): 2.24 | learning rate: 7.830E-05 | global batch size: 512 | lm loss: 1.968416E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.262 | TFLOPs: 23.50 | +63: iteration 45660/ 73814 | consumed samples: 23377920 | consumed tokens: 47877980160 | elapsed time per iteration (s): 2.25 | learning rate: 7.826E-05 | global batch size: 512 | lm loss: 1.981502E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.851 | TFLOPs: 23.46 | +63: iteration 45670/ 73814 | consumed samples: 23383040 | consumed tokens: 47888465920 | elapsed time per iteration (s): 2.24 | learning rate: 7.822E-05 | global batch size: 512 | lm loss: 1.968883E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.692 | TFLOPs: 23.54 | +63: iteration 45680/ 73814 | consumed samples: 23388160 | consumed tokens: 47898951680 | elapsed time per iteration (s): 2.46 | learning rate: 7.819E-05 | global batch size: 512 | lm loss: 1.974433E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 207.735 | TFLOPs: 21.39 | +63: iteration 45690/ 73814 | consumed samples: 23393280 | consumed tokens: 47909437440 | elapsed time per iteration (s): 2.25 | learning rate: 7.815E-05 | global batch size: 512 | lm loss: 1.975940E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.449 | TFLOPs: 23.41 | +63: iteration 45700/ 73814 | consumed samples: 23398400 | consumed tokens: 47919923200 | elapsed time per iteration (s): 2.23 | learning rate: 7.812E-05 | global batch size: 512 | lm loss: 1.942091E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.426 | TFLOPs: 23.62 | +63: iteration 45710/ 73814 | consumed samples: 23403520 | consumed tokens: 47930408960 | elapsed time per iteration (s): 2.27 | learning rate: 7.808E-05 | global batch size: 512 | lm loss: 1.980612E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.232 | TFLOPs: 23.19 | +63: iteration 45720/ 73814 | consumed samples: 23408640 | consumed tokens: 47940894720 | elapsed time per iteration (s): 2.27 | learning rate: 7.804E-05 | global batch size: 512 | lm loss: 1.961877E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.184 | TFLOPs: 23.18 | +63: iteration 45730/ 73814 | consumed samples: 23413760 | consumed tokens: 47951380480 | elapsed time per iteration (s): 2.26 | learning rate: 7.801E-05 | global batch size: 512 | lm loss: 1.975190E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.454 | TFLOPs: 23.31 | +63: iteration 45740/ 73814 | consumed samples: 23418880 | consumed tokens: 47961866240 | elapsed time per iteration (s): 2.58 | learning rate: 7.797E-05 | global batch size: 512 | lm loss: 1.962607E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.418 | TFLOPs: 20.43 | +63: iteration 45750/ 73814 | consumed samples: 23424000 | consumed tokens: 47972352000 | elapsed time per iteration (s): 2.24 | learning rate: 7.793E-05 | global batch size: 512 | lm loss: 2.003132E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.323 | TFLOPs: 23.50 | +63: iteration 45760/ 73814 | consumed samples: 23429120 | consumed tokens: 47982837760 | elapsed time per iteration (s): 2.35 | learning rate: 7.790E-05 | global batch size: 512 | lm loss: 1.971158E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.077 | TFLOPs: 22.45 | +63: iteration 45770/ 73814 | consumed samples: 23434240 | consumed tokens: 47993323520 | elapsed time per iteration (s): 2.96 | learning rate: 7.786E-05 | global batch size: 512 | lm loss: 1.974166E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 173.028 | TFLOPs: 17.81 | +63: iteration 45780/ 73814 | consumed samples: 23439360 | consumed tokens: 48003809280 | elapsed time per iteration (s): 2.86 | learning rate: 7.783E-05 | global batch size: 512 | lm loss: 1.944007E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 179.009 | TFLOPs: 18.43 | +63: iteration 45790/ 73814 | consumed samples: 23444480 | consumed tokens: 48014295040 | elapsed time per iteration (s): 2.73 | learning rate: 7.779E-05 | global batch size: 512 | lm loss: 1.968967E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 187.815 | TFLOPs: 19.33 | +63: iteration 45800/ 73814 | consumed samples: 23449600 | consumed tokens: 48024780800 | elapsed time per iteration (s): 2.44 | learning rate: 7.775E-05 | global batch size: 512 | lm loss: 1.970008E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.235 | TFLOPs: 21.64 | +63: iteration 45810/ 73814 | consumed samples: 23454720 | consumed tokens: 48035266560 | elapsed time per iteration (s): 2.36 | learning rate: 7.772E-05 | global batch size: 512 | lm loss: 1.967741E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.356 | TFLOPs: 22.38 | +63: iteration 45820/ 73814 | consumed samples: 23459840 | consumed tokens: 48045752320 | elapsed time per iteration (s): 2.35 | learning rate: 7.768E-05 | global batch size: 512 | lm loss: 1.969334E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.531 | TFLOPs: 22.39 | +63: iteration 45830/ 73814 | consumed samples: 23464960 | consumed tokens: 48056238080 | elapsed time per iteration (s): 2.26 | learning rate: 7.765E-05 | global batch size: 512 | lm loss: 1.989165E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.184 | TFLOPs: 23.28 | +63: iteration 45840/ 73814 | consumed samples: 23470080 | consumed tokens: 48066723840 | elapsed time per iteration (s): 2.31 | learning rate: 7.761E-05 | global batch size: 512 | lm loss: 1.984337E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.578 | TFLOPs: 22.81 | +63: iteration 45850/ 73814 | consumed samples: 23475200 | consumed tokens: 48077209600 | elapsed time per iteration (s): 2.23 | learning rate: 7.757E-05 | global batch size: 512 | lm loss: 1.945229E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.345 | TFLOPs: 23.61 | +63: iteration 45860/ 73814 | consumed samples: 23480320 | consumed tokens: 48087695360 | elapsed time per iteration (s): 2.24 | learning rate: 7.754E-05 | global batch size: 512 | lm loss: 1.957568E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.812 | TFLOPs: 23.56 | +63: iteration 45870/ 73814 | consumed samples: 23485440 | consumed tokens: 48098181120 | elapsed time per iteration (s): 2.32 | learning rate: 7.750E-05 | global batch size: 512 | lm loss: 1.952493E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.917 | TFLOPs: 22.74 | +63: iteration 45880/ 73814 | consumed samples: 23490560 | consumed tokens: 48108666880 | elapsed time per iteration (s): 2.23 | learning rate: 7.746E-05 | global batch size: 512 | lm loss: 1.953312E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.906 | TFLOPs: 23.67 | +63: iteration 45890/ 73814 | consumed samples: 23495680 | consumed tokens: 48119152640 | elapsed time per iteration (s): 2.25 | learning rate: 7.743E-05 | global batch size: 512 | lm loss: 1.973248E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.115 | TFLOPs: 23.38 | +63: iteration 45900/ 73814 | consumed samples: 23500800 | consumed tokens: 48129638400 | elapsed time per iteration (s): 2.24 | learning rate: 7.739E-05 | global batch size: 512 | lm loss: 1.973545E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.297 | TFLOPs: 23.50 | +63: iteration 45910/ 73814 | consumed samples: 23505920 | consumed tokens: 48140124160 | elapsed time per iteration (s): 2.24 | learning rate: 7.736E-05 | global batch size: 512 | lm loss: 1.971761E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.340 | TFLOPs: 23.51 | +63: iteration 45920/ 73814 | consumed samples: 23511040 | consumed tokens: 48150609920 | elapsed time per iteration (s): 2.24 | learning rate: 7.732E-05 | global batch size: 512 | lm loss: 1.959414E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.836 | TFLOPs: 23.56 | +63: iteration 45930/ 73814 | consumed samples: 23516160 | consumed tokens: 48161095680 | elapsed time per iteration (s): 2.48 | learning rate: 7.728E-05 | global batch size: 512 | lm loss: 1.952545E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.407 | TFLOPs: 21.25 | +63: iteration 45940/ 73814 | consumed samples: 23521280 | consumed tokens: 48171581440 | elapsed time per iteration (s): 2.25 | learning rate: 7.725E-05 | global batch size: 512 | lm loss: 1.955323E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.343 | TFLOPs: 23.40 | +63: iteration 45950/ 73814 | consumed samples: 23526400 | consumed tokens: 48182067200 | elapsed time per iteration (s): 2.34 | learning rate: 7.721E-05 | global batch size: 512 | lm loss: 1.968315E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.378 | TFLOPs: 22.48 | +63: iteration 45960/ 73814 | consumed samples: 23531520 | consumed tokens: 48192552960 | elapsed time per iteration (s): 2.36 | learning rate: 7.718E-05 | global batch size: 512 | lm loss: 1.978603E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.240 | TFLOPs: 22.36 | +63: iteration 45970/ 73814 | consumed samples: 23536640 | consumed tokens: 48203038720 | elapsed time per iteration (s): 2.24 | learning rate: 7.714E-05 | global batch size: 512 | lm loss: 1.958002E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.618 | TFLOPs: 23.54 | +63: iteration 45980/ 73814 | consumed samples: 23541760 | consumed tokens: 48213524480 | elapsed time per iteration (s): 2.26 | learning rate: 7.710E-05 | global batch size: 512 | lm loss: 1.978188E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.582 | TFLOPs: 23.33 | +63: iteration 45990/ 73814 | consumed samples: 23546880 | consumed tokens: 48224010240 | elapsed time per iteration (s): 2.34 | learning rate: 7.707E-05 | global batch size: 512 | lm loss: 1.960182E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.232 | TFLOPs: 22.57 | + 0: [2022-12-02 17:05:06,340] [INFO] [logging.py:68:log_dist] [Rank 0] step=46000, skipped=0, lr=[7.703224342204235e-05, 7.703224342204235e-05, 7.703224342204235e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 46000/ 73814 | consumed samples: 23552000 | consumed tokens: 48234496000 | elapsed time per iteration (s): 2.24 | learning rate: 7.703E-05 | global batch size: 512 | lm loss: 1.967288E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.276 | TFLOPs: 23.50 | + 0: steps: 46000 loss: 1.9056 iter time (s): 2.288 samples/sec: 223.824 +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 46000 | lm loss value: 1.948480E+00 | lm loss PPL: 7.018010E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 46010/ 73814 | consumed samples: 23557120 | consumed tokens: 48244981760 | elapsed time per iteration (s): 2.30 | learning rate: 7.700E-05 | global batch size: 512 | lm loss: 1.984788E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.173 | TFLOPs: 22.87 | +63: iteration 46020/ 73814 | consumed samples: 23562240 | consumed tokens: 48255467520 | elapsed time per iteration (s): 2.53 | learning rate: 7.696E-05 | global batch size: 512 | lm loss: 1.979975E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.363 | TFLOPs: 20.83 | +63: iteration 46030/ 73814 | consumed samples: 23567360 | consumed tokens: 48265953280 | elapsed time per iteration (s): 2.25 | learning rate: 7.692E-05 | global batch size: 512 | lm loss: 1.951060E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.628 | TFLOPs: 23.43 | +63: iteration 46040/ 73814 | consumed samples: 23572480 | consumed tokens: 48276439040 | elapsed time per iteration (s): 2.23 | learning rate: 7.689E-05 | global batch size: 512 | lm loss: 1.966152E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.299 | TFLOPs: 23.61 | +63: iteration 46050/ 73814 | consumed samples: 23577600 | consumed tokens: 48286924800 | elapsed time per iteration (s): 2.23 | learning rate: 7.685E-05 | global batch size: 512 | lm loss: 1.956217E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.108 | TFLOPs: 23.59 | +63: iteration 46060/ 73814 | consumed samples: 23582720 | consumed tokens: 48297410560 | elapsed time per iteration (s): 3.80 | learning rate: 7.682E-05 | global batch size: 512 | lm loss: 2.001337E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 134.823 | TFLOPs: 13.88 | +63: iteration 46070/ 73814 | consumed samples: 23587840 | consumed tokens: 48307896320 | elapsed time per iteration (s): 2.23 | learning rate: 7.678E-05 | global batch size: 512 | lm loss: 1.952073E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.556 | TFLOPs: 23.63 | +63: iteration 46080/ 73814 | consumed samples: 23592960 | consumed tokens: 48318382080 | elapsed time per iteration (s): 2.31 | learning rate: 7.674E-05 | global batch size: 512 | lm loss: 1.943116E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.566 | TFLOPs: 22.81 | +63: iteration 46090/ 73814 | consumed samples: 23598080 | consumed tokens: 48328867840 | elapsed time per iteration (s): 2.25 | learning rate: 7.671E-05 | global batch size: 512 | lm loss: 1.969612E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.482 | TFLOPs: 23.42 | +63: iteration 46100/ 73814 | consumed samples: 23603200 | consumed tokens: 48339353600 | elapsed time per iteration (s): 2.41 | learning rate: 7.667E-05 | global batch size: 512 | lm loss: 1.981883E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.101 | TFLOPs: 21.83 | +63: iteration 46110/ 73814 | consumed samples: 23608320 | consumed tokens: 48349839360 | elapsed time per iteration (s): 2.35 | learning rate: 7.664E-05 | global batch size: 512 | lm loss: 1.952180E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.437 | TFLOPs: 22.38 | +63: iteration 46120/ 73814 | consumed samples: 23613440 | consumed tokens: 48360325120 | elapsed time per iteration (s): 2.25 | learning rate: 7.660E-05 | global batch size: 512 | lm loss: 1.987817E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.125 | TFLOPs: 23.38 | +63: iteration 46130/ 73814 | consumed samples: 23618560 | consumed tokens: 48370810880 | elapsed time per iteration (s): 2.24 | learning rate: 7.656E-05 | global batch size: 512 | lm loss: 1.959382E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.523 | TFLOPs: 23.53 | +63: iteration 46140/ 73814 | consumed samples: 23623680 | consumed tokens: 48381296640 | elapsed time per iteration (s): 2.22 | learning rate: 7.653E-05 | global batch size: 512 | lm loss: 1.993976E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.298 | TFLOPs: 23.71 | +63: iteration 46150/ 73814 | consumed samples: 23628800 | consumed tokens: 48391782400 | elapsed time per iteration (s): 2.23 | learning rate: 7.649E-05 | global batch size: 512 | lm loss: 1.972600E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.535 | TFLOPs: 23.63 | +63: iteration 46160/ 73814 | consumed samples: 23633920 | consumed tokens: 48402268160 | elapsed time per iteration (s): 2.24 | learning rate: 7.646E-05 | global batch size: 512 | lm loss: 1.940620E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.000 | TFLOPs: 23.57 | +63: iteration 46170/ 73814 | consumed samples: 23639040 | consumed tokens: 48412753920 | elapsed time per iteration (s): 2.23 | learning rate: 7.642E-05 | global batch size: 512 | lm loss: 1.969516E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.008 | TFLOPs: 23.68 | +63: iteration 46180/ 73814 | consumed samples: 23644160 | consumed tokens: 48423239680 | elapsed time per iteration (s): 2.23 | learning rate: 7.639E-05 | global batch size: 512 | lm loss: 1.965699E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.581 | TFLOPs: 23.63 | +63: iteration 46190/ 73814 | consumed samples: 23649280 | consumed tokens: 48433725440 | elapsed time per iteration (s): 2.23 | learning rate: 7.635E-05 | global batch size: 512 | lm loss: 1.955164E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.078 | TFLOPs: 23.69 | +63: iteration 46200/ 73814 | consumed samples: 23654400 | consumed tokens: 48444211200 | elapsed time per iteration (s): 2.25 | learning rate: 7.631E-05 | global batch size: 512 | lm loss: 1.966486E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.796 | TFLOPs: 23.45 | +63: iteration 46210/ 73814 | consumed samples: 23659520 | consumed tokens: 48454696960 | elapsed time per iteration (s): 2.24 | learning rate: 7.628E-05 | global batch size: 512 | lm loss: 1.969383E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.919 | TFLOPs: 23.57 | +63: iteration 46220/ 73814 | consumed samples: 23664640 | consumed tokens: 48465182720 | elapsed time per iteration (s): 2.25 | learning rate: 7.624E-05 | global batch size: 512 | lm loss: 1.962120E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.436 | TFLOPs: 23.41 | +63: iteration 46230/ 73814 | consumed samples: 23669760 | consumed tokens: 48475668480 | elapsed time per iteration (s): 2.35 | learning rate: 7.621E-05 | global batch size: 512 | lm loss: 1.961994E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.827 | TFLOPs: 22.42 | +63: iteration 46240/ 73814 | consumed samples: 23674880 | consumed tokens: 48486154240 | elapsed time per iteration (s): 2.33 | learning rate: 7.617E-05 | global batch size: 512 | lm loss: 1.969991E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.032 | TFLOPs: 22.65 | +63: iteration 46250/ 73814 | consumed samples: 23680000 | consumed tokens: 48496640000 | elapsed time per iteration (s): 2.31 | learning rate: 7.613E-05 | global batch size: 512 | lm loss: 1.965003E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.994 | TFLOPs: 22.85 | +63: iteration 46260/ 73814 | consumed samples: 23685120 | consumed tokens: 48507125760 | elapsed time per iteration (s): 2.25 | learning rate: 7.610E-05 | global batch size: 512 | lm loss: 1.965956E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.542 | TFLOPs: 23.42 | +63: iteration 46270/ 73814 | consumed samples: 23690240 | consumed tokens: 48517611520 | elapsed time per iteration (s): 2.35 | learning rate: 7.606E-05 | global batch size: 512 | lm loss: 1.962903E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.188 | TFLOPs: 22.46 | +63: iteration 46280/ 73814 | consumed samples: 23695360 | consumed tokens: 48528097280 | elapsed time per iteration (s): 2.25 | learning rate: 7.603E-05 | global batch size: 512 | lm loss: 1.977465E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.890 | TFLOPs: 23.46 | +63: iteration 46290/ 73814 | consumed samples: 23700480 | consumed tokens: 48538583040 | elapsed time per iteration (s): 2.25 | learning rate: 7.599E-05 | global batch size: 512 | lm loss: 1.980077E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.959 | TFLOPs: 23.47 | +63: iteration 46300/ 73814 | consumed samples: 23705600 | consumed tokens: 48549068800 | elapsed time per iteration (s): 2.27 | learning rate: 7.595E-05 | global batch size: 512 | lm loss: 1.957781E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.418 | TFLOPs: 23.21 | +63: iteration 46310/ 73814 | consumed samples: 23710720 | consumed tokens: 48559554560 | elapsed time per iteration (s): 2.23 | learning rate: 7.592E-05 | global batch size: 512 | lm loss: 1.958591E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.741 | TFLOPs: 23.65 | +63: iteration 46320/ 73814 | consumed samples: 23715840 | consumed tokens: 48570040320 | elapsed time per iteration (s): 2.25 | learning rate: 7.588E-05 | global batch size: 512 | lm loss: 1.980177E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.724 | TFLOPs: 23.44 | +63: iteration 46330/ 73814 | consumed samples: 23720960 | consumed tokens: 48580526080 | elapsed time per iteration (s): 2.24 | learning rate: 7.585E-05 | global batch size: 512 | lm loss: 1.970995E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.012 | TFLOPs: 23.58 | +63: iteration 46340/ 73814 | consumed samples: 23726080 | consumed tokens: 48591011840 | elapsed time per iteration (s): 2.24 | learning rate: 7.581E-05 | global batch size: 512 | lm loss: 1.978847E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.960 | TFLOPs: 23.57 | +63: iteration 46350/ 73814 | consumed samples: 23731200 | consumed tokens: 48601497600 | elapsed time per iteration (s): 2.24 | learning rate: 7.578E-05 | global batch size: 512 | lm loss: 1.963563E+00 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.598 | TFLOPs: 23.53 | +63: iteration 46360/ 73814 | consumed samples: 23736320 | consumed tokens: 48611983360 | elapsed time per iteration (s): 2.23 | learning rate: 7.574E-05 | global batch size: 512 | lm loss: 1.944701E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.704 | TFLOPs: 23.65 | +63: iteration 46370/ 73814 | consumed samples: 23741440 | consumed tokens: 48622469120 | elapsed time per iteration (s): 2.24 | learning rate: 7.570E-05 | global batch size: 512 | lm loss: 1.996121E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.319 | TFLOPs: 23.50 | +63: iteration 46380/ 73814 | consumed samples: 23746560 | consumed tokens: 48632954880 | elapsed time per iteration (s): 2.22 | learning rate: 7.567E-05 | global batch size: 512 | lm loss: 1.969570E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.120 | TFLOPs: 23.69 | +63: iteration 46390/ 73814 | consumed samples: 23751680 | consumed tokens: 48643440640 | elapsed time per iteration (s): 2.33 | learning rate: 7.563E-05 | global batch size: 512 | lm loss: 1.969580E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.176 | TFLOPs: 22.67 | +63: iteration 46400/ 73814 | consumed samples: 23756800 | consumed tokens: 48653926400 | elapsed time per iteration (s): 2.23 | learning rate: 7.560E-05 | global batch size: 512 | lm loss: 1.997671E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.732 | TFLOPs: 23.65 | +63: iteration 46410/ 73814 | consumed samples: 23761920 | consumed tokens: 48664412160 | elapsed time per iteration (s): 2.24 | learning rate: 7.556E-05 | global batch size: 512 | lm loss: 1.966153E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.314 | TFLOPs: 23.50 | +63: iteration 46420/ 73814 | consumed samples: 23767040 | consumed tokens: 48674897920 | elapsed time per iteration (s): 2.48 | learning rate: 7.553E-05 | global batch size: 512 | lm loss: 2.001987E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.403 | TFLOPs: 21.25 | +63: iteration 46430/ 73814 | consumed samples: 23772160 | consumed tokens: 48685383680 | elapsed time per iteration (s): 2.24 | learning rate: 7.549E-05 | global batch size: 512 | lm loss: 1.969004E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.054 | TFLOPs: 23.58 | +63: iteration 46440/ 73814 | consumed samples: 23777280 | consumed tokens: 48695869440 | elapsed time per iteration (s): 2.27 | learning rate: 7.545E-05 | global batch size: 512 | lm loss: 1.965887E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.741 | TFLOPs: 23.24 | +63: iteration 46450/ 73814 | consumed samples: 23782400 | consumed tokens: 48706355200 | elapsed time per iteration (s): 2.23 | learning rate: 7.542E-05 | global batch size: 512 | lm loss: 1.953399E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.628 | TFLOPs: 23.64 | +63: iteration 46460/ 73814 | consumed samples: 23787520 | consumed tokens: 48716840960 | elapsed time per iteration (s): 2.24 | learning rate: 7.538E-05 | global batch size: 512 | lm loss: 1.971301E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.250 | TFLOPs: 23.50 | +63: iteration 46470/ 73814 | consumed samples: 23792640 | consumed tokens: 48727326720 | elapsed time per iteration (s): 2.24 | learning rate: 7.535E-05 | global batch size: 512 | lm loss: 1.992140E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.537 | TFLOPs: 23.53 | +63: iteration 46480/ 73814 | consumed samples: 23797760 | consumed tokens: 48737812480 | elapsed time per iteration (s): 2.23 | learning rate: 7.531E-05 | global batch size: 512 | lm loss: 1.935377E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.621 | TFLOPs: 23.64 | +63: iteration 46490/ 73814 | consumed samples: 23802880 | consumed tokens: 48748298240 | elapsed time per iteration (s): 2.23 | learning rate: 7.528E-05 | global batch size: 512 | lm loss: 1.949775E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.032 | TFLOPs: 23.68 | +63: iteration 46500/ 73814 | consumed samples: 23808000 | consumed tokens: 48758784000 | elapsed time per iteration (s): 2.23 | learning rate: 7.524E-05 | global batch size: 512 | lm loss: 1.982680E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.824 | TFLOPs: 23.66 | +63: iteration 46510/ 73814 | consumed samples: 23813120 | consumed tokens: 48769269760 | elapsed time per iteration (s): 2.24 | learning rate: 7.520E-05 | global batch size: 512 | lm loss: 1.956866E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.003 | TFLOPs: 23.57 | +63: iteration 46520/ 73814 | consumed samples: 23818240 | consumed tokens: 48779755520 | elapsed time per iteration (s): 2.29 | learning rate: 7.517E-05 | global batch size: 512 | lm loss: 1.941126E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.632 | TFLOPs: 23.02 | +63: iteration 46530/ 73814 | consumed samples: 23823360 | consumed tokens: 48790241280 | elapsed time per iteration (s): 2.24 | learning rate: 7.513E-05 | global batch size: 512 | lm loss: 1.963401E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.363 | TFLOPs: 23.51 | +63: iteration 46540/ 73814 | consumed samples: 23828480 | consumed tokens: 48800727040 | elapsed time per iteration (s): 2.23 | learning rate: 7.510E-05 | global batch size: 512 | lm loss: 1.991617E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.101 | TFLOPs: 23.69 | +63: iteration 46550/ 73814 | consumed samples: 23833600 | consumed tokens: 48811212800 | elapsed time per iteration (s): 2.40 | learning rate: 7.506E-05 | global batch size: 512 | lm loss: 1.950436E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.458 | TFLOPs: 21.97 | +63: iteration 46560/ 73814 | consumed samples: 23838720 | consumed tokens: 48821698560 | elapsed time per iteration (s): 2.23 | learning rate: 7.503E-05 | global batch size: 512 | lm loss: 1.947495E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.568 | TFLOPs: 23.63 | +63: iteration 46570/ 73814 | consumed samples: 23843840 | consumed tokens: 48832184320 | elapsed time per iteration (s): 2.25 | learning rate: 7.499E-05 | global batch size: 512 | lm loss: 1.955869E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.226 | TFLOPs: 23.39 | +63: iteration 46580/ 73814 | consumed samples: 23848960 | consumed tokens: 48842670080 | elapsed time per iteration (s): 2.31 | learning rate: 7.495E-05 | global batch size: 512 | lm loss: 1.973715E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.477 | TFLOPs: 22.80 | +63: iteration 46590/ 73814 | consumed samples: 23854080 | consumed tokens: 48853155840 | elapsed time per iteration (s): 2.24 | learning rate: 7.492E-05 | global batch size: 512 | lm loss: 1.987047E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.983 | TFLOPs: 23.57 | +63: iteration 46600/ 73814 | consumed samples: 23859200 | consumed tokens: 48863641600 | elapsed time per iteration (s): 2.25 | learning rate: 7.488E-05 | global batch size: 512 | lm loss: 1.966600E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.186 | TFLOPs: 23.39 | +63: iteration 46610/ 73814 | consumed samples: 23864320 | consumed tokens: 48874127360 | elapsed time per iteration (s): 2.23 | learning rate: 7.485E-05 | global batch size: 512 | lm loss: 1.960892E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.184 | TFLOPs: 23.59 | +63: iteration 46620/ 73814 | consumed samples: 23869440 | consumed tokens: 48884613120 | elapsed time per iteration (s): 2.23 | learning rate: 7.481E-05 | global batch size: 512 | lm loss: 1.959117E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.114 | TFLOPs: 23.59 | +63: iteration 46630/ 73814 | consumed samples: 23874560 | consumed tokens: 48895098880 | elapsed time per iteration (s): 2.26 | learning rate: 7.478E-05 | global batch size: 512 | lm loss: 1.967376E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.457 | TFLOPs: 23.31 | +63: iteration 46640/ 73814 | consumed samples: 23879680 | consumed tokens: 48905584640 | elapsed time per iteration (s): 2.26 | learning rate: 7.474E-05 | global batch size: 512 | lm loss: 1.961949E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.466 | TFLOPs: 23.31 | +63: iteration 46650/ 73814 | consumed samples: 23884800 | consumed tokens: 48916070400 | elapsed time per iteration (s): 2.37 | learning rate: 7.471E-05 | global batch size: 512 | lm loss: 1.980569E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.011 | TFLOPs: 22.24 | +63: iteration 46660/ 73814 | consumed samples: 23889920 | consumed tokens: 48926556160 | elapsed time per iteration (s): 2.45 | learning rate: 7.467E-05 | global batch size: 512 | lm loss: 1.983125E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.313 | TFLOPs: 21.55 | +63: iteration 46670/ 73814 | consumed samples: 23895040 | consumed tokens: 48937041920 | elapsed time per iteration (s): 2.32 | learning rate: 7.463E-05 | global batch size: 512 | lm loss: 1.945358E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.660 | TFLOPs: 22.72 | +63: iteration 46680/ 73814 | consumed samples: 23900160 | consumed tokens: 48947527680 | elapsed time per iteration (s): 2.23 | learning rate: 7.460E-05 | global batch size: 512 | lm loss: 1.978409E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.003 | TFLOPs: 23.68 | +63: iteration 46690/ 73814 | consumed samples: 23905280 | consumed tokens: 48958013440 | elapsed time per iteration (s): 2.23 | learning rate: 7.456E-05 | global batch size: 512 | lm loss: 1.951341E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.500 | TFLOPs: 23.63 | +63: iteration 46700/ 73814 | consumed samples: 23910400 | consumed tokens: 48968499200 | elapsed time per iteration (s): 2.23 | learning rate: 7.453E-05 | global batch size: 512 | lm loss: 1.945219E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.494 | TFLOPs: 23.63 | +63: iteration 46710/ 73814 | consumed samples: 23915520 | consumed tokens: 48978984960 | elapsed time per iteration (s): 2.25 | learning rate: 7.449E-05 | global batch size: 512 | lm loss: 1.960468E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.762 | TFLOPs: 23.45 | +63: iteration 46720/ 73814 | consumed samples: 23920640 | consumed tokens: 48989470720 | elapsed time per iteration (s): 2.23 | learning rate: 7.446E-05 | global batch size: 512 | lm loss: 1.958144E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.805 | TFLOPs: 23.66 | +63: iteration 46730/ 73814 | consumed samples: 23925760 | consumed tokens: 48999956480 | elapsed time per iteration (s): 2.23 | learning rate: 7.442E-05 | global batch size: 512 | lm loss: 1.972588E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.409 | TFLOPs: 23.62 | +63: iteration 46740/ 73814 | consumed samples: 23930880 | consumed tokens: 49010442240 | elapsed time per iteration (s): 2.24 | learning rate: 7.439E-05 | global batch size: 512 | lm loss: 1.987187E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.707 | TFLOPs: 23.54 | +63: iteration 46750/ 73814 | consumed samples: 23936000 | consumed tokens: 49020928000 | elapsed time per iteration (s): 2.23 | learning rate: 7.435E-05 | global batch size: 512 | lm loss: 1.970794E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.139 | TFLOPs: 23.59 | +63: iteration 46760/ 73814 | consumed samples: 23941120 | consumed tokens: 49031413760 | elapsed time per iteration (s): 2.23 | learning rate: 7.431E-05 | global batch size: 512 | lm loss: 1.934551E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.100 | TFLOPs: 23.58 | +63: iteration 46770/ 73814 | consumed samples: 23946240 | consumed tokens: 49041899520 | elapsed time per iteration (s): 2.24 | learning rate: 7.428E-05 | global batch size: 512 | lm loss: 1.961973E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.165 | TFLOPs: 23.49 | +63: iteration 46780/ 73814 | consumed samples: 23951360 | consumed tokens: 49052385280 | elapsed time per iteration (s): 2.23 | learning rate: 7.424E-05 | global batch size: 512 | lm loss: 1.967987E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.446 | TFLOPs: 23.62 | +63: iteration 46790/ 73814 | consumed samples: 23956480 | consumed tokens: 49062871040 | elapsed time per iteration (s): 2.24 | learning rate: 7.421E-05 | global batch size: 512 | lm loss: 1.966764E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.581 | TFLOPs: 23.53 | +63: iteration 46800/ 73814 | consumed samples: 23961600 | consumed tokens: 49073356800 | elapsed time per iteration (s): 2.24 | learning rate: 7.417E-05 | global batch size: 512 | lm loss: 1.983004E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.693 | TFLOPs: 23.54 | +63: iteration 46810/ 73814 | consumed samples: 23966720 | consumed tokens: 49083842560 | elapsed time per iteration (s): 2.23 | learning rate: 7.414E-05 | global batch size: 512 | lm loss: 1.946884E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.917 | TFLOPs: 23.67 | +63: iteration 46820/ 73814 | consumed samples: 23971840 | consumed tokens: 49094328320 | elapsed time per iteration (s): 2.24 | learning rate: 7.410E-05 | global batch size: 512 | lm loss: 1.947371E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.586 | TFLOPs: 23.53 | +63: iteration 46830/ 73814 | consumed samples: 23976960 | consumed tokens: 49104814080 | elapsed time per iteration (s): 2.23 | learning rate: 7.407E-05 | global batch size: 512 | lm loss: 1.955598E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.670 | TFLOPs: 23.64 | +63: iteration 46840/ 73814 | consumed samples: 23982080 | consumed tokens: 49115299840 | elapsed time per iteration (s): 2.44 | learning rate: 7.403E-05 | global batch size: 512 | lm loss: 1.957585E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.958 | TFLOPs: 21.61 | +63: iteration 46850/ 73814 | consumed samples: 23987200 | consumed tokens: 49125785600 | elapsed time per iteration (s): 2.26 | learning rate: 7.399E-05 | global batch size: 512 | lm loss: 1.986196E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.453 | TFLOPs: 23.31 | +63: iteration 46860/ 73814 | consumed samples: 23992320 | consumed tokens: 49136271360 | elapsed time per iteration (s): 2.23 | learning rate: 7.396E-05 | global batch size: 512 | lm loss: 1.966543E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.001 | TFLOPs: 23.68 | +63: iteration 46870/ 73814 | consumed samples: 23997440 | consumed tokens: 49146757120 | elapsed time per iteration (s): 2.24 | learning rate: 7.392E-05 | global batch size: 512 | lm loss: 1.968383E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.742 | TFLOPs: 23.55 | +63: iteration 46880/ 73814 | consumed samples: 24002560 | consumed tokens: 49157242880 | elapsed time per iteration (s): 2.33 | learning rate: 7.389E-05 | global batch size: 512 | lm loss: 1.959254E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.459 | TFLOPs: 22.59 | +63: iteration 46890/ 73814 | consumed samples: 24007680 | consumed tokens: 49167728640 | elapsed time per iteration (s): 2.25 | learning rate: 7.385E-05 | global batch size: 512 | lm loss: 1.973000E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.858 | TFLOPs: 23.46 | +63: iteration 46900/ 73814 | consumed samples: 24012800 | consumed tokens: 49178214400 | elapsed time per iteration (s): 2.24 | learning rate: 7.382E-05 | global batch size: 512 | lm loss: 1.961929E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.879 | TFLOPs: 23.56 | +63: iteration 46910/ 73814 | consumed samples: 24017920 | consumed tokens: 49188700160 | elapsed time per iteration (s): 2.27 | learning rate: 7.378E-05 | global batch size: 512 | lm loss: 1.947673E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.497 | TFLOPs: 23.21 | +63: iteration 46920/ 73814 | consumed samples: 24023040 | consumed tokens: 49199185920 | elapsed time per iteration (s): 2.34 | learning rate: 7.375E-05 | global batch size: 512 | lm loss: 1.959207E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.522 | TFLOPs: 22.50 | +63: iteration 46930/ 73814 | consumed samples: 24028160 | consumed tokens: 49209671680 | elapsed time per iteration (s): 2.23 | learning rate: 7.371E-05 | global batch size: 512 | lm loss: 2.006662E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.681 | TFLOPs: 23.64 | +63: iteration 46940/ 73814 | consumed samples: 24033280 | consumed tokens: 49220157440 | elapsed time per iteration (s): 2.22 | learning rate: 7.368E-05 | global batch size: 512 | lm loss: 1.959495E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.362 | TFLOPs: 23.71 | +63: iteration 46950/ 73814 | consumed samples: 24038400 | consumed tokens: 49230643200 | elapsed time per iteration (s): 2.23 | learning rate: 7.364E-05 | global batch size: 512 | lm loss: 1.966964E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.658 | TFLOPs: 23.64 | +63: iteration 46960/ 73814 | consumed samples: 24043520 | consumed tokens: 49241128960 | elapsed time per iteration (s): 2.27 | learning rate: 7.361E-05 | global batch size: 512 | lm loss: 1.945826E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.363 | TFLOPs: 23.20 | +63: iteration 46970/ 73814 | consumed samples: 24048640 | consumed tokens: 49251614720 | elapsed time per iteration (s): 2.24 | learning rate: 7.357E-05 | global batch size: 512 | lm loss: 1.966626E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.050 | TFLOPs: 23.58 | +63: iteration 46980/ 73814 | consumed samples: 24053760 | consumed tokens: 49262100480 | elapsed time per iteration (s): 2.22 | learning rate: 7.353E-05 | global batch size: 512 | lm loss: 1.973385E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.598 | TFLOPs: 23.74 | +63: iteration 46990/ 73814 | consumed samples: 24058880 | consumed tokens: 49272586240 | elapsed time per iteration (s): 2.24 | learning rate: 7.350E-05 | global batch size: 512 | lm loss: 1.979652E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.139 | TFLOPs: 23.49 | +63: iteration 47000/ 73814 | consumed samples: 24064000 | consumed tokens: 49283072000 | elapsed time per iteration (s): 2.27 | learning rate: 7.346E-05 | global batch size: 512 | lm loss: 1.954100E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.503 | TFLOPs: 23.21 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 47000 | lm loss value: 1.957408E+00 | lm loss PPL: 7.080951E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 47010/ 73814 | consumed samples: 24069120 | consumed tokens: 49293557760 | elapsed time per iteration (s): 2.29 | learning rate: 7.343E-05 | global batch size: 512 | lm loss: 1.961056E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.801 | TFLOPs: 23.04 | +63: iteration 47020/ 73814 | consumed samples: 24074240 | consumed tokens: 49304043520 | elapsed time per iteration (s): 2.25 | learning rate: 7.339E-05 | global batch size: 512 | lm loss: 1.941801E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.948 | TFLOPs: 23.47 | +63: iteration 47030/ 73814 | consumed samples: 24079360 | consumed tokens: 49314529280 | elapsed time per iteration (s): 2.25 | learning rate: 7.336E-05 | global batch size: 512 | lm loss: 1.935258E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.782 | TFLOPs: 23.45 | +63: iteration 47040/ 73814 | consumed samples: 24084480 | consumed tokens: 49325015040 | elapsed time per iteration (s): 2.33 | learning rate: 7.332E-05 | global batch size: 512 | lm loss: 1.938430E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.326 | TFLOPs: 22.58 | +63: iteration 47050/ 73814 | consumed samples: 24089600 | consumed tokens: 49335500800 | elapsed time per iteration (s): 2.44 | learning rate: 7.329E-05 | global batch size: 512 | lm loss: 1.977117E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.909 | TFLOPs: 21.61 | +63: iteration 47060/ 73814 | consumed samples: 24094720 | consumed tokens: 49345986560 | elapsed time per iteration (s): 2.23 | learning rate: 7.325E-05 | global batch size: 512 | lm loss: 1.975760E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.874 | TFLOPs: 23.66 | +63: iteration 47070/ 73814 | consumed samples: 24099840 | consumed tokens: 49356472320 | elapsed time per iteration (s): 2.23 | learning rate: 7.322E-05 | global batch size: 512 | lm loss: 1.977495E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.970 | TFLOPs: 23.67 | +63: iteration 47080/ 73814 | consumed samples: 24104960 | consumed tokens: 49366958080 | elapsed time per iteration (s): 2.25 | learning rate: 7.318E-05 | global batch size: 512 | lm loss: 1.968802E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.844 | TFLOPs: 23.46 | +63: iteration 47090/ 73814 | consumed samples: 24110080 | consumed tokens: 49377443840 | elapsed time per iteration (s): 2.32 | learning rate: 7.315E-05 | global batch size: 512 | lm loss: 1.955651E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.329 | TFLOPs: 22.68 | +63: iteration 47100/ 73814 | consumed samples: 24115200 | consumed tokens: 49387929600 | elapsed time per iteration (s): 2.27 | learning rate: 7.311E-05 | global batch size: 512 | lm loss: 1.967876E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.686 | TFLOPs: 23.23 | +63: iteration 47110/ 73814 | consumed samples: 24120320 | consumed tokens: 49398415360 | elapsed time per iteration (s): 2.26 | learning rate: 7.308E-05 | global batch size: 512 | lm loss: 1.966814E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.852 | TFLOPs: 23.35 | +63: iteration 47120/ 73814 | consumed samples: 24125440 | consumed tokens: 49408901120 | elapsed time per iteration (s): 2.34 | learning rate: 7.304E-05 | global batch size: 512 | lm loss: 1.983433E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.863 | TFLOPs: 22.53 | +63: iteration 47130/ 73814 | consumed samples: 24130560 | consumed tokens: 49419386880 | elapsed time per iteration (s): 2.29 | learning rate: 7.300E-05 | global batch size: 512 | lm loss: 1.959664E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.451 | TFLOPs: 23.00 | +63: iteration 47140/ 73814 | consumed samples: 24135680 | consumed tokens: 49429872640 | elapsed time per iteration (s): 2.37 | learning rate: 7.297E-05 | global batch size: 512 | lm loss: 1.966682E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.799 | TFLOPs: 22.22 | +63: iteration 47150/ 73814 | consumed samples: 24140800 | consumed tokens: 49440358400 | elapsed time per iteration (s): 2.23 | learning rate: 7.293E-05 | global batch size: 512 | lm loss: 1.953964E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.320 | TFLOPs: 23.61 | +63: iteration 47160/ 73814 | consumed samples: 24145920 | consumed tokens: 49450844160 | elapsed time per iteration (s): 2.23 | learning rate: 7.290E-05 | global batch size: 512 | lm loss: 1.944010E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.694 | TFLOPs: 23.65 | +63: iteration 47170/ 73814 | consumed samples: 24151040 | consumed tokens: 49461329920 | elapsed time per iteration (s): 2.49 | learning rate: 7.286E-05 | global batch size: 512 | lm loss: 1.965747E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.578 | TFLOPs: 21.16 | +63: iteration 47180/ 73814 | consumed samples: 24156160 | consumed tokens: 49471815680 | elapsed time per iteration (s): 2.24 | learning rate: 7.283E-05 | global batch size: 512 | lm loss: 1.966645E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.560 | TFLOPs: 23.53 | +63: iteration 47190/ 73814 | consumed samples: 24161280 | consumed tokens: 49482301440 | elapsed time per iteration (s): 2.23 | learning rate: 7.279E-05 | global batch size: 512 | lm loss: 1.940990E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.304 | TFLOPs: 23.61 | +63: iteration 47200/ 73814 | consumed samples: 24166400 | consumed tokens: 49492787200 | elapsed time per iteration (s): 2.23 | learning rate: 7.276E-05 | global batch size: 512 | lm loss: 1.946195E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.842 | TFLOPs: 23.66 | +63: iteration 47210/ 73814 | consumed samples: 24171520 | consumed tokens: 49503272960 | elapsed time per iteration (s): 2.23 | learning rate: 7.272E-05 | global batch size: 512 | lm loss: 1.966526E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.094 | TFLOPs: 23.69 | +63: iteration 47220/ 73814 | consumed samples: 24176640 | consumed tokens: 49513758720 | elapsed time per iteration (s): 2.23 | learning rate: 7.269E-05 | global batch size: 512 | lm loss: 1.963601E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.576 | TFLOPs: 23.63 | +63: iteration 47230/ 73814 | consumed samples: 24181760 | consumed tokens: 49524244480 | elapsed time per iteration (s): 2.23 | learning rate: 7.265E-05 | global batch size: 512 | lm loss: 1.958021E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.990 | TFLOPs: 23.68 | +63: iteration 47240/ 73814 | consumed samples: 24186880 | consumed tokens: 49534730240 | elapsed time per iteration (s): 2.22 | learning rate: 7.262E-05 | global batch size: 512 | lm loss: 1.967664E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.179 | TFLOPs: 23.70 | +63: iteration 47250/ 73814 | consumed samples: 24192000 | consumed tokens: 49545216000 | elapsed time per iteration (s): 2.24 | learning rate: 7.258E-05 | global batch size: 512 | lm loss: 1.977127E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.456 | TFLOPs: 23.52 | +63: iteration 47260/ 73814 | consumed samples: 24197120 | consumed tokens: 49555701760 | elapsed time per iteration (s): 2.24 | learning rate: 7.255E-05 | global batch size: 512 | lm loss: 1.950268E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.293 | TFLOPs: 23.50 | +63: iteration 47270/ 73814 | consumed samples: 24202240 | consumed tokens: 49566187520 | elapsed time per iteration (s): 2.24 | learning rate: 7.251E-05 | global batch size: 512 | lm loss: 1.950360E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.168 | TFLOPs: 23.49 | +63: iteration 47280/ 73814 | consumed samples: 24207360 | consumed tokens: 49576673280 | elapsed time per iteration (s): 2.38 | learning rate: 7.248E-05 | global batch size: 512 | lm loss: 1.960918E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.916 | TFLOPs: 22.12 | +63: iteration 47290/ 73814 | consumed samples: 24212480 | consumed tokens: 49587159040 | elapsed time per iteration (s): 2.30 | learning rate: 7.244E-05 | global batch size: 512 | lm loss: 1.973611E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.327 | TFLOPs: 22.89 | +63: iteration 47300/ 73814 | consumed samples: 24217600 | consumed tokens: 49597644800 | elapsed time per iteration (s): 2.25 | learning rate: 7.241E-05 | global batch size: 512 | lm loss: 1.956562E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.715 | TFLOPs: 23.44 | +63: iteration 47310/ 73814 | consumed samples: 24222720 | consumed tokens: 49608130560 | elapsed time per iteration (s): 2.24 | learning rate: 7.237E-05 | global batch size: 512 | lm loss: 1.945974E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.242 | TFLOPs: 23.50 | +63: iteration 47320/ 73814 | consumed samples: 24227840 | consumed tokens: 49618616320 | elapsed time per iteration (s): 2.24 | learning rate: 7.234E-05 | global batch size: 512 | lm loss: 1.973753E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.660 | TFLOPs: 23.54 | +63: iteration 47330/ 73814 | consumed samples: 24232960 | consumed tokens: 49629102080 | elapsed time per iteration (s): 2.23 | learning rate: 7.230E-05 | global batch size: 512 | lm loss: 1.984000E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.956 | TFLOPs: 23.67 | +63: iteration 47340/ 73814 | consumed samples: 24238080 | consumed tokens: 49639587840 | elapsed time per iteration (s): 2.23 | learning rate: 7.227E-05 | global batch size: 512 | lm loss: 1.967961E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.526 | TFLOPs: 23.63 | +63: iteration 47350/ 73814 | consumed samples: 24243200 | consumed tokens: 49650073600 | elapsed time per iteration (s): 2.33 | learning rate: 7.223E-05 | global batch size: 512 | lm loss: 1.977824E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.954 | TFLOPs: 22.64 | +63: iteration 47360/ 73814 | consumed samples: 24248320 | consumed tokens: 49660559360 | elapsed time per iteration (s): 2.23 | learning rate: 7.220E-05 | global batch size: 512 | lm loss: 1.963400E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.610 | TFLOPs: 23.64 | +63: iteration 47370/ 73814 | consumed samples: 24253440 | consumed tokens: 49671045120 | elapsed time per iteration (s): 2.26 | learning rate: 7.216E-05 | global batch size: 512 | lm loss: 1.968134E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.392 | TFLOPs: 23.31 | +63: iteration 47380/ 73814 | consumed samples: 24258560 | consumed tokens: 49681530880 | elapsed time per iteration (s): 2.42 | learning rate: 7.212E-05 | global batch size: 512 | lm loss: 1.962430E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.969 | TFLOPs: 21.82 | +63: iteration 47390/ 73814 | consumed samples: 24263680 | consumed tokens: 49692016640 | elapsed time per iteration (s): 2.35 | learning rate: 7.209E-05 | global batch size: 512 | lm loss: 1.961377E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.874 | TFLOPs: 22.43 | +63: iteration 47400/ 73814 | consumed samples: 24268800 | consumed tokens: 49702502400 | elapsed time per iteration (s): 2.23 | learning rate: 7.205E-05 | global batch size: 512 | lm loss: 1.969653E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.917 | TFLOPs: 23.67 | +63: iteration 47410/ 73814 | consumed samples: 24273920 | consumed tokens: 49712988160 | elapsed time per iteration (s): 2.25 | learning rate: 7.202E-05 | global batch size: 512 | lm loss: 1.987205E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.902 | TFLOPs: 23.46 | +63: iteration 47420/ 73814 | consumed samples: 24279040 | consumed tokens: 49723473920 | elapsed time per iteration (s): 2.29 | learning rate: 7.198E-05 | global batch size: 512 | lm loss: 1.975763E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.769 | TFLOPs: 23.04 | +63: iteration 47430/ 73814 | consumed samples: 24284160 | consumed tokens: 49733959680 | elapsed time per iteration (s): 2.26 | learning rate: 7.195E-05 | global batch size: 512 | lm loss: 1.962928E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.890 | TFLOPs: 23.36 | +63: iteration 47440/ 73814 | consumed samples: 24289280 | consumed tokens: 49744445440 | elapsed time per iteration (s): 2.33 | learning rate: 7.191E-05 | global batch size: 512 | lm loss: 1.978517E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.110 | TFLOPs: 22.66 | +63: iteration 47450/ 73814 | consumed samples: 24294400 | consumed tokens: 49754931200 | elapsed time per iteration (s): 2.44 | learning rate: 7.188E-05 | global batch size: 512 | lm loss: 1.989548E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.814 | TFLOPs: 21.60 | +63: iteration 47460/ 73814 | consumed samples: 24299520 | consumed tokens: 49765416960 | elapsed time per iteration (s): 2.33 | learning rate: 7.184E-05 | global batch size: 512 | lm loss: 1.956213E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.693 | TFLOPs: 22.62 | +63: iteration 47470/ 73814 | consumed samples: 24304640 | consumed tokens: 49775902720 | elapsed time per iteration (s): 2.62 | learning rate: 7.181E-05 | global batch size: 512 | lm loss: 1.972635E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 195.792 | TFLOPs: 20.16 | +63: iteration 47480/ 73814 | consumed samples: 24309760 | consumed tokens: 49786388480 | elapsed time per iteration (s): 2.49 | learning rate: 7.177E-05 | global batch size: 512 | lm loss: 1.966862E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.932 | TFLOPs: 21.20 | +63: iteration 47490/ 73814 | consumed samples: 24314880 | consumed tokens: 49796874240 | elapsed time per iteration (s): 2.67 | learning rate: 7.174E-05 | global batch size: 512 | lm loss: 1.944459E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 191.694 | TFLOPs: 19.73 | +63: iteration 47500/ 73814 | consumed samples: 24320000 | consumed tokens: 49807360000 | elapsed time per iteration (s): 2.42 | learning rate: 7.170E-05 | global batch size: 512 | lm loss: 1.969426E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.563 | TFLOPs: 21.78 | +63: iteration 47510/ 73814 | consumed samples: 24325120 | consumed tokens: 49817845760 | elapsed time per iteration (s): 2.49 | learning rate: 7.167E-05 | global batch size: 512 | lm loss: 1.945937E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.451 | TFLOPs: 21.15 | +63: iteration 47520/ 73814 | consumed samples: 24330240 | consumed tokens: 49828331520 | elapsed time per iteration (s): 2.39 | learning rate: 7.163E-05 | global batch size: 512 | lm loss: 1.979839E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.827 | TFLOPs: 22.01 | +63: iteration 47530/ 73814 | consumed samples: 24335360 | consumed tokens: 49838817280 | elapsed time per iteration (s): 2.43 | learning rate: 7.160E-05 | global batch size: 512 | lm loss: 1.948443E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.906 | TFLOPs: 21.71 | +63: iteration 47540/ 73814 | consumed samples: 24340480 | consumed tokens: 49849303040 | elapsed time per iteration (s): 2.32 | learning rate: 7.156E-05 | global batch size: 512 | lm loss: 1.954017E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.877 | TFLOPs: 22.74 | +63: iteration 47550/ 73814 | consumed samples: 24345600 | consumed tokens: 49859788800 | elapsed time per iteration (s): 2.35 | learning rate: 7.153E-05 | global batch size: 512 | lm loss: 1.952678E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.143 | TFLOPs: 22.46 | +63: iteration 47560/ 73814 | consumed samples: 24350720 | consumed tokens: 49870274560 | elapsed time per iteration (s): 2.24 | learning rate: 7.149E-05 | global batch size: 512 | lm loss: 1.958405E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.744 | TFLOPs: 23.55 | +63: iteration 47570/ 73814 | consumed samples: 24355840 | consumed tokens: 49880760320 | elapsed time per iteration (s): 2.25 | learning rate: 7.146E-05 | global batch size: 512 | lm loss: 1.982360E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.908 | TFLOPs: 23.46 | +63: iteration 47580/ 73814 | consumed samples: 24360960 | consumed tokens: 49891246080 | elapsed time per iteration (s): 2.32 | learning rate: 7.142E-05 | global batch size: 512 | lm loss: 1.951089E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.057 | TFLOPs: 22.76 | +63: iteration 47590/ 73814 | consumed samples: 24366080 | consumed tokens: 49901731840 | elapsed time per iteration (s): 2.26 | learning rate: 7.139E-05 | global batch size: 512 | lm loss: 1.969259E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.519 | TFLOPs: 23.32 | +63: iteration 47600/ 73814 | consumed samples: 24371200 | consumed tokens: 49912217600 | elapsed time per iteration (s): 2.24 | learning rate: 7.135E-05 | global batch size: 512 | lm loss: 1.965830E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.499 | TFLOPs: 23.52 | +63: iteration 47610/ 73814 | consumed samples: 24376320 | consumed tokens: 49922703360 | elapsed time per iteration (s): 2.33 | learning rate: 7.132E-05 | global batch size: 512 | lm loss: 1.957062E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.482 | TFLOPs: 22.59 | +63: iteration 47620/ 73814 | consumed samples: 24381440 | consumed tokens: 49933189120 | elapsed time per iteration (s): 2.23 | learning rate: 7.128E-05 | global batch size: 512 | lm loss: 1.969109E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.680 | TFLOPs: 23.64 | +63: iteration 47630/ 73814 | consumed samples: 24386560 | consumed tokens: 49943674880 | elapsed time per iteration (s): 2.24 | learning rate: 7.125E-05 | global batch size: 512 | lm loss: 1.974941E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.648 | TFLOPs: 23.54 | +63: iteration 47640/ 73814 | consumed samples: 24391680 | consumed tokens: 49954160640 | elapsed time per iteration (s): 2.49 | learning rate: 7.121E-05 | global batch size: 512 | lm loss: 1.936556E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.425 | TFLOPs: 21.15 | +63: iteration 47650/ 73814 | consumed samples: 24396800 | consumed tokens: 49964646400 | elapsed time per iteration (s): 2.33 | learning rate: 7.118E-05 | global batch size: 512 | lm loss: 1.943332E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.583 | TFLOPs: 22.60 | +63: iteration 47660/ 73814 | consumed samples: 24401920 | consumed tokens: 49975132160 | elapsed time per iteration (s): 2.25 | learning rate: 7.114E-05 | global batch size: 512 | lm loss: 1.965779E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.520 | TFLOPs: 23.42 | +63: iteration 47670/ 73814 | consumed samples: 24407040 | consumed tokens: 49985617920 | elapsed time per iteration (s): 2.36 | learning rate: 7.111E-05 | global batch size: 512 | lm loss: 1.954364E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.330 | TFLOPs: 22.37 | +63: iteration 47680/ 73814 | consumed samples: 24412160 | consumed tokens: 49996103680 | elapsed time per iteration (s): 2.23 | learning rate: 7.108E-05 | global batch size: 512 | lm loss: 1.976370E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.982 | TFLOPs: 23.68 | +63: iteration 47690/ 73814 | consumed samples: 24417280 | consumed tokens: 50006589440 | elapsed time per iteration (s): 2.32 | learning rate: 7.104E-05 | global batch size: 512 | lm loss: 1.954343E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.042 | TFLOPs: 22.76 | +63: iteration 47700/ 73814 | consumed samples: 24422400 | consumed tokens: 50017075200 | elapsed time per iteration (s): 2.23 | learning rate: 7.101E-05 | global batch size: 512 | lm loss: 1.949831E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.999 | TFLOPs: 23.68 | +63: iteration 47710/ 73814 | consumed samples: 24427520 | consumed tokens: 50027560960 | elapsed time per iteration (s): 2.23 | learning rate: 7.097E-05 | global batch size: 512 | lm loss: 1.960244E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.887 | TFLOPs: 23.67 | +63: iteration 47720/ 73814 | consumed samples: 24432640 | consumed tokens: 50038046720 | elapsed time per iteration (s): 2.29 | learning rate: 7.094E-05 | global batch size: 512 | lm loss: 1.968706E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.583 | TFLOPs: 23.02 | +63: iteration 47730/ 73814 | consumed samples: 24437760 | consumed tokens: 50048532480 | elapsed time per iteration (s): 2.39 | learning rate: 7.090E-05 | global batch size: 512 | lm loss: 1.961817E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.840 | TFLOPs: 22.01 | +63: iteration 47740/ 73814 | consumed samples: 24442880 | consumed tokens: 50059018240 | elapsed time per iteration (s): 2.35 | learning rate: 7.087E-05 | global batch size: 512 | lm loss: 1.967659E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.441 | TFLOPs: 22.38 | +63: iteration 47750/ 73814 | consumed samples: 24448000 | consumed tokens: 50069504000 | elapsed time per iteration (s): 2.25 | learning rate: 7.083E-05 | global batch size: 512 | lm loss: 1.965190E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.220 | TFLOPs: 23.39 | +63: iteration 47760/ 73814 | consumed samples: 24453120 | consumed tokens: 50079989760 | elapsed time per iteration (s): 2.25 | learning rate: 7.080E-05 | global batch size: 512 | lm loss: 1.968692E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.127 | TFLOPs: 23.38 | +63: iteration 47770/ 73814 | consumed samples: 24458240 | consumed tokens: 50090475520 | elapsed time per iteration (s): 2.27 | learning rate: 7.076E-05 | global batch size: 512 | lm loss: 1.940418E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.432 | TFLOPs: 23.21 | +63: iteration 47780/ 73814 | consumed samples: 24463360 | consumed tokens: 50100961280 | elapsed time per iteration (s): 2.23 | learning rate: 7.073E-05 | global batch size: 512 | lm loss: 1.941598E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.686 | TFLOPs: 23.65 | +63: iteration 47790/ 73814 | consumed samples: 24468480 | consumed tokens: 50111447040 | elapsed time per iteration (s): 2.31 | learning rate: 7.069E-05 | global batch size: 512 | lm loss: 1.959661E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.470 | TFLOPs: 22.80 | +63: iteration 47800/ 73814 | consumed samples: 24473600 | consumed tokens: 50121932800 | elapsed time per iteration (s): 2.32 | learning rate: 7.066E-05 | global batch size: 512 | lm loss: 1.950933E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.415 | TFLOPs: 22.69 | +63: iteration 47810/ 73814 | consumed samples: 24478720 | consumed tokens: 50132418560 | elapsed time per iteration (s): 2.25 | learning rate: 7.062E-05 | global batch size: 512 | lm loss: 1.957614E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.055 | TFLOPs: 23.48 | +63: iteration 47820/ 73814 | consumed samples: 24483840 | consumed tokens: 50142904320 | elapsed time per iteration (s): 2.24 | learning rate: 7.059E-05 | global batch size: 512 | lm loss: 1.958469E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.710 | TFLOPs: 23.54 | +63: iteration 47830/ 73814 | consumed samples: 24488960 | consumed tokens: 50153390080 | elapsed time per iteration (s): 2.25 | learning rate: 7.055E-05 | global batch size: 512 | lm loss: 1.948518E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.247 | TFLOPs: 23.39 | +63: iteration 47840/ 73814 | consumed samples: 24494080 | consumed tokens: 50163875840 | elapsed time per iteration (s): 2.24 | learning rate: 7.052E-05 | global batch size: 512 | lm loss: 1.933022E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.041 | TFLOPs: 23.58 | +63: iteration 47850/ 73814 | consumed samples: 24499200 | consumed tokens: 50174361600 | elapsed time per iteration (s): 2.24 | learning rate: 7.048E-05 | global batch size: 512 | lm loss: 1.971141E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.738 | TFLOPs: 23.55 | +63: iteration 47860/ 73814 | consumed samples: 24504320 | consumed tokens: 50184847360 | elapsed time per iteration (s): 2.26 | learning rate: 7.045E-05 | global batch size: 512 | lm loss: 1.958053E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.019 | TFLOPs: 23.37 | +63: iteration 47870/ 73814 | consumed samples: 24509440 | consumed tokens: 50195333120 | elapsed time per iteration (s): 2.37 | learning rate: 7.041E-05 | global batch size: 512 | lm loss: 1.976428E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.159 | TFLOPs: 22.25 | +63: iteration 47880/ 73814 | consumed samples: 24514560 | consumed tokens: 50205818880 | elapsed time per iteration (s): 2.23 | learning rate: 7.038E-05 | global batch size: 512 | lm loss: 1.954941E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.834 | TFLOPs: 23.66 | +63: iteration 47890/ 73814 | consumed samples: 24519680 | consumed tokens: 50216304640 | elapsed time per iteration (s): 2.23 | learning rate: 7.034E-05 | global batch size: 512 | lm loss: 1.941641E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.761 | TFLOPs: 23.65 | +63: iteration 47900/ 73814 | consumed samples: 24524800 | consumed tokens: 50226790400 | elapsed time per iteration (s): 2.23 | learning rate: 7.031E-05 | global batch size: 512 | lm loss: 1.966765E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.915 | TFLOPs: 23.67 | +63: iteration 47910/ 73814 | consumed samples: 24529920 | consumed tokens: 50237276160 | elapsed time per iteration (s): 2.23 | learning rate: 7.027E-05 | global batch size: 512 | lm loss: 1.977271E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.772 | TFLOPs: 23.65 | +63: iteration 47920/ 73814 | consumed samples: 24535040 | consumed tokens: 50247761920 | elapsed time per iteration (s): 2.24 | learning rate: 7.024E-05 | global batch size: 512 | lm loss: 1.959264E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.252 | TFLOPs: 23.50 | +63: iteration 47930/ 73814 | consumed samples: 24540160 | consumed tokens: 50258247680 | elapsed time per iteration (s): 2.22 | learning rate: 7.021E-05 | global batch size: 512 | lm loss: 1.971787E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.137 | TFLOPs: 23.69 | +63: iteration 47940/ 73814 | consumed samples: 24545280 | consumed tokens: 50268733440 | elapsed time per iteration (s): 2.34 | learning rate: 7.017E-05 | global batch size: 512 | lm loss: 1.944832E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.876 | TFLOPs: 22.53 | +63: iteration 47950/ 73814 | consumed samples: 24550400 | consumed tokens: 50279219200 | elapsed time per iteration (s): 2.33 | learning rate: 7.014E-05 | global batch size: 512 | lm loss: 1.937532E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.087 | TFLOPs: 22.66 | +63: iteration 47960/ 73814 | consumed samples: 24555520 | consumed tokens: 50289704960 | elapsed time per iteration (s): 2.31 | learning rate: 7.010E-05 | global batch size: 512 | lm loss: 1.966647E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.095 | TFLOPs: 22.86 | +63: iteration 47970/ 73814 | consumed samples: 24560640 | consumed tokens: 50300190720 | elapsed time per iteration (s): 2.30 | learning rate: 7.007E-05 | global batch size: 512 | lm loss: 1.968678E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.655 | TFLOPs: 22.92 | +63: iteration 47980/ 73814 | consumed samples: 24565760 | consumed tokens: 50310676480 | elapsed time per iteration (s): 2.22 | learning rate: 7.003E-05 | global batch size: 512 | lm loss: 1.960762E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.196 | TFLOPs: 23.70 | +63: iteration 47990/ 73814 | consumed samples: 24570880 | consumed tokens: 50321162240 | elapsed time per iteration (s): 2.31 | learning rate: 7.000E-05 | global batch size: 512 | lm loss: 1.943944E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.651 | TFLOPs: 22.82 | + 0: [2022-12-02 18:21:22,402] [INFO] [logging.py:68:log_dist] [Rank 0] step=48000, skipped=0, lr=[6.9962451142474e-05, 6.9962451142474e-05, 6.9962451142474e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 48000/ 73814 | consumed samples: 24576000 | consumed tokens: 50331648000 | elapsed time per iteration (s): 2.24 | learning rate: 6.996E-05 | global batch size: 512 | lm loss: 1.954528E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.125 | TFLOPs: 23.48 | + 0: steps: 48000 loss: 1.9361 iter time (s): 2.285 samples/sec: 224.119 +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 48000 | lm loss value: 1.888528E+00 | lm loss PPL: 6.609634E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 48010/ 73814 | consumed samples: 24581120 | consumed tokens: 50342133760 | elapsed time per iteration (s): 2.30 | learning rate: 6.993E-05 | global batch size: 512 | lm loss: 1.935874E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.755 | TFLOPs: 22.93 | +63: iteration 48020/ 73814 | consumed samples: 24586240 | consumed tokens: 50352619520 | elapsed time per iteration (s): 2.23 | learning rate: 6.989E-05 | global batch size: 512 | lm loss: 1.968486E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.342 | TFLOPs: 23.61 | +63: iteration 48030/ 73814 | consumed samples: 24591360 | consumed tokens: 50363105280 | elapsed time per iteration (s): 2.23 | learning rate: 6.986E-05 | global batch size: 512 | lm loss: 1.942318E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.421 | TFLOPs: 23.62 | +63: iteration 48040/ 73814 | consumed samples: 24596480 | consumed tokens: 50373591040 | elapsed time per iteration (s): 2.23 | learning rate: 6.982E-05 | global batch size: 512 | lm loss: 1.956396E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.375 | TFLOPs: 23.61 | +63: iteration 48050/ 73814 | consumed samples: 24601600 | consumed tokens: 50384076800 | elapsed time per iteration (s): 2.25 | learning rate: 6.979E-05 | global batch size: 512 | lm loss: 1.957452E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.680 | TFLOPs: 23.44 | +63: iteration 48060/ 73814 | consumed samples: 24606720 | consumed tokens: 50394562560 | elapsed time per iteration (s): 2.24 | learning rate: 6.975E-05 | global batch size: 512 | lm loss: 1.958224E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.489 | TFLOPs: 23.52 | +63: iteration 48070/ 73814 | consumed samples: 24611840 | consumed tokens: 50405048320 | elapsed time per iteration (s): 2.23 | learning rate: 6.972E-05 | global batch size: 512 | lm loss: 1.979499E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.824 | TFLOPs: 23.66 | +63: iteration 48080/ 73814 | consumed samples: 24616960 | consumed tokens: 50415534080 | elapsed time per iteration (s): 2.27 | learning rate: 6.969E-05 | global batch size: 512 | lm loss: 1.961723E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.119 | TFLOPs: 23.17 | +63: iteration 48090/ 73814 | consumed samples: 24622080 | consumed tokens: 50426019840 | elapsed time per iteration (s): 2.23 | learning rate: 6.965E-05 | global batch size: 512 | lm loss: 1.943548E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.936 | TFLOPs: 23.67 | +63: iteration 48100/ 73814 | consumed samples: 24627200 | consumed tokens: 50436505600 | elapsed time per iteration (s): 2.36 | learning rate: 6.962E-05 | global batch size: 512 | lm loss: 1.941014E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.656 | TFLOPs: 22.30 | +63: iteration 48110/ 73814 | consumed samples: 24632320 | consumed tokens: 50446991360 | elapsed time per iteration (s): 2.23 | learning rate: 6.958E-05 | global batch size: 512 | lm loss: 1.930322E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.115 | TFLOPs: 23.59 | +63: iteration 48120/ 73814 | consumed samples: 24637440 | consumed tokens: 50457477120 | elapsed time per iteration (s): 2.23 | learning rate: 6.955E-05 | global batch size: 512 | lm loss: 1.941616E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.106 | TFLOPs: 23.59 | +63: iteration 48130/ 73814 | consumed samples: 24642560 | consumed tokens: 50467962880 | elapsed time per iteration (s): 2.48 | learning rate: 6.951E-05 | global batch size: 512 | lm loss: 1.953774E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.793 | TFLOPs: 21.29 | +63: iteration 48140/ 73814 | consumed samples: 24647680 | consumed tokens: 50478448640 | elapsed time per iteration (s): 2.24 | learning rate: 6.948E-05 | global batch size: 512 | lm loss: 1.973396E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.042 | TFLOPs: 23.58 | +63: iteration 48150/ 73814 | consumed samples: 24652800 | consumed tokens: 50488934400 | elapsed time per iteration (s): 2.34 | learning rate: 6.944E-05 | global batch size: 512 | lm loss: 1.976811E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.182 | TFLOPs: 22.56 | +63: iteration 48160/ 73814 | consumed samples: 24657920 | consumed tokens: 50499420160 | elapsed time per iteration (s): 2.23 | learning rate: 6.941E-05 | global batch size: 512 | lm loss: 1.954885E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.791 | TFLOPs: 23.66 | +63: iteration 48170/ 73814 | consumed samples: 24663040 | consumed tokens: 50509905920 | elapsed time per iteration (s): 2.34 | learning rate: 6.937E-05 | global batch size: 512 | lm loss: 1.957148E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.025 | TFLOPs: 22.55 | +63: iteration 48180/ 73814 | consumed samples: 24668160 | consumed tokens: 50520391680 | elapsed time per iteration (s): 2.23 | learning rate: 6.934E-05 | global batch size: 512 | lm loss: 1.955108E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.687 | TFLOPs: 23.65 | +63: iteration 48190/ 73814 | consumed samples: 24673280 | consumed tokens: 50530877440 | elapsed time per iteration (s): 2.26 | learning rate: 6.931E-05 | global batch size: 512 | lm loss: 1.965972E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.770 | TFLOPs: 23.34 | +63: iteration 48200/ 73814 | consumed samples: 24678400 | consumed tokens: 50541363200 | elapsed time per iteration (s): 2.30 | learning rate: 6.927E-05 | global batch size: 512 | lm loss: 1.951140E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.299 | TFLOPs: 22.88 | +63: iteration 48210/ 73814 | consumed samples: 24683520 | consumed tokens: 50551848960 | elapsed time per iteration (s): 2.23 | learning rate: 6.924E-05 | global batch size: 512 | lm loss: 1.966388E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.374 | TFLOPs: 23.61 | +63: iteration 48220/ 73814 | consumed samples: 24688640 | consumed tokens: 50562334720 | elapsed time per iteration (s): 2.24 | learning rate: 6.920E-05 | global batch size: 512 | lm loss: 1.958367E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.555 | TFLOPs: 23.53 | +63: iteration 48230/ 73814 | consumed samples: 24693760 | consumed tokens: 50572820480 | elapsed time per iteration (s): 2.24 | learning rate: 6.917E-05 | global batch size: 512 | lm loss: 1.944810E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.399 | TFLOPs: 23.51 | +63: iteration 48240/ 73814 | consumed samples: 24698880 | consumed tokens: 50583306240 | elapsed time per iteration (s): 2.24 | learning rate: 6.913E-05 | global batch size: 512 | lm loss: 1.966807E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.253 | TFLOPs: 23.50 | +63: iteration 48250/ 73814 | consumed samples: 24704000 | consumed tokens: 50593792000 | elapsed time per iteration (s): 2.23 | learning rate: 6.910E-05 | global batch size: 512 | lm loss: 1.953869E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.638 | TFLOPs: 23.64 | +63: iteration 48260/ 73814 | consumed samples: 24709120 | consumed tokens: 50604277760 | elapsed time per iteration (s): 2.37 | learning rate: 6.906E-05 | global batch size: 512 | lm loss: 1.962994E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.223 | TFLOPs: 22.26 | +63: iteration 48270/ 73814 | consumed samples: 24714240 | consumed tokens: 50614763520 | elapsed time per iteration (s): 2.23 | learning rate: 6.903E-05 | global batch size: 512 | lm loss: 1.953262E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.039 | TFLOPs: 23.68 | +63: iteration 48280/ 73814 | consumed samples: 24719360 | consumed tokens: 50625249280 | elapsed time per iteration (s): 2.22 | learning rate: 6.900E-05 | global batch size: 512 | lm loss: 1.950412E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.164 | TFLOPs: 23.69 | +63: iteration 48290/ 73814 | consumed samples: 24724480 | consumed tokens: 50635735040 | elapsed time per iteration (s): 2.31 | learning rate: 6.896E-05 | global batch size: 512 | lm loss: 1.937617E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.500 | TFLOPs: 22.80 | +63: iteration 48300/ 73814 | consumed samples: 24729600 | consumed tokens: 50646220800 | elapsed time per iteration (s): 2.23 | learning rate: 6.893E-05 | global batch size: 512 | lm loss: 1.915980E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.737 | TFLOPs: 23.65 | +63: iteration 48310/ 73814 | consumed samples: 24734720 | consumed tokens: 50656706560 | elapsed time per iteration (s): 2.25 | learning rate: 6.889E-05 | global batch size: 512 | lm loss: 1.948409E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.783 | TFLOPs: 23.45 | +63: iteration 48320/ 73814 | consumed samples: 24739840 | consumed tokens: 50667192320 | elapsed time per iteration (s): 2.24 | learning rate: 6.886E-05 | global batch size: 512 | lm loss: 1.953573E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.040 | TFLOPs: 23.58 | +63: iteration 48330/ 73814 | consumed samples: 24744960 | consumed tokens: 50677678080 | elapsed time per iteration (s): 2.24 | learning rate: 6.882E-05 | global batch size: 512 | lm loss: 1.950052E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.214 | TFLOPs: 23.49 | +63: iteration 48340/ 73814 | consumed samples: 24750080 | consumed tokens: 50688163840 | elapsed time per iteration (s): 2.35 | learning rate: 6.879E-05 | global batch size: 512 | lm loss: 1.949208E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.990 | TFLOPs: 22.44 | +63: iteration 48350/ 73814 | consumed samples: 24755200 | consumed tokens: 50698649600 | elapsed time per iteration (s): 2.23 | learning rate: 6.875E-05 | global batch size: 512 | lm loss: 1.980577E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.749 | TFLOPs: 23.65 | +63: iteration 48360/ 73814 | consumed samples: 24760320 | consumed tokens: 50709135360 | elapsed time per iteration (s): 2.34 | learning rate: 6.872E-05 | global batch size: 512 | lm loss: 1.955019E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.652 | TFLOPs: 22.51 | +63: iteration 48370/ 73814 | consumed samples: 24765440 | consumed tokens: 50719621120 | elapsed time per iteration (s): 2.45 | learning rate: 6.869E-05 | global batch size: 512 | lm loss: 1.945121E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.659 | TFLOPs: 21.48 | +63: iteration 48380/ 73814 | consumed samples: 24770560 | consumed tokens: 50730106880 | elapsed time per iteration (s): 2.24 | learning rate: 6.865E-05 | global batch size: 512 | lm loss: 1.955329E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.930 | TFLOPs: 23.57 | +63: iteration 48390/ 73814 | consumed samples: 24775680 | consumed tokens: 50740592640 | elapsed time per iteration (s): 2.23 | learning rate: 6.862E-05 | global batch size: 512 | lm loss: 1.958115E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.491 | TFLOPs: 23.63 | +63: iteration 48400/ 73814 | consumed samples: 24780800 | consumed tokens: 50751078400 | elapsed time per iteration (s): 2.23 | learning rate: 6.858E-05 | global batch size: 512 | lm loss: 1.966959E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.531 | TFLOPs: 23.63 | +63: iteration 48410/ 73814 | consumed samples: 24785920 | consumed tokens: 50761564160 | elapsed time per iteration (s): 2.24 | learning rate: 6.855E-05 | global batch size: 512 | lm loss: 1.958341E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.424 | TFLOPs: 23.52 | +63: iteration 48420/ 73814 | consumed samples: 24791040 | consumed tokens: 50772049920 | elapsed time per iteration (s): 2.23 | learning rate: 6.851E-05 | global batch size: 512 | lm loss: 1.962183E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.920 | TFLOPs: 23.67 | +63: iteration 48430/ 73814 | consumed samples: 24796160 | consumed tokens: 50782535680 | elapsed time per iteration (s): 2.24 | learning rate: 6.848E-05 | global batch size: 512 | lm loss: 1.984153E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.519 | TFLOPs: 23.52 | +63: iteration 48440/ 73814 | consumed samples: 24801280 | consumed tokens: 50793021440 | elapsed time per iteration (s): 2.25 | learning rate: 6.845E-05 | global batch size: 512 | lm loss: 1.965783E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.081 | TFLOPs: 23.38 | +63: iteration 48450/ 73814 | consumed samples: 24806400 | consumed tokens: 50803507200 | elapsed time per iteration (s): 2.23 | learning rate: 6.841E-05 | global batch size: 512 | lm loss: 1.958632E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.421 | TFLOPs: 23.62 | +63: iteration 48460/ 73814 | consumed samples: 24811520 | consumed tokens: 50813992960 | elapsed time per iteration (s): 2.23 | learning rate: 6.838E-05 | global batch size: 512 | lm loss: 1.966475E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.841 | TFLOPs: 23.66 | +63: iteration 48470/ 73814 | consumed samples: 24816640 | consumed tokens: 50824478720 | elapsed time per iteration (s): 2.23 | learning rate: 6.834E-05 | global batch size: 512 | lm loss: 1.966718E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.462 | TFLOPs: 23.62 | +63: iteration 48480/ 73814 | consumed samples: 24821760 | consumed tokens: 50834964480 | elapsed time per iteration (s): 2.23 | learning rate: 6.831E-05 | global batch size: 512 | lm loss: 1.935558E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.420 | TFLOPs: 23.62 | +63: iteration 48490/ 73814 | consumed samples: 24826880 | consumed tokens: 50845450240 | elapsed time per iteration (s): 2.23 | learning rate: 6.827E-05 | global batch size: 512 | lm loss: 1.945626E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.788 | TFLOPs: 23.66 | +63: iteration 48500/ 73814 | consumed samples: 24832000 | consumed tokens: 50855936000 | elapsed time per iteration (s): 2.23 | learning rate: 6.824E-05 | global batch size: 512 | lm loss: 1.954486E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.286 | TFLOPs: 23.60 | +63: iteration 48510/ 73814 | consumed samples: 24837120 | consumed tokens: 50866421760 | elapsed time per iteration (s): 2.25 | learning rate: 6.820E-05 | global batch size: 512 | lm loss: 1.938660E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.737 | TFLOPs: 23.44 | +63: iteration 48520/ 73814 | consumed samples: 24842240 | consumed tokens: 50876907520 | elapsed time per iteration (s): 2.23 | learning rate: 6.817E-05 | global batch size: 512 | lm loss: 1.969479E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.790 | TFLOPs: 23.66 | +63: iteration 48530/ 73814 | consumed samples: 24847360 | consumed tokens: 50887393280 | elapsed time per iteration (s): 2.23 | learning rate: 6.814E-05 | global batch size: 512 | lm loss: 1.965120E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.545 | TFLOPs: 23.63 | +63: iteration 48540/ 73814 | consumed samples: 24852480 | consumed tokens: 50897879040 | elapsed time per iteration (s): 2.25 | learning rate: 6.810E-05 | global batch size: 512 | lm loss: 1.977808E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.996 | TFLOPs: 23.47 | +63: iteration 48550/ 73814 | consumed samples: 24857600 | consumed tokens: 50908364800 | elapsed time per iteration (s): 2.41 | learning rate: 6.807E-05 | global batch size: 512 | lm loss: 1.965259E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.553 | TFLOPs: 21.88 | +63: iteration 48560/ 73814 | consumed samples: 24862720 | consumed tokens: 50918850560 | elapsed time per iteration (s): 2.23 | learning rate: 6.803E-05 | global batch size: 512 | lm loss: 1.962830E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.841 | TFLOPs: 23.66 | +63: iteration 48570/ 73814 | consumed samples: 24867840 | consumed tokens: 50929336320 | elapsed time per iteration (s): 2.25 | learning rate: 6.800E-05 | global batch size: 512 | lm loss: 1.954698E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.732 | TFLOPs: 23.44 | +63: iteration 48580/ 73814 | consumed samples: 24872960 | consumed tokens: 50939822080 | elapsed time per iteration (s): 2.25 | learning rate: 6.797E-05 | global batch size: 512 | lm loss: 1.968624E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.730 | TFLOPs: 23.44 | +63: iteration 48590/ 73814 | consumed samples: 24878080 | consumed tokens: 50950307840 | elapsed time per iteration (s): 2.40 | learning rate: 6.793E-05 | global batch size: 512 | lm loss: 1.942031E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.973 | TFLOPs: 21.92 | +63: iteration 48600/ 73814 | consumed samples: 24883200 | consumed tokens: 50960793600 | elapsed time per iteration (s): 2.26 | learning rate: 6.790E-05 | global batch size: 512 | lm loss: 1.973194E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.587 | TFLOPs: 23.33 | +63: iteration 48610/ 73814 | consumed samples: 24888320 | consumed tokens: 50971279360 | elapsed time per iteration (s): 2.24 | learning rate: 6.786E-05 | global batch size: 512 | lm loss: 1.966182E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.924 | TFLOPs: 23.57 | +63: iteration 48620/ 73814 | consumed samples: 24893440 | consumed tokens: 50981765120 | elapsed time per iteration (s): 2.28 | learning rate: 6.783E-05 | global batch size: 512 | lm loss: 1.948187E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.927 | TFLOPs: 23.16 | +63: iteration 48630/ 73814 | consumed samples: 24898560 | consumed tokens: 50992250880 | elapsed time per iteration (s): 2.35 | learning rate: 6.779E-05 | global batch size: 512 | lm loss: 1.956170E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.112 | TFLOPs: 22.45 | +63: iteration 48640/ 73814 | consumed samples: 24903680 | consumed tokens: 51002736640 | elapsed time per iteration (s): 2.23 | learning rate: 6.776E-05 | global batch size: 512 | lm loss: 1.951036E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.537 | TFLOPs: 23.63 | +63: iteration 48650/ 73814 | consumed samples: 24908800 | consumed tokens: 51013222400 | elapsed time per iteration (s): 2.25 | learning rate: 6.773E-05 | global batch size: 512 | lm loss: 1.937051E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.061 | TFLOPs: 23.48 | +63: iteration 48660/ 73814 | consumed samples: 24913920 | consumed tokens: 51023708160 | elapsed time per iteration (s): 2.27 | learning rate: 6.769E-05 | global batch size: 512 | lm loss: 1.961806E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.675 | TFLOPs: 23.23 | +63: iteration 48670/ 73814 | consumed samples: 24919040 | consumed tokens: 51034193920 | elapsed time per iteration (s): 2.26 | learning rate: 6.766E-05 | global batch size: 512 | lm loss: 1.940119E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.428 | TFLOPs: 23.31 | +63: iteration 48680/ 73814 | consumed samples: 24924160 | consumed tokens: 51044679680 | elapsed time per iteration (s): 2.23 | learning rate: 6.762E-05 | global batch size: 512 | lm loss: 1.953480E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.111 | TFLOPs: 23.59 | +63: iteration 48690/ 73814 | consumed samples: 24929280 | consumed tokens: 51055165440 | elapsed time per iteration (s): 2.24 | learning rate: 6.759E-05 | global batch size: 512 | lm loss: 1.972955E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.184 | TFLOPs: 23.49 | +63: iteration 48700/ 73814 | consumed samples: 24934400 | consumed tokens: 51065651200 | elapsed time per iteration (s): 2.23 | learning rate: 6.756E-05 | global batch size: 512 | lm loss: 1.952719E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.048 | TFLOPs: 23.68 | +63: iteration 48710/ 73814 | consumed samples: 24939520 | consumed tokens: 51076136960 | elapsed time per iteration (s): 2.23 | learning rate: 6.752E-05 | global batch size: 512 | lm loss: 1.946523E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.681 | TFLOPs: 23.64 | +63: iteration 48720/ 73814 | consumed samples: 24944640 | consumed tokens: 51086622720 | elapsed time per iteration (s): 2.23 | learning rate: 6.749E-05 | global batch size: 512 | lm loss: 1.944510E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.538 | TFLOPs: 23.63 | +63: iteration 48730/ 73814 | consumed samples: 24949760 | consumed tokens: 51097108480 | elapsed time per iteration (s): 2.22 | learning rate: 6.745E-05 | global batch size: 512 | lm loss: 1.966828E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.247 | TFLOPs: 23.70 | +63: iteration 48740/ 73814 | consumed samples: 24954880 | consumed tokens: 51107594240 | elapsed time per iteration (s): 2.24 | learning rate: 6.742E-05 | global batch size: 512 | lm loss: 1.945320E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.764 | TFLOPs: 23.55 | +63: iteration 48750/ 73814 | consumed samples: 24960000 | consumed tokens: 51118080000 | elapsed time per iteration (s): 2.32 | learning rate: 6.738E-05 | global batch size: 512 | lm loss: 1.947427E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.824 | TFLOPs: 22.73 | +63: iteration 48760/ 73814 | consumed samples: 24965120 | consumed tokens: 51128565760 | elapsed time per iteration (s): 2.23 | learning rate: 6.735E-05 | global batch size: 512 | lm loss: 1.969706E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.981 | TFLOPs: 23.68 | +63: iteration 48770/ 73814 | consumed samples: 24970240 | consumed tokens: 51139051520 | elapsed time per iteration (s): 2.24 | learning rate: 6.732E-05 | global batch size: 512 | lm loss: 1.972228E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.080 | TFLOPs: 23.48 | +63: iteration 48780/ 73814 | consumed samples: 24975360 | consumed tokens: 51149537280 | elapsed time per iteration (s): 2.27 | learning rate: 6.728E-05 | global batch size: 512 | lm loss: 1.969475E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.565 | TFLOPs: 23.22 | +63: iteration 48790/ 73814 | consumed samples: 24980480 | consumed tokens: 51160023040 | elapsed time per iteration (s): 2.23 | learning rate: 6.725E-05 | global batch size: 512 | lm loss: 1.924971E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.055 | TFLOPs: 23.68 | +63: iteration 48800/ 73814 | consumed samples: 24985600 | consumed tokens: 51170508800 | elapsed time per iteration (s): 2.23 | learning rate: 6.721E-05 | global batch size: 512 | lm loss: 1.951062E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.374 | TFLOPs: 23.61 | +63: iteration 48810/ 73814 | consumed samples: 24990720 | consumed tokens: 51180994560 | elapsed time per iteration (s): 2.36 | learning rate: 6.718E-05 | global batch size: 512 | lm loss: 1.945697E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.649 | TFLOPs: 22.30 | +63: iteration 48820/ 73814 | consumed samples: 24995840 | consumed tokens: 51191480320 | elapsed time per iteration (s): 2.23 | learning rate: 6.715E-05 | global batch size: 512 | lm loss: 1.965313E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.255 | TFLOPs: 23.60 | +63: iteration 48830/ 73814 | consumed samples: 25000960 | consumed tokens: 51201966080 | elapsed time per iteration (s): 2.22 | learning rate: 6.711E-05 | global batch size: 512 | lm loss: 1.961379E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.428 | TFLOPs: 23.72 | +63: iteration 48840/ 73814 | consumed samples: 25006080 | consumed tokens: 51212451840 | elapsed time per iteration (s): 2.32 | learning rate: 6.708E-05 | global batch size: 512 | lm loss: 1.943211E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.315 | TFLOPs: 22.68 | +63: iteration 48850/ 73814 | consumed samples: 25011200 | consumed tokens: 51222937600 | elapsed time per iteration (s): 2.49 | learning rate: 6.704E-05 | global batch size: 512 | lm loss: 1.988516E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.496 | TFLOPs: 21.15 | +63: iteration 48860/ 73814 | consumed samples: 25016320 | consumed tokens: 51233423360 | elapsed time per iteration (s): 2.35 | learning rate: 6.701E-05 | global batch size: 512 | lm loss: 1.964470E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.911 | TFLOPs: 22.43 | +63: iteration 48870/ 73814 | consumed samples: 25021440 | consumed tokens: 51243909120 | elapsed time per iteration (s): 2.22 | learning rate: 6.698E-05 | global batch size: 512 | lm loss: 1.960323E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.126 | TFLOPs: 23.69 | +63: iteration 48880/ 73814 | consumed samples: 25026560 | consumed tokens: 51254394880 | elapsed time per iteration (s): 2.24 | learning rate: 6.694E-05 | global batch size: 512 | lm loss: 1.931211E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.149 | TFLOPs: 23.49 | +63: iteration 48890/ 73814 | consumed samples: 25031680 | consumed tokens: 51264880640 | elapsed time per iteration (s): 2.34 | learning rate: 6.691E-05 | global batch size: 512 | lm loss: 1.959567E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.558 | TFLOPs: 22.50 | +63: iteration 48900/ 73814 | consumed samples: 25036800 | consumed tokens: 51275366400 | elapsed time per iteration (s): 2.24 | learning rate: 6.687E-05 | global batch size: 512 | lm loss: 1.961463E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.701 | TFLOPs: 23.54 | +63: iteration 48910/ 73814 | consumed samples: 25041920 | consumed tokens: 51285852160 | elapsed time per iteration (s): 2.23 | learning rate: 6.684E-05 | global batch size: 512 | lm loss: 1.936595E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.327 | TFLOPs: 23.61 | +63: iteration 48920/ 73814 | consumed samples: 25047040 | consumed tokens: 51296337920 | elapsed time per iteration (s): 2.24 | learning rate: 6.681E-05 | global batch size: 512 | lm loss: 1.969533E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.078 | TFLOPs: 23.48 | +63: iteration 48930/ 73814 | consumed samples: 25052160 | consumed tokens: 51306823680 | elapsed time per iteration (s): 2.24 | learning rate: 6.677E-05 | global batch size: 512 | lm loss: 1.959133E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.428 | TFLOPs: 23.52 | +63: iteration 48940/ 73814 | consumed samples: 25057280 | consumed tokens: 51317309440 | elapsed time per iteration (s): 2.23 | learning rate: 6.674E-05 | global batch size: 512 | lm loss: 1.943089E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.905 | TFLOPs: 23.67 | +63: iteration 48950/ 73814 | consumed samples: 25062400 | consumed tokens: 51327795200 | elapsed time per iteration (s): 2.28 | learning rate: 6.670E-05 | global batch size: 512 | lm loss: 1.958163E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.975 | TFLOPs: 23.16 | +63: iteration 48960/ 73814 | consumed samples: 25067520 | consumed tokens: 51338280960 | elapsed time per iteration (s): 2.23 | learning rate: 6.667E-05 | global batch size: 512 | lm loss: 1.947391E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.412 | TFLOPs: 23.62 | +63: iteration 48970/ 73814 | consumed samples: 25072640 | consumed tokens: 51348766720 | elapsed time per iteration (s): 2.23 | learning rate: 6.664E-05 | global batch size: 512 | lm loss: 1.955581E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.891 | TFLOPs: 23.67 | +63: iteration 48980/ 73814 | consumed samples: 25077760 | consumed tokens: 51359252480 | elapsed time per iteration (s): 2.23 | learning rate: 6.660E-05 | global batch size: 512 | lm loss: 1.964932E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.396 | TFLOPs: 23.62 | +63: iteration 48990/ 73814 | consumed samples: 25082880 | consumed tokens: 51369738240 | elapsed time per iteration (s): 2.28 | learning rate: 6.657E-05 | global batch size: 512 | lm loss: 1.956939E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.466 | TFLOPs: 23.11 | +63: iteration 49000/ 73814 | consumed samples: 25088000 | consumed tokens: 51380224000 | elapsed time per iteration (s): 2.37 | learning rate: 6.654E-05 | global batch size: 512 | lm loss: 1.944380E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.187 | TFLOPs: 22.26 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 49000 | lm loss value: 1.835934E+00 | lm loss PPL: 6.270990E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 49010/ 73814 | consumed samples: 25093120 | consumed tokens: 51390709760 | elapsed time per iteration (s): 2.30 | learning rate: 6.650E-05 | global batch size: 512 | lm loss: 1.974759E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.025 | TFLOPs: 22.96 | +63: iteration 49020/ 73814 | consumed samples: 25098240 | consumed tokens: 51401195520 | elapsed time per iteration (s): 2.26 | learning rate: 6.647E-05 | global batch size: 512 | lm loss: 1.961069E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.956 | TFLOPs: 23.36 | +63: iteration 49030/ 73814 | consumed samples: 25103360 | consumed tokens: 51411681280 | elapsed time per iteration (s): 2.23 | learning rate: 6.643E-05 | global batch size: 512 | lm loss: 1.934097E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.795 | TFLOPs: 23.66 | +63: iteration 49040/ 73814 | consumed samples: 25108480 | consumed tokens: 51422167040 | elapsed time per iteration (s): 2.28 | learning rate: 6.640E-05 | global batch size: 512 | lm loss: 1.958404E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.785 | TFLOPs: 23.14 | +63: iteration 49050/ 73814 | consumed samples: 25113600 | consumed tokens: 51432652800 | elapsed time per iteration (s): 2.25 | learning rate: 6.637E-05 | global batch size: 512 | lm loss: 1.940865E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.287 | TFLOPs: 23.40 | +63: iteration 49060/ 73814 | consumed samples: 25118720 | consumed tokens: 51443138560 | elapsed time per iteration (s): 2.23 | learning rate: 6.633E-05 | global batch size: 512 | lm loss: 1.951355E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.900 | TFLOPs: 23.67 | +63: iteration 49070/ 73814 | consumed samples: 25123840 | consumed tokens: 51453624320 | elapsed time per iteration (s): 2.24 | learning rate: 6.630E-05 | global batch size: 512 | lm loss: 1.948106E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.606 | TFLOPs: 23.53 | +63: iteration 49080/ 73814 | consumed samples: 25128960 | consumed tokens: 51464110080 | elapsed time per iteration (s): 2.24 | learning rate: 6.626E-05 | global batch size: 512 | lm loss: 1.980524E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.668 | TFLOPs: 23.54 | +63: iteration 49090/ 73814 | consumed samples: 25134080 | consumed tokens: 51474595840 | elapsed time per iteration (s): 2.25 | learning rate: 6.623E-05 | global batch size: 512 | lm loss: 1.962589E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.904 | TFLOPs: 23.46 | +63: iteration 49100/ 73814 | consumed samples: 25139200 | consumed tokens: 51485081600 | elapsed time per iteration (s): 2.25 | learning rate: 6.620E-05 | global batch size: 512 | lm loss: 1.967711E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.411 | TFLOPs: 23.41 | +63: iteration 49110/ 73814 | consumed samples: 25144320 | consumed tokens: 51495567360 | elapsed time per iteration (s): 2.23 | learning rate: 6.616E-05 | global batch size: 512 | lm loss: 1.957789E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.947 | TFLOPs: 23.67 | +63: iteration 49120/ 73814 | consumed samples: 25149440 | consumed tokens: 51506053120 | elapsed time per iteration (s): 2.25 | learning rate: 6.613E-05 | global batch size: 512 | lm loss: 1.969854E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.756 | TFLOPs: 23.45 | +63: iteration 49130/ 73814 | consumed samples: 25154560 | consumed tokens: 51516538880 | elapsed time per iteration (s): 2.30 | learning rate: 6.610E-05 | global batch size: 512 | lm loss: 1.934698E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.811 | TFLOPs: 22.94 | +63: iteration 49140/ 73814 | consumed samples: 25159680 | consumed tokens: 51527024640 | elapsed time per iteration (s): 2.25 | learning rate: 6.606E-05 | global batch size: 512 | lm loss: 1.949015E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.426 | TFLOPs: 23.41 | +63: iteration 49150/ 73814 | consumed samples: 25164800 | consumed tokens: 51537510400 | elapsed time per iteration (s): 2.44 | learning rate: 6.603E-05 | global batch size: 512 | lm loss: 1.950550E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.880 | TFLOPs: 21.61 | +63: iteration 49160/ 73814 | consumed samples: 25169920 | consumed tokens: 51547996160 | elapsed time per iteration (s): 2.64 | learning rate: 6.599E-05 | global batch size: 512 | lm loss: 1.982256E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 194.001 | TFLOPs: 19.97 | +63: iteration 49170/ 73814 | consumed samples: 25175040 | consumed tokens: 51558481920 | elapsed time per iteration (s): 2.25 | learning rate: 6.596E-05 | global batch size: 512 | lm loss: 1.956081E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.603 | TFLOPs: 23.43 | +63: iteration 49180/ 73814 | consumed samples: 25180160 | consumed tokens: 51568967680 | elapsed time per iteration (s): 2.69 | learning rate: 6.593E-05 | global batch size: 512 | lm loss: 1.968729E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 190.146 | TFLOPs: 19.57 | +63: iteration 49190/ 73814 | consumed samples: 25185280 | consumed tokens: 51579453440 | elapsed time per iteration (s): 2.44 | learning rate: 6.589E-05 | global batch size: 512 | lm loss: 1.950823E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.234 | TFLOPs: 21.64 | +63: iteration 49200/ 73814 | consumed samples: 25190400 | consumed tokens: 51589939200 | elapsed time per iteration (s): 2.64 | learning rate: 6.586E-05 | global batch size: 512 | lm loss: 1.952620E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 193.977 | TFLOPs: 19.97 | +63: iteration 49210/ 73814 | consumed samples: 25195520 | consumed tokens: 51600424960 | elapsed time per iteration (s): 2.54 | learning rate: 6.583E-05 | global batch size: 512 | lm loss: 1.950392E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.859 | TFLOPs: 20.78 | +63: iteration 49220/ 73814 | consumed samples: 25200640 | consumed tokens: 51610910720 | elapsed time per iteration (s): 2.55 | learning rate: 6.579E-05 | global batch size: 512 | lm loss: 1.963324E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.872 | TFLOPs: 20.68 | +63: iteration 49230/ 73814 | consumed samples: 25205760 | consumed tokens: 51621396480 | elapsed time per iteration (s): 2.34 | learning rate: 6.576E-05 | global batch size: 512 | lm loss: 1.963351E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.056 | TFLOPs: 22.55 | +63: iteration 49240/ 73814 | consumed samples: 25210880 | consumed tokens: 51631882240 | elapsed time per iteration (s): 2.53 | learning rate: 6.572E-05 | global batch size: 512 | lm loss: 1.925338E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.445 | TFLOPs: 20.84 | +63: iteration 49250/ 73814 | consumed samples: 25216000 | consumed tokens: 51642368000 | elapsed time per iteration (s): 2.30 | learning rate: 6.569E-05 | global batch size: 512 | lm loss: 1.944141E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.091 | TFLOPs: 22.97 | +63: iteration 49260/ 73814 | consumed samples: 25221120 | consumed tokens: 51652853760 | elapsed time per iteration (s): 2.25 | learning rate: 6.566E-05 | global batch size: 512 | lm loss: 1.952865E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.831 | TFLOPs: 23.45 | +63: iteration 49270/ 73814 | consumed samples: 25226240 | consumed tokens: 51663339520 | elapsed time per iteration (s): 2.24 | learning rate: 6.562E-05 | global batch size: 512 | lm loss: 1.928149E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.701 | TFLOPs: 23.54 | +63: iteration 49280/ 73814 | consumed samples: 25231360 | consumed tokens: 51673825280 | elapsed time per iteration (s): 2.23 | learning rate: 6.559E-05 | global batch size: 512 | lm loss: 1.953885E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.718 | TFLOPs: 23.65 | +63: iteration 49290/ 73814 | consumed samples: 25236480 | consumed tokens: 51684311040 | elapsed time per iteration (s): 2.32 | learning rate: 6.556E-05 | global batch size: 512 | lm loss: 1.944004E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.140 | TFLOPs: 22.77 | +63: iteration 49300/ 73814 | consumed samples: 25241600 | consumed tokens: 51694796800 | elapsed time per iteration (s): 2.23 | learning rate: 6.552E-05 | global batch size: 512 | lm loss: 1.955210E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.712 | TFLOPs: 23.65 | +63: iteration 49310/ 73814 | consumed samples: 25246720 | consumed tokens: 51705282560 | elapsed time per iteration (s): 2.25 | learning rate: 6.549E-05 | global batch size: 512 | lm loss: 1.947039E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.756 | TFLOPs: 23.45 | +63: iteration 49320/ 73814 | consumed samples: 25251840 | consumed tokens: 51715768320 | elapsed time per iteration (s): 2.24 | learning rate: 6.546E-05 | global batch size: 512 | lm loss: 1.957070E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.376 | TFLOPs: 23.51 | +63: iteration 49330/ 73814 | consumed samples: 25256960 | consumed tokens: 51726254080 | elapsed time per iteration (s): 2.25 | learning rate: 6.542E-05 | global batch size: 512 | lm loss: 1.959294E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.855 | TFLOPs: 23.46 | +63: iteration 49340/ 73814 | consumed samples: 25262080 | consumed tokens: 51736739840 | elapsed time per iteration (s): 2.23 | learning rate: 6.539E-05 | global batch size: 512 | lm loss: 1.934629E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.044 | TFLOPs: 23.68 | +63: iteration 49350/ 73814 | consumed samples: 25267200 | consumed tokens: 51747225600 | elapsed time per iteration (s): 2.24 | learning rate: 6.535E-05 | global batch size: 512 | lm loss: 1.953354E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.366 | TFLOPs: 23.51 | +63: iteration 49360/ 73814 | consumed samples: 25272320 | consumed tokens: 51757711360 | elapsed time per iteration (s): 2.33 | learning rate: 6.532E-05 | global batch size: 512 | lm loss: 1.960144E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.571 | TFLOPs: 22.60 | +63: iteration 49370/ 73814 | consumed samples: 25277440 | consumed tokens: 51768197120 | elapsed time per iteration (s): 2.23 | learning rate: 6.529E-05 | global batch size: 512 | lm loss: 1.953747E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.896 | TFLOPs: 23.67 | +63: iteration 49380/ 73814 | consumed samples: 25282560 | consumed tokens: 51778682880 | elapsed time per iteration (s): 2.34 | learning rate: 6.525E-05 | global batch size: 512 | lm loss: 1.965400E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.731 | TFLOPs: 22.52 | +63: iteration 49390/ 73814 | consumed samples: 25287680 | consumed tokens: 51789168640 | elapsed time per iteration (s): 2.27 | learning rate: 6.522E-05 | global batch size: 512 | lm loss: 1.959908E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.906 | TFLOPs: 23.26 | +63: iteration 49400/ 73814 | consumed samples: 25292800 | consumed tokens: 51799654400 | elapsed time per iteration (s): 2.23 | learning rate: 6.519E-05 | global batch size: 512 | lm loss: 1.935572E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.955 | TFLOPs: 23.67 | +63: iteration 49410/ 73814 | consumed samples: 25297920 | consumed tokens: 51810140160 | elapsed time per iteration (s): 2.23 | learning rate: 6.515E-05 | global batch size: 512 | lm loss: 1.945088E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.947 | TFLOPs: 23.67 | +63: iteration 49420/ 73814 | consumed samples: 25303040 | consumed tokens: 51820625920 | elapsed time per iteration (s): 2.33 | learning rate: 6.512E-05 | global batch size: 512 | lm loss: 1.955636E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.039 | TFLOPs: 22.65 | +63: iteration 49430/ 73814 | consumed samples: 25308160 | consumed tokens: 51831111680 | elapsed time per iteration (s): 2.23 | learning rate: 6.509E-05 | global batch size: 512 | lm loss: 1.956428E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.757 | TFLOPs: 23.65 | +63: iteration 49440/ 73814 | consumed samples: 25313280 | consumed tokens: 51841597440 | elapsed time per iteration (s): 2.24 | learning rate: 6.505E-05 | global batch size: 512 | lm loss: 1.940869E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.939 | TFLOPs: 23.57 | +63: iteration 49450/ 73814 | consumed samples: 25318400 | consumed tokens: 51852083200 | elapsed time per iteration (s): 2.23 | learning rate: 6.502E-05 | global batch size: 512 | lm loss: 1.941559E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.782 | TFLOPs: 23.65 | +63: iteration 49460/ 73814 | consumed samples: 25323520 | consumed tokens: 51862568960 | elapsed time per iteration (s): 2.25 | learning rate: 6.499E-05 | global batch size: 512 | lm loss: 1.941674E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.450 | TFLOPs: 23.41 | +63: iteration 49470/ 73814 | consumed samples: 25328640 | consumed tokens: 51873054720 | elapsed time per iteration (s): 2.22 | learning rate: 6.495E-05 | global batch size: 512 | lm loss: 1.961176E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.125 | TFLOPs: 23.69 | +63: iteration 49480/ 73814 | consumed samples: 25333760 | consumed tokens: 51883540480 | elapsed time per iteration (s): 2.42 | learning rate: 6.492E-05 | global batch size: 512 | lm loss: 1.933228E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.803 | TFLOPs: 21.80 | +63: iteration 49490/ 73814 | consumed samples: 25338880 | consumed tokens: 51894026240 | elapsed time per iteration (s): 2.23 | learning rate: 6.488E-05 | global batch size: 512 | lm loss: 1.933177E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.837 | TFLOPs: 23.66 | +63: iteration 49500/ 73814 | consumed samples: 25344000 | consumed tokens: 51904512000 | elapsed time per iteration (s): 2.23 | learning rate: 6.485E-05 | global batch size: 512 | lm loss: 1.933675E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.347 | TFLOPs: 23.61 | +63: iteration 49510/ 73814 | consumed samples: 25349120 | consumed tokens: 51914997760 | elapsed time per iteration (s): 2.52 | learning rate: 6.482E-05 | global batch size: 512 | lm loss: 1.950216E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 203.316 | TFLOPs: 20.93 | +63: iteration 49520/ 73814 | consumed samples: 25354240 | consumed tokens: 51925483520 | elapsed time per iteration (s): 2.47 | learning rate: 6.478E-05 | global batch size: 512 | lm loss: 1.961837E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 207.636 | TFLOPs: 21.38 | +63: iteration 49530/ 73814 | consumed samples: 25359360 | consumed tokens: 51935969280 | elapsed time per iteration (s): 2.31 | learning rate: 6.475E-05 | global batch size: 512 | lm loss: 1.955917E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.298 | TFLOPs: 22.78 | +63: iteration 49540/ 73814 | consumed samples: 25364480 | consumed tokens: 51946455040 | elapsed time per iteration (s): 2.26 | learning rate: 6.472E-05 | global batch size: 512 | lm loss: 1.938119E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.788 | TFLOPs: 23.35 | +63: iteration 49550/ 73814 | consumed samples: 25369600 | consumed tokens: 51956940800 | elapsed time per iteration (s): 2.24 | learning rate: 6.468E-05 | global batch size: 512 | lm loss: 1.958427E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.836 | TFLOPs: 23.56 | +63: iteration 49560/ 73814 | consumed samples: 25374720 | consumed tokens: 51967426560 | elapsed time per iteration (s): 2.23 | learning rate: 6.465E-05 | global batch size: 512 | lm loss: 1.947264E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.080 | TFLOPs: 23.69 | +63: iteration 49570/ 73814 | consumed samples: 25379840 | consumed tokens: 51977912320 | elapsed time per iteration (s): 2.23 | learning rate: 6.462E-05 | global batch size: 512 | lm loss: 1.967049E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.990 | TFLOPs: 23.68 | +63: iteration 49580/ 73814 | consumed samples: 25384960 | consumed tokens: 51988398080 | elapsed time per iteration (s): 2.23 | learning rate: 6.458E-05 | global batch size: 512 | lm loss: 1.965187E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.159 | TFLOPs: 23.59 | +63: iteration 49590/ 73814 | consumed samples: 25390080 | consumed tokens: 51998883840 | elapsed time per iteration (s): 5.10 | learning rate: 6.455E-05 | global batch size: 512 | lm loss: 1.952682E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 100.463 | TFLOPs: 10.34 | +63: iteration 49600/ 73814 | consumed samples: 25395200 | consumed tokens: 52009369600 | elapsed time per iteration (s): 2.24 | learning rate: 6.452E-05 | global batch size: 512 | lm loss: 1.932024E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.998 | TFLOPs: 23.57 | +63: iteration 49610/ 73814 | consumed samples: 25400320 | consumed tokens: 52019855360 | elapsed time per iteration (s): 2.26 | learning rate: 6.448E-05 | global batch size: 512 | lm loss: 1.942927E+00 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.579 | TFLOPs: 23.33 | +63: iteration 49620/ 73814 | consumed samples: 25405440 | consumed tokens: 52030341120 | elapsed time per iteration (s): 2.23 | learning rate: 6.445E-05 | global batch size: 512 | lm loss: 1.957167E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.930 | TFLOPs: 23.67 | +63: iteration 49630/ 73814 | consumed samples: 25410560 | consumed tokens: 52040826880 | elapsed time per iteration (s): 3.18 | learning rate: 6.442E-05 | global batch size: 512 | lm loss: 1.950180E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 160.962 | TFLOPs: 16.57 | +63: iteration 49640/ 73814 | consumed samples: 25415680 | consumed tokens: 52051312640 | elapsed time per iteration (s): 2.32 | learning rate: 6.438E-05 | global batch size: 512 | lm loss: 1.950058E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.702 | TFLOPs: 22.72 | +63: iteration 49650/ 73814 | consumed samples: 25420800 | consumed tokens: 52061798400 | elapsed time per iteration (s): 2.29 | learning rate: 6.435E-05 | global batch size: 512 | lm loss: 1.943260E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.827 | TFLOPs: 23.04 | +63: iteration 49660/ 73814 | consumed samples: 25425920 | consumed tokens: 52072284160 | elapsed time per iteration (s): 2.25 | learning rate: 6.432E-05 | global batch size: 512 | lm loss: 1.967005E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.236 | TFLOPs: 23.39 | +63: iteration 49670/ 73814 | consumed samples: 25431040 | consumed tokens: 52082769920 | elapsed time per iteration (s): 2.24 | learning rate: 6.428E-05 | global batch size: 512 | lm loss: 1.931588E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.243 | TFLOPs: 23.50 | +63: iteration 49680/ 73814 | consumed samples: 25436160 | consumed tokens: 52093255680 | elapsed time per iteration (s): 2.23 | learning rate: 6.425E-05 | global batch size: 512 | lm loss: 1.954702E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.536 | TFLOPs: 23.63 | +63: iteration 49690/ 73814 | consumed samples: 25441280 | consumed tokens: 52103741440 | elapsed time per iteration (s): 2.26 | learning rate: 6.422E-05 | global batch size: 512 | lm loss: 1.964976E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.654 | TFLOPs: 23.33 | +63: iteration 49700/ 73814 | consumed samples: 25446400 | consumed tokens: 52114227200 | elapsed time per iteration (s): 2.34 | learning rate: 6.418E-05 | global batch size: 512 | lm loss: 1.945116E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.811 | TFLOPs: 22.53 | +63: iteration 49710/ 73814 | consumed samples: 25451520 | consumed tokens: 52124712960 | elapsed time per iteration (s): 2.22 | learning rate: 6.415E-05 | global batch size: 512 | lm loss: 1.933627E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.358 | TFLOPs: 23.71 | +63: iteration 49720/ 73814 | consumed samples: 25456640 | consumed tokens: 52135198720 | elapsed time per iteration (s): 2.22 | learning rate: 6.412E-05 | global batch size: 512 | lm loss: 1.936842E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.298 | TFLOPs: 23.71 | +63: iteration 49730/ 73814 | consumed samples: 25461760 | consumed tokens: 52145684480 | elapsed time per iteration (s): 2.23 | learning rate: 6.408E-05 | global batch size: 512 | lm loss: 1.939450E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.670 | TFLOPs: 23.64 | +63: iteration 49740/ 73814 | consumed samples: 25466880 | consumed tokens: 52156170240 | elapsed time per iteration (s): 2.23 | learning rate: 6.405E-05 | global batch size: 512 | lm loss: 1.950523E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.669 | TFLOPs: 23.64 | +63: iteration 49750/ 73814 | consumed samples: 25472000 | consumed tokens: 52166656000 | elapsed time per iteration (s): 2.26 | learning rate: 6.402E-05 | global batch size: 512 | lm loss: 1.945983E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.588 | TFLOPs: 23.33 | +63: iteration 49760/ 73814 | consumed samples: 25477120 | consumed tokens: 52177141760 | elapsed time per iteration (s): 2.23 | learning rate: 6.398E-05 | global batch size: 512 | lm loss: 1.946936E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.225 | TFLOPs: 23.60 | +63: iteration 49770/ 73814 | consumed samples: 25482240 | consumed tokens: 52187627520 | elapsed time per iteration (s): 2.24 | learning rate: 6.395E-05 | global batch size: 512 | lm loss: 1.940019E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.580 | TFLOPs: 23.53 | +63: iteration 49780/ 73814 | consumed samples: 25487360 | consumed tokens: 52198113280 | elapsed time per iteration (s): 2.42 | learning rate: 6.392E-05 | global batch size: 512 | lm loss: 1.927674E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.857 | TFLOPs: 21.81 | +63: iteration 49790/ 73814 | consumed samples: 25492480 | consumed tokens: 52208599040 | elapsed time per iteration (s): 2.23 | learning rate: 6.388E-05 | global batch size: 512 | lm loss: 1.941682E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.893 | TFLOPs: 23.67 | +63: iteration 49800/ 73814 | consumed samples: 25497600 | consumed tokens: 52219084800 | elapsed time per iteration (s): 2.32 | learning rate: 6.385E-05 | global batch size: 512 | lm loss: 1.946626E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.682 | TFLOPs: 22.72 | +63: iteration 49810/ 73814 | consumed samples: 25502720 | consumed tokens: 52229570560 | elapsed time per iteration (s): 2.24 | learning rate: 6.382E-05 | global batch size: 512 | lm loss: 1.933248E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.335 | TFLOPs: 23.51 | +63: iteration 49820/ 73814 | consumed samples: 25507840 | consumed tokens: 52240056320 | elapsed time per iteration (s): 2.24 | learning rate: 6.378E-05 | global batch size: 512 | lm loss: 1.941929E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.431 | TFLOPs: 23.52 | +63: iteration 49830/ 73814 | consumed samples: 25512960 | consumed tokens: 52250542080 | elapsed time per iteration (s): 2.47 | learning rate: 6.375E-05 | global batch size: 512 | lm loss: 1.948180E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 207.344 | TFLOPs: 21.35 | +63: iteration 49840/ 73814 | consumed samples: 25518080 | consumed tokens: 52261027840 | elapsed time per iteration (s): 2.32 | learning rate: 6.372E-05 | global batch size: 512 | lm loss: 1.963227E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.517 | TFLOPs: 22.70 | +63: iteration 49850/ 73814 | consumed samples: 25523200 | consumed tokens: 52271513600 | elapsed time per iteration (s): 2.24 | learning rate: 6.369E-05 | global batch size: 512 | lm loss: 1.948017E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.981 | TFLOPs: 23.57 | +63: iteration 49860/ 73814 | consumed samples: 25528320 | consumed tokens: 52281999360 | elapsed time per iteration (s): 2.25 | learning rate: 6.365E-05 | global batch size: 512 | lm loss: 1.955639E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.077 | TFLOPs: 23.38 | +63: iteration 49870/ 73814 | consumed samples: 25533440 | consumed tokens: 52292485120 | elapsed time per iteration (s): 2.25 | learning rate: 6.362E-05 | global batch size: 512 | lm loss: 1.951686E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.985 | TFLOPs: 23.47 | +63: iteration 49880/ 73814 | consumed samples: 25538560 | consumed tokens: 52302970880 | elapsed time per iteration (s): 2.25 | learning rate: 6.359E-05 | global batch size: 512 | lm loss: 1.939688E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.576 | TFLOPs: 23.43 | +63: iteration 49890/ 73814 | consumed samples: 25543680 | consumed tokens: 52313456640 | elapsed time per iteration (s): 2.23 | learning rate: 6.355E-05 | global batch size: 512 | lm loss: 1.938611E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.811 | TFLOPs: 23.66 | +63: iteration 49900/ 73814 | consumed samples: 25548800 | consumed tokens: 52323942400 | elapsed time per iteration (s): 2.31 | learning rate: 6.352E-05 | global batch size: 512 | lm loss: 1.970776E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.831 | TFLOPs: 22.84 | +63: iteration 49910/ 73814 | consumed samples: 25553920 | consumed tokens: 52334428160 | elapsed time per iteration (s): 2.48 | learning rate: 6.349E-05 | global batch size: 512 | lm loss: 1.930138E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.597 | TFLOPs: 21.27 | +63: iteration 49920/ 73814 | consumed samples: 25559040 | consumed tokens: 52344913920 | elapsed time per iteration (s): 2.24 | learning rate: 6.345E-05 | global batch size: 512 | lm loss: 1.912514E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.820 | TFLOPs: 23.56 | +63: iteration 49930/ 73814 | consumed samples: 25564160 | consumed tokens: 52355399680 | elapsed time per iteration (s): 2.24 | learning rate: 6.342E-05 | global batch size: 512 | lm loss: 1.952979E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.286 | TFLOPs: 23.50 | +63: iteration 49940/ 73814 | consumed samples: 25569280 | consumed tokens: 52365885440 | elapsed time per iteration (s): 2.23 | learning rate: 6.339E-05 | global batch size: 512 | lm loss: 1.953351E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.377 | TFLOPs: 23.61 | +63: iteration 49950/ 73814 | consumed samples: 25574400 | consumed tokens: 52376371200 | elapsed time per iteration (s): 2.45 | learning rate: 6.335E-05 | global batch size: 512 | lm loss: 1.942388E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.332 | TFLOPs: 21.55 | +63: iteration 49960/ 73814 | consumed samples: 25579520 | consumed tokens: 52386856960 | elapsed time per iteration (s): 2.23 | learning rate: 6.332E-05 | global batch size: 512 | lm loss: 1.946526E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.632 | TFLOPs: 23.64 | +63: iteration 49970/ 73814 | consumed samples: 25584640 | consumed tokens: 52397342720 | elapsed time per iteration (s): 2.24 | learning rate: 6.329E-05 | global batch size: 512 | lm loss: 1.960291E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.729 | TFLOPs: 23.55 | +63: iteration 49980/ 73814 | consumed samples: 25589760 | consumed tokens: 52407828480 | elapsed time per iteration (s): 2.30 | learning rate: 6.325E-05 | global batch size: 512 | lm loss: 1.961382E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.258 | TFLOPs: 22.88 | +63: iteration 49990/ 73814 | consumed samples: 25594880 | consumed tokens: 52418314240 | elapsed time per iteration (s): 2.26 | learning rate: 6.322E-05 | global batch size: 512 | lm loss: 1.956193E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.468 | TFLOPs: 23.31 | + 0: [2022-12-02 19:37:57,846] [INFO] [logging.py:68:log_dist] [Rank 0] step=50000, skipped=0, lr=[6.318846499042764e-05, 6.318846499042764e-05, 6.318846499042764e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] + 0: steps: 50000 loss: 1.9335 iter time (s): 2.295 samples/sec: 223.067 +63: iteration 50000/ 73814 | consumed samples: 25600000 | consumed tokens: 52428800000 | elapsed time per iteration (s): 2.24 | learning rate: 6.319E-05 | global batch size: 512 | lm loss: 1.947394E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.903 | TFLOPs: 23.56 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 50000 | lm loss value: 1.925097E+00 | lm loss PPL: 6.855813E+00 | +63: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 50000 to checkpoints_3b977boscar + 0: [2022-12-02 19:37:58,705] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step50000 is begin to save! + 0: [2022-12-02 19:37:58,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_01-model_00-model_states.pt... +32: [2022-12-02 19:37:58,751] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_21-model_00-model_states.pt... +32: [2022-12-02 19:37:59,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_21-model_00-model_states.pt. +32: [2022-12-02 19:37:59,122] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_22-model_00-model_states.pt... + 0: [2022-12-02 19:37:59,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_01-model_00-model_states.pt. + 0: [2022-12-02 19:37:59,145] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_03-model_00-model_states.pt... +32: [2022-12-02 19:37:59,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_22-model_00-model_states.pt. +32: [2022-12-02 19:37:59,344] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_23-model_00-model_states.pt... + 0: [2022-12-02 19:37:59,372] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_03-model_00-model_states.pt. + 0: [2022-12-02 19:37:59,373] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_04-model_00-model_states.pt... +32: [2022-12-02 19:37:59,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_23-model_00-model_states.pt. +32: [2022-12-02 19:37:59,568] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_24-model_00-model_states.pt... + 0: [2022-12-02 19:37:59,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_04-model_00-model_states.pt. + 0: [2022-12-02 19:37:59,604] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_05-model_00-model_states.pt... +32: [2022-12-02 19:37:59,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_24-model_00-model_states.pt. +32: [2022-12-02 19:37:59,794] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_25-model_00-model_states.pt... + 0: [2022-12-02 19:37:59,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_05-model_00-model_states.pt. + 0: [2022-12-02 19:37:59,832] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_06-model_00-model_states.pt... +32: [2022-12-02 19:38:00,016] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_25-model_00-model_states.pt. +32: [2022-12-02 19:38:00,017] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_26-model_00-model_states.pt... + 0: [2022-12-02 19:38:00,062] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_06-model_00-model_states.pt. + 0: [2022-12-02 19:38:00,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_07-model_00-model_states.pt... +32: [2022-12-02 19:38:00,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_26-model_00-model_states.pt. +32: [2022-12-02 19:38:00,238] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_27-model_00-model_states.pt... + 0: [2022-12-02 19:38:00,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_07-model_00-model_states.pt. + 0: [2022-12-02 19:38:00,291] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_08-model_00-model_states.pt... +32: [2022-12-02 19:38:00,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_27-model_00-model_states.pt. +32: [2022-12-02 19:38:00,461] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_28-model_00-model_states.pt... + 0: [2022-12-02 19:38:00,517] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_08-model_00-model_states.pt. + 0: [2022-12-02 19:38:00,518] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_09-model_00-model_states.pt... +32: [2022-12-02 19:38:00,681] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_28-model_00-model_states.pt. +32: [2022-12-02 19:38:00,682] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_29-model_00-model_states.pt... + 0: [2022-12-02 19:38:00,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_09-model_00-model_states.pt. + 0: [2022-12-02 19:38:00,743] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_10-model_00-model_states.pt... +32: [2022-12-02 19:38:00,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_29-model_00-model_states.pt. +32: [2022-12-02 19:38:00,911] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_30-model_00-model_states.pt... + 0: [2022-12-02 19:38:00,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_10-model_00-model_states.pt. + 0: [2022-12-02 19:38:00,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_11-model_00-model_states.pt... +32: [2022-12-02 19:38:01,130] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_30-model_00-model_states.pt. +32: [2022-12-02 19:38:01,131] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_31-model_00-model_states.pt... + 0: [2022-12-02 19:38:01,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_11-model_00-model_states.pt. + 0: [2022-12-02 19:38:01,201] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_12-model_00-model_states.pt... +32: [2022-12-02 19:38:01,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_31-model_00-model_states.pt. +32: [2022-12-02 19:38:01,351] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_32-model_00-model_states.pt... + 0: [2022-12-02 19:38:01,439] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_12-model_00-model_states.pt. + 0: [2022-12-02 19:38:01,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_13-model_00-model_states.pt... +32: [2022-12-02 19:38:01,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_32-model_00-model_states.pt. +32: [2022-12-02 19:38:01,571] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_33-model_00-model_states.pt... + 0: [2022-12-02 19:38:01,672] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_13-model_00-model_states.pt. + 0: [2022-12-02 19:38:01,672] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_14-model_00-model_states.pt... +32: [2022-12-02 19:38:01,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_33-model_00-model_states.pt. +32: [2022-12-02 19:38:01,789] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_34-model_00-model_states.pt... + 0: [2022-12-02 19:38:01,895] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 19:38:01,895] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_15-model_00-model_states.pt... +32: [2022-12-02 19:38:02,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_34-model_00-model_states.pt. +32: [2022-12-02 19:38:02,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_35-model_00-model_states.pt... + 0: [2022-12-02 19:38:02,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_15-model_00-model_states.pt. + 0: [2022-12-02 19:38:02,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_16-model_00-model_states.pt... +32: [2022-12-02 19:38:02,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_35-model_00-model_states.pt. +32: [2022-12-02 19:38:02,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_36-model_00-model_states.pt... + 0: [2022-12-02 19:38:02,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_16-model_00-model_states.pt. + 0: [2022-12-02 19:38:02,343] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_17-model_00-model_states.pt... +32: [2022-12-02 19:38:02,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_36-model_00-model_states.pt. +32: [2022-12-02 19:38:02,447] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_37-model_00-model_states.pt... + 0: [2022-12-02 19:38:02,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_17-model_00-model_states.pt. + 0: [2022-12-02 19:38:02,573] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_18-model_00-model_states.pt... +32: [2022-12-02 19:38:02,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_37-model_00-model_states.pt. +32: [2022-12-02 19:38:02,666] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_38-model_00-model_states.pt... + 0: [2022-12-02 19:38:02,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_18-model_00-model_states.pt. + 0: [2022-12-02 19:38:02,798] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_19-model_00-model_states.pt... +32: [2022-12-02 19:38:02,884] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_38-model_00-model_states.pt. +32: [2022-12-02 19:38:02,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_40-model_00-model_states.pt... +32: [2022-12-02 19:38:02,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_40-model_00-model_states.pt. +32: [2022-12-02 19:38:02,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/mp_rank_01_model_states.pt... +32: [2022-12-02 19:38:02,895] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/mp_rank_01_model_states.pt. + 0: [2022-12-02 19:38:03,023] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_19-model_00-model_states.pt. + 0: [2022-12-02 19:38:03,023] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/layer_20-model_00-model_states.pt... + 0: [2022-12-02 19:38:03,250] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/layer_20-model_00-model_states.pt. + 0: [2022-12-02 19:38:03,251] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_3b977boscar/global_step50000/mp_rank_00_model_states.pt + 0: [2022-12-02 19:38:03,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/mp_rank_00_model_states.pt... + 0: [2022-12-02 19:38:03,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/mp_rank_00_model_states.pt. +32: [2022-12-02 19:38:03,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt... +54: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt... +54: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt... +54: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt... +54: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt... +54: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt... +56: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt... +56: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt... +52: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt... +52: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt... +52: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt... +52: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt... +61: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt... +61: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt... +61: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt... +61: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt... +61: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt... +63: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt... +63: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt... +63: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt... +63: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt... +63: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt... +53: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt... +53: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt... +53: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt... +53: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt... +53: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt... +33: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt... +33: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt... +33: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt... +33: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt... +33: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt... +59: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt... +59: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt... +59: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt... +59: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt... +59: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt... +62: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt... +62: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt... +62: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt... +62: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt... +62: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt... +58: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt... +58: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt... +58: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt... +58: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt... +38: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt... +38: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt... +38: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt... +38: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt... +38: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt... +44: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt... +44: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt... +44: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt... +44: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt... +44: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt... +48: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt... +48: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt... +48: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt... +48: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt... +48: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt... +34: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt... +34: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt... +34: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt... +34: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt... +34: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt... +43: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt... +43: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt... +43: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt... +43: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt... +43: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt... +36: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt... +36: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt... +36: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt... +36: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt... +36: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt... +35: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt... +35: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt... +35: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt... +35: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt... +35: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt... +39: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt... +39: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt... +39: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt... +39: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt... +39: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt... +50: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt... +50: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt... +50: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt... +50: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt... +50: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt... +32: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt... +51: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt... +51: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt... +51: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt... +51: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt... +51: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt... +60: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt... +60: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt... +60: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt... +60: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt... +60: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt... +49: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt... +49: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt... +46: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt... +46: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt... +46: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt... +46: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt... +46: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt... +41: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt... +41: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt... +41: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt... +41: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt... +41: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt... +55: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt... +55: [2022-12-02 19:38:03,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt... +55: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt... +55: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt... +55: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt... +47: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt... +47: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt... +47: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt... +47: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt... +47: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt... +45: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt... +37: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt... +37: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt... +37: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt... +37: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt... +37: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt... +40: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt... +40: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt... +40: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt... +40: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt... +40: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt... +42: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt... +42: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt... +42: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt... +57: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt... +57: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt... +57: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt... +57: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt... +57: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt... +54: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt... +54: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt... +54: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt... +56: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt... +56: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt... +56: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt... +56: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt... +56: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt... +52: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt... +61: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt... +61: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt... +61: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt... +63: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt... +63: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt... +63: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt... +53: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt... +53: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt... +33: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt... +59: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt... +62: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt... +58: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt... +58: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt... +58: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt... +58: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt... +38: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt... +44: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt... +44: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt... +44: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt... +48: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt... +48: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt... +48: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt... +34: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt... +34: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt... +34: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt... +43: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt... +43: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt... +43: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt... +36: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt... +36: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt... +36: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt... +35: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt... +35: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt... +39: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt... +50: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt... +32: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt... +32: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt... +32: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt... +32: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt... +51: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt... +60: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt... +60: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt... +49: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt... +49: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt... +49: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt... +49: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt... +49: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt... +46: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt... +46: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt... +46: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt... +41: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt... +41: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt... +41: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt... +55: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt... +47: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt... +47: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt... +47: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt... +45: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt... +45: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt... +45: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt... +45: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt... +45: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt... +37: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt... +40: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt... +42: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt... +42: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt... +42: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt... +42: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt... +42: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt... +57: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt... +56: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt... +52: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt... +53: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt... +33: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt... +33: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt... +59: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt... +59: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt... +62: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt... +62: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt... +38: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt... +38: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt... +35: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt... +39: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt... +39: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt... +50: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt... +50: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt... +32: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt... +51: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt... +51: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt... +60: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt... +49: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt... +45: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt... +37: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt... +40: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt... +57: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt... +57: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt... +52: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt... +32: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt... +55: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt... +45: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt... +37: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt... +40: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt... + 0: [2022-12-02 19:38:03,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 0: [2022-12-02 19:38:03,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-12-02 19:38:03,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-12-02 19:38:03,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 7: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +19: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +20: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +52: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt... +15: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... + 1: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +11: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... + 5: [2022-12-02 19:38:03,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +10: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +10: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +28: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +22: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +12: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +18: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +18: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +26: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... + 9: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 2: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +25: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... + 4: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 6: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +13: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +31: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +55: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt... + 3: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +27: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... + 8: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... +16: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +14: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +17: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +29: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +30: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +24: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +23: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +21: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... + 0: [2022-12-02 19:38:03,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 7: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +19: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +20: [2022-12-02 19:38:03,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +15: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... + 1: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +11: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... + 5: [2022-12-02 19:38:03,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-12-02 19:38:03,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +10: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +28: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +22: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +12: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +18: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +26: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +26: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... + 9: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 2: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +25: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... + 4: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 6: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +13: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +31: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... + 3: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +27: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +27: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... + 8: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... +16: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +14: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +17: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +29: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +30: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +24: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +23: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +21: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... + 0: [2022-12-02 19:38:03,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 7: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +19: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +20: [2022-12-02 19:38:03,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +15: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... + 1: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +11: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 5: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-12-02 19:38:03,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +10: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +28: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +22: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +12: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +18: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +26: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... + 9: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 2: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +25: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... + 4: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 6: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +13: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +31: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... + 3: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +27: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... + 8: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... +16: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +14: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +17: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +29: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +30: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +24: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +23: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +21: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... + 0: [2022-12-02 19:38:03,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +20: [2022-12-02 19:38:03,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +15: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... + 1: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +11: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... + 5: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-12-02 19:38:03,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-12-02 19:38:03,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +10: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +28: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +22: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +12: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +18: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +26: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... + 9: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... +25: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... + 4: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 6: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +13: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +31: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... + 3: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +27: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... + 8: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +16: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +17: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +29: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +30: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +23: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +21: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... + 0: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +19: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +20: [2022-12-02 19:38:03,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-12-02 19:38:03,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +15: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... + 1: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +11: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +10: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +22: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +12: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +26: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +25: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... + 4: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +13: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... + 8: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +16: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +14: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +23: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +21: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +19: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +20: [2022-12-02 19:38:03,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... + 1: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +11: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +22: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +12: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +18: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +25: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... + 8: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... +17: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +21: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +19: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +20: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... + 1: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +11: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +22: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +12: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +17: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +23: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +21: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +12: [2022-12-02 19:38:03,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +32: [2022-12-02 19:38:03,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt. +32: [2022-12-02 19:38:03,530] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt +32: [2022-12-02 19:38:03,530] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 0: [2022-12-02 19:38:03,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. + 0: [2022-12-02 19:38:03,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-12-02 19:38:03,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-12-02 19:38:03,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 0: [2022-12-02 19:38:03,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-12-02 19:38:03,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-12-02 19:38:03,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 0: [2022-12-02 19:38:03,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-12-02 19:38:03,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-12-02 19:38:03,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-12-02 19:38:03,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 0: [2022-12-02 19:38:03,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-12-02 19:38:03,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +32: [2022-12-02 19:38:03,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt. +32: [2022-12-02 19:38:03,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt +32: [2022-12-02 19:38:03,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt. +32: [2022-12-02 19:38:03,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt. +32: [2022-12-02 19:38:03,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +32: [2022-12-02 19:38:03,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt. +32: [2022-12-02 19:38:03,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt +32: [2022-12-02 19:38:03,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt +32: [2022-12-02 19:38:03,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +32: [2022-12-02 19:38:03,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +32: [2022-12-02 19:38:03,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt +32: [2022-12-02 19:38:03,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +32: [2022-12-02 19:38:03,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt. +32: [2022-12-02 19:38:03,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt +32: [2022-12-02 19:38:03,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +32: [2022-12-02 19:38:03,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt. +32: [2022-12-02 19:38:03,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt. +32: [2022-12-02 19:38:03,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt +32: [2022-12-02 19:38:03,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt +32: [2022-12-02 19:38:03,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +32: [2022-12-02 19:38:03,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 0: [2022-12-02 19:38:03,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-12-02 19:38:03,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-12-02 19:38:03,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 0: [2022-12-02 19:38:03,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-12-02 19:38:03,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-12-02 19:38:03,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 0: [2022-12-02 19:38:03,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-12-02 19:38:03,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-12-02 19:38:03,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +48: [2022-12-02 19:38:03,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt. +48: [2022-12-02 19:38:03,607] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt +48: [2022-12-02 19:38:03,607] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +48: [2022-12-02 19:38:03,608] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt. +48: [2022-12-02 19:38:03,608] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt +48: [2022-12-02 19:38:03,608] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +48: [2022-12-02 19:38:03,608] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt. +48: [2022-12-02 19:38:03,608] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt +48: [2022-12-02 19:38:03,608] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +48: [2022-12-02 19:38:03,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt. +48: [2022-12-02 19:38:03,609] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt +48: [2022-12-02 19:38:03,609] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +25: [2022-12-02 19:38:03,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-12-02 19:38:03,612] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-12-02 19:38:03,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +25: [2022-12-02 19:38:03,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-12-02 19:38:03,612] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-12-02 19:38:03,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +25: [2022-12-02 19:38:03,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +53: [2022-12-02 19:38:03,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt. +53: [2022-12-02 19:38:03,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt. +53: [2022-12-02 19:38:03,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt. +53: [2022-12-02 19:38:03,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt +53: [2022-12-02 19:38:03,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt +53: [2022-12-02 19:38:03,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt +53: [2022-12-02 19:38:03,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +53: [2022-12-02 19:38:03,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +53: [2022-12-02 19:38:03,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +53: [2022-12-02 19:38:03,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt. +53: [2022-12-02 19:38:03,615] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt +53: [2022-12-02 19:38:03,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +53: [2022-12-02 19:38:03,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt. +53: [2022-12-02 19:38:03,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt. +53: [2022-12-02 19:38:03,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt. +53: [2022-12-02 19:38:03,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt. +53: [2022-12-02 19:38:03,616] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt +53: [2022-12-02 19:38:03,616] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt +53: [2022-12-02 19:38:03,616] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt +53: [2022-12-02 19:38:03,616] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt +53: [2022-12-02 19:38:03,616] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +53: [2022-12-02 19:38:03,616] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +53: [2022-12-02 19:38:03,616] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +53: [2022-12-02 19:38:03,616] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 5: [2022-12-02 19:38:03,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-12-02 19:38:03,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-12-02 19:38:03,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-12-02 19:38:03,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-12-02 19:38:03,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-12-02 19:38:03,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-12-02 19:38:03,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-12-02 19:38:03,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-12-02 19:38:03,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 5: [2022-12-02 19:38:03,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-12-02 19:38:03,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 5: [2022-12-02 19:38:03,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 5: [2022-12-02 19:38:03,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-12-02 19:38:03,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 5: [2022-12-02 19:38:03,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +24: [2022-12-02 19:38:03,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-12-02 19:38:03,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-12-02 19:38:03,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-12-02 19:38:03,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-12-02 19:38:03,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-12-02 19:38:03,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-12-02 19:38:03,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +24: [2022-12-02 19:38:03,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +24: [2022-12-02 19:38:03,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 5: [2022-12-02 19:38:03,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-12-02 19:38:03,620] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-12-02 19:38:03,620] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 5: [2022-12-02 19:38:03,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-12-02 19:38:03,621] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-12-02 19:38:03,621] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +48: [2022-12-02 19:38:03,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt. +48: [2022-12-02 19:38:03,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt. +48: [2022-12-02 19:38:03,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt. +25: [2022-12-02 19:38:03,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-12-02 19:38:03,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-12-02 19:38:03,613] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-12-02 19:38:03,613] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-12-02 19:38:03,613] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +25: [2022-12-02 19:38:03,613] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-12-02 19:38:03,613] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +25: [2022-12-02 19:38:03,613] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +48: [2022-12-02 19:38:03,621] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt +48: [2022-12-02 19:38:03,621] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt +48: [2022-12-02 19:38:03,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt. +48: [2022-12-02 19:38:03,621] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt +48: [2022-12-02 19:38:03,621] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +48: [2022-12-02 19:38:03,621] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +48: [2022-12-02 19:38:03,621] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +48: [2022-12-02 19:38:03,621] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt +48: [2022-12-02 19:38:03,621] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +19: [2022-12-02 19:38:03,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-12-02 19:38:03,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-12-02 19:38:03,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-12-02 19:38:03,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-12-02 19:38:03,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-12-02 19:38:03,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-12-02 19:38:03,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-12-02 19:38:03,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-12-02 19:38:03,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-12-02 19:38:03,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-12-02 19:38:03,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-12-02 19:38:03,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-12-02 19:38:03,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-12-02 19:38:03,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-12-02 19:38:03,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +19: [2022-12-02 19:38:03,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +19: [2022-12-02 19:38:03,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +19: [2022-12-02 19:38:03,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +19: [2022-12-02 19:38:03,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +19: [2022-12-02 19:38:03,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +19: [2022-12-02 19:38:03,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +12: [2022-12-02 19:38:03,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-12-02 19:38:03,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-12-02 19:38:03,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +12: [2022-12-02 19:38:03,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-12-02 19:38:03,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-12-02 19:38:03,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-12-02 19:38:03,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-12-02 19:38:03,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-12-02 19:38:03,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-12-02 19:38:03,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +12: [2022-12-02 19:38:03,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +12: [2022-12-02 19:38:03,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 5: [2022-12-02 19:38:03,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +12: [2022-12-02 19:38:03,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-12-02 19:38:03,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-12-02 19:38:03,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +12: [2022-12-02 19:38:03,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-12-02 19:38:03,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-12-02 19:38:03,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-12-02 19:38:03,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +12: [2022-12-02 19:38:03,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +12: [2022-12-02 19:38:03,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 5: [2022-12-02 19:38:03,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-12-02 19:38:03,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +30: [2022-12-02 19:38:03,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-12-02 19:38:03,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +12: [2022-12-02 19:38:03,632] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +52: [2022-12-02 19:38:03,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt. +52: [2022-12-02 19:38:03,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt. +52: [2022-12-02 19:38:03,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt. +52: [2022-12-02 19:38:03,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt. +52: [2022-12-02 19:38:03,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt. + 8: [2022-12-02 19:38:03,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-12-02 19:38:03,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-12-02 19:38:03,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-12-02 19:38:03,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-12-02 19:38:03,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. +52: [2022-12-02 19:38:03,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt. +52: [2022-12-02 19:38:03,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt. + 8: [2022-12-02 19:38:03,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-12-02 19:38:03,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-12-02 19:38:03,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. +52: [2022-12-02 19:38:03,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt + 8: [2022-12-02 19:38:03,635] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-12-02 19:38:03,635] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-12-02 19:38:03,635] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-12-02 19:38:03,635] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt +52: [2022-12-02 19:38:03,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt +52: [2022-12-02 19:38:03,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt +52: [2022-12-02 19:38:03,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt +52: [2022-12-02 19:38:03,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt +52: [2022-12-02 19:38:03,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt + 8: [2022-12-02 19:38:03,635] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-12-02 19:38:03,635] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-12-02 19:38:03,635] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-12-02 19:38:03,635] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-12-02 19:38:03,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 8: [2022-12-02 19:38:03,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +52: [2022-12-02 19:38:03,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt + 8: [2022-12-02 19:38:03,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 8: [2022-12-02 19:38:03,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +52: [2022-12-02 19:38:03,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 8: [2022-12-02 19:38:03,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 8: [2022-12-02 19:38:03,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 8: [2022-12-02 19:38:03,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +52: [2022-12-02 19:38:03,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +52: [2022-12-02 19:38:03,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 8: [2022-12-02 19:38:03,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +52: [2022-12-02 19:38:03,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +52: [2022-12-02 19:38:03,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +52: [2022-12-02 19:38:03,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +52: [2022-12-02 19:38:03,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +12: [2022-12-02 19:38:03,632] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-12-02 19:38:03,632] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +54: [2022-12-02 19:38:03,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt. +54: [2022-12-02 19:38:03,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt. +54: [2022-12-02 19:38:03,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt. +54: [2022-12-02 19:38:03,637] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt +54: [2022-12-02 19:38:03,637] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt +54: [2022-12-02 19:38:03,637] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt +30: [2022-12-02 19:38:03,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +54: [2022-12-02 19:38:03,637] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +30: [2022-12-02 19:38:03,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +54: [2022-12-02 19:38:03,637] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +54: [2022-12-02 19:38:03,637] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +30: [2022-12-02 19:38:03,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-12-02 19:38:03,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-12-02 19:38:03,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +30: [2022-12-02 19:38:03,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +30: [2022-12-02 19:38:03,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-12-02 19:38:03,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-12-02 19:38:03,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +30: [2022-12-02 19:38:03,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +54: [2022-12-02 19:38:03,639] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt. +54: [2022-12-02 19:38:03,639] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt. +54: [2022-12-02 19:38:03,639] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt. +54: [2022-12-02 19:38:03,639] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt. +54: [2022-12-02 19:38:03,639] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt. +54: [2022-12-02 19:38:03,639] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt +54: [2022-12-02 19:38:03,639] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt +54: [2022-12-02 19:38:03,639] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt +54: [2022-12-02 19:38:03,639] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt +54: [2022-12-02 19:38:03,639] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt +54: [2022-12-02 19:38:03,639] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +54: [2022-12-02 19:38:03,639] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +54: [2022-12-02 19:38:03,639] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +54: [2022-12-02 19:38:03,639] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +54: [2022-12-02 19:38:03,639] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +61: [2022-12-02 19:38:03,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt. +61: [2022-12-02 19:38:03,637] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt +61: [2022-12-02 19:38:03,638] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +61: [2022-12-02 19:38:03,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt. +61: [2022-12-02 19:38:03,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt. +61: [2022-12-02 19:38:03,638] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt +61: [2022-12-02 19:38:03,638] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt +61: [2022-12-02 19:38:03,638] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +61: [2022-12-02 19:38:03,638] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +61: [2022-12-02 19:38:03,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt. +61: [2022-12-02 19:38:03,638] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt +61: [2022-12-02 19:38:03,638] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +61: [2022-12-02 19:38:03,643] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt. +61: [2022-12-02 19:38:03,643] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt +61: [2022-12-02 19:38:03,643] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +61: [2022-12-02 19:38:03,643] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt. +61: [2022-12-02 19:38:03,643] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt. +61: [2022-12-02 19:38:03,643] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt. +61: [2022-12-02 19:38:03,643] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt +61: [2022-12-02 19:38:03,643] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt +61: [2022-12-02 19:38:03,643] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt +61: [2022-12-02 19:38:03,643] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +61: [2022-12-02 19:38:03,643] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +61: [2022-12-02 19:38:03,643] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +37: [2022-12-02 19:38:03,647] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt. +37: [2022-12-02 19:38:03,647] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt. +37: [2022-12-02 19:38:03,647] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt. +52: [2022-12-02 19:38:03,649] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt. +37: [2022-12-02 19:38:03,647] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt. +37: [2022-12-02 19:38:03,647] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt. +37: [2022-12-02 19:38:03,647] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt. +37: [2022-12-02 19:38:03,647] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt. +37: [2022-12-02 19:38:03,647] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt. +37: [2022-12-02 19:38:03,647] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt +37: [2022-12-02 19:38:03,647] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt +37: [2022-12-02 19:38:03,647] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt +37: [2022-12-02 19:38:03,647] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt +37: [2022-12-02 19:38:03,647] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +37: [2022-12-02 19:38:03,647] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt +37: [2022-12-02 19:38:03,647] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt +37: [2022-12-02 19:38:03,647] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt +37: [2022-12-02 19:38:03,647] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt +37: [2022-12-02 19:38:03,647] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +37: [2022-12-02 19:38:03,647] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +37: [2022-12-02 19:38:03,647] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +37: [2022-12-02 19:38:03,647] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +37: [2022-12-02 19:38:03,647] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +37: [2022-12-02 19:38:03,647] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +37: [2022-12-02 19:38:03,647] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +52: [2022-12-02 19:38:03,649] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt +52: [2022-12-02 19:38:03,649] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +21: [2022-12-02 19:38:03,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-12-02 19:38:03,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-12-02 19:38:03,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-12-02 19:38:03,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-12-02 19:38:03,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-12-02 19:38:03,653] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-12-02 19:38:03,653] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-12-02 19:38:03,653] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-12-02 19:38:03,653] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-12-02 19:38:03,653] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-12-02 19:38:03,653] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +21: [2022-12-02 19:38:03,653] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +21: [2022-12-02 19:38:03,653] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +21: [2022-12-02 19:38:03,653] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +21: [2022-12-02 19:38:03,653] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 0: [2022-12-02 19:38:03,654] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-12-02 19:38:03,654] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +17: [2022-12-02 19:38:03,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-12-02 19:38:03,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +24: [2022-12-02 19:38:03,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-12-02 19:38:03,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-12-02 19:38:03,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +10: [2022-12-02 19:38:03,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-12-02 19:38:03,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-12-02 19:38:03,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-12-02 19:38:03,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-12-02 19:38:03,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-12-02 19:38:03,657] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-12-02 19:38:03,657] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-12-02 19:38:03,657] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-12-02 19:38:03,657] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-12-02 19:38:03,657] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-12-02 19:38:03,657] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +10: [2022-12-02 19:38:03,657] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +10: [2022-12-02 19:38:03,657] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +10: [2022-12-02 19:38:03,657] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +10: [2022-12-02 19:38:03,657] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +10: [2022-12-02 19:38:03,657] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-12-02 19:38:03,657] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-12-02 19:38:03,657] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +17: [2022-12-02 19:38:03,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-12-02 19:38:03,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-12-02 19:38:03,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-12-02 19:38:03,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-12-02 19:38:03,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-12-02 19:38:03,654] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-12-02 19:38:03,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-12-02 19:38:03,654] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-12-02 19:38:03,654] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-12-02 19:38:03,654] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +17: [2022-12-02 19:38:03,654] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +17: [2022-12-02 19:38:03,654] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-12-02 19:38:03,654] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-12-02 19:38:03,654] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-12-02 19:38:03,654] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-12-02 19:38:03,654] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-12-02 19:38:03,654] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +17: [2022-12-02 19:38:03,654] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +17: [2022-12-02 19:38:03,654] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +17: [2022-12-02 19:38:03,654] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +17: [2022-12-02 19:38:03,654] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +17: [2022-12-02 19:38:03,654] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 2: [2022-12-02 19:38:03,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-12-02 19:38:03,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-12-02 19:38:03,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-12-02 19:38:03,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-12-02 19:38:03,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 2: [2022-12-02 19:38:03,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-12-02 19:38:03,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +39: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt. +39: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt. +39: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt. + 2: [2022-12-02 19:38:03,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-12-02 19:38:03,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-12-02 19:38:03,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-12-02 19:38:03,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-12-02 19:38:03,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-12-02 19:38:03,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 2: [2022-12-02 19:38:03,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 2: [2022-12-02 19:38:03,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 2: [2022-12-02 19:38:03,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-12-02 19:38:03,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-12-02 19:38:03,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-12-02 19:38:03,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 2: [2022-12-02 19:38:03,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 2: [2022-12-02 19:38:03,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 2: [2022-12-02 19:38:03,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 2: [2022-12-02 19:38:03,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 2: [2022-12-02 19:38:03,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +39: [2022-12-02 19:38:03,660] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt +39: [2022-12-02 19:38:03,660] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt +39: [2022-12-02 19:38:03,660] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt +39: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt. +39: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt. +39: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt. +39: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +39: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +39: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt. +39: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +39: [2022-12-02 19:38:03,660] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt +39: [2022-12-02 19:38:03,660] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt +39: [2022-12-02 19:38:03,660] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt +39: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +39: [2022-12-02 19:38:03,660] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt +39: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +39: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +39: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +39: [2022-12-02 19:38:03,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt. +35: [2022-12-02 19:38:03,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt. +35: [2022-12-02 19:38:03,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt. +35: [2022-12-02 19:38:03,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt. +35: [2022-12-02 19:38:03,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt. +35: [2022-12-02 19:38:03,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt. +35: [2022-12-02 19:38:03,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt. +35: [2022-12-02 19:38:03,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt. +35: [2022-12-02 19:38:03,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt. +35: [2022-12-02 19:38:03,662] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt +35: [2022-12-02 19:38:03,662] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt +35: [2022-12-02 19:38:03,662] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt +35: [2022-12-02 19:38:03,662] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt +35: [2022-12-02 19:38:03,662] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt +35: [2022-12-02 19:38:03,662] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt +35: [2022-12-02 19:38:03,662] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt +35: [2022-12-02 19:38:03,662] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt +35: [2022-12-02 19:38:03,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +35: [2022-12-02 19:38:03,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +35: [2022-12-02 19:38:03,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +35: [2022-12-02 19:38:03,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +35: [2022-12-02 19:38:03,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +35: [2022-12-02 19:38:03,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +35: [2022-12-02 19:38:03,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +35: [2022-12-02 19:38:03,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +39: [2022-12-02 19:38:03,661] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt +39: [2022-12-02 19:38:03,661] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +29: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-12-02 19:38:03,660] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-12-02 19:38:03,660] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-12-02 19:38:03,660] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-12-02 19:38:03,660] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +29: [2022-12-02 19:38:03,660] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-12-02 19:38:03,660] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +29: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +29: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +29: [2022-12-02 19:38:03,660] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-12-02 19:38:03,660] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +29: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +29: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +29: [2022-12-02 19:38:03,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 9: [2022-12-02 19:38:03,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-12-02 19:38:03,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-12-02 19:38:03,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. +33: [2022-12-02 19:38:03,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt. +33: [2022-12-02 19:38:03,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt. +22: [2022-12-02 19:38:03,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-12-02 19:38:03,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-12-02 19:38:03,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +33: [2022-12-02 19:38:03,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt. +33: [2022-12-02 19:38:03,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt. +33: [2022-12-02 19:38:03,665] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt +33: [2022-12-02 19:38:03,665] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt +33: [2022-12-02 19:38:03,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt. +33: [2022-12-02 19:38:03,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt. +33: [2022-12-02 19:38:03,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt. +33: [2022-12-02 19:38:03,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt. +33: [2022-12-02 19:38:03,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +33: [2022-12-02 19:38:03,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +33: [2022-12-02 19:38:03,665] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt +33: [2022-12-02 19:38:03,665] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt +33: [2022-12-02 19:38:03,665] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt +33: [2022-12-02 19:38:03,665] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt +33: [2022-12-02 19:38:03,665] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt +33: [2022-12-02 19:38:03,665] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt +33: [2022-12-02 19:38:03,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +33: [2022-12-02 19:38:03,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +33: [2022-12-02 19:38:03,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +33: [2022-12-02 19:38:03,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +33: [2022-12-02 19:38:03,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +33: [2022-12-02 19:38:03,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 9: [2022-12-02 19:38:03,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-12-02 19:38:03,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-12-02 19:38:03,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. +24: [2022-12-02 19:38:03,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. + 9: [2022-12-02 19:38:03,664] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-12-02 19:38:03,664] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-12-02 19:38:03,664] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-12-02 19:38:03,664] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-12-02 19:38:03,664] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 9: [2022-12-02 19:38:03,664] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 9: [2022-12-02 19:38:03,664] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 9: [2022-12-02 19:38:03,664] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-12-02 19:38:03,664] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-12-02 19:38:03,664] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 9: [2022-12-02 19:38:03,664] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 9: [2022-12-02 19:38:03,664] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 9: [2022-12-02 19:38:03,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-12-02 19:38:03,665] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-12-02 19:38:03,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-12-02 19:38:03,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 9: [2022-12-02 19:38:03,665] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-12-02 19:38:03,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +22: [2022-12-02 19:38:03,662] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-12-02 19:38:03,662] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-12-02 19:38:03,662] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-12-02 19:38:03,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +22: [2022-12-02 19:38:03,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +22: [2022-12-02 19:38:03,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +22: [2022-12-02 19:38:03,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-12-02 19:38:03,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-12-02 19:38:03,663] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-12-02 19:38:03,664] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-12-02 19:38:03,664] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +22: [2022-12-02 19:38:03,664] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +24: [2022-12-02 19:38:03,662] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-12-02 19:38:03,663] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +44: [2022-12-02 19:38:03,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt. +44: [2022-12-02 19:38:03,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt. +44: [2022-12-02 19:38:03,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt. +44: [2022-12-02 19:38:03,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt. +44: [2022-12-02 19:38:03,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt. +44: [2022-12-02 19:38:03,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt +44: [2022-12-02 19:38:03,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt +44: [2022-12-02 19:38:03,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt +44: [2022-12-02 19:38:03,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt +44: [2022-12-02 19:38:03,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt. +44: [2022-12-02 19:38:03,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt +44: [2022-12-02 19:38:03,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +44: [2022-12-02 19:38:03,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +44: [2022-12-02 19:38:03,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +44: [2022-12-02 19:38:03,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +44: [2022-12-02 19:38:03,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +44: [2022-12-02 19:38:03,672] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt +44: [2022-12-02 19:38:03,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +42: [2022-12-02 19:38:03,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt. +42: [2022-12-02 19:38:03,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt. +42: [2022-12-02 19:38:03,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt. +14: [2022-12-02 19:38:03,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-12-02 19:38:03,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-12-02 19:38:03,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-12-02 19:38:03,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-12-02 19:38:03,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-12-02 19:38:03,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-12-02 19:38:03,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-12-02 19:38:03,676] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-12-02 19:38:03,676] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-12-02 19:38:03,676] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-12-02 19:38:03,676] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-12-02 19:38:03,676] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-12-02 19:38:03,676] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +14: [2022-12-02 19:38:03,676] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-12-02 19:38:03,676] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +14: [2022-12-02 19:38:03,676] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-12-02 19:38:03,676] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +14: [2022-12-02 19:38:03,676] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +14: [2022-12-02 19:38:03,676] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +14: [2022-12-02 19:38:03,676] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +14: [2022-12-02 19:38:03,676] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +14: [2022-12-02 19:38:03,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-12-02 19:38:03,676] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-12-02 19:38:03,676] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +20: [2022-12-02 19:38:03,679] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-12-02 19:38:03,679] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-12-02 19:38:03,679] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-12-02 19:38:03,679] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-12-02 19:38:03,679] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-12-02 19:38:03,679] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-12-02 19:38:03,679] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-12-02 19:38:03,679] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-12-02 19:38:03,679] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-12-02 19:38:03,679] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-12-02 19:38:03,679] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +20: [2022-12-02 19:38:03,679] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +20: [2022-12-02 19:38:03,679] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +20: [2022-12-02 19:38:03,679] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +20: [2022-12-02 19:38:03,679] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +42: [2022-12-02 19:38:03,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt. +42: [2022-12-02 19:38:03,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt. +42: [2022-12-02 19:38:03,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt. +42: [2022-12-02 19:38:03,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt. +42: [2022-12-02 19:38:03,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt. +42: [2022-12-02 19:38:03,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt +42: [2022-12-02 19:38:03,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt +42: [2022-12-02 19:38:03,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt +42: [2022-12-02 19:38:03,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt +42: [2022-12-02 19:38:03,671] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +42: [2022-12-02 19:38:03,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +42: [2022-12-02 19:38:03,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +42: [2022-12-02 19:38:03,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt +42: [2022-12-02 19:38:03,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt +42: [2022-12-02 19:38:03,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt +42: [2022-12-02 19:38:03,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt +42: [2022-12-02 19:38:03,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +42: [2022-12-02 19:38:03,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +42: [2022-12-02 19:38:03,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +42: [2022-12-02 19:38:03,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +42: [2022-12-02 19:38:03,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +44: [2022-12-02 19:38:03,679] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt. +44: [2022-12-02 19:38:03,679] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt +44: [2022-12-02 19:38:03,679] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt. +44: [2022-12-02 19:38:03,679] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +44: [2022-12-02 19:38:03,679] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt +44: [2022-12-02 19:38:03,679] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +45: [2022-12-02 19:38:03,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt. +45: [2022-12-02 19:38:03,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt. +45: [2022-12-02 19:38:03,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt. +45: [2022-12-02 19:38:03,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt. +45: [2022-12-02 19:38:03,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt. +30: [2022-12-02 19:38:03,685] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-12-02 19:38:03,685] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-12-02 19:38:03,685] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +30: [2022-12-02 19:38:03,686] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-12-02 19:38:03,686] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-12-02 19:38:03,686] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +59: [2022-12-02 19:38:03,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt. +59: [2022-12-02 19:38:03,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt. +59: [2022-12-02 19:38:03,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt. +59: [2022-12-02 19:38:03,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt. +25: [2022-12-02 19:38:03,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +45: [2022-12-02 19:38:03,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt. +45: [2022-12-02 19:38:03,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt. +45: [2022-12-02 19:38:03,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt. +45: [2022-12-02 19:38:03,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt +45: [2022-12-02 19:38:03,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt +45: [2022-12-02 19:38:03,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt +45: [2022-12-02 19:38:03,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt +45: [2022-12-02 19:38:03,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt +45: [2022-12-02 19:38:03,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt +45: [2022-12-02 19:38:03,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt +45: [2022-12-02 19:38:03,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +45: [2022-12-02 19:38:03,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt +45: [2022-12-02 19:38:03,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +45: [2022-12-02 19:38:03,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +45: [2022-12-02 19:38:03,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +45: [2022-12-02 19:38:03,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +45: [2022-12-02 19:38:03,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +45: [2022-12-02 19:38:03,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +45: [2022-12-02 19:38:03,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +55: [2022-12-02 19:38:03,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt. +55: [2022-12-02 19:38:03,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt. +55: [2022-12-02 19:38:03,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt. +55: [2022-12-02 19:38:03,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt. +55: [2022-12-02 19:38:03,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt. +59: [2022-12-02 19:38:03,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt. +59: [2022-12-02 19:38:03,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt. +59: [2022-12-02 19:38:03,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt. +59: [2022-12-02 19:38:03,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt. +59: [2022-12-02 19:38:03,691] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt +59: [2022-12-02 19:38:03,691] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt +59: [2022-12-02 19:38:03,691] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt +59: [2022-12-02 19:38:03,691] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt +59: [2022-12-02 19:38:03,691] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +59: [2022-12-02 19:38:03,691] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +59: [2022-12-02 19:38:03,691] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt +59: [2022-12-02 19:38:03,691] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +59: [2022-12-02 19:38:03,691] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +59: [2022-12-02 19:38:03,691] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt +59: [2022-12-02 19:38:03,691] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt +59: [2022-12-02 19:38:03,691] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt +59: [2022-12-02 19:38:03,691] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +59: [2022-12-02 19:38:03,691] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +59: [2022-12-02 19:38:03,691] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +59: [2022-12-02 19:38:03,691] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +55: [2022-12-02 19:38:03,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt. +55: [2022-12-02 19:38:03,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt. +55: [2022-12-02 19:38:03,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt +55: [2022-12-02 19:38:03,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt +55: [2022-12-02 19:38:03,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt +55: [2022-12-02 19:38:03,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt +55: [2022-12-02 19:38:03,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt +25: [2022-12-02 19:38:03,690] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +55: [2022-12-02 19:38:03,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt +25: [2022-12-02 19:38:03,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +55: [2022-12-02 19:38:03,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt +55: [2022-12-02 19:38:03,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +55: [2022-12-02 19:38:03,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +55: [2022-12-02 19:38:03,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +55: [2022-12-02 19:38:03,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +55: [2022-12-02 19:38:03,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +55: [2022-12-02 19:38:03,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +55: [2022-12-02 19:38:03,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +55: [2022-12-02 19:38:03,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt. +55: [2022-12-02 19:38:03,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt +55: [2022-12-02 19:38:03,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +24: [2022-12-02 19:38:03,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-12-02 19:38:03,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-12-02 19:38:03,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +10: [2022-12-02 19:38:03,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +31: [2022-12-02 19:38:03,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-12-02 19:38:03,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-12-02 19:38:03,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-12-02 19:38:03,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-12-02 19:38:03,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +10: [2022-12-02 19:38:03,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-12-02 19:38:03,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +10: [2022-12-02 19:38:03,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-12-02 19:38:03,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-12-02 19:38:03,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +34: [2022-12-02 19:38:03,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt. +34: [2022-12-02 19:38:03,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt. +34: [2022-12-02 19:38:03,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt. +34: [2022-12-02 19:38:03,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt. +34: [2022-12-02 19:38:03,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt. +34: [2022-12-02 19:38:03,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt +34: [2022-12-02 19:38:03,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt +34: [2022-12-02 19:38:03,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt. +34: [2022-12-02 19:38:03,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt. +34: [2022-12-02 19:38:03,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +34: [2022-12-02 19:38:03,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt +34: [2022-12-02 19:38:03,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +34: [2022-12-02 19:38:03,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt +34: [2022-12-02 19:38:03,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt +34: [2022-12-02 19:38:03,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt +34: [2022-12-02 19:38:03,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt +34: [2022-12-02 19:38:03,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +34: [2022-12-02 19:38:03,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +34: [2022-12-02 19:38:03,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +34: [2022-12-02 19:38:03,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +34: [2022-12-02 19:38:03,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +34: [2022-12-02 19:38:03,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt. +34: [2022-12-02 19:38:03,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt +31: [2022-12-02 19:38:03,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-12-02 19:38:03,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-12-02 19:38:03,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-12-02 19:38:03,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-12-02 19:38:03,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-12-02 19:38:03,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-12-02 19:38:03,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-12-02 19:38:03,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-12-02 19:38:03,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +31: [2022-12-02 19:38:03,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +31: [2022-12-02 19:38:03,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +31: [2022-12-02 19:38:03,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +31: [2022-12-02 19:38:03,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +31: [2022-12-02 19:38:03,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-12-02 19:38:03,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-12-02 19:38:03,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-12-02 19:38:03,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +31: [2022-12-02 19:38:03,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +31: [2022-12-02 19:38:03,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +34: [2022-12-02 19:38:03,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +16: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-12-02 19:38:03,701] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-12-02 19:38:03,701] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-12-02 19:38:03,701] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-12-02 19:38:03,701] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-12-02 19:38:03,701] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-12-02 19:38:03,701] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +16: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +16: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +16: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +16: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +16: [2022-12-02 19:38:03,702] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +16: [2022-12-02 19:38:03,702] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-12-02 19:38:03,702] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +16: [2022-12-02 19:38:03,702] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-12-02 19:38:03,702] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-12-02 19:38:03,702] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +36: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt. +36: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt. +36: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt. +36: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt. +36: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt. +36: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt. +36: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt. +36: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt. +36: [2022-12-02 19:38:03,701] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt +36: [2022-12-02 19:38:03,701] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt +36: [2022-12-02 19:38:03,701] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt +36: [2022-12-02 19:38:03,701] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt +36: [2022-12-02 19:38:03,701] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt +36: [2022-12-02 19:38:03,701] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt +36: [2022-12-02 19:38:03,701] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt +36: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +36: [2022-12-02 19:38:03,701] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt +51: [2022-12-02 19:38:03,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt. +51: [2022-12-02 19:38:03,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt. +51: [2022-12-02 19:38:03,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt. +51: [2022-12-02 19:38:03,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt. +51: [2022-12-02 19:38:03,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt. +36: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +36: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +36: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +36: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +36: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +36: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +40: [2022-12-02 19:38:03,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt. +40: [2022-12-02 19:38:03,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt. +40: [2022-12-02 19:38:03,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt. +36: [2022-12-02 19:38:03,701] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +51: [2022-12-02 19:38:03,706] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt. +51: [2022-12-02 19:38:03,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt. +51: [2022-12-02 19:38:03,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt. +51: [2022-12-02 19:38:03,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt +51: [2022-12-02 19:38:03,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt +51: [2022-12-02 19:38:03,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt +51: [2022-12-02 19:38:03,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt +51: [2022-12-02 19:38:03,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt +51: [2022-12-02 19:38:03,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt +51: [2022-12-02 19:38:03,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +51: [2022-12-02 19:38:03,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +51: [2022-12-02 19:38:03,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +51: [2022-12-02 19:38:03,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt +51: [2022-12-02 19:38:03,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt +51: [2022-12-02 19:38:03,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +51: [2022-12-02 19:38:03,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +51: [2022-12-02 19:38:03,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +51: [2022-12-02 19:38:03,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +51: [2022-12-02 19:38:03,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +40: [2022-12-02 19:38:03,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt. +40: [2022-12-02 19:38:03,704] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt +40: [2022-12-02 19:38:03,704] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt +40: [2022-12-02 19:38:03,704] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt +40: [2022-12-02 19:38:03,704] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt +40: [2022-12-02 19:38:03,704] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +40: [2022-12-02 19:38:03,704] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +40: [2022-12-02 19:38:03,704] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +40: [2022-12-02 19:38:03,704] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +40: [2022-12-02 19:38:03,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt. +40: [2022-12-02 19:38:03,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt. +40: [2022-12-02 19:38:03,705] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt +40: [2022-12-02 19:38:03,705] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt +40: [2022-12-02 19:38:03,705] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +40: [2022-12-02 19:38:03,705] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +13: [2022-12-02 19:38:03,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-12-02 19:38:03,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-12-02 19:38:03,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-12-02 19:38:03,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-12-02 19:38:03,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-12-02 19:38:03,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-12-02 19:38:03,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-12-02 19:38:03,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-12-02 19:38:03,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-12-02 19:38:03,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-12-02 19:38:03,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-12-02 19:38:03,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-12-02 19:38:03,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-12-02 19:38:03,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-12-02 19:38:03,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +13: [2022-12-02 19:38:03,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-12-02 19:38:03,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-12-02 19:38:03,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +13: [2022-12-02 19:38:03,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +13: [2022-12-02 19:38:03,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +13: [2022-12-02 19:38:03,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +13: [2022-12-02 19:38:03,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +13: [2022-12-02 19:38:03,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +13: [2022-12-02 19:38:03,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +28: [2022-12-02 19:38:03,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-12-02 19:38:03,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-12-02 19:38:03,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-12-02 19:38:03,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-12-02 19:38:03,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +40: [2022-12-02 19:38:03,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt. +40: [2022-12-02 19:38:03,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt. +40: [2022-12-02 19:38:03,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt +40: [2022-12-02 19:38:03,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt +40: [2022-12-02 19:38:03,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +40: [2022-12-02 19:38:03,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +18: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +19: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +18: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +18: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +18: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 4: [2022-12-02 19:38:03,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-12-02 19:38:03,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +28: [2022-12-02 19:38:03,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-12-02 19:38:03,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +18: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +18: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +18: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +28: [2022-12-02 19:38:03,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-12-02 19:38:03,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-12-02 19:38:03,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-12-02 19:38:03,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +18: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +28: [2022-12-02 19:38:03,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-12-02 19:38:03,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-12-02 19:38:03,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-12-02 19:38:03,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +28: [2022-12-02 19:38:03,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +28: [2022-12-02 19:38:03,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +28: [2022-12-02 19:38:03,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +18: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +28: [2022-12-02 19:38:03,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +28: [2022-12-02 19:38:03,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +28: [2022-12-02 19:38:03,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +18: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +28: [2022-12-02 19:38:03,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-12-02 19:38:03,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-12-02 19:38:03,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +18: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-12-02 19:38:03,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-12-02 19:38:03,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +63: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt. +63: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt. +63: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt. +63: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt. +63: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt. +63: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt. +63: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt. +63: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt. +63: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt +63: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt +63: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt +63: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt +63: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt +63: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt +63: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt +63: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt +63: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +63: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +63: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +63: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +63: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +63: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +63: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +63: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +43: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt. +43: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt. +43: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt. +43: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt. +43: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt. + 4: [2022-12-02 19:38:03,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-12-02 19:38:03,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-12-02 19:38:03,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-12-02 19:38:03,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-12-02 19:38:03,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 4: [2022-12-02 19:38:03,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 4: [2022-12-02 19:38:03,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-12-02 19:38:03,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-12-02 19:38:03,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 4: [2022-12-02 19:38:03,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 4: [2022-12-02 19:38:03,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-12-02 19:38:03,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-12-02 19:38:03,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-12-02 19:38:03,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-12-02 19:38:03,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-12-02 19:38:03,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-12-02 19:38:03,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 4: [2022-12-02 19:38:03,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 4: [2022-12-02 19:38:03,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-12-02 19:38:03,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 4: [2022-12-02 19:38:03,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-12-02 19:38:03,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +43: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt. +43: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt. +43: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt +43: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt +43: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt +43: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt +43: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt. +43: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt +43: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt +43: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt +43: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +43: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +43: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +43: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +43: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +43: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +43: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +43: [2022-12-02 19:38:03,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt +43: [2022-12-02 19:38:03,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +58: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt. +58: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt. +58: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt. +58: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt. +58: [2022-12-02 19:38:03,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt +58: [2022-12-02 19:38:03,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt +58: [2022-12-02 19:38:03,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt +58: [2022-12-02 19:38:03,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt +58: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +58: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +58: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +58: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +58: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt. +58: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt. +58: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt. +58: [2022-12-02 19:38:03,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt +58: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt. +41: [2022-12-02 19:38:03,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt. +41: [2022-12-02 19:38:03,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt. +41: [2022-12-02 19:38:03,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt. +41: [2022-12-02 19:38:03,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt. +41: [2022-12-02 19:38:03,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt. +41: [2022-12-02 19:38:03,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt. +41: [2022-12-02 19:38:03,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt. +41: [2022-12-02 19:38:03,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt +41: [2022-12-02 19:38:03,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt +41: [2022-12-02 19:38:03,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt +41: [2022-12-02 19:38:03,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt +41: [2022-12-02 19:38:03,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt +41: [2022-12-02 19:38:03,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +41: [2022-12-02 19:38:03,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt +41: [2022-12-02 19:38:03,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt +41: [2022-12-02 19:38:03,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +41: [2022-12-02 19:38:03,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +41: [2022-12-02 19:38:03,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +41: [2022-12-02 19:38:03,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +41: [2022-12-02 19:38:03,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +41: [2022-12-02 19:38:03,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +41: [2022-12-02 19:38:03,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt. +58: [2022-12-02 19:38:03,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt +58: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +58: [2022-12-02 19:38:03,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt +41: [2022-12-02 19:38:03,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt +58: [2022-12-02 19:38:03,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt +58: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +58: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +41: [2022-12-02 19:38:03,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +58: [2022-12-02 19:38:03,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +26: [2022-12-02 19:38:03,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. + 1: [2022-12-02 19:38:03,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-12-02 19:38:03,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-12-02 19:38:03,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-12-02 19:38:03,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-12-02 19:38:03,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-12-02 19:38:03,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-12-02 19:38:03,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-12-02 19:38:03,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-12-02 19:38:03,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-12-02 19:38:03,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-12-02 19:38:03,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-12-02 19:38:03,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-12-02 19:38:03,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 1: [2022-12-02 19:38:03,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 1: [2022-12-02 19:38:03,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-12-02 19:38:03,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 1: [2022-12-02 19:38:03,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-12-02 19:38:03,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 1: [2022-12-02 19:38:03,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 1: [2022-12-02 19:38:03,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 1: [2022-12-02 19:38:03,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +26: [2022-12-02 19:38:03,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-12-02 19:38:03,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-12-02 19:38:03,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-12-02 19:38:03,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-12-02 19:38:03,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-12-02 19:38:03,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +26: [2022-12-02 19:38:03,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-12-02 19:38:03,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +26: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +26: [2022-12-02 19:38:03,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +26: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +26: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +26: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +26: [2022-12-02 19:38:03,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 1: [2022-12-02 19:38:03,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-12-02 19:38:03,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-12-02 19:38:03,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +25: [2022-12-02 19:38:03,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-12-02 19:38:03,725] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-12-02 19:38:03,725] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +46: [2022-12-02 19:38:03,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt. +46: [2022-12-02 19:38:03,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt. +46: [2022-12-02 19:38:03,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt. +46: [2022-12-02 19:38:03,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt. +46: [2022-12-02 19:38:03,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt. +46: [2022-12-02 19:38:03,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt. +46: [2022-12-02 19:38:03,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt. +46: [2022-12-02 19:38:03,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt +46: [2022-12-02 19:38:03,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt. +46: [2022-12-02 19:38:03,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt +46: [2022-12-02 19:38:03,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt +46: [2022-12-02 19:38:03,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt +46: [2022-12-02 19:38:03,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt +46: [2022-12-02 19:38:03,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +46: [2022-12-02 19:38:03,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt +46: [2022-12-02 19:38:03,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +46: [2022-12-02 19:38:03,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +46: [2022-12-02 19:38:03,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt +46: [2022-12-02 19:38:03,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +46: [2022-12-02 19:38:03,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +46: [2022-12-02 19:38:03,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt +46: [2022-12-02 19:38:03,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +46: [2022-12-02 19:38:03,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +46: [2022-12-02 19:38:03,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +15: [2022-12-02 19:38:03,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-12-02 19:38:03,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-12-02 19:38:03,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-12-02 19:38:03,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-12-02 19:38:03,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-12-02 19:38:03,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-12-02 19:38:03,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-12-02 19:38:03,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-12-02 19:38:03,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-12-02 19:38:03,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-12-02 19:38:03,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-12-02 19:38:03,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-12-02 19:38:03,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-12-02 19:38:03,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +15: [2022-12-02 19:38:03,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +15: [2022-12-02 19:38:03,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-12-02 19:38:03,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-12-02 19:38:03,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +15: [2022-12-02 19:38:03,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +15: [2022-12-02 19:38:03,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-12-02 19:38:03,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +15: [2022-12-02 19:38:03,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +15: [2022-12-02 19:38:03,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +15: [2022-12-02 19:38:03,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +49: [2022-12-02 19:38:03,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt. +49: [2022-12-02 19:38:03,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt. +49: [2022-12-02 19:38:03,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt. +49: [2022-12-02 19:38:03,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt. +49: [2022-12-02 19:38:03,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt. +49: [2022-12-02 19:38:03,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt. +49: [2022-12-02 19:38:03,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt. +49: [2022-12-02 19:38:03,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt +49: [2022-12-02 19:38:03,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt +49: [2022-12-02 19:38:03,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt +49: [2022-12-02 19:38:03,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt +49: [2022-12-02 19:38:03,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt +49: [2022-12-02 19:38:03,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt +49: [2022-12-02 19:38:03,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt +49: [2022-12-02 19:38:03,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +49: [2022-12-02 19:38:03,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +49: [2022-12-02 19:38:03,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +49: [2022-12-02 19:38:03,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +49: [2022-12-02 19:38:03,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +49: [2022-12-02 19:38:03,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +49: [2022-12-02 19:38:03,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +50: [2022-12-02 19:38:03,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt. +50: [2022-12-02 19:38:03,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt. +50: [2022-12-02 19:38:03,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt. +50: [2022-12-02 19:38:03,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt. +47: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt. +47: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt. +47: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt. +47: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt. +47: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt. +50: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt. +50: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt. +47: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt. +47: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt. +50: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt. +50: [2022-12-02 19:38:03,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt +50: [2022-12-02 19:38:03,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt +50: [2022-12-02 19:38:03,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt +50: [2022-12-02 19:38:03,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt +47: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt. +50: [2022-12-02 19:38:03,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt +50: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +50: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +50: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +50: [2022-12-02 19:38:03,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt +50: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +47: [2022-12-02 19:38:03,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt +47: [2022-12-02 19:38:03,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt +47: [2022-12-02 19:38:03,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt +47: [2022-12-02 19:38:03,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt +47: [2022-12-02 19:38:03,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt +50: [2022-12-02 19:38:03,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt +47: [2022-12-02 19:38:03,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt +47: [2022-12-02 19:38:03,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt +50: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +47: [2022-12-02 19:38:03,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt +47: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +50: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +47: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +47: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +50: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +47: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +47: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +50: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt. +47: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +47: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +50: [2022-12-02 19:38:03,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt +47: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +50: [2022-12-02 19:38:03,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +23: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +23: [2022-12-02 19:38:03,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-12-02 19:38:03,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-12-02 19:38:03,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +23: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +23: [2022-12-02 19:38:03,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-12-02 19:38:03,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +27: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +23: [2022-12-02 19:38:03,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +27: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +23: [2022-12-02 19:38:03,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +27: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-12-02 19:38:03,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +23: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +23: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +23: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +27: [2022-12-02 19:38:03,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +23: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +27: [2022-12-02 19:38:03,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-12-02 19:38:03,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-12-02 19:38:03,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-12-02 19:38:03,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +27: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +27: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +27: [2022-12-02 19:38:03,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-12-02 19:38:03,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +27: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +27: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +27: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +27: [2022-12-02 19:38:03,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +62: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt. +62: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt. +62: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt. +62: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt. +62: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt. +62: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt. +62: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt. +62: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt. +62: [2022-12-02 19:38:03,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt +62: [2022-12-02 19:38:03,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt +62: [2022-12-02 19:38:03,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt +62: [2022-12-02 19:38:03,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt +62: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +62: [2022-12-02 19:38:03,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt +62: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +62: [2022-12-02 19:38:03,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt +62: [2022-12-02 19:38:03,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt +62: [2022-12-02 19:38:03,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt +49: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt. +62: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +49: [2022-12-02 19:38:03,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt +62: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +49: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +62: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +62: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +62: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +62: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +56: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt. +56: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt. +56: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt. +56: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt. +56: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt. +56: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt. +56: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt. +56: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt. +56: [2022-12-02 19:38:03,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt +56: [2022-12-02 19:38:03,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt +56: [2022-12-02 19:38:03,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt +56: [2022-12-02 19:38:03,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt +56: [2022-12-02 19:38:03,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt +56: [2022-12-02 19:38:03,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt +56: [2022-12-02 19:38:03,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt +56: [2022-12-02 19:38:03,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt +56: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +56: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +56: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +56: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +56: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +56: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +56: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +56: [2022-12-02 19:38:03,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 6: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-12-02 19:38:03,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-12-02 19:38:03,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 3: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 6: [2022-12-02 19:38:03,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-12-02 19:38:03,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-12-02 19:38:03,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-12-02 19:38:03,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-12-02 19:38:03,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 3: [2022-12-02 19:38:03,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-12-02 19:38:03,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-12-02 19:38:03,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-12-02 19:38:03,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-12-02 19:38:03,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 6: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 3: [2022-12-02 19:38:03,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-12-02 19:38:03,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-12-02 19:38:03,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 6: [2022-12-02 19:38:03,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 6: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 6: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 6: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 6: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 6: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 3: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 3: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 3: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 6: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 3: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 3: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 3: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 3: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 3: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +60: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt. +60: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt. +11: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +60: [2022-12-02 19:38:03,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt +60: [2022-12-02 19:38:03,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt +11: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +60: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt. +60: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt. +60: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt. +11: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-12-02 19:38:03,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +60: [2022-12-02 19:38:03,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +11: [2022-12-02 19:38:03,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +60: [2022-12-02 19:38:03,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +60: [2022-12-02 19:38:03,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt +60: [2022-12-02 19:38:03,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt +60: [2022-12-02 19:38:03,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt +11: [2022-12-02 19:38:03,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +60: [2022-12-02 19:38:03,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt. +60: [2022-12-02 19:38:03,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt. +60: [2022-12-02 19:38:03,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt. +11: [2022-12-02 19:38:03,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-12-02 19:38:03,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-12-02 19:38:03,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-12-02 19:38:03,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-12-02 19:38:03,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +60: [2022-12-02 19:38:03,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +60: [2022-12-02 19:38:03,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +60: [2022-12-02 19:38:03,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +11: [2022-12-02 19:38:03,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +60: [2022-12-02 19:38:03,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt +60: [2022-12-02 19:38:03,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt +60: [2022-12-02 19:38:03,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt +11: [2022-12-02 19:38:03,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +11: [2022-12-02 19:38:03,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +11: [2022-12-02 19:38:03,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +11: [2022-12-02 19:38:03,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +11: [2022-12-02 19:38:03,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +60: [2022-12-02 19:38:03,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +60: [2022-12-02 19:38:03,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +60: [2022-12-02 19:38:03,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +21: [2022-12-02 19:38:03,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +11: [2022-12-02 19:38:03,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +21: [2022-12-02 19:38:03,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +11: [2022-12-02 19:38:03,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +21: [2022-12-02 19:38:03,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +11: [2022-12-02 19:38:03,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +57: [2022-12-02 19:38:03,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt. +21: [2022-12-02 19:38:03,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-12-02 19:38:03,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-12-02 19:38:03,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +57: [2022-12-02 19:38:03,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt. +57: [2022-12-02 19:38:03,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt. + 7: [2022-12-02 19:38:03,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-12-02 19:38:03,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-12-02 19:38:03,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-12-02 19:38:03,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +57: [2022-12-02 19:38:03,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt + 7: [2022-12-02 19:38:03,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-12-02 19:38:03,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-12-02 19:38:03,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-12-02 19:38:03,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-12-02 19:38:03,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +57: [2022-12-02 19:38:03,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 7: [2022-12-02 19:38:03,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-12-02 19:38:03,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-12-02 19:38:03,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-12-02 19:38:03,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 7: [2022-12-02 19:38:03,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 7: [2022-12-02 19:38:03,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +57: [2022-12-02 19:38:03,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt +57: [2022-12-02 19:38:03,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt + 7: [2022-12-02 19:38:03,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +57: [2022-12-02 19:38:03,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt. + 7: [2022-12-02 19:38:03,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 7: [2022-12-02 19:38:03,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +57: [2022-12-02 19:38:03,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt. +57: [2022-12-02 19:38:03,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 7: [2022-12-02 19:38:03,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 7: [2022-12-02 19:38:03,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 7: [2022-12-02 19:38:03,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +57: [2022-12-02 19:38:03,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +57: [2022-12-02 19:38:03,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt +57: [2022-12-02 19:38:03,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt +57: [2022-12-02 19:38:03,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +57: [2022-12-02 19:38:03,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt. +57: [2022-12-02 19:38:03,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +57: [2022-12-02 19:38:03,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt +57: [2022-12-02 19:38:03,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +57: [2022-12-02 19:38:03,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt. +57: [2022-12-02 19:38:03,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt. +57: [2022-12-02 19:38:03,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt +57: [2022-12-02 19:38:03,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt +57: [2022-12-02 19:38:03,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +57: [2022-12-02 19:38:03,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 7: [2022-12-02 19:38:03,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-12-02 19:38:03,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-12-02 19:38:03,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +38: [2022-12-02 19:38:03,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt. +38: [2022-12-02 19:38:03,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt. +38: [2022-12-02 19:38:03,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt. +38: [2022-12-02 19:38:03,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt. +38: [2022-12-02 19:38:03,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt. +38: [2022-12-02 19:38:03,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt. +38: [2022-12-02 19:38:03,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt. +38: [2022-12-02 19:38:03,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt. +38: [2022-12-02 19:38:03,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt +38: [2022-12-02 19:38:03,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt +38: [2022-12-02 19:38:03,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt +38: [2022-12-02 19:38:03,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt +38: [2022-12-02 19:38:03,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt +38: [2022-12-02 19:38:03,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt +38: [2022-12-02 19:38:03,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt +38: [2022-12-02 19:38:03,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt +38: [2022-12-02 19:38:03,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +38: [2022-12-02 19:38:03,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +38: [2022-12-02 19:38:03,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +38: [2022-12-02 19:38:03,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +38: [2022-12-02 19:38:03,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +38: [2022-12-02 19:38:03,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +38: [2022-12-02 19:38:03,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +38: [2022-12-02 19:38:03,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +23: [2022-12-02 19:38:03,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-12-02 19:38:03,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-12-02 19:38:03,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +20: [2022-12-02 19:38:03,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-12-02 19:38:03,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-12-02 19:38:03,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +30: [2022-12-02 19:38:03,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-12-02 19:38:03,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-12-02 19:38:03,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +20: [2022-12-02 19:38:03,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-12-02 19:38:03,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-12-02 19:38:03,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +20: [2022-12-02 19:38:03,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-12-02 19:38:03,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-12-02 19:38:03,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +30: [2022-12-02 19:38:03,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-12-02 19:38:03,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-12-02 19:38:03,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +22: [2022-12-02 19:38:03,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-12-02 19:38:03,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-12-02 19:38:03,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +22: [2022-12-02 19:38:03,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-12-02 19:38:03,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-12-02 19:38:03,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +21: [2022-12-02 19:38:03,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-12-02 19:38:03,829] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-12-02 19:38:03,829] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +24: [2022-12-02 19:38:03,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-12-02 19:38:03,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-12-02 19:38:03,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +24: [2022-12-02 19:38:03,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-12-02 19:38:03,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-12-02 19:38:03,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +25: [2022-12-02 19:38:03,840] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-12-02 19:38:03,840] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-12-02 19:38:03,840] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! +22: [2022-12-02 19:38:03,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +22: [2022-12-02 19:38:03,842] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step50000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +22: [2022-12-02 19:38:03,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step50000 is ready now! + 0: successfully saved checkpoint at iteration 50000 to checkpoints_3b977boscar +63: time (ms) | save-checkpoint: 5287.21 +63: iteration 50010/ 73814 | consumed samples: 25605120 | consumed tokens: 52439285760 | elapsed time per iteration (s): 2.81 | learning rate: 6.316E-05 | global batch size: 512 | lm loss: 1.945174E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 182.312 | TFLOPs: 18.77 | +63: iteration 50020/ 73814 | consumed samples: 25610240 | consumed tokens: 52449771520 | elapsed time per iteration (s): 2.24 | learning rate: 6.312E-05 | global batch size: 512 | lm loss: 1.928272E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.479 | TFLOPs: 23.52 | +63: iteration 50030/ 73814 | consumed samples: 25615360 | consumed tokens: 52460257280 | elapsed time per iteration (s): 2.23 | learning rate: 6.309E-05 | global batch size: 512 | lm loss: 1.936322E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.962 | TFLOPs: 23.67 | +63: iteration 50040/ 73814 | consumed samples: 25620480 | consumed tokens: 52470743040 | elapsed time per iteration (s): 2.25 | learning rate: 6.306E-05 | global batch size: 512 | lm loss: 1.954278E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.269 | TFLOPs: 23.40 | +63: iteration 50050/ 73814 | consumed samples: 25625600 | consumed tokens: 52481228800 | elapsed time per iteration (s): 4.10 | learning rate: 6.302E-05 | global batch size: 512 | lm loss: 1.960914E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 124.978 | TFLOPs: 12.87 | +63: iteration 50060/ 73814 | consumed samples: 25630720 | consumed tokens: 52491714560 | elapsed time per iteration (s): 2.24 | learning rate: 6.299E-05 | global batch size: 512 | lm loss: 1.919016E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.587 | TFLOPs: 23.53 | +63: iteration 50070/ 73814 | consumed samples: 25635840 | consumed tokens: 52502200320 | elapsed time per iteration (s): 2.33 | learning rate: 6.296E-05 | global batch size: 512 | lm loss: 1.922890E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.872 | TFLOPs: 22.63 | +63: iteration 50080/ 73814 | consumed samples: 25640960 | consumed tokens: 52512686080 | elapsed time per iteration (s): 2.29 | learning rate: 6.292E-05 | global batch size: 512 | lm loss: 1.942169E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.355 | TFLOPs: 22.99 | +63: iteration 50090/ 73814 | consumed samples: 25646080 | consumed tokens: 52523171840 | elapsed time per iteration (s): 2.22 | learning rate: 6.289E-05 | global batch size: 512 | lm loss: 1.964405E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.359 | TFLOPs: 23.71 | +63: iteration 50100/ 73814 | consumed samples: 25651200 | consumed tokens: 52533657600 | elapsed time per iteration (s): 2.23 | learning rate: 6.286E-05 | global batch size: 512 | lm loss: 1.962371E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.754 | TFLOPs: 23.65 | +63: iteration 50110/ 73814 | consumed samples: 25656320 | consumed tokens: 52544143360 | elapsed time per iteration (s): 2.31 | learning rate: 6.283E-05 | global batch size: 512 | lm loss: 1.948059E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.082 | TFLOPs: 22.86 | +63: iteration 50120/ 73814 | consumed samples: 25661440 | consumed tokens: 52554629120 | elapsed time per iteration (s): 2.23 | learning rate: 6.279E-05 | global batch size: 512 | lm loss: 1.946236E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.063 | TFLOPs: 23.68 | +63: iteration 50130/ 73814 | consumed samples: 25666560 | consumed tokens: 52565114880 | elapsed time per iteration (s): 2.23 | learning rate: 6.276E-05 | global batch size: 512 | lm loss: 1.946695E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.227 | TFLOPs: 23.60 | +63: iteration 50140/ 73814 | consumed samples: 25671680 | consumed tokens: 52575600640 | elapsed time per iteration (s): 2.23 | learning rate: 6.273E-05 | global batch size: 512 | lm loss: 1.969359E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.168 | TFLOPs: 23.59 | +63: iteration 50150/ 73814 | consumed samples: 25676800 | consumed tokens: 52586086400 | elapsed time per iteration (s): 2.23 | learning rate: 6.269E-05 | global batch size: 512 | lm loss: 1.943064E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.269 | TFLOPs: 23.60 | +63: iteration 50160/ 73814 | consumed samples: 25681920 | consumed tokens: 52596572160 | elapsed time per iteration (s): 2.25 | learning rate: 6.266E-05 | global batch size: 512 | lm loss: 1.958381E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.335 | TFLOPs: 23.40 | +63: iteration 50170/ 73814 | consumed samples: 25687040 | consumed tokens: 52607057920 | elapsed time per iteration (s): 2.23 | learning rate: 6.263E-05 | global batch size: 512 | lm loss: 1.960204E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.154 | TFLOPs: 23.59 | +63: iteration 50180/ 73814 | consumed samples: 25692160 | consumed tokens: 52617543680 | elapsed time per iteration (s): 2.24 | learning rate: 6.260E-05 | global batch size: 512 | lm loss: 1.932442E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.588 | TFLOPs: 23.53 | +63: iteration 50190/ 73814 | consumed samples: 25697280 | consumed tokens: 52628029440 | elapsed time per iteration (s): 2.22 | learning rate: 6.256E-05 | global batch size: 512 | lm loss: 1.932875E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.136 | TFLOPs: 23.69 | +63: iteration 50200/ 73814 | consumed samples: 25702400 | consumed tokens: 52638515200 | elapsed time per iteration (s): 2.23 | learning rate: 6.253E-05 | global batch size: 512 | lm loss: 1.954736E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.976 | TFLOPs: 23.67 | +63: iteration 50210/ 73814 | consumed samples: 25707520 | consumed tokens: 52649000960 | elapsed time per iteration (s): 2.25 | learning rate: 6.250E-05 | global batch size: 512 | lm loss: 1.956839E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.048 | TFLOPs: 23.48 | +63: iteration 50220/ 73814 | consumed samples: 25712640 | consumed tokens: 52659486720 | elapsed time per iteration (s): 2.23 | learning rate: 6.246E-05 | global batch size: 512 | lm loss: 1.924161E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.888 | TFLOPs: 23.67 | +63: iteration 50230/ 73814 | consumed samples: 25717760 | consumed tokens: 52669972480 | elapsed time per iteration (s): 2.38 | learning rate: 6.243E-05 | global batch size: 512 | lm loss: 1.963564E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.803 | TFLOPs: 22.11 | +63: iteration 50240/ 73814 | consumed samples: 25722880 | consumed tokens: 52680458240 | elapsed time per iteration (s): 2.24 | learning rate: 6.240E-05 | global batch size: 512 | lm loss: 1.951978E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.393 | TFLOPs: 23.51 | +63: iteration 50250/ 73814 | consumed samples: 25728000 | consumed tokens: 52690944000 | elapsed time per iteration (s): 2.32 | learning rate: 6.237E-05 | global batch size: 512 | lm loss: 1.957135E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.222 | TFLOPs: 22.67 | +63: iteration 50260/ 73814 | consumed samples: 25733120 | consumed tokens: 52701429760 | elapsed time per iteration (s): 2.23 | learning rate: 6.233E-05 | global batch size: 512 | lm loss: 1.931956E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.606 | TFLOPs: 23.64 | +63: iteration 50270/ 73814 | consumed samples: 25738240 | consumed tokens: 52711915520 | elapsed time per iteration (s): 2.23 | learning rate: 6.230E-05 | global batch size: 512 | lm loss: 1.943884E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.081 | TFLOPs: 23.69 | +63: iteration 50280/ 73814 | consumed samples: 25743360 | consumed tokens: 52722401280 | elapsed time per iteration (s): 2.33 | learning rate: 6.227E-05 | global batch size: 512 | lm loss: 1.960484E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.631 | TFLOPs: 22.61 | +63: iteration 50290/ 73814 | consumed samples: 25748480 | consumed tokens: 52732887040 | elapsed time per iteration (s): 2.35 | learning rate: 6.223E-05 | global batch size: 512 | lm loss: 1.941947E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.325 | TFLOPs: 22.48 | +63: iteration 50300/ 73814 | consumed samples: 25753600 | consumed tokens: 52743372800 | elapsed time per iteration (s): 2.28 | learning rate: 6.220E-05 | global batch size: 512 | lm loss: 1.963794E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.154 | TFLOPs: 23.08 | +63: iteration 50310/ 73814 | consumed samples: 25758720 | consumed tokens: 52753858560 | elapsed time per iteration (s): 2.23 | learning rate: 6.217E-05 | global batch size: 512 | lm loss: 1.928331E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.260 | TFLOPs: 23.60 | +63: iteration 50320/ 73814 | consumed samples: 25763840 | consumed tokens: 52764344320 | elapsed time per iteration (s): 2.35 | learning rate: 6.214E-05 | global batch size: 512 | lm loss: 1.959175E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.083 | TFLOPs: 22.45 | +63: iteration 50330/ 73814 | consumed samples: 25768960 | consumed tokens: 52774830080 | elapsed time per iteration (s): 2.23 | learning rate: 6.210E-05 | global batch size: 512 | lm loss: 1.935435E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.453 | TFLOPs: 23.62 | +63: iteration 50340/ 73814 | consumed samples: 25774080 | consumed tokens: 52785315840 | elapsed time per iteration (s): 2.23 | learning rate: 6.207E-05 | global batch size: 512 | lm loss: 1.950647E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.645 | TFLOPs: 23.64 | +63: iteration 50350/ 73814 | consumed samples: 25779200 | consumed tokens: 52795801600 | elapsed time per iteration (s): 2.24 | learning rate: 6.204E-05 | global batch size: 512 | lm loss: 1.935592E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.866 | TFLOPs: 23.56 | +63: iteration 50360/ 73814 | consumed samples: 25784320 | consumed tokens: 52806287360 | elapsed time per iteration (s): 2.23 | learning rate: 6.200E-05 | global batch size: 512 | lm loss: 1.956160E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.050 | TFLOPs: 23.68 | +63: iteration 50370/ 73814 | consumed samples: 25789440 | consumed tokens: 52816773120 | elapsed time per iteration (s): 2.24 | learning rate: 6.197E-05 | global batch size: 512 | lm loss: 1.953717E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.186 | TFLOPs: 23.49 | +63: iteration 50380/ 73814 | consumed samples: 25794560 | consumed tokens: 52827258880 | elapsed time per iteration (s): 2.22 | learning rate: 6.194E-05 | global batch size: 512 | lm loss: 1.934166E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.347 | TFLOPs: 23.71 | +63: iteration 50390/ 73814 | consumed samples: 25799680 | consumed tokens: 52837744640 | elapsed time per iteration (s): 2.23 | learning rate: 6.191E-05 | global batch size: 512 | lm loss: 1.931324E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.203 | TFLOPs: 23.60 | +63: iteration 50400/ 73814 | consumed samples: 25804800 | consumed tokens: 52848230400 | elapsed time per iteration (s): 2.33 | learning rate: 6.187E-05 | global batch size: 512 | lm loss: 1.942771E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.920 | TFLOPs: 22.64 | +63: iteration 50410/ 73814 | consumed samples: 25809920 | consumed tokens: 52858716160 | elapsed time per iteration (s): 2.23 | learning rate: 6.184E-05 | global batch size: 512 | lm loss: 1.953072E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.534 | TFLOPs: 23.63 | +63: iteration 50420/ 73814 | consumed samples: 25815040 | consumed tokens: 52869201920 | elapsed time per iteration (s): 2.23 | learning rate: 6.181E-05 | global batch size: 512 | lm loss: 1.926800E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.193 | TFLOPs: 23.59 | +63: iteration 50430/ 73814 | consumed samples: 25820160 | consumed tokens: 52879687680 | elapsed time per iteration (s): 2.23 | learning rate: 6.178E-05 | global batch size: 512 | lm loss: 1.957446E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.115 | TFLOPs: 23.59 | +63: iteration 50440/ 73814 | consumed samples: 25825280 | consumed tokens: 52890173440 | elapsed time per iteration (s): 2.32 | learning rate: 6.174E-05 | global batch size: 512 | lm loss: 1.948001E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.022 | TFLOPs: 22.75 | +63: iteration 50450/ 73814 | consumed samples: 25830400 | consumed tokens: 52900659200 | elapsed time per iteration (s): 2.23 | learning rate: 6.171E-05 | global batch size: 512 | lm loss: 1.930078E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.842 | TFLOPs: 23.66 | +63: iteration 50460/ 73814 | consumed samples: 25835520 | consumed tokens: 52911144960 | elapsed time per iteration (s): 2.22 | learning rate: 6.168E-05 | global batch size: 512 | lm loss: 1.952296E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.339 | TFLOPs: 23.71 | +63: iteration 50470/ 73814 | consumed samples: 25840640 | consumed tokens: 52921630720 | elapsed time per iteration (s): 2.24 | learning rate: 6.164E-05 | global batch size: 512 | lm loss: 1.948569E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.102 | TFLOPs: 23.48 | +63: iteration 50480/ 73814 | consumed samples: 25845760 | consumed tokens: 52932116480 | elapsed time per iteration (s): 2.29 | learning rate: 6.161E-05 | global batch size: 512 | lm loss: 1.950515E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.684 | TFLOPs: 23.03 | +63: iteration 50490/ 73814 | consumed samples: 25850880 | consumed tokens: 52942602240 | elapsed time per iteration (s): 2.36 | learning rate: 6.158E-05 | global batch size: 512 | lm loss: 1.952034E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.577 | TFLOPs: 22.30 | +63: iteration 50500/ 73814 | consumed samples: 25856000 | consumed tokens: 52953088000 | elapsed time per iteration (s): 2.25 | learning rate: 6.155E-05 | global batch size: 512 | lm loss: 1.956006E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.499 | TFLOPs: 23.42 | +63: iteration 50510/ 73814 | consumed samples: 25861120 | consumed tokens: 52963573760 | elapsed time per iteration (s): 2.24 | learning rate: 6.151E-05 | global batch size: 512 | lm loss: 1.966831E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.513 | TFLOPs: 23.52 | +63: iteration 50520/ 73814 | consumed samples: 25866240 | consumed tokens: 52974059520 | elapsed time per iteration (s): 2.29 | learning rate: 6.148E-05 | global batch size: 512 | lm loss: 1.924724E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.897 | TFLOPs: 23.05 | +63: iteration 50530/ 73814 | consumed samples: 25871360 | consumed tokens: 52984545280 | elapsed time per iteration (s): 2.23 | learning rate: 6.145E-05 | global batch size: 512 | lm loss: 1.930314E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.947 | TFLOPs: 23.67 | +63: iteration 50540/ 73814 | consumed samples: 25876480 | consumed tokens: 52995031040 | elapsed time per iteration (s): 2.35 | learning rate: 6.142E-05 | global batch size: 512 | lm loss: 1.946327E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.267 | TFLOPs: 22.47 | +63: iteration 50550/ 73814 | consumed samples: 25881600 | consumed tokens: 53005516800 | elapsed time per iteration (s): 2.35 | learning rate: 6.138E-05 | global batch size: 512 | lm loss: 1.950080E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.783 | TFLOPs: 22.42 | +63: iteration 50560/ 73814 | consumed samples: 25886720 | consumed tokens: 53016002560 | elapsed time per iteration (s): 2.23 | learning rate: 6.135E-05 | global batch size: 512 | lm loss: 1.947072E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.963 | TFLOPs: 23.67 | +63: iteration 50570/ 73814 | consumed samples: 25891840 | consumed tokens: 53026488320 | elapsed time per iteration (s): 2.35 | learning rate: 6.132E-05 | global batch size: 512 | lm loss: 1.962756E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.150 | TFLOPs: 22.46 | +63: iteration 50580/ 73814 | consumed samples: 25896960 | consumed tokens: 53036974080 | elapsed time per iteration (s): 2.23 | learning rate: 6.129E-05 | global batch size: 512 | lm loss: 1.937315E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.281 | TFLOPs: 23.60 | +63: iteration 50590/ 73814 | consumed samples: 25902080 | consumed tokens: 53047459840 | elapsed time per iteration (s): 2.24 | learning rate: 6.125E-05 | global batch size: 512 | lm loss: 1.967330E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.932 | TFLOPs: 23.57 | +63: iteration 50600/ 73814 | consumed samples: 25907200 | consumed tokens: 53057945600 | elapsed time per iteration (s): 2.25 | learning rate: 6.122E-05 | global batch size: 512 | lm loss: 1.930242E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.210 | TFLOPs: 23.39 | +63: iteration 50610/ 73814 | consumed samples: 25912320 | consumed tokens: 53068431360 | elapsed time per iteration (s): 2.23 | learning rate: 6.119E-05 | global batch size: 512 | lm loss: 1.913033E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.316 | TFLOPs: 23.61 | +63: iteration 50620/ 73814 | consumed samples: 25917440 | consumed tokens: 53078917120 | elapsed time per iteration (s): 2.25 | learning rate: 6.116E-05 | global batch size: 512 | lm loss: 1.939974E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.614 | TFLOPs: 23.43 | +63: iteration 50630/ 73814 | consumed samples: 25922560 | consumed tokens: 53089402880 | elapsed time per iteration (s): 2.33 | learning rate: 6.112E-05 | global batch size: 512 | lm loss: 1.950524E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.910 | TFLOPs: 22.64 | +63: iteration 50640/ 73814 | consumed samples: 25927680 | consumed tokens: 53099888640 | elapsed time per iteration (s): 2.23 | learning rate: 6.109E-05 | global batch size: 512 | lm loss: 1.951434E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.449 | TFLOPs: 23.62 | +63: iteration 50650/ 73814 | consumed samples: 25932800 | consumed tokens: 53110374400 | elapsed time per iteration (s): 2.25 | learning rate: 6.106E-05 | global batch size: 512 | lm loss: 1.940924E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.344 | TFLOPs: 23.40 | +63: iteration 50660/ 73814 | consumed samples: 25937920 | consumed tokens: 53120860160 | elapsed time per iteration (s): 2.24 | learning rate: 6.103E-05 | global batch size: 512 | lm loss: 1.951483E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.536 | TFLOPs: 23.53 | +63: iteration 50670/ 73814 | consumed samples: 25943040 | consumed tokens: 53131345920 | elapsed time per iteration (s): 2.33 | learning rate: 6.099E-05 | global batch size: 512 | lm loss: 1.939630E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.989 | TFLOPs: 22.65 | +63: iteration 50680/ 73814 | consumed samples: 25948160 | consumed tokens: 53141831680 | elapsed time per iteration (s): 2.26 | learning rate: 6.096E-05 | global batch size: 512 | lm loss: 1.951765E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.644 | TFLOPs: 23.33 | +63: iteration 50690/ 73814 | consumed samples: 25953280 | consumed tokens: 53152317440 | elapsed time per iteration (s): 2.24 | learning rate: 6.093E-05 | global batch size: 512 | lm loss: 1.954727E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.252 | TFLOPs: 23.50 | +63: iteration 50700/ 73814 | consumed samples: 25958400 | consumed tokens: 53162803200 | elapsed time per iteration (s): 2.24 | learning rate: 6.090E-05 | global batch size: 512 | lm loss: 1.959420E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.241 | TFLOPs: 23.50 | +63: iteration 50710/ 73814 | consumed samples: 25963520 | consumed tokens: 53173288960 | elapsed time per iteration (s): 2.25 | learning rate: 6.086E-05 | global batch size: 512 | lm loss: 1.956569E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.587 | TFLOPs: 23.43 | +63: iteration 50720/ 73814 | consumed samples: 25968640 | consumed tokens: 53183774720 | elapsed time per iteration (s): 2.24 | learning rate: 6.083E-05 | global batch size: 512 | lm loss: 1.952401E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.320 | TFLOPs: 23.50 | +63: iteration 50730/ 73814 | consumed samples: 25973760 | consumed tokens: 53194260480 | elapsed time per iteration (s): 2.23 | learning rate: 6.080E-05 | global batch size: 512 | lm loss: 1.958371E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.608 | TFLOPs: 23.64 | +63: iteration 50740/ 73814 | consumed samples: 25978880 | consumed tokens: 53204746240 | elapsed time per iteration (s): 2.25 | learning rate: 6.077E-05 | global batch size: 512 | lm loss: 1.948645E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.286 | TFLOPs: 23.40 | +63: iteration 50750/ 73814 | consumed samples: 25984000 | consumed tokens: 53215232000 | elapsed time per iteration (s): 2.23 | learning rate: 6.073E-05 | global batch size: 512 | lm loss: 1.963708E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.893 | TFLOPs: 23.67 | +63: iteration 50760/ 73814 | consumed samples: 25989120 | consumed tokens: 53225717760 | elapsed time per iteration (s): 2.23 | learning rate: 6.070E-05 | global batch size: 512 | lm loss: 1.927275E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.403 | TFLOPs: 23.62 | +63: iteration 50770/ 73814 | consumed samples: 25994240 | consumed tokens: 53236203520 | elapsed time per iteration (s): 2.25 | learning rate: 6.067E-05 | global batch size: 512 | lm loss: 1.947353E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.183 | TFLOPs: 23.39 | +63: iteration 50780/ 73814 | consumed samples: 25999360 | consumed tokens: 53246689280 | elapsed time per iteration (s): 2.23 | learning rate: 6.064E-05 | global batch size: 512 | lm loss: 1.957994E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.666 | TFLOPs: 23.64 | +63: iteration 50790/ 73814 | consumed samples: 26004480 | consumed tokens: 53257175040 | elapsed time per iteration (s): 2.25 | learning rate: 6.061E-05 | global batch size: 512 | lm loss: 1.916101E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.054 | TFLOPs: 23.48 | +63: iteration 50800/ 73814 | consumed samples: 26009600 | consumed tokens: 53267660800 | elapsed time per iteration (s): 2.27 | learning rate: 6.057E-05 | global batch size: 512 | lm loss: 1.958010E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.251 | TFLOPs: 23.19 | +63: iteration 50810/ 73814 | consumed samples: 26014720 | consumed tokens: 53278146560 | elapsed time per iteration (s): 2.29 | learning rate: 6.054E-05 | global batch size: 512 | lm loss: 1.929298E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.887 | TFLOPs: 23.05 | +63: iteration 50820/ 73814 | consumed samples: 26019840 | consumed tokens: 53288632320 | elapsed time per iteration (s): 2.26 | learning rate: 6.051E-05 | global batch size: 512 | lm loss: 1.935910E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.651 | TFLOPs: 23.33 | +63: iteration 50830/ 73814 | consumed samples: 26024960 | consumed tokens: 53299118080 | elapsed time per iteration (s): 2.26 | learning rate: 6.048E-05 | global batch size: 512 | lm loss: 1.944824E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.511 | TFLOPs: 23.32 | +63: iteration 50840/ 73814 | consumed samples: 26030080 | consumed tokens: 53309603840 | elapsed time per iteration (s): 2.47 | learning rate: 6.044E-05 | global batch size: 512 | lm loss: 1.950073E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 207.240 | TFLOPs: 21.33 | +63: iteration 50850/ 73814 | consumed samples: 26035200 | consumed tokens: 53320089600 | elapsed time per iteration (s): 2.26 | learning rate: 6.041E-05 | global batch size: 512 | lm loss: 1.929485E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.314 | TFLOPs: 23.30 | +63: iteration 50860/ 73814 | consumed samples: 26040320 | consumed tokens: 53330575360 | elapsed time per iteration (s): 2.36 | learning rate: 6.038E-05 | global batch size: 512 | lm loss: 1.945950E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.354 | TFLOPs: 22.38 | +63: iteration 50870/ 73814 | consumed samples: 26045440 | consumed tokens: 53341061120 | elapsed time per iteration (s): 2.54 | learning rate: 6.035E-05 | global batch size: 512 | lm loss: 1.940420E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.611 | TFLOPs: 20.75 | +63: iteration 50880/ 73814 | consumed samples: 26050560 | consumed tokens: 53351546880 | elapsed time per iteration (s): 2.66 | learning rate: 6.031E-05 | global batch size: 512 | lm loss: 1.950552E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 192.558 | TFLOPs: 19.82 | +63: iteration 50890/ 73814 | consumed samples: 26055680 | consumed tokens: 53362032640 | elapsed time per iteration (s): 2.60 | learning rate: 6.028E-05 | global batch size: 512 | lm loss: 1.915129E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 196.930 | TFLOPs: 20.27 | +63: iteration 50900/ 73814 | consumed samples: 26060800 | consumed tokens: 53372518400 | elapsed time per iteration (s): 2.82 | learning rate: 6.025E-05 | global batch size: 512 | lm loss: 1.931508E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 181.650 | TFLOPs: 18.70 | +63: iteration 50910/ 73814 | consumed samples: 26065920 | consumed tokens: 53383004160 | elapsed time per iteration (s): 2.26 | learning rate: 6.022E-05 | global batch size: 512 | lm loss: 1.942047E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.550 | TFLOPs: 23.32 | +63: iteration 50920/ 73814 | consumed samples: 26071040 | consumed tokens: 53393489920 | elapsed time per iteration (s): 2.32 | learning rate: 6.019E-05 | global batch size: 512 | lm loss: 1.941361E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.069 | TFLOPs: 22.76 | +63: iteration 50930/ 73814 | consumed samples: 26076160 | consumed tokens: 53403975680 | elapsed time per iteration (s): 2.41 | learning rate: 6.015E-05 | global batch size: 512 | lm loss: 1.942079E+00 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.063 | TFLOPs: 21.83 | +63: iteration 50940/ 73814 | consumed samples: 26081280 | consumed tokens: 53414461440 | elapsed time per iteration (s): 2.28 | learning rate: 6.012E-05 | global batch size: 512 | lm loss: 1.964945E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.709 | TFLOPs: 23.13 | +63: iteration 50950/ 73814 | consumed samples: 26086400 | consumed tokens: 53424947200 | elapsed time per iteration (s): 2.24 | learning rate: 6.009E-05 | global batch size: 512 | lm loss: 1.957165E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.669 | TFLOPs: 23.54 | +63: iteration 50960/ 73814 | consumed samples: 26091520 | consumed tokens: 53435432960 | elapsed time per iteration (s): 2.25 | learning rate: 6.006E-05 | global batch size: 512 | lm loss: 1.945794E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.902 | TFLOPs: 23.46 | +63: iteration 50970/ 73814 | consumed samples: 26096640 | consumed tokens: 53445918720 | elapsed time per iteration (s): 2.28 | learning rate: 6.002E-05 | global batch size: 512 | lm loss: 1.967679E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.599 | TFLOPs: 23.12 | +63: iteration 50980/ 73814 | consumed samples: 26101760 | consumed tokens: 53456404480 | elapsed time per iteration (s): 2.23 | learning rate: 5.999E-05 | global batch size: 512 | lm loss: 1.930412E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.013 | TFLOPs: 23.68 | +63: iteration 50990/ 73814 | consumed samples: 26106880 | consumed tokens: 53466890240 | elapsed time per iteration (s): 2.23 | learning rate: 5.996E-05 | global batch size: 512 | lm loss: 1.947653E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.681 | TFLOPs: 23.64 | +63: iteration 51000/ 73814 | consumed samples: 26112000 | consumed tokens: 53477376000 | elapsed time per iteration (s): 2.43 | learning rate: 5.993E-05 | global batch size: 512 | lm loss: 1.958498E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.829 | TFLOPs: 21.70 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 51000 | lm loss value: 1.913448E+00 | lm loss PPL: 6.776411E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 51010/ 73814 | consumed samples: 26117120 | consumed tokens: 53487861760 | elapsed time per iteration (s): 2.29 | learning rate: 5.990E-05 | global batch size: 512 | lm loss: 1.957352E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.019 | TFLOPs: 23.06 | +63: iteration 51020/ 73814 | consumed samples: 26122240 | consumed tokens: 53498347520 | elapsed time per iteration (s): 2.22 | learning rate: 5.986E-05 | global batch size: 512 | lm loss: 1.946609E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.250 | TFLOPs: 23.70 | +63: iteration 51030/ 73814 | consumed samples: 26127360 | consumed tokens: 53508833280 | elapsed time per iteration (s): 2.23 | learning rate: 5.983E-05 | global batch size: 512 | lm loss: 1.949499E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.932 | TFLOPs: 23.67 | +63: iteration 51040/ 73814 | consumed samples: 26132480 | consumed tokens: 53519319040 | elapsed time per iteration (s): 2.52 | learning rate: 5.980E-05 | global batch size: 512 | lm loss: 1.945708E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 203.067 | TFLOPs: 20.90 | +63: iteration 51050/ 73814 | consumed samples: 26137600 | consumed tokens: 53529804800 | elapsed time per iteration (s): 2.27 | learning rate: 5.977E-05 | global batch size: 512 | lm loss: 1.940715E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.435 | TFLOPs: 23.21 | +63: iteration 51060/ 73814 | consumed samples: 26142720 | consumed tokens: 53540290560 | elapsed time per iteration (s): 2.34 | learning rate: 5.974E-05 | global batch size: 512 | lm loss: 1.945725E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.456 | TFLOPs: 22.49 | +63: iteration 51070/ 73814 | consumed samples: 26147840 | consumed tokens: 53550776320 | elapsed time per iteration (s): 2.24 | learning rate: 5.970E-05 | global batch size: 512 | lm loss: 1.924157E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.096 | TFLOPs: 23.48 | +63: iteration 51080/ 73814 | consumed samples: 26152960 | consumed tokens: 53561262080 | elapsed time per iteration (s): 2.25 | learning rate: 5.967E-05 | global batch size: 512 | lm loss: 1.964666E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.778 | TFLOPs: 23.45 | +63: iteration 51090/ 73814 | consumed samples: 26158080 | consumed tokens: 53571747840 | elapsed time per iteration (s): 2.24 | learning rate: 5.964E-05 | global batch size: 512 | lm loss: 1.944798E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.044 | TFLOPs: 23.58 | +63: iteration 51100/ 73814 | consumed samples: 26163200 | consumed tokens: 53582233600 | elapsed time per iteration (s): 7.21 | learning rate: 5.961E-05 | global batch size: 512 | lm loss: 1.944044E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 71.027 | TFLOPs: 7.31 | +63: iteration 51110/ 73814 | consumed samples: 26168320 | consumed tokens: 53592719360 | elapsed time per iteration (s): 2.24 | learning rate: 5.958E-05 | global batch size: 512 | lm loss: 1.929614E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.310 | TFLOPs: 23.50 | +63: iteration 51120/ 73814 | consumed samples: 26173440 | consumed tokens: 53603205120 | elapsed time per iteration (s): 2.22 | learning rate: 5.954E-05 | global batch size: 512 | lm loss: 1.961445E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.250 | TFLOPs: 23.70 | +63: iteration 51130/ 73814 | consumed samples: 26178560 | consumed tokens: 53613690880 | elapsed time per iteration (s): 2.22 | learning rate: 5.951E-05 | global batch size: 512 | lm loss: 1.965232E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.337 | TFLOPs: 23.71 | +63: iteration 51140/ 73814 | consumed samples: 26183680 | consumed tokens: 53624176640 | elapsed time per iteration (s): 2.24 | learning rate: 5.948E-05 | global batch size: 512 | lm loss: 1.941422E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.407 | TFLOPs: 23.51 | +63: iteration 51150/ 73814 | consumed samples: 26188800 | consumed tokens: 53634662400 | elapsed time per iteration (s): 2.24 | learning rate: 5.945E-05 | global batch size: 512 | lm loss: 1.963037E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.130 | TFLOPs: 23.48 | +63: iteration 51160/ 73814 | consumed samples: 26193920 | consumed tokens: 53645148160 | elapsed time per iteration (s): 2.23 | learning rate: 5.941E-05 | global batch size: 512 | lm loss: 1.929578E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.768 | TFLOPs: 23.65 | +63: iteration 51170/ 73814 | consumed samples: 26199040 | consumed tokens: 53655633920 | elapsed time per iteration (s): 2.24 | learning rate: 5.938E-05 | global batch size: 512 | lm loss: 1.956476E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.015 | TFLOPs: 23.58 | +63: iteration 51180/ 73814 | consumed samples: 26204160 | consumed tokens: 53666119680 | elapsed time per iteration (s): 2.38 | learning rate: 5.935E-05 | global batch size: 512 | lm loss: 1.956258E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.293 | TFLOPs: 22.16 | +63: iteration 51190/ 73814 | consumed samples: 26209280 | consumed tokens: 53676605440 | elapsed time per iteration (s): 2.25 | learning rate: 5.932E-05 | global batch size: 512 | lm loss: 1.948766E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.464 | TFLOPs: 23.42 | +63: iteration 51200/ 73814 | consumed samples: 26214400 | consumed tokens: 53687091200 | elapsed time per iteration (s): 2.28 | learning rate: 5.929E-05 | global batch size: 512 | lm loss: 1.964852E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.947 | TFLOPs: 23.16 | +63: iteration 51210/ 73814 | consumed samples: 26219520 | consumed tokens: 53697576960 | elapsed time per iteration (s): 2.23 | learning rate: 5.926E-05 | global batch size: 512 | lm loss: 1.953189E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.064 | TFLOPs: 23.68 | +63: iteration 51220/ 73814 | consumed samples: 26224640 | consumed tokens: 53708062720 | elapsed time per iteration (s): 2.25 | learning rate: 5.922E-05 | global batch size: 512 | lm loss: 1.955461E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.590 | TFLOPs: 23.43 | +63: iteration 51230/ 73814 | consumed samples: 26229760 | consumed tokens: 53718548480 | elapsed time per iteration (s): 2.23 | learning rate: 5.919E-05 | global batch size: 512 | lm loss: 1.939620E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.739 | TFLOPs: 23.65 | +63: iteration 51240/ 73814 | consumed samples: 26234880 | consumed tokens: 53729034240 | elapsed time per iteration (s): 2.27 | learning rate: 5.916E-05 | global batch size: 512 | lm loss: 1.946191E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.501 | TFLOPs: 23.21 | +63: iteration 51250/ 73814 | consumed samples: 26240000 | consumed tokens: 53739520000 | elapsed time per iteration (s): 2.23 | learning rate: 5.913E-05 | global batch size: 512 | lm loss: 1.941094E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.769 | TFLOPs: 23.65 | +63: iteration 51260/ 73814 | consumed samples: 26245120 | consumed tokens: 53750005760 | elapsed time per iteration (s): 2.24 | learning rate: 5.910E-05 | global batch size: 512 | lm loss: 1.928513E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.105 | TFLOPs: 23.48 | +63: iteration 51270/ 73814 | consumed samples: 26250240 | consumed tokens: 53760491520 | elapsed time per iteration (s): 2.23 | learning rate: 5.906E-05 | global batch size: 512 | lm loss: 1.939338E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.791 | TFLOPs: 23.66 | +63: iteration 51280/ 73814 | consumed samples: 26255360 | consumed tokens: 53770977280 | elapsed time per iteration (s): 2.26 | learning rate: 5.903E-05 | global batch size: 512 | lm loss: 1.962644E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.520 | TFLOPs: 23.32 | +63: iteration 51290/ 73814 | consumed samples: 26260480 | consumed tokens: 53781463040 | elapsed time per iteration (s): 2.23 | learning rate: 5.900E-05 | global batch size: 512 | lm loss: 1.946831E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.934 | TFLOPs: 23.67 | +63: iteration 51300/ 73814 | consumed samples: 26265600 | consumed tokens: 53791948800 | elapsed time per iteration (s): 2.23 | learning rate: 5.897E-05 | global batch size: 512 | lm loss: 1.940291E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.106 | TFLOPs: 23.69 | +63: iteration 51310/ 73814 | consumed samples: 26270720 | consumed tokens: 53802434560 | elapsed time per iteration (s): 2.24 | learning rate: 5.894E-05 | global batch size: 512 | lm loss: 1.931904E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.412 | TFLOPs: 23.51 | +63: iteration 51320/ 73814 | consumed samples: 26275840 | consumed tokens: 53812920320 | elapsed time per iteration (s): 2.38 | learning rate: 5.890E-05 | global batch size: 512 | lm loss: 1.951108E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.246 | TFLOPs: 22.16 | +63: iteration 51330/ 73814 | consumed samples: 26280960 | consumed tokens: 53823406080 | elapsed time per iteration (s): 2.23 | learning rate: 5.887E-05 | global batch size: 512 | lm loss: 1.928338E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.285 | TFLOPs: 23.60 | +63: iteration 51340/ 73814 | consumed samples: 26286080 | consumed tokens: 53833891840 | elapsed time per iteration (s): 2.25 | learning rate: 5.884E-05 | global batch size: 512 | lm loss: 1.946761E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.683 | TFLOPs: 23.44 | +63: iteration 51350/ 73814 | consumed samples: 26291200 | consumed tokens: 53844377600 | elapsed time per iteration (s): 2.25 | learning rate: 5.881E-05 | global batch size: 512 | lm loss: 1.922523E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.159 | TFLOPs: 23.38 | +63: iteration 51360/ 73814 | consumed samples: 26296320 | consumed tokens: 53854863360 | elapsed time per iteration (s): 2.23 | learning rate: 5.878E-05 | global batch size: 512 | lm loss: 1.915178E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.524 | TFLOPs: 23.63 | +63: iteration 51370/ 73814 | consumed samples: 26301440 | consumed tokens: 53865349120 | elapsed time per iteration (s): 2.23 | learning rate: 5.874E-05 | global batch size: 512 | lm loss: 1.937515E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.100 | TFLOPs: 23.58 | +63: iteration 51380/ 73814 | consumed samples: 26306560 | consumed tokens: 53875834880 | elapsed time per iteration (s): 2.23 | learning rate: 5.871E-05 | global batch size: 512 | lm loss: 1.955950E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.732 | TFLOPs: 23.65 | +63: iteration 51390/ 73814 | consumed samples: 26311680 | consumed tokens: 53886320640 | elapsed time per iteration (s): 2.24 | learning rate: 5.868E-05 | global batch size: 512 | lm loss: 1.914932E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.078 | TFLOPs: 23.48 | +63: iteration 51400/ 73814 | consumed samples: 26316800 | consumed tokens: 53896806400 | elapsed time per iteration (s): 2.23 | learning rate: 5.865E-05 | global batch size: 512 | lm loss: 1.923271E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.673 | TFLOPs: 23.64 | +63: iteration 51410/ 73814 | consumed samples: 26321920 | consumed tokens: 53907292160 | elapsed time per iteration (s): 2.24 | learning rate: 5.862E-05 | global batch size: 512 | lm loss: 1.962833E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.360 | TFLOPs: 23.51 | +63: iteration 51420/ 73814 | consumed samples: 26327040 | consumed tokens: 53917777920 | elapsed time per iteration (s): 2.24 | learning rate: 5.859E-05 | global batch size: 512 | lm loss: 1.960547E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.176 | TFLOPs: 23.49 | +63: iteration 51430/ 73814 | consumed samples: 26332160 | consumed tokens: 53928263680 | elapsed time per iteration (s): 2.23 | learning rate: 5.855E-05 | global batch size: 512 | lm loss: 1.930863E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.002 | TFLOPs: 23.68 | +63: iteration 51440/ 73814 | consumed samples: 26337280 | consumed tokens: 53938749440 | elapsed time per iteration (s): 2.24 | learning rate: 5.852E-05 | global batch size: 512 | lm loss: 1.932382E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.479 | TFLOPs: 23.52 | +63: iteration 51450/ 73814 | consumed samples: 26342400 | consumed tokens: 53949235200 | elapsed time per iteration (s): 2.22 | learning rate: 5.849E-05 | global batch size: 512 | lm loss: 1.905140E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.278 | TFLOPs: 23.71 | +63: iteration 51460/ 73814 | consumed samples: 26347520 | consumed tokens: 53959720960 | elapsed time per iteration (s): 2.23 | learning rate: 5.846E-05 | global batch size: 512 | lm loss: 1.962735E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.558 | TFLOPs: 23.63 | +63: iteration 51470/ 73814 | consumed samples: 26352640 | consumed tokens: 53970206720 | elapsed time per iteration (s): 2.24 | learning rate: 5.843E-05 | global batch size: 512 | lm loss: 1.934006E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.613 | TFLOPs: 23.53 | +63: iteration 51480/ 73814 | consumed samples: 26357760 | consumed tokens: 53980692480 | elapsed time per iteration (s): 2.23 | learning rate: 5.840E-05 | global batch size: 512 | lm loss: 1.959295E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.194 | TFLOPs: 23.59 | +63: iteration 51490/ 73814 | consumed samples: 26362880 | consumed tokens: 53991178240 | elapsed time per iteration (s): 2.24 | learning rate: 5.836E-05 | global batch size: 512 | lm loss: 1.926705E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.898 | TFLOPs: 23.56 | +63: iteration 51500/ 73814 | consumed samples: 26368000 | consumed tokens: 54001664000 | elapsed time per iteration (s): 2.22 | learning rate: 5.833E-05 | global batch size: 512 | lm loss: 1.930468E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.420 | TFLOPs: 23.72 | +63: iteration 51510/ 73814 | consumed samples: 26373120 | consumed tokens: 54012149760 | elapsed time per iteration (s): 2.32 | learning rate: 5.830E-05 | global batch size: 512 | lm loss: 1.941790E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.078 | TFLOPs: 22.76 | +63: iteration 51520/ 73814 | consumed samples: 26378240 | consumed tokens: 54022635520 | elapsed time per iteration (s): 2.23 | learning rate: 5.827E-05 | global batch size: 512 | lm loss: 1.918109E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.299 | TFLOPs: 23.61 | +63: iteration 51530/ 73814 | consumed samples: 26383360 | consumed tokens: 54033121280 | elapsed time per iteration (s): 2.25 | learning rate: 5.824E-05 | global batch size: 512 | lm loss: 1.926503E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.368 | TFLOPs: 23.41 | +63: iteration 51540/ 73814 | consumed samples: 26388480 | consumed tokens: 54043607040 | elapsed time per iteration (s): 2.23 | learning rate: 5.821E-05 | global batch size: 512 | lm loss: 1.941798E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.348 | TFLOPs: 23.61 | +63: iteration 51550/ 73814 | consumed samples: 26393600 | consumed tokens: 54054092800 | elapsed time per iteration (s): 2.24 | learning rate: 5.817E-05 | global batch size: 512 | lm loss: 1.943708E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.267 | TFLOPs: 23.50 | +63: iteration 51560/ 73814 | consumed samples: 26398720 | consumed tokens: 54064578560 | elapsed time per iteration (s): 2.23 | learning rate: 5.814E-05 | global batch size: 512 | lm loss: 1.938730E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.797 | TFLOPs: 23.66 | +63: iteration 51570/ 73814 | consumed samples: 26403840 | consumed tokens: 54075064320 | elapsed time per iteration (s): 2.45 | learning rate: 5.811E-05 | global batch size: 512 | lm loss: 1.946920E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.965 | TFLOPs: 21.51 | +63: iteration 51580/ 73814 | consumed samples: 26408960 | consumed tokens: 54085550080 | elapsed time per iteration (s): 2.30 | learning rate: 5.808E-05 | global batch size: 512 | lm loss: 1.935201E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.502 | TFLOPs: 22.91 | +63: iteration 51590/ 73814 | consumed samples: 26414080 | consumed tokens: 54096035840 | elapsed time per iteration (s): 2.46 | learning rate: 5.805E-05 | global batch size: 512 | lm loss: 1.946252E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.463 | TFLOPs: 21.46 | +63: iteration 51600/ 73814 | consumed samples: 26419200 | consumed tokens: 54106521600 | elapsed time per iteration (s): 2.23 | learning rate: 5.802E-05 | global batch size: 512 | lm loss: 1.939457E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.698 | TFLOPs: 23.65 | +63: iteration 51610/ 73814 | consumed samples: 26424320 | consumed tokens: 54117007360 | elapsed time per iteration (s): 2.23 | learning rate: 5.798E-05 | global batch size: 512 | lm loss: 1.941852E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.833 | TFLOPs: 23.66 | +63: iteration 51620/ 73814 | consumed samples: 26429440 | consumed tokens: 54127493120 | elapsed time per iteration (s): 2.23 | learning rate: 5.795E-05 | global batch size: 512 | lm loss: 1.922500E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.568 | TFLOPs: 23.63 | +63: iteration 51630/ 73814 | consumed samples: 26434560 | consumed tokens: 54137978880 | elapsed time per iteration (s): 2.29 | learning rate: 5.792E-05 | global batch size: 512 | lm loss: 1.936418E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.649 | TFLOPs: 23.02 | +63: iteration 51640/ 73814 | consumed samples: 26439680 | consumed tokens: 54148464640 | elapsed time per iteration (s): 2.27 | learning rate: 5.789E-05 | global batch size: 512 | lm loss: 1.955799E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.420 | TFLOPs: 23.21 | +63: iteration 51650/ 73814 | consumed samples: 26444800 | consumed tokens: 54158950400 | elapsed time per iteration (s): 2.23 | learning rate: 5.786E-05 | global batch size: 512 | lm loss: 1.918911E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.637 | TFLOPs: 23.64 | +63: iteration 51660/ 73814 | consumed samples: 26449920 | consumed tokens: 54169436160 | elapsed time per iteration (s): 2.23 | learning rate: 5.783E-05 | global batch size: 512 | lm loss: 1.935251E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.556 | TFLOPs: 23.63 | +63: iteration 51670/ 73814 | consumed samples: 26455040 | consumed tokens: 54179921920 | elapsed time per iteration (s): 2.38 | learning rate: 5.780E-05 | global batch size: 512 | lm loss: 1.943092E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.495 | TFLOPs: 22.18 | +63: iteration 51680/ 73814 | consumed samples: 26460160 | consumed tokens: 54190407680 | elapsed time per iteration (s): 2.24 | learning rate: 5.776E-05 | global batch size: 512 | lm loss: 1.963780E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.851 | TFLOPs: 23.56 | +63: iteration 51690/ 73814 | consumed samples: 26465280 | consumed tokens: 54200893440 | elapsed time per iteration (s): 2.31 | learning rate: 5.773E-05 | global batch size: 512 | lm loss: 1.949883E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.018 | TFLOPs: 22.86 | +63: iteration 51700/ 73814 | consumed samples: 26470400 | consumed tokens: 54211379200 | elapsed time per iteration (s): 2.23 | learning rate: 5.770E-05 | global batch size: 512 | lm loss: 1.954320E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.790 | TFLOPs: 23.66 | +63: iteration 51710/ 73814 | consumed samples: 26475520 | consumed tokens: 54221864960 | elapsed time per iteration (s): 2.22 | learning rate: 5.767E-05 | global batch size: 512 | lm loss: 1.932994E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.117 | TFLOPs: 23.69 | +63: iteration 51720/ 73814 | consumed samples: 26480640 | consumed tokens: 54232350720 | elapsed time per iteration (s): 2.24 | learning rate: 5.764E-05 | global batch size: 512 | lm loss: 1.952029E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.771 | TFLOPs: 23.55 | +63: iteration 51730/ 73814 | consumed samples: 26485760 | consumed tokens: 54242836480 | elapsed time per iteration (s): 2.24 | learning rate: 5.761E-05 | global batch size: 512 | lm loss: 1.935293E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.542 | TFLOPs: 23.53 | +63: iteration 51740/ 73814 | consumed samples: 26490880 | consumed tokens: 54253322240 | elapsed time per iteration (s): 2.23 | learning rate: 5.757E-05 | global batch size: 512 | lm loss: 1.919931E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.334 | TFLOPs: 23.61 | +63: iteration 51750/ 73814 | consumed samples: 26496000 | consumed tokens: 54263808000 | elapsed time per iteration (s): 2.35 | learning rate: 5.754E-05 | global batch size: 512 | lm loss: 1.945741E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.860 | TFLOPs: 22.43 | +63: iteration 51760/ 73814 | consumed samples: 26501120 | consumed tokens: 54274293760 | elapsed time per iteration (s): 2.23 | learning rate: 5.751E-05 | global batch size: 512 | lm loss: 1.925060E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.871 | TFLOPs: 23.66 | +63: iteration 51770/ 73814 | consumed samples: 26506240 | consumed tokens: 54284779520 | elapsed time per iteration (s): 2.22 | learning rate: 5.748E-05 | global batch size: 512 | lm loss: 1.934223E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.158 | TFLOPs: 23.69 | +63: iteration 51780/ 73814 | consumed samples: 26511360 | consumed tokens: 54295265280 | elapsed time per iteration (s): 2.24 | learning rate: 5.745E-05 | global batch size: 512 | lm loss: 1.943184E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.689 | TFLOPs: 23.54 | +63: iteration 51790/ 73814 | consumed samples: 26516480 | consumed tokens: 54305751040 | elapsed time per iteration (s): 2.23 | learning rate: 5.742E-05 | global batch size: 512 | lm loss: 1.939236E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.242 | TFLOPs: 23.60 | +63: iteration 51800/ 73814 | consumed samples: 26521600 | consumed tokens: 54316236800 | elapsed time per iteration (s): 2.36 | learning rate: 5.739E-05 | global batch size: 512 | lm loss: 1.939535E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.898 | TFLOPs: 22.33 | +63: iteration 51810/ 73814 | consumed samples: 26526720 | consumed tokens: 54326722560 | elapsed time per iteration (s): 2.35 | learning rate: 5.735E-05 | global batch size: 512 | lm loss: 1.937960E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.060 | TFLOPs: 22.45 | +63: iteration 51820/ 73814 | consumed samples: 26531840 | consumed tokens: 54337208320 | elapsed time per iteration (s): 2.23 | learning rate: 5.732E-05 | global batch size: 512 | lm loss: 1.935882E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.301 | TFLOPs: 23.61 | +63: iteration 51830/ 73814 | consumed samples: 26536960 | consumed tokens: 54347694080 | elapsed time per iteration (s): 2.23 | learning rate: 5.729E-05 | global batch size: 512 | lm loss: 1.938226E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.854 | TFLOPs: 23.66 | +63: iteration 51840/ 73814 | consumed samples: 26542080 | consumed tokens: 54358179840 | elapsed time per iteration (s): 2.26 | learning rate: 5.726E-05 | global batch size: 512 | lm loss: 1.945028E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.833 | TFLOPs: 23.35 | +63: iteration 51850/ 73814 | consumed samples: 26547200 | consumed tokens: 54368665600 | elapsed time per iteration (s): 2.22 | learning rate: 5.723E-05 | global batch size: 512 | lm loss: 1.936733E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.380 | TFLOPs: 23.72 | +63: iteration 51860/ 73814 | consumed samples: 26552320 | consumed tokens: 54379151360 | elapsed time per iteration (s): 2.24 | learning rate: 5.720E-05 | global batch size: 512 | lm loss: 1.940594E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.112 | TFLOPs: 23.48 | +63: iteration 51870/ 73814 | consumed samples: 26557440 | consumed tokens: 54389637120 | elapsed time per iteration (s): 2.24 | learning rate: 5.717E-05 | global batch size: 512 | lm loss: 1.943746E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.638 | TFLOPs: 23.54 | +63: iteration 51880/ 73814 | consumed samples: 26562560 | consumed tokens: 54400122880 | elapsed time per iteration (s): 2.25 | learning rate: 5.714E-05 | global batch size: 512 | lm loss: 1.948011E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.986 | TFLOPs: 23.47 | +63: iteration 51890/ 73814 | consumed samples: 26567680 | consumed tokens: 54410608640 | elapsed time per iteration (s): 2.24 | learning rate: 5.710E-05 | global batch size: 512 | lm loss: 1.946495E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.546 | TFLOPs: 23.53 | +63: iteration 51900/ 73814 | consumed samples: 26572800 | consumed tokens: 54421094400 | elapsed time per iteration (s): 2.22 | learning rate: 5.707E-05 | global batch size: 512 | lm loss: 1.924255E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.181 | TFLOPs: 23.70 | +63: iteration 51910/ 73814 | consumed samples: 26577920 | consumed tokens: 54431580160 | elapsed time per iteration (s): 2.25 | learning rate: 5.704E-05 | global batch size: 512 | lm loss: 1.936833E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.044 | TFLOPs: 23.48 | +63: iteration 51920/ 73814 | consumed samples: 26583040 | consumed tokens: 54442065920 | elapsed time per iteration (s): 2.23 | learning rate: 5.701E-05 | global batch size: 512 | lm loss: 1.935427E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.892 | TFLOPs: 23.67 | +63: iteration 51930/ 73814 | consumed samples: 26588160 | consumed tokens: 54452551680 | elapsed time per iteration (s): 2.48 | learning rate: 5.698E-05 | global batch size: 512 | lm loss: 1.947932E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.853 | TFLOPs: 21.29 | +63: iteration 51940/ 73814 | consumed samples: 26593280 | consumed tokens: 54463037440 | elapsed time per iteration (s): 2.24 | learning rate: 5.695E-05 | global batch size: 512 | lm loss: 1.932855E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.828 | TFLOPs: 23.56 | +63: iteration 51950/ 73814 | consumed samples: 26598400 | consumed tokens: 54473523200 | elapsed time per iteration (s): 2.24 | learning rate: 5.692E-05 | global batch size: 512 | lm loss: 1.932677E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.293 | TFLOPs: 23.50 | +63: iteration 51960/ 73814 | consumed samples: 26603520 | consumed tokens: 54484008960 | elapsed time per iteration (s): 2.23 | learning rate: 5.689E-05 | global batch size: 512 | lm loss: 1.939328E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.019 | TFLOPs: 23.68 | +63: iteration 51970/ 73814 | consumed samples: 26608640 | consumed tokens: 54494494720 | elapsed time per iteration (s): 2.29 | learning rate: 5.685E-05 | global batch size: 512 | lm loss: 1.937966E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.278 | TFLOPs: 22.99 | +63: iteration 51980/ 73814 | consumed samples: 26613760 | consumed tokens: 54504980480 | elapsed time per iteration (s): 2.26 | learning rate: 5.682E-05 | global batch size: 512 | lm loss: 1.930950E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.399 | TFLOPs: 23.31 | +63: iteration 51990/ 73814 | consumed samples: 26618880 | consumed tokens: 54515466240 | elapsed time per iteration (s): 2.23 | learning rate: 5.679E-05 | global batch size: 512 | lm loss: 1.946104E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.613 | TFLOPs: 23.64 | + 0: [2022-12-02 20:54:52,555] [INFO] [logging.py:68:log_dist] [Rank 0] step=52000, skipped=0, lr=[5.676033265035696e-05, 5.676033265035696e-05, 5.676033265035696e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 52000/ 73814 | consumed samples: 26624000 | consumed tokens: 54525952000 | elapsed time per iteration (s): 2.26 | learning rate: 5.676E-05 | global batch size: 512 | lm loss: 1.934313E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.658 | TFLOPs: 23.33 | + 0: steps: 52000 loss: 1.9343 iter time (s): 2.303 samples/sec: 222.326 +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 52000 | lm loss value: 1.903820E+00 | lm loss PPL: 6.711485E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 52010/ 73814 | consumed samples: 26629120 | consumed tokens: 54536437760 | elapsed time per iteration (s): 2.41 | learning rate: 5.673E-05 | global batch size: 512 | lm loss: 1.931681E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.460 | TFLOPs: 21.87 | +63: iteration 52020/ 73814 | consumed samples: 26634240 | consumed tokens: 54546923520 | elapsed time per iteration (s): 2.24 | learning rate: 5.670E-05 | global batch size: 512 | lm loss: 1.908502E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.119 | TFLOPs: 23.48 | +63: iteration 52030/ 73814 | consumed samples: 26639360 | consumed tokens: 54557409280 | elapsed time per iteration (s): 2.22 | learning rate: 5.667E-05 | global batch size: 512 | lm loss: 1.938348E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.196 | TFLOPs: 23.70 | +63: iteration 52040/ 73814 | consumed samples: 26644480 | consumed tokens: 54567895040 | elapsed time per iteration (s): 2.25 | learning rate: 5.664E-05 | global batch size: 512 | lm loss: 1.952062E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.966 | TFLOPs: 23.47 | +63: iteration 52050/ 73814 | consumed samples: 26649600 | consumed tokens: 54578380800 | elapsed time per iteration (s): 2.23 | learning rate: 5.660E-05 | global batch size: 512 | lm loss: 1.920883E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.975 | TFLOPs: 23.67 | +63: iteration 52060/ 73814 | consumed samples: 26654720 | consumed tokens: 54588866560 | elapsed time per iteration (s): 2.23 | learning rate: 5.657E-05 | global batch size: 512 | lm loss: 1.929084E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.079 | TFLOPs: 23.69 | +63: iteration 52070/ 73814 | consumed samples: 26659840 | consumed tokens: 54599352320 | elapsed time per iteration (s): 2.23 | learning rate: 5.654E-05 | global batch size: 512 | lm loss: 1.943595E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.070 | TFLOPs: 23.68 | +63: iteration 52080/ 73814 | consumed samples: 26664960 | consumed tokens: 54609838080 | elapsed time per iteration (s): 2.24 | learning rate: 5.651E-05 | global batch size: 512 | lm loss: 1.934945E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.661 | TFLOPs: 23.54 | +63: iteration 52090/ 73814 | consumed samples: 26670080 | consumed tokens: 54620323840 | elapsed time per iteration (s): 2.53 | learning rate: 5.648E-05 | global batch size: 512 | lm loss: 1.921716E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.596 | TFLOPs: 20.86 | +63: iteration 52100/ 73814 | consumed samples: 26675200 | consumed tokens: 54630809600 | elapsed time per iteration (s): 2.46 | learning rate: 5.645E-05 | global batch size: 512 | lm loss: 1.936987E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.075 | TFLOPs: 21.42 | +63: iteration 52110/ 73814 | consumed samples: 26680320 | consumed tokens: 54641295360 | elapsed time per iteration (s): 2.38 | learning rate: 5.642E-05 | global batch size: 512 | lm loss: 1.932670E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.497 | TFLOPs: 22.18 | +63: iteration 52120/ 73814 | consumed samples: 26685440 | consumed tokens: 54651781120 | elapsed time per iteration (s): 2.23 | learning rate: 5.639E-05 | global batch size: 512 | lm loss: 1.930438E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.103 | TFLOPs: 23.69 | +63: iteration 52130/ 73814 | consumed samples: 26690560 | consumed tokens: 54662266880 | elapsed time per iteration (s): 2.28 | learning rate: 5.636E-05 | global batch size: 512 | lm loss: 1.934346E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.031 | TFLOPs: 23.17 | +63: iteration 52140/ 73814 | consumed samples: 26695680 | consumed tokens: 54672752640 | elapsed time per iteration (s): 2.23 | learning rate: 5.632E-05 | global batch size: 512 | lm loss: 1.961026E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.148 | TFLOPs: 23.59 | +63: iteration 52150/ 73814 | consumed samples: 26700800 | consumed tokens: 54683238400 | elapsed time per iteration (s): 2.28 | learning rate: 5.629E-05 | global batch size: 512 | lm loss: 1.942084E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.884 | TFLOPs: 23.15 | +63: iteration 52160/ 73814 | consumed samples: 26705920 | consumed tokens: 54693724160 | elapsed time per iteration (s): 2.24 | learning rate: 5.626E-05 | global batch size: 512 | lm loss: 1.937330E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.577 | TFLOPs: 23.53 | +63: iteration 52170/ 73814 | consumed samples: 26711040 | consumed tokens: 54704209920 | elapsed time per iteration (s): 2.23 | learning rate: 5.623E-05 | global batch size: 512 | lm loss: 1.960198E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.717 | TFLOPs: 23.65 | +63: iteration 52180/ 73814 | consumed samples: 26716160 | consumed tokens: 54714695680 | elapsed time per iteration (s): 2.27 | learning rate: 5.620E-05 | global batch size: 512 | lm loss: 1.923460E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.933 | TFLOPs: 23.26 | +63: iteration 52190/ 73814 | consumed samples: 26721280 | consumed tokens: 54725181440 | elapsed time per iteration (s): 2.39 | learning rate: 5.617E-05 | global batch size: 512 | lm loss: 1.928771E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.814 | TFLOPs: 22.01 | +63: iteration 52200/ 73814 | consumed samples: 26726400 | consumed tokens: 54735667200 | elapsed time per iteration (s): 2.23 | learning rate: 5.614E-05 | global batch size: 512 | lm loss: 1.926781E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.028 | TFLOPs: 23.68 | +63: iteration 52210/ 73814 | consumed samples: 26731520 | consumed tokens: 54746152960 | elapsed time per iteration (s): 2.32 | learning rate: 5.611E-05 | global batch size: 512 | lm loss: 1.935887E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.525 | TFLOPs: 22.70 | +63: iteration 52220/ 73814 | consumed samples: 26736640 | consumed tokens: 54756638720 | elapsed time per iteration (s): 2.22 | learning rate: 5.608E-05 | global batch size: 512 | lm loss: 1.938664E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.243 | TFLOPs: 23.70 | +63: iteration 52230/ 73814 | consumed samples: 26741760 | consumed tokens: 54767124480 | elapsed time per iteration (s): 2.23 | learning rate: 5.605E-05 | global batch size: 512 | lm loss: 1.916844E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.557 | TFLOPs: 23.63 | +63: iteration 52240/ 73814 | consumed samples: 26746880 | consumed tokens: 54777610240 | elapsed time per iteration (s): 2.37 | learning rate: 5.601E-05 | global batch size: 512 | lm loss: 1.914627E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.153 | TFLOPs: 22.25 | +63: iteration 52250/ 73814 | consumed samples: 26752000 | consumed tokens: 54788096000 | elapsed time per iteration (s): 2.22 | learning rate: 5.598E-05 | global batch size: 512 | lm loss: 1.928910E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.271 | TFLOPs: 23.71 | +63: iteration 52260/ 73814 | consumed samples: 26757120 | consumed tokens: 54798581760 | elapsed time per iteration (s): 2.39 | learning rate: 5.595E-05 | global batch size: 512 | lm loss: 1.922962E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.809 | TFLOPs: 22.01 | +63: iteration 52270/ 73814 | consumed samples: 26762240 | consumed tokens: 54809067520 | elapsed time per iteration (s): 2.33 | learning rate: 5.592E-05 | global batch size: 512 | lm loss: 1.959752E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.022 | TFLOPs: 22.65 | +63: iteration 52280/ 73814 | consumed samples: 26767360 | consumed tokens: 54819553280 | elapsed time per iteration (s): 2.24 | learning rate: 5.589E-05 | global batch size: 512 | lm loss: 1.921130E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.434 | TFLOPs: 23.52 | +63: iteration 52290/ 73814 | consumed samples: 26772480 | consumed tokens: 54830039040 | elapsed time per iteration (s): 2.23 | learning rate: 5.586E-05 | global batch size: 512 | lm loss: 1.926155E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.539 | TFLOPs: 23.63 | +63: iteration 52300/ 73814 | consumed samples: 26777600 | consumed tokens: 54840524800 | elapsed time per iteration (s): 2.26 | learning rate: 5.583E-05 | global batch size: 512 | lm loss: 1.923327E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.129 | TFLOPs: 23.28 | +63: iteration 52310/ 73814 | consumed samples: 26782720 | consumed tokens: 54851010560 | elapsed time per iteration (s): 2.23 | learning rate: 5.580E-05 | global batch size: 512 | lm loss: 1.933883E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.717 | TFLOPs: 23.65 | +63: iteration 52320/ 73814 | consumed samples: 26787840 | consumed tokens: 54861496320 | elapsed time per iteration (s): 2.24 | learning rate: 5.577E-05 | global batch size: 512 | lm loss: 1.913824E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.501 | TFLOPs: 23.52 | +63: iteration 52330/ 73814 | consumed samples: 26792960 | consumed tokens: 54871982080 | elapsed time per iteration (s): 2.24 | learning rate: 5.574E-05 | global batch size: 512 | lm loss: 1.945810E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.234 | TFLOPs: 23.50 | +63: iteration 52340/ 73814 | consumed samples: 26798080 | consumed tokens: 54882467840 | elapsed time per iteration (s): 2.23 | learning rate: 5.571E-05 | global batch size: 512 | lm loss: 1.951646E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.893 | TFLOPs: 23.67 | +63: iteration 52350/ 73814 | consumed samples: 26803200 | consumed tokens: 54892953600 | elapsed time per iteration (s): 2.22 | learning rate: 5.567E-05 | global batch size: 512 | lm loss: 1.949206E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.188 | TFLOPs: 23.70 | +63: iteration 52360/ 73814 | consumed samples: 26808320 | consumed tokens: 54903439360 | elapsed time per iteration (s): 2.33 | learning rate: 5.564E-05 | global batch size: 512 | lm loss: 1.928395E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.457 | TFLOPs: 22.59 | +63: iteration 52370/ 73814 | consumed samples: 26813440 | consumed tokens: 54913925120 | elapsed time per iteration (s): 2.23 | learning rate: 5.561E-05 | global batch size: 512 | lm loss: 1.927726E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.822 | TFLOPs: 23.66 | +63: iteration 52380/ 73814 | consumed samples: 26818560 | consumed tokens: 54924410880 | elapsed time per iteration (s): 2.39 | learning rate: 5.558E-05 | global batch size: 512 | lm loss: 1.947713E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.427 | TFLOPs: 22.07 | +63: iteration 52390/ 73814 | consumed samples: 26823680 | consumed tokens: 54934896640 | elapsed time per iteration (s): 2.27 | learning rate: 5.555E-05 | global batch size: 512 | lm loss: 1.936894E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.360 | TFLOPs: 23.20 | +63: iteration 52400/ 73814 | consumed samples: 26828800 | consumed tokens: 54945382400 | elapsed time per iteration (s): 2.23 | learning rate: 5.552E-05 | global batch size: 512 | lm loss: 1.935214E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.891 | TFLOPs: 23.67 | +63: iteration 52410/ 73814 | consumed samples: 26833920 | consumed tokens: 54955868160 | elapsed time per iteration (s): 2.45 | learning rate: 5.549E-05 | global batch size: 512 | lm loss: 1.944055E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.817 | TFLOPs: 21.50 | +63: iteration 52420/ 73814 | consumed samples: 26839040 | consumed tokens: 54966353920 | elapsed time per iteration (s): 2.23 | learning rate: 5.546E-05 | global batch size: 512 | lm loss: 1.936750E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.787 | TFLOPs: 23.66 | +63: iteration 52430/ 73814 | consumed samples: 26844160 | consumed tokens: 54976839680 | elapsed time per iteration (s): 2.23 | learning rate: 5.543E-05 | global batch size: 512 | lm loss: 1.952999E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.537 | TFLOPs: 23.63 | +63: iteration 52440/ 73814 | consumed samples: 26849280 | consumed tokens: 54987325440 | elapsed time per iteration (s): 2.25 | learning rate: 5.540E-05 | global batch size: 512 | lm loss: 1.913723E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.493 | TFLOPs: 23.42 | +63: iteration 52450/ 73814 | consumed samples: 26854400 | consumed tokens: 54997811200 | elapsed time per iteration (s): 2.23 | learning rate: 5.537E-05 | global batch size: 512 | lm loss: 1.936836E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.283 | TFLOPs: 23.60 | +63: iteration 52460/ 73814 | consumed samples: 26859520 | consumed tokens: 55008296960 | elapsed time per iteration (s): 2.24 | learning rate: 5.534E-05 | global batch size: 512 | lm loss: 1.947055E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.384 | TFLOPs: 23.51 | +63: iteration 52470/ 73814 | consumed samples: 26864640 | consumed tokens: 55018782720 | elapsed time per iteration (s): 2.23 | learning rate: 5.531E-05 | global batch size: 512 | lm loss: 1.928045E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.775 | TFLOPs: 23.65 | +63: iteration 52480/ 73814 | consumed samples: 26869760 | consumed tokens: 55029268480 | elapsed time per iteration (s): 2.25 | learning rate: 5.527E-05 | global batch size: 512 | lm loss: 1.932209E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.631 | TFLOPs: 23.43 | +63: iteration 52490/ 73814 | consumed samples: 26874880 | consumed tokens: 55039754240 | elapsed time per iteration (s): 2.23 | learning rate: 5.524E-05 | global batch size: 512 | lm loss: 1.936375E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.867 | TFLOPs: 23.66 | +63: iteration 52500/ 73814 | consumed samples: 26880000 | consumed tokens: 55050240000 | elapsed time per iteration (s): 2.27 | learning rate: 5.521E-05 | global batch size: 512 | lm loss: 1.954703E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.825 | TFLOPs: 23.25 | +63: iteration 52510/ 73814 | consumed samples: 26885120 | consumed tokens: 55060725760 | elapsed time per iteration (s): 2.24 | learning rate: 5.518E-05 | global batch size: 512 | lm loss: 1.939284E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.255 | TFLOPs: 23.50 | +63: iteration 52520/ 73814 | consumed samples: 26890240 | consumed tokens: 55071211520 | elapsed time per iteration (s): 2.37 | learning rate: 5.515E-05 | global batch size: 512 | lm loss: 1.918276E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.024 | TFLOPs: 22.24 | +63: iteration 52530/ 73814 | consumed samples: 26895360 | consumed tokens: 55081697280 | elapsed time per iteration (s): 2.47 | learning rate: 5.512E-05 | global batch size: 512 | lm loss: 1.930944E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 207.573 | TFLOPs: 21.37 | +63: iteration 52540/ 73814 | consumed samples: 26900480 | consumed tokens: 55092183040 | elapsed time per iteration (s): 2.40 | learning rate: 5.509E-05 | global batch size: 512 | lm loss: 1.905943E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.218 | TFLOPs: 21.95 | +63: iteration 52550/ 73814 | consumed samples: 26905600 | consumed tokens: 55102668800 | elapsed time per iteration (s): 2.28 | learning rate: 5.506E-05 | global batch size: 512 | lm loss: 1.929072E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.546 | TFLOPs: 23.12 | +63: iteration 52560/ 73814 | consumed samples: 26910720 | consumed tokens: 55113154560 | elapsed time per iteration (s): 2.55 | learning rate: 5.503E-05 | global batch size: 512 | lm loss: 1.937572E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.581 | TFLOPs: 20.65 | +63: iteration 52570/ 73814 | consumed samples: 26915840 | consumed tokens: 55123640320 | elapsed time per iteration (s): 2.81 | learning rate: 5.500E-05 | global batch size: 512 | lm loss: 1.929156E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 182.477 | TFLOPs: 18.79 | +63: iteration 52580/ 73814 | consumed samples: 26920960 | consumed tokens: 55134126080 | elapsed time per iteration (s): 2.55 | learning rate: 5.497E-05 | global batch size: 512 | lm loss: 1.943245E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.797 | TFLOPs: 20.67 | +63: iteration 52590/ 73814 | consumed samples: 26926080 | consumed tokens: 55144611840 | elapsed time per iteration (s): 2.91 | learning rate: 5.494E-05 | global batch size: 512 | lm loss: 1.940222E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 175.809 | TFLOPs: 18.10 | +63: iteration 52600/ 73814 | consumed samples: 26931200 | consumed tokens: 55155097600 | elapsed time per iteration (s): 2.28 | learning rate: 5.491E-05 | global batch size: 512 | lm loss: 1.948776E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.968 | TFLOPs: 23.16 | +63: iteration 52610/ 73814 | consumed samples: 26936320 | consumed tokens: 55165583360 | elapsed time per iteration (s): 2.41 | learning rate: 5.488E-05 | global batch size: 512 | lm loss: 1.925344E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.191 | TFLOPs: 21.84 | +63: iteration 52620/ 73814 | consumed samples: 26941440 | consumed tokens: 55176069120 | elapsed time per iteration (s): 2.52 | learning rate: 5.485E-05 | global batch size: 512 | lm loss: 1.951392E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 203.449 | TFLOPs: 20.94 | +63: iteration 52630/ 73814 | consumed samples: 26946560 | consumed tokens: 55186554880 | elapsed time per iteration (s): 2.25 | learning rate: 5.481E-05 | global batch size: 512 | lm loss: 1.931182E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.738 | TFLOPs: 23.44 | +63: iteration 52640/ 73814 | consumed samples: 26951680 | consumed tokens: 55197040640 | elapsed time per iteration (s): 2.23 | learning rate: 5.478E-05 | global batch size: 512 | lm loss: 1.927724E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.373 | TFLOPs: 23.61 | +63: iteration 52650/ 73814 | consumed samples: 26956800 | consumed tokens: 55207526400 | elapsed time per iteration (s): 2.22 | learning rate: 5.475E-05 | global batch size: 512 | lm loss: 1.952999E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.396 | TFLOPs: 23.72 | +63: iteration 52660/ 73814 | consumed samples: 26961920 | consumed tokens: 55218012160 | elapsed time per iteration (s): 2.33 | learning rate: 5.472E-05 | global batch size: 512 | lm loss: 1.937742E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.673 | TFLOPs: 22.61 | +63: iteration 52670/ 73814 | consumed samples: 26967040 | consumed tokens: 55228497920 | elapsed time per iteration (s): 2.24 | learning rate: 5.469E-05 | global batch size: 512 | lm loss: 1.945748E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.354 | TFLOPs: 23.51 | +63: iteration 52680/ 73814 | consumed samples: 26972160 | consumed tokens: 55238983680 | elapsed time per iteration (s): 2.23 | learning rate: 5.466E-05 | global batch size: 512 | lm loss: 1.930191E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.746 | TFLOPs: 23.65 | +63: iteration 52690/ 73814 | consumed samples: 26977280 | consumed tokens: 55249469440 | elapsed time per iteration (s): 2.50 | learning rate: 5.463E-05 | global batch size: 512 | lm loss: 1.925986E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.077 | TFLOPs: 21.11 | +63: iteration 52700/ 73814 | consumed samples: 26982400 | consumed tokens: 55259955200 | elapsed time per iteration (s): 2.33 | learning rate: 5.460E-05 | global batch size: 512 | lm loss: 1.920149E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.432 | TFLOPs: 22.59 | +63: iteration 52710/ 73814 | consumed samples: 26987520 | consumed tokens: 55270440960 | elapsed time per iteration (s): 2.23 | learning rate: 5.457E-05 | global batch size: 512 | lm loss: 1.936540E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.754 | TFLOPs: 23.65 | +63: iteration 52720/ 73814 | consumed samples: 26992640 | consumed tokens: 55280926720 | elapsed time per iteration (s): 2.23 | learning rate: 5.454E-05 | global batch size: 512 | lm loss: 1.929199E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.977 | TFLOPs: 23.68 | +63: iteration 52730/ 73814 | consumed samples: 26997760 | consumed tokens: 55291412480 | elapsed time per iteration (s): 2.45 | learning rate: 5.451E-05 | global batch size: 512 | lm loss: 1.941323E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.826 | TFLOPs: 21.50 | +63: iteration 52740/ 73814 | consumed samples: 27002880 | consumed tokens: 55301898240 | elapsed time per iteration (s): 2.24 | learning rate: 5.448E-05 | global batch size: 512 | lm loss: 1.951626E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.255 | TFLOPs: 23.50 | +63: iteration 52750/ 73814 | consumed samples: 27008000 | consumed tokens: 55312384000 | elapsed time per iteration (s): 2.29 | learning rate: 5.445E-05 | global batch size: 512 | lm loss: 1.959400E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.826 | TFLOPs: 23.04 | +63: iteration 52760/ 73814 | consumed samples: 27013120 | consumed tokens: 55322869760 | elapsed time per iteration (s): 2.22 | learning rate: 5.442E-05 | global batch size: 512 | lm loss: 1.932952E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.362 | TFLOPs: 23.71 | +63: iteration 52770/ 73814 | consumed samples: 27018240 | consumed tokens: 55333355520 | elapsed time per iteration (s): 2.23 | learning rate: 5.439E-05 | global batch size: 512 | lm loss: 1.934029E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.148 | TFLOPs: 23.59 | +63: iteration 52780/ 73814 | consumed samples: 27023360 | consumed tokens: 55343841280 | elapsed time per iteration (s): 2.23 | learning rate: 5.436E-05 | global batch size: 512 | lm loss: 1.940530E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.934 | TFLOPs: 23.67 | +63: iteration 52790/ 73814 | consumed samples: 27028480 | consumed tokens: 55354327040 | elapsed time per iteration (s): 2.24 | learning rate: 5.433E-05 | global batch size: 512 | lm loss: 1.937220E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.142 | TFLOPs: 23.49 | +63: iteration 52800/ 73814 | consumed samples: 27033600 | consumed tokens: 55364812800 | elapsed time per iteration (s): 2.24 | learning rate: 5.430E-05 | global batch size: 512 | lm loss: 1.947290E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.328 | TFLOPs: 23.51 | +63: iteration 52810/ 73814 | consumed samples: 27038720 | consumed tokens: 55375298560 | elapsed time per iteration (s): 2.24 | learning rate: 5.427E-05 | global batch size: 512 | lm loss: 1.941395E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.058 | TFLOPs: 23.58 | +63: iteration 52820/ 73814 | consumed samples: 27043840 | consumed tokens: 55385784320 | elapsed time per iteration (s): 2.29 | learning rate: 5.424E-05 | global batch size: 512 | lm loss: 1.942035E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.718 | TFLOPs: 23.03 | +63: iteration 52830/ 73814 | consumed samples: 27048960 | consumed tokens: 55396270080 | elapsed time per iteration (s): 2.24 | learning rate: 5.421E-05 | global batch size: 512 | lm loss: 1.935231E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.433 | TFLOPs: 23.52 | +63: iteration 52840/ 73814 | consumed samples: 27054080 | consumed tokens: 55406755840 | elapsed time per iteration (s): 2.24 | learning rate: 5.418E-05 | global batch size: 512 | lm loss: 1.944672E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.012 | TFLOPs: 23.58 | +63: iteration 52850/ 73814 | consumed samples: 27059200 | consumed tokens: 55417241600 | elapsed time per iteration (s): 2.48 | learning rate: 5.414E-05 | global batch size: 512 | lm loss: 1.913356E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.624 | TFLOPs: 21.27 | +63: iteration 52860/ 73814 | consumed samples: 27064320 | consumed tokens: 55427727360 | elapsed time per iteration (s): 2.23 | learning rate: 5.411E-05 | global batch size: 512 | lm loss: 1.914770E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.701 | TFLOPs: 23.65 | +63: iteration 52870/ 73814 | consumed samples: 27069440 | consumed tokens: 55438213120 | elapsed time per iteration (s): 2.24 | learning rate: 5.408E-05 | global batch size: 512 | lm loss: 1.952435E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.093 | TFLOPs: 23.48 | +63: iteration 52880/ 73814 | consumed samples: 27074560 | consumed tokens: 55448698880 | elapsed time per iteration (s): 2.49 | learning rate: 5.405E-05 | global batch size: 512 | lm loss: 1.917893E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.223 | TFLOPs: 21.13 | +63: iteration 52890/ 73814 | consumed samples: 27079680 | consumed tokens: 55459184640 | elapsed time per iteration (s): 2.26 | learning rate: 5.402E-05 | global batch size: 512 | lm loss: 1.928647E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.109 | TFLOPs: 23.28 | +63: iteration 52900/ 73814 | consumed samples: 27084800 | consumed tokens: 55469670400 | elapsed time per iteration (s): 2.30 | learning rate: 5.399E-05 | global batch size: 512 | lm loss: 1.944460E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.365 | TFLOPs: 22.89 | +63: iteration 52910/ 73814 | consumed samples: 27089920 | consumed tokens: 55480156160 | elapsed time per iteration (s): 2.25 | learning rate: 5.396E-05 | global batch size: 512 | lm loss: 1.924289E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.419 | TFLOPs: 23.41 | +63: iteration 52920/ 73814 | consumed samples: 27095040 | consumed tokens: 55490641920 | elapsed time per iteration (s): 2.24 | learning rate: 5.393E-05 | global batch size: 512 | lm loss: 1.928463E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.856 | TFLOPs: 23.56 | +63: iteration 52930/ 73814 | consumed samples: 27100160 | consumed tokens: 55501127680 | elapsed time per iteration (s): 2.23 | learning rate: 5.390E-05 | global batch size: 512 | lm loss: 1.917655E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.183 | TFLOPs: 23.59 | +63: iteration 52940/ 73814 | consumed samples: 27105280 | consumed tokens: 55511613440 | elapsed time per iteration (s): 2.22 | learning rate: 5.387E-05 | global batch size: 512 | lm loss: 1.934784E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.198 | TFLOPs: 23.70 | +63: iteration 52950/ 73814 | consumed samples: 27110400 | consumed tokens: 55522099200 | elapsed time per iteration (s): 2.27 | learning rate: 5.384E-05 | global batch size: 512 | lm loss: 1.941117E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.411 | TFLOPs: 23.21 | +63: iteration 52960/ 73814 | consumed samples: 27115520 | consumed tokens: 55532584960 | elapsed time per iteration (s): 2.25 | learning rate: 5.381E-05 | global batch size: 512 | lm loss: 1.922725E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.156 | TFLOPs: 23.38 | +63: iteration 52970/ 73814 | consumed samples: 27120640 | consumed tokens: 55543070720 | elapsed time per iteration (s): 2.22 | learning rate: 5.378E-05 | global batch size: 512 | lm loss: 1.916914E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.508 | TFLOPs: 23.73 | +63: iteration 52980/ 73814 | consumed samples: 27125760 | consumed tokens: 55553556480 | elapsed time per iteration (s): 2.23 | learning rate: 5.375E-05 | global batch size: 512 | lm loss: 1.944427E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.362 | TFLOPs: 23.61 | +63: iteration 52990/ 73814 | consumed samples: 27130880 | consumed tokens: 55564042240 | elapsed time per iteration (s): 2.23 | learning rate: 5.372E-05 | global batch size: 512 | lm loss: 1.927272E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.898 | TFLOPs: 23.67 | +63: iteration 53000/ 73814 | consumed samples: 27136000 | consumed tokens: 55574528000 | elapsed time per iteration (s): 2.23 | learning rate: 5.369E-05 | global batch size: 512 | lm loss: 1.949436E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.042 | TFLOPs: 23.68 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 53000 | lm loss value: 1.835725E+00 | lm loss PPL: 6.269678E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 53010/ 73814 | consumed samples: 27141120 | consumed tokens: 55585013760 | elapsed time per iteration (s): 2.28 | learning rate: 5.366E-05 | global batch size: 512 | lm loss: 1.930283E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.131 | TFLOPs: 23.07 | +63: iteration 53020/ 73814 | consumed samples: 27146240 | consumed tokens: 55595499520 | elapsed time per iteration (s): 2.22 | learning rate: 5.363E-05 | global batch size: 512 | lm loss: 1.956255E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.491 | TFLOPs: 23.73 | +63: iteration 53030/ 73814 | consumed samples: 27151360 | consumed tokens: 55605985280 | elapsed time per iteration (s): 2.35 | learning rate: 5.360E-05 | global batch size: 512 | lm loss: 1.936203E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.072 | TFLOPs: 22.45 | +63: iteration 53040/ 73814 | consumed samples: 27156480 | consumed tokens: 55616471040 | elapsed time per iteration (s): 2.24 | learning rate: 5.357E-05 | global batch size: 512 | lm loss: 1.929818E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.619 | TFLOPs: 23.54 | +63: iteration 53050/ 73814 | consumed samples: 27161600 | consumed tokens: 55626956800 | elapsed time per iteration (s): 2.23 | learning rate: 5.354E-05 | global batch size: 512 | lm loss: 1.947173E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.769 | TFLOPs: 23.65 | +63: iteration 53060/ 73814 | consumed samples: 27166720 | consumed tokens: 55637442560 | elapsed time per iteration (s): 2.25 | learning rate: 5.351E-05 | global batch size: 512 | lm loss: 1.943161E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.752 | TFLOPs: 23.45 | +63: iteration 53070/ 73814 | consumed samples: 27171840 | consumed tokens: 55647928320 | elapsed time per iteration (s): 2.23 | learning rate: 5.348E-05 | global batch size: 512 | lm loss: 1.917738E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.518 | TFLOPs: 23.63 | +63: iteration 53080/ 73814 | consumed samples: 27176960 | consumed tokens: 55658414080 | elapsed time per iteration (s): 2.24 | learning rate: 5.345E-05 | global batch size: 512 | lm loss: 1.919826E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.815 | TFLOPs: 23.56 | +63: iteration 53090/ 73814 | consumed samples: 27182080 | consumed tokens: 55668899840 | elapsed time per iteration (s): 2.23 | learning rate: 5.342E-05 | global batch size: 512 | lm loss: 1.938908E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.685 | TFLOPs: 23.64 | +63: iteration 53100/ 73814 | consumed samples: 27187200 | consumed tokens: 55679385600 | elapsed time per iteration (s): 2.25 | learning rate: 5.339E-05 | global batch size: 512 | lm loss: 1.927112E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.661 | TFLOPs: 23.44 | +63: iteration 53110/ 73814 | consumed samples: 27192320 | consumed tokens: 55689871360 | elapsed time per iteration (s): 2.23 | learning rate: 5.336E-05 | global batch size: 512 | lm loss: 1.926648E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.012 | TFLOPs: 23.68 | +63: iteration 53120/ 73814 | consumed samples: 27197440 | consumed tokens: 55700357120 | elapsed time per iteration (s): 2.25 | learning rate: 5.333E-05 | global batch size: 512 | lm loss: 1.909148E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.339 | TFLOPs: 23.40 | +63: iteration 53130/ 73814 | consumed samples: 27202560 | consumed tokens: 55710842880 | elapsed time per iteration (s): 2.23 | learning rate: 5.330E-05 | global batch size: 512 | lm loss: 1.924899E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.951 | TFLOPs: 23.67 | +63: iteration 53140/ 73814 | consumed samples: 27207680 | consumed tokens: 55721328640 | elapsed time per iteration (s): 2.23 | learning rate: 5.327E-05 | global batch size: 512 | lm loss: 1.924966E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.636 | TFLOPs: 23.64 | +63: iteration 53150/ 73814 | consumed samples: 27212800 | consumed tokens: 55731814400 | elapsed time per iteration (s): 2.24 | learning rate: 5.324E-05 | global batch size: 512 | lm loss: 1.922829E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.798 | TFLOPs: 23.55 | +63: iteration 53160/ 73814 | consumed samples: 27217920 | consumed tokens: 55742300160 | elapsed time per iteration (s): 2.23 | learning rate: 5.321E-05 | global batch size: 512 | lm loss: 1.956861E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.872 | TFLOPs: 23.66 | +63: iteration 53170/ 73814 | consumed samples: 27223040 | consumed tokens: 55752785920 | elapsed time per iteration (s): 2.23 | learning rate: 5.318E-05 | global batch size: 512 | lm loss: 1.965835E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.438 | TFLOPs: 23.62 | +63: iteration 53180/ 73814 | consumed samples: 27228160 | consumed tokens: 55763271680 | elapsed time per iteration (s): 2.23 | learning rate: 5.315E-05 | global batch size: 512 | lm loss: 1.945949E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.537 | TFLOPs: 23.63 | +63: iteration 53190/ 73814 | consumed samples: 27233280 | consumed tokens: 55773757440 | elapsed time per iteration (s): 2.31 | learning rate: 5.312E-05 | global batch size: 512 | lm loss: 1.924260E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.237 | TFLOPs: 22.78 | +63: iteration 53200/ 73814 | consumed samples: 27238400 | consumed tokens: 55784243200 | elapsed time per iteration (s): 2.25 | learning rate: 5.309E-05 | global batch size: 512 | lm loss: 1.947702E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.333 | TFLOPs: 23.40 | +63: iteration 53210/ 73814 | consumed samples: 27243520 | consumed tokens: 55794728960 | elapsed time per iteration (s): 2.23 | learning rate: 5.306E-05 | global batch size: 512 | lm loss: 1.932597E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.548 | TFLOPs: 23.63 | +63: iteration 53220/ 73814 | consumed samples: 27248640 | consumed tokens: 55805214720 | elapsed time per iteration (s): 2.27 | learning rate: 5.303E-05 | global batch size: 512 | lm loss: 1.924347E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.569 | TFLOPs: 23.22 | +63: iteration 53230/ 73814 | consumed samples: 27253760 | consumed tokens: 55815700480 | elapsed time per iteration (s): 2.25 | learning rate: 5.300E-05 | global batch size: 512 | lm loss: 1.920821E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.405 | TFLOPs: 23.41 | +63: iteration 53240/ 73814 | consumed samples: 27258880 | consumed tokens: 55826186240 | elapsed time per iteration (s): 2.24 | learning rate: 5.297E-05 | global batch size: 512 | lm loss: 1.942947E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.349 | TFLOPs: 23.51 | +63: iteration 53250/ 73814 | consumed samples: 27264000 | consumed tokens: 55836672000 | elapsed time per iteration (s): 2.25 | learning rate: 5.294E-05 | global batch size: 512 | lm loss: 1.945222E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.849 | TFLOPs: 23.46 | +63: iteration 53260/ 73814 | consumed samples: 27269120 | consumed tokens: 55847157760 | elapsed time per iteration (s): 2.26 | learning rate: 5.291E-05 | global batch size: 512 | lm loss: 1.913462E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.514 | TFLOPs: 23.32 | +63: iteration 53270/ 73814 | consumed samples: 27274240 | consumed tokens: 55857643520 | elapsed time per iteration (s): 2.23 | learning rate: 5.288E-05 | global batch size: 512 | lm loss: 1.932858E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.104 | TFLOPs: 23.59 | +63: iteration 53280/ 73814 | consumed samples: 27279360 | consumed tokens: 55868129280 | elapsed time per iteration (s): 2.23 | learning rate: 5.285E-05 | global batch size: 512 | lm loss: 1.906136E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.638 | TFLOPs: 23.64 | +63: iteration 53290/ 73814 | consumed samples: 27284480 | consumed tokens: 55878615040 | elapsed time per iteration (s): 2.35 | learning rate: 5.282E-05 | global batch size: 512 | lm loss: 1.920062E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.971 | TFLOPs: 22.44 | +63: iteration 53300/ 73814 | consumed samples: 27289600 | consumed tokens: 55889100800 | elapsed time per iteration (s): 2.37 | learning rate: 5.279E-05 | global batch size: 512 | lm loss: 1.940457E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.855 | TFLOPs: 22.22 | +63: iteration 53310/ 73814 | consumed samples: 27294720 | consumed tokens: 55899586560 | elapsed time per iteration (s): 2.23 | learning rate: 5.276E-05 | global batch size: 512 | lm loss: 1.939976E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.783 | TFLOPs: 23.66 | +63: iteration 53320/ 73814 | consumed samples: 27299840 | consumed tokens: 55910072320 | elapsed time per iteration (s): 2.25 | learning rate: 5.273E-05 | global batch size: 512 | lm loss: 1.935793E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.167 | TFLOPs: 23.39 | +63: iteration 53330/ 73814 | consumed samples: 27304960 | consumed tokens: 55920558080 | elapsed time per iteration (s): 2.23 | learning rate: 5.270E-05 | global batch size: 512 | lm loss: 1.948787E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.064 | TFLOPs: 23.68 | +63: iteration 53340/ 73814 | consumed samples: 27310080 | consumed tokens: 55931043840 | elapsed time per iteration (s): 2.28 | learning rate: 5.267E-05 | global batch size: 512 | lm loss: 1.921763E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.251 | TFLOPs: 23.09 | +63: iteration 53350/ 73814 | consumed samples: 27315200 | consumed tokens: 55941529600 | elapsed time per iteration (s): 2.29 | learning rate: 5.264E-05 | global batch size: 512 | lm loss: 1.899455E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.063 | TFLOPs: 23.07 | +63: iteration 53360/ 73814 | consumed samples: 27320320 | consumed tokens: 55952015360 | elapsed time per iteration (s): 2.23 | learning rate: 5.261E-05 | global batch size: 512 | lm loss: 1.952893E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.596 | TFLOPs: 23.64 | +63: iteration 53370/ 73814 | consumed samples: 27325440 | consumed tokens: 55962501120 | elapsed time per iteration (s): 2.22 | learning rate: 5.258E-05 | global batch size: 512 | lm loss: 1.928948E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.378 | TFLOPs: 23.72 | +63: iteration 53380/ 73814 | consumed samples: 27330560 | consumed tokens: 55972986880 | elapsed time per iteration (s): 2.58 | learning rate: 5.255E-05 | global batch size: 512 | lm loss: 1.939344E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.357 | TFLOPs: 20.42 | +63: iteration 53390/ 73814 | consumed samples: 27335680 | consumed tokens: 55983472640 | elapsed time per iteration (s): 2.23 | learning rate: 5.252E-05 | global batch size: 512 | lm loss: 1.950410E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.542 | TFLOPs: 23.63 | +63: iteration 53400/ 73814 | consumed samples: 27340800 | consumed tokens: 55993958400 | elapsed time per iteration (s): 2.43 | learning rate: 5.249E-05 | global batch size: 512 | lm loss: 1.916723E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.355 | TFLOPs: 21.66 | +63: iteration 53410/ 73814 | consumed samples: 27345920 | consumed tokens: 56004444160 | elapsed time per iteration (s): 2.23 | learning rate: 5.246E-05 | global batch size: 512 | lm loss: 1.926559E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.703 | TFLOPs: 23.65 | +63: iteration 53420/ 73814 | consumed samples: 27351040 | consumed tokens: 56014929920 | elapsed time per iteration (s): 2.24 | learning rate: 5.243E-05 | global batch size: 512 | lm loss: 1.929764E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.133 | TFLOPs: 23.49 | +63: iteration 53430/ 73814 | consumed samples: 27356160 | consumed tokens: 56025415680 | elapsed time per iteration (s): 2.36 | learning rate: 5.240E-05 | global batch size: 512 | lm loss: 1.919339E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.733 | TFLOPs: 22.31 | +63: iteration 53440/ 73814 | consumed samples: 27361280 | consumed tokens: 56035901440 | elapsed time per iteration (s): 2.25 | learning rate: 5.237E-05 | global batch size: 512 | lm loss: 1.950879E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.661 | TFLOPs: 23.44 | +63: iteration 53450/ 73814 | consumed samples: 27366400 | consumed tokens: 56046387200 | elapsed time per iteration (s): 2.35 | learning rate: 5.234E-05 | global batch size: 512 | lm loss: 1.915179E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.967 | TFLOPs: 22.44 | +63: iteration 53460/ 73814 | consumed samples: 27371520 | consumed tokens: 56056872960 | elapsed time per iteration (s): 2.26 | learning rate: 5.231E-05 | global batch size: 512 | lm loss: 1.918435E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.147 | TFLOPs: 23.28 | +63: iteration 53470/ 73814 | consumed samples: 27376640 | consumed tokens: 56067358720 | elapsed time per iteration (s): 2.25 | learning rate: 5.228E-05 | global batch size: 512 | lm loss: 1.915866E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.303 | TFLOPs: 23.40 | +63: iteration 53480/ 73814 | consumed samples: 27381760 | consumed tokens: 56077844480 | elapsed time per iteration (s): 2.23 | learning rate: 5.225E-05 | global batch size: 512 | lm loss: 1.938758E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.269 | TFLOPs: 23.60 | +63: iteration 53490/ 73814 | consumed samples: 27386880 | consumed tokens: 56088330240 | elapsed time per iteration (s): 2.24 | learning rate: 5.222E-05 | global batch size: 512 | lm loss: 1.948583E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.732 | TFLOPs: 23.55 | +63: iteration 53500/ 73814 | consumed samples: 27392000 | consumed tokens: 56098816000 | elapsed time per iteration (s): 2.35 | learning rate: 5.219E-05 | global batch size: 512 | lm loss: 1.918719E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.013 | TFLOPs: 22.44 | +63: iteration 53510/ 73814 | consumed samples: 27397120 | consumed tokens: 56109301760 | elapsed time per iteration (s): 2.24 | learning rate: 5.217E-05 | global batch size: 512 | lm loss: 1.956576E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.594 | TFLOPs: 23.53 | +63: iteration 53520/ 73814 | consumed samples: 27402240 | consumed tokens: 56119787520 | elapsed time per iteration (s): 2.23 | learning rate: 5.214E-05 | global batch size: 512 | lm loss: 1.945364E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.537 | TFLOPs: 23.63 | +63: iteration 53530/ 73814 | consumed samples: 27407360 | consumed tokens: 56130273280 | elapsed time per iteration (s): 2.22 | learning rate: 5.211E-05 | global batch size: 512 | lm loss: 1.933099E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.268 | TFLOPs: 23.71 | +63: iteration 53540/ 73814 | consumed samples: 27412480 | consumed tokens: 56140759040 | elapsed time per iteration (s): 2.23 | learning rate: 5.208E-05 | global batch size: 512 | lm loss: 1.930367E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.887 | TFLOPs: 23.67 | +63: iteration 53550/ 73814 | consumed samples: 27417600 | consumed tokens: 56151244800 | elapsed time per iteration (s): 2.22 | learning rate: 5.205E-05 | global batch size: 512 | lm loss: 1.941598E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.158 | TFLOPs: 23.69 | +63: iteration 53560/ 73814 | consumed samples: 27422720 | consumed tokens: 56161730560 | elapsed time per iteration (s): 2.22 | learning rate: 5.202E-05 | global batch size: 512 | lm loss: 1.922030E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.139 | TFLOPs: 23.69 | +63: iteration 53570/ 73814 | consumed samples: 27427840 | consumed tokens: 56172216320 | elapsed time per iteration (s): 2.25 | learning rate: 5.199E-05 | global batch size: 512 | lm loss: 1.932816E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.206 | TFLOPs: 23.39 | +63: iteration 53580/ 73814 | consumed samples: 27432960 | consumed tokens: 56182702080 | elapsed time per iteration (s): 2.24 | learning rate: 5.196E-05 | global batch size: 512 | lm loss: 1.925834E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.763 | TFLOPs: 23.55 | +63: iteration 53590/ 73814 | consumed samples: 27438080 | consumed tokens: 56193187840 | elapsed time per iteration (s): 2.23 | learning rate: 5.193E-05 | global batch size: 512 | lm loss: 1.940232E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.927 | TFLOPs: 23.67 | +63: iteration 53600/ 73814 | consumed samples: 27443200 | consumed tokens: 56203673600 | elapsed time per iteration (s): 2.22 | learning rate: 5.190E-05 | global batch size: 512 | lm loss: 1.936303E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.181 | TFLOPs: 23.70 | +63: iteration 53610/ 73814 | consumed samples: 27448320 | consumed tokens: 56214159360 | elapsed time per iteration (s): 2.24 | learning rate: 5.187E-05 | global batch size: 512 | lm loss: 1.923806E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.284 | TFLOPs: 23.50 | +63: iteration 53620/ 73814 | consumed samples: 27453440 | consumed tokens: 56224645120 | elapsed time per iteration (s): 2.28 | learning rate: 5.184E-05 | global batch size: 512 | lm loss: 1.929254E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.320 | TFLOPs: 23.09 | +63: iteration 53630/ 73814 | consumed samples: 27458560 | consumed tokens: 56235130880 | elapsed time per iteration (s): 2.29 | learning rate: 5.181E-05 | global batch size: 512 | lm loss: 1.949050E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.673 | TFLOPs: 23.03 | +63: iteration 53640/ 73814 | consumed samples: 27463680 | consumed tokens: 56245616640 | elapsed time per iteration (s): 2.23 | learning rate: 5.178E-05 | global batch size: 512 | lm loss: 1.923991E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.725 | TFLOPs: 23.65 | +63: iteration 53650/ 73814 | consumed samples: 27468800 | consumed tokens: 56256102400 | elapsed time per iteration (s): 2.25 | learning rate: 5.175E-05 | global batch size: 512 | lm loss: 1.929000E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.350 | TFLOPs: 23.40 | +63: iteration 53660/ 73814 | consumed samples: 27473920 | consumed tokens: 56266588160 | elapsed time per iteration (s): 2.24 | learning rate: 5.172E-05 | global batch size: 512 | lm loss: 1.907322E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.546 | TFLOPs: 23.53 | +63: iteration 53670/ 73814 | consumed samples: 27479040 | consumed tokens: 56277073920 | elapsed time per iteration (s): 2.23 | learning rate: 5.169E-05 | global batch size: 512 | lm loss: 1.904424E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.768 | TFLOPs: 23.65 | +63: iteration 53680/ 73814 | consumed samples: 27484160 | consumed tokens: 56287559680 | elapsed time per iteration (s): 2.28 | learning rate: 5.166E-05 | global batch size: 512 | lm loss: 1.941446E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.875 | TFLOPs: 23.15 | +63: iteration 53690/ 73814 | consumed samples: 27489280 | consumed tokens: 56298045440 | elapsed time per iteration (s): 2.24 | learning rate: 5.163E-05 | global batch size: 512 | lm loss: 1.912819E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.328 | TFLOPs: 23.51 | +63: iteration 53700/ 73814 | consumed samples: 27494400 | consumed tokens: 56308531200 | elapsed time per iteration (s): 2.26 | learning rate: 5.160E-05 | global batch size: 512 | lm loss: 1.920170E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.113 | TFLOPs: 23.28 | +63: iteration 53710/ 73814 | consumed samples: 27499520 | consumed tokens: 56319016960 | elapsed time per iteration (s): 2.29 | learning rate: 5.157E-05 | global batch size: 512 | lm loss: 1.943717E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.484 | TFLOPs: 23.01 | +63: iteration 53720/ 73814 | consumed samples: 27504640 | consumed tokens: 56329502720 | elapsed time per iteration (s): 2.25 | learning rate: 5.155E-05 | global batch size: 512 | lm loss: 1.924791E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.889 | TFLOPs: 23.46 | +63: iteration 53730/ 73814 | consumed samples: 27509760 | consumed tokens: 56339988480 | elapsed time per iteration (s): 2.23 | learning rate: 5.152E-05 | global batch size: 512 | lm loss: 1.910438E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.876 | TFLOPs: 23.66 | +63: iteration 53740/ 73814 | consumed samples: 27514880 | consumed tokens: 56350474240 | elapsed time per iteration (s): 2.23 | learning rate: 5.149E-05 | global batch size: 512 | lm loss: 1.913657E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.917 | TFLOPs: 23.67 | +63: iteration 53750/ 73814 | consumed samples: 27520000 | consumed tokens: 56360960000 | elapsed time per iteration (s): 2.23 | learning rate: 5.146E-05 | global batch size: 512 | lm loss: 1.931589E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.865 | TFLOPs: 23.66 | +63: iteration 53760/ 73814 | consumed samples: 27525120 | consumed tokens: 56371445760 | elapsed time per iteration (s): 2.24 | learning rate: 5.143E-05 | global batch size: 512 | lm loss: 1.936362E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.669 | TFLOPs: 23.54 | +63: iteration 53770/ 73814 | consumed samples: 27530240 | consumed tokens: 56381931520 | elapsed time per iteration (s): 2.23 | learning rate: 5.140E-05 | global batch size: 512 | lm loss: 1.909621E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.764 | TFLOPs: 23.65 | +63: iteration 53780/ 73814 | consumed samples: 27535360 | consumed tokens: 56392417280 | elapsed time per iteration (s): 2.26 | learning rate: 5.137E-05 | global batch size: 512 | lm loss: 1.940369E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.755 | TFLOPs: 23.34 | +63: iteration 53790/ 73814 | consumed samples: 27540480 | consumed tokens: 56402903040 | elapsed time per iteration (s): 2.28 | learning rate: 5.134E-05 | global batch size: 512 | lm loss: 1.941559E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.107 | TFLOPs: 23.07 | +63: iteration 53800/ 73814 | consumed samples: 27545600 | consumed tokens: 56413388800 | elapsed time per iteration (s): 2.35 | learning rate: 5.131E-05 | global batch size: 512 | lm loss: 1.920484E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.519 | TFLOPs: 22.39 | +63: iteration 53810/ 73814 | consumed samples: 27550720 | consumed tokens: 56423874560 | elapsed time per iteration (s): 2.28 | learning rate: 5.128E-05 | global batch size: 512 | lm loss: 1.944615E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.685 | TFLOPs: 23.13 | +63: iteration 53820/ 73814 | consumed samples: 27555840 | consumed tokens: 56434360320 | elapsed time per iteration (s): 2.24 | learning rate: 5.125E-05 | global batch size: 512 | lm loss: 1.931806E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.821 | TFLOPs: 23.56 | +63: iteration 53830/ 73814 | consumed samples: 27560960 | consumed tokens: 56444846080 | elapsed time per iteration (s): 2.26 | learning rate: 5.122E-05 | global batch size: 512 | lm loss: 1.924576E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.566 | TFLOPs: 23.32 | +63: iteration 53840/ 73814 | consumed samples: 27566080 | consumed tokens: 56455331840 | elapsed time per iteration (s): 2.23 | learning rate: 5.119E-05 | global batch size: 512 | lm loss: 1.944370E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.447 | TFLOPs: 23.62 | +63: iteration 53850/ 73814 | consumed samples: 27571200 | consumed tokens: 56465817600 | elapsed time per iteration (s): 2.32 | learning rate: 5.116E-05 | global batch size: 512 | lm loss: 1.945703E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.884 | TFLOPs: 22.74 | +63: iteration 53860/ 73814 | consumed samples: 27576320 | consumed tokens: 56476303360 | elapsed time per iteration (s): 2.25 | learning rate: 5.113E-05 | global batch size: 512 | lm loss: 1.937792E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.945 | TFLOPs: 23.47 | +63: iteration 53870/ 73814 | consumed samples: 27581440 | consumed tokens: 56486789120 | elapsed time per iteration (s): 2.23 | learning rate: 5.110E-05 | global batch size: 512 | lm loss: 1.957179E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.922 | TFLOPs: 23.67 | +63: iteration 53880/ 73814 | consumed samples: 27586560 | consumed tokens: 56497274880 | elapsed time per iteration (s): 2.25 | learning rate: 5.108E-05 | global batch size: 512 | lm loss: 1.918878E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.441 | TFLOPs: 23.41 | +63: iteration 53890/ 73814 | consumed samples: 27591680 | consumed tokens: 56507760640 | elapsed time per iteration (s): 2.24 | learning rate: 5.105E-05 | global batch size: 512 | lm loss: 1.926129E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.109 | TFLOPs: 23.48 | +63: iteration 53900/ 73814 | consumed samples: 27596800 | consumed tokens: 56518246400 | elapsed time per iteration (s): 2.35 | learning rate: 5.102E-05 | global batch size: 512 | lm loss: 1.912858E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.715 | TFLOPs: 22.41 | +63: iteration 53910/ 73814 | consumed samples: 27601920 | consumed tokens: 56528732160 | elapsed time per iteration (s): 4.00 | learning rate: 5.099E-05 | global batch size: 512 | lm loss: 1.907849E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 128.119 | TFLOPs: 13.19 | +63: iteration 53920/ 73814 | consumed samples: 27607040 | consumed tokens: 56539217920 | elapsed time per iteration (s): 2.28 | learning rate: 5.096E-05 | global batch size: 512 | lm loss: 1.925226E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.512 | TFLOPs: 23.11 | +63: iteration 53930/ 73814 | consumed samples: 27612160 | consumed tokens: 56549703680 | elapsed time per iteration (s): 2.34 | learning rate: 5.093E-05 | global batch size: 512 | lm loss: 1.923469E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.377 | TFLOPs: 22.48 | +63: iteration 53940/ 73814 | consumed samples: 27617280 | consumed tokens: 56560189440 | elapsed time per iteration (s): 2.35 | learning rate: 5.090E-05 | global batch size: 512 | lm loss: 1.909413E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.521 | TFLOPs: 22.39 | +63: iteration 53950/ 73814 | consumed samples: 27622400 | consumed tokens: 56570675200 | elapsed time per iteration (s): 2.23 | learning rate: 5.087E-05 | global batch size: 512 | lm loss: 1.933606E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.644 | TFLOPs: 23.64 | +63: iteration 53960/ 73814 | consumed samples: 27627520 | consumed tokens: 56581160960 | elapsed time per iteration (s): 2.26 | learning rate: 5.084E-05 | global batch size: 512 | lm loss: 1.947568E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.573 | TFLOPs: 23.32 | +63: iteration 53970/ 73814 | consumed samples: 27632640 | consumed tokens: 56591646720 | elapsed time per iteration (s): 2.32 | learning rate: 5.081E-05 | global batch size: 512 | lm loss: 1.891072E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.448 | TFLOPs: 22.69 | +63: iteration 53980/ 73814 | consumed samples: 27637760 | consumed tokens: 56602132480 | elapsed time per iteration (s): 2.37 | learning rate: 5.078E-05 | global batch size: 512 | lm loss: 1.919081E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.929 | TFLOPs: 22.23 | +63: iteration 53990/ 73814 | consumed samples: 27642880 | consumed tokens: 56612618240 | elapsed time per iteration (s): 2.24 | learning rate: 5.075E-05 | global batch size: 512 | lm loss: 1.931928E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.574 | TFLOPs: 23.53 | + 0: [2022-12-02 22:11:13,064] [INFO] [logging.py:68:log_dist] [Rank 0] step=54000, skipped=0, lr=[5.072554656345727e-05, 5.072554656345727e-05, 5.072554656345727e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 54000/ 73814 | consumed samples: 27648000 | consumed tokens: 56623104000 | elapsed time per iteration (s): 2.25 | learning rate: 5.073E-05 | global batch size: 512 | lm loss: 1.926645E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.531 | TFLOPs: 23.42 | + 0: steps: 54000 loss: 1.9302 iter time (s): 2.287 samples/sec: 223.852 +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 54000 | lm loss value: 1.825057E+00 | lm loss PPL: 6.203151E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 54010/ 73814 | consumed samples: 27653120 | consumed tokens: 56633589760 | elapsed time per iteration (s): 2.30 | learning rate: 5.070E-05 | global batch size: 512 | lm loss: 1.918237E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.739 | TFLOPs: 22.93 | +63: iteration 54020/ 73814 | consumed samples: 27658240 | consumed tokens: 56644075520 | elapsed time per iteration (s): 2.24 | learning rate: 5.067E-05 | global batch size: 512 | lm loss: 1.953514E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.172 | TFLOPs: 23.49 | +63: iteration 54030/ 73814 | consumed samples: 27663360 | consumed tokens: 56654561280 | elapsed time per iteration (s): 2.23 | learning rate: 5.064E-05 | global batch size: 512 | lm loss: 1.930249E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.094 | TFLOPs: 23.69 | +63: iteration 54040/ 73814 | consumed samples: 27668480 | consumed tokens: 56665047040 | elapsed time per iteration (s): 2.23 | learning rate: 5.061E-05 | global batch size: 512 | lm loss: 1.912397E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.341 | TFLOPs: 23.61 | +63: iteration 54050/ 73814 | consumed samples: 27673600 | consumed tokens: 56675532800 | elapsed time per iteration (s): 2.23 | learning rate: 5.058E-05 | global batch size: 512 | lm loss: 1.921323E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.098 | TFLOPs: 23.58 | +63: iteration 54060/ 73814 | consumed samples: 27678720 | consumed tokens: 56686018560 | elapsed time per iteration (s): 2.26 | learning rate: 5.055E-05 | global batch size: 512 | lm loss: 1.936618E+00 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.517 | TFLOPs: 23.32 | +63: iteration 54070/ 73814 | consumed samples: 27683840 | consumed tokens: 56696504320 | elapsed time per iteration (s): 2.35 | learning rate: 5.052E-05 | global batch size: 512 | lm loss: 1.953156E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.152 | TFLOPs: 22.46 | +63: iteration 54080/ 73814 | consumed samples: 27688960 | consumed tokens: 56706990080 | elapsed time per iteration (s): 2.26 | learning rate: 5.049E-05 | global batch size: 512 | lm loss: 1.920563E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.928 | TFLOPs: 23.36 | +63: iteration 54090/ 73814 | consumed samples: 27694080 | consumed tokens: 56717475840 | elapsed time per iteration (s): 2.37 | learning rate: 5.046E-05 | global batch size: 512 | lm loss: 1.917321E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.093 | TFLOPs: 22.25 | +63: iteration 54100/ 73814 | consumed samples: 27699200 | consumed tokens: 56727961600 | elapsed time per iteration (s): 2.24 | learning rate: 5.043E-05 | global batch size: 512 | lm loss: 1.935909E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.862 | TFLOPs: 23.56 | +63: iteration 54110/ 73814 | consumed samples: 27704320 | consumed tokens: 56738447360 | elapsed time per iteration (s): 2.46 | learning rate: 5.041E-05 | global batch size: 512 | lm loss: 1.932647E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.194 | TFLOPs: 21.43 | +63: iteration 54120/ 73814 | consumed samples: 27709440 | consumed tokens: 56748933120 | elapsed time per iteration (s): 2.23 | learning rate: 5.038E-05 | global batch size: 512 | lm loss: 1.934320E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.542 | TFLOPs: 23.63 | +63: iteration 54130/ 73814 | consumed samples: 27714560 | consumed tokens: 56759418880 | elapsed time per iteration (s): 2.23 | learning rate: 5.035E-05 | global batch size: 512 | lm loss: 1.932211E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.541 | TFLOPs: 23.63 | +63: iteration 54140/ 73814 | consumed samples: 27719680 | consumed tokens: 56769904640 | elapsed time per iteration (s): 2.23 | learning rate: 5.032E-05 | global batch size: 512 | lm loss: 1.903537E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.748 | TFLOPs: 23.65 | +63: iteration 54150/ 73814 | consumed samples: 27724800 | consumed tokens: 56780390400 | elapsed time per iteration (s): 2.35 | learning rate: 5.029E-05 | global batch size: 512 | lm loss: 1.930512E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.657 | TFLOPs: 22.41 | +63: iteration 54160/ 73814 | consumed samples: 27729920 | consumed tokens: 56790876160 | elapsed time per iteration (s): 2.22 | learning rate: 5.026E-05 | global batch size: 512 | lm loss: 1.944210E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.134 | TFLOPs: 23.69 | +63: iteration 54170/ 73814 | consumed samples: 27735040 | consumed tokens: 56801361920 | elapsed time per iteration (s): 2.23 | learning rate: 5.023E-05 | global batch size: 512 | lm loss: 1.929681E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.881 | TFLOPs: 23.67 | +63: iteration 54180/ 73814 | consumed samples: 27740160 | consumed tokens: 56811847680 | elapsed time per iteration (s): 2.24 | learning rate: 5.020E-05 | global batch size: 512 | lm loss: 1.920140E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.559 | TFLOPs: 23.53 | +63: iteration 54190/ 73814 | consumed samples: 27745280 | consumed tokens: 56822333440 | elapsed time per iteration (s): 2.24 | learning rate: 5.017E-05 | global batch size: 512 | lm loss: 1.911279E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.560 | TFLOPs: 23.53 | +63: iteration 54200/ 73814 | consumed samples: 27750400 | consumed tokens: 56832819200 | elapsed time per iteration (s): 2.24 | learning rate: 5.015E-05 | global batch size: 512 | lm loss: 1.913379E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.396 | TFLOPs: 23.51 | +63: iteration 54210/ 73814 | consumed samples: 27755520 | consumed tokens: 56843304960 | elapsed time per iteration (s): 2.30 | learning rate: 5.012E-05 | global batch size: 512 | lm loss: 1.922338E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.327 | TFLOPs: 22.89 | +63: iteration 54220/ 73814 | consumed samples: 27760640 | consumed tokens: 56853790720 | elapsed time per iteration (s): 2.25 | learning rate: 5.009E-05 | global batch size: 512 | lm loss: 1.940116E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.001 | TFLOPs: 23.47 | +63: iteration 54230/ 73814 | consumed samples: 27765760 | consumed tokens: 56864276480 | elapsed time per iteration (s): 2.29 | learning rate: 5.006E-05 | global batch size: 512 | lm loss: 1.929746E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.027 | TFLOPs: 23.06 | +63: iteration 54240/ 73814 | consumed samples: 27770880 | consumed tokens: 56874762240 | elapsed time per iteration (s): 2.39 | learning rate: 5.003E-05 | global batch size: 512 | lm loss: 1.906714E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.354 | TFLOPs: 22.07 | +63: iteration 54250/ 73814 | consumed samples: 27776000 | consumed tokens: 56885248000 | elapsed time per iteration (s): 2.48 | learning rate: 5.000E-05 | global batch size: 512 | lm loss: 1.933789E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.623 | TFLOPs: 21.27 | +63: iteration 54260/ 73814 | consumed samples: 27781120 | consumed tokens: 56895733760 | elapsed time per iteration (s): 2.61 | learning rate: 4.997E-05 | global batch size: 512 | lm loss: 1.921753E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 196.526 | TFLOPs: 20.23 | +63: iteration 54270/ 73814 | consumed samples: 27786240 | consumed tokens: 56906219520 | elapsed time per iteration (s): 2.44 | learning rate: 4.994E-05 | global batch size: 512 | lm loss: 1.937232E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.711 | TFLOPs: 21.59 | +63: iteration 54280/ 73814 | consumed samples: 27791360 | consumed tokens: 56916705280 | elapsed time per iteration (s): 2.68 | learning rate: 4.991E-05 | global batch size: 512 | lm loss: 1.957218E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 190.875 | TFLOPs: 19.65 | +63: iteration 54290/ 73814 | consumed samples: 27796480 | consumed tokens: 56927191040 | elapsed time per iteration (s): 3.00 | learning rate: 4.989E-05 | global batch size: 512 | lm loss: 1.917971E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 170.845 | TFLOPs: 17.59 | +63: iteration 54300/ 73814 | consumed samples: 27801600 | consumed tokens: 56937676800 | elapsed time per iteration (s): 2.39 | learning rate: 4.986E-05 | global batch size: 512 | lm loss: 1.919106E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.178 | TFLOPs: 22.05 | +63: iteration 54310/ 73814 | consumed samples: 27806720 | consumed tokens: 56948162560 | elapsed time per iteration (s): 2.24 | learning rate: 4.983E-05 | global batch size: 512 | lm loss: 1.935763E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.270 | TFLOPs: 23.50 | +63: iteration 54320/ 73814 | consumed samples: 27811840 | consumed tokens: 56958648320 | elapsed time per iteration (s): 2.43 | learning rate: 4.980E-05 | global batch size: 512 | lm loss: 1.909056E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.779 | TFLOPs: 21.70 | +63: iteration 54330/ 73814 | consumed samples: 27816960 | consumed tokens: 56969134080 | elapsed time per iteration (s): 2.41 | learning rate: 4.977E-05 | global batch size: 512 | lm loss: 1.924569E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.132 | TFLOPs: 21.84 | +63: iteration 54340/ 73814 | consumed samples: 27822080 | consumed tokens: 56979619840 | elapsed time per iteration (s): 2.24 | learning rate: 4.974E-05 | global batch size: 512 | lm loss: 1.944172E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.609 | TFLOPs: 23.53 | +63: iteration 54350/ 73814 | consumed samples: 27827200 | consumed tokens: 56990105600 | elapsed time per iteration (s): 2.23 | learning rate: 4.971E-05 | global batch size: 512 | lm loss: 1.900870E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.528 | TFLOPs: 23.63 | +63: iteration 54360/ 73814 | consumed samples: 27832320 | consumed tokens: 57000591360 | elapsed time per iteration (s): 2.29 | learning rate: 4.968E-05 | global batch size: 512 | lm loss: 1.946164E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.540 | TFLOPs: 23.01 | +63: iteration 54370/ 73814 | consumed samples: 27837440 | consumed tokens: 57011077120 | elapsed time per iteration (s): 2.26 | learning rate: 4.966E-05 | global batch size: 512 | lm loss: 1.941814E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.948 | TFLOPs: 23.36 | +63: iteration 54380/ 73814 | consumed samples: 27842560 | consumed tokens: 57021562880 | elapsed time per iteration (s): 2.22 | learning rate: 4.963E-05 | global batch size: 512 | lm loss: 1.943018E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.170 | TFLOPs: 23.69 | +63: iteration 54390/ 73814 | consumed samples: 27847680 | consumed tokens: 57032048640 | elapsed time per iteration (s): 2.23 | learning rate: 4.960E-05 | global batch size: 512 | lm loss: 1.943251E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.739 | TFLOPs: 23.65 | +63: iteration 54400/ 73814 | consumed samples: 27852800 | consumed tokens: 57042534400 | elapsed time per iteration (s): 2.69 | learning rate: 4.957E-05 | global batch size: 512 | lm loss: 1.928489E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 190.074 | TFLOPs: 19.57 | +63: iteration 54410/ 73814 | consumed samples: 27857920 | consumed tokens: 57053020160 | elapsed time per iteration (s): 2.38 | learning rate: 4.954E-05 | global batch size: 512 | lm loss: 1.924327E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.406 | TFLOPs: 22.18 | +63: iteration 54420/ 73814 | consumed samples: 27863040 | consumed tokens: 57063505920 | elapsed time per iteration (s): 2.25 | learning rate: 4.951E-05 | global batch size: 512 | lm loss: 1.906514E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.779 | TFLOPs: 23.45 | +63: iteration 54430/ 73814 | consumed samples: 27868160 | consumed tokens: 57073991680 | elapsed time per iteration (s): 2.28 | learning rate: 4.948E-05 | global batch size: 512 | lm loss: 1.933103E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.617 | TFLOPs: 23.12 | +63: iteration 54440/ 73814 | consumed samples: 27873280 | consumed tokens: 57084477440 | elapsed time per iteration (s): 2.23 | learning rate: 4.946E-05 | global batch size: 512 | lm loss: 1.922507E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.358 | TFLOPs: 23.61 | +63: iteration 54450/ 73814 | consumed samples: 27878400 | consumed tokens: 57094963200 | elapsed time per iteration (s): 2.30 | learning rate: 4.943E-05 | global batch size: 512 | lm loss: 1.911397E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.491 | TFLOPs: 22.90 | +63: iteration 54460/ 73814 | consumed samples: 27883520 | consumed tokens: 57105448960 | elapsed time per iteration (s): 2.24 | learning rate: 4.940E-05 | global batch size: 512 | lm loss: 1.934106E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.254 | TFLOPs: 23.50 | +63: iteration 54470/ 73814 | consumed samples: 27888640 | consumed tokens: 57115934720 | elapsed time per iteration (s): 2.23 | learning rate: 4.937E-05 | global batch size: 512 | lm loss: 1.948278E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.993 | TFLOPs: 23.68 | +63: iteration 54480/ 73814 | consumed samples: 27893760 | consumed tokens: 57126420480 | elapsed time per iteration (s): 2.23 | learning rate: 4.934E-05 | global batch size: 512 | lm loss: 1.934224E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.537 | TFLOPs: 23.63 | +63: iteration 54490/ 73814 | consumed samples: 27898880 | consumed tokens: 57136906240 | elapsed time per iteration (s): 2.25 | learning rate: 4.931E-05 | global batch size: 512 | lm loss: 1.921695E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.226 | TFLOPs: 23.39 | +63: iteration 54500/ 73814 | consumed samples: 27904000 | consumed tokens: 57147392000 | elapsed time per iteration (s): 2.23 | learning rate: 4.928E-05 | global batch size: 512 | lm loss: 1.923920E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.396 | TFLOPs: 23.62 | +63: iteration 54510/ 73814 | consumed samples: 27909120 | consumed tokens: 57157877760 | elapsed time per iteration (s): 2.23 | learning rate: 4.926E-05 | global batch size: 512 | lm loss: 1.923968E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.895 | TFLOPs: 23.67 | +63: iteration 54520/ 73814 | consumed samples: 27914240 | consumed tokens: 57168363520 | elapsed time per iteration (s): 2.24 | learning rate: 4.923E-05 | global batch size: 512 | lm loss: 1.926059E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.310 | TFLOPs: 23.50 | +63: iteration 54530/ 73814 | consumed samples: 27919360 | consumed tokens: 57178849280 | elapsed time per iteration (s): 2.25 | learning rate: 4.920E-05 | global batch size: 512 | lm loss: 1.924399E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.730 | TFLOPs: 23.44 | +63: iteration 54540/ 73814 | consumed samples: 27924480 | consumed tokens: 57189335040 | elapsed time per iteration (s): 2.23 | learning rate: 4.917E-05 | global batch size: 512 | lm loss: 1.927005E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.905 | TFLOPs: 23.67 | +63: iteration 54550/ 73814 | consumed samples: 27929600 | consumed tokens: 57199820800 | elapsed time per iteration (s): 2.23 | learning rate: 4.914E-05 | global batch size: 512 | lm loss: 1.933410E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.872 | TFLOPs: 23.66 | +63: iteration 54560/ 73814 | consumed samples: 27934720 | consumed tokens: 57210306560 | elapsed time per iteration (s): 2.31 | learning rate: 4.911E-05 | global batch size: 512 | lm loss: 1.917921E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.742 | TFLOPs: 22.83 | +63: iteration 54570/ 73814 | consumed samples: 27939840 | consumed tokens: 57220792320 | elapsed time per iteration (s): 2.22 | learning rate: 4.908E-05 | global batch size: 512 | lm loss: 1.945724E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.124 | TFLOPs: 23.69 | +63: iteration 54580/ 73814 | consumed samples: 27944960 | consumed tokens: 57231278080 | elapsed time per iteration (s): 2.23 | learning rate: 4.906E-05 | global batch size: 512 | lm loss: 1.919527E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.942 | TFLOPs: 23.67 | +63: iteration 54590/ 73814 | consumed samples: 27950080 | consumed tokens: 57241763840 | elapsed time per iteration (s): 2.43 | learning rate: 4.903E-05 | global batch size: 512 | lm loss: 1.922888E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.348 | TFLOPs: 21.65 | +63: iteration 54600/ 73814 | consumed samples: 27955200 | consumed tokens: 57252249600 | elapsed time per iteration (s): 2.27 | learning rate: 4.900E-05 | global batch size: 512 | lm loss: 1.931183E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.653 | TFLOPs: 23.23 | +63: iteration 54610/ 73814 | consumed samples: 27960320 | consumed tokens: 57262735360 | elapsed time per iteration (s): 2.31 | learning rate: 4.897E-05 | global batch size: 512 | lm loss: 1.925323E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.262 | TFLOPs: 22.78 | +63: iteration 54620/ 73814 | consumed samples: 27965440 | consumed tokens: 57273221120 | elapsed time per iteration (s): 2.25 | learning rate: 4.894E-05 | global batch size: 512 | lm loss: 1.952535E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.031 | TFLOPs: 23.47 | +63: iteration 54630/ 73814 | consumed samples: 27970560 | consumed tokens: 57283706880 | elapsed time per iteration (s): 2.23 | learning rate: 4.891E-05 | global batch size: 512 | lm loss: 1.914535E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.813 | TFLOPs: 23.66 | +63: iteration 54640/ 73814 | consumed samples: 27975680 | consumed tokens: 57294192640 | elapsed time per iteration (s): 2.23 | learning rate: 4.888E-05 | global batch size: 512 | lm loss: 1.927487E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.669 | TFLOPs: 23.64 | +63: iteration 54650/ 73814 | consumed samples: 27980800 | consumed tokens: 57304678400 | elapsed time per iteration (s): 2.24 | learning rate: 4.886E-05 | global batch size: 512 | lm loss: 1.903778E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.045 | TFLOPs: 23.58 | +63: iteration 54660/ 73814 | consumed samples: 27985920 | consumed tokens: 57315164160 | elapsed time per iteration (s): 2.24 | learning rate: 4.883E-05 | global batch size: 512 | lm loss: 1.935956E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.594 | TFLOPs: 23.53 | +63: iteration 54670/ 73814 | consumed samples: 27991040 | consumed tokens: 57325649920 | elapsed time per iteration (s): 2.23 | learning rate: 4.880E-05 | global batch size: 512 | lm loss: 1.934306E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.424 | TFLOPs: 23.62 | +63: iteration 54680/ 73814 | consumed samples: 27996160 | consumed tokens: 57336135680 | elapsed time per iteration (s): 2.23 | learning rate: 4.877E-05 | global batch size: 512 | lm loss: 1.912980E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.675 | TFLOPs: 23.64 | +63: iteration 54690/ 73814 | consumed samples: 28001280 | consumed tokens: 57346621440 | elapsed time per iteration (s): 2.26 | learning rate: 4.874E-05 | global batch size: 512 | lm loss: 1.908573E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.933 | TFLOPs: 23.36 | +63: iteration 54700/ 73814 | consumed samples: 28006400 | consumed tokens: 57357107200 | elapsed time per iteration (s): 2.24 | learning rate: 4.871E-05 | global batch size: 512 | lm loss: 1.916630E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.622 | TFLOPs: 23.54 | +63: iteration 54710/ 73814 | consumed samples: 28011520 | consumed tokens: 57367592960 | elapsed time per iteration (s): 2.30 | learning rate: 4.869E-05 | global batch size: 512 | lm loss: 1.937270E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.442 | TFLOPs: 22.90 | +63: iteration 54720/ 73814 | consumed samples: 28016640 | consumed tokens: 57378078720 | elapsed time per iteration (s): 2.23 | learning rate: 4.866E-05 | global batch size: 512 | lm loss: 1.920993E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.814 | TFLOPs: 23.66 | +63: iteration 54730/ 73814 | consumed samples: 28021760 | consumed tokens: 57388564480 | elapsed time per iteration (s): 2.32 | learning rate: 4.863E-05 | global batch size: 512 | lm loss: 1.927804E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.403 | TFLOPs: 22.69 | +63: iteration 54740/ 73814 | consumed samples: 28026880 | consumed tokens: 57399050240 | elapsed time per iteration (s): 2.24 | learning rate: 4.860E-05 | global batch size: 512 | lm loss: 1.927980E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.483 | TFLOPs: 23.52 | +63: iteration 54750/ 73814 | consumed samples: 28032000 | consumed tokens: 57409536000 | elapsed time per iteration (s): 2.25 | learning rate: 4.857E-05 | global batch size: 512 | lm loss: 1.919369E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.507 | TFLOPs: 23.42 | +63: iteration 54760/ 73814 | consumed samples: 28037120 | consumed tokens: 57420021760 | elapsed time per iteration (s): 2.24 | learning rate: 4.854E-05 | global batch size: 512 | lm loss: 1.931151E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.269 | TFLOPs: 23.50 | +63: iteration 54770/ 73814 | consumed samples: 28042240 | consumed tokens: 57430507520 | elapsed time per iteration (s): 2.25 | learning rate: 4.852E-05 | global batch size: 512 | lm loss: 1.922598E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.548 | TFLOPs: 23.42 | +63: iteration 54780/ 73814 | consumed samples: 28047360 | consumed tokens: 57440993280 | elapsed time per iteration (s): 2.29 | learning rate: 4.849E-05 | global batch size: 512 | lm loss: 1.925519E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.588 | TFLOPs: 23.02 | +63: iteration 54790/ 73814 | consumed samples: 28052480 | consumed tokens: 57451479040 | elapsed time per iteration (s): 2.24 | learning rate: 4.846E-05 | global batch size: 512 | lm loss: 1.913623E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.488 | TFLOPs: 23.52 | +63: iteration 54800/ 73814 | consumed samples: 28057600 | consumed tokens: 57461964800 | elapsed time per iteration (s): 2.36 | learning rate: 4.843E-05 | global batch size: 512 | lm loss: 1.901151E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.984 | TFLOPs: 22.34 | +63: iteration 54810/ 73814 | consumed samples: 28062720 | consumed tokens: 57472450560 | elapsed time per iteration (s): 2.26 | learning rate: 4.840E-05 | global batch size: 512 | lm loss: 1.934211E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.774 | TFLOPs: 23.35 | +63: iteration 54820/ 73814 | consumed samples: 28067840 | consumed tokens: 57482936320 | elapsed time per iteration (s): 2.25 | learning rate: 4.838E-05 | global batch size: 512 | lm loss: 1.919734E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.618 | TFLOPs: 23.43 | +63: iteration 54830/ 73814 | consumed samples: 28072960 | consumed tokens: 57493422080 | elapsed time per iteration (s): 2.27 | learning rate: 4.835E-05 | global batch size: 512 | lm loss: 1.914581E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.951 | TFLOPs: 23.26 | +63: iteration 54840/ 73814 | consumed samples: 28078080 | consumed tokens: 57503907840 | elapsed time per iteration (s): 2.23 | learning rate: 4.832E-05 | global batch size: 512 | lm loss: 1.913353E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.795 | TFLOPs: 23.66 | +63: iteration 54850/ 73814 | consumed samples: 28083200 | consumed tokens: 57514393600 | elapsed time per iteration (s): 2.24 | learning rate: 4.829E-05 | global batch size: 512 | lm loss: 1.911779E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.989 | TFLOPs: 23.57 | +63: iteration 54860/ 73814 | consumed samples: 28088320 | consumed tokens: 57524879360 | elapsed time per iteration (s): 2.23 | learning rate: 4.826E-05 | global batch size: 512 | lm loss: 1.949169E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.692 | TFLOPs: 23.65 | +63: iteration 54870/ 73814 | consumed samples: 28093440 | consumed tokens: 57535365120 | elapsed time per iteration (s): 2.27 | learning rate: 4.823E-05 | global batch size: 512 | lm loss: 1.897816E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.931 | TFLOPs: 23.26 | +63: iteration 54880/ 73814 | consumed samples: 28098560 | consumed tokens: 57545850880 | elapsed time per iteration (s): 2.24 | learning rate: 4.821E-05 | global batch size: 512 | lm loss: 1.935691E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.912 | TFLOPs: 23.57 | +63: iteration 54890/ 73814 | consumed samples: 28103680 | consumed tokens: 57556336640 | elapsed time per iteration (s): 2.24 | learning rate: 4.818E-05 | global batch size: 512 | lm loss: 1.939024E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.008 | TFLOPs: 23.58 | +63: iteration 54900/ 73814 | consumed samples: 28108800 | consumed tokens: 57566822400 | elapsed time per iteration (s): 2.28 | learning rate: 4.815E-05 | global batch size: 512 | lm loss: 1.933910E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.048 | TFLOPs: 23.17 | +63: iteration 54910/ 73814 | consumed samples: 28113920 | consumed tokens: 57577308160 | elapsed time per iteration (s): 2.21 | learning rate: 4.812E-05 | global batch size: 512 | lm loss: 1.895823E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 232.133 | TFLOPs: 23.90 | +63: iteration 54920/ 73814 | consumed samples: 28119040 | consumed tokens: 57587793920 | elapsed time per iteration (s): 2.24 | learning rate: 4.809E-05 | global batch size: 512 | lm loss: 1.921789E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.442 | TFLOPs: 23.52 | +63: iteration 54930/ 73814 | consumed samples: 28124160 | consumed tokens: 57598279680 | elapsed time per iteration (s): 2.23 | learning rate: 4.807E-05 | global batch size: 512 | lm loss: 1.913789E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.444 | TFLOPs: 23.62 | +63: iteration 54940/ 73814 | consumed samples: 28129280 | consumed tokens: 57608765440 | elapsed time per iteration (s): 2.23 | learning rate: 4.804E-05 | global batch size: 512 | lm loss: 1.908551E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.231 | TFLOPs: 23.60 | +63: iteration 54950/ 73814 | consumed samples: 28134400 | consumed tokens: 57619251200 | elapsed time per iteration (s): 2.24 | learning rate: 4.801E-05 | global batch size: 512 | lm loss: 1.929091E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.297 | TFLOPs: 23.50 | +63: iteration 54960/ 73814 | consumed samples: 28139520 | consumed tokens: 57629736960 | elapsed time per iteration (s): 2.26 | learning rate: 4.798E-05 | global batch size: 512 | lm loss: 1.935479E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.084 | TFLOPs: 23.27 | +63: iteration 54970/ 73814 | consumed samples: 28144640 | consumed tokens: 57640222720 | elapsed time per iteration (s): 2.23 | learning rate: 4.795E-05 | global batch size: 512 | lm loss: 1.917577E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.546 | TFLOPs: 23.63 | +63: iteration 54980/ 73814 | consumed samples: 28149760 | consumed tokens: 57650708480 | elapsed time per iteration (s): 2.24 | learning rate: 4.793E-05 | global batch size: 512 | lm loss: 1.921624E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.560 | TFLOPs: 23.53 | +63: iteration 54990/ 73814 | consumed samples: 28154880 | consumed tokens: 57661194240 | elapsed time per iteration (s): 2.23 | learning rate: 4.790E-05 | global batch size: 512 | lm loss: 1.941606E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.016 | TFLOPs: 23.68 | +63: iteration 55000/ 73814 | consumed samples: 28160000 | consumed tokens: 57671680000 | elapsed time per iteration (s): 2.30 | learning rate: 4.787E-05 | global batch size: 512 | lm loss: 1.925484E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.299 | TFLOPs: 22.88 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 55000 | lm loss value: 1.875230E+00 | lm loss PPL: 6.522320E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 55010/ 73814 | consumed samples: 28165120 | consumed tokens: 57682165760 | elapsed time per iteration (s): 2.43 | learning rate: 4.784E-05 | global batch size: 512 | lm loss: 1.917473E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.406 | TFLOPs: 21.66 | +63: iteration 55020/ 73814 | consumed samples: 28170240 | consumed tokens: 57692651520 | elapsed time per iteration (s): 2.26 | learning rate: 4.781E-05 | global batch size: 512 | lm loss: 1.912395E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.980 | TFLOPs: 23.37 | +63: iteration 55030/ 73814 | consumed samples: 28175360 | consumed tokens: 57703137280 | elapsed time per iteration (s): 2.34 | learning rate: 4.779E-05 | global batch size: 512 | lm loss: 1.917809E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.666 | TFLOPs: 22.51 | +63: iteration 55040/ 73814 | consumed samples: 28180480 | consumed tokens: 57713623040 | elapsed time per iteration (s): 2.31 | learning rate: 4.776E-05 | global batch size: 512 | lm loss: 1.954353E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.710 | TFLOPs: 22.82 | +63: iteration 55050/ 73814 | consumed samples: 28185600 | consumed tokens: 57724108800 | elapsed time per iteration (s): 2.25 | learning rate: 4.773E-05 | global batch size: 512 | lm loss: 1.898188E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.118 | TFLOPs: 23.38 | +63: iteration 55060/ 73814 | consumed samples: 28190720 | consumed tokens: 57734594560 | elapsed time per iteration (s): 2.24 | learning rate: 4.770E-05 | global batch size: 512 | lm loss: 1.913906E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.380 | TFLOPs: 23.51 | +63: iteration 55070/ 73814 | consumed samples: 28195840 | consumed tokens: 57745080320 | elapsed time per iteration (s): 2.24 | learning rate: 4.767E-05 | global batch size: 512 | lm loss: 1.911586E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.811 | TFLOPs: 23.55 | +63: iteration 55080/ 73814 | consumed samples: 28200960 | consumed tokens: 57755566080 | elapsed time per iteration (s): 2.25 | learning rate: 4.765E-05 | global batch size: 512 | lm loss: 1.952175E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.949 | TFLOPs: 23.47 | +63: iteration 55090/ 73814 | consumed samples: 28206080 | consumed tokens: 57766051840 | elapsed time per iteration (s): 2.37 | learning rate: 4.762E-05 | global batch size: 512 | lm loss: 1.945239E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.860 | TFLOPs: 22.22 | +63: iteration 55100/ 73814 | consumed samples: 28211200 | consumed tokens: 57776537600 | elapsed time per iteration (s): 2.54 | learning rate: 4.759E-05 | global batch size: 512 | lm loss: 1.917808E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.637 | TFLOPs: 20.76 | +63: iteration 55110/ 73814 | consumed samples: 28216320 | consumed tokens: 57787023360 | elapsed time per iteration (s): 2.23 | learning rate: 4.756E-05 | global batch size: 512 | lm loss: 1.904787E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.709 | TFLOPs: 23.65 | +63: iteration 55120/ 73814 | consumed samples: 28221440 | consumed tokens: 57797509120 | elapsed time per iteration (s): 2.23 | learning rate: 4.753E-05 | global batch size: 512 | lm loss: 1.915238E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.605 | TFLOPs: 23.64 | +63: iteration 55130/ 73814 | consumed samples: 28226560 | consumed tokens: 57807994880 | elapsed time per iteration (s): 2.23 | learning rate: 4.751E-05 | global batch size: 512 | lm loss: 1.939869E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.043 | TFLOPs: 23.68 | +63: iteration 55140/ 73814 | consumed samples: 28231680 | consumed tokens: 57818480640 | elapsed time per iteration (s): 2.25 | learning rate: 4.748E-05 | global batch size: 512 | lm loss: 1.944000E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.324 | TFLOPs: 23.40 | +63: iteration 55150/ 73814 | consumed samples: 28236800 | consumed tokens: 57828966400 | elapsed time per iteration (s): 2.25 | learning rate: 4.745E-05 | global batch size: 512 | lm loss: 1.921524E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.060 | TFLOPs: 23.48 | +63: iteration 55160/ 73814 | consumed samples: 28241920 | consumed tokens: 57839452160 | elapsed time per iteration (s): 2.36 | learning rate: 4.742E-05 | global batch size: 512 | lm loss: 1.917544E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.516 | TFLOPs: 22.29 | +63: iteration 55170/ 73814 | consumed samples: 28247040 | consumed tokens: 57849937920 | elapsed time per iteration (s): 2.23 | learning rate: 4.740E-05 | global batch size: 512 | lm loss: 1.947260E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.924 | TFLOPs: 23.67 | +63: iteration 55180/ 73814 | consumed samples: 28252160 | consumed tokens: 57860423680 | elapsed time per iteration (s): 2.24 | learning rate: 4.737E-05 | global batch size: 512 | lm loss: 1.943860E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.499 | TFLOPs: 23.52 | +63: iteration 55190/ 73814 | consumed samples: 28257280 | consumed tokens: 57870909440 | elapsed time per iteration (s): 2.23 | learning rate: 4.734E-05 | global batch size: 512 | lm loss: 1.922621E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.916 | TFLOPs: 23.67 | +63: iteration 55200/ 73814 | consumed samples: 28262400 | consumed tokens: 57881395200 | elapsed time per iteration (s): 2.23 | learning rate: 4.731E-05 | global batch size: 512 | lm loss: 1.918291E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.916 | TFLOPs: 23.67 | +63: iteration 55210/ 73814 | consumed samples: 28267520 | consumed tokens: 57891880960 | elapsed time per iteration (s): 2.34 | learning rate: 4.728E-05 | global batch size: 512 | lm loss: 1.931787E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.420 | TFLOPs: 22.49 | +63: iteration 55220/ 73814 | consumed samples: 28272640 | consumed tokens: 57902366720 | elapsed time per iteration (s): 2.34 | learning rate: 4.726E-05 | global batch size: 512 | lm loss: 1.925775E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.625 | TFLOPs: 22.51 | +63: iteration 55230/ 73814 | consumed samples: 28277760 | consumed tokens: 57912852480 | elapsed time per iteration (s): 2.26 | learning rate: 4.723E-05 | global batch size: 512 | lm loss: 1.951874E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.683 | TFLOPs: 23.34 | +63: iteration 55240/ 73814 | consumed samples: 28282880 | consumed tokens: 57923338240 | elapsed time per iteration (s): 2.23 | learning rate: 4.720E-05 | global batch size: 512 | lm loss: 1.907987E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.014 | TFLOPs: 23.68 | +63: iteration 55250/ 73814 | consumed samples: 28288000 | consumed tokens: 57933824000 | elapsed time per iteration (s): 2.23 | learning rate: 4.717E-05 | global batch size: 512 | lm loss: 1.938887E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.567 | TFLOPs: 23.63 | +63: iteration 55260/ 73814 | consumed samples: 28293120 | consumed tokens: 57944309760 | elapsed time per iteration (s): 2.23 | learning rate: 4.715E-05 | global batch size: 512 | lm loss: 1.939688E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.570 | TFLOPs: 23.63 | +63: iteration 55270/ 73814 | consumed samples: 28298240 | consumed tokens: 57954795520 | elapsed time per iteration (s): 2.23 | learning rate: 4.712E-05 | global batch size: 512 | lm loss: 1.924645E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.474 | TFLOPs: 23.62 | +63: iteration 55280/ 73814 | consumed samples: 28303360 | consumed tokens: 57965281280 | elapsed time per iteration (s): 2.23 | learning rate: 4.709E-05 | global batch size: 512 | lm loss: 1.920112E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.771 | TFLOPs: 23.65 | +63: iteration 55290/ 73814 | consumed samples: 28308480 | consumed tokens: 57975767040 | elapsed time per iteration (s): 2.24 | learning rate: 4.706E-05 | global batch size: 512 | lm loss: 1.923482E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.502 | TFLOPs: 23.52 | +63: iteration 55300/ 73814 | consumed samples: 28313600 | consumed tokens: 57986252800 | elapsed time per iteration (s): 2.23 | learning rate: 4.704E-05 | global batch size: 512 | lm loss: 1.914827E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.134 | TFLOPs: 23.59 | +63: iteration 55310/ 73814 | consumed samples: 28318720 | consumed tokens: 57996738560 | elapsed time per iteration (s): 2.24 | learning rate: 4.701E-05 | global batch size: 512 | lm loss: 1.930659E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.709 | TFLOPs: 23.54 | +63: iteration 55320/ 73814 | consumed samples: 28323840 | consumed tokens: 58007224320 | elapsed time per iteration (s): 2.24 | learning rate: 4.698E-05 | global batch size: 512 | lm loss: 1.930711E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.411 | TFLOPs: 23.51 | +63: iteration 55330/ 73814 | consumed samples: 28328960 | consumed tokens: 58017710080 | elapsed time per iteration (s): 2.23 | learning rate: 4.695E-05 | global batch size: 512 | lm loss: 1.914248E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.397 | TFLOPs: 23.62 | +63: iteration 55340/ 73814 | consumed samples: 28334080 | consumed tokens: 58028195840 | elapsed time per iteration (s): 2.30 | learning rate: 4.692E-05 | global batch size: 512 | lm loss: 1.920974E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.387 | TFLOPs: 22.89 | +63: iteration 55350/ 73814 | consumed samples: 28339200 | consumed tokens: 58038681600 | elapsed time per iteration (s): 2.24 | learning rate: 4.690E-05 | global batch size: 512 | lm loss: 1.928082E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.379 | TFLOPs: 23.51 | +63: iteration 55360/ 73814 | consumed samples: 28344320 | consumed tokens: 58049167360 | elapsed time per iteration (s): 2.23 | learning rate: 4.687E-05 | global batch size: 512 | lm loss: 1.912104E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.319 | TFLOPs: 23.61 | +63: iteration 55370/ 73814 | consumed samples: 28349440 | consumed tokens: 58059653120 | elapsed time per iteration (s): 2.26 | learning rate: 4.684E-05 | global batch size: 512 | lm loss: 1.929148E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.309 | TFLOPs: 23.30 | +63: iteration 55380/ 73814 | consumed samples: 28354560 | consumed tokens: 58070138880 | elapsed time per iteration (s): 2.41 | learning rate: 4.681E-05 | global batch size: 512 | lm loss: 1.928849E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.508 | TFLOPs: 21.88 | +63: iteration 55390/ 73814 | consumed samples: 28359680 | consumed tokens: 58080624640 | elapsed time per iteration (s): 2.23 | learning rate: 4.679E-05 | global batch size: 512 | lm loss: 1.919068E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.777 | TFLOPs: 23.65 | +63: iteration 55400/ 73814 | consumed samples: 28364800 | consumed tokens: 58091110400 | elapsed time per iteration (s): 2.26 | learning rate: 4.676E-05 | global batch size: 512 | lm loss: 1.921689E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.474 | TFLOPs: 23.31 | +63: iteration 55410/ 73814 | consumed samples: 28369920 | consumed tokens: 58101596160 | elapsed time per iteration (s): 2.29 | learning rate: 4.673E-05 | global batch size: 512 | lm loss: 1.921418E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.908 | TFLOPs: 23.05 | +63: iteration 55420/ 73814 | consumed samples: 28375040 | consumed tokens: 58112081920 | elapsed time per iteration (s): 2.33 | learning rate: 4.670E-05 | global batch size: 512 | lm loss: 1.947896E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.012 | TFLOPs: 22.65 | +63: iteration 55430/ 73814 | consumed samples: 28380160 | consumed tokens: 58122567680 | elapsed time per iteration (s): 2.24 | learning rate: 4.668E-05 | global batch size: 512 | lm loss: 1.913787E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.737 | TFLOPs: 23.55 | +63: iteration 55440/ 73814 | consumed samples: 28385280 | consumed tokens: 58133053440 | elapsed time per iteration (s): 2.25 | learning rate: 4.665E-05 | global batch size: 512 | lm loss: 1.939889E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.198 | TFLOPs: 23.39 | +63: iteration 55450/ 73814 | consumed samples: 28390400 | consumed tokens: 58143539200 | elapsed time per iteration (s): 2.24 | learning rate: 4.662E-05 | global batch size: 512 | lm loss: 1.917869E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.064 | TFLOPs: 23.58 | +63: iteration 55460/ 73814 | consumed samples: 28395520 | consumed tokens: 58154024960 | elapsed time per iteration (s): 2.23 | learning rate: 4.659E-05 | global batch size: 512 | lm loss: 1.950478E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.492 | TFLOPs: 23.63 | +63: iteration 55470/ 73814 | consumed samples: 28400640 | consumed tokens: 58164510720 | elapsed time per iteration (s): 2.22 | learning rate: 4.657E-05 | global batch size: 512 | lm loss: 1.927190E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.279 | TFLOPs: 23.71 | +63: iteration 55480/ 73814 | consumed samples: 28405760 | consumed tokens: 58174996480 | elapsed time per iteration (s): 2.23 | learning rate: 4.654E-05 | global batch size: 512 | lm loss: 1.920015E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.303 | TFLOPs: 23.61 | +63: iteration 55490/ 73814 | consumed samples: 28410880 | consumed tokens: 58185482240 | elapsed time per iteration (s): 2.23 | learning rate: 4.651E-05 | global batch size: 512 | lm loss: 1.937897E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.675 | TFLOPs: 23.64 | +63: iteration 55500/ 73814 | consumed samples: 28416000 | consumed tokens: 58195968000 | elapsed time per iteration (s): 2.22 | learning rate: 4.648E-05 | global batch size: 512 | lm loss: 1.918457E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.210 | TFLOPs: 23.70 | +63: iteration 55510/ 73814 | consumed samples: 28421120 | consumed tokens: 58206453760 | elapsed time per iteration (s): 2.35 | learning rate: 4.646E-05 | global batch size: 512 | lm loss: 1.896960E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.590 | TFLOPs: 22.40 | +63: iteration 55520/ 73814 | consumed samples: 28426240 | consumed tokens: 58216939520 | elapsed time per iteration (s): 2.23 | learning rate: 4.643E-05 | global batch size: 512 | lm loss: 1.937639E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.048 | TFLOPs: 23.68 | +63: iteration 55530/ 73814 | consumed samples: 28431360 | consumed tokens: 58227425280 | elapsed time per iteration (s): 2.34 | learning rate: 4.640E-05 | global batch size: 512 | lm loss: 1.936832E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.350 | TFLOPs: 22.48 | +63: iteration 55540/ 73814 | consumed samples: 28436480 | consumed tokens: 58237911040 | elapsed time per iteration (s): 2.27 | learning rate: 4.637E-05 | global batch size: 512 | lm loss: 1.934876E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.656 | TFLOPs: 23.23 | +63: iteration 55550/ 73814 | consumed samples: 28441600 | consumed tokens: 58248396800 | elapsed time per iteration (s): 2.28 | learning rate: 4.635E-05 | global batch size: 512 | lm loss: 1.900076E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.526 | TFLOPs: 23.11 | +63: iteration 55560/ 73814 | consumed samples: 28446720 | consumed tokens: 58258882560 | elapsed time per iteration (s): 2.25 | learning rate: 4.632E-05 | global batch size: 512 | lm loss: 1.922059E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.857 | TFLOPs: 23.46 | +63: iteration 55570/ 73814 | consumed samples: 28451840 | consumed tokens: 58269368320 | elapsed time per iteration (s): 2.24 | learning rate: 4.629E-05 | global batch size: 512 | lm loss: 1.930169E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.775 | TFLOPs: 23.55 | +63: iteration 55580/ 73814 | consumed samples: 28456960 | consumed tokens: 58279854080 | elapsed time per iteration (s): 2.23 | learning rate: 4.627E-05 | global batch size: 512 | lm loss: 1.935861E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.513 | TFLOPs: 23.63 | +63: iteration 55590/ 73814 | consumed samples: 28462080 | consumed tokens: 58290339840 | elapsed time per iteration (s): 2.24 | learning rate: 4.624E-05 | global batch size: 512 | lm loss: 1.934272E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.056 | TFLOPs: 23.58 | +63: iteration 55600/ 73814 | consumed samples: 28467200 | consumed tokens: 58300825600 | elapsed time per iteration (s): 2.52 | learning rate: 4.621E-05 | global batch size: 512 | lm loss: 1.920459E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 203.057 | TFLOPs: 20.90 | +63: iteration 55610/ 73814 | consumed samples: 28472320 | consumed tokens: 58311311360 | elapsed time per iteration (s): 2.23 | learning rate: 4.618E-05 | global batch size: 512 | lm loss: 1.937486E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.555 | TFLOPs: 23.63 | +63: iteration 55620/ 73814 | consumed samples: 28477440 | consumed tokens: 58321797120 | elapsed time per iteration (s): 2.24 | learning rate: 4.616E-05 | global batch size: 512 | lm loss: 1.912107E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.722 | TFLOPs: 23.55 | +63: iteration 55630/ 73814 | consumed samples: 28482560 | consumed tokens: 58332282880 | elapsed time per iteration (s): 2.33 | learning rate: 4.613E-05 | global batch size: 512 | lm loss: 1.928309E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.483 | TFLOPs: 22.59 | +63: iteration 55640/ 73814 | consumed samples: 28487680 | consumed tokens: 58342768640 | elapsed time per iteration (s): 2.27 | learning rate: 4.610E-05 | global batch size: 512 | lm loss: 1.909038E+00 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.890 | TFLOPs: 23.25 | +63: iteration 55650/ 73814 | consumed samples: 28492800 | consumed tokens: 58353254400 | elapsed time per iteration (s): 2.32 | learning rate: 4.607E-05 | global batch size: 512 | lm loss: 1.928150E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.085 | TFLOPs: 22.76 | +63: iteration 55660/ 73814 | consumed samples: 28497920 | consumed tokens: 58363740160 | elapsed time per iteration (s): 2.24 | learning rate: 4.605E-05 | global batch size: 512 | lm loss: 1.917152E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.658 | TFLOPs: 23.54 | +63: iteration 55670/ 73814 | consumed samples: 28503040 | consumed tokens: 58374225920 | elapsed time per iteration (s): 2.24 | learning rate: 4.602E-05 | global batch size: 512 | lm loss: 1.926186E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.875 | TFLOPs: 23.56 | +63: iteration 55680/ 73814 | consumed samples: 28508160 | consumed tokens: 58384711680 | elapsed time per iteration (s): 2.33 | learning rate: 4.599E-05 | global batch size: 512 | lm loss: 1.909090E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.525 | TFLOPs: 22.60 | +63: iteration 55690/ 73814 | consumed samples: 28513280 | consumed tokens: 58395197440 | elapsed time per iteration (s): 2.46 | learning rate: 4.597E-05 | global batch size: 512 | lm loss: 1.907549E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 207.783 | TFLOPs: 21.39 | +63: iteration 55700/ 73814 | consumed samples: 28518400 | consumed tokens: 58405683200 | elapsed time per iteration (s): 2.24 | learning rate: 4.594E-05 | global batch size: 512 | lm loss: 1.926979E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.599 | TFLOPs: 23.53 | +63: iteration 55710/ 73814 | consumed samples: 28523520 | consumed tokens: 58416168960 | elapsed time per iteration (s): 2.23 | learning rate: 4.591E-05 | global batch size: 512 | lm loss: 1.910886E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.492 | TFLOPs: 23.63 | +63: iteration 55720/ 73814 | consumed samples: 28528640 | consumed tokens: 58426654720 | elapsed time per iteration (s): 2.35 | learning rate: 4.588E-05 | global batch size: 512 | lm loss: 1.945223E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.423 | TFLOPs: 22.38 | +63: iteration 55730/ 73814 | consumed samples: 28533760 | consumed tokens: 58437140480 | elapsed time per iteration (s): 2.23 | learning rate: 4.586E-05 | global batch size: 512 | lm loss: 1.927956E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.686 | TFLOPs: 23.65 | +63: iteration 55740/ 73814 | consumed samples: 28538880 | consumed tokens: 58447626240 | elapsed time per iteration (s): 2.22 | learning rate: 4.583E-05 | global batch size: 512 | lm loss: 1.908764E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.349 | TFLOPs: 23.71 | +63: iteration 55750/ 73814 | consumed samples: 28544000 | consumed tokens: 58458112000 | elapsed time per iteration (s): 2.24 | learning rate: 4.580E-05 | global batch size: 512 | lm loss: 1.936666E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.103 | TFLOPs: 23.48 | +63: iteration 55760/ 73814 | consumed samples: 28549120 | consumed tokens: 58468597760 | elapsed time per iteration (s): 2.26 | learning rate: 4.578E-05 | global batch size: 512 | lm loss: 1.956060E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.786 | TFLOPs: 23.35 | +63: iteration 55770/ 73814 | consumed samples: 28554240 | consumed tokens: 58479083520 | elapsed time per iteration (s): 2.22 | learning rate: 4.575E-05 | global batch size: 512 | lm loss: 1.917770E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.410 | TFLOPs: 23.72 | +63: iteration 55780/ 73814 | consumed samples: 28559360 | consumed tokens: 58489569280 | elapsed time per iteration (s): 2.23 | learning rate: 4.572E-05 | global batch size: 512 | lm loss: 1.899411E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.294 | TFLOPs: 23.60 | +63: iteration 55790/ 73814 | consumed samples: 28564480 | consumed tokens: 58500055040 | elapsed time per iteration (s): 2.27 | learning rate: 4.569E-05 | global batch size: 512 | lm loss: 1.939742E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.382 | TFLOPs: 23.20 | +63: iteration 55800/ 73814 | consumed samples: 28569600 | consumed tokens: 58510540800 | elapsed time per iteration (s): 2.39 | learning rate: 4.567E-05 | global batch size: 512 | lm loss: 1.924112E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.048 | TFLOPs: 22.04 | +63: iteration 55810/ 73814 | consumed samples: 28574720 | consumed tokens: 58521026560 | elapsed time per iteration (s): 2.26 | learning rate: 4.564E-05 | global batch size: 512 | lm loss: 1.921491E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.355 | TFLOPs: 23.30 | +63: iteration 55820/ 73814 | consumed samples: 28579840 | consumed tokens: 58531512320 | elapsed time per iteration (s): 2.41 | learning rate: 4.561E-05 | global batch size: 512 | lm loss: 1.902431E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.589 | TFLOPs: 21.89 | +63: iteration 55830/ 73814 | consumed samples: 28584960 | consumed tokens: 58541998080 | elapsed time per iteration (s): 2.24 | learning rate: 4.559E-05 | global batch size: 512 | lm loss: 1.948915E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.347 | TFLOPs: 23.51 | +63: iteration 55840/ 73814 | consumed samples: 28590080 | consumed tokens: 58552483840 | elapsed time per iteration (s): 2.23 | learning rate: 4.556E-05 | global batch size: 512 | lm loss: 1.921811E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.561 | TFLOPs: 23.63 | +63: iteration 55850/ 73814 | consumed samples: 28595200 | consumed tokens: 58562969600 | elapsed time per iteration (s): 2.23 | learning rate: 4.553E-05 | global batch size: 512 | lm loss: 1.932152E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.082 | TFLOPs: 23.69 | +63: iteration 55860/ 73814 | consumed samples: 28600320 | consumed tokens: 58573455360 | elapsed time per iteration (s): 2.24 | learning rate: 4.551E-05 | global batch size: 512 | lm loss: 1.894151E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.902 | TFLOPs: 23.56 | +63: iteration 55870/ 73814 | consumed samples: 28605440 | consumed tokens: 58583941120 | elapsed time per iteration (s): 2.23 | learning rate: 4.548E-05 | global batch size: 512 | lm loss: 1.917537E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.332 | TFLOPs: 23.61 | +63: iteration 55880/ 73814 | consumed samples: 28610560 | consumed tokens: 58594426880 | elapsed time per iteration (s): 2.25 | learning rate: 4.545E-05 | global batch size: 512 | lm loss: 1.918753E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.023 | TFLOPs: 23.47 | +63: iteration 55890/ 73814 | consumed samples: 28615680 | consumed tokens: 58604912640 | elapsed time per iteration (s): 2.24 | learning rate: 4.542E-05 | global batch size: 512 | lm loss: 1.917236E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.248 | TFLOPs: 23.50 | +63: iteration 55900/ 73814 | consumed samples: 28620800 | consumed tokens: 58615398400 | elapsed time per iteration (s): 2.25 | learning rate: 4.540E-05 | global batch size: 512 | lm loss: 1.929792E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.963 | TFLOPs: 23.47 | +63: iteration 55910/ 73814 | consumed samples: 28625920 | consumed tokens: 58625884160 | elapsed time per iteration (s): 2.24 | learning rate: 4.537E-05 | global batch size: 512 | lm loss: 1.936035E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.216 | TFLOPs: 23.49 | +63: iteration 55920/ 73814 | consumed samples: 28631040 | consumed tokens: 58636369920 | elapsed time per iteration (s): 2.26 | learning rate: 4.534E-05 | global batch size: 512 | lm loss: 1.913421E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.525 | TFLOPs: 23.32 | +63: iteration 55930/ 73814 | consumed samples: 28636160 | consumed tokens: 58646855680 | elapsed time per iteration (s): 2.25 | learning rate: 4.532E-05 | global batch size: 512 | lm loss: 1.902949E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.076 | TFLOPs: 23.38 | +63: iteration 55940/ 73814 | consumed samples: 28641280 | consumed tokens: 58657341440 | elapsed time per iteration (s): 2.26 | learning rate: 4.529E-05 | global batch size: 512 | lm loss: 1.940603E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.698 | TFLOPs: 23.34 | +63: iteration 55950/ 73814 | consumed samples: 28646400 | consumed tokens: 58667827200 | elapsed time per iteration (s): 2.41 | learning rate: 4.526E-05 | global batch size: 512 | lm loss: 1.916732E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.668 | TFLOPs: 21.89 | +63: iteration 55960/ 73814 | consumed samples: 28651520 | consumed tokens: 58678312960 | elapsed time per iteration (s): 2.23 | learning rate: 4.524E-05 | global batch size: 512 | lm loss: 1.924962E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.337 | TFLOPs: 23.61 | +63: iteration 55970/ 73814 | consumed samples: 28656640 | consumed tokens: 58688798720 | elapsed time per iteration (s): 2.74 | learning rate: 4.521E-05 | global batch size: 512 | lm loss: 1.925915E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 187.048 | TFLOPs: 19.26 | +63: iteration 55980/ 73814 | consumed samples: 28661760 | consumed tokens: 58699284480 | elapsed time per iteration (s): 2.31 | learning rate: 4.518E-05 | global batch size: 512 | lm loss: 1.918648E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.242 | TFLOPs: 22.78 | +63: iteration 55990/ 73814 | consumed samples: 28666880 | consumed tokens: 58709770240 | elapsed time per iteration (s): 2.70 | learning rate: 4.516E-05 | global batch size: 512 | lm loss: 1.903590E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 189.496 | TFLOPs: 19.51 | + 0: [2022-12-02 23:27:28,946] [INFO] [logging.py:68:log_dist] [Rank 0] step=56000, skipped=0, lr=[4.5128693043169876e-05, 4.5128693043169876e-05, 4.5128693043169876e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 56000/ 73814 | consumed samples: 28672000 | consumed tokens: 58720256000 | elapsed time per iteration (s): 2.94 | learning rate: 4.513E-05 | global batch size: 512 | lm loss: 1.938270E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 174.300 | TFLOPs: 17.94 | + 0: steps: 56000 loss: 1.9581 iter time (s): 2.285 samples/sec: 224.037 +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 56000 | lm loss value: 1.828261E+00 | lm loss PPL: 6.223058E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 56010/ 73814 | consumed samples: 28677120 | consumed tokens: 58730741760 | elapsed time per iteration (s): 2.49 | learning rate: 4.510E-05 | global batch size: 512 | lm loss: 1.934245E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.767 | TFLOPs: 21.18 | +63: iteration 56020/ 73814 | consumed samples: 28682240 | consumed tokens: 58741227520 | elapsed time per iteration (s): 2.23 | learning rate: 4.508E-05 | global batch size: 512 | lm loss: 1.912726E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.354 | TFLOPs: 23.61 | +63: iteration 56030/ 73814 | consumed samples: 28687360 | consumed tokens: 58751713280 | elapsed time per iteration (s): 2.53 | learning rate: 4.505E-05 | global batch size: 512 | lm loss: 1.926781E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.551 | TFLOPs: 20.85 | +63: iteration 56040/ 73814 | consumed samples: 28692480 | consumed tokens: 58762199040 | elapsed time per iteration (s): 2.25 | learning rate: 4.502E-05 | global batch size: 512 | lm loss: 1.921815E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.851 | TFLOPs: 23.46 | +63: iteration 56050/ 73814 | consumed samples: 28697600 | consumed tokens: 58772684800 | elapsed time per iteration (s): 2.25 | learning rate: 4.499E-05 | global batch size: 512 | lm loss: 1.939925E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.695 | TFLOPs: 23.44 | +63: iteration 56060/ 73814 | consumed samples: 28702720 | consumed tokens: 58783170560 | elapsed time per iteration (s): 2.23 | learning rate: 4.497E-05 | global batch size: 512 | lm loss: 1.927343E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.461 | TFLOPs: 23.62 | +63: iteration 56070/ 73814 | consumed samples: 28707840 | consumed tokens: 58793656320 | elapsed time per iteration (s): 2.24 | learning rate: 4.494E-05 | global batch size: 512 | lm loss: 1.925109E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.773 | TFLOPs: 23.55 | +63: iteration 56080/ 73814 | consumed samples: 28712960 | consumed tokens: 58804142080 | elapsed time per iteration (s): 2.25 | learning rate: 4.491E-05 | global batch size: 512 | lm loss: 1.894778E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.309 | TFLOPs: 23.40 | +63: iteration 56090/ 73814 | consumed samples: 28718080 | consumed tokens: 58814627840 | elapsed time per iteration (s): 2.22 | learning rate: 4.489E-05 | global batch size: 512 | lm loss: 1.940570E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.290 | TFLOPs: 23.71 | +63: iteration 56100/ 73814 | consumed samples: 28723200 | consumed tokens: 58825113600 | elapsed time per iteration (s): 2.23 | learning rate: 4.486E-05 | global batch size: 512 | lm loss: 1.913739E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.813 | TFLOPs: 23.66 | +63: iteration 56110/ 73814 | consumed samples: 28728320 | consumed tokens: 58835599360 | elapsed time per iteration (s): 2.59 | learning rate: 4.483E-05 | global batch size: 512 | lm loss: 1.908468E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 197.918 | TFLOPs: 20.37 | +63: iteration 56120/ 73814 | consumed samples: 28733440 | consumed tokens: 58846085120 | elapsed time per iteration (s): 2.35 | learning rate: 4.481E-05 | global batch size: 512 | lm loss: 1.913636E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.041 | TFLOPs: 22.45 | +63: iteration 56130/ 73814 | consumed samples: 28738560 | consumed tokens: 58856570880 | elapsed time per iteration (s): 2.24 | learning rate: 4.478E-05 | global batch size: 512 | lm loss: 1.920506E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.207 | TFLOPs: 23.49 | +63: iteration 56140/ 73814 | consumed samples: 28743680 | consumed tokens: 58867056640 | elapsed time per iteration (s): 2.23 | learning rate: 4.475E-05 | global batch size: 512 | lm loss: 1.923118E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.717 | TFLOPs: 23.65 | +63: iteration 56150/ 73814 | consumed samples: 28748800 | consumed tokens: 58877542400 | elapsed time per iteration (s): 2.49 | learning rate: 4.473E-05 | global batch size: 512 | lm loss: 1.920173E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.986 | TFLOPs: 21.21 | +63: iteration 56160/ 73814 | consumed samples: 28753920 | consumed tokens: 58888028160 | elapsed time per iteration (s): 2.23 | learning rate: 4.470E-05 | global batch size: 512 | lm loss: 1.920465E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.505 | TFLOPs: 23.63 | +63: iteration 56170/ 73814 | consumed samples: 28759040 | consumed tokens: 58898513920 | elapsed time per iteration (s): 2.29 | learning rate: 4.467E-05 | global batch size: 512 | lm loss: 1.930567E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.095 | TFLOPs: 22.97 | +63: iteration 56180/ 73814 | consumed samples: 28764160 | consumed tokens: 58908999680 | elapsed time per iteration (s): 2.24 | learning rate: 4.465E-05 | global batch size: 512 | lm loss: 1.931525E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.311 | TFLOPs: 23.50 | +63: iteration 56190/ 73814 | consumed samples: 28769280 | consumed tokens: 58919485440 | elapsed time per iteration (s): 2.23 | learning rate: 4.462E-05 | global batch size: 512 | lm loss: 1.919547E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.817 | TFLOPs: 23.66 | +63: iteration 56200/ 73814 | consumed samples: 28774400 | consumed tokens: 58929971200 | elapsed time per iteration (s): 2.23 | learning rate: 4.459E-05 | global batch size: 512 | lm loss: 1.898583E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.301 | TFLOPs: 23.61 | +63: iteration 56210/ 73814 | consumed samples: 28779520 | consumed tokens: 58940456960 | elapsed time per iteration (s): 2.24 | learning rate: 4.457E-05 | global batch size: 512 | lm loss: 1.917062E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.192 | TFLOPs: 23.49 | +63: iteration 56220/ 73814 | consumed samples: 28784640 | consumed tokens: 58950942720 | elapsed time per iteration (s): 2.23 | learning rate: 4.454E-05 | global batch size: 512 | lm loss: 1.919583E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.813 | TFLOPs: 23.66 | +63: iteration 56230/ 73814 | consumed samples: 28789760 | consumed tokens: 58961428480 | elapsed time per iteration (s): 2.25 | learning rate: 4.452E-05 | global batch size: 512 | lm loss: 1.911476E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.305 | TFLOPs: 23.40 | +63: iteration 56240/ 73814 | consumed samples: 28794880 | consumed tokens: 58971914240 | elapsed time per iteration (s): 2.23 | learning rate: 4.449E-05 | global batch size: 512 | lm loss: 1.942619E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.647 | TFLOPs: 23.64 | +63: iteration 56250/ 73814 | consumed samples: 28800000 | consumed tokens: 58982400000 | elapsed time per iteration (s): 3.83 | learning rate: 4.446E-05 | global batch size: 512 | lm loss: 1.919018E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 133.640 | TFLOPs: 13.76 | +63: iteration 56260/ 73814 | consumed samples: 28805120 | consumed tokens: 58992885760 | elapsed time per iteration (s): 2.46 | learning rate: 4.444E-05 | global batch size: 512 | lm loss: 1.925635E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 207.950 | TFLOPs: 21.41 | +63: iteration 56270/ 73814 | consumed samples: 28810240 | consumed tokens: 59003371520 | elapsed time per iteration (s): 2.30 | learning rate: 4.441E-05 | global batch size: 512 | lm loss: 1.937822E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.470 | TFLOPs: 22.90 | +63: iteration 56280/ 73814 | consumed samples: 28815360 | consumed tokens: 59013857280 | elapsed time per iteration (s): 2.25 | learning rate: 4.438E-05 | global batch size: 512 | lm loss: 1.930668E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.767 | TFLOPs: 23.45 | +63: iteration 56290/ 73814 | consumed samples: 28820480 | consumed tokens: 59024343040 | elapsed time per iteration (s): 2.23 | learning rate: 4.436E-05 | global batch size: 512 | lm loss: 1.907110E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.113 | TFLOPs: 23.59 | +63: iteration 56300/ 73814 | consumed samples: 28825600 | consumed tokens: 59034828800 | elapsed time per iteration (s): 2.38 | learning rate: 4.433E-05 | global batch size: 512 | lm loss: 1.915808E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.311 | TFLOPs: 22.17 | +63: iteration 56310/ 73814 | consumed samples: 28830720 | consumed tokens: 59045314560 | elapsed time per iteration (s): 2.27 | learning rate: 4.430E-05 | global batch size: 512 | lm loss: 1.881768E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.217 | TFLOPs: 23.19 | +63: iteration 56320/ 73814 | consumed samples: 28835840 | consumed tokens: 59055800320 | elapsed time per iteration (s): 2.29 | learning rate: 4.428E-05 | global batch size: 512 | lm loss: 1.928647E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.228 | TFLOPs: 22.98 | +63: iteration 56330/ 73814 | consumed samples: 28840960 | consumed tokens: 59066286080 | elapsed time per iteration (s): 2.24 | learning rate: 4.425E-05 | global batch size: 512 | lm loss: 1.932394E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.103 | TFLOPs: 23.48 | +63: iteration 56340/ 73814 | consumed samples: 28846080 | consumed tokens: 59076771840 | elapsed time per iteration (s): 2.23 | learning rate: 4.422E-05 | global batch size: 512 | lm loss: 1.888380E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.937 | TFLOPs: 23.67 | +63: iteration 56350/ 73814 | consumed samples: 28851200 | consumed tokens: 59087257600 | elapsed time per iteration (s): 2.22 | learning rate: 4.420E-05 | global batch size: 512 | lm loss: 1.933551E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.140 | TFLOPs: 23.69 | +63: iteration 56360/ 73814 | consumed samples: 28856320 | consumed tokens: 59097743360 | elapsed time per iteration (s): 2.23 | learning rate: 4.417E-05 | global batch size: 512 | lm loss: 1.914341E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.414 | TFLOPs: 23.62 | +63: iteration 56370/ 73814 | consumed samples: 28861440 | consumed tokens: 59108229120 | elapsed time per iteration (s): 2.23 | learning rate: 4.414E-05 | global batch size: 512 | lm loss: 1.931487E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.644 | TFLOPs: 23.64 | +63: iteration 56380/ 73814 | consumed samples: 28866560 | consumed tokens: 59118714880 | elapsed time per iteration (s): 2.24 | learning rate: 4.412E-05 | global batch size: 512 | lm loss: 1.906055E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.395 | TFLOPs: 23.51 | +63: iteration 56390/ 73814 | consumed samples: 28871680 | consumed tokens: 59129200640 | elapsed time per iteration (s): 2.26 | learning rate: 4.409E-05 | global batch size: 512 | lm loss: 1.927312E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.295 | TFLOPs: 23.30 | +63: iteration 56400/ 73814 | consumed samples: 28876800 | consumed tokens: 59139686400 | elapsed time per iteration (s): 2.27 | learning rate: 4.407E-05 | global batch size: 512 | lm loss: 1.925198E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.623 | TFLOPs: 23.23 | +63: iteration 56410/ 73814 | consumed samples: 28881920 | consumed tokens: 59150172160 | elapsed time per iteration (s): 2.26 | learning rate: 4.404E-05 | global batch size: 512 | lm loss: 1.923670E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.494 | TFLOPs: 23.32 | +63: iteration 56420/ 73814 | consumed samples: 28887040 | consumed tokens: 59160657920 | elapsed time per iteration (s): 2.23 | learning rate: 4.401E-05 | global batch size: 512 | lm loss: 1.944802E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.026 | TFLOPs: 23.68 | +63: iteration 56430/ 73814 | consumed samples: 28892160 | consumed tokens: 59171143680 | elapsed time per iteration (s): 2.33 | learning rate: 4.399E-05 | global batch size: 512 | lm loss: 1.910535E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.846 | TFLOPs: 22.63 | +63: iteration 56440/ 73814 | consumed samples: 28897280 | consumed tokens: 59181629440 | elapsed time per iteration (s): 2.25 | learning rate: 4.396E-05 | global batch size: 512 | lm loss: 1.937263E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.400 | TFLOPs: 23.41 | +63: iteration 56450/ 73814 | consumed samples: 28902400 | consumed tokens: 59192115200 | elapsed time per iteration (s): 2.25 | learning rate: 4.393E-05 | global batch size: 512 | lm loss: 1.904874E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.650 | TFLOPs: 23.44 | +63: iteration 56460/ 73814 | consumed samples: 28907520 | consumed tokens: 59202600960 | elapsed time per iteration (s): 2.22 | learning rate: 4.391E-05 | global batch size: 512 | lm loss: 1.912146E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.121 | TFLOPs: 23.69 | +63: iteration 56470/ 73814 | consumed samples: 28912640 | consumed tokens: 59213086720 | elapsed time per iteration (s): 2.23 | learning rate: 4.388E-05 | global batch size: 512 | lm loss: 1.919374E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.634 | TFLOPs: 23.64 | +63: iteration 56480/ 73814 | consumed samples: 28917760 | consumed tokens: 59223572480 | elapsed time per iteration (s): 2.23 | learning rate: 4.386E-05 | global batch size: 512 | lm loss: 1.945020E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.656 | TFLOPs: 23.64 | +63: iteration 56490/ 73814 | consumed samples: 28922880 | consumed tokens: 59234058240 | elapsed time per iteration (s): 2.29 | learning rate: 4.383E-05 | global batch size: 512 | lm loss: 1.939561E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.173 | TFLOPs: 22.97 | +63: iteration 56500/ 73814 | consumed samples: 28928000 | consumed tokens: 59244544000 | elapsed time per iteration (s): 2.23 | learning rate: 4.380E-05 | global batch size: 512 | lm loss: 1.925212E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.613 | TFLOPs: 23.64 | +63: iteration 56510/ 73814 | consumed samples: 28933120 | consumed tokens: 59255029760 | elapsed time per iteration (s): 2.23 | learning rate: 4.378E-05 | global batch size: 512 | lm loss: 1.924881E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.918 | TFLOPs: 23.67 | +63: iteration 56520/ 73814 | consumed samples: 28938240 | consumed tokens: 59265515520 | elapsed time per iteration (s): 2.23 | learning rate: 4.375E-05 | global batch size: 512 | lm loss: 1.912388E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.484 | TFLOPs: 23.62 | +63: iteration 56530/ 73814 | consumed samples: 28943360 | consumed tokens: 59276001280 | elapsed time per iteration (s): 2.23 | learning rate: 4.372E-05 | global batch size: 512 | lm loss: 1.919229E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.190 | TFLOPs: 23.59 | +63: iteration 56540/ 73814 | consumed samples: 28948480 | consumed tokens: 59286487040 | elapsed time per iteration (s): 2.23 | learning rate: 4.370E-05 | global batch size: 512 | lm loss: 1.916028E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.595 | TFLOPs: 23.64 | +63: iteration 56550/ 73814 | consumed samples: 28953600 | consumed tokens: 59296972800 | elapsed time per iteration (s): 2.23 | learning rate: 4.367E-05 | global batch size: 512 | lm loss: 1.919856E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.775 | TFLOPs: 23.65 | +63: iteration 56560/ 73814 | consumed samples: 28958720 | consumed tokens: 59307458560 | elapsed time per iteration (s): 2.23 | learning rate: 4.365E-05 | global batch size: 512 | lm loss: 1.906556E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.715 | TFLOPs: 23.65 | +63: iteration 56570/ 73814 | consumed samples: 28963840 | consumed tokens: 59317944320 | elapsed time per iteration (s): 2.23 | learning rate: 4.362E-05 | global batch size: 512 | lm loss: 1.913176E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.026 | TFLOPs: 23.68 | +63: iteration 56580/ 73814 | consumed samples: 28968960 | consumed tokens: 59328430080 | elapsed time per iteration (s): 2.26 | learning rate: 4.359E-05 | global batch size: 512 | lm loss: 1.899376E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.268 | TFLOPs: 23.29 | +63: iteration 56590/ 73814 | consumed samples: 28974080 | consumed tokens: 59338915840 | elapsed time per iteration (s): 2.23 | learning rate: 4.357E-05 | global batch size: 512 | lm loss: 1.905354E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.838 | TFLOPs: 23.66 | +63: iteration 56600/ 73814 | consumed samples: 28979200 | consumed tokens: 59349401600 | elapsed time per iteration (s): 2.31 | learning rate: 4.354E-05 | global batch size: 512 | lm loss: 1.931237E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.670 | TFLOPs: 22.82 | +63: iteration 56610/ 73814 | consumed samples: 28984320 | consumed tokens: 59359887360 | elapsed time per iteration (s): 2.24 | learning rate: 4.352E-05 | global batch size: 512 | lm loss: 1.907648E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.426 | TFLOPs: 23.52 | +63: iteration 56620/ 73814 | consumed samples: 28989440 | consumed tokens: 59370373120 | elapsed time per iteration (s): 2.23 | learning rate: 4.349E-05 | global batch size: 512 | lm loss: 1.938582E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.655 | TFLOPs: 23.64 | +63: iteration 56630/ 73814 | consumed samples: 28994560 | consumed tokens: 59380858880 | elapsed time per iteration (s): 2.23 | learning rate: 4.346E-05 | global batch size: 512 | lm loss: 1.923368E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.398 | TFLOPs: 23.62 | +63: iteration 56640/ 73814 | consumed samples: 28999680 | consumed tokens: 59391344640 | elapsed time per iteration (s): 2.23 | learning rate: 4.344E-05 | global batch size: 512 | lm loss: 1.895986E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.957 | TFLOPs: 23.67 | +63: iteration 56650/ 73814 | consumed samples: 29004800 | consumed tokens: 59401830400 | elapsed time per iteration (s): 2.24 | learning rate: 4.341E-05 | global batch size: 512 | lm loss: 1.916581E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.318 | TFLOPs: 23.50 | +63: iteration 56660/ 73814 | consumed samples: 29009920 | consumed tokens: 59412316160 | elapsed time per iteration (s): 2.23 | learning rate: 4.338E-05 | global batch size: 512 | lm loss: 1.917920E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.304 | TFLOPs: 23.61 | +63: iteration 56670/ 73814 | consumed samples: 29015040 | consumed tokens: 59422801920 | elapsed time per iteration (s): 2.24 | learning rate: 4.336E-05 | global batch size: 512 | lm loss: 1.895098E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.074 | TFLOPs: 23.58 | +63: iteration 56680/ 73814 | consumed samples: 29020160 | consumed tokens: 59433287680 | elapsed time per iteration (s): 2.22 | learning rate: 4.333E-05 | global batch size: 512 | lm loss: 1.926981E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.182 | TFLOPs: 23.70 | +63: iteration 56690/ 73814 | consumed samples: 29025280 | consumed tokens: 59443773440 | elapsed time per iteration (s): 2.23 | learning rate: 4.331E-05 | global batch size: 512 | lm loss: 1.959770E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.659 | TFLOPs: 23.64 | +63: iteration 56700/ 73814 | consumed samples: 29030400 | consumed tokens: 59454259200 | elapsed time per iteration (s): 2.27 | learning rate: 4.328E-05 | global batch size: 512 | lm loss: 1.919444E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.061 | TFLOPs: 23.17 | +63: iteration 56710/ 73814 | consumed samples: 29035520 | consumed tokens: 59464744960 | elapsed time per iteration (s): 2.26 | learning rate: 4.326E-05 | global batch size: 512 | lm loss: 1.917247E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.997 | TFLOPs: 23.37 | +63: iteration 56720/ 73814 | consumed samples: 29040640 | consumed tokens: 59475230720 | elapsed time per iteration (s): 2.36 | learning rate: 4.323E-05 | global batch size: 512 | lm loss: 1.908184E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.691 | TFLOPs: 22.31 | +63: iteration 56730/ 73814 | consumed samples: 29045760 | consumed tokens: 59485716480 | elapsed time per iteration (s): 2.24 | learning rate: 4.320E-05 | global batch size: 512 | lm loss: 1.890381E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.807 | TFLOPs: 23.55 | +63: iteration 56740/ 73814 | consumed samples: 29050880 | consumed tokens: 59496202240 | elapsed time per iteration (s): 2.49 | learning rate: 4.318E-05 | global batch size: 512 | lm loss: 1.909416E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.876 | TFLOPs: 21.19 | +63: iteration 56750/ 73814 | consumed samples: 29056000 | consumed tokens: 59506688000 | elapsed time per iteration (s): 2.43 | learning rate: 4.315E-05 | global batch size: 512 | lm loss: 1.909660E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.945 | TFLOPs: 21.72 | +63: iteration 56760/ 73814 | consumed samples: 29061120 | consumed tokens: 59517173760 | elapsed time per iteration (s): 2.25 | learning rate: 4.313E-05 | global batch size: 512 | lm loss: 1.926966E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.204 | TFLOPs: 23.39 | +63: iteration 56770/ 73814 | consumed samples: 29066240 | consumed tokens: 59527659520 | elapsed time per iteration (s): 2.23 | learning rate: 4.310E-05 | global batch size: 512 | lm loss: 1.928351E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.186 | TFLOPs: 23.59 | +63: iteration 56780/ 73814 | consumed samples: 29071360 | consumed tokens: 59538145280 | elapsed time per iteration (s): 2.24 | learning rate: 4.307E-05 | global batch size: 512 | lm loss: 1.943232E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.714 | TFLOPs: 23.55 | +63: iteration 56790/ 73814 | consumed samples: 29076480 | consumed tokens: 59548631040 | elapsed time per iteration (s): 2.24 | learning rate: 4.305E-05 | global batch size: 512 | lm loss: 1.917984E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.886 | TFLOPs: 23.56 | +63: iteration 56800/ 73814 | consumed samples: 29081600 | consumed tokens: 59559116800 | elapsed time per iteration (s): 2.27 | learning rate: 4.302E-05 | global batch size: 512 | lm loss: 1.925859E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.560 | TFLOPs: 23.22 | +63: iteration 56810/ 73814 | consumed samples: 29086720 | consumed tokens: 59569602560 | elapsed time per iteration (s): 2.36 | learning rate: 4.300E-05 | global batch size: 512 | lm loss: 1.951955E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.259 | TFLOPs: 22.37 | +63: iteration 56820/ 73814 | consumed samples: 29091840 | consumed tokens: 59580088320 | elapsed time per iteration (s): 2.23 | learning rate: 4.297E-05 | global batch size: 512 | lm loss: 1.907172E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.703 | TFLOPs: 23.65 | +63: iteration 56830/ 73814 | consumed samples: 29096960 | consumed tokens: 59590574080 | elapsed time per iteration (s): 2.24 | learning rate: 4.294E-05 | global batch size: 512 | lm loss: 1.918349E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.012 | TFLOPs: 23.58 | +63: iteration 56840/ 73814 | consumed samples: 29102080 | consumed tokens: 59601059840 | elapsed time per iteration (s): 2.23 | learning rate: 4.292E-05 | global batch size: 512 | lm loss: 1.933617E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.951 | TFLOPs: 23.67 | +63: iteration 56850/ 73814 | consumed samples: 29107200 | consumed tokens: 59611545600 | elapsed time per iteration (s): 2.24 | learning rate: 4.289E-05 | global batch size: 512 | lm loss: 1.923291E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.245 | TFLOPs: 23.50 | +63: iteration 56860/ 73814 | consumed samples: 29112320 | consumed tokens: 59622031360 | elapsed time per iteration (s): 2.23 | learning rate: 4.287E-05 | global batch size: 512 | lm loss: 1.894078E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.568 | TFLOPs: 23.63 | +63: iteration 56870/ 73814 | consumed samples: 29117440 | consumed tokens: 59632517120 | elapsed time per iteration (s): 2.23 | learning rate: 4.284E-05 | global batch size: 512 | lm loss: 1.907775E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.631 | TFLOPs: 23.64 | +63: iteration 56880/ 73814 | consumed samples: 29122560 | consumed tokens: 59643002880 | elapsed time per iteration (s): 2.24 | learning rate: 4.282E-05 | global batch size: 512 | lm loss: 1.910675E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.201 | TFLOPs: 23.49 | +63: iteration 56890/ 73814 | consumed samples: 29127680 | consumed tokens: 59653488640 | elapsed time per iteration (s): 2.23 | learning rate: 4.279E-05 | global batch size: 512 | lm loss: 1.934363E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.520 | TFLOPs: 23.63 | +63: iteration 56900/ 73814 | consumed samples: 29132800 | consumed tokens: 59663974400 | elapsed time per iteration (s): 2.23 | learning rate: 4.276E-05 | global batch size: 512 | lm loss: 1.912955E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.705 | TFLOPs: 23.65 | +63: iteration 56910/ 73814 | consumed samples: 29137920 | consumed tokens: 59674460160 | elapsed time per iteration (s): 2.45 | learning rate: 4.274E-05 | global batch size: 512 | lm loss: 1.913981E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.123 | TFLOPs: 21.53 | +63: iteration 56920/ 73814 | consumed samples: 29143040 | consumed tokens: 59684945920 | elapsed time per iteration (s): 2.23 | learning rate: 4.271E-05 | global batch size: 512 | lm loss: 1.918582E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.729 | TFLOPs: 23.65 | +63: iteration 56930/ 73814 | consumed samples: 29148160 | consumed tokens: 59695431680 | elapsed time per iteration (s): 2.37 | learning rate: 4.269E-05 | global batch size: 512 | lm loss: 1.913889E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.933 | TFLOPs: 22.23 | +63: iteration 56940/ 73814 | consumed samples: 29153280 | consumed tokens: 59705917440 | elapsed time per iteration (s): 2.23 | learning rate: 4.266E-05 | global batch size: 512 | lm loss: 1.926771E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.936 | TFLOPs: 23.67 | +63: iteration 56950/ 73814 | consumed samples: 29158400 | consumed tokens: 59716403200 | elapsed time per iteration (s): 2.23 | learning rate: 4.264E-05 | global batch size: 512 | lm loss: 1.926024E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.057 | TFLOPs: 23.68 | +63: iteration 56960/ 73814 | consumed samples: 29163520 | consumed tokens: 59726888960 | elapsed time per iteration (s): 2.23 | learning rate: 4.261E-05 | global batch size: 512 | lm loss: 1.926966E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.937 | TFLOPs: 23.67 | +63: iteration 56970/ 73814 | consumed samples: 29168640 | consumed tokens: 59737374720 | elapsed time per iteration (s): 2.24 | learning rate: 4.258E-05 | global batch size: 512 | lm loss: 1.928526E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.546 | TFLOPs: 23.53 | +63: iteration 56980/ 73814 | consumed samples: 29173760 | consumed tokens: 59747860480 | elapsed time per iteration (s): 2.25 | learning rate: 4.256E-05 | global batch size: 512 | lm loss: 1.892227E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.913 | TFLOPs: 23.46 | +63: iteration 56990/ 73814 | consumed samples: 29178880 | consumed tokens: 59758346240 | elapsed time per iteration (s): 2.26 | learning rate: 4.253E-05 | global batch size: 512 | lm loss: 1.917644E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.604 | TFLOPs: 23.33 | +63: iteration 57000/ 73814 | consumed samples: 29184000 | consumed tokens: 59768832000 | elapsed time per iteration (s): 2.23 | learning rate: 4.251E-05 | global batch size: 512 | lm loss: 1.908849E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.762 | TFLOPs: 23.65 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 57000 | lm loss value: 1.912257E+00 | lm loss PPL: 6.768348E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 57010/ 73814 | consumed samples: 29189120 | consumed tokens: 59779317760 | elapsed time per iteration (s): 2.30 | learning rate: 4.248E-05 | global batch size: 512 | lm loss: 1.918679E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.571 | TFLOPs: 22.91 | +63: iteration 57020/ 73814 | consumed samples: 29194240 | consumed tokens: 59789803520 | elapsed time per iteration (s): 2.23 | learning rate: 4.246E-05 | global batch size: 512 | lm loss: 1.926576E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.654 | TFLOPs: 23.64 | +63: iteration 57030/ 73814 | consumed samples: 29199360 | consumed tokens: 59800289280 | elapsed time per iteration (s): 2.24 | learning rate: 4.243E-05 | global batch size: 512 | lm loss: 1.937727E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.671 | TFLOPs: 23.54 | +63: iteration 57040/ 73814 | consumed samples: 29204480 | consumed tokens: 59810775040 | elapsed time per iteration (s): 2.24 | learning rate: 4.241E-05 | global batch size: 512 | lm loss: 1.916926E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.797 | TFLOPs: 23.55 | +63: iteration 57050/ 73814 | consumed samples: 29209600 | consumed tokens: 59821260800 | elapsed time per iteration (s): 2.32 | learning rate: 4.238E-05 | global batch size: 512 | lm loss: 1.933278E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.353 | TFLOPs: 22.68 | +63: iteration 57060/ 73814 | consumed samples: 29214720 | consumed tokens: 59831746560 | elapsed time per iteration (s): 2.23 | learning rate: 4.235E-05 | global batch size: 512 | lm loss: 1.917872E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.203 | TFLOPs: 23.60 | +63: iteration 57070/ 73814 | consumed samples: 29219840 | consumed tokens: 59842232320 | elapsed time per iteration (s): 2.24 | learning rate: 4.233E-05 | global batch size: 512 | lm loss: 1.915789E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.267 | TFLOPs: 23.50 | +63: iteration 57080/ 73814 | consumed samples: 29224960 | consumed tokens: 59852718080 | elapsed time per iteration (s): 2.23 | learning rate: 4.230E-05 | global batch size: 512 | lm loss: 1.922096E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.740 | TFLOPs: 23.65 | +63: iteration 57090/ 73814 | consumed samples: 29230080 | consumed tokens: 59863203840 | elapsed time per iteration (s): 2.32 | learning rate: 4.228E-05 | global batch size: 512 | lm loss: 1.950246E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.916 | TFLOPs: 22.74 | +63: iteration 57100/ 73814 | consumed samples: 29235200 | consumed tokens: 59873689600 | elapsed time per iteration (s): 2.23 | learning rate: 4.225E-05 | global batch size: 512 | lm loss: 1.919435E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.528 | TFLOPs: 23.63 | +63: iteration 57110/ 73814 | consumed samples: 29240320 | consumed tokens: 59884175360 | elapsed time per iteration (s): 2.23 | learning rate: 4.223E-05 | global batch size: 512 | lm loss: 1.901050E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.703 | TFLOPs: 23.65 | +63: iteration 57120/ 73814 | consumed samples: 29245440 | consumed tokens: 59894661120 | elapsed time per iteration (s): 2.29 | learning rate: 4.220E-05 | global batch size: 512 | lm loss: 1.915655E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.991 | TFLOPs: 23.06 | +63: iteration 57130/ 73814 | consumed samples: 29250560 | consumed tokens: 59905146880 | elapsed time per iteration (s): 2.23 | learning rate: 4.218E-05 | global batch size: 512 | lm loss: 1.925425E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.693 | TFLOPs: 23.65 | +63: iteration 57140/ 73814 | consumed samples: 29255680 | consumed tokens: 59915632640 | elapsed time per iteration (s): 2.24 | learning rate: 4.215E-05 | global batch size: 512 | lm loss: 1.920512E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.853 | TFLOPs: 23.56 | +63: iteration 57150/ 73814 | consumed samples: 29260800 | consumed tokens: 59926118400 | elapsed time per iteration (s): 2.23 | learning rate: 4.213E-05 | global batch size: 512 | lm loss: 1.911047E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.744 | TFLOPs: 23.65 | +63: iteration 57160/ 73814 | consumed samples: 29265920 | consumed tokens: 59936604160 | elapsed time per iteration (s): 2.24 | learning rate: 4.210E-05 | global batch size: 512 | lm loss: 1.935869E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.084 | TFLOPs: 23.48 | +63: iteration 57170/ 73814 | consumed samples: 29271040 | consumed tokens: 59947089920 | elapsed time per iteration (s): 2.25 | learning rate: 4.207E-05 | global batch size: 512 | lm loss: 1.912768E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.279 | TFLOPs: 23.40 | +63: iteration 57180/ 73814 | consumed samples: 29276160 | consumed tokens: 59957575680 | elapsed time per iteration (s): 2.22 | learning rate: 4.205E-05 | global batch size: 512 | lm loss: 1.924385E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.449 | TFLOPs: 23.72 | +63: iteration 57190/ 73814 | consumed samples: 29281280 | consumed tokens: 59968061440 | elapsed time per iteration (s): 2.23 | learning rate: 4.202E-05 | global batch size: 512 | lm loss: 1.899936E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.336 | TFLOPs: 23.61 | +63: iteration 57200/ 73814 | consumed samples: 29286400 | consumed tokens: 59978547200 | elapsed time per iteration (s): 2.27 | learning rate: 4.200E-05 | global batch size: 512 | lm loss: 1.909208E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.951 | TFLOPs: 23.26 | +63: iteration 57210/ 73814 | consumed samples: 29291520 | consumed tokens: 59989032960 | elapsed time per iteration (s): 2.23 | learning rate: 4.197E-05 | global batch size: 512 | lm loss: 1.909644E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.030 | TFLOPs: 23.68 | +63: iteration 57220/ 73814 | consumed samples: 29296640 | consumed tokens: 59999518720 | elapsed time per iteration (s): 2.23 | learning rate: 4.195E-05 | global batch size: 512 | lm loss: 1.909844E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.103 | TFLOPs: 23.59 | +63: iteration 57230/ 73814 | consumed samples: 29301760 | consumed tokens: 60010004480 | elapsed time per iteration (s): 2.23 | learning rate: 4.192E-05 | global batch size: 512 | lm loss: 1.923952E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.801 | TFLOPs: 23.66 | +63: iteration 57240/ 73814 | consumed samples: 29306880 | consumed tokens: 60020490240 | elapsed time per iteration (s): 2.36 | learning rate: 4.190E-05 | global batch size: 512 | lm loss: 1.916145E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.753 | TFLOPs: 22.31 | +63: iteration 57250/ 73814 | consumed samples: 29312000 | consumed tokens: 60030976000 | elapsed time per iteration (s): 2.24 | learning rate: 4.187E-05 | global batch size: 512 | lm loss: 1.923798E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.283 | TFLOPs: 23.50 | +63: iteration 57260/ 73814 | consumed samples: 29317120 | consumed tokens: 60041461760 | elapsed time per iteration (s): 2.31 | learning rate: 4.185E-05 | global batch size: 512 | lm loss: 1.897596E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.301 | TFLOPs: 22.78 | +63: iteration 57270/ 73814 | consumed samples: 29322240 | consumed tokens: 60051947520 | elapsed time per iteration (s): 2.24 | learning rate: 4.182E-05 | global batch size: 512 | lm loss: 1.921150E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.316 | TFLOPs: 23.50 | +63: iteration 57280/ 73814 | consumed samples: 29327360 | consumed tokens: 60062433280 | elapsed time per iteration (s): 2.23 | learning rate: 4.180E-05 | global batch size: 512 | lm loss: 1.899080E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.963 | TFLOPs: 23.67 | +63: iteration 57290/ 73814 | consumed samples: 29332480 | consumed tokens: 60072919040 | elapsed time per iteration (s): 2.23 | learning rate: 4.177E-05 | global batch size: 512 | lm loss: 1.948185E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.302 | TFLOPs: 23.61 | +63: iteration 57300/ 73814 | consumed samples: 29337600 | consumed tokens: 60083404800 | elapsed time per iteration (s): 2.23 | learning rate: 4.175E-05 | global batch size: 512 | lm loss: 1.943419E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.708 | TFLOPs: 23.65 | +63: iteration 57310/ 73814 | consumed samples: 29342720 | consumed tokens: 60093890560 | elapsed time per iteration (s): 2.52 | learning rate: 4.172E-05 | global batch size: 512 | lm loss: 1.931883E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 203.489 | TFLOPs: 20.95 | +63: iteration 57320/ 73814 | consumed samples: 29347840 | consumed tokens: 60104376320 | elapsed time per iteration (s): 2.24 | learning rate: 4.169E-05 | global batch size: 512 | lm loss: 1.911594E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.502 | TFLOPs: 23.52 | +63: iteration 57330/ 73814 | consumed samples: 29352960 | consumed tokens: 60114862080 | elapsed time per iteration (s): 2.23 | learning rate: 4.167E-05 | global batch size: 512 | lm loss: 1.915753E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.130 | TFLOPs: 23.59 | +63: iteration 57340/ 73814 | consumed samples: 29358080 | consumed tokens: 60125347840 | elapsed time per iteration (s): 2.32 | learning rate: 4.164E-05 | global batch size: 512 | lm loss: 1.929603E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.524 | TFLOPs: 22.70 | +63: iteration 57350/ 73814 | consumed samples: 29363200 | consumed tokens: 60135833600 | elapsed time per iteration (s): 2.24 | learning rate: 4.162E-05 | global batch size: 512 | lm loss: 1.908049E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.986 | TFLOPs: 23.57 | +63: iteration 57360/ 73814 | consumed samples: 29368320 | consumed tokens: 60146319360 | elapsed time per iteration (s): 2.38 | learning rate: 4.159E-05 | global batch size: 512 | lm loss: 1.916185E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.465 | TFLOPs: 22.18 | +63: iteration 57370/ 73814 | consumed samples: 29373440 | consumed tokens: 60156805120 | elapsed time per iteration (s): 2.23 | learning rate: 4.157E-05 | global batch size: 512 | lm loss: 1.899107E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.967 | TFLOPs: 23.67 | +63: iteration 57380/ 73814 | consumed samples: 29378560 | consumed tokens: 60167290880 | elapsed time per iteration (s): 2.28 | learning rate: 4.154E-05 | global batch size: 512 | lm loss: 1.942261E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.040 | TFLOPs: 23.17 | +63: iteration 57390/ 73814 | consumed samples: 29383680 | consumed tokens: 60177776640 | elapsed time per iteration (s): 2.42 | learning rate: 4.152E-05 | global batch size: 512 | lm loss: 1.933891E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.592 | TFLOPs: 21.78 | +63: iteration 57400/ 73814 | consumed samples: 29388800 | consumed tokens: 60188262400 | elapsed time per iteration (s): 2.23 | learning rate: 4.149E-05 | global batch size: 512 | lm loss: 1.923736E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.663 | TFLOPs: 23.64 | +63: iteration 57410/ 73814 | consumed samples: 29393920 | consumed tokens: 60198748160 | elapsed time per iteration (s): 2.23 | learning rate: 4.147E-05 | global batch size: 512 | lm loss: 1.901978E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.185 | TFLOPs: 23.59 | +63: iteration 57420/ 73814 | consumed samples: 29399040 | consumed tokens: 60209233920 | elapsed time per iteration (s): 2.39 | learning rate: 4.144E-05 | global batch size: 512 | lm loss: 1.928579E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.331 | TFLOPs: 22.06 | +63: iteration 57430/ 73814 | consumed samples: 29404160 | consumed tokens: 60219719680 | elapsed time per iteration (s): 2.23 | learning rate: 4.142E-05 | global batch size: 512 | lm loss: 1.921473E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.856 | TFLOPs: 23.66 | +63: iteration 57440/ 73814 | consumed samples: 29409280 | consumed tokens: 60230205440 | elapsed time per iteration (s): 2.23 | learning rate: 4.139E-05 | global batch size: 512 | lm loss: 1.901161E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.853 | TFLOPs: 23.66 | +63: iteration 57450/ 73814 | consumed samples: 29414400 | consumed tokens: 60240691200 | elapsed time per iteration (s): 2.22 | learning rate: 4.137E-05 | global batch size: 512 | lm loss: 1.916274E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.292 | TFLOPs: 23.71 | +63: iteration 57460/ 73814 | consumed samples: 29419520 | consumed tokens: 60251176960 | elapsed time per iteration (s): 2.23 | learning rate: 4.134E-05 | global batch size: 512 | lm loss: 1.917192E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.142 | TFLOPs: 23.59 | +63: iteration 57470/ 73814 | consumed samples: 29424640 | consumed tokens: 60261662720 | elapsed time per iteration (s): 2.23 | learning rate: 4.132E-05 | global batch size: 512 | lm loss: 1.908530E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.866 | TFLOPs: 23.66 | +63: iteration 57480/ 73814 | consumed samples: 29429760 | consumed tokens: 60272148480 | elapsed time per iteration (s): 2.23 | learning rate: 4.129E-05 | global batch size: 512 | lm loss: 1.916981E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.680 | TFLOPs: 23.64 | +63: iteration 57490/ 73814 | consumed samples: 29434880 | consumed tokens: 60282634240 | elapsed time per iteration (s): 2.23 | learning rate: 4.127E-05 | global batch size: 512 | lm loss: 1.923764E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.937 | TFLOPs: 23.67 | +63: iteration 57500/ 73814 | consumed samples: 29440000 | consumed tokens: 60293120000 | elapsed time per iteration (s): 2.24 | learning rate: 4.124E-05 | global batch size: 512 | lm loss: 1.919477E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.161 | TFLOPs: 23.49 | +63: iteration 57510/ 73814 | consumed samples: 29445120 | consumed tokens: 60303605760 | elapsed time per iteration (s): 2.53 | learning rate: 4.122E-05 | global batch size: 512 | lm loss: 1.926268E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.384 | TFLOPs: 20.83 | +63: iteration 57520/ 73814 | consumed samples: 29450240 | consumed tokens: 60314091520 | elapsed time per iteration (s): 2.26 | learning rate: 4.119E-05 | global batch size: 512 | lm loss: 1.933558E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.675 | TFLOPs: 23.34 | +63: iteration 57530/ 73814 | consumed samples: 29455360 | consumed tokens: 60324577280 | elapsed time per iteration (s): 2.29 | learning rate: 4.117E-05 | global batch size: 512 | lm loss: 1.909945E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.385 | TFLOPs: 23.00 | +63: iteration 57540/ 73814 | consumed samples: 29460480 | consumed tokens: 60335063040 | elapsed time per iteration (s): 2.23 | learning rate: 4.114E-05 | global batch size: 512 | lm loss: 1.893628E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.543 | TFLOPs: 23.63 | +63: iteration 57550/ 73814 | consumed samples: 29465600 | consumed tokens: 60345548800 | elapsed time per iteration (s): 2.23 | learning rate: 4.112E-05 | global batch size: 512 | lm loss: 1.931527E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.426 | TFLOPs: 23.62 | +63: iteration 57560/ 73814 | consumed samples: 29470720 | consumed tokens: 60356034560 | elapsed time per iteration (s): 2.25 | learning rate: 4.109E-05 | global batch size: 512 | lm loss: 1.896275E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.988 | TFLOPs: 23.47 | +63: iteration 57570/ 73814 | consumed samples: 29475840 | consumed tokens: 60366520320 | elapsed time per iteration (s): 2.22 | learning rate: 4.107E-05 | global batch size: 512 | lm loss: 1.929621E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.129 | TFLOPs: 23.69 | +63: iteration 57580/ 73814 | consumed samples: 29480960 | consumed tokens: 60377006080 | elapsed time per iteration (s): 2.24 | learning rate: 4.104E-05 | global batch size: 512 | lm loss: 1.902514E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.360 | TFLOPs: 23.51 | +63: iteration 57590/ 73814 | consumed samples: 29486080 | consumed tokens: 60387491840 | elapsed time per iteration (s): 2.28 | learning rate: 4.102E-05 | global batch size: 512 | lm loss: 1.910456E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.950 | TFLOPs: 23.16 | +63: iteration 57600/ 73814 | consumed samples: 29491200 | consumed tokens: 60397977600 | elapsed time per iteration (s): 2.24 | learning rate: 4.099E-05 | global batch size: 512 | lm loss: 1.916859E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.531 | TFLOPs: 23.53 | +63: iteration 57610/ 73814 | consumed samples: 29496320 | consumed tokens: 60408463360 | elapsed time per iteration (s): 2.23 | learning rate: 4.097E-05 | global batch size: 512 | lm loss: 1.929573E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.797 | TFLOPs: 23.66 | +63: iteration 57620/ 73814 | consumed samples: 29501440 | consumed tokens: 60418949120 | elapsed time per iteration (s): 2.24 | learning rate: 4.094E-05 | global batch size: 512 | lm loss: 1.909791E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.813 | TFLOPs: 23.56 | +63: iteration 57630/ 73814 | consumed samples: 29506560 | consumed tokens: 60429434880 | elapsed time per iteration (s): 2.27 | learning rate: 4.092E-05 | global batch size: 512 | lm loss: 1.907038E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.184 | TFLOPs: 23.18 | +63: iteration 57640/ 73814 | consumed samples: 29511680 | consumed tokens: 60439920640 | elapsed time per iteration (s): 2.26 | learning rate: 4.090E-05 | global batch size: 512 | lm loss: 1.901362E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.737 | TFLOPs: 23.34 | +63: iteration 57650/ 73814 | consumed samples: 29516800 | consumed tokens: 60450406400 | elapsed time per iteration (s): 2.49 | learning rate: 4.087E-05 | global batch size: 512 | lm loss: 1.926452E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.535 | TFLOPs: 21.16 | +63: iteration 57660/ 73814 | consumed samples: 29521920 | consumed tokens: 60460892160 | elapsed time per iteration (s): 2.36 | learning rate: 4.085E-05 | global batch size: 512 | lm loss: 1.914946E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.994 | TFLOPs: 22.34 | +63: iteration 57670/ 73814 | consumed samples: 29527040 | consumed tokens: 60471377920 | elapsed time per iteration (s): 2.37 | learning rate: 4.082E-05 | global batch size: 512 | lm loss: 1.903249E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.175 | TFLOPs: 22.25 | +63: iteration 57680/ 73814 | consumed samples: 29532160 | consumed tokens: 60481863680 | elapsed time per iteration (s): 2.24 | learning rate: 4.080E-05 | global batch size: 512 | lm loss: 1.927593E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.770 | TFLOPs: 23.55 | +63: iteration 57690/ 73814 | consumed samples: 29537280 | consumed tokens: 60492349440 | elapsed time per iteration (s): 2.72 | learning rate: 4.077E-05 | global batch size: 512 | lm loss: 1.904857E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 188.449 | TFLOPs: 19.40 | +63: iteration 57700/ 73814 | consumed samples: 29542400 | consumed tokens: 60502835200 | elapsed time per iteration (s): 2.67 | learning rate: 4.075E-05 | global batch size: 512 | lm loss: 1.927826E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 192.058 | TFLOPs: 19.77 | +63: iteration 57710/ 73814 | consumed samples: 29547520 | consumed tokens: 60513320960 | elapsed time per iteration (s): 3.05 | learning rate: 4.072E-05 | global batch size: 512 | lm loss: 1.911873E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 167.954 | TFLOPs: 17.29 | +63: iteration 57720/ 73814 | consumed samples: 29552640 | consumed tokens: 60523806720 | elapsed time per iteration (s): 2.55 | learning rate: 4.070E-05 | global batch size: 512 | lm loss: 1.923238E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.079 | TFLOPs: 20.70 | +63: iteration 57730/ 73814 | consumed samples: 29557760 | consumed tokens: 60534292480 | elapsed time per iteration (s): 2.23 | learning rate: 4.067E-05 | global batch size: 512 | lm loss: 1.926144E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.618 | TFLOPs: 23.64 | +63: iteration 57740/ 73814 | consumed samples: 29562880 | consumed tokens: 60544778240 | elapsed time per iteration (s): 2.43 | learning rate: 4.065E-05 | global batch size: 512 | lm loss: 1.935276E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.446 | TFLOPs: 21.66 | +63: iteration 57750/ 73814 | consumed samples: 29568000 | consumed tokens: 60555264000 | elapsed time per iteration (s): 2.26 | learning rate: 4.062E-05 | global batch size: 512 | lm loss: 1.898033E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.576 | TFLOPs: 23.32 | +63: iteration 57760/ 73814 | consumed samples: 29573120 | consumed tokens: 60565749760 | elapsed time per iteration (s): 2.24 | learning rate: 4.060E-05 | global batch size: 512 | lm loss: 1.891501E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.074 | TFLOPs: 23.58 | +63: iteration 57770/ 73814 | consumed samples: 29578240 | consumed tokens: 60576235520 | elapsed time per iteration (s): 2.23 | learning rate: 4.057E-05 | global batch size: 512 | lm loss: 1.931946E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.024 | TFLOPs: 23.68 | +63: iteration 57780/ 73814 | consumed samples: 29583360 | consumed tokens: 60586721280 | elapsed time per iteration (s): 2.24 | learning rate: 4.055E-05 | global batch size: 512 | lm loss: 1.924203E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.192 | TFLOPs: 23.49 | +63: iteration 57790/ 73814 | consumed samples: 29588480 | consumed tokens: 60597207040 | elapsed time per iteration (s): 2.23 | learning rate: 4.052E-05 | global batch size: 512 | lm loss: 1.920903E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.383 | TFLOPs: 23.61 | +63: iteration 57800/ 73814 | consumed samples: 29593600 | consumed tokens: 60607692800 | elapsed time per iteration (s): 5.17 | learning rate: 4.050E-05 | global batch size: 512 | lm loss: 1.921227E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 99.105 | TFLOPs: 10.20 | +63: iteration 57810/ 73814 | consumed samples: 29598720 | consumed tokens: 60618178560 | elapsed time per iteration (s): 2.45 | learning rate: 4.048E-05 | global batch size: 512 | lm loss: 1.907427E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.588 | TFLOPs: 21.47 | +63: iteration 57820/ 73814 | consumed samples: 29603840 | consumed tokens: 60628664320 | elapsed time per iteration (s): 2.23 | learning rate: 4.045E-05 | global batch size: 512 | lm loss: 1.910516E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.518 | TFLOPs: 23.63 | +63: iteration 57830/ 73814 | consumed samples: 29608960 | consumed tokens: 60639150080 | elapsed time per iteration (s): 2.22 | learning rate: 4.043E-05 | global batch size: 512 | lm loss: 1.919249E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.291 | TFLOPs: 23.71 | +63: iteration 57840/ 73814 | consumed samples: 29614080 | consumed tokens: 60649635840 | elapsed time per iteration (s): 2.29 | learning rate: 4.040E-05 | global batch size: 512 | lm loss: 1.922962E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.028 | TFLOPs: 23.06 | +63: iteration 57850/ 73814 | consumed samples: 29619200 | consumed tokens: 60660121600 | elapsed time per iteration (s): 2.36 | learning rate: 4.038E-05 | global batch size: 512 | lm loss: 1.903599E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.989 | TFLOPs: 22.34 | +63: iteration 57860/ 73814 | consumed samples: 29624320 | consumed tokens: 60670607360 | elapsed time per iteration (s): 2.24 | learning rate: 4.035E-05 | global batch size: 512 | lm loss: 1.907600E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.807 | TFLOPs: 23.55 | +63: iteration 57870/ 73814 | consumed samples: 29629440 | consumed tokens: 60681093120 | elapsed time per iteration (s): 2.25 | learning rate: 4.033E-05 | global batch size: 512 | lm loss: 1.915052E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.622 | TFLOPs: 23.43 | +63: iteration 57880/ 73814 | consumed samples: 29634560 | consumed tokens: 60691578880 | elapsed time per iteration (s): 2.23 | learning rate: 4.030E-05 | global batch size: 512 | lm loss: 1.904968E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.608 | TFLOPs: 23.64 | +63: iteration 57890/ 73814 | consumed samples: 29639680 | consumed tokens: 60702064640 | elapsed time per iteration (s): 2.23 | learning rate: 4.028E-05 | global batch size: 512 | lm loss: 1.899976E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.661 | TFLOPs: 23.64 | +63: iteration 57900/ 73814 | consumed samples: 29644800 | consumed tokens: 60712550400 | elapsed time per iteration (s): 2.24 | learning rate: 4.026E-05 | global batch size: 512 | lm loss: 1.927908E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.070 | TFLOPs: 23.58 | +63: iteration 57910/ 73814 | consumed samples: 29649920 | consumed tokens: 60723036160 | elapsed time per iteration (s): 2.23 | learning rate: 4.023E-05 | global batch size: 512 | lm loss: 1.908961E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.804 | TFLOPs: 23.66 | +63: iteration 57920/ 73814 | consumed samples: 29655040 | consumed tokens: 60733521920 | elapsed time per iteration (s): 2.23 | learning rate: 4.021E-05 | global batch size: 512 | lm loss: 1.884831E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.460 | TFLOPs: 23.62 | +63: iteration 57930/ 73814 | consumed samples: 29660160 | consumed tokens: 60744007680 | elapsed time per iteration (s): 2.26 | learning rate: 4.018E-05 | global batch size: 512 | lm loss: 1.927750E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.035 | TFLOPs: 23.37 | +63: iteration 57940/ 73814 | consumed samples: 29665280 | consumed tokens: 60754493440 | elapsed time per iteration (s): 2.23 | learning rate: 4.016E-05 | global batch size: 512 | lm loss: 1.926052E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.505 | TFLOPs: 23.63 | +63: iteration 57950/ 73814 | consumed samples: 29670400 | consumed tokens: 60764979200 | elapsed time per iteration (s): 2.23 | learning rate: 4.013E-05 | global batch size: 512 | lm loss: 1.935740E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.299 | TFLOPs: 23.61 | +63: iteration 57960/ 73814 | consumed samples: 29675520 | consumed tokens: 60775464960 | elapsed time per iteration (s): 2.23 | learning rate: 4.011E-05 | global batch size: 512 | lm loss: 1.921862E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.086 | TFLOPs: 23.69 | +63: iteration 57970/ 73814 | consumed samples: 29680640 | consumed tokens: 60785950720 | elapsed time per iteration (s): 2.43 | learning rate: 4.008E-05 | global batch size: 512 | lm loss: 1.888716E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.015 | TFLOPs: 21.72 | +63: iteration 57980/ 73814 | consumed samples: 29685760 | consumed tokens: 60796436480 | elapsed time per iteration (s): 2.22 | learning rate: 4.006E-05 | global batch size: 512 | lm loss: 1.903227E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.363 | TFLOPs: 23.71 | +63: iteration 57990/ 73814 | consumed samples: 29690880 | consumed tokens: 60806922240 | elapsed time per iteration (s): 2.23 | learning rate: 4.004E-05 | global batch size: 512 | lm loss: 1.914931E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.812 | TFLOPs: 23.66 | + 0: [2022-12-03 00:44:10,529] [INFO] [logging.py:68:log_dist] [Rank 0] step=58000, skipped=0, lr=[4.001112286179204e-05, 4.001112286179204e-05, 4.001112286179204e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 58000/ 73814 | consumed samples: 29696000 | consumed tokens: 60817408000 | elapsed time per iteration (s): 2.41 | learning rate: 4.001E-05 | global batch size: 512 | lm loss: 1.915603E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.046 | TFLOPs: 21.83 | + 0: steps: 58000 loss: 1.8765 iter time (s): 2.298 samples/sec: 222.837 +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 58000 | lm loss value: 1.828101E+00 | lm loss PPL: 6.222061E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 58010/ 73814 | consumed samples: 29701120 | consumed tokens: 60827893760 | elapsed time per iteration (s): 2.34 | learning rate: 3.999E-05 | global batch size: 512 | lm loss: 1.915845E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.569 | TFLOPs: 22.50 | +63: iteration 58020/ 73814 | consumed samples: 29706240 | consumed tokens: 60838379520 | elapsed time per iteration (s): 2.26 | learning rate: 3.996E-05 | global batch size: 512 | lm loss: 1.921589E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.538 | TFLOPs: 23.32 | +63: iteration 58030/ 73814 | consumed samples: 29711360 | consumed tokens: 60848865280 | elapsed time per iteration (s): 2.25 | learning rate: 3.994E-05 | global batch size: 512 | lm loss: 1.924833E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.106 | TFLOPs: 23.38 | +63: iteration 58040/ 73814 | consumed samples: 29716480 | consumed tokens: 60859351040 | elapsed time per iteration (s): 2.24 | learning rate: 3.991E-05 | global batch size: 512 | lm loss: 1.918926E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.435 | TFLOPs: 23.52 | +63: iteration 58050/ 73814 | consumed samples: 29721600 | consumed tokens: 60869836800 | elapsed time per iteration (s): 2.23 | learning rate: 3.989E-05 | global batch size: 512 | lm loss: 1.894785E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.689 | TFLOPs: 23.65 | +63: iteration 58060/ 73814 | consumed samples: 29726720 | consumed tokens: 60880322560 | elapsed time per iteration (s): 2.23 | learning rate: 3.987E-05 | global batch size: 512 | lm loss: 1.918180E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.783 | TFLOPs: 23.66 | +63: iteration 58070/ 73814 | consumed samples: 29731840 | consumed tokens: 60890808320 | elapsed time per iteration (s): 2.24 | learning rate: 3.984E-05 | global batch size: 512 | lm loss: 1.913147E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.530 | TFLOPs: 23.53 | +63: iteration 58080/ 73814 | consumed samples: 29736960 | consumed tokens: 60901294080 | elapsed time per iteration (s): 2.23 | learning rate: 3.982E-05 | global batch size: 512 | lm loss: 1.931882E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.761 | TFLOPs: 23.65 | +63: iteration 58090/ 73814 | consumed samples: 29742080 | consumed tokens: 60911779840 | elapsed time per iteration (s): 2.25 | learning rate: 3.979E-05 | global batch size: 512 | lm loss: 1.916427E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.192 | TFLOPs: 23.39 | +63: iteration 58100/ 73814 | consumed samples: 29747200 | consumed tokens: 60922265600 | elapsed time per iteration (s): 2.24 | learning rate: 3.977E-05 | global batch size: 512 | lm loss: 1.927706E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.616 | TFLOPs: 23.53 | +63: iteration 58110/ 73814 | consumed samples: 29752320 | consumed tokens: 60932751360 | elapsed time per iteration (s): 2.23 | learning rate: 3.974E-05 | global batch size: 512 | lm loss: 1.904825E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.486 | TFLOPs: 23.62 | +63: iteration 58120/ 73814 | consumed samples: 29757440 | consumed tokens: 60943237120 | elapsed time per iteration (s): 2.36 | learning rate: 3.972E-05 | global batch size: 512 | lm loss: 1.922918E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.292 | TFLOPs: 22.37 | +63: iteration 58130/ 73814 | consumed samples: 29762560 | consumed tokens: 60953722880 | elapsed time per iteration (s): 2.24 | learning rate: 3.970E-05 | global batch size: 512 | lm loss: 1.908381E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.380 | TFLOPs: 23.51 | +63: iteration 58140/ 73814 | consumed samples: 29767680 | consumed tokens: 60964208640 | elapsed time per iteration (s): 2.23 | learning rate: 3.967E-05 | global batch size: 512 | lm loss: 1.904837E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.859 | TFLOPs: 23.66 | +63: iteration 58150/ 73814 | consumed samples: 29772800 | consumed tokens: 60974694400 | elapsed time per iteration (s): 2.25 | learning rate: 3.965E-05 | global batch size: 512 | lm loss: 1.907180E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.015 | TFLOPs: 23.47 | +63: iteration 58160/ 73814 | consumed samples: 29777920 | consumed tokens: 60985180160 | elapsed time per iteration (s): 2.23 | learning rate: 3.962E-05 | global batch size: 512 | lm loss: 1.918004E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.612 | TFLOPs: 23.64 | +63: iteration 58170/ 73814 | consumed samples: 29783040 | consumed tokens: 60995665920 | elapsed time per iteration (s): 2.25 | learning rate: 3.960E-05 | global batch size: 512 | lm loss: 1.920937E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.585 | TFLOPs: 23.43 | +63: iteration 58180/ 73814 | consumed samples: 29788160 | consumed tokens: 61006151680 | elapsed time per iteration (s): 2.23 | learning rate: 3.958E-05 | global batch size: 512 | lm loss: 1.935593E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.817 | TFLOPs: 23.66 | +63: iteration 58190/ 73814 | consumed samples: 29793280 | consumed tokens: 61016637440 | elapsed time per iteration (s): 2.27 | learning rate: 3.955E-05 | global batch size: 512 | lm loss: 1.914552E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.681 | TFLOPs: 23.23 | +63: iteration 58200/ 73814 | consumed samples: 29798400 | consumed tokens: 61027123200 | elapsed time per iteration (s): 2.28 | learning rate: 3.953E-05 | global batch size: 512 | lm loss: 1.893738E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.405 | TFLOPs: 23.10 | +63: iteration 58210/ 73814 | consumed samples: 29803520 | consumed tokens: 61037608960 | elapsed time per iteration (s): 2.25 | learning rate: 3.950E-05 | global batch size: 512 | lm loss: 1.877532E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.030 | TFLOPs: 23.47 | +63: iteration 58220/ 73814 | consumed samples: 29808640 | consumed tokens: 61048094720 | elapsed time per iteration (s): 2.26 | learning rate: 3.948E-05 | global batch size: 512 | lm loss: 1.920115E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.564 | TFLOPs: 23.32 | +63: iteration 58230/ 73814 | consumed samples: 29813760 | consumed tokens: 61058580480 | elapsed time per iteration (s): 2.23 | learning rate: 3.946E-05 | global batch size: 512 | lm loss: 1.896094E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.755 | TFLOPs: 23.65 | +63: iteration 58240/ 73814 | consumed samples: 29818880 | consumed tokens: 61069066240 | elapsed time per iteration (s): 2.23 | learning rate: 3.943E-05 | global batch size: 512 | lm loss: 1.916606E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.899 | TFLOPs: 23.67 | +63: iteration 58250/ 73814 | consumed samples: 29824000 | consumed tokens: 61079552000 | elapsed time per iteration (s): 2.22 | learning rate: 3.941E-05 | global batch size: 512 | lm loss: 1.901946E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.180 | TFLOPs: 23.70 | +63: iteration 58260/ 73814 | consumed samples: 29829120 | consumed tokens: 61090037760 | elapsed time per iteration (s): 2.23 | learning rate: 3.938E-05 | global batch size: 512 | lm loss: 1.902315E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.985 | TFLOPs: 23.68 | +63: iteration 58270/ 73814 | consumed samples: 29834240 | consumed tokens: 61100523520 | elapsed time per iteration (s): 2.24 | learning rate: 3.936E-05 | global batch size: 512 | lm loss: 1.922626E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.751 | TFLOPs: 23.55 | +63: iteration 58280/ 73814 | consumed samples: 29839360 | consumed tokens: 61111009280 | elapsed time per iteration (s): 2.24 | learning rate: 3.934E-05 | global batch size: 512 | lm loss: 1.922849E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.838 | TFLOPs: 23.56 | +63: iteration 58290/ 73814 | consumed samples: 29844480 | consumed tokens: 61121495040 | elapsed time per iteration (s): 2.25 | learning rate: 3.931E-05 | global batch size: 512 | lm loss: 1.920502E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.697 | TFLOPs: 23.44 | +63: iteration 58300/ 73814 | consumed samples: 29849600 | consumed tokens: 61131980800 | elapsed time per iteration (s): 2.25 | learning rate: 3.929E-05 | global batch size: 512 | lm loss: 1.929444E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.682 | TFLOPs: 23.44 | +63: iteration 58310/ 73814 | consumed samples: 29854720 | consumed tokens: 61142466560 | elapsed time per iteration (s): 2.33 | learning rate: 3.926E-05 | global batch size: 512 | lm loss: 1.912232E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.116 | TFLOPs: 22.66 | +63: iteration 58320/ 73814 | consumed samples: 29859840 | consumed tokens: 61152952320 | elapsed time per iteration (s): 2.24 | learning rate: 3.924E-05 | global batch size: 512 | lm loss: 1.895003E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.288 | TFLOPs: 23.50 | +63: iteration 58330/ 73814 | consumed samples: 29864960 | consumed tokens: 61163438080 | elapsed time per iteration (s): 2.35 | learning rate: 3.922E-05 | global batch size: 512 | lm loss: 1.942157E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.962 | TFLOPs: 22.44 | +63: iteration 58340/ 73814 | consumed samples: 29870080 | consumed tokens: 61173923840 | elapsed time per iteration (s): 2.23 | learning rate: 3.919E-05 | global batch size: 512 | lm loss: 1.900642E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.286 | TFLOPs: 23.60 | +63: iteration 58350/ 73814 | consumed samples: 29875200 | consumed tokens: 61184409600 | elapsed time per iteration (s): 2.25 | learning rate: 3.917E-05 | global batch size: 512 | lm loss: 1.900224E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.979 | TFLOPs: 23.47 | +63: iteration 58360/ 73814 | consumed samples: 29880320 | consumed tokens: 61194895360 | elapsed time per iteration (s): 2.23 | learning rate: 3.914E-05 | global batch size: 512 | lm loss: 1.920961E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.893 | TFLOPs: 23.67 | +63: iteration 58370/ 73814 | consumed samples: 29885440 | consumed tokens: 61205381120 | elapsed time per iteration (s): 2.24 | learning rate: 3.912E-05 | global batch size: 512 | lm loss: 1.918062E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.358 | TFLOPs: 23.51 | +63: iteration 58380/ 73814 | consumed samples: 29890560 | consumed tokens: 61215866880 | elapsed time per iteration (s): 2.25 | learning rate: 3.910E-05 | global batch size: 512 | lm loss: 1.935062E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.964 | TFLOPs: 23.47 | +63: iteration 58390/ 73814 | consumed samples: 29895680 | consumed tokens: 61226352640 | elapsed time per iteration (s): 2.24 | learning rate: 3.907E-05 | global batch size: 512 | lm loss: 1.906939E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.029 | TFLOPs: 23.58 | +63: iteration 58400/ 73814 | consumed samples: 29900800 | consumed tokens: 61236838400 | elapsed time per iteration (s): 2.28 | learning rate: 3.905E-05 | global batch size: 512 | lm loss: 1.900147E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.532 | TFLOPs: 23.11 | +63: iteration 58410/ 73814 | consumed samples: 29905920 | consumed tokens: 61247324160 | elapsed time per iteration (s): 2.40 | learning rate: 3.902E-05 | global batch size: 512 | lm loss: 1.900326E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.188 | TFLOPs: 21.95 | +63: iteration 58420/ 73814 | consumed samples: 29911040 | consumed tokens: 61257809920 | elapsed time per iteration (s): 2.37 | learning rate: 3.900E-05 | global batch size: 512 | lm loss: 1.923167E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.489 | TFLOPs: 22.29 | +63: iteration 58430/ 73814 | consumed samples: 29916160 | consumed tokens: 61268295680 | elapsed time per iteration (s): 2.23 | learning rate: 3.898E-05 | global batch size: 512 | lm loss: 1.914343E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.867 | TFLOPs: 23.66 | +63: iteration 58440/ 73814 | consumed samples: 29921280 | consumed tokens: 61278781440 | elapsed time per iteration (s): 2.35 | learning rate: 3.895E-05 | global batch size: 512 | lm loss: 1.915116E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.834 | TFLOPs: 22.42 | +63: iteration 58450/ 73814 | consumed samples: 29926400 | consumed tokens: 61289267200 | elapsed time per iteration (s): 2.45 | learning rate: 3.893E-05 | global batch size: 512 | lm loss: 1.935404E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.717 | TFLOPs: 21.49 | +63: iteration 58460/ 73814 | consumed samples: 29931520 | consumed tokens: 61299752960 | elapsed time per iteration (s): 2.24 | learning rate: 3.891E-05 | global batch size: 512 | lm loss: 1.918217E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.822 | TFLOPs: 23.56 | +63: iteration 58470/ 73814 | consumed samples: 29936640 | consumed tokens: 61310238720 | elapsed time per iteration (s): 2.23 | learning rate: 3.888E-05 | global batch size: 512 | lm loss: 1.912352E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.166 | TFLOPs: 23.59 | +63: iteration 58480/ 73814 | consumed samples: 29941760 | consumed tokens: 61320724480 | elapsed time per iteration (s): 2.24 | learning rate: 3.886E-05 | global batch size: 512 | lm loss: 1.922746E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.622 | TFLOPs: 23.54 | +63: iteration 58490/ 73814 | consumed samples: 29946880 | consumed tokens: 61331210240 | elapsed time per iteration (s): 2.26 | learning rate: 3.883E-05 | global batch size: 512 | lm loss: 1.908095E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.506 | TFLOPs: 23.32 | +63: iteration 58500/ 73814 | consumed samples: 29952000 | consumed tokens: 61341696000 | elapsed time per iteration (s): 2.25 | learning rate: 3.881E-05 | global batch size: 512 | lm loss: 1.915669E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.447 | TFLOPs: 23.41 | +63: iteration 58510/ 73814 | consumed samples: 29957120 | consumed tokens: 61352181760 | elapsed time per iteration (s): 2.38 | learning rate: 3.879E-05 | global batch size: 512 | lm loss: 1.912744E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.844 | TFLOPs: 22.12 | +63: iteration 58520/ 73814 | consumed samples: 29962240 | consumed tokens: 61362667520 | elapsed time per iteration (s): 2.25 | learning rate: 3.876E-05 | global batch size: 512 | lm loss: 1.907565E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.474 | TFLOPs: 23.42 | +63: iteration 58530/ 73814 | consumed samples: 29967360 | consumed tokens: 61373153280 | elapsed time per iteration (s): 2.23 | learning rate: 3.874E-05 | global batch size: 512 | lm loss: 1.889626E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.174 | TFLOPs: 23.59 | +63: iteration 58540/ 73814 | consumed samples: 29972480 | consumed tokens: 61383639040 | elapsed time per iteration (s): 2.35 | learning rate: 3.872E-05 | global batch size: 512 | lm loss: 1.911272E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.832 | TFLOPs: 22.42 | +63: iteration 58550/ 73814 | consumed samples: 29977600 | consumed tokens: 61394124800 | elapsed time per iteration (s): 2.23 | learning rate: 3.869E-05 | global batch size: 512 | lm loss: 1.902056E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.671 | TFLOPs: 23.64 | +63: iteration 58560/ 73814 | consumed samples: 29982720 | consumed tokens: 61404610560 | elapsed time per iteration (s): 2.23 | learning rate: 3.867E-05 | global batch size: 512 | lm loss: 1.927317E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.944 | TFLOPs: 23.67 | +63: iteration 58570/ 73814 | consumed samples: 29987840 | consumed tokens: 61415096320 | elapsed time per iteration (s): 2.23 | learning rate: 3.865E-05 | global batch size: 512 | lm loss: 1.884354E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.037 | TFLOPs: 23.68 | +63: iteration 58580/ 73814 | consumed samples: 29992960 | consumed tokens: 61425582080 | elapsed time per iteration (s): 2.26 | learning rate: 3.862E-05 | global batch size: 512 | lm loss: 1.906794E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.782 | TFLOPs: 23.35 | +63: iteration 58590/ 73814 | consumed samples: 29998080 | consumed tokens: 61436067840 | elapsed time per iteration (s): 2.24 | learning rate: 3.860E-05 | global batch size: 512 | lm loss: 1.901460E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.241 | TFLOPs: 23.50 | +63: iteration 58600/ 73814 | consumed samples: 30003200 | consumed tokens: 61446553600 | elapsed time per iteration (s): 2.25 | learning rate: 3.858E-05 | global batch size: 512 | lm loss: 1.912558E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.059 | TFLOPs: 23.48 | +63: iteration 58610/ 73814 | consumed samples: 30008320 | consumed tokens: 61457039360 | elapsed time per iteration (s): 2.23 | learning rate: 3.855E-05 | global batch size: 512 | lm loss: 1.931072E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.464 | TFLOPs: 23.62 | +63: iteration 58620/ 73814 | consumed samples: 30013440 | consumed tokens: 61467525120 | elapsed time per iteration (s): 2.22 | learning rate: 3.853E-05 | global batch size: 512 | lm loss: 1.907744E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.194 | TFLOPs: 23.70 | +63: iteration 58630/ 73814 | consumed samples: 30018560 | consumed tokens: 61478010880 | elapsed time per iteration (s): 2.23 | learning rate: 3.850E-05 | global batch size: 512 | lm loss: 1.898819E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.217 | TFLOPs: 23.60 | +63: iteration 58640/ 73814 | consumed samples: 30023680 | consumed tokens: 61488496640 | elapsed time per iteration (s): 2.24 | learning rate: 3.848E-05 | global batch size: 512 | lm loss: 1.912014E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.102 | TFLOPs: 23.48 | +63: iteration 58650/ 73814 | consumed samples: 30028800 | consumed tokens: 61498982400 | elapsed time per iteration (s): 2.25 | learning rate: 3.846E-05 | global batch size: 512 | lm loss: 1.912810E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.054 | TFLOPs: 23.48 | +63: iteration 58660/ 73814 | consumed samples: 30033920 | consumed tokens: 61509468160 | elapsed time per iteration (s): 2.23 | learning rate: 3.843E-05 | global batch size: 512 | lm loss: 1.896833E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.621 | TFLOPs: 23.64 | +63: iteration 58670/ 73814 | consumed samples: 30039040 | consumed tokens: 61519953920 | elapsed time per iteration (s): 2.22 | learning rate: 3.841E-05 | global batch size: 512 | lm loss: 1.893770E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.240 | TFLOPs: 23.70 | +63: iteration 58680/ 73814 | consumed samples: 30044160 | consumed tokens: 61530439680 | elapsed time per iteration (s): 2.25 | learning rate: 3.839E-05 | global batch size: 512 | lm loss: 1.896630E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.928 | TFLOPs: 23.46 | +63: iteration 58690/ 73814 | consumed samples: 30049280 | consumed tokens: 61540925440 | elapsed time per iteration (s): 2.23 | learning rate: 3.836E-05 | global batch size: 512 | lm loss: 1.890948E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.868 | TFLOPs: 23.66 | +63: iteration 58700/ 73814 | consumed samples: 30054400 | consumed tokens: 61551411200 | elapsed time per iteration (s): 2.22 | learning rate: 3.834E-05 | global batch size: 512 | lm loss: 1.901057E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.191 | TFLOPs: 23.70 | +63: iteration 58710/ 73814 | consumed samples: 30059520 | consumed tokens: 61561896960 | elapsed time per iteration (s): 2.23 | learning rate: 3.832E-05 | global batch size: 512 | lm loss: 1.903972E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.487 | TFLOPs: 23.62 | +63: iteration 58720/ 73814 | consumed samples: 30064640 | consumed tokens: 61572382720 | elapsed time per iteration (s): 2.23 | learning rate: 3.829E-05 | global batch size: 512 | lm loss: 1.912509E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.357 | TFLOPs: 23.61 | +63: iteration 58730/ 73814 | consumed samples: 30069760 | consumed tokens: 61582868480 | elapsed time per iteration (s): 2.24 | learning rate: 3.827E-05 | global batch size: 512 | lm loss: 1.921313E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.434 | TFLOPs: 23.52 | +63: iteration 58740/ 73814 | consumed samples: 30074880 | consumed tokens: 61593354240 | elapsed time per iteration (s): 2.23 | learning rate: 3.825E-05 | global batch size: 512 | lm loss: 1.901405E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.988 | TFLOPs: 23.68 | +63: iteration 58750/ 73814 | consumed samples: 30080000 | consumed tokens: 61603840000 | elapsed time per iteration (s): 2.35 | learning rate: 3.822E-05 | global batch size: 512 | lm loss: 1.899137E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.073 | TFLOPs: 22.45 | +63: iteration 58760/ 73814 | consumed samples: 30085120 | consumed tokens: 61614325760 | elapsed time per iteration (s): 2.23 | learning rate: 3.820E-05 | global batch size: 512 | lm loss: 1.916545E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.437 | TFLOPs: 23.62 | +63: iteration 58770/ 73814 | consumed samples: 30090240 | consumed tokens: 61624811520 | elapsed time per iteration (s): 2.25 | learning rate: 3.818E-05 | global batch size: 512 | lm loss: 1.910343E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.582 | TFLOPs: 23.43 | +63: iteration 58780/ 73814 | consumed samples: 30095360 | consumed tokens: 61635297280 | elapsed time per iteration (s): 2.22 | learning rate: 3.815E-05 | global batch size: 512 | lm loss: 1.887474E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.368 | TFLOPs: 23.72 | +63: iteration 58790/ 73814 | consumed samples: 30100480 | consumed tokens: 61645783040 | elapsed time per iteration (s): 2.34 | learning rate: 3.813E-05 | global batch size: 512 | lm loss: 1.930824E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.344 | TFLOPs: 22.48 | +63: iteration 58800/ 73814 | consumed samples: 30105600 | consumed tokens: 61656268800 | elapsed time per iteration (s): 2.23 | learning rate: 3.811E-05 | global batch size: 512 | lm loss: 1.920904E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.794 | TFLOPs: 23.66 | +63: iteration 58810/ 73814 | consumed samples: 30110720 | consumed tokens: 61666754560 | elapsed time per iteration (s): 2.24 | learning rate: 3.808E-05 | global batch size: 512 | lm loss: 1.896986E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.394 | TFLOPs: 23.51 | +63: iteration 58820/ 73814 | consumed samples: 30115840 | consumed tokens: 61677240320 | elapsed time per iteration (s): 2.26 | learning rate: 3.806E-05 | global batch size: 512 | lm loss: 1.902949E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.127 | TFLOPs: 23.28 | +63: iteration 58830/ 73814 | consumed samples: 30120960 | consumed tokens: 61687726080 | elapsed time per iteration (s): 2.22 | learning rate: 3.804E-05 | global batch size: 512 | lm loss: 1.915328E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.254 | TFLOPs: 23.70 | +63: iteration 58840/ 73814 | consumed samples: 30126080 | consumed tokens: 61698211840 | elapsed time per iteration (s): 2.23 | learning rate: 3.801E-05 | global batch size: 512 | lm loss: 1.907084E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.087 | TFLOPs: 23.58 | +63: iteration 58850/ 73814 | consumed samples: 30131200 | consumed tokens: 61708697600 | elapsed time per iteration (s): 2.23 | learning rate: 3.799E-05 | global batch size: 512 | lm loss: 1.895290E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.831 | TFLOPs: 23.66 | +63: iteration 58860/ 73814 | consumed samples: 30136320 | consumed tokens: 61719183360 | elapsed time per iteration (s): 2.23 | learning rate: 3.797E-05 | global batch size: 512 | lm loss: 1.893028E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.917 | TFLOPs: 23.67 | +63: iteration 58870/ 73814 | consumed samples: 30141440 | consumed tokens: 61729669120 | elapsed time per iteration (s): 2.24 | learning rate: 3.794E-05 | global batch size: 512 | lm loss: 1.909672E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.204 | TFLOPs: 23.49 | +63: iteration 58880/ 73814 | consumed samples: 30146560 | consumed tokens: 61740154880 | elapsed time per iteration (s): 2.24 | learning rate: 3.792E-05 | global batch size: 512 | lm loss: 1.890812E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.328 | TFLOPs: 23.51 | +63: iteration 58890/ 73814 | consumed samples: 30151680 | consumed tokens: 61750640640 | elapsed time per iteration (s): 2.23 | learning rate: 3.790E-05 | global batch size: 512 | lm loss: 1.917978E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.090 | TFLOPs: 23.69 | +63: iteration 58900/ 73814 | consumed samples: 30156800 | consumed tokens: 61761126400 | elapsed time per iteration (s): 2.26 | learning rate: 3.787E-05 | global batch size: 512 | lm loss: 1.890649E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.966 | TFLOPs: 23.37 | +63: iteration 58910/ 73814 | consumed samples: 30161920 | consumed tokens: 61771612160 | elapsed time per iteration (s): 2.22 | learning rate: 3.785E-05 | global batch size: 512 | lm loss: 1.897838E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.244 | TFLOPs: 23.70 | +63: iteration 58920/ 73814 | consumed samples: 30167040 | consumed tokens: 61782097920 | elapsed time per iteration (s): 2.34 | learning rate: 3.783E-05 | global batch size: 512 | lm loss: 1.910329E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.074 | TFLOPs: 22.55 | +63: iteration 58930/ 73814 | consumed samples: 30172160 | consumed tokens: 61792583680 | elapsed time per iteration (s): 2.24 | learning rate: 3.781E-05 | global batch size: 512 | lm loss: 1.913788E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.085 | TFLOPs: 23.48 | +63: iteration 58940/ 73814 | consumed samples: 30177280 | consumed tokens: 61803069440 | elapsed time per iteration (s): 2.23 | learning rate: 3.778E-05 | global batch size: 512 | lm loss: 1.933862E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.983 | TFLOPs: 23.68 | +63: iteration 58950/ 73814 | consumed samples: 30182400 | consumed tokens: 61813555200 | elapsed time per iteration (s): 2.24 | learning rate: 3.776E-05 | global batch size: 512 | lm loss: 1.917044E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.403 | TFLOPs: 23.51 | +63: iteration 58960/ 73814 | consumed samples: 30187520 | consumed tokens: 61824040960 | elapsed time per iteration (s): 2.30 | learning rate: 3.774E-05 | global batch size: 512 | lm loss: 1.913032E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.305 | TFLOPs: 22.89 | +63: iteration 58970/ 73814 | consumed samples: 30192640 | consumed tokens: 61834526720 | elapsed time per iteration (s): 2.23 | learning rate: 3.771E-05 | global batch size: 512 | lm loss: 1.919316E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.510 | TFLOPs: 23.63 | +63: iteration 58980/ 73814 | consumed samples: 30197760 | consumed tokens: 61845012480 | elapsed time per iteration (s): 2.24 | learning rate: 3.769E-05 | global batch size: 512 | lm loss: 1.928371E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.456 | TFLOPs: 23.52 | +63: iteration 58990/ 73814 | consumed samples: 30202880 | consumed tokens: 61855498240 | elapsed time per iteration (s): 2.26 | learning rate: 3.767E-05 | global batch size: 512 | lm loss: 1.931412E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.824 | TFLOPs: 23.35 | +63: iteration 59000/ 73814 | consumed samples: 30208000 | consumed tokens: 61865984000 | elapsed time per iteration (s): 2.22 | learning rate: 3.764E-05 | global batch size: 512 | lm loss: 1.902373E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.316 | TFLOPs: 23.71 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 59000 | lm loss value: 1.785393E+00 | lm loss PPL: 5.961920E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 59010/ 73814 | consumed samples: 30213120 | consumed tokens: 61876469760 | elapsed time per iteration (s): 2.65 | learning rate: 3.762E-05 | global batch size: 512 | lm loss: 1.923991E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 193.000 | TFLOPs: 19.87 | +63: iteration 59020/ 73814 | consumed samples: 30218240 | consumed tokens: 61886955520 | elapsed time per iteration (s): 2.23 | learning rate: 3.760E-05 | global batch size: 512 | lm loss: 1.899667E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.541 | TFLOPs: 23.63 | +63: iteration 59030/ 73814 | consumed samples: 30223360 | consumed tokens: 61897441280 | elapsed time per iteration (s): 2.23 | learning rate: 3.758E-05 | global batch size: 512 | lm loss: 1.914357E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.681 | TFLOPs: 23.64 | +63: iteration 59040/ 73814 | consumed samples: 30228480 | consumed tokens: 61907927040 | elapsed time per iteration (s): 2.35 | learning rate: 3.755E-05 | global batch size: 512 | lm loss: 1.892758E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.947 | TFLOPs: 22.44 | +63: iteration 59050/ 73814 | consumed samples: 30233600 | consumed tokens: 61918412800 | elapsed time per iteration (s): 2.23 | learning rate: 3.753E-05 | global batch size: 512 | lm loss: 1.885231E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.590 | TFLOPs: 23.64 | +63: iteration 59060/ 73814 | consumed samples: 30238720 | consumed tokens: 61928898560 | elapsed time per iteration (s): 2.57 | learning rate: 3.751E-05 | global batch size: 512 | lm loss: 1.901335E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.273 | TFLOPs: 20.51 | +63: iteration 59070/ 73814 | consumed samples: 30243840 | consumed tokens: 61939384320 | elapsed time per iteration (s): 2.24 | learning rate: 3.748E-05 | global batch size: 512 | lm loss: 1.911097E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.282 | TFLOPs: 23.50 | +63: iteration 59080/ 73814 | consumed samples: 30248960 | consumed tokens: 61949870080 | elapsed time per iteration (s): 2.23 | learning rate: 3.746E-05 | global batch size: 512 | lm loss: 1.913248E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.917 | TFLOPs: 23.67 | +63: iteration 59090/ 73814 | consumed samples: 30254080 | consumed tokens: 61960355840 | elapsed time per iteration (s): 2.31 | learning rate: 3.744E-05 | global batch size: 512 | lm loss: 1.899253E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.645 | TFLOPs: 22.82 | +63: iteration 59100/ 73814 | consumed samples: 30259200 | consumed tokens: 61970841600 | elapsed time per iteration (s): 2.24 | learning rate: 3.741E-05 | global batch size: 512 | lm loss: 1.930275E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.921 | TFLOPs: 23.57 | +63: iteration 59110/ 73814 | consumed samples: 30264320 | consumed tokens: 61981327360 | elapsed time per iteration (s): 2.23 | learning rate: 3.739E-05 | global batch size: 512 | lm loss: 1.908433E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.540 | TFLOPs: 23.63 | +63: iteration 59120/ 73814 | consumed samples: 30269440 | consumed tokens: 61991813120 | elapsed time per iteration (s): 2.36 | learning rate: 3.737E-05 | global batch size: 512 | lm loss: 1.895467E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.563 | TFLOPs: 22.29 | +63: iteration 59130/ 73814 | consumed samples: 30274560 | consumed tokens: 62002298880 | elapsed time per iteration (s): 2.48 | learning rate: 3.735E-05 | global batch size: 512 | lm loss: 1.930473E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.825 | TFLOPs: 21.29 | +63: iteration 59140/ 73814 | consumed samples: 30279680 | consumed tokens: 62012784640 | elapsed time per iteration (s): 2.25 | learning rate: 3.732E-05 | global batch size: 512 | lm loss: 1.876255E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.093 | TFLOPs: 23.38 | +63: iteration 59150/ 73814 | consumed samples: 30284800 | consumed tokens: 62023270400 | elapsed time per iteration (s): 2.24 | learning rate: 3.730E-05 | global batch size: 512 | lm loss: 1.916150E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.109 | TFLOPs: 23.48 | +63: iteration 59160/ 73814 | consumed samples: 30289920 | consumed tokens: 62033756160 | elapsed time per iteration (s): 2.23 | learning rate: 3.728E-05 | global batch size: 512 | lm loss: 1.903369E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.890 | TFLOPs: 23.67 | +63: iteration 59170/ 73814 | consumed samples: 30295040 | consumed tokens: 62044241920 | elapsed time per iteration (s): 2.23 | learning rate: 3.725E-05 | global batch size: 512 | lm loss: 1.899816E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.724 | TFLOPs: 23.65 | +63: iteration 59180/ 73814 | consumed samples: 30300160 | consumed tokens: 62054727680 | elapsed time per iteration (s): 2.24 | learning rate: 3.723E-05 | global batch size: 512 | lm loss: 1.891665E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.262 | TFLOPs: 23.50 | +63: iteration 59190/ 73814 | consumed samples: 30305280 | consumed tokens: 62065213440 | elapsed time per iteration (s): 2.23 | learning rate: 3.721E-05 | global batch size: 512 | lm loss: 1.912090E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.930 | TFLOPs: 23.67 | +63: iteration 59200/ 73814 | consumed samples: 30310400 | consumed tokens: 62075699200 | elapsed time per iteration (s): 2.24 | learning rate: 3.719E-05 | global batch size: 512 | lm loss: 1.900993E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.934 | TFLOPs: 23.57 | +63: iteration 59210/ 73814 | consumed samples: 30315520 | consumed tokens: 62086184960 | elapsed time per iteration (s): 2.37 | learning rate: 3.716E-05 | global batch size: 512 | lm loss: 1.896167E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.039 | TFLOPs: 22.24 | +63: iteration 59220/ 73814 | consumed samples: 30320640 | consumed tokens: 62096670720 | elapsed time per iteration (s): 2.23 | learning rate: 3.714E-05 | global batch size: 512 | lm loss: 1.902521E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.700 | TFLOPs: 23.65 | +63: iteration 59230/ 73814 | consumed samples: 30325760 | consumed tokens: 62107156480 | elapsed time per iteration (s): 2.25 | learning rate: 3.712E-05 | global batch size: 512 | lm loss: 1.887376E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.714 | TFLOPs: 23.44 | +63: iteration 59240/ 73814 | consumed samples: 30330880 | consumed tokens: 62117642240 | elapsed time per iteration (s): 2.24 | learning rate: 3.710E-05 | global batch size: 512 | lm loss: 1.922903E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.461 | TFLOPs: 23.52 | +63: iteration 59250/ 73814 | consumed samples: 30336000 | consumed tokens: 62128128000 | elapsed time per iteration (s): 2.23 | learning rate: 3.707E-05 | global batch size: 512 | lm loss: 1.924812E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.960 | TFLOPs: 23.67 | +63: iteration 59260/ 73814 | consumed samples: 30341120 | consumed tokens: 62138613760 | elapsed time per iteration (s): 2.23 | learning rate: 3.705E-05 | global batch size: 512 | lm loss: 1.904477E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.388 | TFLOPs: 23.61 | +63: iteration 59270/ 73814 | consumed samples: 30346240 | consumed tokens: 62149099520 | elapsed time per iteration (s): 2.23 | learning rate: 3.703E-05 | global batch size: 512 | lm loss: 1.897862E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.355 | TFLOPs: 23.61 | +63: iteration 59280/ 73814 | consumed samples: 30351360 | consumed tokens: 62159585280 | elapsed time per iteration (s): 2.24 | learning rate: 3.701E-05 | global batch size: 512 | lm loss: 1.936225E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.100 | TFLOPs: 23.48 | +63: iteration 59290/ 73814 | consumed samples: 30356480 | consumed tokens: 62170071040 | elapsed time per iteration (s): 2.28 | learning rate: 3.698E-05 | global batch size: 512 | lm loss: 1.889674E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.081 | TFLOPs: 23.07 | +63: iteration 59300/ 73814 | consumed samples: 30361600 | consumed tokens: 62180556800 | elapsed time per iteration (s): 2.24 | learning rate: 3.696E-05 | global batch size: 512 | lm loss: 1.908870E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.922 | TFLOPs: 23.57 | +63: iteration 59310/ 73814 | consumed samples: 30366720 | consumed tokens: 62191042560 | elapsed time per iteration (s): 2.24 | learning rate: 3.694E-05 | global batch size: 512 | lm loss: 1.895604E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.488 | TFLOPs: 23.52 | +63: iteration 59320/ 73814 | consumed samples: 30371840 | consumed tokens: 62201528320 | elapsed time per iteration (s): 2.23 | learning rate: 3.691E-05 | global batch size: 512 | lm loss: 1.909458E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.239 | TFLOPs: 23.60 | +63: iteration 59330/ 73814 | consumed samples: 30376960 | consumed tokens: 62212014080 | elapsed time per iteration (s): 2.29 | learning rate: 3.689E-05 | global batch size: 512 | lm loss: 1.927398E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.143 | TFLOPs: 22.97 | +63: iteration 59340/ 73814 | consumed samples: 30382080 | consumed tokens: 62222499840 | elapsed time per iteration (s): 2.24 | learning rate: 3.687E-05 | global batch size: 512 | lm loss: 1.910780E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.743 | TFLOPs: 23.55 | +63: iteration 59350/ 73814 | consumed samples: 30387200 | consumed tokens: 62232985600 | elapsed time per iteration (s): 2.26 | learning rate: 3.685E-05 | global batch size: 512 | lm loss: 1.902963E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.409 | TFLOPs: 23.31 | +63: iteration 59360/ 73814 | consumed samples: 30392320 | consumed tokens: 62243471360 | elapsed time per iteration (s): 2.28 | learning rate: 3.682E-05 | global batch size: 512 | lm loss: 1.921485E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.317 | TFLOPs: 23.09 | +63: iteration 59370/ 73814 | consumed samples: 30397440 | consumed tokens: 62253957120 | elapsed time per iteration (s): 2.34 | learning rate: 3.680E-05 | global batch size: 512 | lm loss: 1.906511E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.724 | TFLOPs: 22.52 | +63: iteration 59380/ 73814 | consumed samples: 30402560 | consumed tokens: 62264442880 | elapsed time per iteration (s): 2.26 | learning rate: 3.678E-05 | global batch size: 512 | lm loss: 1.890243E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.407 | TFLOPs: 23.31 | +63: iteration 59390/ 73814 | consumed samples: 30407680 | consumed tokens: 62274928640 | elapsed time per iteration (s): 2.39 | learning rate: 3.676E-05 | global batch size: 512 | lm loss: 1.897653E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.199 | TFLOPs: 22.05 | +63: iteration 59400/ 73814 | consumed samples: 30412800 | consumed tokens: 62285414400 | elapsed time per iteration (s): 2.55 | learning rate: 3.673E-05 | global batch size: 512 | lm loss: 1.908677E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.482 | TFLOPs: 20.64 | +63: iteration 59410/ 73814 | consumed samples: 30417920 | consumed tokens: 62295900160 | elapsed time per iteration (s): 3.38 | learning rate: 3.671E-05 | global batch size: 512 | lm loss: 1.901190E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 151.348 | TFLOPs: 15.58 | +63: iteration 59420/ 73814 | consumed samples: 30423040 | consumed tokens: 62306385920 | elapsed time per iteration (s): 2.61 | learning rate: 3.669E-05 | global batch size: 512 | lm loss: 1.896502E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 195.794 | TFLOPs: 20.16 | +63: iteration 59430/ 73814 | consumed samples: 30428160 | consumed tokens: 62316871680 | elapsed time per iteration (s): 2.23 | learning rate: 3.667E-05 | global batch size: 512 | lm loss: 1.911386E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.358 | TFLOPs: 23.61 | +63: iteration 59440/ 73814 | consumed samples: 30433280 | consumed tokens: 62327357440 | elapsed time per iteration (s): 2.28 | learning rate: 3.664E-05 | global batch size: 512 | lm loss: 1.891448E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.224 | TFLOPs: 23.08 | +63: iteration 59450/ 73814 | consumed samples: 30438400 | consumed tokens: 62337843200 | elapsed time per iteration (s): 2.30 | learning rate: 3.662E-05 | global batch size: 512 | lm loss: 1.918810E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.615 | TFLOPs: 22.92 | +63: iteration 59460/ 73814 | consumed samples: 30443520 | consumed tokens: 62348328960 | elapsed time per iteration (s): 2.31 | learning rate: 3.660E-05 | global batch size: 512 | lm loss: 1.934694E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.775 | TFLOPs: 22.83 | +63: iteration 59470/ 73814 | consumed samples: 30448640 | consumed tokens: 62358814720 | elapsed time per iteration (s): 2.24 | learning rate: 3.658E-05 | global batch size: 512 | lm loss: 1.931511E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.816 | TFLOPs: 23.56 | +63: iteration 59480/ 73814 | consumed samples: 30453760 | consumed tokens: 62369300480 | elapsed time per iteration (s): 2.23 | learning rate: 3.656E-05 | global batch size: 512 | lm loss: 1.915909E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.105 | TFLOPs: 23.69 | +63: iteration 59490/ 73814 | consumed samples: 30458880 | consumed tokens: 62379786240 | elapsed time per iteration (s): 2.26 | learning rate: 3.653E-05 | global batch size: 512 | lm loss: 1.908859E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.643 | TFLOPs: 23.33 | +63: iteration 59500/ 73814 | consumed samples: 30464000 | consumed tokens: 62390272000 | elapsed time per iteration (s): 2.24 | learning rate: 3.651E-05 | global batch size: 512 | lm loss: 1.913489E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.701 | TFLOPs: 23.54 | +63: iteration 59510/ 73814 | consumed samples: 30469120 | consumed tokens: 62400757760 | elapsed time per iteration (s): 2.36 | learning rate: 3.649E-05 | global batch size: 512 | lm loss: 1.898854E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.713 | TFLOPs: 22.31 | +63: iteration 59520/ 73814 | consumed samples: 30474240 | consumed tokens: 62411243520 | elapsed time per iteration (s): 2.53 | learning rate: 3.647E-05 | global batch size: 512 | lm loss: 1.911486E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.433 | TFLOPs: 20.84 | +63: iteration 59530/ 73814 | consumed samples: 30479360 | consumed tokens: 62421729280 | elapsed time per iteration (s): 2.35 | learning rate: 3.644E-05 | global batch size: 512 | lm loss: 1.918055E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.815 | TFLOPs: 22.42 | +63: iteration 59540/ 73814 | consumed samples: 30484480 | consumed tokens: 62432215040 | elapsed time per iteration (s): 2.23 | learning rate: 3.642E-05 | global batch size: 512 | lm loss: 1.881363E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.951 | TFLOPs: 23.67 | +63: iteration 59550/ 73814 | consumed samples: 30489600 | consumed tokens: 62442700800 | elapsed time per iteration (s): 2.23 | learning rate: 3.640E-05 | global batch size: 512 | lm loss: 1.920061E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.891 | TFLOPs: 23.67 | +63: iteration 59560/ 73814 | consumed samples: 30494720 | consumed tokens: 62453186560 | elapsed time per iteration (s): 2.36 | learning rate: 3.638E-05 | global batch size: 512 | lm loss: 1.910408E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.117 | TFLOPs: 22.35 | +63: iteration 59570/ 73814 | consumed samples: 30499840 | consumed tokens: 62463672320 | elapsed time per iteration (s): 2.23 | learning rate: 3.635E-05 | global batch size: 512 | lm loss: 1.897976E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.202 | TFLOPs: 23.60 | +63: iteration 59580/ 73814 | consumed samples: 30504960 | consumed tokens: 62474158080 | elapsed time per iteration (s): 2.24 | learning rate: 3.633E-05 | global batch size: 512 | lm loss: 1.916229E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.648 | TFLOPs: 23.54 | +63: iteration 59590/ 73814 | consumed samples: 30510080 | consumed tokens: 62484643840 | elapsed time per iteration (s): 2.24 | learning rate: 3.631E-05 | global batch size: 512 | lm loss: 1.916146E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.709 | TFLOPs: 23.54 | +63: iteration 59600/ 73814 | consumed samples: 30515200 | consumed tokens: 62495129600 | elapsed time per iteration (s): 2.25 | learning rate: 3.629E-05 | global batch size: 512 | lm loss: 1.925047E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.791 | TFLOPs: 23.45 | +63: iteration 59610/ 73814 | consumed samples: 30520320 | consumed tokens: 62505615360 | elapsed time per iteration (s): 2.24 | learning rate: 3.627E-05 | global batch size: 512 | lm loss: 1.933817E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.257 | TFLOPs: 23.50 | +63: iteration 59620/ 73814 | consumed samples: 30525440 | consumed tokens: 62516101120 | elapsed time per iteration (s): 2.24 | learning rate: 3.624E-05 | global batch size: 512 | lm loss: 1.904190E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.074 | TFLOPs: 23.58 | +63: iteration 59630/ 73814 | consumed samples: 30530560 | consumed tokens: 62526586880 | elapsed time per iteration (s): 2.24 | learning rate: 3.622E-05 | global batch size: 512 | lm loss: 1.891569E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.344 | TFLOPs: 23.51 | +63: iteration 59640/ 73814 | consumed samples: 30535680 | consumed tokens: 62537072640 | elapsed time per iteration (s): 2.25 | learning rate: 3.620E-05 | global batch size: 512 | lm loss: 1.917745E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.521 | TFLOPs: 23.42 | +63: iteration 59650/ 73814 | consumed samples: 30540800 | consumed tokens: 62547558400 | elapsed time per iteration (s): 2.25 | learning rate: 3.618E-05 | global batch size: 512 | lm loss: 1.909450E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.987 | TFLOPs: 23.47 | +63: iteration 59660/ 73814 | consumed samples: 30545920 | consumed tokens: 62558044160 | elapsed time per iteration (s): 2.22 | learning rate: 3.615E-05 | global batch size: 512 | lm loss: 1.899331E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.589 | TFLOPs: 23.74 | +63: iteration 59670/ 73814 | consumed samples: 30551040 | consumed tokens: 62568529920 | elapsed time per iteration (s): 2.23 | learning rate: 3.613E-05 | global batch size: 512 | lm loss: 1.927044E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.987 | TFLOPs: 23.68 | +63: iteration 59680/ 73814 | consumed samples: 30556160 | consumed tokens: 62579015680 | elapsed time per iteration (s): 2.23 | learning rate: 3.611E-05 | global batch size: 512 | lm loss: 1.895608E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.778 | TFLOPs: 23.65 | +63: iteration 59690/ 73814 | consumed samples: 30561280 | consumed tokens: 62589501440 | elapsed time per iteration (s): 2.51 | learning rate: 3.609E-05 | global batch size: 512 | lm loss: 1.876593E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 203.747 | TFLOPs: 20.97 | +63: iteration 59700/ 73814 | consumed samples: 30566400 | consumed tokens: 62599987200 | elapsed time per iteration (s): 2.25 | learning rate: 3.607E-05 | global batch size: 512 | lm loss: 1.910243E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.119 | TFLOPs: 23.38 | +63: iteration 59710/ 73814 | consumed samples: 30571520 | consumed tokens: 62610472960 | elapsed time per iteration (s): 2.32 | learning rate: 3.604E-05 | global batch size: 512 | lm loss: 1.893528E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.674 | TFLOPs: 22.72 | +63: iteration 59720/ 73814 | consumed samples: 30576640 | consumed tokens: 62620958720 | elapsed time per iteration (s): 2.39 | learning rate: 3.602E-05 | global batch size: 512 | lm loss: 1.924761E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.026 | TFLOPs: 22.03 | +63: iteration 59730/ 73814 | consumed samples: 30581760 | consumed tokens: 62631444480 | elapsed time per iteration (s): 2.25 | learning rate: 3.600E-05 | global batch size: 512 | lm loss: 1.907925E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.467 | TFLOPs: 23.42 | +63: iteration 59740/ 73814 | consumed samples: 30586880 | consumed tokens: 62641930240 | elapsed time per iteration (s): 2.31 | learning rate: 3.598E-05 | global batch size: 512 | lm loss: 1.920174E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.020 | TFLOPs: 22.86 | +63: iteration 59750/ 73814 | consumed samples: 30592000 | consumed tokens: 62652416000 | elapsed time per iteration (s): 2.25 | learning rate: 3.596E-05 | global batch size: 512 | lm loss: 1.916005E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.815 | TFLOPs: 23.45 | +63: iteration 59760/ 73814 | consumed samples: 30597120 | consumed tokens: 62662901760 | elapsed time per iteration (s): 2.24 | learning rate: 3.593E-05 | global batch size: 512 | lm loss: 1.919380E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.119 | TFLOPs: 23.48 | +63: iteration 59770/ 73814 | consumed samples: 30602240 | consumed tokens: 62673387520 | elapsed time per iteration (s): 2.23 | learning rate: 3.591E-05 | global batch size: 512 | lm loss: 1.893630E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.700 | TFLOPs: 23.65 | +63: iteration 59780/ 73814 | consumed samples: 30607360 | consumed tokens: 62683873280 | elapsed time per iteration (s): 2.24 | learning rate: 3.589E-05 | global batch size: 512 | lm loss: 1.916428E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.048 | TFLOPs: 23.58 | +63: iteration 59790/ 73814 | consumed samples: 30612480 | consumed tokens: 62694359040 | elapsed time per iteration (s): 2.22 | learning rate: 3.587E-05 | global batch size: 512 | lm loss: 1.893526E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.287 | TFLOPs: 23.71 | +63: iteration 59800/ 73814 | consumed samples: 30617600 | consumed tokens: 62704844800 | elapsed time per iteration (s): 2.23 | learning rate: 3.585E-05 | global batch size: 512 | lm loss: 1.940660E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.988 | TFLOPs: 23.68 | +63: iteration 59810/ 73814 | consumed samples: 30622720 | consumed tokens: 62715330560 | elapsed time per iteration (s): 2.23 | learning rate: 3.582E-05 | global batch size: 512 | lm loss: 1.901919E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.569 | TFLOPs: 23.63 | +63: iteration 59820/ 73814 | consumed samples: 30627840 | consumed tokens: 62725816320 | elapsed time per iteration (s): 2.24 | learning rate: 3.580E-05 | global batch size: 512 | lm loss: 1.893378E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.381 | TFLOPs: 23.51 | +63: iteration 59830/ 73814 | consumed samples: 30632960 | consumed tokens: 62736302080 | elapsed time per iteration (s): 2.23 | learning rate: 3.578E-05 | global batch size: 512 | lm loss: 1.906613E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.229 | TFLOPs: 23.60 | +63: iteration 59840/ 73814 | consumed samples: 30638080 | consumed tokens: 62746787840 | elapsed time per iteration (s): 2.23 | learning rate: 3.576E-05 | global batch size: 512 | lm loss: 1.882819E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.044 | TFLOPs: 23.68 | +63: iteration 59850/ 73814 | consumed samples: 30643200 | consumed tokens: 62757273600 | elapsed time per iteration (s): 2.23 | learning rate: 3.574E-05 | global batch size: 512 | lm loss: 1.889825E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.040 | TFLOPs: 23.68 | +63: iteration 59860/ 73814 | consumed samples: 30648320 | consumed tokens: 62767759360 | elapsed time per iteration (s): 2.23 | learning rate: 3.572E-05 | global batch size: 512 | lm loss: 1.906286E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.306 | TFLOPs: 23.61 | +63: iteration 59870/ 73814 | consumed samples: 30653440 | consumed tokens: 62778245120 | elapsed time per iteration (s): 2.41 | learning rate: 3.569E-05 | global batch size: 512 | lm loss: 1.918968E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.827 | TFLOPs: 21.91 | +63: iteration 59880/ 73814 | consumed samples: 30658560 | consumed tokens: 62788730880 | elapsed time per iteration (s): 2.24 | learning rate: 3.567E-05 | global batch size: 512 | lm loss: 1.908343E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.232 | TFLOPs: 23.50 | +63: iteration 59890/ 73814 | consumed samples: 30663680 | consumed tokens: 62799216640 | elapsed time per iteration (s): 2.30 | learning rate: 3.565E-05 | global batch size: 512 | lm loss: 1.906995E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.874 | TFLOPs: 22.94 | +63: iteration 59900/ 73814 | consumed samples: 30668800 | consumed tokens: 62809702400 | elapsed time per iteration (s): 2.22 | learning rate: 3.563E-05 | global batch size: 512 | lm loss: 1.910019E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.212 | TFLOPs: 23.70 | +63: iteration 59910/ 73814 | consumed samples: 30673920 | consumed tokens: 62820188160 | elapsed time per iteration (s): 2.23 | learning rate: 3.561E-05 | global batch size: 512 | lm loss: 1.913281E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.819 | TFLOPs: 23.66 | +63: iteration 59920/ 73814 | consumed samples: 30679040 | consumed tokens: 62830673920 | elapsed time per iteration (s): 2.24 | learning rate: 3.558E-05 | global batch size: 512 | lm loss: 1.911848E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.770 | TFLOPs: 23.55 | +63: iteration 59930/ 73814 | consumed samples: 30684160 | consumed tokens: 62841159680 | elapsed time per iteration (s): 2.37 | learning rate: 3.556E-05 | global batch size: 512 | lm loss: 1.914546E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.467 | TFLOPs: 22.28 | +63: iteration 59940/ 73814 | consumed samples: 30689280 | consumed tokens: 62851645440 | elapsed time per iteration (s): 2.23 | learning rate: 3.554E-05 | global batch size: 512 | lm loss: 1.914315E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.001 | TFLOPs: 23.68 | +63: iteration 59950/ 73814 | consumed samples: 30694400 | consumed tokens: 62862131200 | elapsed time per iteration (s): 2.23 | learning rate: 3.552E-05 | global batch size: 512 | lm loss: 1.935332E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.097 | TFLOPs: 23.69 | +63: iteration 59960/ 73814 | consumed samples: 30699520 | consumed tokens: 62872616960 | elapsed time per iteration (s): 2.23 | learning rate: 3.550E-05 | global batch size: 512 | lm loss: 1.905605E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.095 | TFLOPs: 23.69 | +63: iteration 59970/ 73814 | consumed samples: 30704640 | consumed tokens: 62883102720 | elapsed time per iteration (s): 2.23 | learning rate: 3.548E-05 | global batch size: 512 | lm loss: 1.882837E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.756 | TFLOPs: 23.65 | +63: iteration 59980/ 73814 | consumed samples: 30709760 | consumed tokens: 62893588480 | elapsed time per iteration (s): 2.22 | learning rate: 3.545E-05 | global batch size: 512 | lm loss: 1.925039E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.353 | TFLOPs: 23.71 | +63: iteration 59990/ 73814 | consumed samples: 30714880 | consumed tokens: 62904074240 | elapsed time per iteration (s): 2.23 | learning rate: 3.543E-05 | global batch size: 512 | lm loss: 1.923675E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.249 | TFLOPs: 23.60 | + 0: [2022-12-03 01:59:56,861] [INFO] [logging.py:68:log_dist] [Rank 0] step=60000, skipped=0, lr=[3.54106457419684e-05, 3.54106457419684e-05, 3.54106457419684e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 60000/ 73814 | consumed samples: 30720000 | consumed tokens: 62914560000 | elapsed time per iteration (s): 2.24 | learning rate: 3.541E-05 | global batch size: 512 | lm loss: 1.889015E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.386 | TFLOPs: 23.51 | + 0: steps: 60000 loss: 1.8949 iter time (s): 2.270 samples/sec: 225.545 +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 60000 | lm loss value: 1.771106E+00 | lm loss PPL: 5.877349E+00 | +63: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 60000 to checkpoints_3b977boscar + 0: [2022-12-03 01:59:57,708] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step60000 is begin to save! + 0: [2022-12-03 01:59:57,758] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_01-model_00-model_states.pt... +32: [2022-12-03 01:59:57,761] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_21-model_00-model_states.pt... +32: [2022-12-03 01:59:58,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_21-model_00-model_states.pt. +32: [2022-12-03 01:59:58,265] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_22-model_00-model_states.pt... + 0: [2022-12-03 01:59:58,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_01-model_00-model_states.pt. + 0: [2022-12-03 01:59:58,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_03-model_00-model_states.pt... +32: [2022-12-03 01:59:58,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_22-model_00-model_states.pt. +32: [2022-12-03 01:59:58,494] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_23-model_00-model_states.pt... + 0: [2022-12-03 01:59:58,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_03-model_00-model_states.pt. + 0: [2022-12-03 01:59:58,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_04-model_00-model_states.pt... +32: [2022-12-03 01:59:58,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_23-model_00-model_states.pt. +32: [2022-12-03 01:59:58,722] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_24-model_00-model_states.pt... + 0: [2022-12-03 01:59:58,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_04-model_00-model_states.pt. + 0: [2022-12-03 01:59:58,754] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_05-model_00-model_states.pt... +32: [2022-12-03 01:59:58,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_24-model_00-model_states.pt. +32: [2022-12-03 01:59:58,946] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_25-model_00-model_states.pt... + 0: [2022-12-03 01:59:58,978] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_05-model_00-model_states.pt. + 0: [2022-12-03 01:59:58,979] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_06-model_00-model_states.pt... +32: [2022-12-03 01:59:59,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_25-model_00-model_states.pt. +32: [2022-12-03 01:59:59,178] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_26-model_00-model_states.pt... + 0: [2022-12-03 01:59:59,204] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_06-model_00-model_states.pt. + 0: [2022-12-03 01:59:59,204] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_07-model_00-model_states.pt... +32: [2022-12-03 01:59:59,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_26-model_00-model_states.pt. +32: [2022-12-03 01:59:59,410] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_27-model_00-model_states.pt... + 0: [2022-12-03 01:59:59,437] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_07-model_00-model_states.pt. + 0: [2022-12-03 01:59:59,437] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_08-model_00-model_states.pt... +32: [2022-12-03 01:59:59,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_27-model_00-model_states.pt. +32: [2022-12-03 01:59:59,634] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_28-model_00-model_states.pt... + 0: [2022-12-03 01:59:59,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_08-model_00-model_states.pt. + 0: [2022-12-03 01:59:59,668] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_09-model_00-model_states.pt... +32: [2022-12-03 01:59:59,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_28-model_00-model_states.pt. +32: [2022-12-03 01:59:59,864] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_29-model_00-model_states.pt... + 0: [2022-12-03 01:59:59,896] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_09-model_00-model_states.pt. + 0: [2022-12-03 01:59:59,896] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_10-model_00-model_states.pt... +32: [2022-12-03 02:00:00,089] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_29-model_00-model_states.pt. +32: [2022-12-03 02:00:00,089] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_30-model_00-model_states.pt... + 0: [2022-12-03 02:00:00,123] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_10-model_00-model_states.pt. + 0: [2022-12-03 02:00:00,123] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_11-model_00-model_states.pt... +32: [2022-12-03 02:00:00,319] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_30-model_00-model_states.pt. +32: [2022-12-03 02:00:00,319] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_31-model_00-model_states.pt... + 0: [2022-12-03 02:00:00,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_11-model_00-model_states.pt. + 0: [2022-12-03 02:00:00,349] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_12-model_00-model_states.pt... +32: [2022-12-03 02:00:00,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_31-model_00-model_states.pt. +32: [2022-12-03 02:00:00,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_32-model_00-model_states.pt... + 0: [2022-12-03 02:00:00,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_12-model_00-model_states.pt. + 0: [2022-12-03 02:00:00,576] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_13-model_00-model_states.pt... +32: [2022-12-03 02:00:00,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_32-model_00-model_states.pt. +32: [2022-12-03 02:00:00,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_33-model_00-model_states.pt... + 0: [2022-12-03 02:00:00,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_13-model_00-model_states.pt. + 0: [2022-12-03 02:00:00,799] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_14-model_00-model_states.pt... +32: [2022-12-03 02:00:01,001] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_33-model_00-model_states.pt. +32: [2022-12-03 02:00:01,001] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_34-model_00-model_states.pt... + 0: [2022-12-03 02:00:01,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_14-model_00-model_states.pt. + 0: [2022-12-03 02:00:01,025] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_15-model_00-model_states.pt... +32: [2022-12-03 02:00:01,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_34-model_00-model_states.pt. +32: [2022-12-03 02:00:01,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_35-model_00-model_states.pt... + 0: [2022-12-03 02:00:01,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_15-model_00-model_states.pt. + 0: [2022-12-03 02:00:01,254] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_16-model_00-model_states.pt... +32: [2022-12-03 02:00:01,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_35-model_00-model_states.pt. +32: [2022-12-03 02:00:01,453] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_36-model_00-model_states.pt... + 0: [2022-12-03 02:00:01,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_16-model_00-model_states.pt. + 0: [2022-12-03 02:00:01,476] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_17-model_00-model_states.pt... +32: [2022-12-03 02:00:01,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_36-model_00-model_states.pt. +32: [2022-12-03 02:00:01,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_37-model_00-model_states.pt... + 0: [2022-12-03 02:00:01,703] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_17-model_00-model_states.pt. + 0: [2022-12-03 02:00:01,704] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_18-model_00-model_states.pt... +32: [2022-12-03 02:00:01,910] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_37-model_00-model_states.pt. +32: [2022-12-03 02:00:01,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_38-model_00-model_states.pt... + 0: [2022-12-03 02:00:01,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_18-model_00-model_states.pt. + 0: [2022-12-03 02:00:01,930] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_19-model_00-model_states.pt... +32: [2022-12-03 02:00:02,136] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_38-model_00-model_states.pt. +32: [2022-12-03 02:00:02,137] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_40-model_00-model_states.pt... +32: [2022-12-03 02:00:02,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_40-model_00-model_states.pt. +32: [2022-12-03 02:00:02,143] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/mp_rank_01_model_states.pt... +32: [2022-12-03 02:00:02,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/mp_rank_01_model_states.pt. + 0: [2022-12-03 02:00:02,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_19-model_00-model_states.pt. + 0: [2022-12-03 02:00:02,157] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/layer_20-model_00-model_states.pt... + 0: [2022-12-03 02:00:02,384] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/layer_20-model_00-model_states.pt. + 0: [2022-12-03 02:00:02,385] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_3b977boscar/global_step60000/mp_rank_00_model_states.pt + 0: [2022-12-03 02:00:02,385] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/mp_rank_00_model_states.pt... + 0: [2022-12-03 02:00:02,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/mp_rank_00_model_states.pt. +32: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt... +54: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt... +54: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt... +54: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt... +54: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt... +54: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt... +56: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt... +56: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt... +56: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt... +56: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt... +52: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt... +52: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt... +52: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt... +52: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt... +52: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt... +61: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt... +61: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt... +61: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt... +61: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt... +61: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt... +63: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt... +63: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt... +63: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt... +63: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt... +63: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt... +53: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt... +53: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt... +53: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt... +53: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt... +53: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt... +33: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt... +33: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt... +33: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt... +33: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt... +33: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt... +59: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt... +59: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt... +59: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt... +59: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt... +59: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt... +62: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt... +62: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt... +62: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt... +62: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt... +62: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt... +58: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt... +58: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt... +58: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt... +58: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt... +58: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt... +38: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt... +38: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt... +38: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt... +38: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt... +38: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt... +44: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt... +44: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt... +44: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt... +44: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt... +44: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt... +48: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt... +48: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt... +48: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt... +48: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt... +34: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt... +34: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt... +34: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt... +34: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt... +34: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt... +43: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt... +43: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt... +43: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt... +43: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt... +43: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt... +36: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt... +36: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt... +36: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt... +36: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt... +35: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt... +35: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt... +35: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt... +35: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt... +35: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt... +39: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt... +39: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt... +39: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt... +39: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt... +39: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt... +50: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt... +50: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt... +50: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt... +50: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt... +50: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt... +32: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt... +32: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt... +32: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt... +51: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt... +51: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt... +51: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt... +51: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt... +51: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt... +60: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt... +60: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt... +49: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt... +49: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt... +49: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt... +49: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt... +49: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt... +46: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt... +46: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt... +46: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt... +46: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt... +46: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt... +41: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt... +41: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt... +41: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt... +41: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt... +55: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt... +55: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt... +55: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt... +55: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt... +55: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt... +47: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt... +47: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt... +47: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt... +47: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt... +47: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt... +45: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt... +45: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt... +45: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt... +45: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt... +45: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt... +37: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt... +40: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt... +40: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt... +40: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt... +40: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt... +40: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt... +42: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt... +42: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt... +42: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt... +42: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt... +42: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt... +57: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt... +57: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt... +57: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt... +57: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt... +57: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt... +54: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt... +54: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt... +54: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt... +56: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt... +56: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt... +52: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt... +63: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt... +63: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt... +63: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt... +53: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt... +33: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt... +33: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt... +59: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt... +59: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt... +62: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt... +58: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt... +58: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt... +58: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt... +38: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt... +38: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt... +44: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt... +48: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt... +34: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt... +34: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt... +43: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt... +36: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt... +36: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt... +36: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt... +36: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt... +35: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt... +35: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt... +39: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt... +39: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt... +50: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt... +32: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt... +32: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt... +51: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt... +51: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt... +60: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt... +60: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt... +60: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt... +60: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt... +60: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt... +49: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt... +49: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt... +46: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt... +41: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt... +41: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt... +41: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt... +41: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt... +55: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt... +55: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt... +47: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt... +47: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt... +45: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt... +45: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt... +37: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt... +37: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt... +37: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt... +37: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt... +40: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt... +40: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt... +42: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt... +57: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt... +57: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt... +56: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt... +52: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt... +61: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt... +61: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt... +53: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt... +11: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +33: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt... +59: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt... +62: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt... +38: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt... +44: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt... +48: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt... +34: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt... +43: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt... +35: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt... +39: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt... +50: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt... +32: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt... +51: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt... +60: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt... +49: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt... +46: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt... +55: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt... +47: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt... +45: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt... +37: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt... +40: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt... +42: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt... +42: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt... +57: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt... + 0: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 7: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +19: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +20: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +56: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt... +52: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt... +61: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt... +15: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +53: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt... + 1: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +11: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +10: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +28: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +62: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt... +22: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +12: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +26: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +44: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt... +48: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt... +43: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt... + 2: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +25: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +50: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt... +32: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt... + 4: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 6: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +13: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +31: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +46: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt... + 3: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +27: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... + 8: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +16: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +14: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +17: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +17: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +29: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +30: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +24: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +23: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +37: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt... +21: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... + 0: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 0: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 7: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +19: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +20: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +15: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... + 1: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +11: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... + 5: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +10: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +10: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +28: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +22: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +12: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +18: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +26: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +48: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt... + 9: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 2: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +25: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... + 4: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 6: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +13: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +31: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... + 3: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +27: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... + 8: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... +16: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +14: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +17: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +29: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +30: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +24: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +23: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +37: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt... +21: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... + 0: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 7: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +19: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +20: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +15: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... + 1: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +11: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... + 5: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +10: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +28: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +22: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +12: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +18: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +18: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +26: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... + 9: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 2: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +25: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... + 4: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 6: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +13: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +31: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... + 3: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +27: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... + 8: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... +16: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +14: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +17: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +29: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +30: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +24: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +23: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +21: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... + 0: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 7: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +19: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +20: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +15: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +11: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... + 5: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +10: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +28: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +22: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +12: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +18: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +26: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... + 9: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 2: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +25: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... + 4: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 6: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +13: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +31: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... + 3: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +27: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... + 8: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... +16: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +14: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +17: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +29: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +30: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +24: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +23: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +21: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... + 0: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 7: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +19: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +20: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +15: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... + 1: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +11: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 5: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +28: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +22: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +12: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +18: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... + 9: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 2: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +25: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... + 4: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +13: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... + 3: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +27: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... + 8: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... +16: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +14: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +29: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +30: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +24: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +23: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +21: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... + 0: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 7: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +19: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +20: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +15: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... + 5: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +12: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +18: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... + 9: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 2: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +25: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... + 4: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 3: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 8: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... +16: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +14: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +29: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +30: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +24: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +23: [2022-12-03 02:00:02,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +21: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... + 0: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 7: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +19: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +20: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +15: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +28: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +12: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... + 9: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... +25: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... + 4: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 8: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +29: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +30: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +21: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... + 9: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 4: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 8: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 5: [2022-12-03 02:00:02,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +32: [2022-12-03 02:00:02,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt. +32: [2022-12-03 02:00:02,665] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt +32: [2022-12-03 02:00:02,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 0: [2022-12-03 02:00:02,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. + 0: [2022-12-03 02:00:02,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-12-03 02:00:02,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-12-03 02:00:02,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-12-03 02:00:02,671] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 0: [2022-12-03 02:00:02,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-12-03 02:00:02,671] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +32: [2022-12-03 02:00:02,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt. +32: [2022-12-03 02:00:02,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt. +32: [2022-12-03 02:00:02,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt +32: [2022-12-03 02:00:02,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt +32: [2022-12-03 02:00:02,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +32: [2022-12-03 02:00:02,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +32: [2022-12-03 02:00:02,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt. +32: [2022-12-03 02:00:02,675] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt +32: [2022-12-03 02:00:02,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +32: [2022-12-03 02:00:02,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt. +32: [2022-12-03 02:00:02,675] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt +32: [2022-12-03 02:00:02,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 0: [2022-12-03 02:00:02,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-12-03 02:00:02,677] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-12-03 02:00:02,677] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +32: [2022-12-03 02:00:02,679] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt. +32: [2022-12-03 02:00:02,679] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt. +32: [2022-12-03 02:00:02,679] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt. +32: [2022-12-03 02:00:02,679] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt +32: [2022-12-03 02:00:02,679] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt +32: [2022-12-03 02:00:02,679] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt +32: [2022-12-03 02:00:02,679] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +32: [2022-12-03 02:00:02,679] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +32: [2022-12-03 02:00:02,679] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 0: [2022-12-03 02:00:02,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-12-03 02:00:02,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-12-03 02:00:02,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 0: [2022-12-03 02:00:02,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-12-03 02:00:02,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-12-03 02:00:02,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 0: [2022-12-03 02:00:02,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-12-03 02:00:02,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-12-03 02:00:02,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 0: [2022-12-03 02:00:02,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-12-03 02:00:02,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-12-03 02:00:02,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +33: [2022-12-03 02:00:02,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt. +33: [2022-12-03 02:00:02,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt. +33: [2022-12-03 02:00:02,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt +33: [2022-12-03 02:00:02,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt +33: [2022-12-03 02:00:02,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +33: [2022-12-03 02:00:02,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +22: [2022-12-03 02:00:02,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-12-03 02:00:02,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-12-03 02:00:02,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +33: [2022-12-03 02:00:02,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt. +33: [2022-12-03 02:00:02,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt. +33: [2022-12-03 02:00:02,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt +33: [2022-12-03 02:00:02,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt +33: [2022-12-03 02:00:02,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +33: [2022-12-03 02:00:02,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +30: [2022-12-03 02:00:02,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-12-03 02:00:02,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-12-03 02:00:02,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +33: [2022-12-03 02:00:02,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt. +33: [2022-12-03 02:00:02,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt +33: [2022-12-03 02:00:02,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +36: [2022-12-03 02:00:02,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt. +36: [2022-12-03 02:00:02,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt +36: [2022-12-03 02:00:02,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +36: [2022-12-03 02:00:02,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt. +36: [2022-12-03 02:00:02,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt. +36: [2022-12-03 02:00:02,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt. +36: [2022-12-03 02:00:02,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt. +36: [2022-12-03 02:00:02,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt +36: [2022-12-03 02:00:02,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt +36: [2022-12-03 02:00:02,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt +36: [2022-12-03 02:00:02,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt +36: [2022-12-03 02:00:02,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +36: [2022-12-03 02:00:02,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +36: [2022-12-03 02:00:02,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +36: [2022-12-03 02:00:02,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +33: [2022-12-03 02:00:02,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt. +33: [2022-12-03 02:00:02,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt +33: [2022-12-03 02:00:02,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +19: [2022-12-03 02:00:02,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-12-03 02:00:02,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-12-03 02:00:02,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +36: [2022-12-03 02:00:02,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt. +36: [2022-12-03 02:00:02,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt +36: [2022-12-03 02:00:02,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +28: [2022-12-03 02:00:02,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-12-03 02:00:02,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-12-03 02:00:02,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-12-03 02:00:02,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-12-03 02:00:02,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +28: [2022-12-03 02:00:02,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +28: [2022-12-03 02:00:02,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-12-03 02:00:02,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-12-03 02:00:02,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +21: [2022-12-03 02:00:02,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-12-03 02:00:02,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-12-03 02:00:02,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-12-03 02:00:02,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-12-03 02:00:02,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +21: [2022-12-03 02:00:02,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +19: [2022-12-03 02:00:02,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-12-03 02:00:02,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-12-03 02:00:02,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +19: [2022-12-03 02:00:02,725] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-12-03 02:00:02,725] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-12-03 02:00:02,725] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +39: [2022-12-03 02:00:02,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt. +39: [2022-12-03 02:00:02,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt. +39: [2022-12-03 02:00:02,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt. +39: [2022-12-03 02:00:02,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt +39: [2022-12-03 02:00:02,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt +39: [2022-12-03 02:00:02,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +39: [2022-12-03 02:00:02,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt +39: [2022-12-03 02:00:02,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +39: [2022-12-03 02:00:02,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt. +39: [2022-12-03 02:00:02,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +39: [2022-12-03 02:00:02,727] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt +39: [2022-12-03 02:00:02,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +39: [2022-12-03 02:00:02,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt. +39: [2022-12-03 02:00:02,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt. +39: [2022-12-03 02:00:02,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt. +39: [2022-12-03 02:00:02,727] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt +39: [2022-12-03 02:00:02,727] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt +39: [2022-12-03 02:00:02,727] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt +39: [2022-12-03 02:00:02,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +39: [2022-12-03 02:00:02,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +39: [2022-12-03 02:00:02,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +21: [2022-12-03 02:00:02,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-12-03 02:00:02,728] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-12-03 02:00:02,728] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +36: [2022-12-03 02:00:02,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt. +36: [2022-12-03 02:00:02,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt +36: [2022-12-03 02:00:02,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +21: [2022-12-03 02:00:02,731] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +39: [2022-12-03 02:00:02,731] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt. +39: [2022-12-03 02:00:02,731] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt +39: [2022-12-03 02:00:02,731] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +21: [2022-12-03 02:00:02,731] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-12-03 02:00:02,731] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +36: [2022-12-03 02:00:02,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt. +36: [2022-12-03 02:00:02,733] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt +36: [2022-12-03 02:00:02,733] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +19: [2022-12-03 02:00:02,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-12-03 02:00:02,738] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-12-03 02:00:02,738] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +10: [2022-12-03 02:00:02,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-12-03 02:00:02,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-12-03 02:00:02,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-12-03 02:00:02,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-12-03 02:00:02,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +10: [2022-12-03 02:00:02,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +10: [2022-12-03 02:00:02,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-12-03 02:00:02,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-12-03 02:00:02,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +10: [2022-12-03 02:00:02,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-12-03 02:00:02,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-12-03 02:00:02,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 4: [2022-12-03 02:00:02,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-12-03 02:00:02,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-12-03 02:00:02,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-12-03 02:00:02,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-12-03 02:00:02,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-12-03 02:00:02,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-12-03 02:00:02,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-12-03 02:00:02,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-12-03 02:00:02,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 4: [2022-12-03 02:00:02,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 4: [2022-12-03 02:00:02,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 4: [2022-12-03 02:00:02,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +22: [2022-12-03 02:00:02,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-12-03 02:00:02,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-12-03 02:00:02,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +60: [2022-12-03 02:00:02,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt. +60: [2022-12-03 02:00:02,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt. +60: [2022-12-03 02:00:02,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt. +60: [2022-12-03 02:00:02,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt. +45: [2022-12-03 02:00:02,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt. +45: [2022-12-03 02:00:02,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt. +45: [2022-12-03 02:00:02,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt. +45: [2022-12-03 02:00:02,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt. +45: [2022-12-03 02:00:02,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt +45: [2022-12-03 02:00:02,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt +45: [2022-12-03 02:00:02,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +45: [2022-12-03 02:00:02,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +45: [2022-12-03 02:00:02,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt +45: [2022-12-03 02:00:02,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt +45: [2022-12-03 02:00:02,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +45: [2022-12-03 02:00:02,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +33: [2022-12-03 02:00:02,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt. +33: [2022-12-03 02:00:02,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt +33: [2022-12-03 02:00:02,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +60: [2022-12-03 02:00:02,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt +60: [2022-12-03 02:00:02,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt +60: [2022-12-03 02:00:02,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt +60: [2022-12-03 02:00:02,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt +60: [2022-12-03 02:00:02,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +60: [2022-12-03 02:00:02,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +60: [2022-12-03 02:00:02,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +60: [2022-12-03 02:00:02,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +35: [2022-12-03 02:00:02,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt. +35: [2022-12-03 02:00:02,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt. +35: [2022-12-03 02:00:02,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt. +35: [2022-12-03 02:00:02,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt. +35: [2022-12-03 02:00:02,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt +35: [2022-12-03 02:00:02,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt +35: [2022-12-03 02:00:02,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt +35: [2022-12-03 02:00:02,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt +35: [2022-12-03 02:00:02,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +35: [2022-12-03 02:00:02,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +35: [2022-12-03 02:00:02,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +35: [2022-12-03 02:00:02,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +46: [2022-12-03 02:00:02,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt. +46: [2022-12-03 02:00:02,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt. +46: [2022-12-03 02:00:02,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt. +46: [2022-12-03 02:00:02,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt +46: [2022-12-03 02:00:02,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt +46: [2022-12-03 02:00:02,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +46: [2022-12-03 02:00:02,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt +46: [2022-12-03 02:00:02,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +46: [2022-12-03 02:00:02,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +42: [2022-12-03 02:00:02,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt. +42: [2022-12-03 02:00:02,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt. +42: [2022-12-03 02:00:02,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt. +42: [2022-12-03 02:00:02,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt. +42: [2022-12-03 02:00:02,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt. +46: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt. +46: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt. +46: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt. +46: [2022-12-03 02:00:02,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt +46: [2022-12-03 02:00:02,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt +46: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt. +46: [2022-12-03 02:00:02,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt +46: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +46: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +46: [2022-12-03 02:00:02,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt +46: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +46: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 8: [2022-12-03 02:00:02,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-12-03 02:00:02,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-12-03 02:00:02,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 5: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +18: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +57: [2022-12-03 02:00:02,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt. +57: [2022-12-03 02:00:02,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt. +57: [2022-12-03 02:00:02,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt. + 5: [2022-12-03 02:00:02,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 5: [2022-12-03 02:00:02,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +18: [2022-12-03 02:00:02,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-12-03 02:00:02,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +30: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +42: [2022-12-03 02:00:02,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt +42: [2022-12-03 02:00:02,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt +18: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +18: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +42: [2022-12-03 02:00:02,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt +42: [2022-12-03 02:00:02,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt +18: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +42: [2022-12-03 02:00:02,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt +18: [2022-12-03 02:00:02,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +42: [2022-12-03 02:00:02,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +42: [2022-12-03 02:00:02,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +42: [2022-12-03 02:00:02,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +18: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +42: [2022-12-03 02:00:02,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +18: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +42: [2022-12-03 02:00:02,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +18: [2022-12-03 02:00:02,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +18: [2022-12-03 02:00:02,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-12-03 02:00:02,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 5: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +46: [2022-12-03 02:00:02,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt. +10: [2022-12-03 02:00:02,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. + 5: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-12-03 02:00:02,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 5: [2022-12-03 02:00:02,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +51: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt. +51: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt. + 8: [2022-12-03 02:00:02,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-12-03 02:00:02,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-12-03 02:00:02,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-12-03 02:00:02,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 8: [2022-12-03 02:00:02,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 8: [2022-12-03 02:00:02,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 5: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-12-03 02:00:02,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-12-03 02:00:02,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +57: [2022-12-03 02:00:02,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt. +57: [2022-12-03 02:00:02,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt. +57: [2022-12-03 02:00:02,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt +57: [2022-12-03 02:00:02,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt +57: [2022-12-03 02:00:02,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt +57: [2022-12-03 02:00:02,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt +57: [2022-12-03 02:00:02,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +57: [2022-12-03 02:00:02,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt +57: [2022-12-03 02:00:02,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +57: [2022-12-03 02:00:02,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +57: [2022-12-03 02:00:02,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +57: [2022-12-03 02:00:02,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +30: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-12-03 02:00:02,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-12-03 02:00:02,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +30: [2022-12-03 02:00:02,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +46: [2022-12-03 02:00:02,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt +46: [2022-12-03 02:00:02,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 8: [2022-12-03 02:00:02,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-12-03 02:00:02,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-12-03 02:00:02,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-12-03 02:00:02,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-12-03 02:00:02,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 8: [2022-12-03 02:00:02,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 8: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +19: [2022-12-03 02:00:02,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-12-03 02:00:02,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-12-03 02:00:02,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +51: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt. +51: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt. +51: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt. +51: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt. +51: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt. +51: [2022-12-03 02:00:02,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt +51: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt. +51: [2022-12-03 02:00:02,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt +51: [2022-12-03 02:00:02,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt + 2: [2022-12-03 02:00:02,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-12-03 02:00:02,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 2: [2022-12-03 02:00:02,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-12-03 02:00:02,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-12-03 02:00:02,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +51: [2022-12-03 02:00:02,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt +51: [2022-12-03 02:00:02,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt +51: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +51: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +51: [2022-12-03 02:00:02,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt +51: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +51: [2022-12-03 02:00:02,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt +51: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +51: [2022-12-03 02:00:02,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt +51: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +51: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +51: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +51: [2022-12-03 02:00:02,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 2: [2022-12-03 02:00:02,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-12-03 02:00:02,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-12-03 02:00:02,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 2: [2022-12-03 02:00:02,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-12-03 02:00:02,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-12-03 02:00:02,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 2: [2022-12-03 02:00:02,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 2: [2022-12-03 02:00:02,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 2: [2022-12-03 02:00:02,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 2: [2022-12-03 02:00:02,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +15: [2022-12-03 02:00:02,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-12-03 02:00:02,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-12-03 02:00:02,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-12-03 02:00:02,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-12-03 02:00:02,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-12-03 02:00:02,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-12-03 02:00:02,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +15: [2022-12-03 02:00:02,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +15: [2022-12-03 02:00:02,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +15: [2022-12-03 02:00:02,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-12-03 02:00:02,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-12-03 02:00:02,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-12-03 02:00:02,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-12-03 02:00:02,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +15: [2022-12-03 02:00:02,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +15: [2022-12-03 02:00:02,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-12-03 02:00:02,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 5: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +15: [2022-12-03 02:00:02,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +44: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt. +44: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt. +44: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt. +44: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt. +15: [2022-12-03 02:00:02,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +44: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt. +44: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt. +44: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt. +44: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt. +44: [2022-12-03 02:00:02,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt +44: [2022-12-03 02:00:02,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt +44: [2022-12-03 02:00:02,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt +44: [2022-12-03 02:00:02,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt +44: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +44: [2022-12-03 02:00:02,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt +44: [2022-12-03 02:00:02,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt +44: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +44: [2022-12-03 02:00:02,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt +44: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +44: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +44: [2022-12-03 02:00:02,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt +44: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +44: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +44: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +44: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 5: [2022-12-03 02:00:02,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +61: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt. +61: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt. +61: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt. +61: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt. +10: [2022-12-03 02:00:02,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-12-03 02:00:02,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +10: [2022-12-03 02:00:02,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-12-03 02:00:02,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-12-03 02:00:02,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +20: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +59: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt. +59: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt. +59: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt. +59: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt. +59: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt. +20: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-12-03 02:00:02,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-12-03 02:00:02,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-12-03 02:00:02,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-12-03 02:00:02,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +37: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt. +37: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt. +37: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt. +20: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +20: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +20: [2022-12-03 02:00:02,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +20: [2022-12-03 02:00:02,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +20: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +37: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt. +37: [2022-12-03 02:00:02,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt +37: [2022-12-03 02:00:02,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt +37: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt. +37: [2022-12-03 02:00:02,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt +37: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +37: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +37: [2022-12-03 02:00:02,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt +37: [2022-12-03 02:00:02,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt +37: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +37: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +37: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +31: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +61: [2022-12-03 02:00:02,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt +61: [2022-12-03 02:00:02,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt +61: [2022-12-03 02:00:02,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt +61: [2022-12-03 02:00:02,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt +61: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +61: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +61: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +61: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +61: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt. +61: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt. +61: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt. +61: [2022-12-03 02:00:02,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt +61: [2022-12-03 02:00:02,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt +61: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +61: [2022-12-03 02:00:02,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt +61: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +61: [2022-12-03 02:00:02,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +61: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt. +61: [2022-12-03 02:00:02,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt +61: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +26: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +37: [2022-12-03 02:00:02,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt. +31: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-12-03 02:00:02,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-12-03 02:00:02,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-12-03 02:00:02,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +31: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +31: [2022-12-03 02:00:02,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-12-03 02:00:02,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-12-03 02:00:02,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-12-03 02:00:02,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +31: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +31: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +31: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +31: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +37: [2022-12-03 02:00:02,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt +37: [2022-12-03 02:00:02,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +37: [2022-12-03 02:00:02,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt. +37: [2022-12-03 02:00:02,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt. +37: [2022-12-03 02:00:02,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt +37: [2022-12-03 02:00:02,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt +37: [2022-12-03 02:00:02,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +37: [2022-12-03 02:00:02,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +18: [2022-12-03 02:00:02,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-12-03 02:00:02,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-12-03 02:00:02,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 1: [2022-12-03 02:00:02,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-12-03 02:00:02,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-12-03 02:00:02,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +26: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-12-03 02:00:02,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-12-03 02:00:02,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-12-03 02:00:02,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-12-03 02:00:02,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-12-03 02:00:02,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +26: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +26: [2022-12-03 02:00:02,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +26: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +26: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +26: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +26: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-12-03 02:00:02,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +26: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-12-03 02:00:02,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-12-03 02:00:02,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +13: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. + 6: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +48: [2022-12-03 02:00:02,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt. +13: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-12-03 02:00:02,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-12-03 02:00:02,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-12-03 02:00:02,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-12-03 02:00:02,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +13: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +13: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +13: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +47: [2022-12-03 02:00:02,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt. +47: [2022-12-03 02:00:02,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt. +47: [2022-12-03 02:00:02,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt. +47: [2022-12-03 02:00:02,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt. +13: [2022-12-03 02:00:02,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 6: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-12-03 02:00:02,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-12-03 02:00:02,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-12-03 02:00:02,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-12-03 02:00:02,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-12-03 02:00:02,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-12-03 02:00:02,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 6: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 6: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 6: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 6: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 6: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +47: [2022-12-03 02:00:02,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt +47: [2022-12-03 02:00:02,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt +47: [2022-12-03 02:00:02,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt +47: [2022-12-03 02:00:02,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt +47: [2022-12-03 02:00:02,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +47: [2022-12-03 02:00:02,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +47: [2022-12-03 02:00:02,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +47: [2022-12-03 02:00:02,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 1: [2022-12-03 02:00:02,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-12-03 02:00:02,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-12-03 02:00:02,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-12-03 02:00:02,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-12-03 02:00:02,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-12-03 02:00:02,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 1: [2022-12-03 02:00:02,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 1: [2022-12-03 02:00:02,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 1: [2022-12-03 02:00:02,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-12-03 02:00:02,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +48: [2022-12-03 02:00:02,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt. +48: [2022-12-03 02:00:02,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt. +48: [2022-12-03 02:00:02,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt + 1: [2022-12-03 02:00:02,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 1: [2022-12-03 02:00:02,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +48: [2022-12-03 02:00:02,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt. +48: [2022-12-03 02:00:02,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt. +48: [2022-12-03 02:00:02,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt. +48: [2022-12-03 02:00:02,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +48: [2022-12-03 02:00:02,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt +48: [2022-12-03 02:00:02,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt +48: [2022-12-03 02:00:02,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt +48: [2022-12-03 02:00:02,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt +48: [2022-12-03 02:00:02,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt +48: [2022-12-03 02:00:02,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +59: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt. +59: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt. +48: [2022-12-03 02:00:02,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +48: [2022-12-03 02:00:02,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +48: [2022-12-03 02:00:02,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +59: [2022-12-03 02:00:02,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt +59: [2022-12-03 02:00:02,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt +59: [2022-12-03 02:00:02,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt +48: [2022-12-03 02:00:02,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +59: [2022-12-03 02:00:02,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt +59: [2022-12-03 02:00:02,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt +59: [2022-12-03 02:00:02,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt +59: [2022-12-03 02:00:02,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt +48: [2022-12-03 02:00:02,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt. +59: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +48: [2022-12-03 02:00:02,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt +47: [2022-12-03 02:00:02,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt. +47: [2022-12-03 02:00:02,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt. +47: [2022-12-03 02:00:02,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt. +59: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +59: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +48: [2022-12-03 02:00:02,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +59: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +48: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt. +59: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +59: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +48: [2022-12-03 02:00:02,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt +59: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +48: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +59: [2022-12-03 02:00:02,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt. +59: [2022-12-03 02:00:02,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt +59: [2022-12-03 02:00:02,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +63: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt. +63: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt. +63: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt. +63: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt. +63: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt. +47: [2022-12-03 02:00:02,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt +47: [2022-12-03 02:00:02,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt +47: [2022-12-03 02:00:02,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt +47: [2022-12-03 02:00:02,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +47: [2022-12-03 02:00:02,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +47: [2022-12-03 02:00:02,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +47: [2022-12-03 02:00:02,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt. +47: [2022-12-03 02:00:02,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt +47: [2022-12-03 02:00:02,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +14: [2022-12-03 02:00:02,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-12-03 02:00:02,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-12-03 02:00:02,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-12-03 02:00:02,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-12-03 02:00:02,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +63: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt. +63: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt. +63: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt. +63: [2022-12-03 02:00:02,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt +63: [2022-12-03 02:00:02,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt +63: [2022-12-03 02:00:02,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt +63: [2022-12-03 02:00:02,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt +63: [2022-12-03 02:00:02,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt +63: [2022-12-03 02:00:02,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt +63: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +63: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +63: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +63: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +63: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +63: [2022-12-03 02:00:02,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt +63: [2022-12-03 02:00:02,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt +63: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +63: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +63: [2022-12-03 02:00:02,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +14: [2022-12-03 02:00:02,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-12-03 02:00:02,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-12-03 02:00:02,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-12-03 02:00:02,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-12-03 02:00:02,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-12-03 02:00:02,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-12-03 02:00:02,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-12-03 02:00:02,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-12-03 02:00:02,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-12-03 02:00:02,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt + 3: [2022-12-03 02:00:02,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-12-03 02:00:02,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-12-03 02:00:02,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-12-03 02:00:02,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-12-03 02:00:02,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +14: [2022-12-03 02:00:02,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt + 3: [2022-12-03 02:00:02,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +14: [2022-12-03 02:00:02,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +14: [2022-12-03 02:00:02,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 3: [2022-12-03 02:00:02,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-12-03 02:00:02,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-12-03 02:00:02,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +14: [2022-12-03 02:00:02,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +14: [2022-12-03 02:00:02,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 3: [2022-12-03 02:00:02,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +14: [2022-12-03 02:00:02,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 3: [2022-12-03 02:00:02,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +14: [2022-12-03 02:00:02,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +14: [2022-12-03 02:00:02,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +14: [2022-12-03 02:00:02,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 3: [2022-12-03 02:00:02,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 3: [2022-12-03 02:00:02,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-12-03 02:00:02,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-12-03 02:00:02,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 3: [2022-12-03 02:00:02,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-12-03 02:00:02,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 3: [2022-12-03 02:00:02,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 3: [2022-12-03 02:00:02,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 3: [2022-12-03 02:00:02,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 3: [2022-12-03 02:00:02,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +53: [2022-12-03 02:00:02,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt. +53: [2022-12-03 02:00:02,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt. +53: [2022-12-03 02:00:02,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt. +53: [2022-12-03 02:00:02,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt. +53: [2022-12-03 02:00:02,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt. +53: [2022-12-03 02:00:02,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt +53: [2022-12-03 02:00:02,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt +53: [2022-12-03 02:00:02,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt +53: [2022-12-03 02:00:02,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt +53: [2022-12-03 02:00:02,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt +53: [2022-12-03 02:00:02,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +53: [2022-12-03 02:00:02,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +53: [2022-12-03 02:00:02,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +53: [2022-12-03 02:00:02,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +53: [2022-12-03 02:00:02,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +25: [2022-12-03 02:00:02,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-12-03 02:00:02,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-12-03 02:00:02,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-12-03 02:00:02,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-12-03 02:00:02,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-12-03 02:00:02,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-12-03 02:00:02,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-12-03 02:00:02,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-12-03 02:00:02,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-12-03 02:00:02,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +25: [2022-12-03 02:00:02,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +25: [2022-12-03 02:00:02,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +25: [2022-12-03 02:00:02,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-12-03 02:00:02,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +25: [2022-12-03 02:00:02,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +25: [2022-12-03 02:00:02,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-12-03 02:00:02,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-12-03 02:00:02,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +11: [2022-12-03 02:00:02,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-12-03 02:00:02,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-12-03 02:00:02,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-12-03 02:00:02,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-12-03 02:00:02,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-12-03 02:00:02,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-12-03 02:00:02,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-12-03 02:00:02,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-12-03 02:00:02,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-12-03 02:00:02,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-12-03 02:00:02,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-12-03 02:00:02,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-12-03 02:00:02,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-12-03 02:00:02,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +11: [2022-12-03 02:00:02,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-12-03 02:00:02,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +11: [2022-12-03 02:00:02,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +11: [2022-12-03 02:00:02,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +11: [2022-12-03 02:00:02,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +11: [2022-12-03 02:00:02,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +11: [2022-12-03 02:00:02,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +23: [2022-12-03 02:00:02,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-12-03 02:00:02,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-12-03 02:00:02,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-12-03 02:00:02,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-12-03 02:00:02,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +23: [2022-12-03 02:00:02,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +30: [2022-12-03 02:00:02,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +50: [2022-12-03 02:00:02,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt. +50: [2022-12-03 02:00:02,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt. +50: [2022-12-03 02:00:02,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt. +50: [2022-12-03 02:00:02,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt. +50: [2022-12-03 02:00:02,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt. +24: [2022-12-03 02:00:02,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +41: [2022-12-03 02:00:02,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt. +41: [2022-12-03 02:00:02,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt. +41: [2022-12-03 02:00:02,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt. +41: [2022-12-03 02:00:02,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt. +41: [2022-12-03 02:00:02,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt +41: [2022-12-03 02:00:02,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt +41: [2022-12-03 02:00:02,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt +41: [2022-12-03 02:00:02,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt +41: [2022-12-03 02:00:02,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +41: [2022-12-03 02:00:02,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +41: [2022-12-03 02:00:02,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +41: [2022-12-03 02:00:02,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +41: [2022-12-03 02:00:02,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt. +24: [2022-12-03 02:00:02,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-12-03 02:00:02,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-12-03 02:00:02,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-12-03 02:00:02,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +41: [2022-12-03 02:00:02,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt. +41: [2022-12-03 02:00:02,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt. +24: [2022-12-03 02:00:02,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +41: [2022-12-03 02:00:02,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt +41: [2022-12-03 02:00:02,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt +41: [2022-12-03 02:00:02,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt +24: [2022-12-03 02:00:02,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-12-03 02:00:02,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +24: [2022-12-03 02:00:02,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-12-03 02:00:02,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +41: [2022-12-03 02:00:02,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +41: [2022-12-03 02:00:02,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +41: [2022-12-03 02:00:02,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +24: [2022-12-03 02:00:02,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-12-03 02:00:02,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +50: [2022-12-03 02:00:02,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt. +24: [2022-12-03 02:00:02,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +24: [2022-12-03 02:00:02,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +50: [2022-12-03 02:00:02,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt. +24: [2022-12-03 02:00:02,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +50: [2022-12-03 02:00:02,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt +50: [2022-12-03 02:00:02,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt +50: [2022-12-03 02:00:02,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt +50: [2022-12-03 02:00:02,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt +50: [2022-12-03 02:00:02,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt +50: [2022-12-03 02:00:02,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt +50: [2022-12-03 02:00:02,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +50: [2022-12-03 02:00:02,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt +50: [2022-12-03 02:00:02,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +50: [2022-12-03 02:00:02,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +50: [2022-12-03 02:00:02,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +50: [2022-12-03 02:00:02,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +50: [2022-12-03 02:00:02,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +50: [2022-12-03 02:00:02,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +50: [2022-12-03 02:00:02,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt. +50: [2022-12-03 02:00:02,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt +50: [2022-12-03 02:00:02,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +30: [2022-12-03 02:00:02,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-12-03 02:00:02,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +41: [2022-12-03 02:00:02,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt. + 9: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-12-03 02:00:02,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-12-03 02:00:02,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-12-03 02:00:02,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-12-03 02:00:02,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-12-03 02:00:02,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 9: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 9: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 9: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 9: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +41: [2022-12-03 02:00:02,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt +41: [2022-12-03 02:00:02,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +40: [2022-12-03 02:00:02,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt. +40: [2022-12-03 02:00:02,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt. +40: [2022-12-03 02:00:02,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt. +40: [2022-12-03 02:00:02,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt. +40: [2022-12-03 02:00:02,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt. +40: [2022-12-03 02:00:02,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt. +40: [2022-12-03 02:00:02,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt. +40: [2022-12-03 02:00:02,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt. +40: [2022-12-03 02:00:02,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt +40: [2022-12-03 02:00:02,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt +40: [2022-12-03 02:00:02,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt +40: [2022-12-03 02:00:02,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt +40: [2022-12-03 02:00:02,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt +40: [2022-12-03 02:00:02,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt +40: [2022-12-03 02:00:02,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt +40: [2022-12-03 02:00:02,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt +40: [2022-12-03 02:00:02,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +40: [2022-12-03 02:00:02,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +40: [2022-12-03 02:00:02,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +40: [2022-12-03 02:00:02,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +40: [2022-12-03 02:00:02,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +40: [2022-12-03 02:00:02,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +40: [2022-12-03 02:00:02,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +40: [2022-12-03 02:00:02,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +58: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt. +58: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt. +58: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt. +58: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt. +58: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt. + 1: [2022-12-03 02:00:02,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-12-03 02:00:02,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-12-03 02:00:02,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +12: [2022-12-03 02:00:02,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +12: [2022-12-03 02:00:02,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-12-03 02:00:02,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-12-03 02:00:02,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-12-03 02:00:02,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-12-03 02:00:02,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-12-03 02:00:02,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-12-03 02:00:02,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-12-03 02:00:02,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-12-03 02:00:02,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-12-03 02:00:02,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-12-03 02:00:02,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-12-03 02:00:02,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-12-03 02:00:02,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-12-03 02:00:02,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +12: [2022-12-03 02:00:02,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +12: [2022-12-03 02:00:02,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +12: [2022-12-03 02:00:02,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +12: [2022-12-03 02:00:02,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +12: [2022-12-03 02:00:02,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +12: [2022-12-03 02:00:02,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +30: [2022-12-03 02:00:02,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. + 7: [2022-12-03 02:00:02,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-12-03 02:00:02,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-12-03 02:00:02,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-12-03 02:00:02,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-12-03 02:00:02,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-12-03 02:00:02,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-12-03 02:00:02,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-12-03 02:00:02,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-12-03 02:00:02,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-12-03 02:00:02,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-12-03 02:00:02,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-12-03 02:00:02,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-12-03 02:00:02,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 7: [2022-12-03 02:00:02,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 7: [2022-12-03 02:00:02,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 7: [2022-12-03 02:00:02,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 7: [2022-12-03 02:00:02,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 7: [2022-12-03 02:00:02,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +55: [2022-12-03 02:00:02,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt. +55: [2022-12-03 02:00:02,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt. +55: [2022-12-03 02:00:02,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt. +55: [2022-12-03 02:00:02,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt. +55: [2022-12-03 02:00:02,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt. +30: [2022-12-03 02:00:02,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-12-03 02:00:02,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +58: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt. +58: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt. +58: [2022-12-03 02:00:02,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt +58: [2022-12-03 02:00:02,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt +58: [2022-12-03 02:00:02,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt +58: [2022-12-03 02:00:02,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt +58: [2022-12-03 02:00:02,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt +58: [2022-12-03 02:00:02,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt +58: [2022-12-03 02:00:02,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt +58: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +58: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +58: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +58: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +58: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +58: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +58: [2022-12-03 02:00:02,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +58: [2022-12-03 02:00:02,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt. +58: [2022-12-03 02:00:02,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt +58: [2022-12-03 02:00:02,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +11: [2022-12-03 02:00:02,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-12-03 02:00:02,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-12-03 02:00:02,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +23: [2022-12-03 02:00:02,805] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +55: [2022-12-03 02:00:02,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt. +55: [2022-12-03 02:00:02,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt. +55: [2022-12-03 02:00:02,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt. +55: [2022-12-03 02:00:02,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt +55: [2022-12-03 02:00:02,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt +55: [2022-12-03 02:00:02,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt +55: [2022-12-03 02:00:02,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt +55: [2022-12-03 02:00:02,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt +55: [2022-12-03 02:00:02,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt +55: [2022-12-03 02:00:02,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt +55: [2022-12-03 02:00:02,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt +55: [2022-12-03 02:00:02,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +55: [2022-12-03 02:00:02,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +55: [2022-12-03 02:00:02,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +55: [2022-12-03 02:00:02,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +55: [2022-12-03 02:00:02,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +55: [2022-12-03 02:00:02,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +55: [2022-12-03 02:00:02,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +55: [2022-12-03 02:00:02,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +56: [2022-12-03 02:00:02,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt. +56: [2022-12-03 02:00:02,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt. +56: [2022-12-03 02:00:02,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt. +56: [2022-12-03 02:00:02,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt. +56: [2022-12-03 02:00:02,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt. +23: [2022-12-03 02:00:02,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-12-03 02:00:02,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +54: [2022-12-03 02:00:02,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt. +54: [2022-12-03 02:00:02,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt. +54: [2022-12-03 02:00:02,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt. +54: [2022-12-03 02:00:02,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt. +54: [2022-12-03 02:00:02,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt. +56: [2022-12-03 02:00:02,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt. +56: [2022-12-03 02:00:02,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt. +56: [2022-12-03 02:00:02,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt. +56: [2022-12-03 02:00:02,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt +56: [2022-12-03 02:00:02,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt +56: [2022-12-03 02:00:02,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt +56: [2022-12-03 02:00:02,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt +56: [2022-12-03 02:00:02,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt +56: [2022-12-03 02:00:02,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt +56: [2022-12-03 02:00:02,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt +56: [2022-12-03 02:00:02,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +56: [2022-12-03 02:00:02,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +56: [2022-12-03 02:00:02,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +56: [2022-12-03 02:00:02,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +56: [2022-12-03 02:00:02,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +56: [2022-12-03 02:00:02,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +56: [2022-12-03 02:00:02,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +56: [2022-12-03 02:00:02,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt +56: [2022-12-03 02:00:02,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +10: [2022-12-03 02:00:02,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +23: [2022-12-03 02:00:02,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-12-03 02:00:02,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +54: [2022-12-03 02:00:02,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt. +54: [2022-12-03 02:00:02,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt. +54: [2022-12-03 02:00:02,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt +54: [2022-12-03 02:00:02,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt +54: [2022-12-03 02:00:02,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt +54: [2022-12-03 02:00:02,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt +54: [2022-12-03 02:00:02,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt +54: [2022-12-03 02:00:02,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt +10: [2022-12-03 02:00:02,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +54: [2022-12-03 02:00:02,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +54: [2022-12-03 02:00:02,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt +54: [2022-12-03 02:00:02,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +54: [2022-12-03 02:00:02,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +54: [2022-12-03 02:00:02,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +54: [2022-12-03 02:00:02,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +54: [2022-12-03 02:00:02,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +10: [2022-12-03 02:00:02,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +54: [2022-12-03 02:00:02,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +23: [2022-12-03 02:00:02,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +54: [2022-12-03 02:00:02,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt. +54: [2022-12-03 02:00:02,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt +54: [2022-12-03 02:00:02,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +24: [2022-12-03 02:00:02,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-12-03 02:00:02,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-12-03 02:00:02,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +62: [2022-12-03 02:00:02,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt. +62: [2022-12-03 02:00:02,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt. +62: [2022-12-03 02:00:02,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt. +62: [2022-12-03 02:00:02,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt. +62: [2022-12-03 02:00:02,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt. +62: [2022-12-03 02:00:02,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt. +62: [2022-12-03 02:00:02,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt. +62: [2022-12-03 02:00:02,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt +62: [2022-12-03 02:00:02,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt. +62: [2022-12-03 02:00:02,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt +62: [2022-12-03 02:00:02,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt +62: [2022-12-03 02:00:02,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt +62: [2022-12-03 02:00:02,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt +62: [2022-12-03 02:00:02,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt +62: [2022-12-03 02:00:02,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt +62: [2022-12-03 02:00:02,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +62: [2022-12-03 02:00:02,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt +62: [2022-12-03 02:00:02,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +62: [2022-12-03 02:00:02,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +62: [2022-12-03 02:00:02,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +62: [2022-12-03 02:00:02,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +62: [2022-12-03 02:00:02,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +62: [2022-12-03 02:00:02,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +62: [2022-12-03 02:00:02,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +30: [2022-12-03 02:00:02,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-12-03 02:00:02,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-12-03 02:00:02,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +17: [2022-12-03 02:00:02,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-12-03 02:00:02,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-12-03 02:00:02,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-12-03 02:00:02,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-12-03 02:00:02,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-12-03 02:00:02,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-12-03 02:00:02,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-12-03 02:00:02,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-12-03 02:00:02,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-12-03 02:00:02,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-12-03 02:00:02,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-12-03 02:00:02,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-12-03 02:00:02,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-12-03 02:00:02,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-12-03 02:00:02,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +17: [2022-12-03 02:00:02,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +17: [2022-12-03 02:00:02,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +17: [2022-12-03 02:00:02,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +17: [2022-12-03 02:00:02,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +17: [2022-12-03 02:00:02,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +17: [2022-12-03 02:00:02,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +34: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt. +34: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt. +34: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt. +34: [2022-12-03 02:00:02,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt +34: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt. +34: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt. +34: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt. +34: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +34: [2022-12-03 02:00:02,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt +43: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt. +43: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt. +43: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt. +43: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt. +34: [2022-12-03 02:00:02,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt +34: [2022-12-03 02:00:02,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt +34: [2022-12-03 02:00:02,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt +34: [2022-12-03 02:00:02,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt +34: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +34: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +34: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +34: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +34: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +34: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt. +34: [2022-12-03 02:00:02,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt +34: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +34: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt. +34: [2022-12-03 02:00:02,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt +34: [2022-12-03 02:00:02,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +16: [2022-12-03 02:00:02,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-12-03 02:00:02,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-12-03 02:00:02,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-12-03 02:00:02,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-12-03 02:00:02,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-12-03 02:00:02,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-12-03 02:00:02,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-12-03 02:00:02,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-12-03 02:00:02,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-12-03 02:00:02,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-12-03 02:00:02,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-12-03 02:00:02,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-12-03 02:00:02,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +16: [2022-12-03 02:00:02,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +16: [2022-12-03 02:00:02,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +16: [2022-12-03 02:00:02,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +16: [2022-12-03 02:00:02,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-12-03 02:00:02,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-12-03 02:00:02,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +16: [2022-12-03 02:00:02,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +16: [2022-12-03 02:00:02,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +43: [2022-12-03 02:00:02,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt +43: [2022-12-03 02:00:02,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt +43: [2022-12-03 02:00:02,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt +43: [2022-12-03 02:00:02,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt +43: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt. +43: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +43: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +43: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +43: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +43: [2022-12-03 02:00:02,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt +43: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt. +43: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +43: [2022-12-03 02:00:02,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt +43: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +43: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt. +43: [2022-12-03 02:00:02,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt. +43: [2022-12-03 02:00:02,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt +43: [2022-12-03 02:00:02,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt +43: [2022-12-03 02:00:02,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +43: [2022-12-03 02:00:02,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 2: [2022-12-03 02:00:02,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-12-03 02:00:02,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-12-03 02:00:02,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +23: [2022-12-03 02:00:02,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-12-03 02:00:02,832] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-12-03 02:00:02,832] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +23: [2022-12-03 02:00:02,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-12-03 02:00:02,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-12-03 02:00:02,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +35: [2022-12-03 02:00:02,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt. +35: [2022-12-03 02:00:02,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt +35: [2022-12-03 02:00:02,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 0: [2022-12-03 02:00:02,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-12-03 02:00:02,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +38: [2022-12-03 02:00:02,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt. +38: [2022-12-03 02:00:02,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt. +38: [2022-12-03 02:00:02,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt. +38: [2022-12-03 02:00:02,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt. +38: [2022-12-03 02:00:02,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt. +38: [2022-12-03 02:00:02,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt. +38: [2022-12-03 02:00:02,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt. +38: [2022-12-03 02:00:02,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt. +38: [2022-12-03 02:00:02,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt +38: [2022-12-03 02:00:02,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt +38: [2022-12-03 02:00:02,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt +38: [2022-12-03 02:00:02,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt +38: [2022-12-03 02:00:02,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt +38: [2022-12-03 02:00:02,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt +38: [2022-12-03 02:00:02,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt +38: [2022-12-03 02:00:02,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +38: [2022-12-03 02:00:02,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +38: [2022-12-03 02:00:02,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt +38: [2022-12-03 02:00:02,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +38: [2022-12-03 02:00:02,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +38: [2022-12-03 02:00:02,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +38: [2022-12-03 02:00:02,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +38: [2022-12-03 02:00:02,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +38: [2022-12-03 02:00:02,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +27: [2022-12-03 02:00:02,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-12-03 02:00:02,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-12-03 02:00:02,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-12-03 02:00:02,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-12-03 02:00:02,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-12-03 02:00:02,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-12-03 02:00:02,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-12-03 02:00:02,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-12-03 02:00:02,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-12-03 02:00:02,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-12-03 02:00:02,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-12-03 02:00:02,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-12-03 02:00:02,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-12-03 02:00:02,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-12-03 02:00:02,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +27: [2022-12-03 02:00:02,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +27: [2022-12-03 02:00:02,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +27: [2022-12-03 02:00:02,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +27: [2022-12-03 02:00:02,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +27: [2022-12-03 02:00:02,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +27: [2022-12-03 02:00:02,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +27: [2022-12-03 02:00:02,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-12-03 02:00:02,844] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-12-03 02:00:02,844] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +28: [2022-12-03 02:00:02,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-12-03 02:00:02,851] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-12-03 02:00:02,851] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +22: [2022-12-03 02:00:02,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-12-03 02:00:02,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-12-03 02:00:02,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +49: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt. +49: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt. +49: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt. +49: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt. +49: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt. +49: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt. +49: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt. +49: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt. +52: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt. +52: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt. +52: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt. +52: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt. +52: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt. +49: [2022-12-03 02:00:02,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt +52: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt. +49: [2022-12-03 02:00:02,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt +52: [2022-12-03 02:00:02,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt +52: [2022-12-03 02:00:02,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt +52: [2022-12-03 02:00:02,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt +49: [2022-12-03 02:00:02,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt +49: [2022-12-03 02:00:02,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt +49: [2022-12-03 02:00:02,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt +52: [2022-12-03 02:00:02,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt +52: [2022-12-03 02:00:02,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt +49: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +52: [2022-12-03 02:00:02,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt +49: [2022-12-03 02:00:02,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt +49: [2022-12-03 02:00:02,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt +52: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +52: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +49: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +52: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +49: [2022-12-03 02:00:02,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt +52: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +52: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +49: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +49: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +49: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +52: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +49: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +49: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +49: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +52: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt. +52: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt. +52: [2022-12-03 02:00:02,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt +52: [2022-12-03 02:00:02,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt +52: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +52: [2022-12-03 02:00:02,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 6: [2022-12-03 02:00:02,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-12-03 02:00:02,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-12-03 02:00:02,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +17: [2022-12-03 02:00:02,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-12-03 02:00:02,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-12-03 02:00:02,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +25: [2022-12-03 02:00:02,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-12-03 02:00:02,864] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-12-03 02:00:02,864] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +16: [2022-12-03 02:00:02,869] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-12-03 02:00:02,869] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-12-03 02:00:02,869] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +29: [2022-12-03 02:00:02,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-12-03 02:00:02,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +60: [2022-12-03 02:00:02,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt. +29: [2022-12-03 02:00:02,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-12-03 02:00:02,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-12-03 02:00:02,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-12-03 02:00:02,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-12-03 02:00:02,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-12-03 02:00:02,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-12-03 02:00:02,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-12-03 02:00:02,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +60: [2022-12-03 02:00:02,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt +29: [2022-12-03 02:00:02,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-12-03 02:00:02,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-12-03 02:00:02,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +42: [2022-12-03 02:00:02,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt. +60: [2022-12-03 02:00:02,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +29: [2022-12-03 02:00:02,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +29: [2022-12-03 02:00:02,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-12-03 02:00:02,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-12-03 02:00:02,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-12-03 02:00:02,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +42: [2022-12-03 02:00:02,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt +29: [2022-12-03 02:00:02,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +29: [2022-12-03 02:00:02,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +42: [2022-12-03 02:00:02,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +29: [2022-12-03 02:00:02,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +29: [2022-12-03 02:00:02,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +29: [2022-12-03 02:00:02,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +29: [2022-12-03 02:00:02,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 3: [2022-12-03 02:00:02,872] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-12-03 02:00:02,872] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-12-03 02:00:02,872] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +24: [2022-12-03 02:00:02,875] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-12-03 02:00:02,875] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-12-03 02:00:02,875] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 9: [2022-12-03 02:00:02,877] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-12-03 02:00:02,877] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-12-03 02:00:02,877] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +15: [2022-12-03 02:00:02,877] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-12-03 02:00:02,877] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-12-03 02:00:02,877] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +45: [2022-12-03 02:00:02,879] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt. +33: [2022-12-03 02:00:02,879] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt. +33: [2022-12-03 02:00:02,879] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt +33: [2022-12-03 02:00:02,879] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +19: [2022-12-03 02:00:02,880] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +21: [2022-12-03 02:00:02,881] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-12-03 02:00:02,881] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-12-03 02:00:02,881] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 9: [2022-12-03 02:00:02,881] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-12-03 02:00:02,881] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-12-03 02:00:02,881] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 5: [2022-12-03 02:00:02,881] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-12-03 02:00:02,882] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-12-03 02:00:02,882] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 7: [2022-12-03 02:00:02,882] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-12-03 02:00:02,882] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-12-03 02:00:02,883] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +24: [2022-12-03 02:00:02,883] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-12-03 02:00:02,883] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-12-03 02:00:02,883] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +19: [2022-12-03 02:00:02,880] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-12-03 02:00:02,880] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +53: [2022-12-03 02:00:02,885] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt. +53: [2022-12-03 02:00:02,885] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt +53: [2022-12-03 02:00:02,885] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +22: [2022-12-03 02:00:02,886] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-12-03 02:00:02,886] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-12-03 02:00:02,886] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +45: [2022-12-03 02:00:02,879] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt +45: [2022-12-03 02:00:02,879] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +31: [2022-12-03 02:00:02,887] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-12-03 02:00:02,887] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-12-03 02:00:02,887] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +57: [2022-12-03 02:00:02,887] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt. +57: [2022-12-03 02:00:02,887] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt +57: [2022-12-03 02:00:02,887] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +30: [2022-12-03 02:00:02,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-12-03 02:00:02,888] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-12-03 02:00:02,888] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +12: [2022-12-03 02:00:02,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-12-03 02:00:02,888] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-12-03 02:00:02,889] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +13: [2022-12-03 02:00:02,889] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-12-03 02:00:02,889] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-12-03 02:00:02,889] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 8: [2022-12-03 02:00:02,895] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 1: [2022-12-03 02:00:02,899] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-12-03 02:00:02,899] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-12-03 02:00:02,899] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +22: [2022-12-03 02:00:02,899] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-12-03 02:00:02,899] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-12-03 02:00:02,899] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 2: [2022-12-03 02:00:02,900] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-12-03 02:00:02,900] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-12-03 02:00:02,900] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 5: [2022-12-03 02:00:02,901] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-12-03 02:00:02,901] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-12-03 02:00:02,901] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +53: [2022-12-03 02:00:02,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt. +18: [2022-12-03 02:00:02,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +53: [2022-12-03 02:00:02,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt +53: [2022-12-03 02:00:02,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +18: [2022-12-03 02:00:02,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-12-03 02:00:02,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 8: [2022-12-03 02:00:02,895] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-12-03 02:00:02,896] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 8: [2022-12-03 02:00:02,900] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-12-03 02:00:02,900] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-12-03 02:00:02,900] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +25: [2022-12-03 02:00:02,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-12-03 02:00:02,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-12-03 02:00:02,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 6: [2022-12-03 02:00:02,905] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-12-03 02:00:02,905] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-12-03 02:00:02,905] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 9: [2022-12-03 02:00:02,906] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-12-03 02:00:02,906] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-12-03 02:00:02,906] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 7: [2022-12-03 02:00:02,906] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-12-03 02:00:02,906] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-12-03 02:00:02,906] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +30: [2022-12-03 02:00:02,906] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-12-03 02:00:02,906] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-12-03 02:00:02,906] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +19: [2022-12-03 02:00:02,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-12-03 02:00:02,907] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-12-03 02:00:02,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +35: [2022-12-03 02:00:02,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt. +45: [2022-12-03 02:00:02,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt. +35: [2022-12-03 02:00:02,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt +35: [2022-12-03 02:00:02,908] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +60: [2022-12-03 02:00:02,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt. +60: [2022-12-03 02:00:02,909] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt +60: [2022-12-03 02:00:02,909] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 4: [2022-12-03 02:00:02,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-12-03 02:00:02,909] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-12-03 02:00:02,910] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +53: [2022-12-03 02:00:02,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt. +42: [2022-12-03 02:00:02,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt. +53: [2022-12-03 02:00:02,911] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt +42: [2022-12-03 02:00:02,911] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt +53: [2022-12-03 02:00:02,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +42: [2022-12-03 02:00:02,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +60: [2022-12-03 02:00:02,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt. +60: [2022-12-03 02:00:02,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt +60: [2022-12-03 02:00:02,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +21: [2022-12-03 02:00:02,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-12-03 02:00:02,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-12-03 02:00:02,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 1: [2022-12-03 02:00:02,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-12-03 02:00:02,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-12-03 02:00:02,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +35: [2022-12-03 02:00:02,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt. +35: [2022-12-03 02:00:02,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt +35: [2022-12-03 02:00:02,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +57: [2022-12-03 02:00:02,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt. +57: [2022-12-03 02:00:02,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt +57: [2022-12-03 02:00:02,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 2: [2022-12-03 02:00:02,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-12-03 02:00:02,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-12-03 02:00:02,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +45: [2022-12-03 02:00:02,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt +45: [2022-12-03 02:00:02,908] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +45: [2022-12-03 02:00:02,914] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt. +57: [2022-12-03 02:00:02,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt. +57: [2022-12-03 02:00:02,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt +57: [2022-12-03 02:00:02,915] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +18: [2022-12-03 02:00:02,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-12-03 02:00:02,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-12-03 02:00:02,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +13: [2022-12-03 02:00:02,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-12-03 02:00:02,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-12-03 02:00:02,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +60: [2022-12-03 02:00:02,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt. +60: [2022-12-03 02:00:02,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt +60: [2022-12-03 02:00:02,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +23: [2022-12-03 02:00:02,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-12-03 02:00:02,919] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-12-03 02:00:02,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +42: [2022-12-03 02:00:02,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt. +42: [2022-12-03 02:00:02,920] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt +42: [2022-12-03 02:00:02,920] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +10: [2022-12-03 02:00:02,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-12-03 02:00:02,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-12-03 02:00:02,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +13: [2022-12-03 02:00:02,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-12-03 02:00:02,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-12-03 02:00:02,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +22: [2022-12-03 02:00:02,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +45: [2022-12-03 02:00:02,914] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt +22: [2022-12-03 02:00:02,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +45: [2022-12-03 02:00:02,914] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +22: [2022-12-03 02:00:02,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +45: [2022-12-03 02:00:02,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt. +45: [2022-12-03 02:00:02,919] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt +45: [2022-12-03 02:00:02,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +22: [2022-12-03 02:00:02,923] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-12-03 02:00:02,923] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-12-03 02:00:02,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +35: [2022-12-03 02:00:02,923] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt. +35: [2022-12-03 02:00:02,923] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt +35: [2022-12-03 02:00:02,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 4: [2022-12-03 02:00:02,923] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-12-03 02:00:02,924] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-12-03 02:00:02,924] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +21: [2022-12-03 02:00:02,925] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-12-03 02:00:02,925] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-12-03 02:00:02,925] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-12-03 02:00:02,925] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-12-03 02:00:02,925] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +21: [2022-12-03 02:00:02,925] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +28: [2022-12-03 02:00:02,926] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-12-03 02:00:02,926] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-12-03 02:00:02,926] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +28: [2022-12-03 02:00:02,927] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-12-03 02:00:02,927] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-12-03 02:00:02,927] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 4: [2022-12-03 02:00:02,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-12-03 02:00:02,929] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-12-03 02:00:02,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 4: [2022-12-03 02:00:02,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-12-03 02:00:02,929] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-12-03 02:00:02,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +22: [2022-12-03 02:00:02,932] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-12-03 02:00:02,932] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-12-03 02:00:02,932] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +28: [2022-12-03 02:00:02,949] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-12-03 02:00:02,949] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-12-03 02:00:02,949] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-12-03 02:00:02,949] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-12-03 02:00:02,949] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +28: [2022-12-03 02:00:02,949] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +19: [2022-12-03 02:00:02,982] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-12-03 02:00:02,982] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-12-03 02:00:02,982] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +20: [2022-12-03 02:00:02,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-12-03 02:00:02,990] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-12-03 02:00:02,990] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +23: [2022-12-03 02:00:03,015] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +23: [2022-12-03 02:00:03,016] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-12-03 02:00:03,016] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! +20: [2022-12-03 02:00:03,081] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-12-03 02:00:03,082] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step60000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-12-03 02:00:03,082] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step60000 is ready now! + 0: successfully saved checkpoint at iteration 60000 to checkpoints_3b977boscar +63: time (ms) | save-checkpoint: 5518.63 +63: iteration 60010/ 73814 | consumed samples: 30725120 | consumed tokens: 62925045760 | elapsed time per iteration (s): 2.83 | learning rate: 3.539E-05 | global batch size: 512 | lm loss: 1.906231E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 180.784 | TFLOPs: 18.61 | +63: iteration 60020/ 73814 | consumed samples: 30730240 | consumed tokens: 62935531520 | elapsed time per iteration (s): 2.30 | learning rate: 3.537E-05 | global batch size: 512 | lm loss: 1.908979E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.065 | TFLOPs: 22.96 | +63: iteration 60030/ 73814 | consumed samples: 30735360 | consumed tokens: 62946017280 | elapsed time per iteration (s): 2.27 | learning rate: 3.535E-05 | global batch size: 512 | lm loss: 1.908213E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.792 | TFLOPs: 23.24 | +63: iteration 60040/ 73814 | consumed samples: 30740480 | consumed tokens: 62956503040 | elapsed time per iteration (s): 2.36 | learning rate: 3.532E-05 | global batch size: 512 | lm loss: 1.908436E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.308 | TFLOPs: 22.37 | +63: iteration 60050/ 73814 | consumed samples: 30745600 | consumed tokens: 62966988800 | elapsed time per iteration (s): 2.23 | learning rate: 3.530E-05 | global batch size: 512 | lm loss: 1.893652E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.670 | TFLOPs: 23.64 | +63: iteration 60060/ 73814 | consumed samples: 30750720 | consumed tokens: 62977474560 | elapsed time per iteration (s): 2.23 | learning rate: 3.528E-05 | global batch size: 512 | lm loss: 1.901402E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.760 | TFLOPs: 23.65 | +63: iteration 60070/ 73814 | consumed samples: 30755840 | consumed tokens: 62987960320 | elapsed time per iteration (s): 2.23 | learning rate: 3.526E-05 | global batch size: 512 | lm loss: 1.885699E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.651 | TFLOPs: 23.64 | +63: iteration 60080/ 73814 | consumed samples: 30760960 | consumed tokens: 62998446080 | elapsed time per iteration (s): 2.24 | learning rate: 3.524E-05 | global batch size: 512 | lm loss: 1.913607E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.476 | TFLOPs: 23.52 | +63: iteration 60090/ 73814 | consumed samples: 30766080 | consumed tokens: 63008931840 | elapsed time per iteration (s): 2.25 | learning rate: 3.522E-05 | global batch size: 512 | lm loss: 1.914042E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.676 | TFLOPs: 23.44 | +63: iteration 60100/ 73814 | consumed samples: 30771200 | consumed tokens: 63019417600 | elapsed time per iteration (s): 2.23 | learning rate: 3.519E-05 | global batch size: 512 | lm loss: 1.893850E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.877 | TFLOPs: 23.66 | +63: iteration 60110/ 73814 | consumed samples: 30776320 | consumed tokens: 63029903360 | elapsed time per iteration (s): 2.24 | learning rate: 3.517E-05 | global batch size: 512 | lm loss: 1.917635E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.772 | TFLOPs: 23.55 | +63: iteration 60120/ 73814 | consumed samples: 30781440 | consumed tokens: 63040389120 | elapsed time per iteration (s): 2.43 | learning rate: 3.515E-05 | global batch size: 512 | lm loss: 1.909082E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.818 | TFLOPs: 21.70 | +63: iteration 60130/ 73814 | consumed samples: 30786560 | consumed tokens: 63050874880 | elapsed time per iteration (s): 2.23 | learning rate: 3.513E-05 | global batch size: 512 | lm loss: 1.926228E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.565 | TFLOPs: 23.63 | +63: iteration 60140/ 73814 | consumed samples: 30791680 | consumed tokens: 63061360640 | elapsed time per iteration (s): 2.37 | learning rate: 3.511E-05 | global batch size: 512 | lm loss: 1.913312E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.914 | TFLOPs: 22.23 | +63: iteration 60150/ 73814 | consumed samples: 30796800 | consumed tokens: 63071846400 | elapsed time per iteration (s): 2.24 | learning rate: 3.509E-05 | global batch size: 512 | lm loss: 1.925385E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.020 | TFLOPs: 23.58 | +63: iteration 60160/ 73814 | consumed samples: 30801920 | consumed tokens: 63082332160 | elapsed time per iteration (s): 2.22 | learning rate: 3.507E-05 | global batch size: 512 | lm loss: 1.902242E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.266 | TFLOPs: 23.70 | +63: iteration 60170/ 73814 | consumed samples: 30807040 | consumed tokens: 63092817920 | elapsed time per iteration (s): 2.24 | learning rate: 3.504E-05 | global batch size: 512 | lm loss: 1.888725E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.986 | TFLOPs: 23.57 | +63: iteration 60180/ 73814 | consumed samples: 30812160 | consumed tokens: 63103303680 | elapsed time per iteration (s): 2.24 | learning rate: 3.502E-05 | global batch size: 512 | lm loss: 1.898684E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.090 | TFLOPs: 23.48 | +63: iteration 60190/ 73814 | consumed samples: 30817280 | consumed tokens: 63113789440 | elapsed time per iteration (s): 2.22 | learning rate: 3.500E-05 | global batch size: 512 | lm loss: 1.925400E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.159 | TFLOPs: 23.69 | +63: iteration 60200/ 73814 | consumed samples: 30822400 | consumed tokens: 63124275200 | elapsed time per iteration (s): 2.24 | learning rate: 3.498E-05 | global batch size: 512 | lm loss: 1.934158E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.722 | TFLOPs: 23.55 | +63: iteration 60210/ 73814 | consumed samples: 30827520 | consumed tokens: 63134760960 | elapsed time per iteration (s): 2.25 | learning rate: 3.496E-05 | global batch size: 512 | lm loss: 1.898512E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.590 | TFLOPs: 23.43 | +63: iteration 60220/ 73814 | consumed samples: 30832640 | consumed tokens: 63145246720 | elapsed time per iteration (s): 2.25 | learning rate: 3.494E-05 | global batch size: 512 | lm loss: 1.902842E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.838 | TFLOPs: 23.45 | +63: iteration 60230/ 73814 | consumed samples: 30837760 | consumed tokens: 63155732480 | elapsed time per iteration (s): 2.24 | learning rate: 3.492E-05 | global batch size: 512 | lm loss: 1.912991E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.751 | TFLOPs: 23.55 | +63: iteration 60240/ 73814 | consumed samples: 30842880 | consumed tokens: 63166218240 | elapsed time per iteration (s): 2.25 | learning rate: 3.489E-05 | global batch size: 512 | lm loss: 1.914495E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.788 | TFLOPs: 23.45 | +63: iteration 60250/ 73814 | consumed samples: 30848000 | consumed tokens: 63176704000 | elapsed time per iteration (s): 2.23 | learning rate: 3.487E-05 | global batch size: 512 | lm loss: 1.922695E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.044 | TFLOPs: 23.68 | +63: iteration 60260/ 73814 | consumed samples: 30853120 | consumed tokens: 63187189760 | elapsed time per iteration (s): 2.34 | learning rate: 3.485E-05 | global batch size: 512 | lm loss: 1.878873E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.918 | TFLOPs: 22.54 | +63: iteration 60270/ 73814 | consumed samples: 30858240 | consumed tokens: 63197675520 | elapsed time per iteration (s): 2.24 | learning rate: 3.483E-05 | global batch size: 512 | lm loss: 1.905042E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.805 | TFLOPs: 23.55 | +63: iteration 60280/ 73814 | consumed samples: 30863360 | consumed tokens: 63208161280 | elapsed time per iteration (s): 2.24 | learning rate: 3.481E-05 | global batch size: 512 | lm loss: 1.922313E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.956 | TFLOPs: 23.57 | +63: iteration 60290/ 73814 | consumed samples: 30868480 | consumed tokens: 63218647040 | elapsed time per iteration (s): 2.24 | learning rate: 3.479E-05 | global batch size: 512 | lm loss: 1.905824E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.064 | TFLOPs: 23.58 | +63: iteration 60300/ 73814 | consumed samples: 30873600 | consumed tokens: 63229132800 | elapsed time per iteration (s): 2.24 | learning rate: 3.477E-05 | global batch size: 512 | lm loss: 1.875190E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.319 | TFLOPs: 23.50 | +63: iteration 60310/ 73814 | consumed samples: 30878720 | consumed tokens: 63239618560 | elapsed time per iteration (s): 2.23 | learning rate: 3.475E-05 | global batch size: 512 | lm loss: 1.896824E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.842 | TFLOPs: 23.66 | +63: iteration 60320/ 73814 | consumed samples: 30883840 | consumed tokens: 63250104320 | elapsed time per iteration (s): 2.24 | learning rate: 3.472E-05 | global batch size: 512 | lm loss: 1.900645E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.896 | TFLOPs: 23.56 | +63: iteration 60330/ 73814 | consumed samples: 30888960 | consumed tokens: 63260590080 | elapsed time per iteration (s): 2.23 | learning rate: 3.470E-05 | global batch size: 512 | lm loss: 1.891370E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.486 | TFLOPs: 23.62 | +63: iteration 60340/ 73814 | consumed samples: 30894080 | consumed tokens: 63271075840 | elapsed time per iteration (s): 2.36 | learning rate: 3.468E-05 | global batch size: 512 | lm loss: 1.917519E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.633 | TFLOPs: 22.30 | +63: iteration 60350/ 73814 | consumed samples: 30899200 | consumed tokens: 63281561600 | elapsed time per iteration (s): 2.24 | learning rate: 3.466E-05 | global batch size: 512 | lm loss: 1.893575E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.626 | TFLOPs: 23.54 | +63: iteration 60360/ 73814 | consumed samples: 30904320 | consumed tokens: 63292047360 | elapsed time per iteration (s): 2.23 | learning rate: 3.464E-05 | global batch size: 512 | lm loss: 1.905815E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.068 | TFLOPs: 23.68 | +63: iteration 60370/ 73814 | consumed samples: 30909440 | consumed tokens: 63302533120 | elapsed time per iteration (s): 2.24 | learning rate: 3.462E-05 | global batch size: 512 | lm loss: 1.895099E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.151 | TFLOPs: 23.49 | +63: iteration 60380/ 73814 | consumed samples: 30914560 | consumed tokens: 63313018880 | elapsed time per iteration (s): 2.24 | learning rate: 3.460E-05 | global batch size: 512 | lm loss: 1.922764E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.975 | TFLOPs: 23.57 | +63: iteration 60390/ 73814 | consumed samples: 30919680 | consumed tokens: 63323504640 | elapsed time per iteration (s): 2.23 | learning rate: 3.458E-05 | global batch size: 512 | lm loss: 1.930427E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.461 | TFLOPs: 23.62 | +63: iteration 60400/ 73814 | consumed samples: 30924800 | consumed tokens: 63333990400 | elapsed time per iteration (s): 2.24 | learning rate: 3.456E-05 | global batch size: 512 | lm loss: 1.885628E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.604 | TFLOPs: 23.53 | +63: iteration 60410/ 73814 | consumed samples: 30929920 | consumed tokens: 63344476160 | elapsed time per iteration (s): 2.25 | learning rate: 3.453E-05 | global batch size: 512 | lm loss: 1.916570E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.673 | TFLOPs: 23.44 | +63: iteration 60420/ 73814 | consumed samples: 30935040 | consumed tokens: 63354961920 | elapsed time per iteration (s): 2.36 | learning rate: 3.451E-05 | global batch size: 512 | lm loss: 1.908883E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.838 | TFLOPs: 22.32 | +63: iteration 60430/ 73814 | consumed samples: 30940160 | consumed tokens: 63365447680 | elapsed time per iteration (s): 2.24 | learning rate: 3.449E-05 | global batch size: 512 | lm loss: 1.937196E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.574 | TFLOPs: 23.53 | +63: iteration 60440/ 73814 | consumed samples: 30945280 | consumed tokens: 63375933440 | elapsed time per iteration (s): 2.23 | learning rate: 3.447E-05 | global batch size: 512 | lm loss: 1.906634E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.434 | TFLOPs: 23.62 | +63: iteration 60450/ 73814 | consumed samples: 30950400 | consumed tokens: 63386419200 | elapsed time per iteration (s): 2.23 | learning rate: 3.445E-05 | global batch size: 512 | lm loss: 1.879168E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.699 | TFLOPs: 23.65 | +63: iteration 60460/ 73814 | consumed samples: 30955520 | consumed tokens: 63396904960 | elapsed time per iteration (s): 2.32 | learning rate: 3.443E-05 | global batch size: 512 | lm loss: 1.916364E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.692 | TFLOPs: 22.72 | +63: iteration 60470/ 73814 | consumed samples: 30960640 | consumed tokens: 63407390720 | elapsed time per iteration (s): 2.23 | learning rate: 3.441E-05 | global batch size: 512 | lm loss: 1.926991E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.599 | TFLOPs: 23.64 | +63: iteration 60480/ 73814 | consumed samples: 30965760 | consumed tokens: 63417876480 | elapsed time per iteration (s): 2.24 | learning rate: 3.439E-05 | global batch size: 512 | lm loss: 1.899725E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.204 | TFLOPs: 23.49 | +63: iteration 60490/ 73814 | consumed samples: 30970880 | consumed tokens: 63428362240 | elapsed time per iteration (s): 2.24 | learning rate: 3.437E-05 | global batch size: 512 | lm loss: 1.909199E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.680 | TFLOPs: 23.54 | +63: iteration 60500/ 73814 | consumed samples: 30976000 | consumed tokens: 63438848000 | elapsed time per iteration (s): 2.23 | learning rate: 3.435E-05 | global batch size: 512 | lm loss: 1.926336E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.555 | TFLOPs: 23.63 | +63: iteration 60510/ 73814 | consumed samples: 30981120 | consumed tokens: 63449333760 | elapsed time per iteration (s): 2.48 | learning rate: 3.432E-05 | global batch size: 512 | lm loss: 1.917186E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.796 | TFLOPs: 21.29 | +63: iteration 60520/ 73814 | consumed samples: 30986240 | consumed tokens: 63459819520 | elapsed time per iteration (s): 2.24 | learning rate: 3.430E-05 | global batch size: 512 | lm loss: 1.913135E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.844 | TFLOPs: 23.56 | +63: iteration 60530/ 73814 | consumed samples: 30991360 | consumed tokens: 63470305280 | elapsed time per iteration (s): 2.27 | learning rate: 3.428E-05 | global batch size: 512 | lm loss: 1.897330E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.667 | TFLOPs: 23.23 | +63: iteration 60540/ 73814 | consumed samples: 30996480 | consumed tokens: 63480791040 | elapsed time per iteration (s): 2.22 | learning rate: 3.426E-05 | global batch size: 512 | lm loss: 1.889781E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.161 | TFLOPs: 23.69 | +63: iteration 60550/ 73814 | consumed samples: 31001600 | consumed tokens: 63491276800 | elapsed time per iteration (s): 2.23 | learning rate: 3.424E-05 | global batch size: 512 | lm loss: 1.876306E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.365 | TFLOPs: 23.61 | +63: iteration 60560/ 73814 | consumed samples: 31006720 | consumed tokens: 63501762560 | elapsed time per iteration (s): 2.23 | learning rate: 3.422E-05 | global batch size: 512 | lm loss: 1.883232E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.769 | TFLOPs: 23.65 | +63: iteration 60570/ 73814 | consumed samples: 31011840 | consumed tokens: 63512248320 | elapsed time per iteration (s): 2.23 | learning rate: 3.420E-05 | global batch size: 512 | lm loss: 1.875794E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.880 | TFLOPs: 23.67 | +63: iteration 60580/ 73814 | consumed samples: 31016960 | consumed tokens: 63522734080 | elapsed time per iteration (s): 2.23 | learning rate: 3.418E-05 | global batch size: 512 | lm loss: 1.936465E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.571 | TFLOPs: 23.63 | +63: iteration 60590/ 73814 | consumed samples: 31022080 | consumed tokens: 63533219840 | elapsed time per iteration (s): 2.22 | learning rate: 3.416E-05 | global batch size: 512 | lm loss: 1.908361E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.159 | TFLOPs: 23.69 | +63: iteration 60600/ 73814 | consumed samples: 31027200 | consumed tokens: 63543705600 | elapsed time per iteration (s): 2.24 | learning rate: 3.414E-05 | global batch size: 512 | lm loss: 1.899761E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.186 | TFLOPs: 23.49 | +63: iteration 60610/ 73814 | consumed samples: 31032320 | consumed tokens: 63554191360 | elapsed time per iteration (s): 2.24 | learning rate: 3.412E-05 | global batch size: 512 | lm loss: 1.912033E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.850 | TFLOPs: 23.56 | +63: iteration 60620/ 73814 | consumed samples: 31037440 | consumed tokens: 63564677120 | elapsed time per iteration (s): 2.23 | learning rate: 3.409E-05 | global batch size: 512 | lm loss: 1.914185E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.981 | TFLOPs: 23.68 | +63: iteration 60630/ 73814 | consumed samples: 31042560 | consumed tokens: 63575162880 | elapsed time per iteration (s): 2.25 | learning rate: 3.407E-05 | global batch size: 512 | lm loss: 1.893344E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.556 | TFLOPs: 23.43 | +63: iteration 60640/ 73814 | consumed samples: 31047680 | consumed tokens: 63585648640 | elapsed time per iteration (s): 2.23 | learning rate: 3.405E-05 | global batch size: 512 | lm loss: 1.905644E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.220 | TFLOPs: 23.60 | +63: iteration 60650/ 73814 | consumed samples: 31052800 | consumed tokens: 63596134400 | elapsed time per iteration (s): 2.23 | learning rate: 3.403E-05 | global batch size: 512 | lm loss: 1.896420E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.890 | TFLOPs: 23.67 | +63: iteration 60660/ 73814 | consumed samples: 31057920 | consumed tokens: 63606620160 | elapsed time per iteration (s): 2.23 | learning rate: 3.401E-05 | global batch size: 512 | lm loss: 1.899234E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.252 | TFLOPs: 23.60 | +63: iteration 60670/ 73814 | consumed samples: 31063040 | consumed tokens: 63617105920 | elapsed time per iteration (s): 2.22 | learning rate: 3.399E-05 | global batch size: 512 | lm loss: 1.903594E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.128 | TFLOPs: 23.69 | +63: iteration 60680/ 73814 | consumed samples: 31068160 | consumed tokens: 63627591680 | elapsed time per iteration (s): 2.23 | learning rate: 3.397E-05 | global batch size: 512 | lm loss: 1.887447E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.469 | TFLOPs: 23.62 | +63: iteration 60690/ 73814 | consumed samples: 31073280 | consumed tokens: 63638077440 | elapsed time per iteration (s): 2.25 | learning rate: 3.395E-05 | global batch size: 512 | lm loss: 1.888336E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.468 | TFLOPs: 23.42 | +63: iteration 60700/ 73814 | consumed samples: 31078400 | consumed tokens: 63648563200 | elapsed time per iteration (s): 2.37 | learning rate: 3.393E-05 | global batch size: 512 | lm loss: 1.882727E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.174 | TFLOPs: 22.25 | +63: iteration 60710/ 73814 | consumed samples: 31083520 | consumed tokens: 63659048960 | elapsed time per iteration (s): 2.24 | learning rate: 3.391E-05 | global batch size: 512 | lm loss: 1.879712E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.241 | TFLOPs: 23.50 | +63: iteration 60720/ 73814 | consumed samples: 31088640 | consumed tokens: 63669534720 | elapsed time per iteration (s): 2.40 | learning rate: 3.389E-05 | global batch size: 512 | lm loss: 1.910941E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.533 | TFLOPs: 21.98 | +63: iteration 60730/ 73814 | consumed samples: 31093760 | consumed tokens: 63680020480 | elapsed time per iteration (s): 2.33 | learning rate: 3.387E-05 | global batch size: 512 | lm loss: 1.915477E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.706 | TFLOPs: 22.62 | +63: iteration 60740/ 73814 | consumed samples: 31098880 | consumed tokens: 63690506240 | elapsed time per iteration (s): 2.24 | learning rate: 3.385E-05 | global batch size: 512 | lm loss: 1.891186E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.009 | TFLOPs: 23.58 | +63: iteration 60750/ 73814 | consumed samples: 31104000 | consumed tokens: 63700992000 | elapsed time per iteration (s): 2.24 | learning rate: 3.383E-05 | global batch size: 512 | lm loss: 1.913359E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.037 | TFLOPs: 23.58 | +63: iteration 60760/ 73814 | consumed samples: 31109120 | consumed tokens: 63711477760 | elapsed time per iteration (s): 2.23 | learning rate: 3.381E-05 | global batch size: 512 | lm loss: 1.927039E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.605 | TFLOPs: 23.64 | +63: iteration 60770/ 73814 | consumed samples: 31114240 | consumed tokens: 63721963520 | elapsed time per iteration (s): 2.41 | learning rate: 3.378E-05 | global batch size: 512 | lm loss: 1.904558E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.670 | TFLOPs: 21.89 | +63: iteration 60780/ 73814 | consumed samples: 31119360 | consumed tokens: 63732449280 | elapsed time per iteration (s): 2.28 | learning rate: 3.376E-05 | global batch size: 512 | lm loss: 1.894894E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.747 | TFLOPs: 23.14 | +63: iteration 60790/ 73814 | consumed samples: 31124480 | consumed tokens: 63742935040 | elapsed time per iteration (s): 2.24 | learning rate: 3.374E-05 | global batch size: 512 | lm loss: 1.896611E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.856 | TFLOPs: 23.56 | +63: iteration 60800/ 73814 | consumed samples: 31129600 | consumed tokens: 63753420800 | elapsed time per iteration (s): 2.28 | learning rate: 3.372E-05 | global batch size: 512 | lm loss: 1.904048E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.378 | TFLOPs: 23.10 | +63: iteration 60810/ 73814 | consumed samples: 31134720 | consumed tokens: 63763906560 | elapsed time per iteration (s): 2.26 | learning rate: 3.370E-05 | global batch size: 512 | lm loss: 1.917277E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.973 | TFLOPs: 23.37 | +63: iteration 60820/ 73814 | consumed samples: 31139840 | consumed tokens: 63774392320 | elapsed time per iteration (s): 2.24 | learning rate: 3.368E-05 | global batch size: 512 | lm loss: 1.917211E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.904 | TFLOPs: 23.56 | +63: iteration 60830/ 73814 | consumed samples: 31144960 | consumed tokens: 63784878080 | elapsed time per iteration (s): 2.24 | learning rate: 3.366E-05 | global batch size: 512 | lm loss: 1.904365E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.988 | TFLOPs: 23.57 | +63: iteration 60840/ 73814 | consumed samples: 31150080 | consumed tokens: 63795363840 | elapsed time per iteration (s): 2.35 | learning rate: 3.364E-05 | global batch size: 512 | lm loss: 1.918999E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.331 | TFLOPs: 22.48 | +63: iteration 60850/ 73814 | consumed samples: 31155200 | consumed tokens: 63805849600 | elapsed time per iteration (s): 2.23 | learning rate: 3.362E-05 | global batch size: 512 | lm loss: 1.899693E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.769 | TFLOPs: 23.65 | +63: iteration 60860/ 73814 | consumed samples: 31160320 | consumed tokens: 63816335360 | elapsed time per iteration (s): 2.24 | learning rate: 3.360E-05 | global batch size: 512 | lm loss: 1.898356E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.522 | TFLOPs: 23.53 | +63: iteration 60870/ 73814 | consumed samples: 31165440 | consumed tokens: 63826821120 | elapsed time per iteration (s): 2.23 | learning rate: 3.358E-05 | global batch size: 512 | lm loss: 1.862122E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.709 | TFLOPs: 23.65 | +63: iteration 60880/ 73814 | consumed samples: 31170560 | consumed tokens: 63837306880 | elapsed time per iteration (s): 2.24 | learning rate: 3.356E-05 | global batch size: 512 | lm loss: 1.905177E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.826 | TFLOPs: 23.56 | +63: iteration 60890/ 73814 | consumed samples: 31175680 | consumed tokens: 63847792640 | elapsed time per iteration (s): 2.24 | learning rate: 3.354E-05 | global batch size: 512 | lm loss: 1.903721E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.585 | TFLOPs: 23.53 | +63: iteration 60900/ 73814 | consumed samples: 31180800 | consumed tokens: 63858278400 | elapsed time per iteration (s): 2.24 | learning rate: 3.352E-05 | global batch size: 512 | lm loss: 1.901923E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.358 | TFLOPs: 23.51 | +63: iteration 60910/ 73814 | consumed samples: 31185920 | consumed tokens: 63868764160 | elapsed time per iteration (s): 2.23 | learning rate: 3.350E-05 | global batch size: 512 | lm loss: 1.869355E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.637 | TFLOPs: 23.64 | +63: iteration 60920/ 73814 | consumed samples: 31191040 | consumed tokens: 63879249920 | elapsed time per iteration (s): 2.26 | learning rate: 3.348E-05 | global batch size: 512 | lm loss: 1.911583E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.814 | TFLOPs: 23.35 | +63: iteration 60930/ 73814 | consumed samples: 31196160 | consumed tokens: 63889735680 | elapsed time per iteration (s): 2.27 | learning rate: 3.346E-05 | global batch size: 512 | lm loss: 1.917591E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.376 | TFLOPs: 23.20 | +63: iteration 60940/ 73814 | consumed samples: 31201280 | consumed tokens: 63900221440 | elapsed time per iteration (s): 2.25 | learning rate: 3.344E-05 | global batch size: 512 | lm loss: 1.899651E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.504 | TFLOPs: 23.42 | +63: iteration 60950/ 73814 | consumed samples: 31206400 | consumed tokens: 63910707200 | elapsed time per iteration (s): 2.28 | learning rate: 3.342E-05 | global batch size: 512 | lm loss: 1.897436E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.431 | TFLOPs: 23.10 | +63: iteration 60960/ 73814 | consumed samples: 31211520 | consumed tokens: 63921192960 | elapsed time per iteration (s): 2.24 | learning rate: 3.340E-05 | global batch size: 512 | lm loss: 1.875497E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.652 | TFLOPs: 23.54 | +63: iteration 60970/ 73814 | consumed samples: 31216640 | consumed tokens: 63931678720 | elapsed time per iteration (s): 2.24 | learning rate: 3.338E-05 | global batch size: 512 | lm loss: 1.894531E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.968 | TFLOPs: 23.57 | +63: iteration 60980/ 73814 | consumed samples: 31221760 | consumed tokens: 63942164480 | elapsed time per iteration (s): 2.23 | learning rate: 3.336E-05 | global batch size: 512 | lm loss: 1.885733E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.286 | TFLOPs: 23.60 | +63: iteration 60990/ 73814 | consumed samples: 31226880 | consumed tokens: 63952650240 | elapsed time per iteration (s): 2.22 | learning rate: 3.334E-05 | global batch size: 512 | lm loss: 1.899352E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.330 | TFLOPs: 23.71 | +63: iteration 61000/ 73814 | consumed samples: 31232000 | consumed tokens: 63963136000 | elapsed time per iteration (s): 2.25 | learning rate: 3.332E-05 | global batch size: 512 | lm loss: 1.893992E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.016 | TFLOPs: 23.47 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 61000 | lm loss value: 1.870841E+00 | lm loss PPL: 6.493752E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 61010/ 73814 | consumed samples: 31237120 | consumed tokens: 63973621760 | elapsed time per iteration (s): 2.29 | learning rate: 3.329E-05 | global batch size: 512 | lm loss: 1.891496E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.064 | TFLOPs: 23.07 | +63: iteration 61020/ 73814 | consumed samples: 31242240 | consumed tokens: 63984107520 | elapsed time per iteration (s): 2.23 | learning rate: 3.327E-05 | global batch size: 512 | lm loss: 1.891103E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.247 | TFLOPs: 23.60 | +63: iteration 61030/ 73814 | consumed samples: 31247360 | consumed tokens: 63994593280 | elapsed time per iteration (s): 2.23 | learning rate: 3.325E-05 | global batch size: 512 | lm loss: 1.902849E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.016 | TFLOPs: 23.68 | +63: iteration 61040/ 73814 | consumed samples: 31252480 | consumed tokens: 64005079040 | elapsed time per iteration (s): 2.24 | learning rate: 3.323E-05 | global batch size: 512 | lm loss: 1.872666E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.771 | TFLOPs: 23.55 | +63: iteration 61050/ 73814 | consumed samples: 31257600 | consumed tokens: 64015564800 | elapsed time per iteration (s): 2.31 | learning rate: 3.321E-05 | global batch size: 512 | lm loss: 1.909514E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.857 | TFLOPs: 22.84 | +63: iteration 61060/ 73814 | consumed samples: 31262720 | consumed tokens: 64026050560 | elapsed time per iteration (s): 2.27 | learning rate: 3.319E-05 | global batch size: 512 | lm loss: 1.903560E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.981 | TFLOPs: 23.26 | +63: iteration 61070/ 73814 | consumed samples: 31267840 | consumed tokens: 64036536320 | elapsed time per iteration (s): 2.38 | learning rate: 3.317E-05 | global batch size: 512 | lm loss: 1.920246E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.928 | TFLOPs: 22.13 | +63: iteration 61080/ 73814 | consumed samples: 31272960 | consumed tokens: 64047022080 | elapsed time per iteration (s): 2.27 | learning rate: 3.315E-05 | global batch size: 512 | lm loss: 1.922088E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.745 | TFLOPs: 23.24 | +63: iteration 61090/ 73814 | consumed samples: 31278080 | consumed tokens: 64057507840 | elapsed time per iteration (s): 2.38 | learning rate: 3.313E-05 | global batch size: 512 | lm loss: 1.893861E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.402 | TFLOPs: 22.17 | +63: iteration 61100/ 73814 | consumed samples: 31283200 | consumed tokens: 64067993600 | elapsed time per iteration (s): 2.38 | learning rate: 3.311E-05 | global batch size: 512 | lm loss: 1.913221E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.213 | TFLOPs: 22.16 | +63: iteration 61110/ 73814 | consumed samples: 31288320 | consumed tokens: 64078479360 | elapsed time per iteration (s): 2.42 | learning rate: 3.309E-05 | global batch size: 512 | lm loss: 1.881252E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.387 | TFLOPs: 21.76 | +63: iteration 61120/ 73814 | consumed samples: 31293440 | consumed tokens: 64088965120 | elapsed time per iteration (s): 2.80 | learning rate: 3.307E-05 | global batch size: 512 | lm loss: 1.889960E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 182.666 | TFLOPs: 18.80 | +63: iteration 61130/ 73814 | consumed samples: 31298560 | consumed tokens: 64099450880 | elapsed time per iteration (s): 3.34 | learning rate: 3.305E-05 | global batch size: 512 | lm loss: 1.887098E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 153.519 | TFLOPs: 15.80 | +63: iteration 61140/ 73814 | consumed samples: 31303680 | consumed tokens: 64109936640 | elapsed time per iteration (s): 2.31 | learning rate: 3.303E-05 | global batch size: 512 | lm loss: 1.926397E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.096 | TFLOPs: 22.86 | +63: iteration 61150/ 73814 | consumed samples: 31308800 | consumed tokens: 64120422400 | elapsed time per iteration (s): 2.25 | learning rate: 3.301E-05 | global batch size: 512 | lm loss: 1.901339E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.189 | TFLOPs: 23.39 | +63: iteration 61160/ 73814 | consumed samples: 31313920 | consumed tokens: 64130908160 | elapsed time per iteration (s): 2.33 | learning rate: 3.299E-05 | global batch size: 512 | lm loss: 1.892619E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.753 | TFLOPs: 22.62 | +63: iteration 61170/ 73814 | consumed samples: 31319040 | consumed tokens: 64141393920 | elapsed time per iteration (s): 2.28 | learning rate: 3.297E-05 | global batch size: 512 | lm loss: 1.894409E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.809 | TFLOPs: 23.14 | +63: iteration 61180/ 73814 | consumed samples: 31324160 | consumed tokens: 64151879680 | elapsed time per iteration (s): 2.30 | learning rate: 3.295E-05 | global batch size: 512 | lm loss: 1.894368E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.839 | TFLOPs: 22.94 | +63: iteration 61190/ 73814 | consumed samples: 31329280 | consumed tokens: 64162365440 | elapsed time per iteration (s): 2.23 | learning rate: 3.293E-05 | global batch size: 512 | lm loss: 1.905911E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.012 | TFLOPs: 23.68 | +63: iteration 61200/ 73814 | consumed samples: 31334400 | consumed tokens: 64172851200 | elapsed time per iteration (s): 2.23 | learning rate: 3.291E-05 | global batch size: 512 | lm loss: 1.914862E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.791 | TFLOPs: 23.66 | +63: iteration 61210/ 73814 | consumed samples: 31339520 | consumed tokens: 64183336960 | elapsed time per iteration (s): 2.24 | learning rate: 3.289E-05 | global batch size: 512 | lm loss: 1.888835E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.214 | TFLOPs: 23.49 | +63: iteration 61220/ 73814 | consumed samples: 31344640 | consumed tokens: 64193822720 | elapsed time per iteration (s): 2.31 | learning rate: 3.287E-05 | global batch size: 512 | lm loss: 1.904042E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.550 | TFLOPs: 22.81 | +63: iteration 61230/ 73814 | consumed samples: 31349760 | consumed tokens: 64204308480 | elapsed time per iteration (s): 2.25 | learning rate: 3.285E-05 | global batch size: 512 | lm loss: 1.907181E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.942 | TFLOPs: 23.47 | +63: iteration 61240/ 73814 | consumed samples: 31354880 | consumed tokens: 64214794240 | elapsed time per iteration (s): 2.60 | learning rate: 3.283E-05 | global batch size: 512 | lm loss: 1.891930E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 196.550 | TFLOPs: 20.23 | +63: iteration 61250/ 73814 | consumed samples: 31360000 | consumed tokens: 64225280000 | elapsed time per iteration (s): 2.23 | learning rate: 3.281E-05 | global batch size: 512 | lm loss: 1.889469E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.378 | TFLOPs: 23.61 | +63: iteration 61260/ 73814 | consumed samples: 31365120 | consumed tokens: 64235765760 | elapsed time per iteration (s): 2.22 | learning rate: 3.279E-05 | global batch size: 512 | lm loss: 1.907800E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.387 | TFLOPs: 23.72 | +63: iteration 61270/ 73814 | consumed samples: 31370240 | consumed tokens: 64246251520 | elapsed time per iteration (s): 2.54 | learning rate: 3.277E-05 | global batch size: 512 | lm loss: 1.895355E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.262 | TFLOPs: 20.72 | +63: iteration 61280/ 73814 | consumed samples: 31375360 | consumed tokens: 64256737280 | elapsed time per iteration (s): 2.23 | learning rate: 3.275E-05 | global batch size: 512 | lm loss: 1.917175E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.813 | TFLOPs: 23.66 | +63: iteration 61290/ 73814 | consumed samples: 31380480 | consumed tokens: 64267223040 | elapsed time per iteration (s): 2.24 | learning rate: 3.273E-05 | global batch size: 512 | lm loss: 1.905510E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.724 | TFLOPs: 23.55 | +63: iteration 61300/ 73814 | consumed samples: 31385600 | consumed tokens: 64277708800 | elapsed time per iteration (s): 2.23 | learning rate: 3.271E-05 | global batch size: 512 | lm loss: 1.912018E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.765 | TFLOPs: 23.65 | +63: iteration 61310/ 73814 | consumed samples: 31390720 | consumed tokens: 64288194560 | elapsed time per iteration (s): 2.22 | learning rate: 3.269E-05 | global batch size: 512 | lm loss: 1.893093E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.189 | TFLOPs: 23.70 | +63: iteration 61320/ 73814 | consumed samples: 31395840 | consumed tokens: 64298680320 | elapsed time per iteration (s): 2.23 | learning rate: 3.267E-05 | global batch size: 512 | lm loss: 1.895531E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.525 | TFLOPs: 23.63 | +63: iteration 61330/ 73814 | consumed samples: 31400960 | consumed tokens: 64309166080 | elapsed time per iteration (s): 2.23 | learning rate: 3.265E-05 | global batch size: 512 | lm loss: 1.903284E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.989 | TFLOPs: 23.68 | +63: iteration 61340/ 73814 | consumed samples: 31406080 | consumed tokens: 64319651840 | elapsed time per iteration (s): 2.22 | learning rate: 3.263E-05 | global batch size: 512 | lm loss: 1.900705E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.424 | TFLOPs: 23.72 | +63: iteration 61350/ 73814 | consumed samples: 31411200 | consumed tokens: 64330137600 | elapsed time per iteration (s): 2.24 | learning rate: 3.261E-05 | global batch size: 512 | lm loss: 1.927233E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.750 | TFLOPs: 23.55 | +63: iteration 61360/ 73814 | consumed samples: 31416320 | consumed tokens: 64340623360 | elapsed time per iteration (s): 2.23 | learning rate: 3.260E-05 | global batch size: 512 | lm loss: 1.916500E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.620 | TFLOPs: 23.64 | +63: iteration 61370/ 73814 | consumed samples: 31421440 | consumed tokens: 64351109120 | elapsed time per iteration (s): 2.22 | learning rate: 3.258E-05 | global batch size: 512 | lm loss: 1.901586E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.359 | TFLOPs: 23.71 | +63: iteration 61380/ 73814 | consumed samples: 31426560 | consumed tokens: 64361594880 | elapsed time per iteration (s): 2.23 | learning rate: 3.256E-05 | global batch size: 512 | lm loss: 1.892154E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.961 | TFLOPs: 23.67 | +63: iteration 61390/ 73814 | consumed samples: 31431680 | consumed tokens: 64372080640 | elapsed time per iteration (s): 2.24 | learning rate: 3.254E-05 | global batch size: 512 | lm loss: 1.894695E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.785 | TFLOPs: 23.55 | +63: iteration 61400/ 73814 | consumed samples: 31436800 | consumed tokens: 64382566400 | elapsed time per iteration (s): 2.24 | learning rate: 3.252E-05 | global batch size: 512 | lm loss: 1.881526E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.158 | TFLOPs: 23.49 | +63: iteration 61410/ 73814 | consumed samples: 31441920 | consumed tokens: 64393052160 | elapsed time per iteration (s): 2.26 | learning rate: 3.250E-05 | global batch size: 512 | lm loss: 1.901175E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.021 | TFLOPs: 23.37 | +63: iteration 61420/ 73814 | consumed samples: 31447040 | consumed tokens: 64403537920 | elapsed time per iteration (s): 2.22 | learning rate: 3.248E-05 | global batch size: 512 | lm loss: 1.911086E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.255 | TFLOPs: 23.70 | +63: iteration 61430/ 73814 | consumed samples: 31452160 | consumed tokens: 64414023680 | elapsed time per iteration (s): 2.51 | learning rate: 3.246E-05 | global batch size: 512 | lm loss: 1.900187E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 204.378 | TFLOPs: 21.04 | +63: iteration 61440/ 73814 | consumed samples: 31457280 | consumed tokens: 64424509440 | elapsed time per iteration (s): 2.36 | learning rate: 3.244E-05 | global batch size: 512 | lm loss: 1.901600E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.079 | TFLOPs: 22.35 | +63: iteration 61450/ 73814 | consumed samples: 31462400 | consumed tokens: 64434995200 | elapsed time per iteration (s): 2.22 | learning rate: 3.242E-05 | global batch size: 512 | lm loss: 1.877866E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.350 | TFLOPs: 23.71 | +63: iteration 61460/ 73814 | consumed samples: 31467520 | consumed tokens: 64445480960 | elapsed time per iteration (s): 2.45 | learning rate: 3.240E-05 | global batch size: 512 | lm loss: 1.878636E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.607 | TFLOPs: 21.48 | +63: iteration 61470/ 73814 | consumed samples: 31472640 | consumed tokens: 64455966720 | elapsed time per iteration (s): 2.24 | learning rate: 3.238E-05 | global batch size: 512 | lm loss: 1.887442E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.597 | TFLOPs: 23.53 | +63: iteration 61480/ 73814 | consumed samples: 31477760 | consumed tokens: 64466452480 | elapsed time per iteration (s): 2.25 | learning rate: 3.236E-05 | global batch size: 512 | lm loss: 1.913846E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.780 | TFLOPs: 23.45 | +63: iteration 61490/ 73814 | consumed samples: 31482880 | consumed tokens: 64476938240 | elapsed time per iteration (s): 2.23 | learning rate: 3.234E-05 | global batch size: 512 | lm loss: 1.894810E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.473 | TFLOPs: 23.62 | +63: iteration 61500/ 73814 | consumed samples: 31488000 | consumed tokens: 64487424000 | elapsed time per iteration (s): 2.22 | learning rate: 3.232E-05 | global batch size: 512 | lm loss: 1.913767E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.421 | TFLOPs: 23.72 | +63: iteration 61510/ 73814 | consumed samples: 31493120 | consumed tokens: 64497909760 | elapsed time per iteration (s): 2.23 | learning rate: 3.230E-05 | global batch size: 512 | lm loss: 1.883331E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.916 | TFLOPs: 23.67 | +63: iteration 61520/ 73814 | consumed samples: 31498240 | consumed tokens: 64508395520 | elapsed time per iteration (s): 2.24 | learning rate: 3.228E-05 | global batch size: 512 | lm loss: 1.910764E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.072 | TFLOPs: 23.58 | +63: iteration 61530/ 73814 | consumed samples: 31503360 | consumed tokens: 64518881280 | elapsed time per iteration (s): 2.22 | learning rate: 3.226E-05 | global batch size: 512 | lm loss: 1.905273E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.304 | TFLOPs: 23.71 | +63: iteration 61540/ 73814 | consumed samples: 31508480 | consumed tokens: 64529367040 | elapsed time per iteration (s): 2.24 | learning rate: 3.224E-05 | global batch size: 512 | lm loss: 1.911538E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.293 | TFLOPs: 23.50 | +63: iteration 61550/ 73814 | consumed samples: 31513600 | consumed tokens: 64539852800 | elapsed time per iteration (s): 2.24 | learning rate: 3.222E-05 | global batch size: 512 | lm loss: 1.911539E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.908 | TFLOPs: 23.56 | +63: iteration 61560/ 73814 | consumed samples: 31518720 | consumed tokens: 64550338560 | elapsed time per iteration (s): 2.25 | learning rate: 3.220E-05 | global batch size: 512 | lm loss: 1.903996E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.756 | TFLOPs: 23.45 | +63: iteration 61570/ 73814 | consumed samples: 31523840 | consumed tokens: 64560824320 | elapsed time per iteration (s): 2.25 | learning rate: 3.218E-05 | global batch size: 512 | lm loss: 1.894965E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.437 | TFLOPs: 23.41 | +63: iteration 61580/ 73814 | consumed samples: 31528960 | consumed tokens: 64571310080 | elapsed time per iteration (s): 2.22 | learning rate: 3.216E-05 | global batch size: 512 | lm loss: 1.896004E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.227 | TFLOPs: 23.70 | +63: iteration 61590/ 73814 | consumed samples: 31534080 | consumed tokens: 64581795840 | elapsed time per iteration (s): 2.23 | learning rate: 3.214E-05 | global batch size: 512 | lm loss: 1.894892E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.407 | TFLOPs: 23.62 | +63: iteration 61600/ 73814 | consumed samples: 31539200 | consumed tokens: 64592281600 | elapsed time per iteration (s): 2.22 | learning rate: 3.213E-05 | global batch size: 512 | lm loss: 1.894775E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.287 | TFLOPs: 23.71 | +63: iteration 61610/ 73814 | consumed samples: 31544320 | consumed tokens: 64602767360 | elapsed time per iteration (s): 2.22 | learning rate: 3.211E-05 | global batch size: 512 | lm loss: 1.921398E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.419 | TFLOPs: 23.72 | +63: iteration 61620/ 73814 | consumed samples: 31549440 | consumed tokens: 64613253120 | elapsed time per iteration (s): 2.23 | learning rate: 3.209E-05 | global batch size: 512 | lm loss: 1.911394E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.116 | TFLOPs: 23.59 | +63: iteration 61630/ 73814 | consumed samples: 31554560 | consumed tokens: 64623738880 | elapsed time per iteration (s): 2.30 | learning rate: 3.207E-05 | global batch size: 512 | lm loss: 1.902105E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.453 | TFLOPs: 22.90 | +63: iteration 61640/ 73814 | consumed samples: 31559680 | consumed tokens: 64634224640 | elapsed time per iteration (s): 2.24 | learning rate: 3.205E-05 | global batch size: 512 | lm loss: 1.905162E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.555 | TFLOPs: 23.53 | +63: iteration 61650/ 73814 | consumed samples: 31564800 | consumed tokens: 64644710400 | elapsed time per iteration (s): 2.23 | learning rate: 3.203E-05 | global batch size: 512 | lm loss: 1.892470E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.654 | TFLOPs: 23.64 | +63: iteration 61660/ 73814 | consumed samples: 31569920 | consumed tokens: 64655196160 | elapsed time per iteration (s): 2.22 | learning rate: 3.201E-05 | global batch size: 512 | lm loss: 1.910168E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.133 | TFLOPs: 23.69 | +63: iteration 61670/ 73814 | consumed samples: 31575040 | consumed tokens: 64665681920 | elapsed time per iteration (s): 2.24 | learning rate: 3.199E-05 | global batch size: 512 | lm loss: 1.897673E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.933 | TFLOPs: 23.57 | +63: iteration 61680/ 73814 | consumed samples: 31580160 | consumed tokens: 64676167680 | elapsed time per iteration (s): 2.22 | learning rate: 3.197E-05 | global batch size: 512 | lm loss: 1.890241E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.210 | TFLOPs: 23.70 | +63: iteration 61690/ 73814 | consumed samples: 31585280 | consumed tokens: 64686653440 | elapsed time per iteration (s): 2.23 | learning rate: 3.195E-05 | global batch size: 512 | lm loss: 1.914325E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.592 | TFLOPs: 23.64 | +63: iteration 61700/ 73814 | consumed samples: 31590400 | consumed tokens: 64697139200 | elapsed time per iteration (s): 2.22 | learning rate: 3.193E-05 | global batch size: 512 | lm loss: 1.925497E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.153 | TFLOPs: 23.69 | +63: iteration 61710/ 73814 | consumed samples: 31595520 | consumed tokens: 64707624960 | elapsed time per iteration (s): 2.24 | learning rate: 3.191E-05 | global batch size: 512 | lm loss: 1.899837E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.056 | TFLOPs: 23.58 | +63: iteration 61720/ 73814 | consumed samples: 31600640 | consumed tokens: 64718110720 | elapsed time per iteration (s): 2.26 | learning rate: 3.189E-05 | global batch size: 512 | lm loss: 1.900362E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.325 | TFLOPs: 23.30 | +63: iteration 61730/ 73814 | consumed samples: 31605760 | consumed tokens: 64728596480 | elapsed time per iteration (s): 2.24 | learning rate: 3.187E-05 | global batch size: 512 | lm loss: 1.874942E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.771 | TFLOPs: 23.55 | +63: iteration 61740/ 73814 | consumed samples: 31610880 | consumed tokens: 64739082240 | elapsed time per iteration (s): 2.57 | learning rate: 3.186E-05 | global batch size: 512 | lm loss: 1.879556E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 198.988 | TFLOPs: 20.48 | +63: iteration 61750/ 73814 | consumed samples: 31616000 | consumed tokens: 64749568000 | elapsed time per iteration (s): 2.25 | learning rate: 3.184E-05 | global batch size: 512 | lm loss: 1.895066E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.421 | TFLOPs: 23.41 | +63: iteration 61760/ 73814 | consumed samples: 31621120 | consumed tokens: 64760053760 | elapsed time per iteration (s): 2.34 | learning rate: 3.182E-05 | global batch size: 512 | lm loss: 1.878396E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.662 | TFLOPs: 22.51 | +63: iteration 61770/ 73814 | consumed samples: 31626240 | consumed tokens: 64770539520 | elapsed time per iteration (s): 2.22 | learning rate: 3.180E-05 | global batch size: 512 | lm loss: 1.890696E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.375 | TFLOPs: 23.72 | +63: iteration 61780/ 73814 | consumed samples: 31631360 | consumed tokens: 64781025280 | elapsed time per iteration (s): 2.23 | learning rate: 3.178E-05 | global batch size: 512 | lm loss: 1.869582E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.386 | TFLOPs: 23.61 | +63: iteration 61790/ 73814 | consumed samples: 31636480 | consumed tokens: 64791511040 | elapsed time per iteration (s): 2.29 | learning rate: 3.176E-05 | global batch size: 512 | lm loss: 1.899744E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.593 | TFLOPs: 23.02 | +63: iteration 61800/ 73814 | consumed samples: 31641600 | consumed tokens: 64801996800 | elapsed time per iteration (s): 2.22 | learning rate: 3.174E-05 | global batch size: 512 | lm loss: 1.888386E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.205 | TFLOPs: 23.70 | +63: iteration 61810/ 73814 | consumed samples: 31646720 | consumed tokens: 64812482560 | elapsed time per iteration (s): 2.24 | learning rate: 3.172E-05 | global batch size: 512 | lm loss: 1.904670E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.760 | TFLOPs: 23.55 | +63: iteration 61820/ 73814 | consumed samples: 31651840 | consumed tokens: 64822968320 | elapsed time per iteration (s): 2.25 | learning rate: 3.170E-05 | global batch size: 512 | lm loss: 1.908005E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.957 | TFLOPs: 23.47 | +63: iteration 61830/ 73814 | consumed samples: 31656960 | consumed tokens: 64833454080 | elapsed time per iteration (s): 2.23 | learning rate: 3.168E-05 | global batch size: 512 | lm loss: 1.917412E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.226 | TFLOPs: 23.60 | +63: iteration 61840/ 73814 | consumed samples: 31662080 | consumed tokens: 64843939840 | elapsed time per iteration (s): 2.43 | learning rate: 3.166E-05 | global batch size: 512 | lm loss: 1.892071E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.637 | TFLOPs: 21.68 | +63: iteration 61850/ 73814 | consumed samples: 31667200 | consumed tokens: 64854425600 | elapsed time per iteration (s): 2.36 | learning rate: 3.165E-05 | global batch size: 512 | lm loss: 1.893706E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.205 | TFLOPs: 22.36 | +63: iteration 61860/ 73814 | consumed samples: 31672320 | consumed tokens: 64864911360 | elapsed time per iteration (s): 2.24 | learning rate: 3.163E-05 | global batch size: 512 | lm loss: 1.882518E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.340 | TFLOPs: 23.51 | +63: iteration 61870/ 73814 | consumed samples: 31677440 | consumed tokens: 64875397120 | elapsed time per iteration (s): 2.26 | learning rate: 3.161E-05 | global batch size: 512 | lm loss: 1.896418E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.673 | TFLOPs: 23.33 | +63: iteration 61880/ 73814 | consumed samples: 31682560 | consumed tokens: 64885882880 | elapsed time per iteration (s): 2.23 | learning rate: 3.159E-05 | global batch size: 512 | lm loss: 1.901208E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.831 | TFLOPs: 23.66 | +63: iteration 61890/ 73814 | consumed samples: 31687680 | consumed tokens: 64896368640 | elapsed time per iteration (s): 2.24 | learning rate: 3.157E-05 | global batch size: 512 | lm loss: 1.902574E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.789 | TFLOPs: 23.55 | +63: iteration 61900/ 73814 | consumed samples: 31692800 | consumed tokens: 64906854400 | elapsed time per iteration (s): 2.22 | learning rate: 3.155E-05 | global batch size: 512 | lm loss: 1.904619E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.156 | TFLOPs: 23.69 | +63: iteration 61910/ 73814 | consumed samples: 31697920 | consumed tokens: 64917340160 | elapsed time per iteration (s): 2.24 | learning rate: 3.153E-05 | global batch size: 512 | lm loss: 1.908790E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.394 | TFLOPs: 23.51 | +63: iteration 61920/ 73814 | consumed samples: 31703040 | consumed tokens: 64927825920 | elapsed time per iteration (s): 2.22 | learning rate: 3.151E-05 | global batch size: 512 | lm loss: 1.898742E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.197 | TFLOPs: 23.70 | +63: iteration 61930/ 73814 | consumed samples: 31708160 | consumed tokens: 64938311680 | elapsed time per iteration (s): 2.26 | learning rate: 3.149E-05 | global batch size: 512 | lm loss: 1.887152E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.632 | TFLOPs: 23.33 | +63: iteration 61940/ 73814 | consumed samples: 31713280 | consumed tokens: 64948797440 | elapsed time per iteration (s): 2.26 | learning rate: 3.147E-05 | global batch size: 512 | lm loss: 1.922510E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.709 | TFLOPs: 23.34 | +63: iteration 61950/ 73814 | consumed samples: 31718400 | consumed tokens: 64959283200 | elapsed time per iteration (s): 2.24 | learning rate: 3.146E-05 | global batch size: 512 | lm loss: 1.880968E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.733 | TFLOPs: 23.55 | +63: iteration 61960/ 73814 | consumed samples: 31723520 | consumed tokens: 64969768960 | elapsed time per iteration (s): 2.23 | learning rate: 3.144E-05 | global batch size: 512 | lm loss: 1.892005E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.796 | TFLOPs: 23.66 | +63: iteration 61970/ 73814 | consumed samples: 31728640 | consumed tokens: 64980254720 | elapsed time per iteration (s): 2.24 | learning rate: 3.142E-05 | global batch size: 512 | lm loss: 1.900327E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.535 | TFLOPs: 23.53 | +63: iteration 61980/ 73814 | consumed samples: 31733760 | consumed tokens: 64990740480 | elapsed time per iteration (s): 2.34 | learning rate: 3.140E-05 | global batch size: 512 | lm loss: 1.934963E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.085 | TFLOPs: 22.55 | +63: iteration 61990/ 73814 | consumed samples: 31738880 | consumed tokens: 65001226240 | elapsed time per iteration (s): 2.26 | learning rate: 3.138E-05 | global batch size: 512 | lm loss: 1.887117E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.703 | TFLOPs: 23.34 | + 0: [2022-12-03 03:15:45,771] [INFO] [logging.py:68:log_dist] [Rank 0] step=62000, skipped=0, lr=[3.136125101022868e-05, 3.136125101022868e-05, 3.136125101022868e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 62000/ 73814 | consumed samples: 31744000 | consumed tokens: 65011712000 | elapsed time per iteration (s): 2.24 | learning rate: 3.136E-05 | global batch size: 512 | lm loss: 1.896104E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.519 | TFLOPs: 23.52 | + 0: steps: 62000 loss: 1.9601 iter time (s): 2.270 samples/sec: 225.536 +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 62000 | lm loss value: 1.838680E+00 | lm loss PPL: 6.288235E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 62010/ 73814 | consumed samples: 31749120 | consumed tokens: 65022197760 | elapsed time per iteration (s): 2.29 | learning rate: 3.134E-05 | global batch size: 512 | lm loss: 1.896750E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.838 | TFLOPs: 23.04 | +63: iteration 62020/ 73814 | consumed samples: 31754240 | consumed tokens: 65032683520 | elapsed time per iteration (s): 2.23 | learning rate: 3.132E-05 | global batch size: 512 | lm loss: 1.897715E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.325 | TFLOPs: 23.61 | +63: iteration 62030/ 73814 | consumed samples: 31759360 | consumed tokens: 65043169280 | elapsed time per iteration (s): 2.22 | learning rate: 3.130E-05 | global batch size: 512 | lm loss: 1.926208E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.243 | TFLOPs: 23.70 | +63: iteration 62040/ 73814 | consumed samples: 31764480 | consumed tokens: 65053655040 | elapsed time per iteration (s): 2.22 | learning rate: 3.129E-05 | global batch size: 512 | lm loss: 1.914902E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.245 | TFLOPs: 23.70 | +63: iteration 62050/ 73814 | consumed samples: 31769600 | consumed tokens: 65064140800 | elapsed time per iteration (s): 2.35 | learning rate: 3.127E-05 | global batch size: 512 | lm loss: 1.907178E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.101 | TFLOPs: 22.45 | +63: iteration 62060/ 73814 | consumed samples: 31774720 | consumed tokens: 65074626560 | elapsed time per iteration (s): 4.10 | learning rate: 3.125E-05 | global batch size: 512 | lm loss: 1.874046E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 125.018 | TFLOPs: 12.87 | +63: iteration 62070/ 73814 | consumed samples: 31779840 | consumed tokens: 65085112320 | elapsed time per iteration (s): 2.25 | learning rate: 3.123E-05 | global batch size: 512 | lm loss: 1.881541E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.447 | TFLOPs: 23.41 | +63: iteration 62080/ 73814 | consumed samples: 31784960 | consumed tokens: 65095598080 | elapsed time per iteration (s): 2.23 | learning rate: 3.121E-05 | global batch size: 512 | lm loss: 1.893804E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.063 | TFLOPs: 23.68 | +63: iteration 62090/ 73814 | consumed samples: 31790080 | consumed tokens: 65106083840 | elapsed time per iteration (s): 2.23 | learning rate: 3.119E-05 | global batch size: 512 | lm loss: 1.891704E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.319 | TFLOPs: 23.61 | +63: iteration 62100/ 73814 | consumed samples: 31795200 | consumed tokens: 65116569600 | elapsed time per iteration (s): 2.24 | learning rate: 3.117E-05 | global batch size: 512 | lm loss: 1.883937E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.761 | TFLOPs: 23.55 | +63: iteration 62110/ 73814 | consumed samples: 31800320 | consumed tokens: 65127055360 | elapsed time per iteration (s): 2.23 | learning rate: 3.116E-05 | global batch size: 512 | lm loss: 1.901822E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.348 | TFLOPs: 23.61 | +63: iteration 62120/ 73814 | consumed samples: 31805440 | consumed tokens: 65137541120 | elapsed time per iteration (s): 2.23 | learning rate: 3.114E-05 | global batch size: 512 | lm loss: 1.898702E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.951 | TFLOPs: 23.67 | +63: iteration 62130/ 73814 | consumed samples: 31810560 | consumed tokens: 65148026880 | elapsed time per iteration (s): 2.41 | learning rate: 3.112E-05 | global batch size: 512 | lm loss: 1.920220E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.220 | TFLOPs: 21.85 | +63: iteration 62140/ 73814 | consumed samples: 31815680 | consumed tokens: 65158512640 | elapsed time per iteration (s): 2.23 | learning rate: 3.110E-05 | global batch size: 512 | lm loss: 1.906727E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.492 | TFLOPs: 23.63 | +63: iteration 62150/ 73814 | consumed samples: 31820800 | consumed tokens: 65168998400 | elapsed time per iteration (s): 2.23 | learning rate: 3.108E-05 | global batch size: 512 | lm loss: 1.897110E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.986 | TFLOPs: 23.68 | +63: iteration 62160/ 73814 | consumed samples: 31825920 | consumed tokens: 65179484160 | elapsed time per iteration (s): 2.24 | learning rate: 3.106E-05 | global batch size: 512 | lm loss: 1.907928E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.200 | TFLOPs: 23.49 | +63: iteration 62170/ 73814 | consumed samples: 31831040 | consumed tokens: 65189969920 | elapsed time per iteration (s): 2.38 | learning rate: 3.104E-05 | global batch size: 512 | lm loss: 1.899128E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.115 | TFLOPs: 22.15 | +63: iteration 62180/ 73814 | consumed samples: 31836160 | consumed tokens: 65200455680 | elapsed time per iteration (s): 2.28 | learning rate: 3.102E-05 | global batch size: 512 | lm loss: 1.883421E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.997 | TFLOPs: 23.16 | +63: iteration 62190/ 73814 | consumed samples: 31841280 | consumed tokens: 65210941440 | elapsed time per iteration (s): 2.25 | learning rate: 3.101E-05 | global batch size: 512 | lm loss: 1.901688E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.973 | TFLOPs: 23.47 | +63: iteration 62200/ 73814 | consumed samples: 31846400 | consumed tokens: 65221427200 | elapsed time per iteration (s): 2.23 | learning rate: 3.099E-05 | global batch size: 512 | lm loss: 1.904698E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.695 | TFLOPs: 23.65 | +63: iteration 62210/ 73814 | consumed samples: 31851520 | consumed tokens: 65231912960 | elapsed time per iteration (s): 2.52 | learning rate: 3.097E-05 | global batch size: 512 | lm loss: 1.894864E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 203.262 | TFLOPs: 20.92 | +63: iteration 62220/ 73814 | consumed samples: 31856640 | consumed tokens: 65242398720 | elapsed time per iteration (s): 2.30 | learning rate: 3.095E-05 | global batch size: 512 | lm loss: 1.912639E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.925 | TFLOPs: 22.95 | +63: iteration 62230/ 73814 | consumed samples: 31861760 | consumed tokens: 65252884480 | elapsed time per iteration (s): 2.26 | learning rate: 3.093E-05 | global batch size: 512 | lm loss: 1.886473E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.821 | TFLOPs: 23.35 | +63: iteration 62240/ 73814 | consumed samples: 31866880 | consumed tokens: 65263370240 | elapsed time per iteration (s): 2.23 | learning rate: 3.091E-05 | global batch size: 512 | lm loss: 1.879435E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.374 | TFLOPs: 23.61 | +63: iteration 62250/ 73814 | consumed samples: 31872000 | consumed tokens: 65273856000 | elapsed time per iteration (s): 2.23 | learning rate: 3.090E-05 | global batch size: 512 | lm loss: 1.891171E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.444 | TFLOPs: 23.62 | +63: iteration 62260/ 73814 | consumed samples: 31877120 | consumed tokens: 65284341760 | elapsed time per iteration (s): 2.23 | learning rate: 3.088E-05 | global batch size: 512 | lm loss: 1.886226E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.938 | TFLOPs: 23.67 | +63: iteration 62270/ 73814 | consumed samples: 31882240 | consumed tokens: 65294827520 | elapsed time per iteration (s): 2.24 | learning rate: 3.086E-05 | global batch size: 512 | lm loss: 1.886751E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.725 | TFLOPs: 23.55 | +63: iteration 62280/ 73814 | consumed samples: 31887360 | consumed tokens: 65305313280 | elapsed time per iteration (s): 2.25 | learning rate: 3.084E-05 | global batch size: 512 | lm loss: 1.912257E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.979 | TFLOPs: 23.47 | +63: iteration 62290/ 73814 | consumed samples: 31892480 | consumed tokens: 65315799040 | elapsed time per iteration (s): 2.37 | learning rate: 3.082E-05 | global batch size: 512 | lm loss: 1.915805E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.809 | TFLOPs: 22.22 | +63: iteration 62300/ 73814 | consumed samples: 31897600 | consumed tokens: 65326284800 | elapsed time per iteration (s): 2.22 | learning rate: 3.080E-05 | global batch size: 512 | lm loss: 1.883312E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.283 | TFLOPs: 23.71 | +63: iteration 62310/ 73814 | consumed samples: 31902720 | consumed tokens: 65336770560 | elapsed time per iteration (s): 2.24 | learning rate: 3.078E-05 | global batch size: 512 | lm loss: 1.894009E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.499 | TFLOPs: 23.52 | +63: iteration 62320/ 73814 | consumed samples: 31907840 | consumed tokens: 65347256320 | elapsed time per iteration (s): 2.23 | learning rate: 3.077E-05 | global batch size: 512 | lm loss: 1.909693E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.311 | TFLOPs: 23.61 | +63: iteration 62330/ 73814 | consumed samples: 31912960 | consumed tokens: 65357742080 | elapsed time per iteration (s): 2.25 | learning rate: 3.075E-05 | global batch size: 512 | lm loss: 1.908893E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.860 | TFLOPs: 23.46 | +63: iteration 62340/ 73814 | consumed samples: 31918080 | consumed tokens: 65368227840 | elapsed time per iteration (s): 2.23 | learning rate: 3.073E-05 | global batch size: 512 | lm loss: 1.903454E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.609 | TFLOPs: 23.64 | +63: iteration 62350/ 73814 | consumed samples: 31923200 | consumed tokens: 65378713600 | elapsed time per iteration (s): 2.23 | learning rate: 3.071E-05 | global batch size: 512 | lm loss: 1.887870E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.959 | TFLOPs: 23.67 | +63: iteration 62360/ 73814 | consumed samples: 31928320 | consumed tokens: 65389199360 | elapsed time per iteration (s): 2.24 | learning rate: 3.069E-05 | global batch size: 512 | lm loss: 1.901109E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.248 | TFLOPs: 23.50 | +63: iteration 62370/ 73814 | consumed samples: 31933440 | consumed tokens: 65399685120 | elapsed time per iteration (s): 2.23 | learning rate: 3.067E-05 | global batch size: 512 | lm loss: 1.878318E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.606 | TFLOPs: 23.64 | +63: iteration 62380/ 73814 | consumed samples: 31938560 | consumed tokens: 65410170880 | elapsed time per iteration (s): 2.22 | learning rate: 3.066E-05 | global batch size: 512 | lm loss: 1.902681E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.216 | TFLOPs: 23.70 | +63: iteration 62390/ 73814 | consumed samples: 31943680 | consumed tokens: 65420656640 | elapsed time per iteration (s): 2.25 | learning rate: 3.064E-05 | global batch size: 512 | lm loss: 1.912914E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.964 | TFLOPs: 23.47 | +63: iteration 62400/ 73814 | consumed samples: 31948800 | consumed tokens: 65431142400 | elapsed time per iteration (s): 2.36 | learning rate: 3.062E-05 | global batch size: 512 | lm loss: 1.910703E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.991 | TFLOPs: 22.34 | +63: iteration 62410/ 73814 | consumed samples: 31953920 | consumed tokens: 65441628160 | elapsed time per iteration (s): 2.23 | learning rate: 3.060E-05 | global batch size: 512 | lm loss: 1.896725E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.112 | TFLOPs: 23.59 | +63: iteration 62420/ 73814 | consumed samples: 31959040 | consumed tokens: 65452113920 | elapsed time per iteration (s): 2.36 | learning rate: 3.058E-05 | global batch size: 512 | lm loss: 1.902687E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.593 | TFLOPs: 22.30 | +63: iteration 62430/ 73814 | consumed samples: 31964160 | consumed tokens: 65462599680 | elapsed time per iteration (s): 2.31 | learning rate: 3.057E-05 | global batch size: 512 | lm loss: 1.896650E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.493 | TFLOPs: 22.80 | +63: iteration 62440/ 73814 | consumed samples: 31969280 | consumed tokens: 65473085440 | elapsed time per iteration (s): 2.29 | learning rate: 3.055E-05 | global batch size: 512 | lm loss: 1.903816E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.154 | TFLOPs: 22.97 | +63: iteration 62450/ 73814 | consumed samples: 31974400 | consumed tokens: 65483571200 | elapsed time per iteration (s): 2.23 | learning rate: 3.053E-05 | global batch size: 512 | lm loss: 1.909033E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.172 | TFLOPs: 23.59 | +63: iteration 62460/ 73814 | consumed samples: 31979520 | consumed tokens: 65494056960 | elapsed time per iteration (s): 2.22 | learning rate: 3.051E-05 | global batch size: 512 | lm loss: 1.914293E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.488 | TFLOPs: 23.73 | +63: iteration 62470/ 73814 | consumed samples: 31984640 | consumed tokens: 65504542720 | elapsed time per iteration (s): 2.35 | learning rate: 3.049E-05 | global batch size: 512 | lm loss: 1.897504E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.735 | TFLOPs: 22.41 | +63: iteration 62480/ 73814 | consumed samples: 31989760 | consumed tokens: 65515028480 | elapsed time per iteration (s): 2.37 | learning rate: 3.047E-05 | global batch size: 512 | lm loss: 1.879592E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.430 | TFLOPs: 22.28 | +63: iteration 62490/ 73814 | consumed samples: 31994880 | consumed tokens: 65525514240 | elapsed time per iteration (s): 2.22 | learning rate: 3.046E-05 | global batch size: 512 | lm loss: 1.908865E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.153 | TFLOPs: 23.69 | +63: iteration 62500/ 73814 | consumed samples: 32000000 | consumed tokens: 65536000000 | elapsed time per iteration (s): 2.23 | learning rate: 3.044E-05 | global batch size: 512 | lm loss: 1.897592E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.673 | TFLOPs: 23.64 | +63: iteration 62510/ 73814 | consumed samples: 32005120 | consumed tokens: 65546485760 | elapsed time per iteration (s): 2.32 | learning rate: 3.042E-05 | global batch size: 512 | lm loss: 1.889474E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.518 | TFLOPs: 22.70 | +63: iteration 62520/ 73814 | consumed samples: 32010240 | consumed tokens: 65556971520 | elapsed time per iteration (s): 2.37 | learning rate: 3.040E-05 | global batch size: 512 | lm loss: 1.912590E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.744 | TFLOPs: 22.21 | +63: iteration 62530/ 73814 | consumed samples: 32015360 | consumed tokens: 65567457280 | elapsed time per iteration (s): 2.25 | learning rate: 3.038E-05 | global batch size: 512 | lm loss: 1.891296E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.324 | TFLOPs: 23.40 | +63: iteration 62540/ 73814 | consumed samples: 32020480 | consumed tokens: 65577943040 | elapsed time per iteration (s): 2.38 | learning rate: 3.037E-05 | global batch size: 512 | lm loss: 1.894967E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.108 | TFLOPs: 22.14 | +63: iteration 62550/ 73814 | consumed samples: 32025600 | consumed tokens: 65588428800 | elapsed time per iteration (s): 2.23 | learning rate: 3.035E-05 | global batch size: 512 | lm loss: 1.911486E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.113 | TFLOPs: 23.59 | +63: iteration 62560/ 73814 | consumed samples: 32030720 | consumed tokens: 65598914560 | elapsed time per iteration (s): 2.23 | learning rate: 3.033E-05 | global batch size: 512 | lm loss: 1.890019E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.659 | TFLOPs: 23.64 | +63: iteration 62570/ 73814 | consumed samples: 32035840 | consumed tokens: 65609400320 | elapsed time per iteration (s): 2.23 | learning rate: 3.031E-05 | global batch size: 512 | lm loss: 1.894242E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.828 | TFLOPs: 23.66 | +63: iteration 62580/ 73814 | consumed samples: 32040960 | consumed tokens: 65619886080 | elapsed time per iteration (s): 2.25 | learning rate: 3.029E-05 | global batch size: 512 | lm loss: 1.908279E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.356 | TFLOPs: 23.41 | +63: iteration 62590/ 73814 | consumed samples: 32046080 | consumed tokens: 65630371840 | elapsed time per iteration (s): 2.23 | learning rate: 3.028E-05 | global batch size: 512 | lm loss: 1.892596E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.759 | TFLOPs: 23.65 | +63: iteration 62600/ 73814 | consumed samples: 32051200 | consumed tokens: 65640857600 | elapsed time per iteration (s): 2.23 | learning rate: 3.026E-05 | global batch size: 512 | lm loss: 1.895032E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.736 | TFLOPs: 23.65 | +63: iteration 62610/ 73814 | consumed samples: 32056320 | consumed tokens: 65651343360 | elapsed time per iteration (s): 2.23 | learning rate: 3.024E-05 | global batch size: 512 | lm loss: 1.891024E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.643 | TFLOPs: 23.64 | +63: iteration 62620/ 73814 | consumed samples: 32061440 | consumed tokens: 65661829120 | elapsed time per iteration (s): 2.23 | learning rate: 3.022E-05 | global batch size: 512 | lm loss: 1.902305E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.555 | TFLOPs: 23.63 | +63: iteration 62630/ 73814 | consumed samples: 32066560 | consumed tokens: 65672314880 | elapsed time per iteration (s): 2.33 | learning rate: 3.020E-05 | global batch size: 512 | lm loss: 1.909468E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.925 | TFLOPs: 22.64 | +63: iteration 62640/ 73814 | consumed samples: 32071680 | consumed tokens: 65682800640 | elapsed time per iteration (s): 2.25 | learning rate: 3.019E-05 | global batch size: 512 | lm loss: 1.885886E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.897 | TFLOPs: 23.46 | +63: iteration 62650/ 73814 | consumed samples: 32076800 | consumed tokens: 65693286400 | elapsed time per iteration (s): 2.24 | learning rate: 3.017E-05 | global batch size: 512 | lm loss: 1.896510E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.721 | TFLOPs: 23.55 | +63: iteration 62660/ 73814 | consumed samples: 32081920 | consumed tokens: 65703772160 | elapsed time per iteration (s): 2.25 | learning rate: 3.015E-05 | global batch size: 512 | lm loss: 1.908291E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.085 | TFLOPs: 23.38 | +63: iteration 62670/ 73814 | consumed samples: 32087040 | consumed tokens: 65714257920 | elapsed time per iteration (s): 2.22 | learning rate: 3.013E-05 | global batch size: 512 | lm loss: 1.902377E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.160 | TFLOPs: 23.69 | +63: iteration 62680/ 73814 | consumed samples: 32092160 | consumed tokens: 65724743680 | elapsed time per iteration (s): 2.22 | learning rate: 3.012E-05 | global batch size: 512 | lm loss: 1.915260E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.411 | TFLOPs: 23.72 | +63: iteration 62690/ 73814 | consumed samples: 32097280 | consumed tokens: 65735229440 | elapsed time per iteration (s): 2.25 | learning rate: 3.010E-05 | global batch size: 512 | lm loss: 1.893253E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.008 | TFLOPs: 23.47 | +63: iteration 62700/ 73814 | consumed samples: 32102400 | consumed tokens: 65745715200 | elapsed time per iteration (s): 2.23 | learning rate: 3.008E-05 | global batch size: 512 | lm loss: 1.904950E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.117 | TFLOPs: 23.59 | +63: iteration 62710/ 73814 | consumed samples: 32107520 | consumed tokens: 65756200960 | elapsed time per iteration (s): 2.23 | learning rate: 3.006E-05 | global batch size: 512 | lm loss: 1.900203E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.295 | TFLOPs: 23.60 | +63: iteration 62720/ 73814 | consumed samples: 32112640 | consumed tokens: 65766686720 | elapsed time per iteration (s): 2.23 | learning rate: 3.004E-05 | global batch size: 512 | lm loss: 1.899392E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.165 | TFLOPs: 23.59 | +63: iteration 62730/ 73814 | consumed samples: 32117760 | consumed tokens: 65777172480 | elapsed time per iteration (s): 2.24 | learning rate: 3.003E-05 | global batch size: 512 | lm loss: 1.888472E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.716 | TFLOPs: 23.55 | +63: iteration 62740/ 73814 | consumed samples: 32122880 | consumed tokens: 65787658240 | elapsed time per iteration (s): 2.23 | learning rate: 3.001E-05 | global batch size: 512 | lm loss: 1.907238E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.563 | TFLOPs: 23.63 | +63: iteration 62750/ 73814 | consumed samples: 32128000 | consumed tokens: 65798144000 | elapsed time per iteration (s): 2.22 | learning rate: 2.999E-05 | global batch size: 512 | lm loss: 1.886226E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.370 | TFLOPs: 23.72 | +63: iteration 62760/ 73814 | consumed samples: 32133120 | consumed tokens: 65808629760 | elapsed time per iteration (s): 2.25 | learning rate: 2.997E-05 | global batch size: 512 | lm loss: 1.884090E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.858 | TFLOPs: 23.46 | +63: iteration 62770/ 73814 | consumed samples: 32138240 | consumed tokens: 65819115520 | elapsed time per iteration (s): 2.27 | learning rate: 2.996E-05 | global batch size: 512 | lm loss: 1.905993E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.532 | TFLOPs: 23.22 | +63: iteration 62780/ 73814 | consumed samples: 32143360 | consumed tokens: 65829601280 | elapsed time per iteration (s): 2.41 | learning rate: 2.994E-05 | global batch size: 512 | lm loss: 1.911958E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.770 | TFLOPs: 21.90 | +63: iteration 62790/ 73814 | consumed samples: 32148480 | consumed tokens: 65840087040 | elapsed time per iteration (s): 2.53 | learning rate: 2.992E-05 | global batch size: 512 | lm loss: 1.876629E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.274 | TFLOPs: 20.82 | +63: iteration 62800/ 73814 | consumed samples: 32153600 | consumed tokens: 65850572800 | elapsed time per iteration (s): 2.39 | learning rate: 2.990E-05 | global batch size: 512 | lm loss: 1.908137E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.908 | TFLOPs: 22.02 | +63: iteration 62810/ 73814 | consumed samples: 32158720 | consumed tokens: 65861058560 | elapsed time per iteration (s): 2.35 | learning rate: 2.989E-05 | global batch size: 512 | lm loss: 1.907400E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.789 | TFLOPs: 22.42 | +63: iteration 62820/ 73814 | consumed samples: 32163840 | consumed tokens: 65871544320 | elapsed time per iteration (s): 2.67 | learning rate: 2.987E-05 | global batch size: 512 | lm loss: 1.903205E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 191.645 | TFLOPs: 19.73 | +63: iteration 62830/ 73814 | consumed samples: 32168960 | consumed tokens: 65882030080 | elapsed time per iteration (s): 3.05 | learning rate: 2.985E-05 | global batch size: 512 | lm loss: 1.893053E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 167.667 | TFLOPs: 17.26 | +63: iteration 62840/ 73814 | consumed samples: 32174080 | consumed tokens: 65892515840 | elapsed time per iteration (s): 2.56 | learning rate: 2.983E-05 | global batch size: 512 | lm loss: 1.886273E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.025 | TFLOPs: 20.59 | +63: iteration 62850/ 73814 | consumed samples: 32179200 | consumed tokens: 65903001600 | elapsed time per iteration (s): 2.27 | learning rate: 2.981E-05 | global batch size: 512 | lm loss: 1.886944E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.284 | TFLOPs: 23.19 | +63: iteration 62860/ 73814 | consumed samples: 32184320 | consumed tokens: 65913487360 | elapsed time per iteration (s): 2.25 | learning rate: 2.980E-05 | global batch size: 512 | lm loss: 1.901985E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.692 | TFLOPs: 23.44 | +63: iteration 62870/ 73814 | consumed samples: 32189440 | consumed tokens: 65923973120 | elapsed time per iteration (s): 2.28 | learning rate: 2.978E-05 | global batch size: 512 | lm loss: 1.893849E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.331 | TFLOPs: 23.09 | +63: iteration 62880/ 73814 | consumed samples: 32194560 | consumed tokens: 65934458880 | elapsed time per iteration (s): 2.32 | learning rate: 2.976E-05 | global batch size: 512 | lm loss: 1.899814E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.370 | TFLOPs: 22.69 | +63: iteration 62890/ 73814 | consumed samples: 32199680 | consumed tokens: 65944944640 | elapsed time per iteration (s): 2.23 | learning rate: 2.974E-05 | global batch size: 512 | lm loss: 1.912393E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.022 | TFLOPs: 23.68 | +63: iteration 62900/ 73814 | consumed samples: 32204800 | consumed tokens: 65955430400 | elapsed time per iteration (s): 2.23 | learning rate: 2.973E-05 | global batch size: 512 | lm loss: 1.894434E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.838 | TFLOPs: 23.66 | +63: iteration 62910/ 73814 | consumed samples: 32209920 | consumed tokens: 65965916160 | elapsed time per iteration (s): 2.29 | learning rate: 2.971E-05 | global batch size: 512 | lm loss: 1.896367E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.277 | TFLOPs: 22.99 | +63: iteration 62920/ 73814 | consumed samples: 32215040 | consumed tokens: 65976401920 | elapsed time per iteration (s): 2.23 | learning rate: 2.969E-05 | global batch size: 512 | lm loss: 1.901855E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.820 | TFLOPs: 23.66 | +63: iteration 62930/ 73814 | consumed samples: 32220160 | consumed tokens: 65986887680 | elapsed time per iteration (s): 2.24 | learning rate: 2.967E-05 | global batch size: 512 | lm loss: 1.907614E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.274 | TFLOPs: 23.50 | +63: iteration 62940/ 73814 | consumed samples: 32225280 | consumed tokens: 65997373440 | elapsed time per iteration (s): 2.56 | learning rate: 2.966E-05 | global batch size: 512 | lm loss: 1.900102E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.978 | TFLOPs: 20.59 | +63: iteration 62950/ 73814 | consumed samples: 32230400 | consumed tokens: 66007859200 | elapsed time per iteration (s): 2.37 | learning rate: 2.964E-05 | global batch size: 512 | lm loss: 1.919953E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.921 | TFLOPs: 22.23 | +63: iteration 62960/ 73814 | consumed samples: 32235520 | consumed tokens: 66018344960 | elapsed time per iteration (s): 2.23 | learning rate: 2.962E-05 | global batch size: 512 | lm loss: 1.902341E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.629 | TFLOPs: 23.64 | +63: iteration 62970/ 73814 | consumed samples: 32240640 | consumed tokens: 66028830720 | elapsed time per iteration (s): 2.25 | learning rate: 2.960E-05 | global batch size: 512 | lm loss: 1.895684E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.897 | TFLOPs: 23.46 | +63: iteration 62980/ 73814 | consumed samples: 32245760 | consumed tokens: 66039316480 | elapsed time per iteration (s): 2.38 | learning rate: 2.959E-05 | global batch size: 512 | lm loss: 1.888177E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.480 | TFLOPs: 22.18 | +63: iteration 62990/ 73814 | consumed samples: 32250880 | consumed tokens: 66049802240 | elapsed time per iteration (s): 2.23 | learning rate: 2.957E-05 | global batch size: 512 | lm loss: 1.898245E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.993 | TFLOPs: 23.68 | +63: iteration 63000/ 73814 | consumed samples: 32256000 | consumed tokens: 66060288000 | elapsed time per iteration (s): 2.22 | learning rate: 2.955E-05 | global batch size: 512 | lm loss: 1.923141E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.145 | TFLOPs: 23.69 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 63000 | lm loss value: 1.901562E+00 | lm loss PPL: 6.696343E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 63010/ 73814 | consumed samples: 32261120 | consumed tokens: 66070773760 | elapsed time per iteration (s): 2.29 | learning rate: 2.954E-05 | global batch size: 512 | lm loss: 1.902055E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.811 | TFLOPs: 23.04 | +63: iteration 63020/ 73814 | consumed samples: 32266240 | consumed tokens: 66081259520 | elapsed time per iteration (s): 4.17 | learning rate: 2.952E-05 | global batch size: 512 | lm loss: 1.876202E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 122.653 | TFLOPs: 12.63 | +63: iteration 63030/ 73814 | consumed samples: 32271360 | consumed tokens: 66091745280 | elapsed time per iteration (s): 2.24 | learning rate: 2.950E-05 | global batch size: 512 | lm loss: 1.906222E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.913 | TFLOPs: 23.57 | +63: iteration 63040/ 73814 | consumed samples: 32276480 | consumed tokens: 66102231040 | elapsed time per iteration (s): 2.23 | learning rate: 2.948E-05 | global batch size: 512 | lm loss: 1.904429E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.566 | TFLOPs: 23.63 | +63: iteration 63050/ 73814 | consumed samples: 32281600 | consumed tokens: 66112716800 | elapsed time per iteration (s): 2.24 | learning rate: 2.947E-05 | global batch size: 512 | lm loss: 1.894063E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.868 | TFLOPs: 23.56 | +63: iteration 63060/ 73814 | consumed samples: 32286720 | consumed tokens: 66123202560 | elapsed time per iteration (s): 2.39 | learning rate: 2.945E-05 | global batch size: 512 | lm loss: 1.922950E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.407 | TFLOPs: 22.07 | +63: iteration 63070/ 73814 | consumed samples: 32291840 | consumed tokens: 66133688320 | elapsed time per iteration (s): 2.25 | learning rate: 2.943E-05 | global batch size: 512 | lm loss: 1.895773E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.785 | TFLOPs: 23.45 | +63: iteration 63080/ 73814 | consumed samples: 32296960 | consumed tokens: 66144174080 | elapsed time per iteration (s): 2.23 | learning rate: 2.941E-05 | global batch size: 512 | lm loss: 1.887626E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.006 | TFLOPs: 23.68 | +63: iteration 63090/ 73814 | consumed samples: 32302080 | consumed tokens: 66154659840 | elapsed time per iteration (s): 2.23 | learning rate: 2.940E-05 | global batch size: 512 | lm loss: 1.881306E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.032 | TFLOPs: 23.68 | +63: iteration 63100/ 73814 | consumed samples: 32307200 | consumed tokens: 66165145600 | elapsed time per iteration (s): 2.24 | learning rate: 2.938E-05 | global batch size: 512 | lm loss: 1.880797E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.520 | TFLOPs: 23.53 | +63: iteration 63110/ 73814 | consumed samples: 32312320 | consumed tokens: 66175631360 | elapsed time per iteration (s): 2.24 | learning rate: 2.936E-05 | global batch size: 512 | lm loss: 1.897185E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.031 | TFLOPs: 23.58 | +63: iteration 63120/ 73814 | consumed samples: 32317440 | consumed tokens: 66186117120 | elapsed time per iteration (s): 2.23 | learning rate: 2.935E-05 | global batch size: 512 | lm loss: 1.916986E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.282 | TFLOPs: 23.60 | +63: iteration 63130/ 73814 | consumed samples: 32322560 | consumed tokens: 66196602880 | elapsed time per iteration (s): 2.36 | learning rate: 2.933E-05 | global batch size: 512 | lm loss: 1.911471E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.141 | TFLOPs: 22.35 | +63: iteration 63140/ 73814 | consumed samples: 32327680 | consumed tokens: 66207088640 | elapsed time per iteration (s): 2.26 | learning rate: 2.931E-05 | global batch size: 512 | lm loss: 1.880612E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.729 | TFLOPs: 23.34 | +63: iteration 63150/ 73814 | consumed samples: 32332800 | consumed tokens: 66217574400 | elapsed time per iteration (s): 2.22 | learning rate: 2.929E-05 | global batch size: 512 | lm loss: 1.905898E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.182 | TFLOPs: 23.70 | +63: iteration 63160/ 73814 | consumed samples: 32337920 | consumed tokens: 66228060160 | elapsed time per iteration (s): 2.33 | learning rate: 2.928E-05 | global batch size: 512 | lm loss: 1.886026E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.297 | TFLOPs: 22.58 | +63: iteration 63170/ 73814 | consumed samples: 32343040 | consumed tokens: 66238545920 | elapsed time per iteration (s): 2.23 | learning rate: 2.926E-05 | global batch size: 512 | lm loss: 1.917641E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.485 | TFLOPs: 23.62 | +63: iteration 63180/ 73814 | consumed samples: 32348160 | consumed tokens: 66249031680 | elapsed time per iteration (s): 2.23 | learning rate: 2.924E-05 | global batch size: 512 | lm loss: 1.875162E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.335 | TFLOPs: 23.61 | +63: iteration 63190/ 73814 | consumed samples: 32353280 | consumed tokens: 66259517440 | elapsed time per iteration (s): 2.23 | learning rate: 2.923E-05 | global batch size: 512 | lm loss: 1.909154E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.882 | TFLOPs: 23.67 | +63: iteration 63200/ 73814 | consumed samples: 32358400 | consumed tokens: 66270003200 | elapsed time per iteration (s): 2.24 | learning rate: 2.921E-05 | global batch size: 512 | lm loss: 1.920327E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.156 | TFLOPs: 23.49 | +63: iteration 63210/ 73814 | consumed samples: 32363520 | consumed tokens: 66280488960 | elapsed time per iteration (s): 2.25 | learning rate: 2.919E-05 | global batch size: 512 | lm loss: 1.878306E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.686 | TFLOPs: 23.44 | +63: iteration 63220/ 73814 | consumed samples: 32368640 | consumed tokens: 66290974720 | elapsed time per iteration (s): 2.23 | learning rate: 2.917E-05 | global batch size: 512 | lm loss: 1.900938E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.007 | TFLOPs: 23.68 | +63: iteration 63230/ 73814 | consumed samples: 32373760 | consumed tokens: 66301460480 | elapsed time per iteration (s): 2.24 | learning rate: 2.916E-05 | global batch size: 512 | lm loss: 1.898531E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.657 | TFLOPs: 23.54 | +63: iteration 63240/ 73814 | consumed samples: 32378880 | consumed tokens: 66311946240 | elapsed time per iteration (s): 2.23 | learning rate: 2.914E-05 | global batch size: 512 | lm loss: 1.910880E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.963 | TFLOPs: 23.67 | +63: iteration 63250/ 73814 | consumed samples: 32384000 | consumed tokens: 66322432000 | elapsed time per iteration (s): 2.23 | learning rate: 2.912E-05 | global batch size: 512 | lm loss: 1.884676E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.716 | TFLOPs: 23.65 | +63: iteration 63260/ 73814 | consumed samples: 32389120 | consumed tokens: 66332917760 | elapsed time per iteration (s): 2.23 | learning rate: 2.911E-05 | global batch size: 512 | lm loss: 1.881530E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.864 | TFLOPs: 23.66 | +63: iteration 63270/ 73814 | consumed samples: 32394240 | consumed tokens: 66343403520 | elapsed time per iteration (s): 2.23 | learning rate: 2.909E-05 | global batch size: 512 | lm loss: 1.913443E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.369 | TFLOPs: 23.61 | +63: iteration 63280/ 73814 | consumed samples: 32399360 | consumed tokens: 66353889280 | elapsed time per iteration (s): 2.23 | learning rate: 2.907E-05 | global batch size: 512 | lm loss: 1.885112E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.221 | TFLOPs: 23.60 | +63: iteration 63290/ 73814 | consumed samples: 32404480 | consumed tokens: 66364375040 | elapsed time per iteration (s): 2.24 | learning rate: 2.906E-05 | global batch size: 512 | lm loss: 1.913354E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.641 | TFLOPs: 23.54 | +63: iteration 63300/ 73814 | consumed samples: 32409600 | consumed tokens: 66374860800 | elapsed time per iteration (s): 2.24 | learning rate: 2.904E-05 | global batch size: 512 | lm loss: 1.884100E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.937 | TFLOPs: 23.57 | +63: iteration 63310/ 73814 | consumed samples: 32414720 | consumed tokens: 66385346560 | elapsed time per iteration (s): 2.23 | learning rate: 2.902E-05 | global batch size: 512 | lm loss: 1.893311E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.791 | TFLOPs: 23.66 | +63: iteration 63320/ 73814 | consumed samples: 32419840 | consumed tokens: 66395832320 | elapsed time per iteration (s): 2.26 | learning rate: 2.901E-05 | global batch size: 512 | lm loss: 1.881688E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.376 | TFLOPs: 23.30 | +63: iteration 63330/ 73814 | consumed samples: 32424960 | consumed tokens: 66406318080 | elapsed time per iteration (s): 2.33 | learning rate: 2.899E-05 | global batch size: 512 | lm loss: 1.900048E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.811 | TFLOPs: 22.63 | +63: iteration 63340/ 73814 | consumed samples: 32430080 | consumed tokens: 66416803840 | elapsed time per iteration (s): 2.23 | learning rate: 2.897E-05 | global batch size: 512 | lm loss: 1.907600E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.278 | TFLOPs: 23.60 | +63: iteration 63350/ 73814 | consumed samples: 32435200 | consumed tokens: 66427289600 | elapsed time per iteration (s): 2.24 | learning rate: 2.895E-05 | global batch size: 512 | lm loss: 1.900114E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.056 | TFLOPs: 23.58 | +63: iteration 63360/ 73814 | consumed samples: 32440320 | consumed tokens: 66437775360 | elapsed time per iteration (s): 2.23 | learning rate: 2.894E-05 | global batch size: 512 | lm loss: 1.881928E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.213 | TFLOPs: 23.60 | +63: iteration 63370/ 73814 | consumed samples: 32445440 | consumed tokens: 66448261120 | elapsed time per iteration (s): 2.22 | learning rate: 2.892E-05 | global batch size: 512 | lm loss: 1.895423E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.465 | TFLOPs: 23.73 | +63: iteration 63380/ 73814 | consumed samples: 32450560 | consumed tokens: 66458746880 | elapsed time per iteration (s): 2.25 | learning rate: 2.890E-05 | global batch size: 512 | lm loss: 1.898651E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.674 | TFLOPs: 23.44 | +63: iteration 63390/ 73814 | consumed samples: 32455680 | consumed tokens: 66469232640 | elapsed time per iteration (s): 2.23 | learning rate: 2.889E-05 | global batch size: 512 | lm loss: 1.878928E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.660 | TFLOPs: 23.64 | +63: iteration 63400/ 73814 | consumed samples: 32460800 | consumed tokens: 66479718400 | elapsed time per iteration (s): 2.24 | learning rate: 2.887E-05 | global batch size: 512 | lm loss: 1.894161E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.281 | TFLOPs: 23.50 | +63: iteration 63410/ 73814 | consumed samples: 32465920 | consumed tokens: 66490204160 | elapsed time per iteration (s): 2.23 | learning rate: 2.885E-05 | global batch size: 512 | lm loss: 1.877585E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.923 | TFLOPs: 23.67 | +63: iteration 63420/ 73814 | consumed samples: 32471040 | consumed tokens: 66500689920 | elapsed time per iteration (s): 2.28 | learning rate: 2.884E-05 | global batch size: 512 | lm loss: 1.891418E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.926 | TFLOPs: 23.16 | +63: iteration 63430/ 73814 | consumed samples: 32476160 | consumed tokens: 66511175680 | elapsed time per iteration (s): 2.25 | learning rate: 2.882E-05 | global batch size: 512 | lm loss: 1.900737E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.718 | TFLOPs: 23.44 | +63: iteration 63440/ 73814 | consumed samples: 32481280 | consumed tokens: 66521661440 | elapsed time per iteration (s): 2.47 | learning rate: 2.880E-05 | global batch size: 512 | lm loss: 1.884881E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 206.931 | TFLOPs: 21.30 | +63: iteration 63450/ 73814 | consumed samples: 32486400 | consumed tokens: 66532147200 | elapsed time per iteration (s): 2.25 | learning rate: 2.879E-05 | global batch size: 512 | lm loss: 1.915483E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.703 | TFLOPs: 23.44 | +63: iteration 63460/ 73814 | consumed samples: 32491520 | consumed tokens: 66542632960 | elapsed time per iteration (s): 2.24 | learning rate: 2.877E-05 | global batch size: 512 | lm loss: 1.888260E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.857 | TFLOPs: 23.56 | +63: iteration 63470/ 73814 | consumed samples: 32496640 | consumed tokens: 66553118720 | elapsed time per iteration (s): 2.23 | learning rate: 2.875E-05 | global batch size: 512 | lm loss: 1.921861E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.567 | TFLOPs: 23.63 | +63: iteration 63480/ 73814 | consumed samples: 32501760 | consumed tokens: 66563604480 | elapsed time per iteration (s): 2.22 | learning rate: 2.874E-05 | global batch size: 512 | lm loss: 1.879427E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.285 | TFLOPs: 23.71 | +63: iteration 63490/ 73814 | consumed samples: 32506880 | consumed tokens: 66574090240 | elapsed time per iteration (s): 2.39 | learning rate: 2.872E-05 | global batch size: 512 | lm loss: 1.916410E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.582 | TFLOPs: 22.09 | +63: iteration 63500/ 73814 | consumed samples: 32512000 | consumed tokens: 66584576000 | elapsed time per iteration (s): 2.23 | learning rate: 2.870E-05 | global batch size: 512 | lm loss: 1.891063E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.553 | TFLOPs: 23.63 | +63: iteration 63510/ 73814 | consumed samples: 32517120 | consumed tokens: 66595061760 | elapsed time per iteration (s): 2.23 | learning rate: 2.869E-05 | global batch size: 512 | lm loss: 1.901916E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.862 | TFLOPs: 23.66 | +63: iteration 63520/ 73814 | consumed samples: 32522240 | consumed tokens: 66605547520 | elapsed time per iteration (s): 2.23 | learning rate: 2.867E-05 | global batch size: 512 | lm loss: 1.890888E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.105 | TFLOPs: 23.59 | +63: iteration 63530/ 73814 | consumed samples: 32527360 | consumed tokens: 66616033280 | elapsed time per iteration (s): 2.24 | learning rate: 2.865E-05 | global batch size: 512 | lm loss: 1.931168E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.491 | TFLOPs: 23.52 | +63: iteration 63540/ 73814 | consumed samples: 32532480 | consumed tokens: 66626519040 | elapsed time per iteration (s): 2.36 | learning rate: 2.864E-05 | global batch size: 512 | lm loss: 1.928187E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.788 | TFLOPs: 22.32 | +63: iteration 63550/ 73814 | consumed samples: 32537600 | consumed tokens: 66637004800 | elapsed time per iteration (s): 2.23 | learning rate: 2.862E-05 | global batch size: 512 | lm loss: 1.901129E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.898 | TFLOPs: 23.67 | +63: iteration 63560/ 73814 | consumed samples: 32542720 | consumed tokens: 66647490560 | elapsed time per iteration (s): 2.23 | learning rate: 2.860E-05 | global batch size: 512 | lm loss: 1.888434E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.766 | TFLOPs: 23.65 | +63: iteration 63570/ 73814 | consumed samples: 32547840 | consumed tokens: 66657976320 | elapsed time per iteration (s): 2.26 | learning rate: 2.859E-05 | global batch size: 512 | lm loss: 1.921012E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.732 | TFLOPs: 23.34 | +63: iteration 63580/ 73814 | consumed samples: 32552960 | consumed tokens: 66668462080 | elapsed time per iteration (s): 2.24 | learning rate: 2.857E-05 | global batch size: 512 | lm loss: 1.903363E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.722 | TFLOPs: 23.55 | +63: iteration 63590/ 73814 | consumed samples: 32558080 | consumed tokens: 66678947840 | elapsed time per iteration (s): 2.23 | learning rate: 2.856E-05 | global batch size: 512 | lm loss: 1.872662E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.868 | TFLOPs: 23.66 | +63: iteration 63600/ 73814 | consumed samples: 32563200 | consumed tokens: 66689433600 | elapsed time per iteration (s): 2.23 | learning rate: 2.854E-05 | global batch size: 512 | lm loss: 1.895174E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.461 | TFLOPs: 23.62 | +63: iteration 63610/ 73814 | consumed samples: 32568320 | consumed tokens: 66699919360 | elapsed time per iteration (s): 2.26 | learning rate: 2.852E-05 | global batch size: 512 | lm loss: 1.897194E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.007 | TFLOPs: 23.37 | +63: iteration 63620/ 73814 | consumed samples: 32573440 | consumed tokens: 66710405120 | elapsed time per iteration (s): 2.25 | learning rate: 2.851E-05 | global batch size: 512 | lm loss: 1.899533E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.932 | TFLOPs: 23.46 | +63: iteration 63630/ 73814 | consumed samples: 32578560 | consumed tokens: 66720890880 | elapsed time per iteration (s): 2.24 | learning rate: 2.849E-05 | global batch size: 512 | lm loss: 1.874602E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.092 | TFLOPs: 23.48 | +63: iteration 63640/ 73814 | consumed samples: 32583680 | consumed tokens: 66731376640 | elapsed time per iteration (s): 2.35 | learning rate: 2.847E-05 | global batch size: 512 | lm loss: 1.908560E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.586 | TFLOPs: 22.40 | +63: iteration 63650/ 73814 | consumed samples: 32588800 | consumed tokens: 66741862400 | elapsed time per iteration (s): 2.24 | learning rate: 2.846E-05 | global batch size: 512 | lm loss: 1.881381E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.250 | TFLOPs: 23.50 | +63: iteration 63660/ 73814 | consumed samples: 32593920 | consumed tokens: 66752348160 | elapsed time per iteration (s): 2.24 | learning rate: 2.844E-05 | global batch size: 512 | lm loss: 1.916745E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.659 | TFLOPs: 23.54 | +63: iteration 63670/ 73814 | consumed samples: 32599040 | consumed tokens: 66762833920 | elapsed time per iteration (s): 2.35 | learning rate: 2.842E-05 | global batch size: 512 | lm loss: 1.884969E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.893 | TFLOPs: 22.43 | +63: iteration 63680/ 73814 | consumed samples: 32604160 | consumed tokens: 66773319680 | elapsed time per iteration (s): 2.23 | learning rate: 2.841E-05 | global batch size: 512 | lm loss: 1.889938E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.588 | TFLOPs: 23.64 | +63: iteration 63690/ 73814 | consumed samples: 32609280 | consumed tokens: 66783805440 | elapsed time per iteration (s): 2.23 | learning rate: 2.839E-05 | global batch size: 512 | lm loss: 1.899398E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.772 | TFLOPs: 23.65 | +63: iteration 63700/ 73814 | consumed samples: 32614400 | consumed tokens: 66794291200 | elapsed time per iteration (s): 2.25 | learning rate: 2.838E-05 | global batch size: 512 | lm loss: 1.891243E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.609 | TFLOPs: 23.43 | +63: iteration 63710/ 73814 | consumed samples: 32619520 | consumed tokens: 66804776960 | elapsed time per iteration (s): 2.23 | learning rate: 2.836E-05 | global batch size: 512 | lm loss: 1.882688E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.069 | TFLOPs: 23.68 | +63: iteration 63720/ 73814 | consumed samples: 32624640 | consumed tokens: 66815262720 | elapsed time per iteration (s): 2.24 | learning rate: 2.834E-05 | global batch size: 512 | lm loss: 1.889739E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.572 | TFLOPs: 23.53 | +63: iteration 63730/ 73814 | consumed samples: 32629760 | consumed tokens: 66825748480 | elapsed time per iteration (s): 2.23 | learning rate: 2.833E-05 | global batch size: 512 | lm loss: 1.888370E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.563 | TFLOPs: 23.63 | +63: iteration 63740/ 73814 | consumed samples: 32634880 | consumed tokens: 66836234240 | elapsed time per iteration (s): 2.26 | learning rate: 2.831E-05 | global batch size: 512 | lm loss: 1.895474E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.302 | TFLOPs: 23.30 | +63: iteration 63750/ 73814 | consumed samples: 32640000 | consumed tokens: 66846720000 | elapsed time per iteration (s): 2.36 | learning rate: 2.829E-05 | global batch size: 512 | lm loss: 1.907038E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.883 | TFLOPs: 22.33 | +63: iteration 63760/ 73814 | consumed samples: 32645120 | consumed tokens: 66857205760 | elapsed time per iteration (s): 2.23 | learning rate: 2.828E-05 | global batch size: 512 | lm loss: 1.901601E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.346 | TFLOPs: 23.61 | +63: iteration 63770/ 73814 | consumed samples: 32650240 | consumed tokens: 66867691520 | elapsed time per iteration (s): 2.22 | learning rate: 2.826E-05 | global batch size: 512 | lm loss: 1.898274E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.263 | TFLOPs: 23.70 | +63: iteration 63780/ 73814 | consumed samples: 32655360 | consumed tokens: 66878177280 | elapsed time per iteration (s): 2.24 | learning rate: 2.825E-05 | global batch size: 512 | lm loss: 1.911225E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.310 | TFLOPs: 23.50 | +63: iteration 63790/ 73814 | consumed samples: 32660480 | consumed tokens: 66888663040 | elapsed time per iteration (s): 2.25 | learning rate: 2.823E-05 | global batch size: 512 | lm loss: 1.879739E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.972 | TFLOPs: 23.47 | +63: iteration 63800/ 73814 | consumed samples: 32665600 | consumed tokens: 66899148800 | elapsed time per iteration (s): 2.28 | learning rate: 2.821E-05 | global batch size: 512 | lm loss: 1.900891E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.967 | TFLOPs: 23.16 | +63: iteration 63810/ 73814 | consumed samples: 32670720 | consumed tokens: 66909634560 | elapsed time per iteration (s): 2.24 | learning rate: 2.820E-05 | global batch size: 512 | lm loss: 1.901690E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.863 | TFLOPs: 23.56 | +63: iteration 63820/ 73814 | consumed samples: 32675840 | consumed tokens: 66920120320 | elapsed time per iteration (s): 2.22 | learning rate: 2.818E-05 | global batch size: 512 | lm loss: 1.905517E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.296 | TFLOPs: 23.71 | +63: iteration 63830/ 73814 | consumed samples: 32680960 | consumed tokens: 66930606080 | elapsed time per iteration (s): 2.23 | learning rate: 2.816E-05 | global batch size: 512 | lm loss: 1.902277E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.422 | TFLOPs: 23.62 | +63: iteration 63840/ 73814 | consumed samples: 32686080 | consumed tokens: 66941091840 | elapsed time per iteration (s): 2.30 | learning rate: 2.815E-05 | global batch size: 512 | lm loss: 1.906503E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.821 | TFLOPs: 22.94 | +63: iteration 63850/ 73814 | consumed samples: 32691200 | consumed tokens: 66951577600 | elapsed time per iteration (s): 2.24 | learning rate: 2.813E-05 | global batch size: 512 | lm loss: 1.898149E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.861 | TFLOPs: 23.56 | +63: iteration 63860/ 73814 | consumed samples: 32696320 | consumed tokens: 66962063360 | elapsed time per iteration (s): 2.25 | learning rate: 2.812E-05 | global batch size: 512 | lm loss: 1.898564E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.939 | TFLOPs: 23.47 | +63: iteration 63870/ 73814 | consumed samples: 32701440 | consumed tokens: 66972549120 | elapsed time per iteration (s): 2.24 | learning rate: 2.810E-05 | global batch size: 512 | lm loss: 1.880263E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.756 | TFLOPs: 23.55 | +63: iteration 63880/ 73814 | consumed samples: 32706560 | consumed tokens: 66983034880 | elapsed time per iteration (s): 2.37 | learning rate: 2.808E-05 | global batch size: 512 | lm loss: 1.890696E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.257 | TFLOPs: 22.26 | +63: iteration 63890/ 73814 | consumed samples: 32711680 | consumed tokens: 66993520640 | elapsed time per iteration (s): 2.24 | learning rate: 2.807E-05 | global batch size: 512 | lm loss: 1.882626E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.075 | TFLOPs: 23.48 | +63: iteration 63900/ 73814 | consumed samples: 32716800 | consumed tokens: 67004006400 | elapsed time per iteration (s): 2.23 | learning rate: 2.805E-05 | global batch size: 512 | lm loss: 1.890890E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.193 | TFLOPs: 23.59 | +63: iteration 63910/ 73814 | consumed samples: 32721920 | consumed tokens: 67014492160 | elapsed time per iteration (s): 2.25 | learning rate: 2.804E-05 | global batch size: 512 | lm loss: 1.888498E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.473 | TFLOPs: 23.42 | +63: iteration 63920/ 73814 | consumed samples: 32727040 | consumed tokens: 67024977920 | elapsed time per iteration (s): 2.86 | learning rate: 2.802E-05 | global batch size: 512 | lm loss: 1.909607E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 179.156 | TFLOPs: 18.44 | +63: iteration 63930/ 73814 | consumed samples: 32732160 | consumed tokens: 67035463680 | elapsed time per iteration (s): 2.23 | learning rate: 2.800E-05 | global batch size: 512 | lm loss: 1.879473E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.191 | TFLOPs: 23.59 | +63: iteration 63940/ 73814 | consumed samples: 32737280 | consumed tokens: 67045949440 | elapsed time per iteration (s): 2.29 | learning rate: 2.799E-05 | global batch size: 512 | lm loss: 1.908179E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.446 | TFLOPs: 23.00 | +63: iteration 63950/ 73814 | consumed samples: 32742400 | consumed tokens: 67056435200 | elapsed time per iteration (s): 2.23 | learning rate: 2.797E-05 | global batch size: 512 | lm loss: 1.892979E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.719 | TFLOPs: 23.65 | +63: iteration 63960/ 73814 | consumed samples: 32747520 | consumed tokens: 67066920960 | elapsed time per iteration (s): 2.24 | learning rate: 2.796E-05 | global batch size: 512 | lm loss: 1.892197E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.015 | TFLOPs: 23.58 | +63: iteration 63970/ 73814 | consumed samples: 32752640 | consumed tokens: 67077406720 | elapsed time per iteration (s): 2.23 | learning rate: 2.794E-05 | global batch size: 512 | lm loss: 1.852011E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.450 | TFLOPs: 23.62 | +63: iteration 63980/ 73814 | consumed samples: 32757760 | consumed tokens: 67087892480 | elapsed time per iteration (s): 2.24 | learning rate: 2.792E-05 | global batch size: 512 | lm loss: 1.899042E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.688 | TFLOPs: 23.54 | +63: iteration 63990/ 73814 | consumed samples: 32762880 | consumed tokens: 67098378240 | elapsed time per iteration (s): 2.44 | learning rate: 2.791E-05 | global batch size: 512 | lm loss: 1.900100E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.695 | TFLOPs: 21.59 | + 0: [2022-12-03 04:32:13,219] [INFO] [logging.py:68:log_dist] [Rank 0] step=64000, skipped=0, lr=[2.7892856476443495e-05, 2.7892856476443495e-05, 2.7892856476443495e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 64000/ 73814 | consumed samples: 32768000 | consumed tokens: 67108864000 | elapsed time per iteration (s): 2.25 | learning rate: 2.789E-05 | global batch size: 512 | lm loss: 1.888042E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.979 | TFLOPs: 23.47 | + 0: steps: 64000 loss: 1.7672 iter time (s): 2.290 samples/sec: 223.606 +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 64000 | lm loss value: 1.781718E+00 | lm loss PPL: 5.940056E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 64010/ 73814 | consumed samples: 32773120 | consumed tokens: 67119349760 | elapsed time per iteration (s): 2.30 | learning rate: 2.788E-05 | global batch size: 512 | lm loss: 1.912301E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.439 | TFLOPs: 22.90 | +63: iteration 64020/ 73814 | consumed samples: 32778240 | consumed tokens: 67129835520 | elapsed time per iteration (s): 2.24 | learning rate: 2.786E-05 | global batch size: 512 | lm loss: 1.897389E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.941 | TFLOPs: 23.57 | +63: iteration 64030/ 73814 | consumed samples: 32783360 | consumed tokens: 67140321280 | elapsed time per iteration (s): 2.25 | learning rate: 2.785E-05 | global batch size: 512 | lm loss: 1.919954E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.284 | TFLOPs: 23.40 | +63: iteration 64040/ 73814 | consumed samples: 32788480 | consumed tokens: 67150807040 | elapsed time per iteration (s): 2.23 | learning rate: 2.783E-05 | global batch size: 512 | lm loss: 1.899480E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.803 | TFLOPs: 23.66 | +63: iteration 64050/ 73814 | consumed samples: 32793600 | consumed tokens: 67161292800 | elapsed time per iteration (s): 2.24 | learning rate: 2.781E-05 | global batch size: 512 | lm loss: 1.882003E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.418 | TFLOPs: 23.51 | +63: iteration 64060/ 73814 | consumed samples: 32798720 | consumed tokens: 67171778560 | elapsed time per iteration (s): 2.35 | learning rate: 2.780E-05 | global batch size: 512 | lm loss: 1.863790E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.742 | TFLOPs: 22.42 | +63: iteration 64070/ 73814 | consumed samples: 32803840 | consumed tokens: 67182264320 | elapsed time per iteration (s): 2.38 | learning rate: 2.778E-05 | global batch size: 512 | lm loss: 1.896224E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.932 | TFLOPs: 22.13 | +63: iteration 64080/ 73814 | consumed samples: 32808960 | consumed tokens: 67192750080 | elapsed time per iteration (s): 2.45 | learning rate: 2.777E-05 | global batch size: 512 | lm loss: 1.901518E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.921 | TFLOPs: 21.51 | +63: iteration 64090/ 73814 | consumed samples: 32814080 | consumed tokens: 67203235840 | elapsed time per iteration (s): 2.24 | learning rate: 2.775E-05 | global batch size: 512 | lm loss: 1.896339E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.794 | TFLOPs: 23.55 | +63: iteration 64100/ 73814 | consumed samples: 32819200 | consumed tokens: 67213721600 | elapsed time per iteration (s): 2.23 | learning rate: 2.774E-05 | global batch size: 512 | lm loss: 1.890441E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.022 | TFLOPs: 23.68 | +63: iteration 64110/ 73814 | consumed samples: 32824320 | consumed tokens: 67224207360 | elapsed time per iteration (s): 2.24 | learning rate: 2.772E-05 | global batch size: 512 | lm loss: 1.893522E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.707 | TFLOPs: 23.54 | +63: iteration 64120/ 73814 | consumed samples: 32829440 | consumed tokens: 67234693120 | elapsed time per iteration (s): 2.23 | learning rate: 2.770E-05 | global batch size: 512 | lm loss: 1.891942E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.977 | TFLOPs: 23.68 | +63: iteration 64130/ 73814 | consumed samples: 32834560 | consumed tokens: 67245178880 | elapsed time per iteration (s): 2.23 | learning rate: 2.769E-05 | global batch size: 512 | lm loss: 1.906271E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.658 | TFLOPs: 23.64 | +63: iteration 64140/ 73814 | consumed samples: 32839680 | consumed tokens: 67255664640 | elapsed time per iteration (s): 2.30 | learning rate: 2.767E-05 | global batch size: 512 | lm loss: 1.915654E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.158 | TFLOPs: 22.87 | +63: iteration 64150/ 73814 | consumed samples: 32844800 | consumed tokens: 67266150400 | elapsed time per iteration (s): 2.22 | learning rate: 2.766E-05 | global batch size: 512 | lm loss: 1.889505E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.217 | TFLOPs: 23.70 | +63: iteration 64160/ 73814 | consumed samples: 32849920 | consumed tokens: 67276636160 | elapsed time per iteration (s): 2.37 | learning rate: 2.764E-05 | global batch size: 512 | lm loss: 1.893736E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.773 | TFLOPs: 22.21 | +63: iteration 64170/ 73814 | consumed samples: 32855040 | consumed tokens: 67287121920 | elapsed time per iteration (s): 2.23 | learning rate: 2.763E-05 | global batch size: 512 | lm loss: 1.890292E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.928 | TFLOPs: 23.67 | +63: iteration 64180/ 73814 | consumed samples: 32860160 | consumed tokens: 67297607680 | elapsed time per iteration (s): 2.56 | learning rate: 2.761E-05 | global batch size: 512 | lm loss: 1.899117E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.794 | TFLOPs: 20.57 | +63: iteration 64190/ 73814 | consumed samples: 32865280 | consumed tokens: 67308093440 | elapsed time per iteration (s): 2.22 | learning rate: 2.759E-05 | global batch size: 512 | lm loss: 1.862989E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.244 | TFLOPs: 23.70 | +63: iteration 64200/ 73814 | consumed samples: 32870400 | consumed tokens: 67318579200 | elapsed time per iteration (s): 2.25 | learning rate: 2.758E-05 | global batch size: 512 | lm loss: 1.876382E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.806 | TFLOPs: 23.45 | +63: iteration 64210/ 73814 | consumed samples: 32875520 | consumed tokens: 67329064960 | elapsed time per iteration (s): 2.23 | learning rate: 2.756E-05 | global batch size: 512 | lm loss: 1.891429E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.323 | TFLOPs: 23.61 | +63: iteration 64220/ 73814 | consumed samples: 32880640 | consumed tokens: 67339550720 | elapsed time per iteration (s): 2.62 | learning rate: 2.755E-05 | global batch size: 512 | lm loss: 1.876443E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 195.241 | TFLOPs: 20.10 | +63: iteration 64230/ 73814 | consumed samples: 32885760 | consumed tokens: 67350036480 | elapsed time per iteration (s): 2.24 | learning rate: 2.753E-05 | global batch size: 512 | lm loss: 1.919471E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.257 | TFLOPs: 23.50 | +63: iteration 64240/ 73814 | consumed samples: 32890880 | consumed tokens: 67360522240 | elapsed time per iteration (s): 2.26 | learning rate: 2.752E-05 | global batch size: 512 | lm loss: 1.901767E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.105 | TFLOPs: 23.28 | +63: iteration 64250/ 73814 | consumed samples: 32896000 | consumed tokens: 67371008000 | elapsed time per iteration (s): 2.36 | learning rate: 2.750E-05 | global batch size: 512 | lm loss: 1.910477E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.540 | TFLOPs: 22.29 | +63: iteration 64260/ 73814 | consumed samples: 32901120 | consumed tokens: 67381493760 | elapsed time per iteration (s): 2.23 | learning rate: 2.749E-05 | global batch size: 512 | lm loss: 1.886925E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.962 | TFLOPs: 23.67 | +63: iteration 64270/ 73814 | consumed samples: 32906240 | consumed tokens: 67391979520 | elapsed time per iteration (s): 2.22 | learning rate: 2.747E-05 | global batch size: 512 | lm loss: 1.893219E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.117 | TFLOPs: 23.69 | +63: iteration 64280/ 73814 | consumed samples: 32911360 | consumed tokens: 67402465280 | elapsed time per iteration (s): 2.25 | learning rate: 2.746E-05 | global batch size: 512 | lm loss: 1.890320E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.065 | TFLOPs: 23.38 | +63: iteration 64290/ 73814 | consumed samples: 32916480 | consumed tokens: 67412951040 | elapsed time per iteration (s): 2.24 | learning rate: 2.744E-05 | global batch size: 512 | lm loss: 1.872971E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.735 | TFLOPs: 23.55 | +63: iteration 64300/ 73814 | consumed samples: 32921600 | consumed tokens: 67423436800 | elapsed time per iteration (s): 2.22 | learning rate: 2.742E-05 | global batch size: 512 | lm loss: 1.891548E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.512 | TFLOPs: 23.73 | +63: iteration 64310/ 73814 | consumed samples: 32926720 | consumed tokens: 67433922560 | elapsed time per iteration (s): 2.22 | learning rate: 2.741E-05 | global batch size: 512 | lm loss: 1.877846E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.194 | TFLOPs: 23.70 | +63: iteration 64320/ 73814 | consumed samples: 32931840 | consumed tokens: 67444408320 | elapsed time per iteration (s): 2.24 | learning rate: 2.739E-05 | global batch size: 512 | lm loss: 1.873219E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.384 | TFLOPs: 23.51 | +63: iteration 64330/ 73814 | consumed samples: 32936960 | consumed tokens: 67454894080 | elapsed time per iteration (s): 2.24 | learning rate: 2.738E-05 | global batch size: 512 | lm loss: 1.900772E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.427 | TFLOPs: 23.52 | +63: iteration 64340/ 73814 | consumed samples: 32942080 | consumed tokens: 67465379840 | elapsed time per iteration (s): 2.25 | learning rate: 2.736E-05 | global batch size: 512 | lm loss: 1.905991E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.534 | TFLOPs: 23.42 | +63: iteration 64350/ 73814 | consumed samples: 32947200 | consumed tokens: 67475865600 | elapsed time per iteration (s): 2.25 | learning rate: 2.735E-05 | global batch size: 512 | lm loss: 1.895654E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.072 | TFLOPs: 23.38 | +63: iteration 64360/ 73814 | consumed samples: 32952320 | consumed tokens: 67486351360 | elapsed time per iteration (s): 2.23 | learning rate: 2.733E-05 | global batch size: 512 | lm loss: 1.882411E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.835 | TFLOPs: 23.66 | +63: iteration 64370/ 73814 | consumed samples: 32957440 | consumed tokens: 67496837120 | elapsed time per iteration (s): 2.24 | learning rate: 2.732E-05 | global batch size: 512 | lm loss: 1.859883E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.071 | TFLOPs: 23.48 | +63: iteration 64380/ 73814 | consumed samples: 32962560 | consumed tokens: 67507322880 | elapsed time per iteration (s): 2.23 | learning rate: 2.730E-05 | global batch size: 512 | lm loss: 1.892172E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.764 | TFLOPs: 23.65 | +63: iteration 64390/ 73814 | consumed samples: 32967680 | consumed tokens: 67517808640 | elapsed time per iteration (s): 2.23 | learning rate: 2.729E-05 | global batch size: 512 | lm loss: 1.877451E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.128 | TFLOPs: 23.59 | +63: iteration 64400/ 73814 | consumed samples: 32972800 | consumed tokens: 67528294400 | elapsed time per iteration (s): 2.25 | learning rate: 2.727E-05 | global batch size: 512 | lm loss: 1.871932E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.607 | TFLOPs: 23.43 | +63: iteration 64410/ 73814 | consumed samples: 32977920 | consumed tokens: 67538780160 | elapsed time per iteration (s): 2.36 | learning rate: 2.726E-05 | global batch size: 512 | lm loss: 1.890759E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.755 | TFLOPs: 22.31 | +63: iteration 64420/ 73814 | consumed samples: 32983040 | consumed tokens: 67549265920 | elapsed time per iteration (s): 2.25 | learning rate: 2.724E-05 | global batch size: 512 | lm loss: 1.872613E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.934 | TFLOPs: 23.46 | +63: iteration 64430/ 73814 | consumed samples: 32988160 | consumed tokens: 67559751680 | elapsed time per iteration (s): 2.23 | learning rate: 2.723E-05 | global batch size: 512 | lm loss: 1.908626E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.886 | TFLOPs: 23.67 | +63: iteration 64440/ 73814 | consumed samples: 32993280 | consumed tokens: 67570237440 | elapsed time per iteration (s): 2.24 | learning rate: 2.721E-05 | global batch size: 512 | lm loss: 1.892338E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.267 | TFLOPs: 23.50 | +63: iteration 64450/ 73814 | consumed samples: 32998400 | consumed tokens: 67580723200 | elapsed time per iteration (s): 2.35 | learning rate: 2.720E-05 | global batch size: 512 | lm loss: 1.868721E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.736 | TFLOPs: 22.41 | +63: iteration 64460/ 73814 | consumed samples: 33003520 | consumed tokens: 67591208960 | elapsed time per iteration (s): 2.24 | learning rate: 2.718E-05 | global batch size: 512 | lm loss: 1.887696E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.524 | TFLOPs: 23.53 | +63: iteration 64470/ 73814 | consumed samples: 33008640 | consumed tokens: 67601694720 | elapsed time per iteration (s): 2.26 | learning rate: 2.716E-05 | global batch size: 512 | lm loss: 1.903175E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.703 | TFLOPs: 23.34 | +63: iteration 64480/ 73814 | consumed samples: 33013760 | consumed tokens: 67612180480 | elapsed time per iteration (s): 2.56 | learning rate: 2.715E-05 | global batch size: 512 | lm loss: 1.916865E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.255 | TFLOPs: 20.62 | +63: iteration 64490/ 73814 | consumed samples: 33018880 | consumed tokens: 67622666240 | elapsed time per iteration (s): 2.36 | learning rate: 2.713E-05 | global batch size: 512 | lm loss: 1.878230E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.906 | TFLOPs: 22.33 | +63: iteration 64500/ 73814 | consumed samples: 33024000 | consumed tokens: 67633152000 | elapsed time per iteration (s): 2.38 | learning rate: 2.712E-05 | global batch size: 512 | lm loss: 1.891537E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.363 | TFLOPs: 22.17 | +63: iteration 64510/ 73814 | consumed samples: 33029120 | consumed tokens: 67643637760 | elapsed time per iteration (s): 2.29 | learning rate: 2.710E-05 | global batch size: 512 | lm loss: 1.883623E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.555 | TFLOPs: 23.01 | +63: iteration 64520/ 73814 | consumed samples: 33034240 | consumed tokens: 67654123520 | elapsed time per iteration (s): 2.59 | learning rate: 2.709E-05 | global batch size: 512 | lm loss: 1.907761E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 197.738 | TFLOPs: 20.36 | +63: iteration 64530/ 73814 | consumed samples: 33039360 | consumed tokens: 67664609280 | elapsed time per iteration (s): 2.32 | learning rate: 2.707E-05 | global batch size: 512 | lm loss: 1.902357E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.383 | TFLOPs: 22.69 | +63: iteration 64540/ 73814 | consumed samples: 33044480 | consumed tokens: 67675095040 | elapsed time per iteration (s): 2.94 | learning rate: 2.706E-05 | global batch size: 512 | lm loss: 1.886785E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 174.303 | TFLOPs: 17.94 | +63: iteration 64550/ 73814 | consumed samples: 33049600 | consumed tokens: 67685580800 | elapsed time per iteration (s): 2.54 | learning rate: 2.704E-05 | global batch size: 512 | lm loss: 1.887550E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.549 | TFLOPs: 20.75 | +63: iteration 64560/ 73814 | consumed samples: 33054720 | consumed tokens: 67696066560 | elapsed time per iteration (s): 2.24 | learning rate: 2.703E-05 | global batch size: 512 | lm loss: 1.902635E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.010 | TFLOPs: 23.58 | +63: iteration 64570/ 73814 | consumed samples: 33059840 | consumed tokens: 67706552320 | elapsed time per iteration (s): 2.45 | learning rate: 2.701E-05 | global batch size: 512 | lm loss: 1.889411E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.112 | TFLOPs: 21.53 | +63: iteration 64580/ 73814 | consumed samples: 33064960 | consumed tokens: 67717038080 | elapsed time per iteration (s): 2.26 | learning rate: 2.700E-05 | global batch size: 512 | lm loss: 1.893633E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.313 | TFLOPs: 23.30 | +63: iteration 64590/ 73814 | consumed samples: 33070080 | consumed tokens: 67727523840 | elapsed time per iteration (s): 2.29 | learning rate: 2.698E-05 | global batch size: 512 | lm loss: 1.911586E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.208 | TFLOPs: 22.98 | +63: iteration 64600/ 73814 | consumed samples: 33075200 | consumed tokens: 67738009600 | elapsed time per iteration (s): 2.24 | learning rate: 2.697E-05 | global batch size: 512 | lm loss: 1.887024E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.259 | TFLOPs: 23.50 | +63: iteration 64610/ 73814 | consumed samples: 33080320 | consumed tokens: 67748495360 | elapsed time per iteration (s): 2.23 | learning rate: 2.695E-05 | global batch size: 512 | lm loss: 1.897894E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.276 | TFLOPs: 23.60 | +63: iteration 64620/ 73814 | consumed samples: 33085440 | consumed tokens: 67758981120 | elapsed time per iteration (s): 2.23 | learning rate: 2.694E-05 | global batch size: 512 | lm loss: 1.892510E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.060 | TFLOPs: 23.68 | +63: iteration 64630/ 73814 | consumed samples: 33090560 | consumed tokens: 67769466880 | elapsed time per iteration (s): 2.25 | learning rate: 2.692E-05 | global batch size: 512 | lm loss: 1.901138E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.935 | TFLOPs: 23.46 | +63: iteration 64640/ 73814 | consumed samples: 33095680 | consumed tokens: 67779952640 | elapsed time per iteration (s): 2.24 | learning rate: 2.691E-05 | global batch size: 512 | lm loss: 1.891478E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.773 | TFLOPs: 23.55 | +63: iteration 64650/ 73814 | consumed samples: 33100800 | consumed tokens: 67790438400 | elapsed time per iteration (s): 2.45 | learning rate: 2.690E-05 | global batch size: 512 | lm loss: 1.869622E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.731 | TFLOPs: 21.49 | +63: iteration 64660/ 73814 | consumed samples: 33105920 | consumed tokens: 67800924160 | elapsed time per iteration (s): 2.42 | learning rate: 2.688E-05 | global batch size: 512 | lm loss: 1.886651E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.226 | TFLOPs: 21.74 | +63: iteration 64670/ 73814 | consumed samples: 33111040 | consumed tokens: 67811409920 | elapsed time per iteration (s): 2.25 | learning rate: 2.687E-05 | global batch size: 512 | lm loss: 1.878986E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.824 | TFLOPs: 23.45 | +63: iteration 64680/ 73814 | consumed samples: 33116160 | consumed tokens: 67821895680 | elapsed time per iteration (s): 2.23 | learning rate: 2.685E-05 | global batch size: 512 | lm loss: 1.883965E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.664 | TFLOPs: 23.64 | +63: iteration 64690/ 73814 | consumed samples: 33121280 | consumed tokens: 67832381440 | elapsed time per iteration (s): 2.30 | learning rate: 2.684E-05 | global batch size: 512 | lm loss: 1.903466E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.768 | TFLOPs: 22.93 | +63: iteration 64700/ 73814 | consumed samples: 33126400 | consumed tokens: 67842867200 | elapsed time per iteration (s): 2.24 | learning rate: 2.682E-05 | global batch size: 512 | lm loss: 1.889044E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.099 | TFLOPs: 23.48 | +63: iteration 64710/ 73814 | consumed samples: 33131520 | consumed tokens: 67853352960 | elapsed time per iteration (s): 2.23 | learning rate: 2.681E-05 | global batch size: 512 | lm loss: 1.884484E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.966 | TFLOPs: 23.67 | +63: iteration 64720/ 73814 | consumed samples: 33136640 | consumed tokens: 67863838720 | elapsed time per iteration (s): 2.24 | learning rate: 2.679E-05 | global batch size: 512 | lm loss: 1.918649E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.261 | TFLOPs: 23.50 | +63: iteration 64730/ 73814 | consumed samples: 33141760 | consumed tokens: 67874324480 | elapsed time per iteration (s): 2.23 | learning rate: 2.678E-05 | global batch size: 512 | lm loss: 1.881598E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.491 | TFLOPs: 23.62 | +63: iteration 64740/ 73814 | consumed samples: 33146880 | consumed tokens: 67884810240 | elapsed time per iteration (s): 2.23 | learning rate: 2.676E-05 | global batch size: 512 | lm loss: 1.883780E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.315 | TFLOPs: 23.61 | +63: iteration 64750/ 73814 | consumed samples: 33152000 | consumed tokens: 67895296000 | elapsed time per iteration (s): 2.24 | learning rate: 2.675E-05 | global batch size: 512 | lm loss: 1.888982E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.404 | TFLOPs: 23.51 | +63: iteration 64760/ 73814 | consumed samples: 33157120 | consumed tokens: 67905781760 | elapsed time per iteration (s): 2.23 | learning rate: 2.673E-05 | global batch size: 512 | lm loss: 1.875034E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.729 | TFLOPs: 23.65 | +63: iteration 64770/ 73814 | consumed samples: 33162240 | consumed tokens: 67916267520 | elapsed time per iteration (s): 2.35 | learning rate: 2.672E-05 | global batch size: 512 | lm loss: 1.879440E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.109 | TFLOPs: 22.45 | +63: iteration 64780/ 73814 | consumed samples: 33167360 | consumed tokens: 67926753280 | elapsed time per iteration (s): 2.38 | learning rate: 2.670E-05 | global batch size: 512 | lm loss: 1.877792E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.677 | TFLOPs: 22.10 | +63: iteration 64790/ 73814 | consumed samples: 33172480 | consumed tokens: 67937239040 | elapsed time per iteration (s): 2.46 | learning rate: 2.669E-05 | global batch size: 512 | lm loss: 1.897138E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.272 | TFLOPs: 21.44 | +63: iteration 64800/ 73814 | consumed samples: 33177600 | consumed tokens: 67947724800 | elapsed time per iteration (s): 2.25 | learning rate: 2.667E-05 | global batch size: 512 | lm loss: 1.893031E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.885 | TFLOPs: 23.46 | +63: iteration 64810/ 73814 | consumed samples: 33182720 | consumed tokens: 67958210560 | elapsed time per iteration (s): 2.27 | learning rate: 2.666E-05 | global batch size: 512 | lm loss: 1.918110E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.234 | TFLOPs: 23.19 | +63: iteration 64820/ 73814 | consumed samples: 33187840 | consumed tokens: 67968696320 | elapsed time per iteration (s): 2.41 | learning rate: 2.664E-05 | global batch size: 512 | lm loss: 1.891720E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.572 | TFLOPs: 21.88 | +63: iteration 64830/ 73814 | consumed samples: 33192960 | consumed tokens: 67979182080 | elapsed time per iteration (s): 2.24 | learning rate: 2.663E-05 | global batch size: 512 | lm loss: 1.886305E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.733 | TFLOPs: 23.55 | +63: iteration 64840/ 73814 | consumed samples: 33198080 | consumed tokens: 67989667840 | elapsed time per iteration (s): 2.36 | learning rate: 2.662E-05 | global batch size: 512 | lm loss: 1.889467E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.335 | TFLOPs: 22.37 | +63: iteration 64850/ 73814 | consumed samples: 33203200 | consumed tokens: 68000153600 | elapsed time per iteration (s): 2.26 | learning rate: 2.660E-05 | global batch size: 512 | lm loss: 1.886552E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.595 | TFLOPs: 23.33 | +63: iteration 64860/ 73814 | consumed samples: 33208320 | consumed tokens: 68010639360 | elapsed time per iteration (s): 2.23 | learning rate: 2.659E-05 | global batch size: 512 | lm loss: 1.908789E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.639 | TFLOPs: 23.64 | +63: iteration 64870/ 73814 | consumed samples: 33213440 | consumed tokens: 68021125120 | elapsed time per iteration (s): 2.33 | learning rate: 2.657E-05 | global batch size: 512 | lm loss: 1.886294E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.879 | TFLOPs: 22.64 | +63: iteration 64880/ 73814 | consumed samples: 33218560 | consumed tokens: 68031610880 | elapsed time per iteration (s): 2.24 | learning rate: 2.656E-05 | global batch size: 512 | lm loss: 1.876348E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.701 | TFLOPs: 23.54 | +63: iteration 64890/ 73814 | consumed samples: 33223680 | consumed tokens: 68042096640 | elapsed time per iteration (s): 2.23 | learning rate: 2.654E-05 | global batch size: 512 | lm loss: 1.931210E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.613 | TFLOPs: 23.64 | +63: iteration 64900/ 73814 | consumed samples: 33228800 | consumed tokens: 68052582400 | elapsed time per iteration (s): 2.23 | learning rate: 2.653E-05 | global batch size: 512 | lm loss: 1.886125E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.725 | TFLOPs: 23.65 | +63: iteration 64910/ 73814 | consumed samples: 33233920 | consumed tokens: 68063068160 | elapsed time per iteration (s): 2.28 | learning rate: 2.651E-05 | global batch size: 512 | lm loss: 1.887224E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.393 | TFLOPs: 23.10 | +63: iteration 64920/ 73814 | consumed samples: 33239040 | consumed tokens: 68073553920 | elapsed time per iteration (s): 2.22 | learning rate: 2.650E-05 | global batch size: 512 | lm loss: 1.896361E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.189 | TFLOPs: 23.70 | +63: iteration 64930/ 73814 | consumed samples: 33244160 | consumed tokens: 68084039680 | elapsed time per iteration (s): 2.22 | learning rate: 2.649E-05 | global batch size: 512 | lm loss: 1.895428E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.280 | TFLOPs: 23.71 | +63: iteration 64940/ 73814 | consumed samples: 33249280 | consumed tokens: 68094525440 | elapsed time per iteration (s): 2.24 | learning rate: 2.647E-05 | global batch size: 512 | lm loss: 1.895212E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.591 | TFLOPs: 23.53 | +63: iteration 64950/ 73814 | consumed samples: 33254400 | consumed tokens: 68105011200 | elapsed time per iteration (s): 2.22 | learning rate: 2.646E-05 | global batch size: 512 | lm loss: 1.891231E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.160 | TFLOPs: 23.69 | +63: iteration 64960/ 73814 | consumed samples: 33259520 | consumed tokens: 68115496960 | elapsed time per iteration (s): 2.23 | learning rate: 2.644E-05 | global batch size: 512 | lm loss: 1.895688E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.895 | TFLOPs: 23.67 | +63: iteration 64970/ 73814 | consumed samples: 33264640 | consumed tokens: 68125982720 | elapsed time per iteration (s): 2.23 | learning rate: 2.643E-05 | global batch size: 512 | lm loss: 1.901299E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.549 | TFLOPs: 23.63 | +63: iteration 64980/ 73814 | consumed samples: 33269760 | consumed tokens: 68136468480 | elapsed time per iteration (s): 2.24 | learning rate: 2.641E-05 | global batch size: 512 | lm loss: 1.910183E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.491 | TFLOPs: 23.52 | +63: iteration 64990/ 73814 | consumed samples: 33274880 | consumed tokens: 68146954240 | elapsed time per iteration (s): 2.24 | learning rate: 2.640E-05 | global batch size: 512 | lm loss: 1.885561E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.204 | TFLOPs: 23.49 | +63: iteration 65000/ 73814 | consumed samples: 33280000 | consumed tokens: 68157440000 | elapsed time per iteration (s): 2.23 | learning rate: 2.638E-05 | global batch size: 512 | lm loss: 1.904431E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.583 | TFLOPs: 23.63 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 65000 | lm loss value: 1.801786E+00 | lm loss PPL: 6.060461E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 65010/ 73814 | consumed samples: 33285120 | consumed tokens: 68167925760 | elapsed time per iteration (s): 2.31 | learning rate: 2.637E-05 | global batch size: 512 | lm loss: 1.888324E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.112 | TFLOPs: 22.87 | +63: iteration 65020/ 73814 | consumed samples: 33290240 | consumed tokens: 68178411520 | elapsed time per iteration (s): 2.23 | learning rate: 2.636E-05 | global batch size: 512 | lm loss: 1.893286E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.730 | TFLOPs: 23.65 | +63: iteration 65030/ 73814 | consumed samples: 33295360 | consumed tokens: 68188897280 | elapsed time per iteration (s): 2.23 | learning rate: 2.634E-05 | global batch size: 512 | lm loss: 1.899302E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.710 | TFLOPs: 23.65 | +63: iteration 65040/ 73814 | consumed samples: 33300480 | consumed tokens: 68199383040 | elapsed time per iteration (s): 2.29 | learning rate: 2.633E-05 | global batch size: 512 | lm loss: 1.918321E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.156 | TFLOPs: 22.97 | +63: iteration 65050/ 73814 | consumed samples: 33305600 | consumed tokens: 68209868800 | elapsed time per iteration (s): 2.24 | learning rate: 2.631E-05 | global batch size: 512 | lm loss: 1.872711E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.165 | TFLOPs: 23.49 | +63: iteration 65060/ 73814 | consumed samples: 33310720 | consumed tokens: 68220354560 | elapsed time per iteration (s): 2.23 | learning rate: 2.630E-05 | global batch size: 512 | lm loss: 1.899000E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.453 | TFLOPs: 23.62 | +63: iteration 65070/ 73814 | consumed samples: 33315840 | consumed tokens: 68230840320 | elapsed time per iteration (s): 2.22 | learning rate: 2.628E-05 | global batch size: 512 | lm loss: 1.897142E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.305 | TFLOPs: 23.71 | +63: iteration 65080/ 73814 | consumed samples: 33320960 | consumed tokens: 68241326080 | elapsed time per iteration (s): 2.22 | learning rate: 2.627E-05 | global batch size: 512 | lm loss: 1.890326E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.471 | TFLOPs: 23.73 | +63: iteration 65090/ 73814 | consumed samples: 33326080 | consumed tokens: 68251811840 | elapsed time per iteration (s): 2.24 | learning rate: 2.626E-05 | global batch size: 512 | lm loss: 1.901793E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.753 | TFLOPs: 23.55 | +63: iteration 65100/ 73814 | consumed samples: 33331200 | consumed tokens: 68262297600 | elapsed time per iteration (s): 2.23 | learning rate: 2.624E-05 | global batch size: 512 | lm loss: 1.896584E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.293 | TFLOPs: 23.60 | +63: iteration 65110/ 73814 | consumed samples: 33336320 | consumed tokens: 68272783360 | elapsed time per iteration (s): 2.25 | learning rate: 2.623E-05 | global batch size: 512 | lm loss: 1.890287E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.365 | TFLOPs: 23.41 | +63: iteration 65120/ 73814 | consumed samples: 33341440 | consumed tokens: 68283269120 | elapsed time per iteration (s): 2.23 | learning rate: 2.621E-05 | global batch size: 512 | lm loss: 1.915451E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.940 | TFLOPs: 23.67 | +63: iteration 65130/ 73814 | consumed samples: 33346560 | consumed tokens: 68293754880 | elapsed time per iteration (s): 2.46 | learning rate: 2.620E-05 | global batch size: 512 | lm loss: 1.898048E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 207.816 | TFLOPs: 21.39 | +63: iteration 65140/ 73814 | consumed samples: 33351680 | consumed tokens: 68304240640 | elapsed time per iteration (s): 2.23 | learning rate: 2.619E-05 | global batch size: 512 | lm loss: 1.890102E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.101 | TFLOPs: 23.69 | +63: iteration 65150/ 73814 | consumed samples: 33356800 | consumed tokens: 68314726400 | elapsed time per iteration (s): 2.36 | learning rate: 2.617E-05 | global batch size: 512 | lm loss: 1.889734E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.323 | TFLOPs: 22.37 | +63: iteration 65160/ 73814 | consumed samples: 33361920 | consumed tokens: 68325212160 | elapsed time per iteration (s): 2.24 | learning rate: 2.616E-05 | global batch size: 512 | lm loss: 1.872973E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.615 | TFLOPs: 23.53 | +63: iteration 65170/ 73814 | consumed samples: 33367040 | consumed tokens: 68335697920 | elapsed time per iteration (s): 2.23 | learning rate: 2.614E-05 | global batch size: 512 | lm loss: 1.902875E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.252 | TFLOPs: 23.60 | +63: iteration 65180/ 73814 | consumed samples: 33372160 | consumed tokens: 68346183680 | elapsed time per iteration (s): 2.22 | learning rate: 2.613E-05 | global batch size: 512 | lm loss: 1.902419E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.597 | TFLOPs: 23.74 | +63: iteration 65190/ 73814 | consumed samples: 33377280 | consumed tokens: 68356669440 | elapsed time per iteration (s): 2.23 | learning rate: 2.612E-05 | global batch size: 512 | lm loss: 1.877431E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.696 | TFLOPs: 23.65 | +63: iteration 65200/ 73814 | consumed samples: 33382400 | consumed tokens: 68367155200 | elapsed time per iteration (s): 2.23 | learning rate: 2.610E-05 | global batch size: 512 | lm loss: 1.895117E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.172 | TFLOPs: 23.59 | +63: iteration 65210/ 73814 | consumed samples: 33387520 | consumed tokens: 68377640960 | elapsed time per iteration (s): 2.23 | learning rate: 2.609E-05 | global batch size: 512 | lm loss: 1.899682E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.047 | TFLOPs: 23.68 | +63: iteration 65220/ 73814 | consumed samples: 33392640 | consumed tokens: 68388126720 | elapsed time per iteration (s): 2.25 | learning rate: 2.607E-05 | global batch size: 512 | lm loss: 1.896102E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.585 | TFLOPs: 23.43 | +63: iteration 65230/ 73814 | consumed samples: 33397760 | consumed tokens: 68398612480 | elapsed time per iteration (s): 2.23 | learning rate: 2.606E-05 | global batch size: 512 | lm loss: 1.886366E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.915 | TFLOPs: 23.67 | +63: iteration 65240/ 73814 | consumed samples: 33402880 | consumed tokens: 68409098240 | elapsed time per iteration (s): 2.24 | learning rate: 2.605E-05 | global batch size: 512 | lm loss: 1.891600E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.511 | TFLOPs: 23.52 | +63: iteration 65250/ 73814 | consumed samples: 33408000 | consumed tokens: 68419584000 | elapsed time per iteration (s): 2.34 | learning rate: 2.603E-05 | global batch size: 512 | lm loss: 1.899700E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.235 | TFLOPs: 22.57 | +63: iteration 65260/ 73814 | consumed samples: 33413120 | consumed tokens: 68430069760 | elapsed time per iteration (s): 2.25 | learning rate: 2.602E-05 | global batch size: 512 | lm loss: 1.895635E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.341 | TFLOPs: 23.40 | +63: iteration 65270/ 73814 | consumed samples: 33418240 | consumed tokens: 68440555520 | elapsed time per iteration (s): 2.23 | learning rate: 2.600E-05 | global batch size: 512 | lm loss: 1.891077E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.531 | TFLOPs: 23.63 | +63: iteration 65280/ 73814 | consumed samples: 33423360 | consumed tokens: 68451041280 | elapsed time per iteration (s): 2.24 | learning rate: 2.599E-05 | global batch size: 512 | lm loss: 1.916164E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.441 | TFLOPs: 23.52 | +63: iteration 65290/ 73814 | consumed samples: 33428480 | consumed tokens: 68461527040 | elapsed time per iteration (s): 2.23 | learning rate: 2.598E-05 | global batch size: 512 | lm loss: 1.880811E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.544 | TFLOPs: 23.63 | +63: iteration 65300/ 73814 | consumed samples: 33433600 | consumed tokens: 68472012800 | elapsed time per iteration (s): 2.28 | learning rate: 2.596E-05 | global batch size: 512 | lm loss: 1.883405E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.559 | TFLOPs: 23.12 | +63: iteration 65310/ 73814 | consumed samples: 33438720 | consumed tokens: 68482498560 | elapsed time per iteration (s): 2.23 | learning rate: 2.595E-05 | global batch size: 512 | lm loss: 1.870028E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.029 | TFLOPs: 23.68 | +63: iteration 65320/ 73814 | consumed samples: 33443840 | consumed tokens: 68492984320 | elapsed time per iteration (s): 2.26 | learning rate: 2.593E-05 | global batch size: 512 | lm loss: 1.894551E+00 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.903 | TFLOPs: 23.36 | +63: iteration 65330/ 73814 | consumed samples: 33448960 | consumed tokens: 68503470080 | elapsed time per iteration (s): 2.26 | learning rate: 2.592E-05 | global batch size: 512 | lm loss: 1.902305E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.291 | TFLOPs: 23.30 | +63: iteration 65340/ 73814 | consumed samples: 33454080 | consumed tokens: 68513955840 | elapsed time per iteration (s): 2.30 | learning rate: 2.591E-05 | global batch size: 512 | lm loss: 1.886109E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.656 | TFLOPs: 22.92 | +63: iteration 65350/ 73814 | consumed samples: 33459200 | consumed tokens: 68524441600 | elapsed time per iteration (s): 2.27 | learning rate: 2.589E-05 | global batch size: 512 | lm loss: 1.898367E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.237 | TFLOPs: 23.19 | +63: iteration 65360/ 73814 | consumed samples: 33464320 | consumed tokens: 68534927360 | elapsed time per iteration (s): 2.25 | learning rate: 2.588E-05 | global batch size: 512 | lm loss: 1.896659E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.207 | TFLOPs: 23.39 | +63: iteration 65370/ 73814 | consumed samples: 33469440 | consumed tokens: 68545413120 | elapsed time per iteration (s): 2.23 | learning rate: 2.587E-05 | global batch size: 512 | lm loss: 1.887584E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.036 | TFLOPs: 23.68 | +63: iteration 65380/ 73814 | consumed samples: 33474560 | consumed tokens: 68555898880 | elapsed time per iteration (s): 2.23 | learning rate: 2.585E-05 | global batch size: 512 | lm loss: 1.878588E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.335 | TFLOPs: 23.61 | +63: iteration 65390/ 73814 | consumed samples: 33479680 | consumed tokens: 68566384640 | elapsed time per iteration (s): 2.34 | learning rate: 2.584E-05 | global batch size: 512 | lm loss: 1.872156E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.627 | TFLOPs: 22.51 | +63: iteration 65400/ 73814 | consumed samples: 33484800 | consumed tokens: 68576870400 | elapsed time per iteration (s): 2.22 | learning rate: 2.582E-05 | global batch size: 512 | lm loss: 1.906743E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.287 | TFLOPs: 23.71 | +63: iteration 65410/ 73814 | consumed samples: 33489920 | consumed tokens: 68587356160 | elapsed time per iteration (s): 2.39 | learning rate: 2.581E-05 | global batch size: 512 | lm loss: 1.885199E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.867 | TFLOPs: 22.02 | +63: iteration 65420/ 73814 | consumed samples: 33495040 | consumed tokens: 68597841920 | elapsed time per iteration (s): 2.24 | learning rate: 2.580E-05 | global batch size: 512 | lm loss: 1.915874E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.250 | TFLOPs: 23.50 | +63: iteration 65430/ 73814 | consumed samples: 33500160 | consumed tokens: 68608327680 | elapsed time per iteration (s): 2.24 | learning rate: 2.578E-05 | global batch size: 512 | lm loss: 1.896757E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.858 | TFLOPs: 23.56 | +63: iteration 65440/ 73814 | consumed samples: 33505280 | consumed tokens: 68618813440 | elapsed time per iteration (s): 2.26 | learning rate: 2.577E-05 | global batch size: 512 | lm loss: 1.919780E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.998 | TFLOPs: 23.37 | +63: iteration 65450/ 73814 | consumed samples: 33510400 | consumed tokens: 68629299200 | elapsed time per iteration (s): 2.23 | learning rate: 2.576E-05 | global batch size: 512 | lm loss: 1.873076E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.103 | TFLOPs: 23.69 | +63: iteration 65460/ 73814 | consumed samples: 33515520 | consumed tokens: 68639784960 | elapsed time per iteration (s): 2.24 | learning rate: 2.574E-05 | global batch size: 512 | lm loss: 1.887194E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.899 | TFLOPs: 23.56 | +63: iteration 65470/ 73814 | consumed samples: 33520640 | consumed tokens: 68650270720 | elapsed time per iteration (s): 2.23 | learning rate: 2.573E-05 | global batch size: 512 | lm loss: 1.884546E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.104 | TFLOPs: 23.69 | +63: iteration 65480/ 73814 | consumed samples: 33525760 | consumed tokens: 68660756480 | elapsed time per iteration (s): 2.24 | learning rate: 2.572E-05 | global batch size: 512 | lm loss: 1.889552E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.449 | TFLOPs: 23.52 | +63: iteration 65490/ 73814 | consumed samples: 33530880 | consumed tokens: 68671242240 | elapsed time per iteration (s): 2.23 | learning rate: 2.570E-05 | global batch size: 512 | lm loss: 1.884526E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.993 | TFLOPs: 23.68 | +63: iteration 65500/ 73814 | consumed samples: 33536000 | consumed tokens: 68681728000 | elapsed time per iteration (s): 2.26 | learning rate: 2.569E-05 | global batch size: 512 | lm loss: 1.889029E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.257 | TFLOPs: 23.29 | +63: iteration 65510/ 73814 | consumed samples: 33541120 | consumed tokens: 68692213760 | elapsed time per iteration (s): 2.24 | learning rate: 2.567E-05 | global batch size: 512 | lm loss: 1.885798E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.066 | TFLOPs: 23.48 | +63: iteration 65520/ 73814 | consumed samples: 33546240 | consumed tokens: 68702699520 | elapsed time per iteration (s): 2.25 | learning rate: 2.566E-05 | global batch size: 512 | lm loss: 1.876506E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.598 | TFLOPs: 23.43 | +63: iteration 65530/ 73814 | consumed samples: 33551360 | consumed tokens: 68713185280 | elapsed time per iteration (s): 2.22 | learning rate: 2.565E-05 | global batch size: 512 | lm loss: 1.890290E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.226 | TFLOPs: 23.70 | +63: iteration 65540/ 73814 | consumed samples: 33556480 | consumed tokens: 68723671040 | elapsed time per iteration (s): 2.23 | learning rate: 2.563E-05 | global batch size: 512 | lm loss: 1.880832E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.777 | TFLOPs: 23.65 | +63: iteration 65550/ 73814 | consumed samples: 33561600 | consumed tokens: 68734156800 | elapsed time per iteration (s): 2.23 | learning rate: 2.562E-05 | global batch size: 512 | lm loss: 1.902954E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.850 | TFLOPs: 23.66 | +63: iteration 65560/ 73814 | consumed samples: 33566720 | consumed tokens: 68744642560 | elapsed time per iteration (s): 2.23 | learning rate: 2.561E-05 | global batch size: 512 | lm loss: 1.910888E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.398 | TFLOPs: 23.62 | +63: iteration 65570/ 73814 | consumed samples: 33571840 | consumed tokens: 68755128320 | elapsed time per iteration (s): 2.23 | learning rate: 2.559E-05 | global batch size: 512 | lm loss: 1.919045E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.984 | TFLOPs: 23.68 | +63: iteration 65580/ 73814 | consumed samples: 33576960 | consumed tokens: 68765614080 | elapsed time per iteration (s): 2.24 | learning rate: 2.558E-05 | global batch size: 512 | lm loss: 1.892689E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.677 | TFLOPs: 23.54 | +63: iteration 65590/ 73814 | consumed samples: 33582080 | consumed tokens: 68776099840 | elapsed time per iteration (s): 2.46 | learning rate: 2.557E-05 | global batch size: 512 | lm loss: 1.909847E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 207.904 | TFLOPs: 21.40 | +63: iteration 65600/ 73814 | consumed samples: 33587200 | consumed tokens: 68786585600 | elapsed time per iteration (s): 2.25 | learning rate: 2.555E-05 | global batch size: 512 | lm loss: 1.910292E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.156 | TFLOPs: 23.38 | +63: iteration 65610/ 73814 | consumed samples: 33592320 | consumed tokens: 68797071360 | elapsed time per iteration (s): 2.23 | learning rate: 2.554E-05 | global batch size: 512 | lm loss: 1.906248E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.190 | TFLOPs: 23.59 | +63: iteration 65620/ 73814 | consumed samples: 33597440 | consumed tokens: 68807557120 | elapsed time per iteration (s): 2.23 | learning rate: 2.553E-05 | global batch size: 512 | lm loss: 1.900226E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.990 | TFLOPs: 23.68 | +63: iteration 65630/ 73814 | consumed samples: 33602560 | consumed tokens: 68818042880 | elapsed time per iteration (s): 2.39 | learning rate: 2.551E-05 | global batch size: 512 | lm loss: 1.902919E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.146 | TFLOPs: 22.05 | +63: iteration 65640/ 73814 | consumed samples: 33607680 | consumed tokens: 68828528640 | elapsed time per iteration (s): 2.23 | learning rate: 2.550E-05 | global batch size: 512 | lm loss: 1.874511E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.615 | TFLOPs: 23.64 | +63: iteration 65650/ 73814 | consumed samples: 33612800 | consumed tokens: 68839014400 | elapsed time per iteration (s): 2.27 | learning rate: 2.549E-05 | global batch size: 512 | lm loss: 1.882511E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.096 | TFLOPs: 23.17 | +63: iteration 65660/ 73814 | consumed samples: 33617920 | consumed tokens: 68849500160 | elapsed time per iteration (s): 2.22 | learning rate: 2.547E-05 | global batch size: 512 | lm loss: 1.884566E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.193 | TFLOPs: 23.70 | +63: iteration 65670/ 73814 | consumed samples: 33623040 | consumed tokens: 68859985920 | elapsed time per iteration (s): 2.26 | learning rate: 2.546E-05 | global batch size: 512 | lm loss: 1.879226E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.010 | TFLOPs: 23.37 | +63: iteration 65680/ 73814 | consumed samples: 33628160 | consumed tokens: 68870471680 | elapsed time per iteration (s): 2.24 | learning rate: 2.545E-05 | global batch size: 512 | lm loss: 1.889186E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.329 | TFLOPs: 23.51 | +63: iteration 65690/ 73814 | consumed samples: 33633280 | consumed tokens: 68880957440 | elapsed time per iteration (s): 2.22 | learning rate: 2.543E-05 | global batch size: 512 | lm loss: 1.912764E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.497 | TFLOPs: 23.73 | +63: iteration 65700/ 73814 | consumed samples: 33638400 | consumed tokens: 68891443200 | elapsed time per iteration (s): 2.29 | learning rate: 2.542E-05 | global batch size: 512 | lm loss: 1.897397E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.868 | TFLOPs: 23.05 | +63: iteration 65710/ 73814 | consumed samples: 33643520 | consumed tokens: 68901928960 | elapsed time per iteration (s): 2.37 | learning rate: 2.541E-05 | global batch size: 512 | lm loss: 1.892631E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.040 | TFLOPs: 22.24 | +63: iteration 65720/ 73814 | consumed samples: 33648640 | consumed tokens: 68912414720 | elapsed time per iteration (s): 2.24 | learning rate: 2.539E-05 | global batch size: 512 | lm loss: 1.886939E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.765 | TFLOPs: 23.55 | +63: iteration 65730/ 73814 | consumed samples: 33653760 | consumed tokens: 68922900480 | elapsed time per iteration (s): 2.23 | learning rate: 2.538E-05 | global batch size: 512 | lm loss: 1.884784E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.575 | TFLOPs: 23.63 | +63: iteration 65740/ 73814 | consumed samples: 33658880 | consumed tokens: 68933386240 | elapsed time per iteration (s): 2.26 | learning rate: 2.537E-05 | global batch size: 512 | lm loss: 1.894006E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.446 | TFLOPs: 23.31 | +63: iteration 65750/ 73814 | consumed samples: 33664000 | consumed tokens: 68943872000 | elapsed time per iteration (s): 2.23 | learning rate: 2.535E-05 | global batch size: 512 | lm loss: 1.882848E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.064 | TFLOPs: 23.68 | +63: iteration 65760/ 73814 | consumed samples: 33669120 | consumed tokens: 68954357760 | elapsed time per iteration (s): 2.26 | learning rate: 2.534E-05 | global batch size: 512 | lm loss: 1.895886E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.745 | TFLOPs: 23.34 | +63: iteration 65770/ 73814 | consumed samples: 33674240 | consumed tokens: 68964843520 | elapsed time per iteration (s): 2.36 | learning rate: 2.533E-05 | global batch size: 512 | lm loss: 1.904850E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.232 | TFLOPs: 22.36 | +63: iteration 65780/ 73814 | consumed samples: 33679360 | consumed tokens: 68975329280 | elapsed time per iteration (s): 2.52 | learning rate: 2.532E-05 | global batch size: 512 | lm loss: 1.901535E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.982 | TFLOPs: 20.90 | +63: iteration 65790/ 73814 | consumed samples: 33684480 | consumed tokens: 68985815040 | elapsed time per iteration (s): 2.37 | learning rate: 2.530E-05 | global batch size: 512 | lm loss: 1.895129E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.678 | TFLOPs: 22.20 | +63: iteration 65800/ 73814 | consumed samples: 33689600 | consumed tokens: 68996300800 | elapsed time per iteration (s): 2.34 | learning rate: 2.529E-05 | global batch size: 512 | lm loss: 1.873948E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.762 | TFLOPs: 22.52 | +63: iteration 65810/ 73814 | consumed samples: 33694720 | consumed tokens: 69006786560 | elapsed time per iteration (s): 2.22 | learning rate: 2.528E-05 | global batch size: 512 | lm loss: 1.888626E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.208 | TFLOPs: 23.70 | +63: iteration 65820/ 73814 | consumed samples: 33699840 | consumed tokens: 69017272320 | elapsed time per iteration (s): 2.24 | learning rate: 2.526E-05 | global batch size: 512 | lm loss: 1.919621E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.366 | TFLOPs: 23.51 | +63: iteration 65830/ 73814 | consumed samples: 33704960 | consumed tokens: 69027758080 | elapsed time per iteration (s): 2.25 | learning rate: 2.525E-05 | global batch size: 512 | lm loss: 1.900026E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.864 | TFLOPs: 23.46 | +63: iteration 65840/ 73814 | consumed samples: 33710080 | consumed tokens: 69038243840 | elapsed time per iteration (s): 2.36 | learning rate: 2.524E-05 | global batch size: 512 | lm loss: 1.853368E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.184 | TFLOPs: 22.36 | +63: iteration 65850/ 73814 | consumed samples: 33715200 | consumed tokens: 69048729600 | elapsed time per iteration (s): 2.23 | learning rate: 2.522E-05 | global batch size: 512 | lm loss: 1.896942E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.298 | TFLOPs: 23.61 | +63: iteration 65860/ 73814 | consumed samples: 33720320 | consumed tokens: 69059215360 | elapsed time per iteration (s): 2.33 | learning rate: 2.521E-05 | global batch size: 512 | lm loss: 1.883048E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.747 | TFLOPs: 22.62 | +63: iteration 65870/ 73814 | consumed samples: 33725440 | consumed tokens: 69069701120 | elapsed time per iteration (s): 2.40 | learning rate: 2.520E-05 | global batch size: 512 | lm loss: 1.892645E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.289 | TFLOPs: 21.96 | +63: iteration 65880/ 73814 | consumed samples: 33730560 | consumed tokens: 69080186880 | elapsed time per iteration (s): 2.22 | learning rate: 2.519E-05 | global batch size: 512 | lm loss: 1.891461E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.398 | TFLOPs: 23.72 | +63: iteration 65890/ 73814 | consumed samples: 33735680 | consumed tokens: 69090672640 | elapsed time per iteration (s): 2.40 | learning rate: 2.517E-05 | global batch size: 512 | lm loss: 1.879548E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.373 | TFLOPs: 21.97 | +63: iteration 65900/ 73814 | consumed samples: 33740800 | consumed tokens: 69101158400 | elapsed time per iteration (s): 2.24 | learning rate: 2.516E-05 | global batch size: 512 | lm loss: 1.869871E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.124 | TFLOPs: 23.48 | +63: iteration 65910/ 73814 | consumed samples: 33745920 | consumed tokens: 69111644160 | elapsed time per iteration (s): 2.23 | learning rate: 2.515E-05 | global batch size: 512 | lm loss: 1.876599E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.103 | TFLOPs: 23.69 | +63: iteration 65920/ 73814 | consumed samples: 33751040 | consumed tokens: 69122129920 | elapsed time per iteration (s): 2.23 | learning rate: 2.513E-05 | global batch size: 512 | lm loss: 1.901426E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.848 | TFLOPs: 23.66 | +63: iteration 65930/ 73814 | consumed samples: 33756160 | consumed tokens: 69132615680 | elapsed time per iteration (s): 2.29 | learning rate: 2.512E-05 | global batch size: 512 | lm loss: 1.880641E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.810 | TFLOPs: 23.04 | +63: iteration 65940/ 73814 | consumed samples: 33761280 | consumed tokens: 69143101440 | elapsed time per iteration (s): 2.28 | learning rate: 2.511E-05 | global batch size: 512 | lm loss: 1.876196E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.786 | TFLOPs: 23.14 | +63: iteration 65950/ 73814 | consumed samples: 33766400 | consumed tokens: 69153587200 | elapsed time per iteration (s): 2.23 | learning rate: 2.510E-05 | global batch size: 512 | lm loss: 1.871008E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.458 | TFLOPs: 23.62 | +63: iteration 65960/ 73814 | consumed samples: 33771520 | consumed tokens: 69164072960 | elapsed time per iteration (s): 2.25 | learning rate: 2.508E-05 | global batch size: 512 | lm loss: 1.882006E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.037 | TFLOPs: 23.48 | +63: iteration 65970/ 73814 | consumed samples: 33776640 | consumed tokens: 69174558720 | elapsed time per iteration (s): 2.53 | learning rate: 2.507E-05 | global batch size: 512 | lm loss: 1.899403E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.688 | TFLOPs: 20.87 | +63: iteration 65980/ 73814 | consumed samples: 33781760 | consumed tokens: 69185044480 | elapsed time per iteration (s): 2.22 | learning rate: 2.506E-05 | global batch size: 512 | lm loss: 1.901441E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.292 | TFLOPs: 23.71 | +63: iteration 65990/ 73814 | consumed samples: 33786880 | consumed tokens: 69195530240 | elapsed time per iteration (s): 2.23 | learning rate: 2.504E-05 | global batch size: 512 | lm loss: 1.894484E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.006 | TFLOPs: 23.68 | + 0: [2022-12-03 05:48:13,560] [INFO] [logging.py:68:log_dist] [Rank 0] step=66000, skipped=0, lr=[2.50310873945315e-05, 2.50310873945315e-05, 2.50310873945315e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 66000/ 73814 | consumed samples: 33792000 | consumed tokens: 69206016000 | elapsed time per iteration (s): 2.25 | learning rate: 2.503E-05 | global batch size: 512 | lm loss: 1.901638E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.453 | TFLOPs: 23.42 | + 0: steps: 66000 loss: 1.8970 iter time (s): 2.277 samples/sec: 224.843 +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 66000 | lm loss value: 1.764780E+00 | lm loss PPL: 5.840290E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 66010/ 73814 | consumed samples: 33797120 | consumed tokens: 69216501760 | elapsed time per iteration (s): 2.29 | learning rate: 2.502E-05 | global batch size: 512 | lm loss: 1.872518E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.114 | TFLOPs: 22.97 | +63: iteration 66020/ 73814 | consumed samples: 33802240 | consumed tokens: 69226987520 | elapsed time per iteration (s): 2.25 | learning rate: 2.501E-05 | global batch size: 512 | lm loss: 1.926254E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.818 | TFLOPs: 23.45 | +63: iteration 66030/ 73814 | consumed samples: 33807360 | consumed tokens: 69237473280 | elapsed time per iteration (s): 2.22 | learning rate: 2.499E-05 | global batch size: 512 | lm loss: 1.905527E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.366 | TFLOPs: 23.72 | +63: iteration 66040/ 73814 | consumed samples: 33812480 | consumed tokens: 69247959040 | elapsed time per iteration (s): 2.24 | learning rate: 2.498E-05 | global batch size: 512 | lm loss: 1.881892E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.214 | TFLOPs: 23.49 | +63: iteration 66050/ 73814 | consumed samples: 33817600 | consumed tokens: 69258444800 | elapsed time per iteration (s): 2.23 | learning rate: 2.497E-05 | global batch size: 512 | lm loss: 1.903530E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.264 | TFLOPs: 23.60 | +63: iteration 66060/ 73814 | consumed samples: 33822720 | consumed tokens: 69268930560 | elapsed time per iteration (s): 2.24 | learning rate: 2.495E-05 | global batch size: 512 | lm loss: 1.896893E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.059 | TFLOPs: 23.58 | +63: iteration 66070/ 73814 | consumed samples: 33827840 | consumed tokens: 69279416320 | elapsed time per iteration (s): 2.26 | learning rate: 2.494E-05 | global batch size: 512 | lm loss: 1.880866E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.823 | TFLOPs: 23.35 | +63: iteration 66080/ 73814 | consumed samples: 33832960 | consumed tokens: 69289902080 | elapsed time per iteration (s): 2.25 | learning rate: 2.493E-05 | global batch size: 512 | lm loss: 1.875421E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.884 | TFLOPs: 23.46 | +63: iteration 66090/ 73814 | consumed samples: 33838080 | consumed tokens: 69300387840 | elapsed time per iteration (s): 2.28 | learning rate: 2.492E-05 | global batch size: 512 | lm loss: 1.883227E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.731 | TFLOPs: 23.13 | +63: iteration 66100/ 73814 | consumed samples: 33843200 | consumed tokens: 69310873600 | elapsed time per iteration (s): 2.23 | learning rate: 2.490E-05 | global batch size: 512 | lm loss: 1.895304E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.566 | TFLOPs: 23.63 | +63: iteration 66110/ 73814 | consumed samples: 33848320 | consumed tokens: 69321359360 | elapsed time per iteration (s): 2.23 | learning rate: 2.489E-05 | global batch size: 512 | lm loss: 1.905124E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.822 | TFLOPs: 23.66 | +63: iteration 66120/ 73814 | consumed samples: 33853440 | consumed tokens: 69331845120 | elapsed time per iteration (s): 2.23 | learning rate: 2.488E-05 | global batch size: 512 | lm loss: 1.871285E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.554 | TFLOPs: 23.63 | +63: iteration 66130/ 73814 | consumed samples: 33858560 | consumed tokens: 69342330880 | elapsed time per iteration (s): 2.45 | learning rate: 2.487E-05 | global batch size: 512 | lm loss: 1.887564E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.370 | TFLOPs: 21.55 | +63: iteration 66140/ 73814 | consumed samples: 33863680 | consumed tokens: 69352816640 | elapsed time per iteration (s): 2.24 | learning rate: 2.485E-05 | global batch size: 512 | lm loss: 1.897836E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.923 | TFLOPs: 23.57 | +63: iteration 66150/ 73814 | consumed samples: 33868800 | consumed tokens: 69363302400 | elapsed time per iteration (s): 2.23 | learning rate: 2.484E-05 | global batch size: 512 | lm loss: 1.875895E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.482 | TFLOPs: 23.62 | +63: iteration 66160/ 73814 | consumed samples: 33873920 | consumed tokens: 69373788160 | elapsed time per iteration (s): 2.38 | learning rate: 2.483E-05 | global batch size: 512 | lm loss: 1.905152E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.576 | TFLOPs: 22.19 | +63: iteration 66170/ 73814 | consumed samples: 33879040 | consumed tokens: 69384273920 | elapsed time per iteration (s): 2.28 | learning rate: 2.482E-05 | global batch size: 512 | lm loss: 1.902051E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.658 | TFLOPs: 23.13 | +63: iteration 66180/ 73814 | consumed samples: 33884160 | consumed tokens: 69394759680 | elapsed time per iteration (s): 2.42 | learning rate: 2.480E-05 | global batch size: 512 | lm loss: 1.883589E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.557 | TFLOPs: 21.78 | +63: iteration 66190/ 73814 | consumed samples: 33889280 | consumed tokens: 69405245440 | elapsed time per iteration (s): 2.54 | learning rate: 2.479E-05 | global batch size: 512 | lm loss: 1.896952E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.323 | TFLOPs: 20.73 | +63: iteration 66200/ 73814 | consumed samples: 33894400 | consumed tokens: 69415731200 | elapsed time per iteration (s): 2.37 | learning rate: 2.478E-05 | global batch size: 512 | lm loss: 1.916754E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.222 | TFLOPs: 22.26 | +63: iteration 66210/ 73814 | consumed samples: 33899520 | consumed tokens: 69426216960 | elapsed time per iteration (s): 2.35 | learning rate: 2.477E-05 | global batch size: 512 | lm loss: 1.887748E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.868 | TFLOPs: 22.43 | +63: iteration 66220/ 73814 | consumed samples: 33904640 | consumed tokens: 69436702720 | elapsed time per iteration (s): 2.55 | learning rate: 2.475E-05 | global batch size: 512 | lm loss: 1.890603E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.848 | TFLOPs: 20.68 | +63: iteration 66230/ 73814 | consumed samples: 33909760 | consumed tokens: 69447188480 | elapsed time per iteration (s): 2.71 | learning rate: 2.474E-05 | global batch size: 512 | lm loss: 1.906319E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 188.703 | TFLOPs: 19.43 | +63: iteration 66240/ 73814 | consumed samples: 33914880 | consumed tokens: 69457674240 | elapsed time per iteration (s): 2.42 | learning rate: 2.473E-05 | global batch size: 512 | lm loss: 1.881887E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.006 | TFLOPs: 21.83 | +63: iteration 66250/ 73814 | consumed samples: 33920000 | consumed tokens: 69468160000 | elapsed time per iteration (s): 2.99 | learning rate: 2.472E-05 | global batch size: 512 | lm loss: 1.886449E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 171.340 | TFLOPs: 17.64 | +63: iteration 66260/ 73814 | consumed samples: 33925120 | consumed tokens: 69478645760 | elapsed time per iteration (s): 2.69 | learning rate: 2.470E-05 | global batch size: 512 | lm loss: 1.894027E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 190.286 | TFLOPs: 19.59 | +63: iteration 66270/ 73814 | consumed samples: 33930240 | consumed tokens: 69489131520 | elapsed time per iteration (s): 2.25 | learning rate: 2.469E-05 | global batch size: 512 | lm loss: 1.896790E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.831 | TFLOPs: 23.45 | +63: iteration 66280/ 73814 | consumed samples: 33935360 | consumed tokens: 69499617280 | elapsed time per iteration (s): 2.28 | learning rate: 2.468E-05 | global batch size: 512 | lm loss: 1.884730E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.428 | TFLOPs: 23.10 | +63: iteration 66290/ 73814 | consumed samples: 33940480 | consumed tokens: 69510103040 | elapsed time per iteration (s): 2.29 | learning rate: 2.467E-05 | global batch size: 512 | lm loss: 1.900502E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.928 | TFLOPs: 23.05 | +63: iteration 66300/ 73814 | consumed samples: 33945600 | consumed tokens: 69520588800 | elapsed time per iteration (s): 2.30 | learning rate: 2.466E-05 | global batch size: 512 | lm loss: 1.871783E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.645 | TFLOPs: 22.92 | +63: iteration 66310/ 73814 | consumed samples: 33950720 | consumed tokens: 69531074560 | elapsed time per iteration (s): 2.23 | learning rate: 2.464E-05 | global batch size: 512 | lm loss: 1.909694E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.746 | TFLOPs: 23.65 | +63: iteration 66320/ 73814 | consumed samples: 33955840 | consumed tokens: 69541560320 | elapsed time per iteration (s): 2.23 | learning rate: 2.463E-05 | global batch size: 512 | lm loss: 1.877290E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.313 | TFLOPs: 23.61 | +63: iteration 66330/ 73814 | consumed samples: 33960960 | consumed tokens: 69552046080 | elapsed time per iteration (s): 2.23 | learning rate: 2.462E-05 | global batch size: 512 | lm loss: 1.895871E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.869 | TFLOPs: 23.66 | +63: iteration 66340/ 73814 | consumed samples: 33966080 | consumed tokens: 69562531840 | elapsed time per iteration (s): 2.24 | learning rate: 2.461E-05 | global batch size: 512 | lm loss: 1.892192E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.471 | TFLOPs: 23.52 | +63: iteration 66350/ 73814 | consumed samples: 33971200 | consumed tokens: 69573017600 | elapsed time per iteration (s): 2.26 | learning rate: 2.459E-05 | global batch size: 512 | lm loss: 1.868879E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.695 | TFLOPs: 23.34 | +63: iteration 66360/ 73814 | consumed samples: 33976320 | consumed tokens: 69583503360 | elapsed time per iteration (s): 2.25 | learning rate: 2.458E-05 | global batch size: 512 | lm loss: 1.902646E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.627 | TFLOPs: 23.43 | +63: iteration 66370/ 73814 | consumed samples: 33981440 | consumed tokens: 69593989120 | elapsed time per iteration (s): 2.31 | learning rate: 2.457E-05 | global batch size: 512 | lm loss: 1.884631E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.760 | TFLOPs: 22.83 | +63: iteration 66380/ 73814 | consumed samples: 33986560 | consumed tokens: 69604474880 | elapsed time per iteration (s): 2.23 | learning rate: 2.456E-05 | global batch size: 512 | lm loss: 1.886219E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.754 | TFLOPs: 23.65 | +63: iteration 66390/ 73814 | consumed samples: 33991680 | consumed tokens: 69614960640 | elapsed time per iteration (s): 2.26 | learning rate: 2.455E-05 | global batch size: 512 | lm loss: 1.875713E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.088 | TFLOPs: 23.27 | +63: iteration 66400/ 73814 | consumed samples: 33996800 | consumed tokens: 69625446400 | elapsed time per iteration (s): 2.26 | learning rate: 2.453E-05 | global batch size: 512 | lm loss: 1.889725E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.755 | TFLOPs: 23.34 | +63: iteration 66410/ 73814 | consumed samples: 34001920 | consumed tokens: 69635932160 | elapsed time per iteration (s): 2.23 | learning rate: 2.452E-05 | global batch size: 512 | lm loss: 1.890819E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.959 | TFLOPs: 23.67 | +63: iteration 66420/ 73814 | consumed samples: 34007040 | consumed tokens: 69646417920 | elapsed time per iteration (s): 2.30 | learning rate: 2.451E-05 | global batch size: 512 | lm loss: 1.902455E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.237 | TFLOPs: 22.88 | +63: iteration 66430/ 73814 | consumed samples: 34012160 | consumed tokens: 69656903680 | elapsed time per iteration (s): 2.29 | learning rate: 2.450E-05 | global batch size: 512 | lm loss: 1.889680E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.229 | TFLOPs: 22.98 | +63: iteration 66440/ 73814 | consumed samples: 34017280 | consumed tokens: 69667389440 | elapsed time per iteration (s): 2.25 | learning rate: 2.449E-05 | global batch size: 512 | lm loss: 1.874234E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.824 | TFLOPs: 23.45 | +63: iteration 66450/ 73814 | consumed samples: 34022400 | consumed tokens: 69677875200 | elapsed time per iteration (s): 2.25 | learning rate: 2.447E-05 | global batch size: 512 | lm loss: 1.893430E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.380 | TFLOPs: 23.41 | +63: iteration 66460/ 73814 | consumed samples: 34027520 | consumed tokens: 69688360960 | elapsed time per iteration (s): 2.25 | learning rate: 2.446E-05 | global batch size: 512 | lm loss: 1.899091E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.266 | TFLOPs: 23.40 | +63: iteration 66470/ 73814 | consumed samples: 34032640 | consumed tokens: 69698846720 | elapsed time per iteration (s): 2.23 | learning rate: 2.445E-05 | global batch size: 512 | lm loss: 1.873133E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.576 | TFLOPs: 23.63 | +63: iteration 66480/ 73814 | consumed samples: 34037760 | consumed tokens: 69709332480 | elapsed time per iteration (s): 2.25 | learning rate: 2.444E-05 | global batch size: 512 | lm loss: 1.878158E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.048 | TFLOPs: 23.48 | +63: iteration 66490/ 73814 | consumed samples: 34042880 | consumed tokens: 69719818240 | elapsed time per iteration (s): 2.37 | learning rate: 2.442E-05 | global batch size: 512 | lm loss: 1.912342E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.685 | TFLOPs: 22.20 | +63: iteration 66500/ 73814 | consumed samples: 34048000 | consumed tokens: 69730304000 | elapsed time per iteration (s): 2.25 | learning rate: 2.441E-05 | global batch size: 512 | lm loss: 1.905222E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.126 | TFLOPs: 23.38 | +63: iteration 66510/ 73814 | consumed samples: 34053120 | consumed tokens: 69740789760 | elapsed time per iteration (s): 2.23 | learning rate: 2.440E-05 | global batch size: 512 | lm loss: 1.885702E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.614 | TFLOPs: 23.64 | +63: iteration 66520/ 73814 | consumed samples: 34058240 | consumed tokens: 69751275520 | elapsed time per iteration (s): 2.23 | learning rate: 2.439E-05 | global batch size: 512 | lm loss: 1.888672E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.794 | TFLOPs: 23.66 | +63: iteration 66530/ 73814 | consumed samples: 34063360 | consumed tokens: 69761761280 | elapsed time per iteration (s): 2.24 | learning rate: 2.438E-05 | global batch size: 512 | lm loss: 1.868595E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.494 | TFLOPs: 23.52 | +63: iteration 66540/ 73814 | consumed samples: 34068480 | consumed tokens: 69772247040 | elapsed time per iteration (s): 2.30 | learning rate: 2.437E-05 | global batch size: 512 | lm loss: 1.893909E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.283 | TFLOPs: 22.88 | +63: iteration 66550/ 73814 | consumed samples: 34073600 | consumed tokens: 69782732800 | elapsed time per iteration (s): 2.37 | learning rate: 2.435E-05 | global batch size: 512 | lm loss: 1.897607E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.289 | TFLOPs: 22.27 | +63: iteration 66560/ 73814 | consumed samples: 34078720 | consumed tokens: 69793218560 | elapsed time per iteration (s): 2.22 | learning rate: 2.434E-05 | global batch size: 512 | lm loss: 1.868555E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.122 | TFLOPs: 23.69 | +63: iteration 66570/ 73814 | consumed samples: 34083840 | consumed tokens: 69803704320 | elapsed time per iteration (s): 2.25 | learning rate: 2.433E-05 | global batch size: 512 | lm loss: 1.882979E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.932 | TFLOPs: 23.46 | +63: iteration 66580/ 73814 | consumed samples: 34088960 | consumed tokens: 69814190080 | elapsed time per iteration (s): 2.33 | learning rate: 2.432E-05 | global batch size: 512 | lm loss: 1.887414E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.199 | TFLOPs: 22.67 | +63: iteration 66590/ 73814 | consumed samples: 34094080 | consumed tokens: 69824675840 | elapsed time per iteration (s): 2.23 | learning rate: 2.431E-05 | global batch size: 512 | lm loss: 1.877271E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.116 | TFLOPs: 23.59 | +63: iteration 66600/ 73814 | consumed samples: 34099200 | consumed tokens: 69835161600 | elapsed time per iteration (s): 2.23 | learning rate: 2.429E-05 | global batch size: 512 | lm loss: 1.897776E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.435 | TFLOPs: 23.62 | +63: iteration 66610/ 73814 | consumed samples: 34104320 | consumed tokens: 69845647360 | elapsed time per iteration (s): 2.28 | learning rate: 2.428E-05 | global batch size: 512 | lm loss: 1.888838E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.722 | TFLOPs: 23.13 | +63: iteration 66620/ 73814 | consumed samples: 34109440 | consumed tokens: 69856133120 | elapsed time per iteration (s): 2.24 | learning rate: 2.427E-05 | global batch size: 512 | lm loss: 1.894359E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.107 | TFLOPs: 23.48 | +63: iteration 66630/ 73814 | consumed samples: 34114560 | consumed tokens: 69866618880 | elapsed time per iteration (s): 2.24 | learning rate: 2.426E-05 | global batch size: 512 | lm loss: 1.895202E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.701 | TFLOPs: 23.54 | +63: iteration 66640/ 73814 | consumed samples: 34119680 | consumed tokens: 69877104640 | elapsed time per iteration (s): 2.23 | learning rate: 2.425E-05 | global batch size: 512 | lm loss: 1.899455E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.055 | TFLOPs: 23.68 | +63: iteration 66650/ 73814 | consumed samples: 34124800 | consumed tokens: 69887590400 | elapsed time per iteration (s): 2.23 | learning rate: 2.424E-05 | global batch size: 512 | lm loss: 1.893393E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.774 | TFLOPs: 23.65 | +63: iteration 66660/ 73814 | consumed samples: 34129920 | consumed tokens: 69898076160 | elapsed time per iteration (s): 2.27 | learning rate: 2.422E-05 | global batch size: 512 | lm loss: 1.884249E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.946 | TFLOPs: 23.26 | +63: iteration 66670/ 73814 | consumed samples: 34135040 | consumed tokens: 69908561920 | elapsed time per iteration (s): 2.23 | learning rate: 2.421E-05 | global batch size: 512 | lm loss: 1.892480E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.742 | TFLOPs: 23.65 | +63: iteration 66680/ 73814 | consumed samples: 34140160 | consumed tokens: 69919047680 | elapsed time per iteration (s): 2.22 | learning rate: 2.420E-05 | global batch size: 512 | lm loss: 1.888994E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.187 | TFLOPs: 23.70 | +63: iteration 66690/ 73814 | consumed samples: 34145280 | consumed tokens: 69929533440 | elapsed time per iteration (s): 2.25 | learning rate: 2.419E-05 | global batch size: 512 | lm loss: 1.890108E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.845 | TFLOPs: 23.46 | +63: iteration 66700/ 73814 | consumed samples: 34150400 | consumed tokens: 69940019200 | elapsed time per iteration (s): 2.23 | learning rate: 2.418E-05 | global batch size: 512 | lm loss: 1.887606E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.619 | TFLOPs: 23.64 | +63: iteration 66710/ 73814 | consumed samples: 34155520 | consumed tokens: 69950504960 | elapsed time per iteration (s): 2.34 | learning rate: 2.417E-05 | global batch size: 512 | lm loss: 1.868854E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.831 | TFLOPs: 22.53 | +63: iteration 66720/ 73814 | consumed samples: 34160640 | consumed tokens: 69960990720 | elapsed time per iteration (s): 2.23 | learning rate: 2.415E-05 | global batch size: 512 | lm loss: 1.902938E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.679 | TFLOPs: 23.64 | +63: iteration 66730/ 73814 | consumed samples: 34165760 | consumed tokens: 69971476480 | elapsed time per iteration (s): 2.22 | learning rate: 2.414E-05 | global batch size: 512 | lm loss: 1.889646E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.288 | TFLOPs: 23.71 | +63: iteration 66740/ 73814 | consumed samples: 34170880 | consumed tokens: 69981962240 | elapsed time per iteration (s): 2.24 | learning rate: 2.413E-05 | global batch size: 512 | lm loss: 1.873737E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.698 | TFLOPs: 23.54 | +63: iteration 66750/ 73814 | consumed samples: 34176000 | consumed tokens: 69992448000 | elapsed time per iteration (s): 2.24 | learning rate: 2.412E-05 | global batch size: 512 | lm loss: 1.885022E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.807 | TFLOPs: 23.55 | +63: iteration 66760/ 73814 | consumed samples: 34181120 | consumed tokens: 70002933760 | elapsed time per iteration (s): 2.23 | learning rate: 2.411E-05 | global batch size: 512 | lm loss: 1.870572E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.331 | TFLOPs: 23.61 | +63: iteration 66770/ 73814 | consumed samples: 34186240 | consumed tokens: 70013419520 | elapsed time per iteration (s): 2.23 | learning rate: 2.410E-05 | global batch size: 512 | lm loss: 1.876223E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.522 | TFLOPs: 23.63 | +63: iteration 66780/ 73814 | consumed samples: 34191360 | consumed tokens: 70023905280 | elapsed time per iteration (s): 2.23 | learning rate: 2.408E-05 | global batch size: 512 | lm loss: 1.880927E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.588 | TFLOPs: 23.64 | +63: iteration 66790/ 73814 | consumed samples: 34196480 | consumed tokens: 70034391040 | elapsed time per iteration (s): 2.27 | learning rate: 2.407E-05 | global batch size: 512 | lm loss: 1.901714E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.739 | TFLOPs: 23.24 | +63: iteration 66800/ 73814 | consumed samples: 34201600 | consumed tokens: 70044876800 | elapsed time per iteration (s): 2.23 | learning rate: 2.406E-05 | global batch size: 512 | lm loss: 1.900566E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.622 | TFLOPs: 23.64 | +63: iteration 66810/ 73814 | consumed samples: 34206720 | consumed tokens: 70055362560 | elapsed time per iteration (s): 2.24 | learning rate: 2.405E-05 | global batch size: 512 | lm loss: 1.897865E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.181 | TFLOPs: 23.49 | +63: iteration 66820/ 73814 | consumed samples: 34211840 | consumed tokens: 70065848320 | elapsed time per iteration (s): 2.24 | learning rate: 2.404E-05 | global batch size: 512 | lm loss: 1.882400E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.939 | TFLOPs: 23.57 | +63: iteration 66830/ 73814 | consumed samples: 34216960 | consumed tokens: 70076334080 | elapsed time per iteration (s): 2.23 | learning rate: 2.403E-05 | global batch size: 512 | lm loss: 1.869782E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.439 | TFLOPs: 23.62 | +63: iteration 66840/ 73814 | consumed samples: 34222080 | consumed tokens: 70086819840 | elapsed time per iteration (s): 2.45 | learning rate: 2.402E-05 | global batch size: 512 | lm loss: 1.893497E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.352 | TFLOPs: 21.55 | +63: iteration 66850/ 73814 | consumed samples: 34227200 | consumed tokens: 70097305600 | elapsed time per iteration (s): 2.24 | learning rate: 2.400E-05 | global batch size: 512 | lm loss: 1.874493E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.976 | TFLOPs: 23.57 | +63: iteration 66860/ 73814 | consumed samples: 34232320 | consumed tokens: 70107791360 | elapsed time per iteration (s): 2.26 | learning rate: 2.399E-05 | global batch size: 512 | lm loss: 1.884358E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.622 | TFLOPs: 23.33 | +63: iteration 66870/ 73814 | consumed samples: 34237440 | consumed tokens: 70118277120 | elapsed time per iteration (s): 2.25 | learning rate: 2.398E-05 | global batch size: 512 | lm loss: 1.919958E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.793 | TFLOPs: 23.45 | +63: iteration 66880/ 73814 | consumed samples: 34242560 | consumed tokens: 70128762880 | elapsed time per iteration (s): 2.28 | learning rate: 2.397E-05 | global batch size: 512 | lm loss: 1.870769E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.887 | TFLOPs: 23.15 | +63: iteration 66890/ 73814 | consumed samples: 34247680 | consumed tokens: 70139248640 | elapsed time per iteration (s): 2.22 | learning rate: 2.396E-05 | global batch size: 512 | lm loss: 1.893050E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.154 | TFLOPs: 23.69 | +63: iteration 66900/ 73814 | consumed samples: 34252800 | consumed tokens: 70149734400 | elapsed time per iteration (s): 2.25 | learning rate: 2.395E-05 | global batch size: 512 | lm loss: 1.898492E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.607 | TFLOPs: 23.43 | +63: iteration 66910/ 73814 | consumed samples: 34257920 | consumed tokens: 70160220160 | elapsed time per iteration (s): 2.23 | learning rate: 2.394E-05 | global batch size: 512 | lm loss: 1.886858E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.845 | TFLOPs: 23.66 | +63: iteration 66920/ 73814 | consumed samples: 34263040 | consumed tokens: 70170705920 | elapsed time per iteration (s): 2.25 | learning rate: 2.392E-05 | global batch size: 512 | lm loss: 1.888836E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.095 | TFLOPs: 23.38 | +63: iteration 66930/ 73814 | consumed samples: 34268160 | consumed tokens: 70181191680 | elapsed time per iteration (s): 2.23 | learning rate: 2.391E-05 | global batch size: 512 | lm loss: 1.876123E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.864 | TFLOPs: 23.66 | +63: iteration 66940/ 73814 | consumed samples: 34273280 | consumed tokens: 70191677440 | elapsed time per iteration (s): 2.22 | learning rate: 2.390E-05 | global batch size: 512 | lm loss: 1.868119E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.187 | TFLOPs: 23.70 | +63: iteration 66950/ 73814 | consumed samples: 34278400 | consumed tokens: 70202163200 | elapsed time per iteration (s): 2.23 | learning rate: 2.389E-05 | global batch size: 512 | lm loss: 1.893552E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.421 | TFLOPs: 23.62 | +63: iteration 66960/ 73814 | consumed samples: 34283520 | consumed tokens: 70212648960 | elapsed time per iteration (s): 2.26 | learning rate: 2.388E-05 | global batch size: 512 | lm loss: 1.874629E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.916 | TFLOPs: 23.36 | +63: iteration 66970/ 73814 | consumed samples: 34288640 | consumed tokens: 70223134720 | elapsed time per iteration (s): 2.22 | learning rate: 2.387E-05 | global batch size: 512 | lm loss: 1.884899E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.216 | TFLOPs: 23.70 | +63: iteration 66980/ 73814 | consumed samples: 34293760 | consumed tokens: 70233620480 | elapsed time per iteration (s): 2.23 | learning rate: 2.386E-05 | global batch size: 512 | lm loss: 1.863692E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.468 | TFLOPs: 23.62 | +63: iteration 66990/ 73814 | consumed samples: 34298880 | consumed tokens: 70244106240 | elapsed time per iteration (s): 2.24 | learning rate: 2.385E-05 | global batch size: 512 | lm loss: 1.868927E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.353 | TFLOPs: 23.51 | +63: iteration 67000/ 73814 | consumed samples: 34304000 | consumed tokens: 70254592000 | elapsed time per iteration (s): 2.23 | learning rate: 2.383E-05 | global batch size: 512 | lm loss: 1.904327E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.641 | TFLOPs: 23.64 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 67000 | lm loss value: 1.774746E+00 | lm loss PPL: 5.898785E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 67010/ 73814 | consumed samples: 34309120 | consumed tokens: 70265077760 | elapsed time per iteration (s): 2.29 | learning rate: 2.382E-05 | global batch size: 512 | lm loss: 1.886192E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.402 | TFLOPs: 23.00 | +63: iteration 67020/ 73814 | consumed samples: 34314240 | consumed tokens: 70275563520 | elapsed time per iteration (s): 2.23 | learning rate: 2.381E-05 | global batch size: 512 | lm loss: 1.861380E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.096 | TFLOPs: 23.69 | +63: iteration 67030/ 73814 | consumed samples: 34319360 | consumed tokens: 70286049280 | elapsed time per iteration (s): 2.23 | learning rate: 2.380E-05 | global batch size: 512 | lm loss: 1.883841E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.899 | TFLOPs: 23.67 | +63: iteration 67040/ 73814 | consumed samples: 34324480 | consumed tokens: 70296535040 | elapsed time per iteration (s): 2.31 | learning rate: 2.379E-05 | global batch size: 512 | lm loss: 1.877950E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.990 | TFLOPs: 22.85 | +63: iteration 67050/ 73814 | consumed samples: 34329600 | consumed tokens: 70307020800 | elapsed time per iteration (s): 2.39 | learning rate: 2.378E-05 | global batch size: 512 | lm loss: 1.888408E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.872 | TFLOPs: 22.02 | +63: iteration 67060/ 73814 | consumed samples: 34334720 | consumed tokens: 70317506560 | elapsed time per iteration (s): 2.36 | learning rate: 2.377E-05 | global batch size: 512 | lm loss: 1.864430E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.946 | TFLOPs: 22.33 | +63: iteration 67070/ 73814 | consumed samples: 34339840 | consumed tokens: 70327992320 | elapsed time per iteration (s): 2.24 | learning rate: 2.376E-05 | global batch size: 512 | lm loss: 1.909176E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.889 | TFLOPs: 23.56 | +63: iteration 67080/ 73814 | consumed samples: 34344960 | consumed tokens: 70338478080 | elapsed time per iteration (s): 2.23 | learning rate: 2.375E-05 | global batch size: 512 | lm loss: 1.886849E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.964 | TFLOPs: 23.67 | +63: iteration 67090/ 73814 | consumed samples: 34350080 | consumed tokens: 70348963840 | elapsed time per iteration (s): 2.25 | learning rate: 2.373E-05 | global batch size: 512 | lm loss: 1.896682E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.505 | TFLOPs: 23.42 | +63: iteration 67100/ 73814 | consumed samples: 34355200 | consumed tokens: 70359449600 | elapsed time per iteration (s): 2.36 | learning rate: 2.372E-05 | global batch size: 512 | lm loss: 1.894696E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.039 | TFLOPs: 22.34 | +63: iteration 67110/ 73814 | consumed samples: 34360320 | consumed tokens: 70369935360 | elapsed time per iteration (s): 2.23 | learning rate: 2.371E-05 | global batch size: 512 | lm loss: 1.886836E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.156 | TFLOPs: 23.59 | +63: iteration 67120/ 73814 | consumed samples: 34365440 | consumed tokens: 70380421120 | elapsed time per iteration (s): 2.23 | learning rate: 2.370E-05 | global batch size: 512 | lm loss: 1.887680E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.856 | TFLOPs: 23.66 | +63: iteration 67130/ 73814 | consumed samples: 34370560 | consumed tokens: 70390906880 | elapsed time per iteration (s): 2.38 | learning rate: 2.369E-05 | global batch size: 512 | lm loss: 1.884005E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.556 | TFLOPs: 22.19 | +63: iteration 67140/ 73814 | consumed samples: 34375680 | consumed tokens: 70401392640 | elapsed time per iteration (s): 2.24 | learning rate: 2.368E-05 | global batch size: 512 | lm loss: 1.887406E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.577 | TFLOPs: 23.53 | +63: iteration 67150/ 73814 | consumed samples: 34380800 | consumed tokens: 70411878400 | elapsed time per iteration (s): 2.24 | learning rate: 2.367E-05 | global batch size: 512 | lm loss: 1.895718E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.184 | TFLOPs: 23.49 | +63: iteration 67160/ 73814 | consumed samples: 34385920 | consumed tokens: 70422364160 | elapsed time per iteration (s): 2.24 | learning rate: 2.366E-05 | global batch size: 512 | lm loss: 1.887846E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.557 | TFLOPs: 23.53 | +63: iteration 67170/ 73814 | consumed samples: 34391040 | consumed tokens: 70432849920 | elapsed time per iteration (s): 2.23 | learning rate: 2.365E-05 | global batch size: 512 | lm loss: 1.885177E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.710 | TFLOPs: 23.65 | +63: iteration 67180/ 73814 | consumed samples: 34396160 | consumed tokens: 70443335680 | elapsed time per iteration (s): 2.25 | learning rate: 2.364E-05 | global batch size: 512 | lm loss: 1.886219E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.564 | TFLOPs: 23.43 | +63: iteration 67190/ 73814 | consumed samples: 34401280 | consumed tokens: 70453821440 | elapsed time per iteration (s): 2.24 | learning rate: 2.363E-05 | global batch size: 512 | lm loss: 1.866206E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.808 | TFLOPs: 23.55 | +63: iteration 67200/ 73814 | consumed samples: 34406400 | consumed tokens: 70464307200 | elapsed time per iteration (s): 2.25 | learning rate: 2.361E-05 | global batch size: 512 | lm loss: 1.882869E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.856 | TFLOPs: 23.46 | +63: iteration 67210/ 73814 | consumed samples: 34411520 | consumed tokens: 70474792960 | elapsed time per iteration (s): 2.22 | learning rate: 2.360E-05 | global batch size: 512 | lm loss: 1.891582E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.146 | TFLOPs: 23.69 | +63: iteration 67220/ 73814 | consumed samples: 34416640 | consumed tokens: 70485278720 | elapsed time per iteration (s): 2.25 | learning rate: 2.359E-05 | global batch size: 512 | lm loss: 1.897825E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.614 | TFLOPs: 23.43 | +63: iteration 67230/ 73814 | consumed samples: 34421760 | consumed tokens: 70495764480 | elapsed time per iteration (s): 2.24 | learning rate: 2.358E-05 | global batch size: 512 | lm loss: 1.872457E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.963 | TFLOPs: 23.57 | +63: iteration 67240/ 73814 | consumed samples: 34426880 | consumed tokens: 70506250240 | elapsed time per iteration (s): 2.25 | learning rate: 2.357E-05 | global batch size: 512 | lm loss: 1.892284E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.048 | TFLOPs: 23.48 | +63: iteration 67250/ 73814 | consumed samples: 34432000 | consumed tokens: 70516736000 | elapsed time per iteration (s): 2.23 | learning rate: 2.356E-05 | global batch size: 512 | lm loss: 1.913427E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.498 | TFLOPs: 23.63 | +63: iteration 67260/ 73814 | consumed samples: 34437120 | consumed tokens: 70527221760 | elapsed time per iteration (s): 2.23 | learning rate: 2.355E-05 | global batch size: 512 | lm loss: 1.898725E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.946 | TFLOPs: 23.67 | +63: iteration 67270/ 73814 | consumed samples: 34442240 | consumed tokens: 70537707520 | elapsed time per iteration (s): 2.24 | learning rate: 2.354E-05 | global batch size: 512 | lm loss: 1.888649E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.802 | TFLOPs: 23.55 | +63: iteration 67280/ 73814 | consumed samples: 34447360 | consumed tokens: 70548193280 | elapsed time per iteration (s): 2.23 | learning rate: 2.353E-05 | global batch size: 512 | lm loss: 1.885288E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.244 | TFLOPs: 23.60 | +63: iteration 67290/ 73814 | consumed samples: 34452480 | consumed tokens: 70558679040 | elapsed time per iteration (s): 2.24 | learning rate: 2.352E-05 | global batch size: 512 | lm loss: 1.895036E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.325 | TFLOPs: 23.50 | +63: iteration 67300/ 73814 | consumed samples: 34457600 | consumed tokens: 70569164800 | elapsed time per iteration (s): 2.30 | learning rate: 2.351E-05 | global batch size: 512 | lm loss: 1.880961E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.141 | TFLOPs: 22.87 | +63: iteration 67310/ 73814 | consumed samples: 34462720 | consumed tokens: 70579650560 | elapsed time per iteration (s): 2.23 | learning rate: 2.350E-05 | global batch size: 512 | lm loss: 1.876272E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.741 | TFLOPs: 23.65 | +63: iteration 67320/ 73814 | consumed samples: 34467840 | consumed tokens: 70590136320 | elapsed time per iteration (s): 2.23 | learning rate: 2.349E-05 | global batch size: 512 | lm loss: 1.880423E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.828 | TFLOPs: 23.66 | +63: iteration 67330/ 73814 | consumed samples: 34472960 | consumed tokens: 70600622080 | elapsed time per iteration (s): 2.23 | learning rate: 2.347E-05 | global batch size: 512 | lm loss: 1.865746E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.224 | TFLOPs: 23.60 | +63: iteration 67340/ 73814 | consumed samples: 34478080 | consumed tokens: 70611107840 | elapsed time per iteration (s): 2.24 | learning rate: 2.346E-05 | global batch size: 512 | lm loss: 1.891923E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.821 | TFLOPs: 23.56 | +63: iteration 67350/ 73814 | consumed samples: 34483200 | consumed tokens: 70621593600 | elapsed time per iteration (s): 2.42 | learning rate: 2.345E-05 | global batch size: 512 | lm loss: 1.872653E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.873 | TFLOPs: 21.81 | +63: iteration 67360/ 73814 | consumed samples: 34488320 | consumed tokens: 70632079360 | elapsed time per iteration (s): 2.39 | learning rate: 2.344E-05 | global batch size: 512 | lm loss: 1.902637E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.125 | TFLOPs: 22.04 | +63: iteration 67370/ 73814 | consumed samples: 34493440 | consumed tokens: 70642565120 | elapsed time per iteration (s): 2.26 | learning rate: 2.343E-05 | global batch size: 512 | lm loss: 1.909273E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.377 | TFLOPs: 23.30 | +63: iteration 67380/ 73814 | consumed samples: 34498560 | consumed tokens: 70653050880 | elapsed time per iteration (s): 2.26 | learning rate: 2.342E-05 | global batch size: 512 | lm loss: 1.902229E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.891 | TFLOPs: 23.36 | +63: iteration 67390/ 73814 | consumed samples: 34503680 | consumed tokens: 70663536640 | elapsed time per iteration (s): 2.25 | learning rate: 2.341E-05 | global batch size: 512 | lm loss: 1.893910E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.025 | TFLOPs: 23.47 | +63: iteration 67400/ 73814 | consumed samples: 34508800 | consumed tokens: 70674022400 | elapsed time per iteration (s): 2.24 | learning rate: 2.340E-05 | global batch size: 512 | lm loss: 1.898491E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.131 | TFLOPs: 23.48 | +63: iteration 67410/ 73814 | consumed samples: 34513920 | consumed tokens: 70684508160 | elapsed time per iteration (s): 2.23 | learning rate: 2.339E-05 | global batch size: 512 | lm loss: 1.902734E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.916 | TFLOPs: 23.67 | +63: iteration 67420/ 73814 | consumed samples: 34519040 | consumed tokens: 70694993920 | elapsed time per iteration (s): 2.39 | learning rate: 2.338E-05 | global batch size: 512 | lm loss: 1.878299E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.477 | TFLOPs: 22.08 | +63: iteration 67430/ 73814 | consumed samples: 34524160 | consumed tokens: 70705479680 | elapsed time per iteration (s): 2.23 | learning rate: 2.337E-05 | global batch size: 512 | lm loss: 1.898549E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.991 | TFLOPs: 23.68 | +63: iteration 67440/ 73814 | consumed samples: 34529280 | consumed tokens: 70715965440 | elapsed time per iteration (s): 2.24 | learning rate: 2.336E-05 | global batch size: 512 | lm loss: 1.885827E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.621 | TFLOPs: 23.54 | +63: iteration 67450/ 73814 | consumed samples: 34534400 | consumed tokens: 70726451200 | elapsed time per iteration (s): 2.26 | learning rate: 2.335E-05 | global batch size: 512 | lm loss: 1.895214E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.495 | TFLOPs: 23.32 | +63: iteration 67460/ 73814 | consumed samples: 34539520 | consumed tokens: 70736936960 | elapsed time per iteration (s): 2.26 | learning rate: 2.334E-05 | global batch size: 512 | lm loss: 1.885273E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.900 | TFLOPs: 23.36 | +63: iteration 67470/ 73814 | consumed samples: 34544640 | consumed tokens: 70747422720 | elapsed time per iteration (s): 2.22 | learning rate: 2.333E-05 | global batch size: 512 | lm loss: 1.883817E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.253 | TFLOPs: 23.70 | +63: iteration 67480/ 73814 | consumed samples: 34549760 | consumed tokens: 70757908480 | elapsed time per iteration (s): 2.23 | learning rate: 2.332E-05 | global batch size: 512 | lm loss: 1.912385E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.105 | TFLOPs: 23.69 | +63: iteration 67490/ 73814 | consumed samples: 34554880 | consumed tokens: 70768394240 | elapsed time per iteration (s): 2.53 | learning rate: 2.331E-05 | global batch size: 512 | lm loss: 1.916826E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.403 | TFLOPs: 20.84 | +63: iteration 67500/ 73814 | consumed samples: 34560000 | consumed tokens: 70778880000 | elapsed time per iteration (s): 2.37 | learning rate: 2.330E-05 | global batch size: 512 | lm loss: 1.890756E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.448 | TFLOPs: 22.28 | +63: iteration 67510/ 73814 | consumed samples: 34565120 | consumed tokens: 70789365760 | elapsed time per iteration (s): 2.35 | learning rate: 2.329E-05 | global batch size: 512 | lm loss: 1.895584E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.814 | TFLOPs: 22.42 | +63: iteration 67520/ 73814 | consumed samples: 34570240 | consumed tokens: 70799851520 | elapsed time per iteration (s): 2.24 | learning rate: 2.328E-05 | global batch size: 512 | lm loss: 1.879998E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.597 | TFLOPs: 23.53 | +63: iteration 67530/ 73814 | consumed samples: 34575360 | consumed tokens: 70810337280 | elapsed time per iteration (s): 2.23 | learning rate: 2.326E-05 | global batch size: 512 | lm loss: 1.894358E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.645 | TFLOPs: 23.64 | +63: iteration 67540/ 73814 | consumed samples: 34580480 | consumed tokens: 70820823040 | elapsed time per iteration (s): 2.23 | learning rate: 2.325E-05 | global batch size: 512 | lm loss: 1.890501E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.748 | TFLOPs: 23.65 | +63: iteration 67550/ 73814 | consumed samples: 34585600 | consumed tokens: 70831308800 | elapsed time per iteration (s): 2.23 | learning rate: 2.324E-05 | global batch size: 512 | lm loss: 1.914531E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.838 | TFLOPs: 23.66 | +63: iteration 67560/ 73814 | consumed samples: 34590720 | consumed tokens: 70841794560 | elapsed time per iteration (s): 2.42 | learning rate: 2.323E-05 | global batch size: 512 | lm loss: 1.900268E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.166 | TFLOPs: 21.74 | +63: iteration 67570/ 73814 | consumed samples: 34595840 | consumed tokens: 70852280320 | elapsed time per iteration (s): 2.30 | learning rate: 2.322E-05 | global batch size: 512 | lm loss: 1.913023E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.071 | TFLOPs: 22.96 | +63: iteration 67580/ 73814 | consumed samples: 34600960 | consumed tokens: 70862766080 | elapsed time per iteration (s): 2.22 | learning rate: 2.321E-05 | global batch size: 512 | lm loss: 1.889453E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.296 | TFLOPs: 23.71 | +63: iteration 67590/ 73814 | consumed samples: 34606080 | consumed tokens: 70873251840 | elapsed time per iteration (s): 2.39 | learning rate: 2.320E-05 | global batch size: 512 | lm loss: 1.860005E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.491 | TFLOPs: 22.08 | +63: iteration 67600/ 73814 | consumed samples: 34611200 | consumed tokens: 70883737600 | elapsed time per iteration (s): 2.24 | learning rate: 2.319E-05 | global batch size: 512 | lm loss: 1.890077E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.198 | TFLOPs: 23.49 | +63: iteration 67610/ 73814 | consumed samples: 34616320 | consumed tokens: 70894223360 | elapsed time per iteration (s): 2.25 | learning rate: 2.318E-05 | global batch size: 512 | lm loss: 1.925385E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.543 | TFLOPs: 23.42 | +63: iteration 67620/ 73814 | consumed samples: 34621440 | consumed tokens: 70904709120 | elapsed time per iteration (s): 2.37 | learning rate: 2.317E-05 | global batch size: 512 | lm loss: 1.893569E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.592 | TFLOPs: 22.19 | +63: iteration 67630/ 73814 | consumed samples: 34626560 | consumed tokens: 70915194880 | elapsed time per iteration (s): 2.25 | learning rate: 2.316E-05 | global batch size: 512 | lm loss: 1.889419E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.872 | TFLOPs: 23.46 | +63: iteration 67640/ 73814 | consumed samples: 34631680 | consumed tokens: 70925680640 | elapsed time per iteration (s): 2.37 | learning rate: 2.315E-05 | global batch size: 512 | lm loss: 1.895146E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.891 | TFLOPs: 22.22 | +63: iteration 67650/ 73814 | consumed samples: 34636800 | consumed tokens: 70936166400 | elapsed time per iteration (s): 2.41 | learning rate: 2.314E-05 | global batch size: 512 | lm loss: 1.882378E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.561 | TFLOPs: 21.88 | +63: iteration 67660/ 73814 | consumed samples: 34641920 | consumed tokens: 70946652160 | elapsed time per iteration (s): 2.25 | learning rate: 2.313E-05 | global batch size: 512 | lm loss: 1.904752E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.976 | TFLOPs: 23.47 | +63: iteration 67670/ 73814 | consumed samples: 34647040 | consumed tokens: 70957137920 | elapsed time per iteration (s): 2.23 | learning rate: 2.312E-05 | global batch size: 512 | lm loss: 1.898549E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.879 | TFLOPs: 23.66 | +63: iteration 67680/ 73814 | consumed samples: 34652160 | consumed tokens: 70967623680 | elapsed time per iteration (s): 2.64 | learning rate: 2.311E-05 | global batch size: 512 | lm loss: 1.882115E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 193.864 | TFLOPs: 19.96 | +63: iteration 67690/ 73814 | consumed samples: 34657280 | consumed tokens: 70978109440 | elapsed time per iteration (s): 2.23 | learning rate: 2.310E-05 | global batch size: 512 | lm loss: 1.901764E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.239 | TFLOPs: 23.60 | +63: iteration 67700/ 73814 | consumed samples: 34662400 | consumed tokens: 70988595200 | elapsed time per iteration (s): 2.23 | learning rate: 2.309E-05 | global batch size: 512 | lm loss: 1.863724E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.428 | TFLOPs: 23.62 | +63: iteration 67710/ 73814 | consumed samples: 34667520 | consumed tokens: 70999080960 | elapsed time per iteration (s): 2.23 | learning rate: 2.308E-05 | global batch size: 512 | lm loss: 1.881607E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.991 | TFLOPs: 23.68 | +63: iteration 67720/ 73814 | consumed samples: 34672640 | consumed tokens: 71009566720 | elapsed time per iteration (s): 2.25 | learning rate: 2.307E-05 | global batch size: 512 | lm loss: 1.891211E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.313 | TFLOPs: 23.40 | +63: iteration 67730/ 73814 | consumed samples: 34677760 | consumed tokens: 71020052480 | elapsed time per iteration (s): 2.25 | learning rate: 2.306E-05 | global batch size: 512 | lm loss: 1.894923E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.784 | TFLOPs: 23.45 | +63: iteration 67740/ 73814 | consumed samples: 34682880 | consumed tokens: 71030538240 | elapsed time per iteration (s): 2.24 | learning rate: 2.305E-05 | global batch size: 512 | lm loss: 1.893280E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.038 | TFLOPs: 23.58 | +63: iteration 67750/ 73814 | consumed samples: 34688000 | consumed tokens: 71041024000 | elapsed time per iteration (s): 2.24 | learning rate: 2.304E-05 | global batch size: 512 | lm loss: 1.896245E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.458 | TFLOPs: 23.52 | +63: iteration 67760/ 73814 | consumed samples: 34693120 | consumed tokens: 71051509760 | elapsed time per iteration (s): 2.23 | learning rate: 2.303E-05 | global batch size: 512 | lm loss: 1.907732E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.236 | TFLOPs: 23.60 | +63: iteration 67770/ 73814 | consumed samples: 34698240 | consumed tokens: 71061995520 | elapsed time per iteration (s): 2.24 | learning rate: 2.302E-05 | global batch size: 512 | lm loss: 1.894485E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.196 | TFLOPs: 23.49 | +63: iteration 67780/ 73814 | consumed samples: 34703360 | consumed tokens: 71072481280 | elapsed time per iteration (s): 2.24 | learning rate: 2.301E-05 | global batch size: 512 | lm loss: 1.878655E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.200 | TFLOPs: 23.49 | +63: iteration 67790/ 73814 | consumed samples: 34708480 | consumed tokens: 71082967040 | elapsed time per iteration (s): 2.29 | learning rate: 2.300E-05 | global batch size: 512 | lm loss: 1.896906E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.673 | TFLOPs: 23.03 | +63: iteration 67800/ 73814 | consumed samples: 34713600 | consumed tokens: 71093452800 | elapsed time per iteration (s): 2.27 | learning rate: 2.299E-05 | global batch size: 512 | lm loss: 1.867918E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.476 | TFLOPs: 23.21 | +63: iteration 67810/ 73814 | consumed samples: 34718720 | consumed tokens: 71103938560 | elapsed time per iteration (s): 2.23 | learning rate: 2.298E-05 | global batch size: 512 | lm loss: 1.897894E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.924 | TFLOPs: 23.67 | +63: iteration 67820/ 73814 | consumed samples: 34723840 | consumed tokens: 71114424320 | elapsed time per iteration (s): 2.35 | learning rate: 2.297E-05 | global batch size: 512 | lm loss: 1.891867E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.508 | TFLOPs: 22.39 | +63: iteration 67830/ 73814 | consumed samples: 34728960 | consumed tokens: 71124910080 | elapsed time per iteration (s): 2.23 | learning rate: 2.296E-05 | global batch size: 512 | lm loss: 1.923722E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.653 | TFLOPs: 23.64 | +63: iteration 67840/ 73814 | consumed samples: 34734080 | consumed tokens: 71135395840 | elapsed time per iteration (s): 2.23 | learning rate: 2.295E-05 | global batch size: 512 | lm loss: 1.920368E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.472 | TFLOPs: 23.62 | +63: iteration 67850/ 73814 | consumed samples: 34739200 | consumed tokens: 71145881600 | elapsed time per iteration (s): 2.23 | learning rate: 2.294E-05 | global batch size: 512 | lm loss: 1.876154E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.697 | TFLOPs: 23.65 | +63: iteration 67860/ 73814 | consumed samples: 34744320 | consumed tokens: 71156367360 | elapsed time per iteration (s): 2.23 | learning rate: 2.293E-05 | global batch size: 512 | lm loss: 1.891343E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.922 | TFLOPs: 23.67 | +63: iteration 67870/ 73814 | consumed samples: 34749440 | consumed tokens: 71166853120 | elapsed time per iteration (s): 2.23 | learning rate: 2.292E-05 | global batch size: 512 | lm loss: 1.874545E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.648 | TFLOPs: 23.64 | +63: iteration 67880/ 73814 | consumed samples: 34754560 | consumed tokens: 71177338880 | elapsed time per iteration (s): 2.29 | learning rate: 2.291E-05 | global batch size: 512 | lm loss: 1.887127E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.434 | TFLOPs: 23.00 | +63: iteration 67890/ 73814 | consumed samples: 34759680 | consumed tokens: 71187824640 | elapsed time per iteration (s): 2.32 | learning rate: 2.290E-05 | global batch size: 512 | lm loss: 1.874802E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.467 | TFLOPs: 22.70 | +63: iteration 67900/ 73814 | consumed samples: 34764800 | consumed tokens: 71198310400 | elapsed time per iteration (s): 2.40 | learning rate: 2.289E-05 | global batch size: 512 | lm loss: 1.888398E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.672 | TFLOPs: 22.00 | +63: iteration 67910/ 73814 | consumed samples: 34769920 | consumed tokens: 71208796160 | elapsed time per iteration (s): 2.42 | learning rate: 2.288E-05 | global batch size: 512 | lm loss: 1.879653E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.806 | TFLOPs: 21.80 | +63: iteration 67920/ 73814 | consumed samples: 34775040 | consumed tokens: 71219281920 | elapsed time per iteration (s): 2.37 | learning rate: 2.287E-05 | global batch size: 512 | lm loss: 1.881291E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.431 | TFLOPs: 22.28 | +63: iteration 67930/ 73814 | consumed samples: 34780160 | consumed tokens: 71229767680 | elapsed time per iteration (s): 2.38 | learning rate: 2.286E-05 | global batch size: 512 | lm loss: 1.885653E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.353 | TFLOPs: 22.17 | +63: iteration 67940/ 73814 | consumed samples: 34785280 | consumed tokens: 71240253440 | elapsed time per iteration (s): 2.56 | learning rate: 2.285E-05 | global batch size: 512 | lm loss: 1.875959E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.851 | TFLOPs: 20.57 | +63: iteration 67950/ 73814 | consumed samples: 34790400 | consumed tokens: 71250739200 | elapsed time per iteration (s): 2.46 | learning rate: 2.285E-05 | global batch size: 512 | lm loss: 1.884743E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 207.790 | TFLOPs: 21.39 | +63: iteration 67960/ 73814 | consumed samples: 34795520 | consumed tokens: 71261224960 | elapsed time per iteration (s): 3.11 | learning rate: 2.284E-05 | global batch size: 512 | lm loss: 1.896556E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 164.803 | TFLOPs: 16.97 | +63: iteration 67970/ 73814 | consumed samples: 34800640 | consumed tokens: 71271710720 | elapsed time per iteration (s): 2.70 | learning rate: 2.283E-05 | global batch size: 512 | lm loss: 1.904130E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 189.813 | TFLOPs: 19.54 | +63: iteration 67980/ 73814 | consumed samples: 34805760 | consumed tokens: 71282196480 | elapsed time per iteration (s): 2.52 | learning rate: 2.282E-05 | global batch size: 512 | lm loss: 1.911816E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.866 | TFLOPs: 20.88 | +63: iteration 67990/ 73814 | consumed samples: 34810880 | consumed tokens: 71292682240 | elapsed time per iteration (s): 2.27 | learning rate: 2.281E-05 | global batch size: 512 | lm loss: 1.892742E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.967 | TFLOPs: 23.26 | + 0: [2022-12-03 07:04:35,826] [INFO] [logging.py:68:log_dist] [Rank 0] step=68000, skipped=0, lr=[2.279708713750479e-05, 2.279708713750479e-05, 2.279708713750479e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 68000/ 73814 | consumed samples: 34816000 | consumed tokens: 71303168000 | elapsed time per iteration (s): 2.28 | learning rate: 2.280E-05 | global batch size: 512 | lm loss: 1.885761E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.501 | TFLOPs: 23.11 | + 0: steps: 68000 loss: 1.8732 iter time (s): 2.288 samples/sec: 223.786 +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 68000 | lm loss value: 1.736961E+00 | lm loss PPL: 5.680055E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 68010/ 73814 | consumed samples: 34821120 | consumed tokens: 71313653760 | elapsed time per iteration (s): 2.34 | learning rate: 2.279E-05 | global batch size: 512 | lm loss: 1.854901E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.022 | TFLOPs: 22.55 | +63: iteration 68020/ 73814 | consumed samples: 34826240 | consumed tokens: 71324139520 | elapsed time per iteration (s): 2.23 | learning rate: 2.278E-05 | global batch size: 512 | lm loss: 1.893962E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.869 | TFLOPs: 23.66 | +63: iteration 68030/ 73814 | consumed samples: 34831360 | consumed tokens: 71334625280 | elapsed time per iteration (s): 2.27 | learning rate: 2.277E-05 | global batch size: 512 | lm loss: 1.918285E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.856 | TFLOPs: 23.25 | +63: iteration 68040/ 73814 | consumed samples: 34836480 | consumed tokens: 71345111040 | elapsed time per iteration (s): 2.51 | learning rate: 2.276E-05 | global batch size: 512 | lm loss: 1.877389E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 203.657 | TFLOPs: 20.97 | +63: iteration 68050/ 73814 | consumed samples: 34841600 | consumed tokens: 71355596800 | elapsed time per iteration (s): 2.23 | learning rate: 2.275E-05 | global batch size: 512 | lm loss: 1.877538E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.333 | TFLOPs: 23.61 | +63: iteration 68060/ 73814 | consumed samples: 34846720 | consumed tokens: 71366082560 | elapsed time per iteration (s): 2.23 | learning rate: 2.274E-05 | global batch size: 512 | lm loss: 1.879993E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.656 | TFLOPs: 23.64 | +63: iteration 68070/ 73814 | consumed samples: 34851840 | consumed tokens: 71376568320 | elapsed time per iteration (s): 2.30 | learning rate: 2.273E-05 | global batch size: 512 | lm loss: 1.883819E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.913 | TFLOPs: 22.95 | +63: iteration 68080/ 73814 | consumed samples: 34856960 | consumed tokens: 71387054080 | elapsed time per iteration (s): 2.39 | learning rate: 2.272E-05 | global batch size: 512 | lm loss: 1.885471E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.803 | TFLOPs: 22.01 | +63: iteration 68090/ 73814 | consumed samples: 34862080 | consumed tokens: 71397539840 | elapsed time per iteration (s): 2.23 | learning rate: 2.271E-05 | global batch size: 512 | lm loss: 1.883422E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.089 | TFLOPs: 23.69 | +63: iteration 68100/ 73814 | consumed samples: 34867200 | consumed tokens: 71408025600 | elapsed time per iteration (s): 2.36 | learning rate: 2.270E-05 | global batch size: 512 | lm loss: 1.906597E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.183 | TFLOPs: 22.36 | +63: iteration 68110/ 73814 | consumed samples: 34872320 | consumed tokens: 71418511360 | elapsed time per iteration (s): 2.25 | learning rate: 2.269E-05 | global batch size: 512 | lm loss: 1.867807E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.815 | TFLOPs: 23.45 | +63: iteration 68120/ 73814 | consumed samples: 34877440 | consumed tokens: 71428997120 | elapsed time per iteration (s): 2.22 | learning rate: 2.268E-05 | global batch size: 512 | lm loss: 1.868514E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.324 | TFLOPs: 23.71 | +63: iteration 68130/ 73814 | consumed samples: 34882560 | consumed tokens: 71439482880 | elapsed time per iteration (s): 2.23 | learning rate: 2.267E-05 | global batch size: 512 | lm loss: 1.897819E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.681 | TFLOPs: 23.64 | +63: iteration 68140/ 73814 | consumed samples: 34887680 | consumed tokens: 71449968640 | elapsed time per iteration (s): 2.24 | learning rate: 2.266E-05 | global batch size: 512 | lm loss: 1.878267E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.277 | TFLOPs: 23.50 | +63: iteration 68150/ 73814 | consumed samples: 34892800 | consumed tokens: 71460454400 | elapsed time per iteration (s): 2.23 | learning rate: 2.266E-05 | global batch size: 512 | lm loss: 1.894612E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.850 | TFLOPs: 23.66 | +63: iteration 68160/ 73814 | consumed samples: 34897920 | consumed tokens: 71470940160 | elapsed time per iteration (s): 2.24 | learning rate: 2.265E-05 | global batch size: 512 | lm loss: 1.878789E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.014 | TFLOPs: 23.58 | +63: iteration 68170/ 73814 | consumed samples: 34903040 | consumed tokens: 71481425920 | elapsed time per iteration (s): 2.22 | learning rate: 2.264E-05 | global batch size: 512 | lm loss: 1.893153E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.159 | TFLOPs: 23.69 | +63: iteration 68180/ 73814 | consumed samples: 34908160 | consumed tokens: 71491911680 | elapsed time per iteration (s): 2.25 | learning rate: 2.263E-05 | global batch size: 512 | lm loss: 1.871632E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.926 | TFLOPs: 23.46 | +63: iteration 68190/ 73814 | consumed samples: 34913280 | consumed tokens: 71502397440 | elapsed time per iteration (s): 2.23 | learning rate: 2.262E-05 | global batch size: 512 | lm loss: 1.895736E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.279 | TFLOPs: 23.60 | +63: iteration 68200/ 73814 | consumed samples: 34918400 | consumed tokens: 71512883200 | elapsed time per iteration (s): 2.39 | learning rate: 2.261E-05 | global batch size: 512 | lm loss: 1.891608E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.480 | TFLOPs: 22.08 | +63: iteration 68210/ 73814 | consumed samples: 34923520 | consumed tokens: 71523368960 | elapsed time per iteration (s): 2.24 | learning rate: 2.260E-05 | global batch size: 512 | lm loss: 1.897213E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.634 | TFLOPs: 23.54 | +63: iteration 68220/ 73814 | consumed samples: 34928640 | consumed tokens: 71533854720 | elapsed time per iteration (s): 2.23 | learning rate: 2.259E-05 | global batch size: 512 | lm loss: 1.901251E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.019 | TFLOPs: 23.68 | +63: iteration 68230/ 73814 | consumed samples: 34933760 | consumed tokens: 71544340480 | elapsed time per iteration (s): 2.26 | learning rate: 2.258E-05 | global batch size: 512 | lm loss: 1.893952E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.956 | TFLOPs: 23.36 | +63: iteration 68240/ 73814 | consumed samples: 34938880 | consumed tokens: 71554826240 | elapsed time per iteration (s): 2.26 | learning rate: 2.257E-05 | global batch size: 512 | lm loss: 1.881628E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.041 | TFLOPs: 23.37 | +63: iteration 68250/ 73814 | consumed samples: 34944000 | consumed tokens: 71565312000 | elapsed time per iteration (s): 2.23 | learning rate: 2.256E-05 | global batch size: 512 | lm loss: 1.882157E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.036 | TFLOPs: 23.68 | +63: iteration 68260/ 73814 | consumed samples: 34949120 | consumed tokens: 71575797760 | elapsed time per iteration (s): 2.24 | learning rate: 2.255E-05 | global batch size: 512 | lm loss: 1.889546E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.546 | TFLOPs: 23.53 | +63: iteration 68270/ 73814 | consumed samples: 34954240 | consumed tokens: 71586283520 | elapsed time per iteration (s): 2.22 | learning rate: 2.254E-05 | global batch size: 512 | lm loss: 1.874603E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.137 | TFLOPs: 23.69 | +63: iteration 68280/ 73814 | consumed samples: 34959360 | consumed tokens: 71596769280 | elapsed time per iteration (s): 2.25 | learning rate: 2.254E-05 | global batch size: 512 | lm loss: 1.888304E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.611 | TFLOPs: 23.43 | +63: iteration 68290/ 73814 | consumed samples: 34964480 | consumed tokens: 71607255040 | elapsed time per iteration (s): 2.33 | learning rate: 2.253E-05 | global batch size: 512 | lm loss: 1.893762E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.942 | TFLOPs: 22.64 | +63: iteration 68300/ 73814 | consumed samples: 34969600 | consumed tokens: 71617740800 | elapsed time per iteration (s): 2.23 | learning rate: 2.252E-05 | global batch size: 512 | lm loss: 1.907138E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.014 | TFLOPs: 23.68 | +63: iteration 68310/ 73814 | consumed samples: 34974720 | consumed tokens: 71628226560 | elapsed time per iteration (s): 2.23 | learning rate: 2.251E-05 | global batch size: 512 | lm loss: 1.885263E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.724 | TFLOPs: 23.65 | +63: iteration 68320/ 73814 | consumed samples: 34979840 | consumed tokens: 71638712320 | elapsed time per iteration (s): 2.23 | learning rate: 2.250E-05 | global batch size: 512 | lm loss: 1.889723E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.717 | TFLOPs: 23.65 | +63: iteration 68330/ 73814 | consumed samples: 34984960 | consumed tokens: 71649198080 | elapsed time per iteration (s): 2.22 | learning rate: 2.249E-05 | global batch size: 512 | lm loss: 1.878546E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.595 | TFLOPs: 23.74 | +63: iteration 68340/ 73814 | consumed samples: 34990080 | consumed tokens: 71659683840 | elapsed time per iteration (s): 2.28 | learning rate: 2.248E-05 | global batch size: 512 | lm loss: 1.904324E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.861 | TFLOPs: 23.15 | +63: iteration 68350/ 73814 | consumed samples: 34995200 | consumed tokens: 71670169600 | elapsed time per iteration (s): 2.22 | learning rate: 2.247E-05 | global batch size: 512 | lm loss: 1.893097E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.120 | TFLOPs: 23.69 | +63: iteration 68360/ 73814 | consumed samples: 35000320 | consumed tokens: 71680655360 | elapsed time per iteration (s): 2.23 | learning rate: 2.246E-05 | global batch size: 512 | lm loss: 1.908437E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.828 | TFLOPs: 23.66 | +63: iteration 68370/ 73814 | consumed samples: 35005440 | consumed tokens: 71691141120 | elapsed time per iteration (s): 2.23 | learning rate: 2.245E-05 | global batch size: 512 | lm loss: 1.885743E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.687 | TFLOPs: 23.65 | +63: iteration 68380/ 73814 | consumed samples: 35010560 | consumed tokens: 71701626880 | elapsed time per iteration (s): 2.23 | learning rate: 2.245E-05 | global batch size: 512 | lm loss: 1.892230E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.234 | TFLOPs: 23.60 | +63: iteration 68390/ 73814 | consumed samples: 35015680 | consumed tokens: 71712112640 | elapsed time per iteration (s): 2.25 | learning rate: 2.244E-05 | global batch size: 512 | lm loss: 1.859403E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.711 | TFLOPs: 23.44 | +63: iteration 68400/ 73814 | consumed samples: 35020800 | consumed tokens: 71722598400 | elapsed time per iteration (s): 2.23 | learning rate: 2.243E-05 | global batch size: 512 | lm loss: 1.896321E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.591 | TFLOPs: 23.64 | +63: iteration 68410/ 73814 | consumed samples: 35025920 | consumed tokens: 71733084160 | elapsed time per iteration (s): 2.23 | learning rate: 2.242E-05 | global batch size: 512 | lm loss: 1.897973E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.097 | TFLOPs: 23.58 | +63: iteration 68420/ 73814 | consumed samples: 35031040 | consumed tokens: 71743569920 | elapsed time per iteration (s): 2.23 | learning rate: 2.241E-05 | global batch size: 512 | lm loss: 1.903467E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.991 | TFLOPs: 23.68 | +63: iteration 68430/ 73814 | consumed samples: 35036160 | consumed tokens: 71754055680 | elapsed time per iteration (s): 2.49 | learning rate: 2.240E-05 | global batch size: 512 | lm loss: 1.884598E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.796 | TFLOPs: 21.19 | +63: iteration 68440/ 73814 | consumed samples: 35041280 | consumed tokens: 71764541440 | elapsed time per iteration (s): 2.23 | learning rate: 2.239E-05 | global batch size: 512 | lm loss: 1.883723E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.988 | TFLOPs: 23.68 | +63: iteration 68450/ 73814 | consumed samples: 35046400 | consumed tokens: 71775027200 | elapsed time per iteration (s): 2.23 | learning rate: 2.238E-05 | global batch size: 512 | lm loss: 1.867896E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.316 | TFLOPs: 23.61 | +63: iteration 68460/ 73814 | consumed samples: 35051520 | consumed tokens: 71785512960 | elapsed time per iteration (s): 2.24 | learning rate: 2.237E-05 | global batch size: 512 | lm loss: 1.891300E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.222 | TFLOPs: 23.49 | +63: iteration 68470/ 73814 | consumed samples: 35056640 | consumed tokens: 71795998720 | elapsed time per iteration (s): 2.27 | learning rate: 2.237E-05 | global batch size: 512 | lm loss: 1.908965E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.977 | TFLOPs: 23.26 | +63: iteration 68480/ 73814 | consumed samples: 35061760 | consumed tokens: 71806484480 | elapsed time per iteration (s): 2.29 | learning rate: 2.236E-05 | global batch size: 512 | lm loss: 1.873140E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.265 | TFLOPs: 22.98 | +63: iteration 68490/ 73814 | consumed samples: 35066880 | consumed tokens: 71816970240 | elapsed time per iteration (s): 3.44 | learning rate: 2.235E-05 | global batch size: 512 | lm loss: 1.886309E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 148.741 | TFLOPs: 15.31 | +63: iteration 68500/ 73814 | consumed samples: 35072000 | consumed tokens: 71827456000 | elapsed time per iteration (s): 2.22 | learning rate: 2.234E-05 | global batch size: 512 | lm loss: 1.875469E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.148 | TFLOPs: 23.69 | +63: iteration 68510/ 73814 | consumed samples: 35077120 | consumed tokens: 71837941760 | elapsed time per iteration (s): 2.24 | learning rate: 2.233E-05 | global batch size: 512 | lm loss: 1.887726E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.547 | TFLOPs: 23.53 | +63: iteration 68520/ 73814 | consumed samples: 35082240 | consumed tokens: 71848427520 | elapsed time per iteration (s): 2.23 | learning rate: 2.232E-05 | global batch size: 512 | lm loss: 1.896567E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.686 | TFLOPs: 23.65 | +63: iteration 68530/ 73814 | consumed samples: 35087360 | consumed tokens: 71858913280 | elapsed time per iteration (s): 2.24 | learning rate: 2.231E-05 | global batch size: 512 | lm loss: 1.872213E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.901 | TFLOPs: 23.56 | +63: iteration 68540/ 73814 | consumed samples: 35092480 | consumed tokens: 71869399040 | elapsed time per iteration (s): 2.22 | learning rate: 2.230E-05 | global batch size: 512 | lm loss: 1.925789E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.242 | TFLOPs: 23.70 | +63: iteration 68550/ 73814 | consumed samples: 35097600 | consumed tokens: 71879884800 | elapsed time per iteration (s): 2.42 | learning rate: 2.230E-05 | global batch size: 512 | lm loss: 1.892123E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.795 | TFLOPs: 21.80 | +63: iteration 68560/ 73814 | consumed samples: 35102720 | consumed tokens: 71890370560 | elapsed time per iteration (s): 2.23 | learning rate: 2.229E-05 | global batch size: 512 | lm loss: 1.880892E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.149 | TFLOPs: 23.59 | +63: iteration 68570/ 73814 | consumed samples: 35107840 | consumed tokens: 71900856320 | elapsed time per iteration (s): 2.23 | learning rate: 2.228E-05 | global batch size: 512 | lm loss: 1.893825E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.519 | TFLOPs: 23.63 | +63: iteration 68580/ 73814 | consumed samples: 35112960 | consumed tokens: 71911342080 | elapsed time per iteration (s): 2.24 | learning rate: 2.227E-05 | global batch size: 512 | lm loss: 1.884652E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.071 | TFLOPs: 23.58 | +63: iteration 68590/ 73814 | consumed samples: 35118080 | consumed tokens: 71921827840 | elapsed time per iteration (s): 2.25 | learning rate: 2.226E-05 | global batch size: 512 | lm loss: 1.880535E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.670 | TFLOPs: 23.44 | +63: iteration 68600/ 73814 | consumed samples: 35123200 | consumed tokens: 71932313600 | elapsed time per iteration (s): 2.24 | learning rate: 2.225E-05 | global batch size: 512 | lm loss: 1.900492E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.738 | TFLOPs: 23.55 | +63: iteration 68610/ 73814 | consumed samples: 35128320 | consumed tokens: 71942799360 | elapsed time per iteration (s): 2.25 | learning rate: 2.224E-05 | global batch size: 512 | lm loss: 1.902296E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.043 | TFLOPs: 23.48 | +63: iteration 68620/ 73814 | consumed samples: 35133440 | consumed tokens: 71953285120 | elapsed time per iteration (s): 2.23 | learning rate: 2.223E-05 | global batch size: 512 | lm loss: 1.905620E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.669 | TFLOPs: 23.64 | +63: iteration 68630/ 73814 | consumed samples: 35138560 | consumed tokens: 71963770880 | elapsed time per iteration (s): 2.23 | learning rate: 2.223E-05 | global batch size: 512 | lm loss: 1.893294E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.706 | TFLOPs: 23.65 | +63: iteration 68640/ 73814 | consumed samples: 35143680 | consumed tokens: 71974256640 | elapsed time per iteration (s): 2.25 | learning rate: 2.222E-05 | global batch size: 512 | lm loss: 1.890215E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.078 | TFLOPs: 23.38 | +63: iteration 68650/ 73814 | consumed samples: 35148800 | consumed tokens: 71984742400 | elapsed time per iteration (s): 2.23 | learning rate: 2.221E-05 | global batch size: 512 | lm loss: 1.893121E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.822 | TFLOPs: 23.66 | +63: iteration 68660/ 73814 | consumed samples: 35153920 | consumed tokens: 71995228160 | elapsed time per iteration (s): 2.24 | learning rate: 2.220E-05 | global batch size: 512 | lm loss: 1.876934E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.717 | TFLOPs: 23.55 | +63: iteration 68670/ 73814 | consumed samples: 35159040 | consumed tokens: 72005713920 | elapsed time per iteration (s): 2.23 | learning rate: 2.219E-05 | global batch size: 512 | lm loss: 1.864980E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.721 | TFLOPs: 23.65 | +63: iteration 68680/ 73814 | consumed samples: 35164160 | consumed tokens: 72016199680 | elapsed time per iteration (s): 2.23 | learning rate: 2.218E-05 | global batch size: 512 | lm loss: 1.884695E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.847 | TFLOPs: 23.66 | +63: iteration 68690/ 73814 | consumed samples: 35169280 | consumed tokens: 72026685440 | elapsed time per iteration (s): 2.24 | learning rate: 2.218E-05 | global batch size: 512 | lm loss: 1.909464E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.764 | TFLOPs: 23.55 | +63: iteration 68700/ 73814 | consumed samples: 35174400 | consumed tokens: 72037171200 | elapsed time per iteration (s): 2.22 | learning rate: 2.217E-05 | global batch size: 512 | lm loss: 1.879111E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.313 | TFLOPs: 23.71 | +63: iteration 68710/ 73814 | consumed samples: 35179520 | consumed tokens: 72047656960 | elapsed time per iteration (s): 2.23 | learning rate: 2.216E-05 | global batch size: 512 | lm loss: 1.883835E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.316 | TFLOPs: 23.61 | +63: iteration 68720/ 73814 | consumed samples: 35184640 | consumed tokens: 72058142720 | elapsed time per iteration (s): 2.23 | learning rate: 2.215E-05 | global batch size: 512 | lm loss: 1.879721E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.969 | TFLOPs: 23.67 | +63: iteration 68730/ 73814 | consumed samples: 35189760 | consumed tokens: 72068628480 | elapsed time per iteration (s): 2.23 | learning rate: 2.214E-05 | global batch size: 512 | lm loss: 1.884931E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.344 | TFLOPs: 23.61 | +63: iteration 68740/ 73814 | consumed samples: 35194880 | consumed tokens: 72079114240 | elapsed time per iteration (s): 2.22 | learning rate: 2.213E-05 | global batch size: 512 | lm loss: 1.896760E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.190 | TFLOPs: 23.70 | +63: iteration 68750/ 73814 | consumed samples: 35200000 | consumed tokens: 72089600000 | elapsed time per iteration (s): 2.22 | learning rate: 2.212E-05 | global batch size: 512 | lm loss: 1.901795E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.381 | TFLOPs: 23.72 | +63: iteration 68760/ 73814 | consumed samples: 35205120 | consumed tokens: 72100085760 | elapsed time per iteration (s): 2.40 | learning rate: 2.212E-05 | global batch size: 512 | lm loss: 1.893484E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.118 | TFLOPs: 21.94 | +63: iteration 68770/ 73814 | consumed samples: 35210240 | consumed tokens: 72110571520 | elapsed time per iteration (s): 2.37 | learning rate: 2.211E-05 | global batch size: 512 | lm loss: 1.855225E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.690 | TFLOPs: 22.20 | +63: iteration 68780/ 73814 | consumed samples: 35215360 | consumed tokens: 72121057280 | elapsed time per iteration (s): 2.23 | learning rate: 2.210E-05 | global batch size: 512 | lm loss: 1.861552E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.092 | TFLOPs: 23.69 | +63: iteration 68790/ 73814 | consumed samples: 35220480 | consumed tokens: 72131543040 | elapsed time per iteration (s): 2.23 | learning rate: 2.209E-05 | global batch size: 512 | lm loss: 1.914660E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.563 | TFLOPs: 23.63 | +63: iteration 68800/ 73814 | consumed samples: 35225600 | consumed tokens: 72142028800 | elapsed time per iteration (s): 2.36 | learning rate: 2.208E-05 | global batch size: 512 | lm loss: 1.876896E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.219 | TFLOPs: 22.36 | +63: iteration 68810/ 73814 | consumed samples: 35230720 | consumed tokens: 72152514560 | elapsed time per iteration (s): 2.46 | learning rate: 2.207E-05 | global batch size: 512 | lm loss: 1.897949E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.111 | TFLOPs: 21.42 | +63: iteration 68820/ 73814 | consumed samples: 35235840 | consumed tokens: 72163000320 | elapsed time per iteration (s): 2.22 | learning rate: 2.207E-05 | global batch size: 512 | lm loss: 1.866384E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.135 | TFLOPs: 23.69 | +63: iteration 68830/ 73814 | consumed samples: 35240960 | consumed tokens: 72173486080 | elapsed time per iteration (s): 2.24 | learning rate: 2.206E-05 | global batch size: 512 | lm loss: 1.878527E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.349 | TFLOPs: 23.51 | +63: iteration 68840/ 73814 | consumed samples: 35246080 | consumed tokens: 72183971840 | elapsed time per iteration (s): 2.22 | learning rate: 2.205E-05 | global batch size: 512 | lm loss: 1.888728E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.333 | TFLOPs: 23.71 | +63: iteration 68850/ 73814 | consumed samples: 35251200 | consumed tokens: 72194457600 | elapsed time per iteration (s): 2.23 | learning rate: 2.204E-05 | global batch size: 512 | lm loss: 1.905524E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.931 | TFLOPs: 23.67 | +63: iteration 68860/ 73814 | consumed samples: 35256320 | consumed tokens: 72204943360 | elapsed time per iteration (s): 2.53 | learning rate: 2.203E-05 | global batch size: 512 | lm loss: 1.897093E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.744 | TFLOPs: 20.87 | +63: iteration 68870/ 73814 | consumed samples: 35261440 | consumed tokens: 72215429120 | elapsed time per iteration (s): 2.23 | learning rate: 2.203E-05 | global batch size: 512 | lm loss: 1.901949E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.041 | TFLOPs: 23.68 | +63: iteration 68880/ 73814 | consumed samples: 35266560 | consumed tokens: 72225914880 | elapsed time per iteration (s): 2.23 | learning rate: 2.202E-05 | global batch size: 512 | lm loss: 1.883382E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.584 | TFLOPs: 23.63 | +63: iteration 68890/ 73814 | consumed samples: 35271680 | consumed tokens: 72236400640 | elapsed time per iteration (s): 2.23 | learning rate: 2.201E-05 | global batch size: 512 | lm loss: 1.894337E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.387 | TFLOPs: 23.61 | +63: iteration 68900/ 73814 | consumed samples: 35276800 | consumed tokens: 72246886400 | elapsed time per iteration (s): 2.24 | learning rate: 2.200E-05 | global batch size: 512 | lm loss: 1.866668E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.414 | TFLOPs: 23.51 | +63: iteration 68910/ 73814 | consumed samples: 35281920 | consumed tokens: 72257372160 | elapsed time per iteration (s): 2.23 | learning rate: 2.199E-05 | global batch size: 512 | lm loss: 1.884386E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.650 | TFLOPs: 23.64 | +63: iteration 68920/ 73814 | consumed samples: 35287040 | consumed tokens: 72267857920 | elapsed time per iteration (s): 2.23 | learning rate: 2.198E-05 | global batch size: 512 | lm loss: 1.885081E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.063 | TFLOPs: 23.68 | +63: iteration 68930/ 73814 | consumed samples: 35292160 | consumed tokens: 72278343680 | elapsed time per iteration (s): 2.27 | learning rate: 2.198E-05 | global batch size: 512 | lm loss: 1.893584E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.589 | TFLOPs: 23.22 | +63: iteration 68940/ 73814 | consumed samples: 35297280 | consumed tokens: 72288829440 | elapsed time per iteration (s): 2.23 | learning rate: 2.197E-05 | global batch size: 512 | lm loss: 1.886934E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.133 | TFLOPs: 23.59 | +63: iteration 68950/ 73814 | consumed samples: 35302400 | consumed tokens: 72299315200 | elapsed time per iteration (s): 2.23 | learning rate: 2.196E-05 | global batch size: 512 | lm loss: 1.898519E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.914 | TFLOPs: 23.67 | +63: iteration 68960/ 73814 | consumed samples: 35307520 | consumed tokens: 72309800960 | elapsed time per iteration (s): 2.23 | learning rate: 2.195E-05 | global batch size: 512 | lm loss: 1.902720E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.481 | TFLOPs: 23.62 | +63: iteration 68970/ 73814 | consumed samples: 35312640 | consumed tokens: 72320286720 | elapsed time per iteration (s): 2.25 | learning rate: 2.194E-05 | global batch size: 512 | lm loss: 1.903085E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.296 | TFLOPs: 23.40 | +63: iteration 68980/ 73814 | consumed samples: 35317760 | consumed tokens: 72330772480 | elapsed time per iteration (s): 2.26 | learning rate: 2.194E-05 | global batch size: 512 | lm loss: 1.887629E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.949 | TFLOPs: 23.36 | +63: iteration 68990/ 73814 | consumed samples: 35322880 | consumed tokens: 72341258240 | elapsed time per iteration (s): 2.23 | learning rate: 2.193E-05 | global batch size: 512 | lm loss: 1.874816E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.486 | TFLOPs: 23.62 | +63: iteration 69000/ 73814 | consumed samples: 35328000 | consumed tokens: 72351744000 | elapsed time per iteration (s): 2.23 | learning rate: 2.192E-05 | global batch size: 512 | lm loss: 1.908064E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.944 | TFLOPs: 23.67 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 69000 | lm loss value: 1.839545E+00 | lm loss PPL: 6.293677E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 69010/ 73814 | consumed samples: 35333120 | consumed tokens: 72362229760 | elapsed time per iteration (s): 2.51 | learning rate: 2.191E-05 | global batch size: 512 | lm loss: 1.899069E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 203.748 | TFLOPs: 20.97 | +63: iteration 69020/ 73814 | consumed samples: 35338240 | consumed tokens: 72372715520 | elapsed time per iteration (s): 2.25 | learning rate: 2.190E-05 | global batch size: 512 | lm loss: 1.897305E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.782 | TFLOPs: 23.45 | +63: iteration 69030/ 73814 | consumed samples: 35343360 | consumed tokens: 72383201280 | elapsed time per iteration (s): 2.23 | learning rate: 2.190E-05 | global batch size: 512 | lm loss: 1.902729E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.281 | TFLOPs: 23.60 | +63: iteration 69040/ 73814 | consumed samples: 35348480 | consumed tokens: 72393687040 | elapsed time per iteration (s): 2.24 | learning rate: 2.189E-05 | global batch size: 512 | lm loss: 1.883037E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.616 | TFLOPs: 23.53 | +63: iteration 69050/ 73814 | consumed samples: 35353600 | consumed tokens: 72404172800 | elapsed time per iteration (s): 2.43 | learning rate: 2.188E-05 | global batch size: 512 | lm loss: 1.878778E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.570 | TFLOPs: 21.68 | +63: iteration 69060/ 73814 | consumed samples: 35358720 | consumed tokens: 72414658560 | elapsed time per iteration (s): 2.41 | learning rate: 2.187E-05 | global batch size: 512 | lm loss: 1.879303E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.870 | TFLOPs: 21.91 | +63: iteration 69070/ 73814 | consumed samples: 35363840 | consumed tokens: 72425144320 | elapsed time per iteration (s): 2.22 | learning rate: 2.187E-05 | global batch size: 512 | lm loss: 1.867916E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.150 | TFLOPs: 23.69 | +63: iteration 69080/ 73814 | consumed samples: 35368960 | consumed tokens: 72435630080 | elapsed time per iteration (s): 2.23 | learning rate: 2.186E-05 | global batch size: 512 | lm loss: 1.859642E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.844 | TFLOPs: 23.66 | +63: iteration 69090/ 73814 | consumed samples: 35374080 | consumed tokens: 72446115840 | elapsed time per iteration (s): 2.28 | learning rate: 2.185E-05 | global batch size: 512 | lm loss: 1.879940E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.495 | TFLOPs: 23.11 | +63: iteration 69100/ 73814 | consumed samples: 35379200 | consumed tokens: 72456601600 | elapsed time per iteration (s): 2.22 | learning rate: 2.184E-05 | global batch size: 512 | lm loss: 1.868351E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.264 | TFLOPs: 23.70 | +63: iteration 69110/ 73814 | consumed samples: 35384320 | consumed tokens: 72467087360 | elapsed time per iteration (s): 2.26 | learning rate: 2.183E-05 | global batch size: 512 | lm loss: 1.910294E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.784 | TFLOPs: 23.35 | +63: iteration 69120/ 73814 | consumed samples: 35389440 | consumed tokens: 72477573120 | elapsed time per iteration (s): 2.40 | learning rate: 2.183E-05 | global batch size: 512 | lm loss: 1.861127E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.778 | TFLOPs: 22.01 | +63: iteration 69130/ 73814 | consumed samples: 35394560 | consumed tokens: 72488058880 | elapsed time per iteration (s): 2.24 | learning rate: 2.182E-05 | global batch size: 512 | lm loss: 1.875290E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.633 | TFLOPs: 23.54 | +63: iteration 69140/ 73814 | consumed samples: 35399680 | consumed tokens: 72498544640 | elapsed time per iteration (s): 2.26 | learning rate: 2.181E-05 | global batch size: 512 | lm loss: 1.898570E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.550 | TFLOPs: 23.32 | +63: iteration 69150/ 73814 | consumed samples: 35404800 | consumed tokens: 72509030400 | elapsed time per iteration (s): 2.25 | learning rate: 2.180E-05 | global batch size: 512 | lm loss: 1.892409E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.139 | TFLOPs: 23.38 | +63: iteration 69160/ 73814 | consumed samples: 35409920 | consumed tokens: 72519516160 | elapsed time per iteration (s): 2.23 | learning rate: 2.180E-05 | global batch size: 512 | lm loss: 1.873299E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.309 | TFLOPs: 23.61 | +63: iteration 69170/ 73814 | consumed samples: 35415040 | consumed tokens: 72530001920 | elapsed time per iteration (s): 2.22 | learning rate: 2.179E-05 | global batch size: 512 | lm loss: 1.879734E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.117 | TFLOPs: 23.69 | +63: iteration 69180/ 73814 | consumed samples: 35420160 | consumed tokens: 72540487680 | elapsed time per iteration (s): 2.24 | learning rate: 2.178E-05 | global batch size: 512 | lm loss: 1.894326E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.081 | TFLOPs: 23.48 | +63: iteration 69190/ 73814 | consumed samples: 35425280 | consumed tokens: 72550973440 | elapsed time per iteration (s): 2.23 | learning rate: 2.177E-05 | global batch size: 512 | lm loss: 1.880752E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.290 | TFLOPs: 23.60 | +63: iteration 69200/ 73814 | consumed samples: 35430400 | consumed tokens: 72561459200 | elapsed time per iteration (s): 2.23 | learning rate: 2.177E-05 | global batch size: 512 | lm loss: 1.891594E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.799 | TFLOPs: 23.66 | +63: iteration 69210/ 73814 | consumed samples: 35435520 | consumed tokens: 72571944960 | elapsed time per iteration (s): 2.25 | learning rate: 2.176E-05 | global batch size: 512 | lm loss: 1.877951E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.657 | TFLOPs: 23.44 | +63: iteration 69220/ 73814 | consumed samples: 35440640 | consumed tokens: 72582430720 | elapsed time per iteration (s): 2.34 | learning rate: 2.175E-05 | global batch size: 512 | lm loss: 1.881386E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.614 | TFLOPs: 22.51 | +63: iteration 69230/ 73814 | consumed samples: 35445760 | consumed tokens: 72592916480 | elapsed time per iteration (s): 2.24 | learning rate: 2.174E-05 | global batch size: 512 | lm loss: 1.869115E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.514 | TFLOPs: 23.52 | +63: iteration 69240/ 73814 | consumed samples: 35450880 | consumed tokens: 72603402240 | elapsed time per iteration (s): 2.24 | learning rate: 2.173E-05 | global batch size: 512 | lm loss: 1.893045E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.039 | TFLOPs: 23.58 | +63: iteration 69250/ 73814 | consumed samples: 35456000 | consumed tokens: 72613888000 | elapsed time per iteration (s): 2.23 | learning rate: 2.173E-05 | global batch size: 512 | lm loss: 1.878425E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.463 | TFLOPs: 23.62 | +63: iteration 69260/ 73814 | consumed samples: 35461120 | consumed tokens: 72624373760 | elapsed time per iteration (s): 2.23 | learning rate: 2.172E-05 | global batch size: 512 | lm loss: 1.887986E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.769 | TFLOPs: 23.65 | +63: iteration 69270/ 73814 | consumed samples: 35466240 | consumed tokens: 72634859520 | elapsed time per iteration (s): 2.23 | learning rate: 2.171E-05 | global batch size: 512 | lm loss: 1.909164E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.638 | TFLOPs: 23.64 | +63: iteration 69280/ 73814 | consumed samples: 35471360 | consumed tokens: 72645345280 | elapsed time per iteration (s): 2.31 | learning rate: 2.170E-05 | global batch size: 512 | lm loss: 1.877494E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.478 | TFLOPs: 22.80 | +63: iteration 69290/ 73814 | consumed samples: 35476480 | consumed tokens: 72655831040 | elapsed time per iteration (s): 2.37 | learning rate: 2.170E-05 | global batch size: 512 | lm loss: 1.905133E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.195 | TFLOPs: 22.26 | +63: iteration 69300/ 73814 | consumed samples: 35481600 | consumed tokens: 72666316800 | elapsed time per iteration (s): 2.23 | learning rate: 2.169E-05 | global batch size: 512 | lm loss: 1.884232E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.475 | TFLOPs: 23.62 | +63: iteration 69310/ 73814 | consumed samples: 35486720 | consumed tokens: 72676802560 | elapsed time per iteration (s): 2.26 | learning rate: 2.168E-05 | global batch size: 512 | lm loss: 1.875215E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.328 | TFLOPs: 23.30 | +63: iteration 69320/ 73814 | consumed samples: 35491840 | consumed tokens: 72687288320 | elapsed time per iteration (s): 2.39 | learning rate: 2.167E-05 | global batch size: 512 | lm loss: 1.861045E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.669 | TFLOPs: 22.10 | +63: iteration 69330/ 73814 | consumed samples: 35496960 | consumed tokens: 72697774080 | elapsed time per iteration (s): 2.24 | learning rate: 2.167E-05 | global batch size: 512 | lm loss: 1.870104E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.118 | TFLOPs: 23.48 | +63: iteration 69340/ 73814 | consumed samples: 35502080 | consumed tokens: 72708259840 | elapsed time per iteration (s): 2.26 | learning rate: 2.166E-05 | global batch size: 512 | lm loss: 1.904046E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.055 | TFLOPs: 23.27 | +63: iteration 69350/ 73814 | consumed samples: 35507200 | consumed tokens: 72718745600 | elapsed time per iteration (s): 2.36 | learning rate: 2.165E-05 | global batch size: 512 | lm loss: 1.882722E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.800 | TFLOPs: 22.32 | +63: iteration 69360/ 73814 | consumed samples: 35512320 | consumed tokens: 72729231360 | elapsed time per iteration (s): 2.35 | learning rate: 2.165E-05 | global batch size: 512 | lm loss: 1.864687E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.259 | TFLOPs: 22.47 | +63: iteration 69370/ 73814 | consumed samples: 35517440 | consumed tokens: 72739717120 | elapsed time per iteration (s): 2.26 | learning rate: 2.164E-05 | global batch size: 512 | lm loss: 1.918496E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.625 | TFLOPs: 23.33 | +63: iteration 69380/ 73814 | consumed samples: 35522560 | consumed tokens: 72750202880 | elapsed time per iteration (s): 2.38 | learning rate: 2.163E-05 | global batch size: 512 | lm loss: 1.902161E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.805 | TFLOPs: 22.11 | +63: iteration 69390/ 73814 | consumed samples: 35527680 | consumed tokens: 72760688640 | elapsed time per iteration (s): 2.36 | learning rate: 2.162E-05 | global batch size: 512 | lm loss: 1.881485E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.324 | TFLOPs: 22.37 | +63: iteration 69400/ 73814 | consumed samples: 35532800 | consumed tokens: 72771174400 | elapsed time per iteration (s): 2.22 | learning rate: 2.162E-05 | global batch size: 512 | lm loss: 1.885958E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.352 | TFLOPs: 23.71 | +63: iteration 69410/ 73814 | consumed samples: 35537920 | consumed tokens: 72781660160 | elapsed time per iteration (s): 2.23 | learning rate: 2.161E-05 | global batch size: 512 | lm loss: 1.885199E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.751 | TFLOPs: 23.65 | +63: iteration 69420/ 73814 | consumed samples: 35543040 | consumed tokens: 72792145920 | elapsed time per iteration (s): 2.39 | learning rate: 2.160E-05 | global batch size: 512 | lm loss: 1.895413E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.403 | TFLOPs: 22.07 | +63: iteration 69430/ 73814 | consumed samples: 35548160 | consumed tokens: 72802631680 | elapsed time per iteration (s): 2.23 | learning rate: 2.159E-05 | global batch size: 512 | lm loss: 1.878350E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.482 | TFLOPs: 23.62 | +63: iteration 69440/ 73814 | consumed samples: 35553280 | consumed tokens: 72813117440 | elapsed time per iteration (s): 2.23 | learning rate: 2.159E-05 | global batch size: 512 | lm loss: 1.893851E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.382 | TFLOPs: 23.61 | +63: iteration 69450/ 73814 | consumed samples: 35558400 | consumed tokens: 72823603200 | elapsed time per iteration (s): 2.24 | learning rate: 2.158E-05 | global batch size: 512 | lm loss: 1.898505E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.615 | TFLOPs: 23.53 | +63: iteration 69460/ 73814 | consumed samples: 35563520 | consumed tokens: 72834088960 | elapsed time per iteration (s): 2.29 | learning rate: 2.157E-05 | global batch size: 512 | lm loss: 1.883359E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.028 | TFLOPs: 23.06 | +63: iteration 69470/ 73814 | consumed samples: 35568640 | consumed tokens: 72844574720 | elapsed time per iteration (s): 2.24 | learning rate: 2.157E-05 | global batch size: 512 | lm loss: 1.880723E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.424 | TFLOPs: 23.52 | +63: iteration 69480/ 73814 | consumed samples: 35573760 | consumed tokens: 72855060480 | elapsed time per iteration (s): 2.25 | learning rate: 2.156E-05 | global batch size: 512 | lm loss: 1.886838E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.591 | TFLOPs: 23.43 | +63: iteration 69490/ 73814 | consumed samples: 35578880 | consumed tokens: 72865546240 | elapsed time per iteration (s): 2.42 | learning rate: 2.155E-05 | global batch size: 512 | lm loss: 1.877331E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.554 | TFLOPs: 21.78 | +63: iteration 69500/ 73814 | consumed samples: 35584000 | consumed tokens: 72876032000 | elapsed time per iteration (s): 2.29 | learning rate: 2.154E-05 | global batch size: 512 | lm loss: 1.891455E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.804 | TFLOPs: 23.04 | +63: iteration 69510/ 73814 | consumed samples: 35589120 | consumed tokens: 72886517760 | elapsed time per iteration (s): 2.23 | learning rate: 2.154E-05 | global batch size: 512 | lm loss: 1.897803E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.029 | TFLOPs: 23.68 | +63: iteration 69520/ 73814 | consumed samples: 35594240 | consumed tokens: 72897003520 | elapsed time per iteration (s): 2.24 | learning rate: 2.153E-05 | global batch size: 512 | lm loss: 1.895515E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.954 | TFLOPs: 23.57 | +63: iteration 69530/ 73814 | consumed samples: 35599360 | consumed tokens: 72907489280 | elapsed time per iteration (s): 2.23 | learning rate: 2.152E-05 | global batch size: 512 | lm loss: 1.876471E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.088 | TFLOPs: 23.69 | +63: iteration 69540/ 73814 | consumed samples: 35604480 | consumed tokens: 72917975040 | elapsed time per iteration (s): 2.23 | learning rate: 2.152E-05 | global batch size: 512 | lm loss: 1.889450E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.925 | TFLOPs: 23.67 | +63: iteration 69550/ 73814 | consumed samples: 35609600 | consumed tokens: 72928460800 | elapsed time per iteration (s): 2.25 | learning rate: 2.151E-05 | global batch size: 512 | lm loss: 1.895421E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.672 | TFLOPs: 23.44 | +63: iteration 69560/ 73814 | consumed samples: 35614720 | consumed tokens: 72938946560 | elapsed time per iteration (s): 2.23 | learning rate: 2.150E-05 | global batch size: 512 | lm loss: 1.902098E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.477 | TFLOPs: 23.62 | +63: iteration 69570/ 73814 | consumed samples: 35619840 | consumed tokens: 72949432320 | elapsed time per iteration (s): 2.23 | learning rate: 2.149E-05 | global batch size: 512 | lm loss: 1.892920E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.832 | TFLOPs: 23.66 | +63: iteration 69580/ 73814 | consumed samples: 35624960 | consumed tokens: 72959918080 | elapsed time per iteration (s): 2.23 | learning rate: 2.149E-05 | global batch size: 512 | lm loss: 1.887882E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.677 | TFLOPs: 23.64 | +63: iteration 69590/ 73814 | consumed samples: 35630080 | consumed tokens: 72970403840 | elapsed time per iteration (s): 2.35 | learning rate: 2.148E-05 | global batch size: 512 | lm loss: 1.889352E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.581 | TFLOPs: 22.40 | +63: iteration 69600/ 73814 | consumed samples: 35635200 | consumed tokens: 72980889600 | elapsed time per iteration (s): 2.35 | learning rate: 2.147E-05 | global batch size: 512 | lm loss: 1.864869E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.801 | TFLOPs: 22.42 | +63: iteration 69610/ 73814 | consumed samples: 35640320 | consumed tokens: 72991375360 | elapsed time per iteration (s): 2.31 | learning rate: 2.147E-05 | global batch size: 512 | lm loss: 1.894676E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.984 | TFLOPs: 22.85 | +63: iteration 69620/ 73814 | consumed samples: 35645440 | consumed tokens: 73001861120 | elapsed time per iteration (s): 2.24 | learning rate: 2.146E-05 | global batch size: 512 | lm loss: 1.880584E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.756 | TFLOPs: 23.55 | +63: iteration 69630/ 73814 | consumed samples: 35650560 | consumed tokens: 73012346880 | elapsed time per iteration (s): 2.53 | learning rate: 2.145E-05 | global batch size: 512 | lm loss: 1.897590E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.708 | TFLOPs: 20.87 | +63: iteration 69640/ 73814 | consumed samples: 35655680 | consumed tokens: 73022832640 | elapsed time per iteration (s): 2.35 | learning rate: 2.145E-05 | global batch size: 512 | lm loss: 1.888426E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.889 | TFLOPs: 22.43 | +63: iteration 69650/ 73814 | consumed samples: 35660800 | consumed tokens: 73033318400 | elapsed time per iteration (s): 2.55 | learning rate: 2.144E-05 | global batch size: 512 | lm loss: 1.866789E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.754 | TFLOPs: 20.67 | +63: iteration 69660/ 73814 | consumed samples: 35665920 | consumed tokens: 73043804160 | elapsed time per iteration (s): 2.45 | learning rate: 2.143E-05 | global batch size: 512 | lm loss: 1.896906E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.047 | TFLOPs: 21.52 | +63: iteration 69670/ 73814 | consumed samples: 35671040 | consumed tokens: 73054289920 | elapsed time per iteration (s): 3.40 | learning rate: 2.142E-05 | global batch size: 512 | lm loss: 1.885798E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 150.773 | TFLOPs: 15.52 | +63: iteration 69680/ 73814 | consumed samples: 35676160 | consumed tokens: 73064775680 | elapsed time per iteration (s): 2.64 | learning rate: 2.142E-05 | global batch size: 512 | lm loss: 1.883299E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 194.245 | TFLOPs: 20.00 | +63: iteration 69690/ 73814 | consumed samples: 35681280 | consumed tokens: 73075261440 | elapsed time per iteration (s): 2.27 | learning rate: 2.141E-05 | global batch size: 512 | lm loss: 1.876610E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.119 | TFLOPs: 23.17 | +63: iteration 69700/ 73814 | consumed samples: 35686400 | consumed tokens: 73085747200 | elapsed time per iteration (s): 2.28 | learning rate: 2.140E-05 | global batch size: 512 | lm loss: 1.890167E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.551 | TFLOPs: 23.12 | +63: iteration 69710/ 73814 | consumed samples: 35691520 | consumed tokens: 73096232960 | elapsed time per iteration (s): 2.29 | learning rate: 2.140E-05 | global batch size: 512 | lm loss: 1.879285E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.884 | TFLOPs: 23.05 | +63: iteration 69720/ 73814 | consumed samples: 35696640 | consumed tokens: 73106718720 | elapsed time per iteration (s): 2.32 | learning rate: 2.139E-05 | global batch size: 512 | lm loss: 1.872155E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.001 | TFLOPs: 22.75 | +63: iteration 69730/ 73814 | consumed samples: 35701760 | consumed tokens: 73117204480 | elapsed time per iteration (s): 2.53 | learning rate: 2.138E-05 | global batch size: 512 | lm loss: 1.859501E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.463 | TFLOPs: 20.84 | +63: iteration 69740/ 73814 | consumed samples: 35706880 | consumed tokens: 73127690240 | elapsed time per iteration (s): 2.49 | learning rate: 2.138E-05 | global batch size: 512 | lm loss: 1.885274E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.663 | TFLOPs: 21.17 | +63: iteration 69750/ 73814 | consumed samples: 35712000 | consumed tokens: 73138176000 | elapsed time per iteration (s): 2.25 | learning rate: 2.137E-05 | global batch size: 512 | lm loss: 1.881571E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.281 | TFLOPs: 23.40 | +63: iteration 69760/ 73814 | consumed samples: 35717120 | consumed tokens: 73148661760 | elapsed time per iteration (s): 2.24 | learning rate: 2.136E-05 | global batch size: 512 | lm loss: 1.887877E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.333 | TFLOPs: 23.51 | +63: iteration 69770/ 73814 | consumed samples: 35722240 | consumed tokens: 73159147520 | elapsed time per iteration (s): 2.22 | learning rate: 2.136E-05 | global batch size: 512 | lm loss: 1.881526E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.511 | TFLOPs: 23.73 | +63: iteration 69780/ 73814 | consumed samples: 35727360 | consumed tokens: 73169633280 | elapsed time per iteration (s): 2.31 | learning rate: 2.135E-05 | global batch size: 512 | lm loss: 1.893018E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.611 | TFLOPs: 22.81 | +63: iteration 69790/ 73814 | consumed samples: 35732480 | consumed tokens: 73180119040 | elapsed time per iteration (s): 2.38 | learning rate: 2.134E-05 | global batch size: 512 | lm loss: 1.897791E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.554 | TFLOPs: 22.19 | +63: iteration 69800/ 73814 | consumed samples: 35737600 | consumed tokens: 73190604800 | elapsed time per iteration (s): 2.23 | learning rate: 2.134E-05 | global batch size: 512 | lm loss: 1.911334E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.779 | TFLOPs: 23.65 | +63: iteration 69810/ 73814 | consumed samples: 35742720 | consumed tokens: 73201090560 | elapsed time per iteration (s): 2.26 | learning rate: 2.133E-05 | global batch size: 512 | lm loss: 1.864091E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.695 | TFLOPs: 23.34 | +63: iteration 69820/ 73814 | consumed samples: 35747840 | consumed tokens: 73211576320 | elapsed time per iteration (s): 2.22 | learning rate: 2.132E-05 | global batch size: 512 | lm loss: 1.884864E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.418 | TFLOPs: 23.72 | +63: iteration 69830/ 73814 | consumed samples: 35752960 | consumed tokens: 73222062080 | elapsed time per iteration (s): 2.23 | learning rate: 2.132E-05 | global batch size: 512 | lm loss: 1.903965E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.875 | TFLOPs: 23.66 | +63: iteration 69840/ 73814 | consumed samples: 35758080 | consumed tokens: 73232547840 | elapsed time per iteration (s): 2.24 | learning rate: 2.131E-05 | global batch size: 512 | lm loss: 1.913438E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.825 | TFLOPs: 23.56 | +63: iteration 69850/ 73814 | consumed samples: 35763200 | consumed tokens: 73243033600 | elapsed time per iteration (s): 2.24 | learning rate: 2.130E-05 | global batch size: 512 | lm loss: 1.874100E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.743 | TFLOPs: 23.55 | +63: iteration 69860/ 73814 | consumed samples: 35768320 | consumed tokens: 73253519360 | elapsed time per iteration (s): 2.23 | learning rate: 2.130E-05 | global batch size: 512 | lm loss: 1.886399E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.474 | TFLOPs: 23.62 | +63: iteration 69870/ 73814 | consumed samples: 35773440 | consumed tokens: 73264005120 | elapsed time per iteration (s): 2.23 | learning rate: 2.129E-05 | global batch size: 512 | lm loss: 1.866876E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.459 | TFLOPs: 23.62 | +63: iteration 69880/ 73814 | consumed samples: 35778560 | consumed tokens: 73274490880 | elapsed time per iteration (s): 2.26 | learning rate: 2.128E-05 | global batch size: 512 | lm loss: 1.884492E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.001 | TFLOPs: 23.37 | +63: iteration 69890/ 73814 | consumed samples: 35783680 | consumed tokens: 73284976640 | elapsed time per iteration (s): 2.25 | learning rate: 2.128E-05 | global batch size: 512 | lm loss: 1.896791E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.341 | TFLOPs: 23.40 | +63: iteration 69900/ 73814 | consumed samples: 35788800 | consumed tokens: 73295462400 | elapsed time per iteration (s): 2.37 | learning rate: 2.127E-05 | global batch size: 512 | lm loss: 1.867501E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.851 | TFLOPs: 22.22 | +63: iteration 69910/ 73814 | consumed samples: 35793920 | consumed tokens: 73305948160 | elapsed time per iteration (s): 2.23 | learning rate: 2.126E-05 | global batch size: 512 | lm loss: 1.893309E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.075 | TFLOPs: 23.69 | +63: iteration 69920/ 73814 | consumed samples: 35799040 | consumed tokens: 73316433920 | elapsed time per iteration (s): 2.25 | learning rate: 2.126E-05 | global batch size: 512 | lm loss: 1.882727E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.999 | TFLOPs: 23.47 | +63: iteration 69930/ 73814 | consumed samples: 35804160 | consumed tokens: 73326919680 | elapsed time per iteration (s): 2.25 | learning rate: 2.125E-05 | global batch size: 512 | lm loss: 1.879553E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.646 | TFLOPs: 23.44 | +63: iteration 69940/ 73814 | consumed samples: 35809280 | consumed tokens: 73337405440 | elapsed time per iteration (s): 2.23 | learning rate: 2.125E-05 | global batch size: 512 | lm loss: 1.862379E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.483 | TFLOPs: 23.62 | +63: iteration 69950/ 73814 | consumed samples: 35814400 | consumed tokens: 73347891200 | elapsed time per iteration (s): 2.24 | learning rate: 2.124E-05 | global batch size: 512 | lm loss: 1.888205E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.286 | TFLOPs: 23.50 | +63: iteration 69960/ 73814 | consumed samples: 35819520 | consumed tokens: 73358376960 | elapsed time per iteration (s): 2.25 | learning rate: 2.123E-05 | global batch size: 512 | lm loss: 1.884783E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.654 | TFLOPs: 23.44 | +63: iteration 69970/ 73814 | consumed samples: 35824640 | consumed tokens: 73368862720 | elapsed time per iteration (s): 2.26 | learning rate: 2.123E-05 | global batch size: 512 | lm loss: 1.874703E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.552 | TFLOPs: 23.32 | +63: iteration 69980/ 73814 | consumed samples: 35829760 | consumed tokens: 73379348480 | elapsed time per iteration (s): 2.25 | learning rate: 2.122E-05 | global batch size: 512 | lm loss: 1.884063E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.056 | TFLOPs: 23.37 | +63: iteration 69990/ 73814 | consumed samples: 35834880 | consumed tokens: 73389834240 | elapsed time per iteration (s): 2.36 | learning rate: 2.121E-05 | global batch size: 512 | lm loss: 1.886388E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.317 | TFLOPs: 22.37 | + 0: [2022-12-03 08:20:47,397] [INFO] [logging.py:68:log_dist] [Rank 0] step=70000, skipped=0, lr=[2.1207360985625776e-05, 2.1207360985625776e-05, 2.1207360985625776e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 70000/ 73814 | consumed samples: 35840000 | consumed tokens: 73400320000 | elapsed time per iteration (s): 2.26 | learning rate: 2.121E-05 | global batch size: 512 | lm loss: 1.869443E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.855 | TFLOPs: 23.35 | + 0: steps: 70000 loss: 1.8364 iter time (s): 2.283 samples/sec: 224.275 +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 70000 | lm loss value: 1.861456E+00 | lm loss PPL: 6.433099E+00 | +63: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 70000 to checkpoints_3b977boscar + 0: [2022-12-03 08:20:48,245] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step70000 is begin to save! + 0: [2022-12-03 08:20:48,259] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_01-model_00-model_states.pt... +32: [2022-12-03 08:20:48,259] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_21-model_00-model_states.pt... +32: [2022-12-03 08:20:48,672] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_21-model_00-model_states.pt. +32: [2022-12-03 08:20:48,672] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_22-model_00-model_states.pt... + 0: [2022-12-03 08:20:48,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_01-model_00-model_states.pt. + 0: [2022-12-03 08:20:48,762] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_03-model_00-model_states.pt... +32: [2022-12-03 08:20:48,914] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_22-model_00-model_states.pt. +32: [2022-12-03 08:20:48,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_23-model_00-model_states.pt... + 0: [2022-12-03 08:20:48,982] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_03-model_00-model_states.pt. + 0: [2022-12-03 08:20:48,982] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_04-model_00-model_states.pt... +32: [2022-12-03 08:20:49,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_23-model_00-model_states.pt. +32: [2022-12-03 08:20:49,157] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_24-model_00-model_states.pt... + 0: [2022-12-03 08:20:49,205] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_04-model_00-model_states.pt. + 0: [2022-12-03 08:20:49,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_05-model_00-model_states.pt... +32: [2022-12-03 08:20:49,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_24-model_00-model_states.pt. +32: [2022-12-03 08:20:49,397] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_25-model_00-model_states.pt... + 0: [2022-12-03 08:20:49,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_05-model_00-model_states.pt. + 0: [2022-12-03 08:20:49,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_06-model_00-model_states.pt... +32: [2022-12-03 08:20:49,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_25-model_00-model_states.pt. +32: [2022-12-03 08:20:49,642] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_26-model_00-model_states.pt... + 0: [2022-12-03 08:20:49,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_06-model_00-model_states.pt. + 0: [2022-12-03 08:20:49,653] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_07-model_00-model_states.pt... + 0: [2022-12-03 08:20:49,872] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_07-model_00-model_states.pt. + 0: [2022-12-03 08:20:49,872] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_08-model_00-model_states.pt... +32: [2022-12-03 08:20:49,884] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_26-model_00-model_states.pt. +32: [2022-12-03 08:20:49,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_27-model_00-model_states.pt... + 0: [2022-12-03 08:20:50,096] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_08-model_00-model_states.pt. + 0: [2022-12-03 08:20:50,097] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_09-model_00-model_states.pt... +32: [2022-12-03 08:20:50,128] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_27-model_00-model_states.pt. +32: [2022-12-03 08:20:50,128] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_28-model_00-model_states.pt... + 0: [2022-12-03 08:20:50,321] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_09-model_00-model_states.pt. + 0: [2022-12-03 08:20:50,321] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_10-model_00-model_states.pt... +32: [2022-12-03 08:20:50,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_28-model_00-model_states.pt. +32: [2022-12-03 08:20:50,378] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_29-model_00-model_states.pt... + 0: [2022-12-03 08:20:50,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_10-model_00-model_states.pt. + 0: [2022-12-03 08:20:50,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_11-model_00-model_states.pt... +32: [2022-12-03 08:20:50,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_29-model_00-model_states.pt. +32: [2022-12-03 08:20:50,623] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_30-model_00-model_states.pt... + 0: [2022-12-03 08:20:50,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_11-model_00-model_states.pt. + 0: [2022-12-03 08:20:50,762] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_12-model_00-model_states.pt... +32: [2022-12-03 08:20:50,874] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_30-model_00-model_states.pt. +32: [2022-12-03 08:20:50,874] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_31-model_00-model_states.pt... + 0: [2022-12-03 08:20:50,976] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_12-model_00-model_states.pt. + 0: [2022-12-03 08:20:50,977] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_13-model_00-model_states.pt... +32: [2022-12-03 08:20:51,126] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_31-model_00-model_states.pt. +32: [2022-12-03 08:20:51,126] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_32-model_00-model_states.pt... + 0: [2022-12-03 08:20:51,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_13-model_00-model_states.pt. + 0: [2022-12-03 08:20:51,199] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_14-model_00-model_states.pt... +32: [2022-12-03 08:20:51,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_32-model_00-model_states.pt. +32: [2022-12-03 08:20:51,368] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_33-model_00-model_states.pt... + 0: [2022-12-03 08:20:51,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_14-model_00-model_states.pt. + 0: [2022-12-03 08:20:51,418] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_15-model_00-model_states.pt... +32: [2022-12-03 08:20:51,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_33-model_00-model_states.pt. +32: [2022-12-03 08:20:51,608] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_34-model_00-model_states.pt... + 0: [2022-12-03 08:20:51,636] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_15-model_00-model_states.pt. + 0: [2022-12-03 08:20:51,636] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_16-model_00-model_states.pt... +32: [2022-12-03 08:20:51,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_34-model_00-model_states.pt. +32: [2022-12-03 08:20:51,847] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_35-model_00-model_states.pt... + 0: [2022-12-03 08:20:51,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_16-model_00-model_states.pt. + 0: [2022-12-03 08:20:51,852] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_17-model_00-model_states.pt... + 0: [2022-12-03 08:20:52,069] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_17-model_00-model_states.pt. + 0: [2022-12-03 08:20:52,070] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_18-model_00-model_states.pt... +32: [2022-12-03 08:20:52,086] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_35-model_00-model_states.pt. +32: [2022-12-03 08:20:52,086] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_36-model_00-model_states.pt... + 0: [2022-12-03 08:20:52,292] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_18-model_00-model_states.pt. + 0: [2022-12-03 08:20:52,293] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_19-model_00-model_states.pt... +32: [2022-12-03 08:20:52,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_36-model_00-model_states.pt. +32: [2022-12-03 08:20:52,322] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_37-model_00-model_states.pt... + 0: [2022-12-03 08:20:52,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_19-model_00-model_states.pt. + 0: [2022-12-03 08:20:52,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_20-model_00-model_states.pt... +32: [2022-12-03 08:20:52,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_37-model_00-model_states.pt. +32: [2022-12-03 08:20:52,563] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_38-model_00-model_states.pt... + 0: [2022-12-03 08:20:52,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_20-model_00-model_states.pt. + 0: [2022-12-03 08:20:52,723] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_3b977boscar/global_step70000/mp_rank_00_model_states.pt + 0: [2022-12-03 08:20:52,723] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/mp_rank_00_model_states.pt... + 0: [2022-12-03 08:20:52,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/mp_rank_00_model_states.pt. +32: [2022-12-03 08:20:52,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_38-model_00-model_states.pt. +32: [2022-12-03 08:20:52,802] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/layer_40-model_00-model_states.pt... +32: [2022-12-03 08:20:52,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/layer_40-model_00-model_states.pt. +32: [2022-12-03 08:20:52,805] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/mp_rank_01_model_states.pt... +32: [2022-12-03 08:20:52,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/mp_rank_01_model_states.pt. +32: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt... +56: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt... +56: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt... +56: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt... +56: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt... +56: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt... +52: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt... +52: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt... +52: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt... +52: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt... +52: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt... +61: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt... +61: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt... +61: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt... +61: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt... +61: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt... +63: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt... +63: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt... +53: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt... +53: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt... +53: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt... +53: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt... +59: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt... +59: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt... +59: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt... +62: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt... +62: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt... +62: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt... +58: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt... +58: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt... +58: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt... +58: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt... +58: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt... +44: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt... +44: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt... +44: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt... +44: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt... +44: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt... +48: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt... +48: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt... +48: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt... +48: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt... +48: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt... +34: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt... +34: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt... +34: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt... +34: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt... +34: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt... +43: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt... +43: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt... +43: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt... +43: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt... +43: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt... +36: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt... +36: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt... +36: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt... +36: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt... +36: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt... +35: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt... +35: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt... +35: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt... +35: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt... +50: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt... +50: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt... +50: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt... +50: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt... +50: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt... +32: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt... +51: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt... +51: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt... +51: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt... +51: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt... +51: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt... +60: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt... +60: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt... +60: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt... +60: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt... +60: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt... +49: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt... +49: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt... +49: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt... +46: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt... +46: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt... +46: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt... +46: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt... +46: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt... +55: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt... +55: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt... +55: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt... +55: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt... +55: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt... +47: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt... +47: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt... +47: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt... +47: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt... +47: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt... +37: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt... +37: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt... +37: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt... +37: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt... +37: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt... +40: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt... +40: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt... +40: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt... +40: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt... +40: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt... +42: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt... +42: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt... +42: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt... +42: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt... +54: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt... +54: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt... +54: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt... +54: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt... +54: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt... +56: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt... +56: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt... +52: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt... +61: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt... +61: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt... +61: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt... +63: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt... +63: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt... +63: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt... +63: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt... +63: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt... +53: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt... +53: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt... +53: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt... +33: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt... +33: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt... +33: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt... +33: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt... +59: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt... +59: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt... +59: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt... +62: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt... +62: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt... +62: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt... +62: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt... +58: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt... +58: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt... +38: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt... +38: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt... +38: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt... +38: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt... +38: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt... +44: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt... +44: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt... +48: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt... +48: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt... +48: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt... +34: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt... +34: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt... +34: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt... +43: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt... +36: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt... +36: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt... +36: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt... +35: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt... +39: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt... +39: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt... +39: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt... +39: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt... +39: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt... +50: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt... +50: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt... +32: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt... +32: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt... +51: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt... +51: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt... +51: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt... +60: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt... +60: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt... +49: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt... +49: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt... +49: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt... +49: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt... +46: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt... +41: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt... +41: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt... +55: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt... +45: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt... +45: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt... +45: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt... +45: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt... +45: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt... +37: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt... +40: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt... +40: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt... +42: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt... +42: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt... +42: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt... +42: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt... +57: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt... +57: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt... +57: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt... +57: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt... +57: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt... +54: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt... +56: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt... +52: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt... +52: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt... +53: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt... +33: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt... +33: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt... +59: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt... +59: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt... +62: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt... +58: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt... +38: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt... +38: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt... +44: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt... +43: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt... +35: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt... +39: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt... +39: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt... +39: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt... +50: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt... +32: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt... +60: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt... +49: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt... +46: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt... +46: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt... +41: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt... +41: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt... +41: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt... +41: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt... +41: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt... +55: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt... +55: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt... +47: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt... +45: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt... +45: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt... +45: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt... +37: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt... +37: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt... +40: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt... +57: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt... +57: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt... +57: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt... +20: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +54: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt... +63: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt... +33: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt... +28: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +38: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt... +26: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +43: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt... +35: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt... +35: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt... +32: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt... +41: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt... +47: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt... +47: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt... +27: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... + 0: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 7: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +19: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +20: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +54: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt... +15: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... + 1: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +11: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +33: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt... + 5: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +10: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +28: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +22: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +12: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +18: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +26: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... + 9: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 2: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +25: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +32: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt... + 4: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 6: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +13: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +31: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... + 3: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +27: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... + 8: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +16: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +14: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +17: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +17: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +29: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +30: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +24: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +24: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +23: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +23: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +21: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... + 0: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 7: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +19: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +20: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +15: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... + 1: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +11: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... + 5: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +10: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +28: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +22: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +12: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +18: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +26: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... + 9: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 2: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +25: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +32: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt... + 4: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 6: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +13: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +31: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... + 3: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +27: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... + 8: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +16: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +14: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +17: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +29: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +30: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +24: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +23: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +21: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... + 0: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 7: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +19: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +20: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +15: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... + 1: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +11: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 5: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +10: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +28: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +22: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +12: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +18: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +26: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... + 9: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 2: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +25: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... + 4: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 6: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +13: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +31: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... + 3: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +27: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... + 8: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... +16: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +14: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +17: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +29: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +30: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +24: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +23: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +21: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... + 0: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 7: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +20: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +15: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... + 1: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +11: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... + 5: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +10: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +28: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +22: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +12: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +18: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +26: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... + 9: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 2: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +25: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... + 4: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 6: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +13: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +31: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... + 3: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +27: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... + 8: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... +16: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +14: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +17: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +29: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +30: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +23: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +21: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... + 0: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 7: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +20: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +15: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... + 1: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +11: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... + 5: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +28: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +22: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +18: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +26: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... + 9: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 2: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 4: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 6: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +13: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +31: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... + 3: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +27: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... + 8: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... +16: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +17: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +29: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +30: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +21: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... + 0: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 7: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +20: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +15: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +11: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +22: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +18: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... + 9: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 4: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 6: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +13: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +31: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +27: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... + 8: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... +17: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +29: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +30: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +24: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... + 0: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 7: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +22: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... + 6: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +13: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +31: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... + 8: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... +29: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +30: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +24: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... + 6: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +13: [2022-12-03 08:20:52,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +32: [2022-12-03 08:20:53,088] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt. +32: [2022-12-03 08:20:53,088] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt +32: [2022-12-03 08:20:53,088] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +32: [2022-12-03 08:20:53,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt. +32: [2022-12-03 08:20:53,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt. +32: [2022-12-03 08:20:53,110] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt +32: [2022-12-03 08:20:53,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt. +32: [2022-12-03 08:20:53,110] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt +32: [2022-12-03 08:20:53,110] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +32: [2022-12-03 08:20:53,110] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +32: [2022-12-03 08:20:53,110] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt +32: [2022-12-03 08:20:53,110] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +10: [2022-12-03 08:20:53,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-12-03 08:20:53,115] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-12-03 08:20:53,115] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +10: [2022-12-03 08:20:53,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-12-03 08:20:53,115] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-12-03 08:20:53,115] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +25: [2022-12-03 08:20:53,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-12-03 08:20:53,120] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-12-03 08:20:53,120] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +25: [2022-12-03 08:20:53,125] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-12-03 08:20:53,125] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-12-03 08:20:53,126] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +10: [2022-12-03 08:20:53,129] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-12-03 08:20:53,129] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-12-03 08:20:53,129] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +25: [2022-12-03 08:20:53,133] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-12-03 08:20:53,133] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-12-03 08:20:53,133] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +15: [2022-12-03 08:20:53,137] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-12-03 08:20:53,137] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-12-03 08:20:53,137] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +25: [2022-12-03 08:20:53,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. + 0: [2022-12-03 08:20:53,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-12-03 08:20:53,141] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-12-03 08:20:53,141] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 0: [2022-12-03 08:20:53,141] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-12-03 08:20:53,141] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-12-03 08:20:53,141] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 0: [2022-12-03 08:20:53,141] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-12-03 08:20:53,141] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-12-03 08:20:53,141] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-12-03 08:20:53,141] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 0: [2022-12-03 08:20:53,141] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-12-03 08:20:53,141] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +25: [2022-12-03 08:20:53,140] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-12-03 08:20:53,140] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +10: [2022-12-03 08:20:53,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-12-03 08:20:53,145] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-12-03 08:20:53,145] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +32: [2022-12-03 08:20:53,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt. +32: [2022-12-03 08:20:53,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt. +32: [2022-12-03 08:20:53,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt. +32: [2022-12-03 08:20:53,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt. +32: [2022-12-03 08:20:53,149] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt +32: [2022-12-03 08:20:53,149] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt +32: [2022-12-03 08:20:53,149] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt +32: [2022-12-03 08:20:53,149] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +32: [2022-12-03 08:20:53,149] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +32: [2022-12-03 08:20:53,149] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt +32: [2022-12-03 08:20:53,149] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +32: [2022-12-03 08:20:53,149] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +15: [2022-12-03 08:20:53,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-12-03 08:20:53,151] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-12-03 08:20:53,151] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +15: [2022-12-03 08:20:53,152] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-12-03 08:20:53,152] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-12-03 08:20:53,152] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +15: [2022-12-03 08:20:53,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-12-03 08:20:53,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-12-03 08:20:53,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-12-03 08:20:53,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-12-03 08:20:53,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +15: [2022-12-03 08:20:53,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +23: [2022-12-03 08:20:53,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +23: [2022-12-03 08:20:53,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-12-03 08:20:53,163] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-12-03 08:20:53,163] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-12-03 08:20:53,163] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +23: [2022-12-03 08:20:53,163] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +23: [2022-12-03 08:20:53,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-12-03 08:20:53,165] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-12-03 08:20:53,165] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +20: [2022-12-03 08:20:53,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-12-03 08:20:53,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-12-03 08:20:53,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-12-03 08:20:53,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-12-03 08:20:53,173] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-12-03 08:20:53,173] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-12-03 08:20:53,173] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +20: [2022-12-03 08:20:53,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-12-03 08:20:53,173] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +20: [2022-12-03 08:20:53,173] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-12-03 08:20:53,173] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-12-03 08:20:53,173] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-12-03 08:20:53,173] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +20: [2022-12-03 08:20:53,173] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +20: [2022-12-03 08:20:53,173] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +23: [2022-12-03 08:20:53,174] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-12-03 08:20:53,174] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-12-03 08:20:53,174] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +25: [2022-12-03 08:20:53,174] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-12-03 08:20:53,174] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-12-03 08:20:53,175] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +23: [2022-12-03 08:20:53,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-12-03 08:20:53,179] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-12-03 08:20:53,179] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +61: [2022-12-03 08:20:53,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt. +61: [2022-12-03 08:20:53,149] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt +61: [2022-12-03 08:20:53,149] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +61: [2022-12-03 08:20:53,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt. +61: [2022-12-03 08:20:53,149] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt +61: [2022-12-03 08:20:53,149] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +61: [2022-12-03 08:20:53,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt. +61: [2022-12-03 08:20:53,150] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt +61: [2022-12-03 08:20:53,150] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +61: [2022-12-03 08:20:53,174] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt. +61: [2022-12-03 08:20:53,174] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt +61: [2022-12-03 08:20:53,174] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +61: [2022-12-03 08:20:53,174] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt. +61: [2022-12-03 08:20:53,174] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt +61: [2022-12-03 08:20:53,174] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +61: [2022-12-03 08:20:53,174] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt. +61: [2022-12-03 08:20:53,175] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt +61: [2022-12-03 08:20:53,175] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 0: [2022-12-03 08:20:53,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-12-03 08:20:53,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-12-03 08:20:53,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +63: [2022-12-03 08:20:53,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt. +63: [2022-12-03 08:20:53,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt. +63: [2022-12-03 08:20:53,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt. +63: [2022-12-03 08:20:53,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt. +63: [2022-12-03 08:20:53,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt +63: [2022-12-03 08:20:53,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt +63: [2022-12-03 08:20:53,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt +63: [2022-12-03 08:20:53,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +63: [2022-12-03 08:20:53,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt +63: [2022-12-03 08:20:53,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +63: [2022-12-03 08:20:53,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +63: [2022-12-03 08:20:53,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 0: [2022-12-03 08:20:53,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-12-03 08:20:53,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. + 0: [2022-12-03 08:20:53,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-12-03 08:20:53,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-12-03 08:20:53,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-12-03 08:20:53,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 0: [2022-12-03 08:20:53,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +63: [2022-12-03 08:20:53,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt. +63: [2022-12-03 08:20:53,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt +63: [2022-12-03 08:20:53,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 1: [2022-12-03 08:20:53,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-12-03 08:20:53,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-12-03 08:20:53,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-12-03 08:20:53,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-12-03 08:20:53,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-12-03 08:20:53,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-12-03 08:20:53,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-12-03 08:20:53,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-12-03 08:20:53,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-12-03 08:20:53,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-12-03 08:20:53,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 1: [2022-12-03 08:20:53,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 1: [2022-12-03 08:20:53,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 1: [2022-12-03 08:20:53,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 1: [2022-12-03 08:20:53,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +52: [2022-12-03 08:20:53,205] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt. +52: [2022-12-03 08:20:53,205] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt. +52: [2022-12-03 08:20:53,205] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt. +52: [2022-12-03 08:20:53,206] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt. +52: [2022-12-03 08:20:53,206] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt. +52: [2022-12-03 08:20:53,206] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt. +52: [2022-12-03 08:20:53,206] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt +52: [2022-12-03 08:20:53,206] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt +52: [2022-12-03 08:20:53,206] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt +52: [2022-12-03 08:20:53,206] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt +52: [2022-12-03 08:20:53,206] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt +52: [2022-12-03 08:20:53,206] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt +52: [2022-12-03 08:20:53,206] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +52: [2022-12-03 08:20:53,206] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +52: [2022-12-03 08:20:53,206] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +52: [2022-12-03 08:20:53,206] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +52: [2022-12-03 08:20:53,206] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +52: [2022-12-03 08:20:53,206] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +56: [2022-12-03 08:20:53,209] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt. +10: [2022-12-03 08:20:53,213] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-12-03 08:20:53,213] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-12-03 08:20:53,213] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +56: [2022-12-03 08:20:53,209] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt +56: [2022-12-03 08:20:53,209] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt. +56: [2022-12-03 08:20:53,209] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +56: [2022-12-03 08:20:53,209] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt +56: [2022-12-03 08:20:53,209] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +56: [2022-12-03 08:20:53,218] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt. +56: [2022-12-03 08:20:53,218] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt. +56: [2022-12-03 08:20:53,218] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt +56: [2022-12-03 08:20:53,218] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +56: [2022-12-03 08:20:53,218] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt +56: [2022-12-03 08:20:53,218] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +56: [2022-12-03 08:20:53,219] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt. +56: [2022-12-03 08:20:53,219] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt +56: [2022-12-03 08:20:53,219] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +56: [2022-12-03 08:20:53,219] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt. +56: [2022-12-03 08:20:53,219] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt +56: [2022-12-03 08:20:53,219] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +37: [2022-12-03 08:20:53,221] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt. +37: [2022-12-03 08:20:53,221] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt. +37: [2022-12-03 08:20:53,221] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt. +37: [2022-12-03 08:20:53,221] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt. +37: [2022-12-03 08:20:53,221] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt. +37: [2022-12-03 08:20:53,221] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt +37: [2022-12-03 08:20:53,221] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt +37: [2022-12-03 08:20:53,221] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt +37: [2022-12-03 08:20:53,221] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +37: [2022-12-03 08:20:53,221] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +37: [2022-12-03 08:20:53,221] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt +37: [2022-12-03 08:20:53,221] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +37: [2022-12-03 08:20:53,221] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt +37: [2022-12-03 08:20:53,221] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +37: [2022-12-03 08:20:53,221] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +61: [2022-12-03 08:20:53,225] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt. +61: [2022-12-03 08:20:53,225] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt +61: [2022-12-03 08:20:53,225] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +54: [2022-12-03 08:20:53,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt. +54: [2022-12-03 08:20:53,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt. +54: [2022-12-03 08:20:53,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt. +54: [2022-12-03 08:20:53,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt. +54: [2022-12-03 08:20:53,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt. +54: [2022-12-03 08:20:53,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt. +54: [2022-12-03 08:20:53,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt. +54: [2022-12-03 08:20:53,230] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt +54: [2022-12-03 08:20:53,230] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt +54: [2022-12-03 08:20:53,230] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt +54: [2022-12-03 08:20:53,230] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt +54: [2022-12-03 08:20:53,230] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt +54: [2022-12-03 08:20:53,230] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt +54: [2022-12-03 08:20:53,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +54: [2022-12-03 08:20:53,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +54: [2022-12-03 08:20:53,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +54: [2022-12-03 08:20:53,230] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt +54: [2022-12-03 08:20:53,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +54: [2022-12-03 08:20:53,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +54: [2022-12-03 08:20:53,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +54: [2022-12-03 08:20:53,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +26: [2022-12-03 08:20:53,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-12-03 08:20:53,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-12-03 08:20:53,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-12-03 08:20:53,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-12-03 08:20:53,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-12-03 08:20:53,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-12-03 08:20:53,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-12-03 08:20:53,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +26: [2022-12-03 08:20:53,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-12-03 08:20:53,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +26: [2022-12-03 08:20:53,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-12-03 08:20:53,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-12-03 08:20:53,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +26: [2022-12-03 08:20:53,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +26: [2022-12-03 08:20:53,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +53: [2022-12-03 08:20:53,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt. +53: [2022-12-03 08:20:53,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt. +53: [2022-12-03 08:20:53,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt. +53: [2022-12-03 08:20:53,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt. +53: [2022-12-03 08:20:53,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt. +53: [2022-12-03 08:20:53,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt. +53: [2022-12-03 08:20:53,240] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt +53: [2022-12-03 08:20:53,240] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt +53: [2022-12-03 08:20:53,240] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt +53: [2022-12-03 08:20:53,240] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt +53: [2022-12-03 08:20:53,240] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt +53: [2022-12-03 08:20:53,240] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt +53: [2022-12-03 08:20:53,240] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +53: [2022-12-03 08:20:53,240] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +53: [2022-12-03 08:20:53,241] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +53: [2022-12-03 08:20:53,241] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +53: [2022-12-03 08:20:53,241] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +53: [2022-12-03 08:20:53,241] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +17: [2022-12-03 08:20:53,242] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-12-03 08:20:53,242] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-12-03 08:20:53,242] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-12-03 08:20:53,242] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-12-03 08:20:53,242] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-12-03 08:20:53,242] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-12-03 08:20:53,242] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-12-03 08:20:53,242] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-12-03 08:20:53,242] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-12-03 08:20:53,242] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-12-03 08:20:53,242] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +17: [2022-12-03 08:20:53,242] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +17: [2022-12-03 08:20:53,242] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +17: [2022-12-03 08:20:53,242] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +17: [2022-12-03 08:20:53,242] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 0: [2022-12-03 08:20:53,246] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-12-03 08:20:53,246] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +11: [2022-12-03 08:20:53,246] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-12-03 08:20:53,246] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-12-03 08:20:53,246] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-12-03 08:20:53,246] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-12-03 08:20:53,246] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-12-03 08:20:53,246] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-12-03 08:20:53,246] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-12-03 08:20:53,246] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-12-03 08:20:53,246] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-12-03 08:20:53,246] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-12-03 08:20:53,246] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +11: [2022-12-03 08:20:53,246] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +11: [2022-12-03 08:20:53,247] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +11: [2022-12-03 08:20:53,247] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +11: [2022-12-03 08:20:53,247] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +14: [2022-12-03 08:20:53,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-12-03 08:20:53,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-12-03 08:20:53,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-12-03 08:20:53,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-12-03 08:20:53,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-12-03 08:20:53,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-12-03 08:20:53,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-12-03 08:20:53,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-12-03 08:20:53,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-12-03 08:20:53,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-12-03 08:20:53,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +14: [2022-12-03 08:20:53,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +14: [2022-12-03 08:20:53,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +14: [2022-12-03 08:20:53,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +14: [2022-12-03 08:20:53,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +48: [2022-12-03 08:20:53,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt. +48: [2022-12-03 08:20:53,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt. +48: [2022-12-03 08:20:53,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt. +48: [2022-12-03 08:20:53,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt +48: [2022-12-03 08:20:53,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt +48: [2022-12-03 08:20:53,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt +48: [2022-12-03 08:20:53,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +48: [2022-12-03 08:20:53,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +48: [2022-12-03 08:20:53,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 5: [2022-12-03 08:20:53,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-12-03 08:20:53,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-12-03 08:20:53,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-12-03 08:20:53,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-12-03 08:20:53,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-12-03 08:20:53,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-12-03 08:20:53,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-12-03 08:20:53,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-12-03 08:20:53,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-12-03 08:20:53,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-12-03 08:20:53,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 5: [2022-12-03 08:20:53,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 5: [2022-12-03 08:20:53,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 5: [2022-12-03 08:20:53,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 5: [2022-12-03 08:20:53,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 9: [2022-12-03 08:20:53,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-12-03 08:20:53,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-12-03 08:20:53,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-12-03 08:20:53,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-12-03 08:20:53,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-12-03 08:20:53,275] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-12-03 08:20:53,275] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-12-03 08:20:53,275] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-12-03 08:20:53,275] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-12-03 08:20:53,275] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-12-03 08:20:53,275] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 9: [2022-12-03 08:20:53,275] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 9: [2022-12-03 08:20:53,275] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 9: [2022-12-03 08:20:53,275] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 9: [2022-12-03 08:20:53,275] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +53: [2022-12-03 08:20:53,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt. +48: [2022-12-03 08:20:53,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt. +53: [2022-12-03 08:20:53,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt +48: [2022-12-03 08:20:53,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt +53: [2022-12-03 08:20:53,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +48: [2022-12-03 08:20:53,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +48: [2022-12-03 08:20:53,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt. +48: [2022-12-03 08:20:53,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt +48: [2022-12-03 08:20:53,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +12: [2022-12-03 08:20:53,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-12-03 08:20:53,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-12-03 08:20:53,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +12: [2022-12-03 08:20:53,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-12-03 08:20:53,280] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-12-03 08:20:53,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +56: [2022-12-03 08:20:53,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt. +56: [2022-12-03 08:20:53,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt +56: [2022-12-03 08:20:53,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 2: [2022-12-03 08:20:53,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 2: [2022-12-03 08:20:53,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-12-03 08:20:53,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-12-03 08:20:53,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-12-03 08:20:53,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-12-03 08:20:53,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-12-03 08:20:53,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-12-03 08:20:53,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 2: [2022-12-03 08:20:53,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-12-03 08:20:53,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-12-03 08:20:53,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 2: [2022-12-03 08:20:53,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 2: [2022-12-03 08:20:53,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 2: [2022-12-03 08:20:53,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 2: [2022-12-03 08:20:53,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 3: [2022-12-03 08:20:53,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-12-03 08:20:53,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-12-03 08:20:53,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-12-03 08:20:53,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-12-03 08:20:53,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-12-03 08:20:53,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-12-03 08:20:53,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-12-03 08:20:53,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-12-03 08:20:53,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-12-03 08:20:53,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-12-03 08:20:53,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 3: [2022-12-03 08:20:53,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 3: [2022-12-03 08:20:53,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 3: [2022-12-03 08:20:53,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 3: [2022-12-03 08:20:53,284] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +12: [2022-12-03 08:20:53,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-12-03 08:20:53,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-12-03 08:20:53,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +12: [2022-12-03 08:20:53,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +12: [2022-12-03 08:20:53,287] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-12-03 08:20:53,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +12: [2022-12-03 08:20:53,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-12-03 08:20:53,287] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-12-03 08:20:53,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 7: [2022-12-03 08:20:53,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-12-03 08:20:53,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-12-03 08:20:53,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +42: [2022-12-03 08:20:53,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt. +42: [2022-12-03 08:20:53,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt. +42: [2022-12-03 08:20:53,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt. + 7: [2022-12-03 08:20:53,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-12-03 08:20:53,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-12-03 08:20:53,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +42: [2022-12-03 08:20:53,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt + 7: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 7: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 7: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +42: [2022-12-03 08:20:53,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt +42: [2022-12-03 08:20:53,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt +42: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +42: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +42: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 6: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-12-03 08:20:53,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-12-03 08:20:53,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-12-03 08:20:53,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-12-03 08:20:53,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-12-03 08:20:53,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 6: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 6: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 6: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +42: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt. + 6: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +42: [2022-12-03 08:20:53,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt +42: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt. +42: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt. +42: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +42: [2022-12-03 08:20:53,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt +42: [2022-12-03 08:20:53,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt +42: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +42: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt. +42: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +42: [2022-12-03 08:20:53,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt +42: [2022-12-03 08:20:53,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +28: [2022-12-03 08:20:53,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-12-03 08:20:53,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-12-03 08:20:53,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-12-03 08:20:53,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-12-03 08:20:53,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-12-03 08:20:53,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-12-03 08:20:53,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-12-03 08:20:53,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-12-03 08:20:53,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-12-03 08:20:53,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +28: [2022-12-03 08:20:53,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +28: [2022-12-03 08:20:53,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +28: [2022-12-03 08:20:53,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-12-03 08:20:53,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +28: [2022-12-03 08:20:53,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 7: [2022-12-03 08:20:53,294] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-12-03 08:20:53,294] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-12-03 08:20:53,294] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 7: [2022-12-03 08:20:53,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-12-03 08:20:53,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-12-03 08:20:53,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +38: [2022-12-03 08:20:53,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt. +38: [2022-12-03 08:20:53,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt. +38: [2022-12-03 08:20:53,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt. +38: [2022-12-03 08:20:53,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt. +38: [2022-12-03 08:20:53,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt. +38: [2022-12-03 08:20:53,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt. +38: [2022-12-03 08:20:53,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt +38: [2022-12-03 08:20:53,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt +38: [2022-12-03 08:20:53,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt +38: [2022-12-03 08:20:53,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt +38: [2022-12-03 08:20:53,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt +38: [2022-12-03 08:20:53,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt +38: [2022-12-03 08:20:53,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +38: [2022-12-03 08:20:53,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +38: [2022-12-03 08:20:53,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +38: [2022-12-03 08:20:53,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +38: [2022-12-03 08:20:53,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +38: [2022-12-03 08:20:53,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +59: [2022-12-03 08:20:53,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt. +59: [2022-12-03 08:20:53,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt. +59: [2022-12-03 08:20:53,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt. +59: [2022-12-03 08:20:53,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt. +50: [2022-12-03 08:20:53,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt. +50: [2022-12-03 08:20:53,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt. +50: [2022-12-03 08:20:53,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt. +50: [2022-12-03 08:20:53,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt. +50: [2022-12-03 08:20:53,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt. +50: [2022-12-03 08:20:53,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt. +50: [2022-12-03 08:20:53,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt +50: [2022-12-03 08:20:53,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt +50: [2022-12-03 08:20:53,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt. +50: [2022-12-03 08:20:53,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt +50: [2022-12-03 08:20:53,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt +50: [2022-12-03 08:20:53,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt +50: [2022-12-03 08:20:53,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +50: [2022-12-03 08:20:53,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +50: [2022-12-03 08:20:53,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt +50: [2022-12-03 08:20:53,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +50: [2022-12-03 08:20:53,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt +50: [2022-12-03 08:20:53,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +50: [2022-12-03 08:20:53,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +50: [2022-12-03 08:20:53,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +50: [2022-12-03 08:20:53,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +49: [2022-12-03 08:20:53,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt. +49: [2022-12-03 08:20:53,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt. +49: [2022-12-03 08:20:53,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt. +49: [2022-12-03 08:20:53,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt. +49: [2022-12-03 08:20:53,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt. +49: [2022-12-03 08:20:53,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt. +49: [2022-12-03 08:20:53,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt. +49: [2022-12-03 08:20:53,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt. +49: [2022-12-03 08:20:53,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt +49: [2022-12-03 08:20:53,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt +49: [2022-12-03 08:20:53,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt +49: [2022-12-03 08:20:53,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +49: [2022-12-03 08:20:53,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt +49: [2022-12-03 08:20:53,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt +49: [2022-12-03 08:20:53,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt +49: [2022-12-03 08:20:53,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt +49: [2022-12-03 08:20:53,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +49: [2022-12-03 08:20:53,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +49: [2022-12-03 08:20:53,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt +49: [2022-12-03 08:20:53,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +49: [2022-12-03 08:20:53,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +49: [2022-12-03 08:20:53,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +49: [2022-12-03 08:20:53,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +49: [2022-12-03 08:20:53,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +59: [2022-12-03 08:20:53,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt. +59: [2022-12-03 08:20:53,298] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt +59: [2022-12-03 08:20:53,298] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt +59: [2022-12-03 08:20:53,298] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt +59: [2022-12-03 08:20:53,298] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt +59: [2022-12-03 08:20:53,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +59: [2022-12-03 08:20:53,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +59: [2022-12-03 08:20:53,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +59: [2022-12-03 08:20:53,298] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt +59: [2022-12-03 08:20:53,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +59: [2022-12-03 08:20:53,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +45: [2022-12-03 08:20:53,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt. +45: [2022-12-03 08:20:53,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt. +45: [2022-12-03 08:20:53,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt. +45: [2022-12-03 08:20:53,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt. +45: [2022-12-03 08:20:53,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt +45: [2022-12-03 08:20:53,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt +45: [2022-12-03 08:20:53,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt. +45: [2022-12-03 08:20:53,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt +45: [2022-12-03 08:20:53,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt +45: [2022-12-03 08:20:53,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +45: [2022-12-03 08:20:53,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +45: [2022-12-03 08:20:53,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +22: [2022-12-03 08:20:53,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +22: [2022-12-03 08:20:53,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +45: [2022-12-03 08:20:53,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +45: [2022-12-03 08:20:53,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt +22: [2022-12-03 08:20:53,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +22: [2022-12-03 08:20:53,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-12-03 08:20:53,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +22: [2022-12-03 08:20:53,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +18: [2022-12-03 08:20:53,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-12-03 08:20:53,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-12-03 08:20:53,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-12-03 08:20:53,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-12-03 08:20:53,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-12-03 08:20:53,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-12-03 08:20:53,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-12-03 08:20:53,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-12-03 08:20:53,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-12-03 08:20:53,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-12-03 08:20:53,315] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +18: [2022-12-03 08:20:53,315] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +18: [2022-12-03 08:20:53,315] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +18: [2022-12-03 08:20:53,315] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +18: [2022-12-03 08:20:53,315] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +45: [2022-12-03 08:20:53,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +30: [2022-12-03 08:20:53,329] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-12-03 08:20:53,329] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-12-03 08:20:53,329] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-12-03 08:20:53,329] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-12-03 08:20:53,329] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-12-03 08:20:53,329] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-12-03 08:20:53,329] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +30: [2022-12-03 08:20:53,329] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +30: [2022-12-03 08:20:53,329] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +22: [2022-12-03 08:20:53,330] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-12-03 08:20:53,330] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-12-03 08:20:53,330] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +31: [2022-12-03 08:20:53,331] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-12-03 08:20:53,331] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-12-03 08:20:53,331] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-12-03 08:20:53,331] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-12-03 08:20:53,331] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-12-03 08:20:53,332] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-12-03 08:20:53,332] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-12-03 08:20:53,332] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-12-03 08:20:53,332] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-12-03 08:20:53,332] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-12-03 08:20:53,332] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +31: [2022-12-03 08:20:53,332] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +31: [2022-12-03 08:20:53,332] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +31: [2022-12-03 08:20:53,332] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +31: [2022-12-03 08:20:53,332] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +22: [2022-12-03 08:20:53,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-12-03 08:20:53,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-12-03 08:20:53,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +13: [2022-12-03 08:20:53,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-12-03 08:20:53,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-12-03 08:20:53,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-12-03 08:20:53,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-12-03 08:20:53,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-12-03 08:20:53,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-12-03 08:20:53,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-12-03 08:20:53,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +13: [2022-12-03 08:20:53,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-12-03 08:20:53,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-12-03 08:20:53,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +13: [2022-12-03 08:20:53,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +13: [2022-12-03 08:20:53,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +13: [2022-12-03 08:20:53,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-12-03 08:20:53,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +62: [2022-12-03 08:20:53,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt. +62: [2022-12-03 08:20:53,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt. +62: [2022-12-03 08:20:53,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt. +62: [2022-12-03 08:20:53,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt. +62: [2022-12-03 08:20:53,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt. +62: [2022-12-03 08:20:53,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt +62: [2022-12-03 08:20:53,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt +62: [2022-12-03 08:20:53,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt +62: [2022-12-03 08:20:53,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt +62: [2022-12-03 08:20:53,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt +62: [2022-12-03 08:20:53,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +62: [2022-12-03 08:20:53,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +62: [2022-12-03 08:20:53,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +62: [2022-12-03 08:20:53,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +62: [2022-12-03 08:20:53,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +21: [2022-12-03 08:20:53,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-12-03 08:20:53,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-12-03 08:20:53,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-12-03 08:20:53,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-12-03 08:20:53,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-12-03 08:20:53,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-12-03 08:20:53,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +21: [2022-12-03 08:20:53,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +21: [2022-12-03 08:20:53,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +19: [2022-12-03 08:20:53,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-12-03 08:20:53,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-12-03 08:20:53,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-12-03 08:20:53,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-12-03 08:20:53,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-12-03 08:20:53,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-12-03 08:20:53,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +19: [2022-12-03 08:20:53,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +19: [2022-12-03 08:20:53,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +51: [2022-12-03 08:20:53,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt. +51: [2022-12-03 08:20:53,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt. +51: [2022-12-03 08:20:53,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt. +51: [2022-12-03 08:20:53,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt. +51: [2022-12-03 08:20:53,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt. +51: [2022-12-03 08:20:53,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt. +51: [2022-12-03 08:20:53,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt. +51: [2022-12-03 08:20:53,339] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt +51: [2022-12-03 08:20:53,339] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt +51: [2022-12-03 08:20:53,339] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt +51: [2022-12-03 08:20:53,339] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt +51: [2022-12-03 08:20:53,339] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt +51: [2022-12-03 08:20:53,339] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt +51: [2022-12-03 08:20:53,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt. +51: [2022-12-03 08:20:53,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +51: [2022-12-03 08:20:53,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +51: [2022-12-03 08:20:53,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +51: [2022-12-03 08:20:53,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +51: [2022-12-03 08:20:53,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +51: [2022-12-03 08:20:53,339] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt +51: [2022-12-03 08:20:53,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +51: [2022-12-03 08:20:53,339] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt +51: [2022-12-03 08:20:53,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +51: [2022-12-03 08:20:53,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +40: [2022-12-03 08:20:53,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt. +40: [2022-12-03 08:20:53,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt. +40: [2022-12-03 08:20:53,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt. +40: [2022-12-03 08:20:53,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt. +40: [2022-12-03 08:20:53,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt. +40: [2022-12-03 08:20:53,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt. +40: [2022-12-03 08:20:53,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt. +40: [2022-12-03 08:20:53,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt +40: [2022-12-03 08:20:53,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt +40: [2022-12-03 08:20:53,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt +40: [2022-12-03 08:20:53,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt +40: [2022-12-03 08:20:53,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt +40: [2022-12-03 08:20:53,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +40: [2022-12-03 08:20:53,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt +40: [2022-12-03 08:20:53,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt +40: [2022-12-03 08:20:53,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +40: [2022-12-03 08:20:53,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +40: [2022-12-03 08:20:53,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +40: [2022-12-03 08:20:53,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +40: [2022-12-03 08:20:53,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +40: [2022-12-03 08:20:53,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +39: [2022-12-03 08:20:53,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt. +39: [2022-12-03 08:20:53,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt. +39: [2022-12-03 08:20:53,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt +39: [2022-12-03 08:20:53,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt. +39: [2022-12-03 08:20:53,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt +39: [2022-12-03 08:20:53,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt +39: [2022-12-03 08:20:53,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +39: [2022-12-03 08:20:53,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +39: [2022-12-03 08:20:53,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +36: [2022-12-03 08:20:53,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt. +36: [2022-12-03 08:20:53,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt. +36: [2022-12-03 08:20:53,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt. +36: [2022-12-03 08:20:53,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt. +36: [2022-12-03 08:20:53,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt. +36: [2022-12-03 08:20:53,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt +36: [2022-12-03 08:20:53,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt +36: [2022-12-03 08:20:53,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt +36: [2022-12-03 08:20:53,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt +36: [2022-12-03 08:20:53,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt +36: [2022-12-03 08:20:53,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +36: [2022-12-03 08:20:53,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +36: [2022-12-03 08:20:53,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +36: [2022-12-03 08:20:53,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +36: [2022-12-03 08:20:53,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +57: [2022-12-03 08:20:53,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt. +57: [2022-12-03 08:20:53,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt. +57: [2022-12-03 08:20:53,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt. +57: [2022-12-03 08:20:53,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt. +57: [2022-12-03 08:20:53,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt. +57: [2022-12-03 08:20:53,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt. +57: [2022-12-03 08:20:53,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt. +57: [2022-12-03 08:20:53,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt +57: [2022-12-03 08:20:53,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt +57: [2022-12-03 08:20:53,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt +57: [2022-12-03 08:20:53,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt +57: [2022-12-03 08:20:53,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt +57: [2022-12-03 08:20:53,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt +57: [2022-12-03 08:20:53,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt +57: [2022-12-03 08:20:53,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +57: [2022-12-03 08:20:53,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +57: [2022-12-03 08:20:53,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +57: [2022-12-03 08:20:53,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +57: [2022-12-03 08:20:53,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +57: [2022-12-03 08:20:53,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +57: [2022-12-03 08:20:53,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +39: [2022-12-03 08:20:53,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt. +39: [2022-12-03 08:20:53,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt. +39: [2022-12-03 08:20:53,346] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt +39: [2022-12-03 08:20:53,346] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt +39: [2022-12-03 08:20:53,347] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +39: [2022-12-03 08:20:53,347] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +39: [2022-12-03 08:20:53,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt. +39: [2022-12-03 08:20:53,347] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt +39: [2022-12-03 08:20:53,347] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +33: [2022-12-03 08:20:53,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt. +33: [2022-12-03 08:20:53,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt. +33: [2022-12-03 08:20:53,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt. +33: [2022-12-03 08:20:53,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt. +33: [2022-12-03 08:20:53,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt. +33: [2022-12-03 08:20:53,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt. +33: [2022-12-03 08:20:53,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt +33: [2022-12-03 08:20:53,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt +33: [2022-12-03 08:20:53,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt +33: [2022-12-03 08:20:53,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt +33: [2022-12-03 08:20:53,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +33: [2022-12-03 08:20:53,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +33: [2022-12-03 08:20:53,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt +33: [2022-12-03 08:20:53,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +33: [2022-12-03 08:20:53,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt +33: [2022-12-03 08:20:53,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +33: [2022-12-03 08:20:53,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +33: [2022-12-03 08:20:53,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +60: [2022-12-03 08:20:53,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt. +60: [2022-12-03 08:20:53,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt. +60: [2022-12-03 08:20:53,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt. +60: [2022-12-03 08:20:53,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt. +60: [2022-12-03 08:20:53,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt. +60: [2022-12-03 08:20:53,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt +60: [2022-12-03 08:20:53,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt +60: [2022-12-03 08:20:53,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt +60: [2022-12-03 08:20:53,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt +60: [2022-12-03 08:20:53,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt +60: [2022-12-03 08:20:53,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +60: [2022-12-03 08:20:53,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +60: [2022-12-03 08:20:53,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +60: [2022-12-03 08:20:53,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +60: [2022-12-03 08:20:53,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +29: [2022-12-03 08:20:53,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-12-03 08:20:53,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-12-03 08:20:53,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-12-03 08:20:53,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-12-03 08:20:53,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-12-03 08:20:53,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-12-03 08:20:53,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-12-03 08:20:53,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-12-03 08:20:53,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +29: [2022-12-03 08:20:53,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-12-03 08:20:53,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +29: [2022-12-03 08:20:53,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +29: [2022-12-03 08:20:53,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-12-03 08:20:53,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +29: [2022-12-03 08:20:53,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +21: [2022-12-03 08:20:53,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-12-03 08:20:53,356] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-12-03 08:20:53,356] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +30: [2022-12-03 08:20:53,356] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-12-03 08:20:53,356] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-12-03 08:20:53,356] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +52: [2022-12-03 08:20:53,357] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt. +52: [2022-12-03 08:20:53,357] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt +52: [2022-12-03 08:20:53,357] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 4: [2022-12-03 08:20:53,359] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-12-03 08:20:53,359] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-12-03 08:20:53,359] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-12-03 08:20:53,359] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-12-03 08:20:53,359] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-12-03 08:20:53,359] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-12-03 08:20:53,359] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 4: [2022-12-03 08:20:53,359] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 4: [2022-12-03 08:20:53,359] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +47: [2022-12-03 08:20:53,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt. +27: [2022-12-03 08:20:53,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-12-03 08:20:53,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-12-03 08:20:53,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-12-03 08:20:53,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-12-03 08:20:53,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +47: [2022-12-03 08:20:53,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt. +27: [2022-12-03 08:20:53,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +47: [2022-12-03 08:20:53,360] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt +27: [2022-12-03 08:20:53,360] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-12-03 08:20:53,360] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-12-03 08:20:53,360] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-12-03 08:20:53,360] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-12-03 08:20:53,360] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +47: [2022-12-03 08:20:53,360] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt +47: [2022-12-03 08:20:53,360] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +27: [2022-12-03 08:20:53,360] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +47: [2022-12-03 08:20:53,360] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +27: [2022-12-03 08:20:53,360] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +27: [2022-12-03 08:20:53,360] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +27: [2022-12-03 08:20:53,360] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +27: [2022-12-03 08:20:53,360] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +27: [2022-12-03 08:20:53,360] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +27: [2022-12-03 08:20:53,360] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +22: [2022-12-03 08:20:53,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. + 4: [2022-12-03 08:20:53,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +22: [2022-12-03 08:20:53,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt + 4: [2022-12-03 08:20:53,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +22: [2022-12-03 08:20:53,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 4: [2022-12-03 08:20:53,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-12-03 08:20:53,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-12-03 08:20:53,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +47: [2022-12-03 08:20:53,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt. +47: [2022-12-03 08:20:53,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt. + 4: [2022-12-03 08:20:53,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +47: [2022-12-03 08:20:53,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt +47: [2022-12-03 08:20:53,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt +47: [2022-12-03 08:20:53,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +47: [2022-12-03 08:20:53,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +24: [2022-12-03 08:20:53,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-12-03 08:20:53,363] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-12-03 08:20:53,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-12-03 08:20:53,363] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-12-03 08:20:53,363] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-12-03 08:20:53,363] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-12-03 08:20:53,363] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-12-03 08:20:53,363] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-12-03 08:20:53,363] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-12-03 08:20:53,363] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-12-03 08:20:53,363] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +24: [2022-12-03 08:20:53,363] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +24: [2022-12-03 08:20:53,363] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +24: [2022-12-03 08:20:53,363] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +24: [2022-12-03 08:20:53,363] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +34: [2022-12-03 08:20:53,363] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt. +34: [2022-12-03 08:20:53,363] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt. +34: [2022-12-03 08:20:53,363] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt. +34: [2022-12-03 08:20:53,363] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt. +34: [2022-12-03 08:20:53,363] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt. +34: [2022-12-03 08:20:53,363] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt +34: [2022-12-03 08:20:53,363] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt +34: [2022-12-03 08:20:53,363] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt +34: [2022-12-03 08:20:53,363] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt +34: [2022-12-03 08:20:53,363] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt +34: [2022-12-03 08:20:53,363] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +34: [2022-12-03 08:20:53,363] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +34: [2022-12-03 08:20:53,363] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +34: [2022-12-03 08:20:53,363] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +34: [2022-12-03 08:20:53,363] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +30: [2022-12-03 08:20:53,367] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-12-03 08:20:53,367] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-12-03 08:20:53,367] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +46: [2022-12-03 08:20:53,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt. +46: [2022-12-03 08:20:53,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt. +46: [2022-12-03 08:20:53,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt. +46: [2022-12-03 08:20:53,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt. +46: [2022-12-03 08:20:53,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt. +46: [2022-12-03 08:20:53,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt. +46: [2022-12-03 08:20:53,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt. +46: [2022-12-03 08:20:53,368] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt +46: [2022-12-03 08:20:53,368] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt +46: [2022-12-03 08:20:53,368] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt +46: [2022-12-03 08:20:53,368] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt +46: [2022-12-03 08:20:53,368] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt +46: [2022-12-03 08:20:53,368] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt +46: [2022-12-03 08:20:53,368] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +46: [2022-12-03 08:20:53,368] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt +46: [2022-12-03 08:20:53,368] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +46: [2022-12-03 08:20:53,368] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +46: [2022-12-03 08:20:53,368] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +46: [2022-12-03 08:20:53,368] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +46: [2022-12-03 08:20:53,368] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +46: [2022-12-03 08:20:53,368] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 8: [2022-12-03 08:20:53,372] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-12-03 08:20:53,372] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-12-03 08:20:53,372] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-12-03 08:20:53,372] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-12-03 08:20:53,372] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-12-03 08:20:53,372] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-12-03 08:20:53,372] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-12-03 08:20:53,372] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-12-03 08:20:53,372] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-12-03 08:20:53,372] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-12-03 08:20:53,372] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 8: [2022-12-03 08:20:53,372] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 8: [2022-12-03 08:20:53,372] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 8: [2022-12-03 08:20:53,372] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 8: [2022-12-03 08:20:53,372] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +16: [2022-12-03 08:20:53,374] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-12-03 08:20:53,374] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-12-03 08:20:53,374] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-12-03 08:20:53,374] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-12-03 08:20:53,374] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-12-03 08:20:53,374] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-12-03 08:20:53,374] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-12-03 08:20:53,374] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-12-03 08:20:53,374] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-12-03 08:20:53,374] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-12-03 08:20:53,374] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +16: [2022-12-03 08:20:53,374] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +16: [2022-12-03 08:20:53,374] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-12-03 08:20:53,374] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-12-03 08:20:53,374] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +16: [2022-12-03 08:20:53,374] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +16: [2022-12-03 08:20:53,374] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +16: [2022-12-03 08:20:53,374] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +39: [2022-12-03 08:20:53,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt. +39: [2022-12-03 08:20:53,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt +39: [2022-12-03 08:20:53,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +35: [2022-12-03 08:20:53,381] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt. +35: [2022-12-03 08:20:53,381] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt +35: [2022-12-03 08:20:53,381] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +35: [2022-12-03 08:20:53,381] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt. +35: [2022-12-03 08:20:53,381] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt +35: [2022-12-03 08:20:53,381] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +35: [2022-12-03 08:20:53,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt. +35: [2022-12-03 08:20:53,382] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt +35: [2022-12-03 08:20:53,382] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +35: [2022-12-03 08:20:53,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt. +35: [2022-12-03 08:20:53,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt. +35: [2022-12-03 08:20:53,382] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt +35: [2022-12-03 08:20:53,382] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt +35: [2022-12-03 08:20:53,382] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +35: [2022-12-03 08:20:53,382] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +19: [2022-12-03 08:20:53,385] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +58: [2022-12-03 08:20:53,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt. +58: [2022-12-03 08:20:53,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt. +58: [2022-12-03 08:20:53,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt. +58: [2022-12-03 08:20:53,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt. +58: [2022-12-03 08:20:53,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt. +58: [2022-12-03 08:20:53,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt. +58: [2022-12-03 08:20:53,387] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt +58: [2022-12-03 08:20:53,387] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt +43: [2022-12-03 08:20:53,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt. +43: [2022-12-03 08:20:53,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt. +43: [2022-12-03 08:20:53,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt. +58: [2022-12-03 08:20:53,387] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt +58: [2022-12-03 08:20:53,387] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt +58: [2022-12-03 08:20:53,387] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt +58: [2022-12-03 08:20:53,387] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt +58: [2022-12-03 08:20:53,387] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +58: [2022-12-03 08:20:53,387] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +58: [2022-12-03 08:20:53,387] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +58: [2022-12-03 08:20:53,387] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +58: [2022-12-03 08:20:53,387] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +58: [2022-12-03 08:20:53,387] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +58: [2022-12-03 08:20:53,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt. +58: [2022-12-03 08:20:53,388] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt +58: [2022-12-03 08:20:53,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +43: [2022-12-03 08:20:53,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt. +43: [2022-12-03 08:20:53,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt. +43: [2022-12-03 08:20:53,387] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt +43: [2022-12-03 08:20:53,387] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt +43: [2022-12-03 08:20:53,387] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt +43: [2022-12-03 08:20:53,387] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt +43: [2022-12-03 08:20:53,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +43: [2022-12-03 08:20:53,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +43: [2022-12-03 08:20:53,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +43: [2022-12-03 08:20:53,388] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt +43: [2022-12-03 08:20:53,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +43: [2022-12-03 08:20:53,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +19: [2022-12-03 08:20:53,385] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-12-03 08:20:53,385] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +35: [2022-12-03 08:20:53,391] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt. +35: [2022-12-03 08:20:53,391] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt. +35: [2022-12-03 08:20:53,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt +35: [2022-12-03 08:20:53,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt +35: [2022-12-03 08:20:53,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +35: [2022-12-03 08:20:53,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +35: [2022-12-03 08:20:53,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt. +35: [2022-12-03 08:20:53,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt +35: [2022-12-03 08:20:53,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 7: [2022-12-03 08:20:53,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-12-03 08:20:53,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-12-03 08:20:53,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +41: [2022-12-03 08:20:53,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt. +41: [2022-12-03 08:20:53,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt. +41: [2022-12-03 08:20:53,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt. +41: [2022-12-03 08:20:53,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt. +41: [2022-12-03 08:20:53,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt +41: [2022-12-03 08:20:53,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt +41: [2022-12-03 08:20:53,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt +41: [2022-12-03 08:20:53,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt +41: [2022-12-03 08:20:53,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt. +41: [2022-12-03 08:20:53,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +41: [2022-12-03 08:20:53,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +41: [2022-12-03 08:20:53,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +41: [2022-12-03 08:20:53,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +41: [2022-12-03 08:20:53,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt +41: [2022-12-03 08:20:53,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +44: [2022-12-03 08:20:53,398] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt. +44: [2022-12-03 08:20:53,398] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt. +44: [2022-12-03 08:20:53,398] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt. +44: [2022-12-03 08:20:53,398] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt. +44: [2022-12-03 08:20:53,398] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt. +44: [2022-12-03 08:20:53,398] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt +44: [2022-12-03 08:20:53,398] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt +44: [2022-12-03 08:20:53,398] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt +44: [2022-12-03 08:20:53,398] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt +44: [2022-12-03 08:20:53,398] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt +44: [2022-12-03 08:20:53,398] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt. +44: [2022-12-03 08:20:53,398] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +44: [2022-12-03 08:20:53,398] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +44: [2022-12-03 08:20:53,398] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +44: [2022-12-03 08:20:53,398] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt +44: [2022-12-03 08:20:53,398] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +44: [2022-12-03 08:20:53,398] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +44: [2022-12-03 08:20:53,398] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +31: [2022-12-03 08:20:53,400] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-12-03 08:20:53,400] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-12-03 08:20:53,400] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +18: [2022-12-03 08:20:53,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-12-03 08:20:53,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-12-03 08:20:53,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +12: [2022-12-03 08:20:53,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-12-03 08:20:53,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-12-03 08:20:53,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +38: [2022-12-03 08:20:53,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt. +38: [2022-12-03 08:20:53,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt +38: [2022-12-03 08:20:53,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +22: [2022-12-03 08:20:53,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-12-03 08:20:53,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-12-03 08:20:53,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +15: [2022-12-03 08:20:53,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-12-03 08:20:53,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-12-03 08:20:53,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +21: [2022-12-03 08:20:53,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-12-03 08:20:53,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-12-03 08:20:53,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +45: [2022-12-03 08:20:53,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt. +45: [2022-12-03 08:20:53,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt +45: [2022-12-03 08:20:53,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +28: [2022-12-03 08:20:53,420] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-12-03 08:20:53,420] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-12-03 08:20:53,420] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +31: [2022-12-03 08:20:53,423] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-12-03 08:20:53,423] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-12-03 08:20:53,423] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +20: [2022-12-03 08:20:53,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-12-03 08:20:53,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-12-03 08:20:53,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +24: [2022-12-03 08:20:53,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +57: [2022-12-03 08:20:53,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt. +24: [2022-12-03 08:20:53,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +57: [2022-12-03 08:20:53,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt +24: [2022-12-03 08:20:53,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +57: [2022-12-03 08:20:53,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +29: [2022-12-03 08:20:53,435] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-12-03 08:20:53,435] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-12-03 08:20:53,435] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +47: [2022-12-03 08:20:53,435] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt. +47: [2022-12-03 08:20:53,435] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt +47: [2022-12-03 08:20:53,435] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +11: [2022-12-03 08:20:53,435] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. + 4: [2022-12-03 08:20:53,435] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +11: [2022-12-03 08:20:53,436] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt + 4: [2022-12-03 08:20:53,436] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +11: [2022-12-03 08:20:53,436] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 4: [2022-12-03 08:20:53,436] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +25: [2022-12-03 08:20:53,436] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-12-03 08:20:53,436] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-12-03 08:20:53,436] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +47: [2022-12-03 08:20:53,437] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt. +47: [2022-12-03 08:20:53,437] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt +47: [2022-12-03 08:20:53,437] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +47: [2022-12-03 08:20:53,437] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt. +47: [2022-12-03 08:20:53,437] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt +47: [2022-12-03 08:20:53,437] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +23: [2022-12-03 08:20:53,438] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-12-03 08:20:53,438] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-12-03 08:20:53,438] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +54: [2022-12-03 08:20:53,438] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt. +54: [2022-12-03 08:20:53,438] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt +54: [2022-12-03 08:20:53,438] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 1: [2022-12-03 08:20:53,438] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-12-03 08:20:53,439] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-12-03 08:20:53,439] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +13: [2022-12-03 08:20:53,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-12-03 08:20:53,440] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-12-03 08:20:53,440] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 8: [2022-12-03 08:20:53,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-12-03 08:20:53,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt +14: [2022-12-03 08:20:53,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. + 8: [2022-12-03 08:20:53,443] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +14: [2022-12-03 08:20:53,443] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-12-03 08:20:53,443] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +63: [2022-12-03 08:20:53,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt. +63: [2022-12-03 08:20:53,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt +63: [2022-12-03 08:20:53,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +62: [2022-12-03 08:20:53,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt. +62: [2022-12-03 08:20:53,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt +62: [2022-12-03 08:20:53,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +19: [2022-12-03 08:20:53,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-12-03 08:20:53,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-12-03 08:20:53,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +34: [2022-12-03 08:20:53,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt. +34: [2022-12-03 08:20:53,450] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt +36: [2022-12-03 08:20:53,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt. +34: [2022-12-03 08:20:53,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +36: [2022-12-03 08:20:53,450] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt +26: [2022-12-03 08:20:53,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +36: [2022-12-03 08:20:53,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +26: [2022-12-03 08:20:53,451] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-12-03 08:20:53,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +48: [2022-12-03 08:20:53,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt. +48: [2022-12-03 08:20:53,453] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt +48: [2022-12-03 08:20:53,453] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +59: [2022-12-03 08:20:53,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt. +59: [2022-12-03 08:20:53,454] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt +59: [2022-12-03 08:20:53,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +40: [2022-12-03 08:20:53,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt. +40: [2022-12-03 08:20:53,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt +40: [2022-12-03 08:20:53,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 5: [2022-12-03 08:20:53,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-12-03 08:20:53,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-12-03 08:20:53,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +21: [2022-12-03 08:20:53,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-12-03 08:20:53,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-12-03 08:20:53,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +55: [2022-12-03 08:20:53,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt. +55: [2022-12-03 08:20:53,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt. +55: [2022-12-03 08:20:53,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt. +55: [2022-12-03 08:20:53,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt +55: [2022-12-03 08:20:53,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt. +55: [2022-12-03 08:20:53,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +55: [2022-12-03 08:20:53,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt +55: [2022-12-03 08:20:53,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt +55: [2022-12-03 08:20:53,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt +55: [2022-12-03 08:20:53,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +55: [2022-12-03 08:20:53,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +55: [2022-12-03 08:20:53,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 6: [2022-12-03 08:20:53,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-12-03 08:20:53,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-12-03 08:20:53,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +43: [2022-12-03 08:20:53,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt. +37: [2022-12-03 08:20:53,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt. +43: [2022-12-03 08:20:53,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt +37: [2022-12-03 08:20:53,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt +43: [2022-12-03 08:20:53,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +37: [2022-12-03 08:20:53,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +10: [2022-12-03 08:20:53,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-12-03 08:20:53,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-12-03 08:20:53,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +17: [2022-12-03 08:20:53,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-12-03 08:20:53,459] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-12-03 08:20:53,459] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 3: [2022-12-03 08:20:53,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-12-03 08:20:53,459] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-12-03 08:20:53,459] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 2: [2022-12-03 08:20:53,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-12-03 08:20:53,461] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-12-03 08:20:53,461] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 9: [2022-12-03 08:20:53,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-12-03 08:20:53,462] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-12-03 08:20:53,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +41: [2022-12-03 08:20:53,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt. +41: [2022-12-03 08:20:53,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt +41: [2022-12-03 08:20:53,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +60: [2022-12-03 08:20:53,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt. +60: [2022-12-03 08:20:53,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt +60: [2022-12-03 08:20:53,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +30: [2022-12-03 08:20:53,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-12-03 08:20:53,467] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-12-03 08:20:53,467] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +56: [2022-12-03 08:20:53,468] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt. +56: [2022-12-03 08:20:53,468] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt +56: [2022-12-03 08:20:53,468] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +19: [2022-12-03 08:20:53,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-12-03 08:20:53,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-12-03 08:20:53,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +33: [2022-12-03 08:20:53,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt. +33: [2022-12-03 08:20:53,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt +33: [2022-12-03 08:20:53,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +53: [2022-12-03 08:20:53,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt. +53: [2022-12-03 08:20:53,477] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt +53: [2022-12-03 08:20:53,477] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +58: [2022-12-03 08:20:53,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt. +58: [2022-12-03 08:20:53,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt +58: [2022-12-03 08:20:53,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +50: [2022-12-03 08:20:53,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt. +50: [2022-12-03 08:20:53,479] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt +50: [2022-12-03 08:20:53,479] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +39: [2022-12-03 08:20:53,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt. +39: [2022-12-03 08:20:53,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt +39: [2022-12-03 08:20:53,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +27: [2022-12-03 08:20:53,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-12-03 08:20:53,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-12-03 08:20:53,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +61: [2022-12-03 08:20:53,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt. +61: [2022-12-03 08:20:53,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt +42: [2022-12-03 08:20:53,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt. +61: [2022-12-03 08:20:53,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +42: [2022-12-03 08:20:53,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt +42: [2022-12-03 08:20:53,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +46: [2022-12-03 08:20:53,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt. +46: [2022-12-03 08:20:53,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt +46: [2022-12-03 08:20:53,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +52: [2022-12-03 08:20:53,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt. +52: [2022-12-03 08:20:53,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt +52: [2022-12-03 08:20:53,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +55: [2022-12-03 08:20:53,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt. +55: [2022-12-03 08:20:53,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt. +55: [2022-12-03 08:20:53,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt. +55: [2022-12-03 08:20:53,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt +55: [2022-12-03 08:20:53,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt +55: [2022-12-03 08:20:53,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt +55: [2022-12-03 08:20:53,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +55: [2022-12-03 08:20:53,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +55: [2022-12-03 08:20:53,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +55: [2022-12-03 08:20:53,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt. +55: [2022-12-03 08:20:53,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt +55: [2022-12-03 08:20:53,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +47: [2022-12-03 08:20:53,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt. +47: [2022-12-03 08:20:53,508] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt +47: [2022-12-03 08:20:53,508] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +20: [2022-12-03 08:20:53,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-12-03 08:20:53,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-12-03 08:20:53,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +12: [2022-12-03 08:20:53,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-12-03 08:20:53,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-12-03 08:20:53,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +38: [2022-12-03 08:20:53,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt. +38: [2022-12-03 08:20:53,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt +38: [2022-12-03 08:20:53,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +31: [2022-12-03 08:20:53,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-12-03 08:20:53,547] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-12-03 08:20:53,547] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +36: [2022-12-03 08:20:53,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt. +36: [2022-12-03 08:20:53,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt +36: [2022-12-03 08:20:53,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +26: [2022-12-03 08:20:53,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-12-03 08:20:53,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +19: [2022-12-03 08:20:53,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +15: [2022-12-03 08:20:53,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +26: [2022-12-03 08:20:53,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +19: [2022-12-03 08:20:53,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +15: [2022-12-03 08:20:53,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt + 4: [2022-12-03 08:20:53,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +19: [2022-12-03 08:20:53,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +15: [2022-12-03 08:20:53,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 4: [2022-12-03 08:20:53,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-12-03 08:20:53,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 8: [2022-12-03 08:20:53,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-12-03 08:20:53,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-12-03 08:20:53,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +16: [2022-12-03 08:20:53,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-12-03 08:20:53,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-12-03 08:20:53,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 7: [2022-12-03 08:20:53,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-12-03 08:20:53,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-12-03 08:20:53,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +25: [2022-12-03 08:20:53,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-12-03 08:20:53,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-12-03 08:20:53,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +29: [2022-12-03 08:20:53,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-12-03 08:20:53,550] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-12-03 08:20:53,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +24: [2022-12-03 08:20:53,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-12-03 08:20:53,551] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-12-03 08:20:53,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +28: [2022-12-03 08:20:53,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-12-03 08:20:53,551] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-12-03 08:20:53,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +14: [2022-12-03 08:20:53,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-12-03 08:20:53,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-12-03 08:20:53,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 1: [2022-12-03 08:20:53,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-12-03 08:20:53,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-12-03 08:20:53,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +63: [2022-12-03 08:20:53,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt. +63: [2022-12-03 08:20:53,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt +63: [2022-12-03 08:20:53,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +11: [2022-12-03 08:20:53,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-12-03 08:20:53,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-12-03 08:20:53,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 5: [2022-12-03 08:20:53,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-12-03 08:20:53,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-12-03 08:20:53,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +62: [2022-12-03 08:20:53,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt. +62: [2022-12-03 08:20:53,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt +62: [2022-12-03 08:20:53,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +27: [2022-12-03 08:20:53,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +23: [2022-12-03 08:20:53,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +27: [2022-12-03 08:20:53,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +23: [2022-12-03 08:20:53,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +27: [2022-12-03 08:20:53,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +23: [2022-12-03 08:20:53,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +44: [2022-12-03 08:20:53,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt. +44: [2022-12-03 08:20:53,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt +44: [2022-12-03 08:20:53,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +21: [2022-12-03 08:20:53,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-12-03 08:20:53,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-12-03 08:20:53,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +13: [2022-12-03 08:20:53,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-12-03 08:20:53,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-12-03 08:20:53,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +63: [2022-12-03 08:20:53,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt. +63: [2022-12-03 08:20:53,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt +63: [2022-12-03 08:20:53,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +12: [2022-12-03 08:20:53,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-12-03 08:20:53,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-12-03 08:20:53,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +18: [2022-12-03 08:20:53,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-12-03 08:20:53,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-12-03 08:20:53,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +24: [2022-12-03 08:20:53,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-12-03 08:20:53,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-12-03 08:20:53,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 8: [2022-12-03 08:20:53,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-12-03 08:20:53,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-12-03 08:20:53,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +45: [2022-12-03 08:20:53,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt. + 3: [2022-12-03 08:20:53,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +45: [2022-12-03 08:20:53,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt + 3: [2022-12-03 08:20:53,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-12-03 08:20:53,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +45: [2022-12-03 08:20:53,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +62: [2022-12-03 08:20:53,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt. +62: [2022-12-03 08:20:53,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt +62: [2022-12-03 08:20:53,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +34: [2022-12-03 08:20:53,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt. +34: [2022-12-03 08:20:53,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt +29: [2022-12-03 08:20:53,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +34: [2022-12-03 08:20:53,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +29: [2022-12-03 08:20:53,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-12-03 08:20:53,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +34: [2022-12-03 08:20:53,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt. +34: [2022-12-03 08:20:53,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt +34: [2022-12-03 08:20:53,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +26: [2022-12-03 08:20:53,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-12-03 08:20:53,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-12-03 08:20:53,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +33: [2022-12-03 08:20:53,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt. +33: [2022-12-03 08:20:53,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt +33: [2022-12-03 08:20:53,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +22: [2022-12-03 08:20:53,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-12-03 08:20:53,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-12-03 08:20:53,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +21: [2022-12-03 08:20:53,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-12-03 08:20:53,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-12-03 08:20:53,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +20: [2022-12-03 08:20:53,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-12-03 08:20:53,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-12-03 08:20:53,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +16: [2022-12-03 08:20:53,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +19: [2022-12-03 08:20:53,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +16: [2022-12-03 08:20:53,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-12-03 08:20:53,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +19: [2022-12-03 08:20:53,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt + 2: [2022-12-03 08:20:53,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-12-03 08:20:53,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-12-03 08:20:53,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +19: [2022-12-03 08:20:53,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 5: [2022-12-03 08:20:53,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-12-03 08:20:53,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 2: [2022-12-03 08:20:53,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 5: [2022-12-03 08:20:53,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 2: [2022-12-03 08:20:53,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-12-03 08:20:53,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +48: [2022-12-03 08:20:53,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt. +48: [2022-12-03 08:20:53,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt +48: [2022-12-03 08:20:53,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +48: [2022-12-03 08:20:53,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt. +48: [2022-12-03 08:20:53,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt + 6: [2022-12-03 08:20:53,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +48: [2022-12-03 08:20:53,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +36: [2022-12-03 08:20:53,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt. + 6: [2022-12-03 08:20:53,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +36: [2022-12-03 08:20:53,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt + 6: [2022-12-03 08:20:53,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +36: [2022-12-03 08:20:53,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 9: [2022-12-03 08:20:53,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-12-03 08:20:53,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-12-03 08:20:53,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-12-03 08:20:53,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-12-03 08:20:53,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 9: [2022-12-03 08:20:53,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 3: [2022-12-03 08:20:53,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-12-03 08:20:53,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 4: [2022-12-03 08:20:53,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-12-03 08:20:53,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 3: [2022-12-03 08:20:53,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 4: [2022-12-03 08:20:53,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +44: [2022-12-03 08:20:53,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt. +44: [2022-12-03 08:20:53,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt +44: [2022-12-03 08:20:53,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +37: [2022-12-03 08:20:53,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt. +37: [2022-12-03 08:20:53,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt +37: [2022-12-03 08:20:53,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +59: [2022-12-03 08:20:53,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt. +18: [2022-12-03 08:20:53,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +10: [2022-12-03 08:20:53,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +18: [2022-12-03 08:20:53,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +10: [2022-12-03 08:20:53,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +18: [2022-12-03 08:20:53,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +10: [2022-12-03 08:20:53,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +15: [2022-12-03 08:20:53,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-12-03 08:20:53,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-12-03 08:20:53,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +23: [2022-12-03 08:20:53,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-12-03 08:20:53,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-12-03 08:20:53,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +41: [2022-12-03 08:20:53,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt. +60: [2022-12-03 08:20:53,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt. +41: [2022-12-03 08:20:53,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt +60: [2022-12-03 08:20:53,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt +41: [2022-12-03 08:20:53,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +60: [2022-12-03 08:20:53,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +43: [2022-12-03 08:20:53,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt. +43: [2022-12-03 08:20:53,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt +43: [2022-12-03 08:20:53,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +13: [2022-12-03 08:20:53,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. + 6: [2022-12-03 08:20:53,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +13: [2022-12-03 08:20:53,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-12-03 08:20:53,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 6: [2022-12-03 08:20:53,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-12-03 08:20:53,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +28: [2022-12-03 08:20:53,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-12-03 08:20:53,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-12-03 08:20:53,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +10: [2022-12-03 08:20:53,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +45: [2022-12-03 08:20:53,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt. +37: [2022-12-03 08:20:53,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt. +10: [2022-12-03 08:20:53,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +45: [2022-12-03 08:20:53,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt +37: [2022-12-03 08:20:53,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt +45: [2022-12-03 08:20:53,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +37: [2022-12-03 08:20:53,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +10: [2022-12-03 08:20:53,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 7: [2022-12-03 08:20:53,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-12-03 08:20:53,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-12-03 08:20:53,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +14: [2022-12-03 08:20:53,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-12-03 08:20:53,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-12-03 08:20:53,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 1: [2022-12-03 08:20:53,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-12-03 08:20:53,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-12-03 08:20:53,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +17: [2022-12-03 08:20:53,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-12-03 08:20:53,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-12-03 08:20:53,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-12-03 08:20:53,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-12-03 08:20:53,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +17: [2022-12-03 08:20:53,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +59: [2022-12-03 08:20:53,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt +59: [2022-12-03 08:20:53,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +59: [2022-12-03 08:20:53,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt. +59: [2022-12-03 08:20:53,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt +59: [2022-12-03 08:20:53,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +43: [2022-12-03 08:20:53,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt. +43: [2022-12-03 08:20:53,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt +43: [2022-12-03 08:20:53,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +41: [2022-12-03 08:20:53,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt. +41: [2022-12-03 08:20:53,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt +41: [2022-12-03 08:20:53,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +60: [2022-12-03 08:20:53,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt. +60: [2022-12-03 08:20:53,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt +60: [2022-12-03 08:20:53,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +25: [2022-12-03 08:20:53,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-12-03 08:20:53,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-12-03 08:20:53,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +11: [2022-12-03 08:20:53,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-12-03 08:20:53,571] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-12-03 08:20:53,571] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +22: [2022-12-03 08:20:53,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-12-03 08:20:53,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-12-03 08:20:53,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +30: [2022-12-03 08:20:53,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-12-03 08:20:53,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-12-03 08:20:53,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-12-03 08:20:53,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step70000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-12-03 08:20:53,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! +30: [2022-12-03 08:20:53,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step70000 is ready now! + 0: successfully saved checkpoint at iteration 70000 to checkpoints_3b977boscar +63: time (ms) | save-checkpoint: 5445.65 +63: iteration 70010/ 73814 | consumed samples: 35845120 | consumed tokens: 73410805760 | elapsed time per iteration (s): 2.85 | learning rate: 2.120E-05 | global batch size: 512 | lm loss: 1.880692E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 179.598 | TFLOPs: 18.49 | +63: iteration 70020/ 73814 | consumed samples: 35850240 | consumed tokens: 73421291520 | elapsed time per iteration (s): 2.24 | learning rate: 2.119E-05 | global batch size: 512 | lm loss: 1.883545E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.263 | TFLOPs: 23.50 | +63: iteration 70030/ 73814 | consumed samples: 35855360 | consumed tokens: 73431777280 | elapsed time per iteration (s): 2.23 | learning rate: 2.119E-05 | global batch size: 512 | lm loss: 1.867384E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.429 | TFLOPs: 23.62 | +63: iteration 70040/ 73814 | consumed samples: 35860480 | consumed tokens: 73442263040 | elapsed time per iteration (s): 2.25 | learning rate: 2.118E-05 | global batch size: 512 | lm loss: 1.893393E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.329 | TFLOPs: 23.40 | +63: iteration 70050/ 73814 | consumed samples: 35865600 | consumed tokens: 73452748800 | elapsed time per iteration (s): 2.24 | learning rate: 2.118E-05 | global batch size: 512 | lm loss: 1.867708E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.166 | TFLOPs: 23.49 | +63: iteration 70060/ 73814 | consumed samples: 35870720 | consumed tokens: 73463234560 | elapsed time per iteration (s): 2.23 | learning rate: 2.117E-05 | global batch size: 512 | lm loss: 1.891092E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.174 | TFLOPs: 23.59 | +63: iteration 70070/ 73814 | consumed samples: 35875840 | consumed tokens: 73473720320 | elapsed time per iteration (s): 2.23 | learning rate: 2.116E-05 | global batch size: 512 | lm loss: 1.884312E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.167 | TFLOPs: 23.59 | +63: iteration 70080/ 73814 | consumed samples: 35880960 | consumed tokens: 73484206080 | elapsed time per iteration (s): 2.23 | learning rate: 2.116E-05 | global batch size: 512 | lm loss: 1.888001E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.818 | TFLOPs: 23.66 | +63: iteration 70090/ 73814 | consumed samples: 35886080 | consumed tokens: 73494691840 | elapsed time per iteration (s): 2.24 | learning rate: 2.115E-05 | global batch size: 512 | lm loss: 1.897122E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.026 | TFLOPs: 23.58 | +63: iteration 70100/ 73814 | consumed samples: 35891200 | consumed tokens: 73505177600 | elapsed time per iteration (s): 2.23 | learning rate: 2.115E-05 | global batch size: 512 | lm loss: 1.889647E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.353 | TFLOPs: 23.61 | +63: iteration 70110/ 73814 | consumed samples: 35896320 | consumed tokens: 73515663360 | elapsed time per iteration (s): 2.23 | learning rate: 2.114E-05 | global batch size: 512 | lm loss: 1.879790E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.543 | TFLOPs: 23.63 | +63: iteration 70120/ 73814 | consumed samples: 35901440 | consumed tokens: 73526149120 | elapsed time per iteration (s): 2.22 | learning rate: 2.113E-05 | global batch size: 512 | lm loss: 1.890749E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.155 | TFLOPs: 23.69 | +63: iteration 70130/ 73814 | consumed samples: 35906560 | consumed tokens: 73536634880 | elapsed time per iteration (s): 2.49 | learning rate: 2.113E-05 | global batch size: 512 | lm loss: 1.879839E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.387 | TFLOPs: 21.14 | +63: iteration 70140/ 73814 | consumed samples: 35911680 | consumed tokens: 73547120640 | elapsed time per iteration (s): 2.22 | learning rate: 2.112E-05 | global batch size: 512 | lm loss: 1.881909E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.451 | TFLOPs: 23.72 | +63: iteration 70150/ 73814 | consumed samples: 35916800 | consumed tokens: 73557606400 | elapsed time per iteration (s): 2.23 | learning rate: 2.111E-05 | global batch size: 512 | lm loss: 1.875913E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.831 | TFLOPs: 23.66 | +63: iteration 70160/ 73814 | consumed samples: 35921920 | consumed tokens: 73568092160 | elapsed time per iteration (s): 2.23 | learning rate: 2.111E-05 | global batch size: 512 | lm loss: 1.881379E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.791 | TFLOPs: 23.66 | +63: iteration 70170/ 73814 | consumed samples: 35927040 | consumed tokens: 73578577920 | elapsed time per iteration (s): 2.24 | learning rate: 2.110E-05 | global batch size: 512 | lm loss: 1.910877E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.962 | TFLOPs: 23.57 | +63: iteration 70180/ 73814 | consumed samples: 35932160 | consumed tokens: 73589063680 | elapsed time per iteration (s): 2.24 | learning rate: 2.110E-05 | global batch size: 512 | lm loss: 1.904046E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.014 | TFLOPs: 23.58 | +63: iteration 70190/ 73814 | consumed samples: 35937280 | consumed tokens: 73599549440 | elapsed time per iteration (s): 2.23 | learning rate: 2.109E-05 | global batch size: 512 | lm loss: 1.892829E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.737 | TFLOPs: 23.65 | +63: iteration 70200/ 73814 | consumed samples: 35942400 | consumed tokens: 73610035200 | elapsed time per iteration (s): 2.24 | learning rate: 2.108E-05 | global batch size: 512 | lm loss: 1.882936E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.907 | TFLOPs: 23.56 | +63: iteration 70210/ 73814 | consumed samples: 35947520 | consumed tokens: 73620520960 | elapsed time per iteration (s): 2.24 | learning rate: 2.108E-05 | global batch size: 512 | lm loss: 1.899464E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.974 | TFLOPs: 23.57 | +63: iteration 70220/ 73814 | consumed samples: 35952640 | consumed tokens: 73631006720 | elapsed time per iteration (s): 2.24 | learning rate: 2.107E-05 | global batch size: 512 | lm loss: 1.882408E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.598 | TFLOPs: 23.53 | +63: iteration 70230/ 73814 | consumed samples: 35957760 | consumed tokens: 73641492480 | elapsed time per iteration (s): 2.24 | learning rate: 2.107E-05 | global batch size: 512 | lm loss: 1.900307E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.363 | TFLOPs: 23.51 | +63: iteration 70240/ 73814 | consumed samples: 35962880 | consumed tokens: 73651978240 | elapsed time per iteration (s): 2.24 | learning rate: 2.106E-05 | global batch size: 512 | lm loss: 1.882613E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.081 | TFLOPs: 23.58 | +63: iteration 70250/ 73814 | consumed samples: 35968000 | consumed tokens: 73662464000 | elapsed time per iteration (s): 2.28 | learning rate: 2.105E-05 | global batch size: 512 | lm loss: 1.881024E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.966 | TFLOPs: 23.16 | +63: iteration 70260/ 73814 | consumed samples: 35973120 | consumed tokens: 73672949760 | elapsed time per iteration (s): 2.25 | learning rate: 2.105E-05 | global batch size: 512 | lm loss: 1.864403E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.128 | TFLOPs: 23.38 | +63: iteration 70270/ 73814 | consumed samples: 35978240 | consumed tokens: 73683435520 | elapsed time per iteration (s): 2.23 | learning rate: 2.104E-05 | global batch size: 512 | lm loss: 1.885548E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.142 | TFLOPs: 23.59 | +63: iteration 70280/ 73814 | consumed samples: 35983360 | consumed tokens: 73693921280 | elapsed time per iteration (s): 2.24 | learning rate: 2.104E-05 | global batch size: 512 | lm loss: 1.910362E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.312 | TFLOPs: 23.50 | +63: iteration 70290/ 73814 | consumed samples: 35988480 | consumed tokens: 73704407040 | elapsed time per iteration (s): 2.25 | learning rate: 2.103E-05 | global batch size: 512 | lm loss: 1.869803E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.344 | TFLOPs: 23.40 | +63: iteration 70300/ 73814 | consumed samples: 35993600 | consumed tokens: 73714892800 | elapsed time per iteration (s): 2.23 | learning rate: 2.103E-05 | global batch size: 512 | lm loss: 1.885546E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.619 | TFLOPs: 23.64 | +63: iteration 70310/ 73814 | consumed samples: 35998720 | consumed tokens: 73725378560 | elapsed time per iteration (s): 2.23 | learning rate: 2.102E-05 | global batch size: 512 | lm loss: 1.886340E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.104 | TFLOPs: 23.69 | +63: iteration 70320/ 73814 | consumed samples: 36003840 | consumed tokens: 73735864320 | elapsed time per iteration (s): 2.23 | learning rate: 2.101E-05 | global batch size: 512 | lm loss: 1.902679E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.623 | TFLOPs: 23.64 | +63: iteration 70330/ 73814 | consumed samples: 36008960 | consumed tokens: 73746350080 | elapsed time per iteration (s): 2.25 | learning rate: 2.101E-05 | global batch size: 512 | lm loss: 1.902342E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.708 | TFLOPs: 23.44 | +63: iteration 70340/ 73814 | consumed samples: 36014080 | consumed tokens: 73756835840 | elapsed time per iteration (s): 2.23 | learning rate: 2.100E-05 | global batch size: 512 | lm loss: 1.876478E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.900 | TFLOPs: 23.67 | +63: iteration 70350/ 73814 | consumed samples: 36019200 | consumed tokens: 73767321600 | elapsed time per iteration (s): 2.25 | learning rate: 2.100E-05 | global batch size: 512 | lm loss: 1.884930E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.918 | TFLOPs: 23.46 | +63: iteration 70360/ 73814 | consumed samples: 36024320 | consumed tokens: 73777807360 | elapsed time per iteration (s): 2.23 | learning rate: 2.099E-05 | global batch size: 512 | lm loss: 1.875189E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.885 | TFLOPs: 23.67 | +63: iteration 70370/ 73814 | consumed samples: 36029440 | consumed tokens: 73788293120 | elapsed time per iteration (s): 2.24 | learning rate: 2.098E-05 | global batch size: 512 | lm loss: 1.877060E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.080 | TFLOPs: 23.58 | +63: iteration 70380/ 73814 | consumed samples: 36034560 | consumed tokens: 73798778880 | elapsed time per iteration (s): 2.23 | learning rate: 2.098E-05 | global batch size: 512 | lm loss: 1.876846E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.055 | TFLOPs: 23.68 | +63: iteration 70390/ 73814 | consumed samples: 36039680 | consumed tokens: 73809264640 | elapsed time per iteration (s): 2.24 | learning rate: 2.097E-05 | global batch size: 512 | lm loss: 1.876492E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.854 | TFLOPs: 23.56 | +63: iteration 70400/ 73814 | consumed samples: 36044800 | consumed tokens: 73819750400 | elapsed time per iteration (s): 2.23 | learning rate: 2.097E-05 | global batch size: 512 | lm loss: 1.895937E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.704 | TFLOPs: 23.65 | +63: iteration 70410/ 73814 | consumed samples: 36049920 | consumed tokens: 73830236160 | elapsed time per iteration (s): 2.23 | learning rate: 2.096E-05 | global batch size: 512 | lm loss: 1.896392E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.961 | TFLOPs: 23.67 | +63: iteration 70420/ 73814 | consumed samples: 36055040 | consumed tokens: 73840721920 | elapsed time per iteration (s): 2.36 | learning rate: 2.096E-05 | global batch size: 512 | lm loss: 1.879196E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.661 | TFLOPs: 22.30 | +63: iteration 70430/ 73814 | consumed samples: 36060160 | consumed tokens: 73851207680 | elapsed time per iteration (s): 2.23 | learning rate: 2.095E-05 | global batch size: 512 | lm loss: 1.887584E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.893 | TFLOPs: 23.67 | +63: iteration 70440/ 73814 | consumed samples: 36065280 | consumed tokens: 73861693440 | elapsed time per iteration (s): 2.23 | learning rate: 2.095E-05 | global batch size: 512 | lm loss: 1.887986E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.983 | TFLOPs: 23.68 | +63: iteration 70450/ 73814 | consumed samples: 36070400 | consumed tokens: 73872179200 | elapsed time per iteration (s): 4.13 | learning rate: 2.094E-05 | global batch size: 512 | lm loss: 1.876914E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 123.976 | TFLOPs: 12.76 | +63: iteration 70460/ 73814 | consumed samples: 36075520 | consumed tokens: 73882664960 | elapsed time per iteration (s): 2.40 | learning rate: 2.093E-05 | global batch size: 512 | lm loss: 1.874536E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.238 | TFLOPs: 21.95 | +63: iteration 70470/ 73814 | consumed samples: 36080640 | consumed tokens: 73893150720 | elapsed time per iteration (s): 2.23 | learning rate: 2.093E-05 | global batch size: 512 | lm loss: 1.895172E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.959 | TFLOPs: 23.67 | +63: iteration 70480/ 73814 | consumed samples: 36085760 | consumed tokens: 73903636480 | elapsed time per iteration (s): 2.24 | learning rate: 2.092E-05 | global batch size: 512 | lm loss: 1.889416E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.743 | TFLOPs: 23.55 | +63: iteration 70490/ 73814 | consumed samples: 36090880 | consumed tokens: 73914122240 | elapsed time per iteration (s): 2.22 | learning rate: 2.092E-05 | global batch size: 512 | lm loss: 1.900886E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.388 | TFLOPs: 23.72 | +63: iteration 70500/ 73814 | consumed samples: 36096000 | consumed tokens: 73924608000 | elapsed time per iteration (s): 2.37 | learning rate: 2.091E-05 | global batch size: 512 | lm loss: 1.874822E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.490 | TFLOPs: 22.29 | +63: iteration 70510/ 73814 | consumed samples: 36101120 | consumed tokens: 73935093760 | elapsed time per iteration (s): 2.23 | learning rate: 2.091E-05 | global batch size: 512 | lm loss: 1.872717E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.311 | TFLOPs: 23.61 | +63: iteration 70520/ 73814 | consumed samples: 36106240 | consumed tokens: 73945579520 | elapsed time per iteration (s): 2.23 | learning rate: 2.090E-05 | global batch size: 512 | lm loss: 1.892264E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.587 | TFLOPs: 23.63 | +63: iteration 70530/ 73814 | consumed samples: 36111360 | consumed tokens: 73956065280 | elapsed time per iteration (s): 2.38 | learning rate: 2.090E-05 | global batch size: 512 | lm loss: 1.899216E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.550 | TFLOPs: 22.19 | +63: iteration 70540/ 73814 | consumed samples: 36116480 | consumed tokens: 73966551040 | elapsed time per iteration (s): 2.26 | learning rate: 2.089E-05 | global batch size: 512 | lm loss: 1.887946E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.448 | TFLOPs: 23.31 | +63: iteration 70550/ 73814 | consumed samples: 36121600 | consumed tokens: 73977036800 | elapsed time per iteration (s): 2.22 | learning rate: 2.088E-05 | global batch size: 512 | lm loss: 1.876104E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.224 | TFLOPs: 23.70 | +63: iteration 70560/ 73814 | consumed samples: 36126720 | consumed tokens: 73987522560 | elapsed time per iteration (s): 2.24 | learning rate: 2.088E-05 | global batch size: 512 | lm loss: 1.897195E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.255 | TFLOPs: 23.50 | +63: iteration 70570/ 73814 | consumed samples: 36131840 | consumed tokens: 73998008320 | elapsed time per iteration (s): 2.23 | learning rate: 2.087E-05 | global batch size: 512 | lm loss: 1.899736E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.731 | TFLOPs: 23.65 | +63: iteration 70580/ 73814 | consumed samples: 36136960 | consumed tokens: 74008494080 | elapsed time per iteration (s): 2.24 | learning rate: 2.087E-05 | global batch size: 512 | lm loss: 1.878415E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.888 | TFLOPs: 23.56 | +63: iteration 70590/ 73814 | consumed samples: 36142080 | consumed tokens: 74018979840 | elapsed time per iteration (s): 2.23 | learning rate: 2.086E-05 | global batch size: 512 | lm loss: 1.874353E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.025 | TFLOPs: 23.68 | +63: iteration 70600/ 73814 | consumed samples: 36147200 | consumed tokens: 74029465600 | elapsed time per iteration (s): 2.23 | learning rate: 2.086E-05 | global batch size: 512 | lm loss: 1.882051E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.059 | TFLOPs: 23.68 | +63: iteration 70610/ 73814 | consumed samples: 36152320 | consumed tokens: 74039951360 | elapsed time per iteration (s): 2.24 | learning rate: 2.085E-05 | global batch size: 512 | lm loss: 1.900397E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.247 | TFLOPs: 23.50 | +63: iteration 70620/ 73814 | consumed samples: 36157440 | consumed tokens: 74050437120 | elapsed time per iteration (s): 2.22 | learning rate: 2.085E-05 | global batch size: 512 | lm loss: 1.901530E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.454 | TFLOPs: 23.72 | +63: iteration 70630/ 73814 | consumed samples: 36162560 | consumed tokens: 74060922880 | elapsed time per iteration (s): 2.23 | learning rate: 2.084E-05 | global batch size: 512 | lm loss: 1.891579E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.373 | TFLOPs: 23.61 | +63: iteration 70640/ 73814 | consumed samples: 36167680 | consumed tokens: 74071408640 | elapsed time per iteration (s): 2.23 | learning rate: 2.084E-05 | global batch size: 512 | lm loss: 1.873201E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.877 | TFLOPs: 23.66 | +63: iteration 70650/ 73814 | consumed samples: 36172800 | consumed tokens: 74081894400 | elapsed time per iteration (s): 2.22 | learning rate: 2.083E-05 | global batch size: 512 | lm loss: 1.890809E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.327 | TFLOPs: 23.71 | +63: iteration 70660/ 73814 | consumed samples: 36177920 | consumed tokens: 74092380160 | elapsed time per iteration (s): 2.23 | learning rate: 2.083E-05 | global batch size: 512 | lm loss: 1.863205E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.039 | TFLOPs: 23.68 | +63: iteration 70670/ 73814 | consumed samples: 36183040 | consumed tokens: 74102865920 | elapsed time per iteration (s): 2.22 | learning rate: 2.082E-05 | global batch size: 512 | lm loss: 1.885624E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.241 | TFLOPs: 23.70 | +63: iteration 70680/ 73814 | consumed samples: 36188160 | consumed tokens: 74113351680 | elapsed time per iteration (s): 2.25 | learning rate: 2.082E-05 | global batch size: 512 | lm loss: 1.883615E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.579 | TFLOPs: 23.43 | +63: iteration 70690/ 73814 | consumed samples: 36193280 | consumed tokens: 74123837440 | elapsed time per iteration (s): 2.23 | learning rate: 2.081E-05 | global batch size: 512 | lm loss: 1.895318E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.020 | TFLOPs: 23.68 | +63: iteration 70700/ 73814 | consumed samples: 36198400 | consumed tokens: 74134323200 | elapsed time per iteration (s): 2.25 | learning rate: 2.081E-05 | global batch size: 512 | lm loss: 1.871225E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.042 | TFLOPs: 23.48 | +63: iteration 70710/ 73814 | consumed samples: 36203520 | consumed tokens: 74144808960 | elapsed time per iteration (s): 2.42 | learning rate: 2.080E-05 | global batch size: 512 | lm loss: 1.870463E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.913 | TFLOPs: 21.82 | +63: iteration 70720/ 73814 | consumed samples: 36208640 | consumed tokens: 74155294720 | elapsed time per iteration (s): 2.23 | learning rate: 2.080E-05 | global batch size: 512 | lm loss: 1.888205E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.826 | TFLOPs: 23.66 | +63: iteration 70730/ 73814 | consumed samples: 36213760 | consumed tokens: 74165780480 | elapsed time per iteration (s): 2.22 | learning rate: 2.079E-05 | global batch size: 512 | lm loss: 1.886855E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.378 | TFLOPs: 23.72 | +63: iteration 70740/ 73814 | consumed samples: 36218880 | consumed tokens: 74176266240 | elapsed time per iteration (s): 2.23 | learning rate: 2.078E-05 | global batch size: 512 | lm loss: 1.854226E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.624 | TFLOPs: 23.64 | +63: iteration 70750/ 73814 | consumed samples: 36224000 | consumed tokens: 74186752000 | elapsed time per iteration (s): 2.41 | learning rate: 2.078E-05 | global batch size: 512 | lm loss: 1.896907E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.341 | TFLOPs: 21.86 | +63: iteration 70760/ 73814 | consumed samples: 36229120 | consumed tokens: 74197237760 | elapsed time per iteration (s): 2.38 | learning rate: 2.077E-05 | global batch size: 512 | lm loss: 1.896799E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.753 | TFLOPs: 22.11 | +63: iteration 70770/ 73814 | consumed samples: 36234240 | consumed tokens: 74207723520 | elapsed time per iteration (s): 2.24 | learning rate: 2.077E-05 | global batch size: 512 | lm loss: 1.882339E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.284 | TFLOPs: 23.50 | +63: iteration 70780/ 73814 | consumed samples: 36239360 | consumed tokens: 74218209280 | elapsed time per iteration (s): 2.23 | learning rate: 2.076E-05 | global batch size: 512 | lm loss: 1.857144E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.470 | TFLOPs: 23.62 | +63: iteration 70790/ 73814 | consumed samples: 36244480 | consumed tokens: 74228695040 | elapsed time per iteration (s): 2.28 | learning rate: 2.076E-05 | global batch size: 512 | lm loss: 1.887929E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.788 | TFLOPs: 23.14 | +63: iteration 70800/ 73814 | consumed samples: 36249600 | consumed tokens: 74239180800 | elapsed time per iteration (s): 2.23 | learning rate: 2.075E-05 | global batch size: 512 | lm loss: 1.882555E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.619 | TFLOPs: 23.64 | +63: iteration 70810/ 73814 | consumed samples: 36254720 | consumed tokens: 74249666560 | elapsed time per iteration (s): 2.23 | learning rate: 2.075E-05 | global batch size: 512 | lm loss: 1.898164E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.690 | TFLOPs: 23.65 | +63: iteration 70820/ 73814 | consumed samples: 36259840 | consumed tokens: 74260152320 | elapsed time per iteration (s): 2.25 | learning rate: 2.074E-05 | global batch size: 512 | lm loss: 1.881322E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.044 | TFLOPs: 23.48 | +63: iteration 70830/ 73814 | consumed samples: 36264960 | consumed tokens: 74270638080 | elapsed time per iteration (s): 2.25 | learning rate: 2.074E-05 | global batch size: 512 | lm loss: 1.896264E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.597 | TFLOPs: 23.43 | +63: iteration 70840/ 73814 | consumed samples: 36270080 | consumed tokens: 74281123840 | elapsed time per iteration (s): 2.23 | learning rate: 2.073E-05 | global batch size: 512 | lm loss: 1.879946E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.425 | TFLOPs: 23.62 | +63: iteration 70850/ 73814 | consumed samples: 36275200 | consumed tokens: 74291609600 | elapsed time per iteration (s): 2.25 | learning rate: 2.073E-05 | global batch size: 512 | lm loss: 1.872877E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.052 | TFLOPs: 23.48 | +63: iteration 70860/ 73814 | consumed samples: 36280320 | consumed tokens: 74302095360 | elapsed time per iteration (s): 2.24 | learning rate: 2.072E-05 | global batch size: 512 | lm loss: 1.907102E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.262 | TFLOPs: 23.50 | +63: iteration 70870/ 73814 | consumed samples: 36285440 | consumed tokens: 74312581120 | elapsed time per iteration (s): 2.25 | learning rate: 2.072E-05 | global batch size: 512 | lm loss: 1.876807E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.906 | TFLOPs: 23.46 | +63: iteration 70880/ 73814 | consumed samples: 36290560 | consumed tokens: 74323066880 | elapsed time per iteration (s): 2.24 | learning rate: 2.072E-05 | global batch size: 512 | lm loss: 1.876185E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.348 | TFLOPs: 23.51 | +63: iteration 70890/ 73814 | consumed samples: 36295680 | consumed tokens: 74333552640 | elapsed time per iteration (s): 2.23 | learning rate: 2.071E-05 | global batch size: 512 | lm loss: 1.868684E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.096 | TFLOPs: 23.69 | +63: iteration 70900/ 73814 | consumed samples: 36300800 | consumed tokens: 74344038400 | elapsed time per iteration (s): 2.25 | learning rate: 2.071E-05 | global batch size: 512 | lm loss: 1.867164E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.760 | TFLOPs: 23.45 | +63: iteration 70910/ 73814 | consumed samples: 36305920 | consumed tokens: 74354524160 | elapsed time per iteration (s): 2.39 | learning rate: 2.070E-05 | global batch size: 512 | lm loss: 1.891982E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.201 | TFLOPs: 22.05 | +63: iteration 70920/ 73814 | consumed samples: 36311040 | consumed tokens: 74365009920 | elapsed time per iteration (s): 2.34 | learning rate: 2.070E-05 | global batch size: 512 | lm loss: 1.885851E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.980 | TFLOPs: 22.54 | +63: iteration 70930/ 73814 | consumed samples: 36316160 | consumed tokens: 74375495680 | elapsed time per iteration (s): 2.24 | learning rate: 2.069E-05 | global batch size: 512 | lm loss: 1.878867E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.424 | TFLOPs: 23.52 | +63: iteration 70940/ 73814 | consumed samples: 36321280 | consumed tokens: 74385981440 | elapsed time per iteration (s): 2.23 | learning rate: 2.069E-05 | global batch size: 512 | lm loss: 1.885785E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.427 | TFLOPs: 23.62 | +63: iteration 70950/ 73814 | consumed samples: 36326400 | consumed tokens: 74396467200 | elapsed time per iteration (s): 2.24 | learning rate: 2.068E-05 | global batch size: 512 | lm loss: 1.883385E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.041 | TFLOPs: 23.58 | +63: iteration 70960/ 73814 | consumed samples: 36331520 | consumed tokens: 74406952960 | elapsed time per iteration (s): 2.22 | learning rate: 2.068E-05 | global batch size: 512 | lm loss: 1.878004E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.116 | TFLOPs: 23.69 | +63: iteration 70970/ 73814 | consumed samples: 36336640 | consumed tokens: 74417438720 | elapsed time per iteration (s): 2.24 | learning rate: 2.067E-05 | global batch size: 512 | lm loss: 1.882561E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.114 | TFLOPs: 23.48 | +63: iteration 70980/ 73814 | consumed samples: 36341760 | consumed tokens: 74427924480 | elapsed time per iteration (s): 2.24 | learning rate: 2.067E-05 | global batch size: 512 | lm loss: 1.874480E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.195 | TFLOPs: 23.49 | +63: iteration 70990/ 73814 | consumed samples: 36346880 | consumed tokens: 74438410240 | elapsed time per iteration (s): 2.43 | learning rate: 2.066E-05 | global batch size: 512 | lm loss: 1.884331E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.521 | TFLOPs: 21.67 | +63: iteration 71000/ 73814 | consumed samples: 36352000 | consumed tokens: 74448896000 | elapsed time per iteration (s): 2.24 | learning rate: 2.066E-05 | global batch size: 512 | lm loss: 1.900011E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.020 | TFLOPs: 23.58 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 71000 | lm loss value: 1.755011E+00 | lm loss PPL: 5.783509E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 71010/ 73814 | consumed samples: 36357120 | consumed tokens: 74459381760 | elapsed time per iteration (s): 2.29 | learning rate: 2.065E-05 | global batch size: 512 | lm loss: 1.878987E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.936 | TFLOPs: 23.05 | +63: iteration 71020/ 73814 | consumed samples: 36362240 | consumed tokens: 74469867520 | elapsed time per iteration (s): 2.24 | learning rate: 2.065E-05 | global batch size: 512 | lm loss: 1.885247E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.079 | TFLOPs: 23.58 | +63: iteration 71030/ 73814 | consumed samples: 36367360 | consumed tokens: 74480353280 | elapsed time per iteration (s): 2.23 | learning rate: 2.064E-05 | global batch size: 512 | lm loss: 1.879837E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.605 | TFLOPs: 23.64 | +63: iteration 71040/ 73814 | consumed samples: 36372480 | consumed tokens: 74490839040 | elapsed time per iteration (s): 2.24 | learning rate: 2.064E-05 | global batch size: 512 | lm loss: 1.900474E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.413 | TFLOPs: 23.51 | +63: iteration 71050/ 73814 | consumed samples: 36377600 | consumed tokens: 74501324800 | elapsed time per iteration (s): 2.39 | learning rate: 2.063E-05 | global batch size: 512 | lm loss: 1.894429E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.928 | TFLOPs: 22.02 | +63: iteration 71060/ 73814 | consumed samples: 36382720 | consumed tokens: 74511810560 | elapsed time per iteration (s): 2.32 | learning rate: 2.063E-05 | global batch size: 512 | lm loss: 1.899816E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.444 | TFLOPs: 22.69 | +63: iteration 71070/ 73814 | consumed samples: 36387840 | consumed tokens: 74522296320 | elapsed time per iteration (s): 2.22 | learning rate: 2.063E-05 | global batch size: 512 | lm loss: 1.870744E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.222 | TFLOPs: 23.70 | +63: iteration 71080/ 73814 | consumed samples: 36392960 | consumed tokens: 74532782080 | elapsed time per iteration (s): 2.24 | learning rate: 2.062E-05 | global batch size: 512 | lm loss: 1.875773E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.815 | TFLOPs: 23.56 | +63: iteration 71090/ 73814 | consumed samples: 36398080 | consumed tokens: 74543267840 | elapsed time per iteration (s): 2.49 | learning rate: 2.062E-05 | global batch size: 512 | lm loss: 1.883126E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 205.936 | TFLOPs: 21.20 | +63: iteration 71100/ 73814 | consumed samples: 36403200 | consumed tokens: 74553753600 | elapsed time per iteration (s): 2.22 | learning rate: 2.061E-05 | global batch size: 512 | lm loss: 1.901693E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.277 | TFLOPs: 23.71 | +63: iteration 71110/ 73814 | consumed samples: 36408320 | consumed tokens: 74564239360 | elapsed time per iteration (s): 2.25 | learning rate: 2.061E-05 | global batch size: 512 | lm loss: 1.878061E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.986 | TFLOPs: 23.47 | +63: iteration 71120/ 73814 | consumed samples: 36413440 | consumed tokens: 74574725120 | elapsed time per iteration (s): 2.24 | learning rate: 2.060E-05 | global batch size: 512 | lm loss: 1.897123E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.258 | TFLOPs: 23.50 | +63: iteration 71130/ 73814 | consumed samples: 36418560 | consumed tokens: 74585210880 | elapsed time per iteration (s): 2.23 | learning rate: 2.060E-05 | global batch size: 512 | lm loss: 1.862800E+00 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.515 | TFLOPs: 23.63 | +63: iteration 71140/ 73814 | consumed samples: 36423680 | consumed tokens: 74595696640 | elapsed time per iteration (s): 2.24 | learning rate: 2.059E-05 | global batch size: 512 | lm loss: 1.895023E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.424 | TFLOPs: 23.52 | +63: iteration 71150/ 73814 | consumed samples: 36428800 | consumed tokens: 74606182400 | elapsed time per iteration (s): 2.26 | learning rate: 2.059E-05 | global batch size: 512 | lm loss: 1.865993E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.903 | TFLOPs: 23.36 | +63: iteration 71160/ 73814 | consumed samples: 36433920 | consumed tokens: 74616668160 | elapsed time per iteration (s): 2.23 | learning rate: 2.059E-05 | global batch size: 512 | lm loss: 1.856455E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.912 | TFLOPs: 23.67 | +63: iteration 71170/ 73814 | consumed samples: 36439040 | consumed tokens: 74627153920 | elapsed time per iteration (s): 2.24 | learning rate: 2.058E-05 | global batch size: 512 | lm loss: 1.886297E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.979 | TFLOPs: 23.57 | +63: iteration 71180/ 73814 | consumed samples: 36444160 | consumed tokens: 74637639680 | elapsed time per iteration (s): 2.23 | learning rate: 2.058E-05 | global batch size: 512 | lm loss: 1.886881E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.264 | TFLOPs: 23.60 | +63: iteration 71190/ 73814 | consumed samples: 36449280 | consumed tokens: 74648125440 | elapsed time per iteration (s): 2.23 | learning rate: 2.057E-05 | global batch size: 512 | lm loss: 1.883321E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.381 | TFLOPs: 23.61 | +63: iteration 71200/ 73814 | consumed samples: 36454400 | consumed tokens: 74658611200 | elapsed time per iteration (s): 2.33 | learning rate: 2.057E-05 | global batch size: 512 | lm loss: 1.892325E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.347 | TFLOPs: 22.58 | +63: iteration 71210/ 73814 | consumed samples: 36459520 | consumed tokens: 74669096960 | elapsed time per iteration (s): 2.22 | learning rate: 2.056E-05 | global batch size: 512 | lm loss: 1.889995E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.439 | TFLOPs: 23.72 | +63: iteration 71220/ 73814 | consumed samples: 36464640 | consumed tokens: 74679582720 | elapsed time per iteration (s): 2.24 | learning rate: 2.056E-05 | global batch size: 512 | lm loss: 1.882725E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.653 | TFLOPs: 23.54 | +63: iteration 71230/ 73814 | consumed samples: 36469760 | consumed tokens: 74690068480 | elapsed time per iteration (s): 2.23 | learning rate: 2.055E-05 | global batch size: 512 | lm loss: 1.876520E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.970 | TFLOPs: 23.67 | +63: iteration 71240/ 73814 | consumed samples: 36474880 | consumed tokens: 74700554240 | elapsed time per iteration (s): 2.22 | learning rate: 2.055E-05 | global batch size: 512 | lm loss: 1.887052E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.188 | TFLOPs: 23.70 | +63: iteration 71250/ 73814 | consumed samples: 36480000 | consumed tokens: 74711040000 | elapsed time per iteration (s): 2.26 | learning rate: 2.055E-05 | global batch size: 512 | lm loss: 1.880540E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.047 | TFLOPs: 23.37 | +63: iteration 71260/ 73814 | consumed samples: 36485120 | consumed tokens: 74721525760 | elapsed time per iteration (s): 2.23 | learning rate: 2.054E-05 | global batch size: 512 | lm loss: 1.896225E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.684 | TFLOPs: 23.64 | +63: iteration 71270/ 73814 | consumed samples: 36490240 | consumed tokens: 74732011520 | elapsed time per iteration (s): 2.23 | learning rate: 2.054E-05 | global batch size: 512 | lm loss: 1.878058E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.863 | TFLOPs: 23.66 | +63: iteration 71280/ 73814 | consumed samples: 36495360 | consumed tokens: 74742497280 | elapsed time per iteration (s): 2.24 | learning rate: 2.053E-05 | global batch size: 512 | lm loss: 1.861368E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.082 | TFLOPs: 23.48 | +63: iteration 71290/ 73814 | consumed samples: 36500480 | consumed tokens: 74752983040 | elapsed time per iteration (s): 2.27 | learning rate: 2.053E-05 | global batch size: 512 | lm loss: 1.877422E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.514 | TFLOPs: 23.22 | +63: iteration 71300/ 73814 | consumed samples: 36505600 | consumed tokens: 74763468800 | elapsed time per iteration (s): 2.26 | learning rate: 2.053E-05 | global batch size: 512 | lm loss: 1.862952E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.578 | TFLOPs: 23.33 | +63: iteration 71310/ 73814 | consumed samples: 36510720 | consumed tokens: 74773954560 | elapsed time per iteration (s): 2.39 | learning rate: 2.052E-05 | global batch size: 512 | lm loss: 1.891964E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.300 | TFLOPs: 22.06 | +63: iteration 71320/ 73814 | consumed samples: 36515840 | consumed tokens: 74784440320 | elapsed time per iteration (s): 2.26 | learning rate: 2.052E-05 | global batch size: 512 | lm loss: 1.892424E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.177 | TFLOPs: 23.28 | +63: iteration 71330/ 73814 | consumed samples: 36520960 | consumed tokens: 74794926080 | elapsed time per iteration (s): 2.39 | learning rate: 2.051E-05 | global batch size: 512 | lm loss: 1.883922E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.910 | TFLOPs: 22.02 | +63: iteration 71340/ 73814 | consumed samples: 36526080 | consumed tokens: 74805411840 | elapsed time per iteration (s): 2.54 | learning rate: 2.051E-05 | global batch size: 512 | lm loss: 1.882078E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.711 | TFLOPs: 20.77 | +63: iteration 71350/ 73814 | consumed samples: 36531200 | consumed tokens: 74815897600 | elapsed time per iteration (s): 2.62 | learning rate: 2.050E-05 | global batch size: 512 | lm loss: 1.874288E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 195.205 | TFLOPs: 20.10 | +63: iteration 71360/ 73814 | consumed samples: 36536320 | consumed tokens: 74826383360 | elapsed time per iteration (s): 2.32 | learning rate: 2.050E-05 | global batch size: 512 | lm loss: 1.902891E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.439 | TFLOPs: 22.69 | +63: iteration 71370/ 73814 | consumed samples: 36541440 | consumed tokens: 74836869120 | elapsed time per iteration (s): 3.32 | learning rate: 2.050E-05 | global batch size: 512 | lm loss: 1.874987E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 154.250 | TFLOPs: 15.88 | +63: iteration 71380/ 73814 | consumed samples: 36546560 | consumed tokens: 74847354880 | elapsed time per iteration (s): 2.44 | learning rate: 2.049E-05 | global batch size: 512 | lm loss: 1.871373E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 209.513 | TFLOPs: 21.57 | +63: iteration 71390/ 73814 | consumed samples: 36551680 | consumed tokens: 74857840640 | elapsed time per iteration (s): 2.54 | learning rate: 2.049E-05 | global batch size: 512 | lm loss: 1.879885E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.359 | TFLOPs: 20.73 | +63: iteration 71400/ 73814 | consumed samples: 36556800 | consumed tokens: 74868326400 | elapsed time per iteration (s): 2.25 | learning rate: 2.048E-05 | global batch size: 512 | lm loss: 1.871622E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.619 | TFLOPs: 23.43 | +63: iteration 71410/ 73814 | consumed samples: 36561920 | consumed tokens: 74878812160 | elapsed time per iteration (s): 2.43 | learning rate: 2.048E-05 | global batch size: 512 | lm loss: 1.892480E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.648 | TFLOPs: 21.69 | +63: iteration 71420/ 73814 | consumed samples: 36567040 | consumed tokens: 74889297920 | elapsed time per iteration (s): 2.46 | learning rate: 2.048E-05 | global batch size: 512 | lm loss: 1.899431E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 208.326 | TFLOPs: 21.45 | +63: iteration 71430/ 73814 | consumed samples: 36572160 | consumed tokens: 74899783680 | elapsed time per iteration (s): 2.25 | learning rate: 2.047E-05 | global batch size: 512 | lm loss: 1.863096E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.897 | TFLOPs: 23.46 | +63: iteration 71440/ 73814 | consumed samples: 36577280 | consumed tokens: 74910269440 | elapsed time per iteration (s): 2.55 | learning rate: 2.047E-05 | global batch size: 512 | lm loss: 1.892359E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.760 | TFLOPs: 20.67 | +63: iteration 71450/ 73814 | consumed samples: 36582400 | consumed tokens: 74920755200 | elapsed time per iteration (s): 2.24 | learning rate: 2.046E-05 | global batch size: 512 | lm loss: 1.875447E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.525 | TFLOPs: 23.53 | +63: iteration 71460/ 73814 | consumed samples: 36587520 | consumed tokens: 74931240960 | elapsed time per iteration (s): 2.33 | learning rate: 2.046E-05 | global batch size: 512 | lm loss: 1.871832E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.320 | TFLOPs: 22.58 | +63: iteration 71470/ 73814 | consumed samples: 36592640 | consumed tokens: 74941726720 | elapsed time per iteration (s): 2.24 | learning rate: 2.046E-05 | global batch size: 512 | lm loss: 1.893060E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.037 | TFLOPs: 23.58 | +63: iteration 71480/ 73814 | consumed samples: 36597760 | consumed tokens: 74952212480 | elapsed time per iteration (s): 2.22 | learning rate: 2.045E-05 | global batch size: 512 | lm loss: 1.885837E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.246 | TFLOPs: 23.70 | +63: iteration 71490/ 73814 | consumed samples: 36602880 | consumed tokens: 74962698240 | elapsed time per iteration (s): 2.28 | learning rate: 2.045E-05 | global batch size: 512 | lm loss: 1.873063E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.072 | TFLOPs: 23.07 | +63: iteration 71500/ 73814 | consumed samples: 36608000 | consumed tokens: 74973184000 | elapsed time per iteration (s): 2.24 | learning rate: 2.045E-05 | global batch size: 512 | lm loss: 1.872639E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.718 | TFLOPs: 23.55 | +63: iteration 71510/ 73814 | consumed samples: 36613120 | consumed tokens: 74983669760 | elapsed time per iteration (s): 2.23 | learning rate: 2.044E-05 | global batch size: 512 | lm loss: 1.881678E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.341 | TFLOPs: 23.61 | +63: iteration 71520/ 73814 | consumed samples: 36618240 | consumed tokens: 74994155520 | elapsed time per iteration (s): 2.27 | learning rate: 2.044E-05 | global batch size: 512 | lm loss: 1.883369E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.582 | TFLOPs: 23.22 | +63: iteration 71530/ 73814 | consumed samples: 36623360 | consumed tokens: 75004641280 | elapsed time per iteration (s): 2.22 | learning rate: 2.043E-05 | global batch size: 512 | lm loss: 1.868852E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.463 | TFLOPs: 23.73 | +63: iteration 71540/ 73814 | consumed samples: 36628480 | consumed tokens: 75015127040 | elapsed time per iteration (s): 2.22 | learning rate: 2.043E-05 | global batch size: 512 | lm loss: 1.893663E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.162 | TFLOPs: 23.69 | +63: iteration 71550/ 73814 | consumed samples: 36633600 | consumed tokens: 75025612800 | elapsed time per iteration (s): 2.23 | learning rate: 2.043E-05 | global batch size: 512 | lm loss: 1.865489E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.191 | TFLOPs: 23.59 | +63: iteration 71560/ 73814 | consumed samples: 36638720 | consumed tokens: 75036098560 | elapsed time per iteration (s): 2.23 | learning rate: 2.042E-05 | global batch size: 512 | lm loss: 1.883873E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.919 | TFLOPs: 23.67 | +63: iteration 71570/ 73814 | consumed samples: 36643840 | consumed tokens: 75046584320 | elapsed time per iteration (s): 2.23 | learning rate: 2.042E-05 | global batch size: 512 | lm loss: 1.883578E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.378 | TFLOPs: 23.61 | +63: iteration 71580/ 73814 | consumed samples: 36648960 | consumed tokens: 75057070080 | elapsed time per iteration (s): 2.23 | learning rate: 2.041E-05 | global batch size: 512 | lm loss: 1.909396E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.032 | TFLOPs: 23.68 | +63: iteration 71590/ 73814 | consumed samples: 36654080 | consumed tokens: 75067555840 | elapsed time per iteration (s): 2.24 | learning rate: 2.041E-05 | global batch size: 512 | lm loss: 1.874506E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.173 | TFLOPs: 23.49 | +63: iteration 71600/ 73814 | consumed samples: 36659200 | consumed tokens: 75078041600 | elapsed time per iteration (s): 2.23 | learning rate: 2.041E-05 | global batch size: 512 | lm loss: 1.906742E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.051 | TFLOPs: 23.68 | +63: iteration 71610/ 73814 | consumed samples: 36664320 | consumed tokens: 75088527360 | elapsed time per iteration (s): 2.22 | learning rate: 2.040E-05 | global batch size: 512 | lm loss: 1.854054E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.122 | TFLOPs: 23.69 | +63: iteration 71620/ 73814 | consumed samples: 36669440 | consumed tokens: 75099013120 | elapsed time per iteration (s): 2.23 | learning rate: 2.040E-05 | global batch size: 512 | lm loss: 1.876072E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.051 | TFLOPs: 23.68 | +63: iteration 71630/ 73814 | consumed samples: 36674560 | consumed tokens: 75109498880 | elapsed time per iteration (s): 2.23 | learning rate: 2.040E-05 | global batch size: 512 | lm loss: 1.898136E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.867 | TFLOPs: 23.66 | +63: iteration 71640/ 73814 | consumed samples: 36679680 | consumed tokens: 75119984640 | elapsed time per iteration (s): 2.26 | learning rate: 2.039E-05 | global batch size: 512 | lm loss: 1.867551E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.852 | TFLOPs: 23.35 | +63: iteration 71650/ 73814 | consumed samples: 36684800 | consumed tokens: 75130470400 | elapsed time per iteration (s): 2.25 | learning rate: 2.039E-05 | global batch size: 512 | lm loss: 1.885839E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.474 | TFLOPs: 23.42 | +63: iteration 71660/ 73814 | consumed samples: 36689920 | consumed tokens: 75140956160 | elapsed time per iteration (s): 2.23 | learning rate: 2.039E-05 | global batch size: 512 | lm loss: 1.896168E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.585 | TFLOPs: 23.63 | +63: iteration 71670/ 73814 | consumed samples: 36695040 | consumed tokens: 75151441920 | elapsed time per iteration (s): 2.24 | learning rate: 2.038E-05 | global batch size: 512 | lm loss: 1.883473E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.542 | TFLOPs: 23.53 | +63: iteration 71680/ 73814 | consumed samples: 36700160 | consumed tokens: 75161927680 | elapsed time per iteration (s): 2.23 | learning rate: 2.038E-05 | global batch size: 512 | lm loss: 1.904912E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.007 | TFLOPs: 23.68 | +63: iteration 71690/ 73814 | consumed samples: 36705280 | consumed tokens: 75172413440 | elapsed time per iteration (s): 2.23 | learning rate: 2.038E-05 | global batch size: 512 | lm loss: 1.904903E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.578 | TFLOPs: 23.63 | +63: iteration 71700/ 73814 | consumed samples: 36710400 | consumed tokens: 75182899200 | elapsed time per iteration (s): 2.66 | learning rate: 2.037E-05 | global batch size: 512 | lm loss: 1.903383E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 192.472 | TFLOPs: 19.81 | +63: iteration 71710/ 73814 | consumed samples: 36715520 | consumed tokens: 75193384960 | elapsed time per iteration (s): 2.43 | learning rate: 2.037E-05 | global batch size: 512 | lm loss: 1.899660E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.017 | TFLOPs: 21.72 | +63: iteration 71720/ 73814 | consumed samples: 36720640 | consumed tokens: 75203870720 | elapsed time per iteration (s): 2.25 | learning rate: 2.036E-05 | global batch size: 512 | lm loss: 1.875929E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.576 | TFLOPs: 23.43 | +63: iteration 71730/ 73814 | consumed samples: 36725760 | consumed tokens: 75214356480 | elapsed time per iteration (s): 2.31 | learning rate: 2.036E-05 | global batch size: 512 | lm loss: 1.881997E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.177 | TFLOPs: 22.77 | +63: iteration 71740/ 73814 | consumed samples: 36730880 | consumed tokens: 75224842240 | elapsed time per iteration (s): 2.22 | learning rate: 2.036E-05 | global batch size: 512 | lm loss: 1.891349E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.117 | TFLOPs: 23.69 | +63: iteration 71750/ 73814 | consumed samples: 36736000 | consumed tokens: 75235328000 | elapsed time per iteration (s): 2.23 | learning rate: 2.035E-05 | global batch size: 512 | lm loss: 1.887683E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.020 | TFLOPs: 23.68 | +63: iteration 71760/ 73814 | consumed samples: 36741120 | consumed tokens: 75245813760 | elapsed time per iteration (s): 2.36 | learning rate: 2.035E-05 | global batch size: 512 | lm loss: 1.877122E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.403 | TFLOPs: 22.38 | +63: iteration 71770/ 73814 | consumed samples: 36746240 | consumed tokens: 75256299520 | elapsed time per iteration (s): 2.26 | learning rate: 2.035E-05 | global batch size: 512 | lm loss: 1.896453E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.300 | TFLOPs: 23.30 | +63: iteration 71780/ 73814 | consumed samples: 36751360 | consumed tokens: 75266785280 | elapsed time per iteration (s): 2.26 | learning rate: 2.034E-05 | global batch size: 512 | lm loss: 1.890184E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.287 | TFLOPs: 23.30 | +63: iteration 71790/ 73814 | consumed samples: 36756480 | consumed tokens: 75277271040 | elapsed time per iteration (s): 2.22 | learning rate: 2.034E-05 | global batch size: 512 | lm loss: 1.892909E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.190 | TFLOPs: 23.70 | +63: iteration 71800/ 73814 | consumed samples: 36761600 | consumed tokens: 75287756800 | elapsed time per iteration (s): 2.23 | learning rate: 2.034E-05 | global batch size: 512 | lm loss: 1.880167E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.812 | TFLOPs: 23.66 | +63: iteration 71810/ 73814 | consumed samples: 36766720 | consumed tokens: 75298242560 | elapsed time per iteration (s): 2.23 | learning rate: 2.033E-05 | global batch size: 512 | lm loss: 1.868256E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.701 | TFLOPs: 23.65 | +63: iteration 71820/ 73814 | consumed samples: 36771840 | consumed tokens: 75308728320 | elapsed time per iteration (s): 2.35 | learning rate: 2.033E-05 | global batch size: 512 | lm loss: 1.865567E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.454 | TFLOPs: 22.39 | +63: iteration 71830/ 73814 | consumed samples: 36776960 | consumed tokens: 75319214080 | elapsed time per iteration (s): 2.36 | learning rate: 2.033E-05 | global batch size: 512 | lm loss: 1.873262E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.902 | TFLOPs: 22.33 | +63: iteration 71840/ 73814 | consumed samples: 36782080 | consumed tokens: 75329699840 | elapsed time per iteration (s): 2.38 | learning rate: 2.032E-05 | global batch size: 512 | lm loss: 1.900574E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.090 | TFLOPs: 22.14 | +63: iteration 71850/ 73814 | consumed samples: 36787200 | consumed tokens: 75340185600 | elapsed time per iteration (s): 2.24 | learning rate: 2.032E-05 | global batch size: 512 | lm loss: 1.887916E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.786 | TFLOPs: 23.55 | +63: iteration 71860/ 73814 | consumed samples: 36792320 | consumed tokens: 75350671360 | elapsed time per iteration (s): 2.24 | learning rate: 2.032E-05 | global batch size: 512 | lm loss: 1.884984E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.018 | TFLOPs: 23.58 | +63: iteration 71870/ 73814 | consumed samples: 36797440 | consumed tokens: 75361157120 | elapsed time per iteration (s): 2.38 | learning rate: 2.031E-05 | global batch size: 512 | lm loss: 1.868758E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.916 | TFLOPs: 22.12 | +63: iteration 71880/ 73814 | consumed samples: 36802560 | consumed tokens: 75371642880 | elapsed time per iteration (s): 2.23 | learning rate: 2.031E-05 | global batch size: 512 | lm loss: 1.893854E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.867 | TFLOPs: 23.66 | +63: iteration 71890/ 73814 | consumed samples: 36807680 | consumed tokens: 75382128640 | elapsed time per iteration (s): 2.38 | learning rate: 2.031E-05 | global batch size: 512 | lm loss: 1.865828E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.943 | TFLOPs: 22.13 | +63: iteration 71900/ 73814 | consumed samples: 36812800 | consumed tokens: 75392614400 | elapsed time per iteration (s): 2.23 | learning rate: 2.030E-05 | global batch size: 512 | lm loss: 1.907099E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.829 | TFLOPs: 23.66 | +63: iteration 71910/ 73814 | consumed samples: 36817920 | consumed tokens: 75403100160 | elapsed time per iteration (s): 2.23 | learning rate: 2.030E-05 | global batch size: 512 | lm loss: 1.906366E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.571 | TFLOPs: 23.63 | +63: iteration 71920/ 73814 | consumed samples: 36823040 | consumed tokens: 75413585920 | elapsed time per iteration (s): 2.24 | learning rate: 2.030E-05 | global batch size: 512 | lm loss: 1.872996E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.802 | TFLOPs: 23.55 | +63: iteration 71930/ 73814 | consumed samples: 36828160 | consumed tokens: 75424071680 | elapsed time per iteration (s): 2.23 | learning rate: 2.030E-05 | global batch size: 512 | lm loss: 1.870922E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.782 | TFLOPs: 23.65 | +63: iteration 71940/ 73814 | consumed samples: 36833280 | consumed tokens: 75434557440 | elapsed time per iteration (s): 2.23 | learning rate: 2.029E-05 | global batch size: 512 | lm loss: 1.887138E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.546 | TFLOPs: 23.63 | +63: iteration 71950/ 73814 | consumed samples: 36838400 | consumed tokens: 75445043200 | elapsed time per iteration (s): 2.24 | learning rate: 2.029E-05 | global batch size: 512 | lm loss: 1.900105E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.306 | TFLOPs: 23.50 | +63: iteration 71960/ 73814 | consumed samples: 36843520 | consumed tokens: 75455528960 | elapsed time per iteration (s): 2.23 | learning rate: 2.029E-05 | global batch size: 512 | lm loss: 1.875111E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.856 | TFLOPs: 23.66 | +63: iteration 71970/ 73814 | consumed samples: 36848640 | consumed tokens: 75466014720 | elapsed time per iteration (s): 2.26 | learning rate: 2.028E-05 | global batch size: 512 | lm loss: 1.878106E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.682 | TFLOPs: 23.34 | +63: iteration 71980/ 73814 | consumed samples: 36853760 | consumed tokens: 75476500480 | elapsed time per iteration (s): 2.23 | learning rate: 2.028E-05 | global batch size: 512 | lm loss: 1.871520E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.518 | TFLOPs: 23.63 | +63: iteration 71990/ 73814 | consumed samples: 36858880 | consumed tokens: 75486986240 | elapsed time per iteration (s): 2.23 | learning rate: 2.028E-05 | global batch size: 512 | lm loss: 1.879107E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.591 | TFLOPs: 23.64 | + 0: [2022-12-03 09:36:59,357] [INFO] [logging.py:68:log_dist] [Rank 0] step=72000, skipped=0, lr=[2.027365418180334e-05, 2.027365418180334e-05, 2.027365418180334e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +63: iteration 72000/ 73814 | consumed samples: 36864000 | consumed tokens: 75497472000 | elapsed time per iteration (s): 2.25 | learning rate: 2.027E-05 | global batch size: 512 | lm loss: 1.879913E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.435 | TFLOPs: 23.41 | + 0: steps: 72000 loss: 1.9118 iter time (s): 2.281 samples/sec: 224.437 +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 72000 | lm loss value: 1.830850E+00 | lm loss PPL: 6.239185E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 72010/ 73814 | consumed samples: 36869120 | consumed tokens: 75507957760 | elapsed time per iteration (s): 2.29 | learning rate: 2.027E-05 | global batch size: 512 | lm loss: 1.902262E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.406 | TFLOPs: 23.00 | +63: iteration 72020/ 73814 | consumed samples: 36874240 | consumed tokens: 75518443520 | elapsed time per iteration (s): 2.23 | learning rate: 2.027E-05 | global batch size: 512 | lm loss: 1.871913E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.134 | TFLOPs: 23.59 | +63: iteration 72030/ 73814 | consumed samples: 36879360 | consumed tokens: 75528929280 | elapsed time per iteration (s): 2.23 | learning rate: 2.026E-05 | global batch size: 512 | lm loss: 1.890938E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.372 | TFLOPs: 23.61 | +63: iteration 72040/ 73814 | consumed samples: 36884480 | consumed tokens: 75539415040 | elapsed time per iteration (s): 2.23 | learning rate: 2.026E-05 | global batch size: 512 | lm loss: 1.881656E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.274 | TFLOPs: 23.60 | +63: iteration 72050/ 73814 | consumed samples: 36889600 | consumed tokens: 75549900800 | elapsed time per iteration (s): 2.23 | learning rate: 2.026E-05 | global batch size: 512 | lm loss: 1.873133E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.932 | TFLOPs: 23.67 | +63: iteration 72060/ 73814 | consumed samples: 36894720 | consumed tokens: 75560386560 | elapsed time per iteration (s): 2.22 | learning rate: 2.026E-05 | global batch size: 512 | lm loss: 1.907172E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.238 | TFLOPs: 23.70 | +63: iteration 72070/ 73814 | consumed samples: 36899840 | consumed tokens: 75570872320 | elapsed time per iteration (s): 2.23 | learning rate: 2.025E-05 | global batch size: 512 | lm loss: 1.874334E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.553 | TFLOPs: 23.63 | +63: iteration 72080/ 73814 | consumed samples: 36904960 | consumed tokens: 75581358080 | elapsed time per iteration (s): 2.24 | learning rate: 2.025E-05 | global batch size: 512 | lm loss: 1.883950E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.876 | TFLOPs: 23.56 | +63: iteration 72090/ 73814 | consumed samples: 36910080 | consumed tokens: 75591843840 | elapsed time per iteration (s): 2.23 | learning rate: 2.025E-05 | global batch size: 512 | lm loss: 1.865249E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.090 | TFLOPs: 23.69 | +63: iteration 72100/ 73814 | consumed samples: 36915200 | consumed tokens: 75602329600 | elapsed time per iteration (s): 2.23 | learning rate: 2.024E-05 | global batch size: 512 | lm loss: 1.864443E+00 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.473 | TFLOPs: 23.62 | +63: iteration 72110/ 73814 | consumed samples: 36920320 | consumed tokens: 75612815360 | elapsed time per iteration (s): 2.23 | learning rate: 2.024E-05 | global batch size: 512 | lm loss: 1.890059E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.919 | TFLOPs: 23.67 | +63: iteration 72120/ 73814 | consumed samples: 36925440 | consumed tokens: 75623301120 | elapsed time per iteration (s): 2.36 | learning rate: 2.024E-05 | global batch size: 512 | lm loss: 1.881198E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.883 | TFLOPs: 22.33 | +63: iteration 72130/ 73814 | consumed samples: 36930560 | consumed tokens: 75633786880 | elapsed time per iteration (s): 2.24 | learning rate: 2.024E-05 | global batch size: 512 | lm loss: 1.892664E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.068 | TFLOPs: 23.48 | +63: iteration 72140/ 73814 | consumed samples: 36935680 | consumed tokens: 75644272640 | elapsed time per iteration (s): 2.22 | learning rate: 2.023E-05 | global batch size: 512 | lm loss: 1.880104E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.247 | TFLOPs: 23.70 | +63: iteration 72150/ 73814 | consumed samples: 36940800 | consumed tokens: 75654758400 | elapsed time per iteration (s): 2.23 | learning rate: 2.023E-05 | global batch size: 512 | lm loss: 1.889986E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.712 | TFLOPs: 23.65 | +63: iteration 72160/ 73814 | consumed samples: 36945920 | consumed tokens: 75665244160 | elapsed time per iteration (s): 2.24 | learning rate: 2.023E-05 | global batch size: 512 | lm loss: 1.875009E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.493 | TFLOPs: 23.52 | +63: iteration 72170/ 73814 | consumed samples: 36951040 | consumed tokens: 75675729920 | elapsed time per iteration (s): 2.43 | learning rate: 2.022E-05 | global batch size: 512 | lm loss: 1.893010E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.344 | TFLOPs: 21.65 | +63: iteration 72180/ 73814 | consumed samples: 36956160 | consumed tokens: 75686215680 | elapsed time per iteration (s): 2.39 | learning rate: 2.022E-05 | global batch size: 512 | lm loss: 1.885329E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.013 | TFLOPs: 22.03 | +63: iteration 72190/ 73814 | consumed samples: 36961280 | consumed tokens: 75696701440 | elapsed time per iteration (s): 2.25 | learning rate: 2.022E-05 | global batch size: 512 | lm loss: 1.882560E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.400 | TFLOPs: 23.41 | +63: iteration 72200/ 73814 | consumed samples: 36966400 | consumed tokens: 75707187200 | elapsed time per iteration (s): 2.23 | learning rate: 2.022E-05 | global batch size: 512 | lm loss: 1.889280E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.005 | TFLOPs: 23.68 | +63: iteration 72210/ 73814 | consumed samples: 36971520 | consumed tokens: 75717672960 | elapsed time per iteration (s): 2.24 | learning rate: 2.021E-05 | global batch size: 512 | lm loss: 1.864216E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.484 | TFLOPs: 23.52 | +63: iteration 72220/ 73814 | consumed samples: 36976640 | consumed tokens: 75728158720 | elapsed time per iteration (s): 2.44 | learning rate: 2.021E-05 | global batch size: 512 | lm loss: 1.880976E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.177 | TFLOPs: 21.64 | +63: iteration 72230/ 73814 | consumed samples: 36981760 | consumed tokens: 75738644480 | elapsed time per iteration (s): 2.25 | learning rate: 2.021E-05 | global batch size: 512 | lm loss: 1.895400E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.551 | TFLOPs: 23.43 | +63: iteration 72240/ 73814 | consumed samples: 36986880 | consumed tokens: 75749130240 | elapsed time per iteration (s): 2.41 | learning rate: 2.021E-05 | global batch size: 512 | lm loss: 1.886150E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.500 | TFLOPs: 21.88 | +63: iteration 72250/ 73814 | consumed samples: 36992000 | consumed tokens: 75759616000 | elapsed time per iteration (s): 2.25 | learning rate: 2.020E-05 | global batch size: 512 | lm loss: 1.898933E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.549 | TFLOPs: 23.43 | +63: iteration 72260/ 73814 | consumed samples: 36997120 | consumed tokens: 75770101760 | elapsed time per iteration (s): 2.24 | learning rate: 2.020E-05 | global batch size: 512 | lm loss: 1.877660E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.798 | TFLOPs: 23.55 | +63: iteration 72270/ 73814 | consumed samples: 37002240 | consumed tokens: 75780587520 | elapsed time per iteration (s): 2.22 | learning rate: 2.020E-05 | global batch size: 512 | lm loss: 1.862532E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.153 | TFLOPs: 23.69 | +63: iteration 72280/ 73814 | consumed samples: 37007360 | consumed tokens: 75791073280 | elapsed time per iteration (s): 2.23 | learning rate: 2.020E-05 | global batch size: 512 | lm loss: 1.881516E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.974 | TFLOPs: 23.67 | +63: iteration 72290/ 73814 | consumed samples: 37012480 | consumed tokens: 75801559040 | elapsed time per iteration (s): 2.25 | learning rate: 2.019E-05 | global batch size: 512 | lm loss: 1.881927E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.973 | TFLOPs: 23.47 | +63: iteration 72300/ 73814 | consumed samples: 37017600 | consumed tokens: 75812044800 | elapsed time per iteration (s): 2.24 | learning rate: 2.019E-05 | global batch size: 512 | lm loss: 1.887444E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.563 | TFLOPs: 23.53 | +63: iteration 72310/ 73814 | consumed samples: 37022720 | consumed tokens: 75822530560 | elapsed time per iteration (s): 2.25 | learning rate: 2.019E-05 | global batch size: 512 | lm loss: 1.874345E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.952 | TFLOPs: 23.47 | +63: iteration 72320/ 73814 | consumed samples: 37027840 | consumed tokens: 75833016320 | elapsed time per iteration (s): 2.23 | learning rate: 2.019E-05 | global batch size: 512 | lm loss: 1.867896E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.812 | TFLOPs: 23.66 | +63: iteration 72330/ 73814 | consumed samples: 37032960 | consumed tokens: 75843502080 | elapsed time per iteration (s): 2.24 | learning rate: 2.018E-05 | global batch size: 512 | lm loss: 1.899481E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.912 | TFLOPs: 23.57 | +63: iteration 72340/ 73814 | consumed samples: 37038080 | consumed tokens: 75853987840 | elapsed time per iteration (s): 2.25 | learning rate: 2.018E-05 | global batch size: 512 | lm loss: 1.902033E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.747 | TFLOPs: 23.45 | +63: iteration 72350/ 73814 | consumed samples: 37043200 | consumed tokens: 75864473600 | elapsed time per iteration (s): 2.24 | learning rate: 2.018E-05 | global batch size: 512 | lm loss: 1.889672E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.721 | TFLOPs: 23.55 | +63: iteration 72360/ 73814 | consumed samples: 37048320 | consumed tokens: 75874959360 | elapsed time per iteration (s): 2.24 | learning rate: 2.018E-05 | global batch size: 512 | lm loss: 1.858687E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.148 | TFLOPs: 23.49 | +63: iteration 72370/ 73814 | consumed samples: 37053440 | consumed tokens: 75885445120 | elapsed time per iteration (s): 2.24 | learning rate: 2.017E-05 | global batch size: 512 | lm loss: 1.878136E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.294 | TFLOPs: 23.50 | +63: iteration 72380/ 73814 | consumed samples: 37058560 | consumed tokens: 75895930880 | elapsed time per iteration (s): 2.22 | learning rate: 2.017E-05 | global batch size: 512 | lm loss: 1.865599E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.280 | TFLOPs: 23.71 | +63: iteration 72390/ 73814 | consumed samples: 37063680 | consumed tokens: 75906416640 | elapsed time per iteration (s): 2.24 | learning rate: 2.017E-05 | global batch size: 512 | lm loss: 1.881506E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.138 | TFLOPs: 23.49 | +63: iteration 72400/ 73814 | consumed samples: 37068800 | consumed tokens: 75916902400 | elapsed time per iteration (s): 2.23 | learning rate: 2.017E-05 | global batch size: 512 | lm loss: 1.869892E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.009 | TFLOPs: 23.68 | +63: iteration 72410/ 73814 | consumed samples: 37073920 | consumed tokens: 75927388160 | elapsed time per iteration (s): 2.26 | learning rate: 2.016E-05 | global batch size: 512 | lm loss: 1.870018E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.974 | TFLOPs: 23.37 | +63: iteration 72420/ 73814 | consumed samples: 37079040 | consumed tokens: 75937873920 | elapsed time per iteration (s): 2.53 | learning rate: 2.016E-05 | global batch size: 512 | lm loss: 1.868497E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.029 | TFLOPs: 20.80 | +63: iteration 72430/ 73814 | consumed samples: 37084160 | consumed tokens: 75948359680 | elapsed time per iteration (s): 2.24 | learning rate: 2.016E-05 | global batch size: 512 | lm loss: 1.901020E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.549 | TFLOPs: 23.53 | +63: iteration 72440/ 73814 | consumed samples: 37089280 | consumed tokens: 75958845440 | elapsed time per iteration (s): 2.24 | learning rate: 2.016E-05 | global batch size: 512 | lm loss: 1.885030E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.135 | TFLOPs: 23.49 | +63: iteration 72450/ 73814 | consumed samples: 37094400 | consumed tokens: 75969331200 | elapsed time per iteration (s): 2.24 | learning rate: 2.015E-05 | global batch size: 512 | lm loss: 1.861790E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.154 | TFLOPs: 23.49 | +63: iteration 72460/ 73814 | consumed samples: 37099520 | consumed tokens: 75979816960 | elapsed time per iteration (s): 2.39 | learning rate: 2.015E-05 | global batch size: 512 | lm loss: 1.870899E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.436 | TFLOPs: 22.08 | +63: iteration 72470/ 73814 | consumed samples: 37104640 | consumed tokens: 75990302720 | elapsed time per iteration (s): 2.38 | learning rate: 2.015E-05 | global batch size: 512 | lm loss: 1.879116E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.859 | TFLOPs: 22.12 | +63: iteration 72480/ 73814 | consumed samples: 37109760 | consumed tokens: 76000788480 | elapsed time per iteration (s): 2.23 | learning rate: 2.015E-05 | global batch size: 512 | lm loss: 1.872954E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.588 | TFLOPs: 23.63 | +63: iteration 72490/ 73814 | consumed samples: 37114880 | consumed tokens: 76011274240 | elapsed time per iteration (s): 2.24 | learning rate: 2.015E-05 | global batch size: 512 | lm loss: 1.893810E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.778 | TFLOPs: 23.55 | +63: iteration 72500/ 73814 | consumed samples: 37120000 | consumed tokens: 76021760000 | elapsed time per iteration (s): 2.28 | learning rate: 2.014E-05 | global batch size: 512 | lm loss: 1.898709E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.052 | TFLOPs: 23.17 | +63: iteration 72510/ 73814 | consumed samples: 37125120 | consumed tokens: 76032245760 | elapsed time per iteration (s): 2.22 | learning rate: 2.014E-05 | global batch size: 512 | lm loss: 1.864264E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.114 | TFLOPs: 23.69 | +63: iteration 72520/ 73814 | consumed samples: 37130240 | consumed tokens: 76042731520 | elapsed time per iteration (s): 2.24 | learning rate: 2.014E-05 | global batch size: 512 | lm loss: 1.878628E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.743 | TFLOPs: 23.55 | +63: iteration 72530/ 73814 | consumed samples: 37135360 | consumed tokens: 76053217280 | elapsed time per iteration (s): 2.23 | learning rate: 2.014E-05 | global batch size: 512 | lm loss: 1.871830E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.681 | TFLOPs: 23.64 | +63: iteration 72540/ 73814 | consumed samples: 37140480 | consumed tokens: 76063703040 | elapsed time per iteration (s): 2.37 | learning rate: 2.014E-05 | global batch size: 512 | lm loss: 1.886028E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.654 | TFLOPs: 22.20 | +63: iteration 72550/ 73814 | consumed samples: 37145600 | consumed tokens: 76074188800 | elapsed time per iteration (s): 2.42 | learning rate: 2.013E-05 | global batch size: 512 | lm loss: 1.880725E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.408 | TFLOPs: 21.76 | +63: iteration 72560/ 73814 | consumed samples: 37150720 | consumed tokens: 76084674560 | elapsed time per iteration (s): 2.23 | learning rate: 2.013E-05 | global batch size: 512 | lm loss: 1.867588E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.475 | TFLOPs: 23.62 | +63: iteration 72570/ 73814 | consumed samples: 37155840 | consumed tokens: 76095160320 | elapsed time per iteration (s): 2.25 | learning rate: 2.013E-05 | global batch size: 512 | lm loss: 1.868257E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.456 | TFLOPs: 23.42 | +63: iteration 72580/ 73814 | consumed samples: 37160960 | consumed tokens: 76105646080 | elapsed time per iteration (s): 2.23 | learning rate: 2.013E-05 | global batch size: 512 | lm loss: 1.887837E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.750 | TFLOPs: 23.65 | +63: iteration 72590/ 73814 | consumed samples: 37166080 | consumed tokens: 76116131840 | elapsed time per iteration (s): 2.22 | learning rate: 2.012E-05 | global batch size: 512 | lm loss: 1.882961E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.187 | TFLOPs: 23.70 | +63: iteration 72600/ 73814 | consumed samples: 37171200 | consumed tokens: 76126617600 | elapsed time per iteration (s): 2.23 | learning rate: 2.012E-05 | global batch size: 512 | lm loss: 1.871236E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.629 | TFLOPs: 23.64 | +63: iteration 72610/ 73814 | consumed samples: 37176320 | consumed tokens: 76137103360 | elapsed time per iteration (s): 2.25 | learning rate: 2.012E-05 | global batch size: 512 | lm loss: 1.866315E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.079 | TFLOPs: 23.38 | +63: iteration 72620/ 73814 | consumed samples: 37181440 | consumed tokens: 76147589120 | elapsed time per iteration (s): 2.38 | learning rate: 2.012E-05 | global batch size: 512 | lm loss: 1.896651E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.189 | TFLOPs: 22.15 | +63: iteration 72630/ 73814 | consumed samples: 37186560 | consumed tokens: 76158074880 | elapsed time per iteration (s): 2.27 | learning rate: 2.012E-05 | global batch size: 512 | lm loss: 1.865177E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.162 | TFLOPs: 23.18 | +63: iteration 72640/ 73814 | consumed samples: 37191680 | consumed tokens: 76168560640 | elapsed time per iteration (s): 2.23 | learning rate: 2.011E-05 | global batch size: 512 | lm loss: 1.891219E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.358 | TFLOPs: 23.61 | +63: iteration 72650/ 73814 | consumed samples: 37196800 | consumed tokens: 76179046400 | elapsed time per iteration (s): 2.23 | learning rate: 2.011E-05 | global batch size: 512 | lm loss: 1.878682E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.727 | TFLOPs: 23.65 | +63: iteration 72660/ 73814 | consumed samples: 37201920 | consumed tokens: 76189532160 | elapsed time per iteration (s): 2.23 | learning rate: 2.011E-05 | global batch size: 512 | lm loss: 1.872725E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.887 | TFLOPs: 23.67 | +63: iteration 72670/ 73814 | consumed samples: 37207040 | consumed tokens: 76200017920 | elapsed time per iteration (s): 2.24 | learning rate: 2.011E-05 | global batch size: 512 | lm loss: 1.888036E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.678 | TFLOPs: 23.54 | +63: iteration 72680/ 73814 | consumed samples: 37212160 | consumed tokens: 76210503680 | elapsed time per iteration (s): 2.22 | learning rate: 2.011E-05 | global batch size: 512 | lm loss: 1.883760E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.130 | TFLOPs: 23.69 | +63: iteration 72690/ 73814 | consumed samples: 37217280 | consumed tokens: 76220989440 | elapsed time per iteration (s): 2.24 | learning rate: 2.011E-05 | global batch size: 512 | lm loss: 1.882250E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.084 | TFLOPs: 23.48 | +63: iteration 72700/ 73814 | consumed samples: 37222400 | consumed tokens: 76231475200 | elapsed time per iteration (s): 2.40 | learning rate: 2.010E-05 | global batch size: 512 | lm loss: 1.871260E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.709 | TFLOPs: 22.00 | +63: iteration 72710/ 73814 | consumed samples: 37227520 | consumed tokens: 76241960960 | elapsed time per iteration (s): 2.23 | learning rate: 2.010E-05 | global batch size: 512 | lm loss: 1.866807E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.026 | TFLOPs: 23.68 | +63: iteration 72720/ 73814 | consumed samples: 37232640 | consumed tokens: 76252446720 | elapsed time per iteration (s): 2.23 | learning rate: 2.010E-05 | global batch size: 512 | lm loss: 1.895394E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.536 | TFLOPs: 23.63 | +63: iteration 72730/ 73814 | consumed samples: 37237760 | consumed tokens: 76262932480 | elapsed time per iteration (s): 2.24 | learning rate: 2.010E-05 | global batch size: 512 | lm loss: 1.881466E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.476 | TFLOPs: 23.52 | +63: iteration 72740/ 73814 | consumed samples: 37242880 | consumed tokens: 76273418240 | elapsed time per iteration (s): 2.23 | learning rate: 2.010E-05 | global batch size: 512 | lm loss: 1.864545E+00 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.106 | TFLOPs: 23.59 | +63: iteration 72750/ 73814 | consumed samples: 37248000 | consumed tokens: 76283904000 | elapsed time per iteration (s): 2.23 | learning rate: 2.009E-05 | global batch size: 512 | lm loss: 1.901733E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.053 | TFLOPs: 23.68 | +63: iteration 72760/ 73814 | consumed samples: 37253120 | consumed tokens: 76294389760 | elapsed time per iteration (s): 2.37 | learning rate: 2.009E-05 | global batch size: 512 | lm loss: 1.869249E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.729 | TFLOPs: 22.21 | +63: iteration 72770/ 73814 | consumed samples: 37258240 | consumed tokens: 76304875520 | elapsed time per iteration (s): 2.28 | learning rate: 2.009E-05 | global batch size: 512 | lm loss: 1.882121E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.331 | TFLOPs: 23.09 | +63: iteration 72780/ 73814 | consumed samples: 37263360 | consumed tokens: 76315361280 | elapsed time per iteration (s): 2.23 | learning rate: 2.009E-05 | global batch size: 512 | lm loss: 1.892370E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.598 | TFLOPs: 23.64 | +63: iteration 72790/ 73814 | consumed samples: 37268480 | consumed tokens: 76325847040 | elapsed time per iteration (s): 2.23 | learning rate: 2.009E-05 | global batch size: 512 | lm loss: 1.890268E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.852 | TFLOPs: 23.66 | +63: iteration 72800/ 73814 | consumed samples: 37273600 | consumed tokens: 76336332800 | elapsed time per iteration (s): 2.50 | learning rate: 2.009E-05 | global batch size: 512 | lm loss: 1.894895E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 204.838 | TFLOPs: 21.09 | +63: iteration 72810/ 73814 | consumed samples: 37278720 | consumed tokens: 76346818560 | elapsed time per iteration (s): 2.24 | learning rate: 2.008E-05 | global batch size: 512 | lm loss: 1.868402E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.547 | TFLOPs: 23.53 | +63: iteration 72820/ 73814 | consumed samples: 37283840 | consumed tokens: 76357304320 | elapsed time per iteration (s): 2.23 | learning rate: 2.008E-05 | global batch size: 512 | lm loss: 1.895582E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.324 | TFLOPs: 23.61 | +63: iteration 72830/ 73814 | consumed samples: 37288960 | consumed tokens: 76367790080 | elapsed time per iteration (s): 2.23 | learning rate: 2.008E-05 | global batch size: 512 | lm loss: 1.880425E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.973 | TFLOPs: 23.67 | +63: iteration 72840/ 73814 | consumed samples: 37294080 | consumed tokens: 76378275840 | elapsed time per iteration (s): 2.36 | learning rate: 2.008E-05 | global batch size: 512 | lm loss: 1.884316E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.825 | TFLOPs: 22.32 | +63: iteration 72850/ 73814 | consumed samples: 37299200 | consumed tokens: 76388761600 | elapsed time per iteration (s): 2.23 | learning rate: 2.008E-05 | global batch size: 512 | lm loss: 1.864544E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.720 | TFLOPs: 23.65 | +63: iteration 72860/ 73814 | consumed samples: 37304320 | consumed tokens: 76399247360 | elapsed time per iteration (s): 2.23 | learning rate: 2.008E-05 | global batch size: 512 | lm loss: 1.897647E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.644 | TFLOPs: 23.64 | +63: iteration 72870/ 73814 | consumed samples: 37309440 | consumed tokens: 76409733120 | elapsed time per iteration (s): 2.23 | learning rate: 2.007E-05 | global batch size: 512 | lm loss: 1.888621E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.255 | TFLOPs: 23.60 | +63: iteration 72880/ 73814 | consumed samples: 37314560 | consumed tokens: 76420218880 | elapsed time per iteration (s): 2.25 | learning rate: 2.007E-05 | global batch size: 512 | lm loss: 1.864468E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.358 | TFLOPs: 23.41 | +63: iteration 72890/ 73814 | consumed samples: 37319680 | consumed tokens: 76430704640 | elapsed time per iteration (s): 2.24 | learning rate: 2.007E-05 | global batch size: 512 | lm loss: 1.890326E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.918 | TFLOPs: 23.57 | +63: iteration 72900/ 73814 | consumed samples: 37324800 | consumed tokens: 76441190400 | elapsed time per iteration (s): 2.24 | learning rate: 2.007E-05 | global batch size: 512 | lm loss: 1.897334E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.662 | TFLOPs: 23.54 | +63: iteration 72910/ 73814 | consumed samples: 37329920 | consumed tokens: 76451676160 | elapsed time per iteration (s): 2.31 | learning rate: 2.007E-05 | global batch size: 512 | lm loss: 1.869129E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.557 | TFLOPs: 22.81 | +63: iteration 72920/ 73814 | consumed samples: 37335040 | consumed tokens: 76462161920 | elapsed time per iteration (s): 2.23 | learning rate: 2.007E-05 | global batch size: 512 | lm loss: 1.876586E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.004 | TFLOPs: 23.68 | +63: iteration 72930/ 73814 | consumed samples: 37340160 | consumed tokens: 76472647680 | elapsed time per iteration (s): 2.25 | learning rate: 2.007E-05 | global batch size: 512 | lm loss: 1.882600E+00 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.545 | TFLOPs: 23.42 | +63: iteration 72940/ 73814 | consumed samples: 37345280 | consumed tokens: 76483133440 | elapsed time per iteration (s): 2.24 | learning rate: 2.006E-05 | global batch size: 512 | lm loss: 1.898980E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.165 | TFLOPs: 23.49 | +63: iteration 72950/ 73814 | consumed samples: 37350400 | consumed tokens: 76493619200 | elapsed time per iteration (s): 2.23 | learning rate: 2.006E-05 | global batch size: 512 | lm loss: 1.879497E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.666 | TFLOPs: 23.64 | +63: iteration 72960/ 73814 | consumed samples: 37355520 | consumed tokens: 76504104960 | elapsed time per iteration (s): 2.24 | learning rate: 2.006E-05 | global batch size: 512 | lm loss: 1.874363E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.620 | TFLOPs: 23.54 | +63: iteration 72970/ 73814 | consumed samples: 37360640 | consumed tokens: 76514590720 | elapsed time per iteration (s): 2.23 | learning rate: 2.006E-05 | global batch size: 512 | lm loss: 1.886542E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.001 | TFLOPs: 23.68 | +63: iteration 72980/ 73814 | consumed samples: 37365760 | consumed tokens: 76525076480 | elapsed time per iteration (s): 2.24 | learning rate: 2.006E-05 | global batch size: 512 | lm loss: 1.862887E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.392 | TFLOPs: 23.51 | +63: iteration 72990/ 73814 | consumed samples: 37370880 | consumed tokens: 76535562240 | elapsed time per iteration (s): 2.23 | learning rate: 2.006E-05 | global batch size: 512 | lm loss: 1.880769E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.951 | TFLOPs: 23.67 | +63: iteration 73000/ 73814 | consumed samples: 37376000 | consumed tokens: 76546048000 | elapsed time per iteration (s): 2.24 | learning rate: 2.006E-05 | global batch size: 512 | lm loss: 1.857703E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.595 | TFLOPs: 23.53 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 73000 | lm loss value: 1.820767E+00 | lm loss PPL: 6.176594E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 73010/ 73814 | consumed samples: 37381120 | consumed tokens: 76556533760 | elapsed time per iteration (s): 2.44 | learning rate: 2.005E-05 | global batch size: 512 | lm loss: 1.875656E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.158 | TFLOPs: 21.63 | +63: iteration 73020/ 73814 | consumed samples: 37386240 | consumed tokens: 76567019520 | elapsed time per iteration (s): 2.42 | learning rate: 2.005E-05 | global batch size: 512 | lm loss: 1.878521E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.970 | TFLOPs: 21.82 | +63: iteration 73030/ 73814 | consumed samples: 37391360 | consumed tokens: 76577505280 | elapsed time per iteration (s): 2.42 | learning rate: 2.005E-05 | global batch size: 512 | lm loss: 1.915824E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.934 | TFLOPs: 21.82 | +63: iteration 73040/ 73814 | consumed samples: 37396480 | consumed tokens: 76587991040 | elapsed time per iteration (s): 2.53 | learning rate: 2.005E-05 | global batch size: 512 | lm loss: 1.881921E+00 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.993 | TFLOPs: 20.79 | +63: iteration 73050/ 73814 | consumed samples: 37401600 | consumed tokens: 76598476800 | elapsed time per iteration (s): 2.52 | learning rate: 2.005E-05 | global batch size: 512 | lm loss: 1.875508E+00 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 202.850 | TFLOPs: 20.88 | +63: iteration 73060/ 73814 | consumed samples: 37406720 | consumed tokens: 76608962560 | elapsed time per iteration (s): 2.55 | learning rate: 2.005E-05 | global batch size: 512 | lm loss: 1.872338E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 200.403 | TFLOPs: 20.63 | +63: iteration 73070/ 73814 | consumed samples: 37411840 | consumed tokens: 76619448320 | elapsed time per iteration (s): 2.31 | learning rate: 2.005E-05 | global batch size: 512 | lm loss: 1.863263E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.061 | TFLOPs: 22.86 | +63: iteration 73080/ 73814 | consumed samples: 37416960 | consumed tokens: 76629934080 | elapsed time per iteration (s): 3.09 | learning rate: 2.004E-05 | global batch size: 512 | lm loss: 1.896743E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 165.885 | TFLOPs: 17.08 | +63: iteration 73090/ 73814 | consumed samples: 37422080 | consumed tokens: 76640419840 | elapsed time per iteration (s): 2.39 | learning rate: 2.004E-05 | global batch size: 512 | lm loss: 1.870855E+00 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.052 | TFLOPs: 22.04 | +63: iteration 73100/ 73814 | consumed samples: 37427200 | consumed tokens: 76650905600 | elapsed time per iteration (s): 2.40 | learning rate: 2.004E-05 | global batch size: 512 | lm loss: 1.872662E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.250 | TFLOPs: 21.95 | +63: iteration 73110/ 73814 | consumed samples: 37432320 | consumed tokens: 76661391360 | elapsed time per iteration (s): 2.26 | learning rate: 2.004E-05 | global batch size: 512 | lm loss: 1.867773E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.185 | TFLOPs: 23.28 | +63: iteration 73120/ 73814 | consumed samples: 37437440 | consumed tokens: 76671877120 | elapsed time per iteration (s): 2.27 | learning rate: 2.004E-05 | global batch size: 512 | lm loss: 1.874463E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.492 | TFLOPs: 23.21 | +63: iteration 73130/ 73814 | consumed samples: 37442560 | consumed tokens: 76682362880 | elapsed time per iteration (s): 2.39 | learning rate: 2.004E-05 | global batch size: 512 | lm loss: 1.891732E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 213.915 | TFLOPs: 22.02 | +63: iteration 73140/ 73814 | consumed samples: 37447680 | consumed tokens: 76692848640 | elapsed time per iteration (s): 2.23 | learning rate: 2.004E-05 | global batch size: 512 | lm loss: 1.871702E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.197 | TFLOPs: 23.59 | +63: iteration 73150/ 73814 | consumed samples: 37452800 | consumed tokens: 76703334400 | elapsed time per iteration (s): 2.24 | learning rate: 2.004E-05 | global batch size: 512 | lm loss: 1.883010E+00 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.232 | TFLOPs: 23.50 | +63: iteration 73160/ 73814 | consumed samples: 37457920 | consumed tokens: 76713820160 | elapsed time per iteration (s): 2.23 | learning rate: 2.004E-05 | global batch size: 512 | lm loss: 1.872967E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.825 | TFLOPs: 23.66 | +63: iteration 73170/ 73814 | consumed samples: 37463040 | consumed tokens: 76724305920 | elapsed time per iteration (s): 2.24 | learning rate: 2.003E-05 | global batch size: 512 | lm loss: 1.871847E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.974 | TFLOPs: 23.57 | +63: iteration 73180/ 73814 | consumed samples: 37468160 | consumed tokens: 76734791680 | elapsed time per iteration (s): 2.23 | learning rate: 2.003E-05 | global batch size: 512 | lm loss: 1.888418E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.830 | TFLOPs: 23.66 | +63: iteration 73190/ 73814 | consumed samples: 37473280 | consumed tokens: 76745277440 | elapsed time per iteration (s): 2.23 | learning rate: 2.003E-05 | global batch size: 512 | lm loss: 1.874891E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.600 | TFLOPs: 23.64 | +63: iteration 73200/ 73814 | consumed samples: 37478400 | consumed tokens: 76755763200 | elapsed time per iteration (s): 2.24 | learning rate: 2.003E-05 | global batch size: 512 | lm loss: 1.873258E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.347 | TFLOPs: 23.51 | +63: iteration 73210/ 73814 | consumed samples: 37483520 | consumed tokens: 76766248960 | elapsed time per iteration (s): 2.25 | learning rate: 2.003E-05 | global batch size: 512 | lm loss: 1.873823E+00 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.787 | TFLOPs: 23.45 | +63: iteration 73220/ 73814 | consumed samples: 37488640 | consumed tokens: 76776734720 | elapsed time per iteration (s): 2.23 | learning rate: 2.003E-05 | global batch size: 512 | lm loss: 1.887173E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.061 | TFLOPs: 23.68 | +63: iteration 73230/ 73814 | consumed samples: 37493760 | consumed tokens: 76787220480 | elapsed time per iteration (s): 2.22 | learning rate: 2.003E-05 | global batch size: 512 | lm loss: 1.868550E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.258 | TFLOPs: 23.70 | +63: iteration 73240/ 73814 | consumed samples: 37498880 | consumed tokens: 76797706240 | elapsed time per iteration (s): 2.26 | learning rate: 2.003E-05 | global batch size: 512 | lm loss: 1.873211E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.119 | TFLOPs: 23.28 | +63: iteration 73250/ 73814 | consumed samples: 37504000 | consumed tokens: 76808192000 | elapsed time per iteration (s): 2.23 | learning rate: 2.003E-05 | global batch size: 512 | lm loss: 1.906306E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.809 | TFLOPs: 23.66 | +63: iteration 73260/ 73814 | consumed samples: 37509120 | consumed tokens: 76818677760 | elapsed time per iteration (s): 2.27 | learning rate: 2.003E-05 | global batch size: 512 | lm loss: 1.873577E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.167 | TFLOPs: 23.18 | +63: iteration 73270/ 73814 | consumed samples: 37514240 | consumed tokens: 76829163520 | elapsed time per iteration (s): 2.24 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.867253E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.564 | TFLOPs: 23.53 | +63: iteration 73280/ 73814 | consumed samples: 37519360 | consumed tokens: 76839649280 | elapsed time per iteration (s): 2.24 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.871992E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.426 | TFLOPs: 23.52 | +63: iteration 73290/ 73814 | consumed samples: 37524480 | consumed tokens: 76850135040 | elapsed time per iteration (s): 2.23 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.889383E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.920 | TFLOPs: 23.67 | +63: iteration 73300/ 73814 | consumed samples: 37529600 | consumed tokens: 76860620800 | elapsed time per iteration (s): 2.25 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.859873E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.911 | TFLOPs: 23.46 | +63: iteration 73310/ 73814 | consumed samples: 37534720 | consumed tokens: 76871106560 | elapsed time per iteration (s): 2.23 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.886442E+00 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.769 | TFLOPs: 23.65 | +63: iteration 73320/ 73814 | consumed samples: 37539840 | consumed tokens: 76881592320 | elapsed time per iteration (s): 2.22 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.870482E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.187 | TFLOPs: 23.70 | +63: iteration 73330/ 73814 | consumed samples: 37544960 | consumed tokens: 76892078080 | elapsed time per iteration (s): 2.23 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.869245E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.857 | TFLOPs: 23.66 | +63: iteration 73340/ 73814 | consumed samples: 37550080 | consumed tokens: 76902563840 | elapsed time per iteration (s): 2.22 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.895779E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.206 | TFLOPs: 23.70 | +63: iteration 73350/ 73814 | consumed samples: 37555200 | consumed tokens: 76913049600 | elapsed time per iteration (s): 2.23 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.883505E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.645 | TFLOPs: 23.64 | +63: iteration 73360/ 73814 | consumed samples: 37560320 | consumed tokens: 76923535360 | elapsed time per iteration (s): 2.47 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.879420E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 207.056 | TFLOPs: 21.32 | +63: iteration 73370/ 73814 | consumed samples: 37565440 | consumed tokens: 76934021120 | elapsed time per iteration (s): 2.22 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.889694E+00 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.188 | TFLOPs: 23.70 | +63: iteration 73380/ 73814 | consumed samples: 37570560 | consumed tokens: 76944506880 | elapsed time per iteration (s): 2.23 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.883966E+00 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.794 | TFLOPs: 23.66 | +63: iteration 73390/ 73814 | consumed samples: 37575680 | consumed tokens: 76954992640 | elapsed time per iteration (s): 2.28 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.896903E+00 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.071 | TFLOPs: 23.07 | +63: iteration 73400/ 73814 | consumed samples: 37580800 | consumed tokens: 76965478400 | elapsed time per iteration (s): 2.22 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.891599E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.379 | TFLOPs: 23.72 | +63: iteration 73410/ 73814 | consumed samples: 37585920 | consumed tokens: 76975964160 | elapsed time per iteration (s): 2.27 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.854401E+00 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.758 | TFLOPs: 23.24 | +63: iteration 73420/ 73814 | consumed samples: 37591040 | consumed tokens: 76986449920 | elapsed time per iteration (s): 2.29 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.893397E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.441 | TFLOPs: 23.00 | +63: iteration 73430/ 73814 | consumed samples: 37596160 | consumed tokens: 76996935680 | elapsed time per iteration (s): 2.41 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.867019E+00 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 212.545 | TFLOPs: 21.88 | +63: iteration 73440/ 73814 | consumed samples: 37601280 | consumed tokens: 77007421440 | elapsed time per iteration (s): 2.24 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.879911E+00 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.195 | TFLOPs: 23.49 | +63: iteration 73450/ 73814 | consumed samples: 37606400 | consumed tokens: 77017907200 | elapsed time per iteration (s): 2.23 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.845935E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.953 | TFLOPs: 23.67 | +63: iteration 73460/ 73814 | consumed samples: 37611520 | consumed tokens: 77028392960 | elapsed time per iteration (s): 2.25 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.886277E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.567 | TFLOPs: 23.43 | +63: iteration 73470/ 73814 | consumed samples: 37616640 | consumed tokens: 77038878720 | elapsed time per iteration (s): 2.24 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.872311E+00 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.063 | TFLOPs: 23.58 | +63: iteration 73480/ 73814 | consumed samples: 37621760 | consumed tokens: 77049364480 | elapsed time per iteration (s): 2.25 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.887707E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.704 | TFLOPs: 23.44 | +63: iteration 73490/ 73814 | consumed samples: 37626880 | consumed tokens: 77059850240 | elapsed time per iteration (s): 2.24 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.881611E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.270 | TFLOPs: 23.50 | +63: iteration 73500/ 73814 | consumed samples: 37632000 | consumed tokens: 77070336000 | elapsed time per iteration (s): 2.23 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.861779E+00 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.494 | TFLOPs: 23.63 | +63: iteration 73510/ 73814 | consumed samples: 37637120 | consumed tokens: 77080821760 | elapsed time per iteration (s): 2.23 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.864933E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.690 | TFLOPs: 23.65 | +63: iteration 73520/ 73814 | consumed samples: 37642240 | consumed tokens: 77091307520 | elapsed time per iteration (s): 2.23 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.882100E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.479 | TFLOPs: 23.62 | +63: iteration 73530/ 73814 | consumed samples: 37647360 | consumed tokens: 77101793280 | elapsed time per iteration (s): 2.23 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.881924E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.042 | TFLOPs: 23.68 | +63: iteration 73540/ 73814 | consumed samples: 37652480 | consumed tokens: 77112279040 | elapsed time per iteration (s): 2.23 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.880730E+00 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.990 | TFLOPs: 23.68 | +63: iteration 73550/ 73814 | consumed samples: 37657600 | consumed tokens: 77122764800 | elapsed time per iteration (s): 2.65 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.900206E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 192.922 | TFLOPs: 19.86 | +63: iteration 73560/ 73814 | consumed samples: 37662720 | consumed tokens: 77133250560 | elapsed time per iteration (s): 2.22 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.880198E+00 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.338 | TFLOPs: 23.71 | +63: iteration 73570/ 73814 | consumed samples: 37667840 | consumed tokens: 77143736320 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.897386E+00 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.236 | TFLOPs: 23.60 | +63: iteration 73580/ 73814 | consumed samples: 37672960 | consumed tokens: 77154222080 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.866630E+00 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.202 | TFLOPs: 23.39 | +63: iteration 73590/ 73814 | consumed samples: 37678080 | consumed tokens: 77164707840 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.871079E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.468 | TFLOPs: 23.42 | +63: iteration 73600/ 73814 | consumed samples: 37683200 | consumed tokens: 77175193600 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.887200E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.417 | TFLOPs: 23.41 | +63: iteration 73610/ 73814 | consumed samples: 37688320 | consumed tokens: 77185679360 | elapsed time per iteration (s): 2.42 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.870945E+00 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 211.608 | TFLOPs: 21.78 | +63: iteration 73620/ 73814 | consumed samples: 37693440 | consumed tokens: 77196165120 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.877700E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.009 | TFLOPs: 23.68 | +63: iteration 73630/ 73814 | consumed samples: 37698560 | consumed tokens: 77206650880 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.850995E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.440 | TFLOPs: 23.52 | +63: iteration 73640/ 73814 | consumed samples: 37703680 | consumed tokens: 77217136640 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.901507E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.906 | TFLOPs: 23.67 | +63: iteration 73650/ 73814 | consumed samples: 37708800 | consumed tokens: 77227622400 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.876544E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.112 | TFLOPs: 23.69 | +63: iteration 73660/ 73814 | consumed samples: 37713920 | consumed tokens: 77238108160 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.868012E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.534 | TFLOPs: 23.53 | +63: iteration 73670/ 73814 | consumed samples: 37719040 | consumed tokens: 77248593920 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.855519E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.032 | TFLOPs: 23.68 | +63: iteration 73680/ 73814 | consumed samples: 37724160 | consumed tokens: 77259079680 | elapsed time per iteration (s): 2.26 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.884282E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.159 | TFLOPs: 23.28 | +63: iteration 73690/ 73814 | consumed samples: 37729280 | consumed tokens: 77269565440 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.889445E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.109 | TFLOPs: 23.38 | +63: iteration 73700/ 73814 | consumed samples: 37734400 | consumed tokens: 77280051200 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.865038E+00 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.844 | TFLOPs: 23.66 | +63: iteration 73710/ 73814 | consumed samples: 37739520 | consumed tokens: 77290536960 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.904472E+00 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.989 | TFLOPs: 23.57 | +63: iteration 73720/ 73814 | consumed samples: 37744640 | consumed tokens: 77301022720 | elapsed time per iteration (s): 2.26 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.887667E+00 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.122 | TFLOPs: 23.28 | +63: iteration 73730/ 73814 | consumed samples: 37749760 | consumed tokens: 77311508480 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.877744E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.657 | TFLOPs: 23.64 | +63: iteration 73740/ 73814 | consumed samples: 37754880 | consumed tokens: 77321994240 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.873761E+00 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.255 | TFLOPs: 23.60 | +63: iteration 73750/ 73814 | consumed samples: 37760000 | consumed tokens: 77332480000 | elapsed time per iteration (s): 2.38 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.847493E+00 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.561 | TFLOPs: 22.19 | +63: iteration 73760/ 73814 | consumed samples: 37765120 | consumed tokens: 77342965760 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.894987E+00 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.022 | TFLOPs: 23.68 | +63: iteration 73770/ 73814 | consumed samples: 37770240 | consumed tokens: 77353451520 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.875412E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.984 | TFLOPs: 23.68 | +63: iteration 73780/ 73814 | consumed samples: 37775360 | consumed tokens: 77363937280 | elapsed time per iteration (s): 2.22 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.859592E+00 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.296 | TFLOPs: 23.71 | +63: iteration 73790/ 73814 | consumed samples: 37780480 | consumed tokens: 77374423040 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.875615E+00 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.475 | TFLOPs: 23.42 | +63: iteration 73800/ 73814 | consumed samples: 37785600 | consumed tokens: 77384908800 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.878992E+00 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.520 | TFLOPs: 23.63 | +63: iteration 73810/ 73814 | consumed samples: 37790720 | consumed tokens: 77395394560 | elapsed time per iteration (s): 2.22 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.885787E+00 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.238 | TFLOPs: 23.70 | + 0: [after training is done] datetime: 2022-12-03 10:45:45 + 0: saving checkpoint at iteration 73814 to checkpoints_3b977boscar +63: ------------------------------------------------------------------------------------------------------------ +63: valid loss at the end of training for val data | lm loss value: 1.765185E+00 | lm loss PPL: 5.842656E+00 | +63: ------------------------------------------------------------------------------------------------------------ + 0: [2022-12-03 10:45:46,420] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step73814 is begin to save! +32: [2022-12-03 10:45:46,449] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_21-model_00-model_states.pt... + 0: [2022-12-03 10:45:46,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_01-model_00-model_states.pt... +32: [2022-12-03 10:45:46,951] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_21-model_00-model_states.pt. +32: [2022-12-03 10:45:46,951] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_22-model_00-model_states.pt... + 0: [2022-12-03 10:45:46,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_01-model_00-model_states.pt. + 0: [2022-12-03 10:45:46,963] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_03-model_00-model_states.pt... +32: [2022-12-03 10:45:47,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_22-model_00-model_states.pt. +32: [2022-12-03 10:45:47,195] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_23-model_00-model_states.pt... + 0: [2022-12-03 10:45:47,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_03-model_00-model_states.pt. + 0: [2022-12-03 10:45:47,201] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_04-model_00-model_states.pt... + 0: [2022-12-03 10:45:47,438] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_04-model_00-model_states.pt. + 0: [2022-12-03 10:45:47,438] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_05-model_00-model_states.pt... +32: [2022-12-03 10:45:47,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_23-model_00-model_states.pt. +32: [2022-12-03 10:45:47,444] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_24-model_00-model_states.pt... + 0: [2022-12-03 10:45:47,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_05-model_00-model_states.pt. + 0: [2022-12-03 10:45:47,676] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_06-model_00-model_states.pt... +32: [2022-12-03 10:45:47,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_24-model_00-model_states.pt. +32: [2022-12-03 10:45:47,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_25-model_00-model_states.pt... + 0: [2022-12-03 10:45:47,914] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_06-model_00-model_states.pt. + 0: [2022-12-03 10:45:47,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_07-model_00-model_states.pt... +32: [2022-12-03 10:45:47,933] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_25-model_00-model_states.pt. +32: [2022-12-03 10:45:47,934] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_26-model_00-model_states.pt... + 0: [2022-12-03 10:45:48,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_07-model_00-model_states.pt. + 0: [2022-12-03 10:45:48,155] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_08-model_00-model_states.pt... +32: [2022-12-03 10:45:48,172] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_26-model_00-model_states.pt. +32: [2022-12-03 10:45:48,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_27-model_00-model_states.pt... +32: [2022-12-03 10:45:48,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_27-model_00-model_states.pt. +32: [2022-12-03 10:45:48,411] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_28-model_00-model_states.pt... + 0: [2022-12-03 10:45:48,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_08-model_00-model_states.pt. + 0: [2022-12-03 10:45:48,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_09-model_00-model_states.pt... +32: [2022-12-03 10:45:48,649] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_28-model_00-model_states.pt. +32: [2022-12-03 10:45:48,649] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_29-model_00-model_states.pt... + 0: [2022-12-03 10:45:48,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_09-model_00-model_states.pt. + 0: [2022-12-03 10:45:48,771] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_10-model_00-model_states.pt... +32: [2022-12-03 10:45:48,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_29-model_00-model_states.pt. +32: [2022-12-03 10:45:48,891] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_30-model_00-model_states.pt... + 0: [2022-12-03 10:45:49,002] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_10-model_00-model_states.pt. + 0: [2022-12-03 10:45:49,002] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_11-model_00-model_states.pt... +32: [2022-12-03 10:45:49,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_30-model_00-model_states.pt. +32: [2022-12-03 10:45:49,135] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_31-model_00-model_states.pt... + 0: [2022-12-03 10:45:49,225] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_11-model_00-model_states.pt. + 0: [2022-12-03 10:45:49,225] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_12-model_00-model_states.pt... +32: [2022-12-03 10:45:49,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_31-model_00-model_states.pt. +32: [2022-12-03 10:45:49,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_32-model_00-model_states.pt... + 0: [2022-12-03 10:45:49,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_12-model_00-model_states.pt. + 0: [2022-12-03 10:45:49,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_13-model_00-model_states.pt... +32: [2022-12-03 10:45:49,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_32-model_00-model_states.pt. +32: [2022-12-03 10:45:49,621] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_33-model_00-model_states.pt... + 0: [2022-12-03 10:45:49,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_13-model_00-model_states.pt. + 0: [2022-12-03 10:45:49,678] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_14-model_00-model_states.pt... +32: [2022-12-03 10:45:49,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_33-model_00-model_states.pt. +32: [2022-12-03 10:45:49,863] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_34-model_00-model_states.pt... + 0: [2022-12-03 10:45:49,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_14-model_00-model_states.pt. + 0: [2022-12-03 10:45:49,904] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_15-model_00-model_states.pt... +32: [2022-12-03 10:45:50,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_34-model_00-model_states.pt. +32: [2022-12-03 10:45:50,105] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_35-model_00-model_states.pt... + 0: [2022-12-03 10:45:50,128] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_15-model_00-model_states.pt. + 0: [2022-12-03 10:45:50,129] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_16-model_00-model_states.pt... +32: [2022-12-03 10:45:50,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_35-model_00-model_states.pt. +32: [2022-12-03 10:45:50,346] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_36-model_00-model_states.pt... + 0: [2022-12-03 10:45:50,358] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_16-model_00-model_states.pt. + 0: [2022-12-03 10:45:50,358] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_17-model_00-model_states.pt... + 0: [2022-12-03 10:45:50,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_17-model_00-model_states.pt. + 0: [2022-12-03 10:45:50,584] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_18-model_00-model_states.pt... +32: [2022-12-03 10:45:50,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_36-model_00-model_states.pt. +32: [2022-12-03 10:45:50,587] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_37-model_00-model_states.pt... + 0: [2022-12-03 10:45:50,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_18-model_00-model_states.pt. + 0: [2022-12-03 10:45:50,810] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_19-model_00-model_states.pt... +32: [2022-12-03 10:45:50,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_37-model_00-model_states.pt. +32: [2022-12-03 10:45:50,825] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_38-model_00-model_states.pt... + 0: [2022-12-03 10:45:51,037] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_19-model_00-model_states.pt. + 0: [2022-12-03 10:45:51,038] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_20-model_00-model_states.pt... +32: [2022-12-03 10:45:51,062] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_38-model_00-model_states.pt. +32: [2022-12-03 10:45:51,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/layer_40-model_00-model_states.pt... +32: [2022-12-03 10:45:51,065] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_40-model_00-model_states.pt. +32: [2022-12-03 10:45:51,066] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/mp_rank_01_model_states.pt... +32: [2022-12-03 10:45:51,072] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/mp_rank_01_model_states.pt. + 0: [2022-12-03 10:45:51,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/layer_20-model_00-model_states.pt. + 0: [2022-12-03 10:45:51,265] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_3b977boscar/global_step73814/mp_rank_00_model_states.pt + 0: [2022-12-03 10:45:51,265] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/mp_rank_00_model_states.pt... + 0: [2022-12-03 10:45:51,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/mp_rank_00_model_states.pt. +32: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt... +54: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt... +54: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt... +54: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt... +54: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt... +54: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt... +56: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt... +56: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt... +56: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt... +56: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt... +56: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt... +52: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt... +52: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt... +52: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt... +52: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt... +52: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt... +61: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt... +61: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt... +61: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt... +61: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt... +61: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt... +63: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt... +63: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt... +63: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt... +63: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt... +63: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt... +53: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt... +53: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt... +53: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt... +53: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt... +53: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt... +59: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt... +59: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt... +59: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt... +59: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt... +59: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt... +62: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt... +62: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt... +62: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt... +58: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt... +58: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt... +58: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt... +58: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt... +58: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt... +38: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt... +38: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt... +38: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt... +38: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt... +38: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt... +44: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt... +44: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt... +44: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt... +44: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt... +44: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt... +48: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt... +48: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt... +48: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt... +48: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt... +48: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt... +34: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt... +34: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt... +34: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt... +34: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt... +34: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt... +43: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt... +43: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt... +43: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt... +43: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt... +43: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt... +36: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt... +36: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt... +36: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt... +36: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt... +36: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt... +35: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt... +35: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt... +35: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt... +35: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt... +35: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt... +39: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt... +39: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt... +50: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt... +50: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt... +50: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt... +50: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt... +50: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt... +32: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt... +32: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt... +32: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt... +32: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt... +51: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt... +51: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt... +51: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt... +51: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt... +51: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt... +60: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt... +60: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt... +60: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt... +60: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt... +60: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt... +49: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt... +49: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt... +49: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt... +49: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt... +46: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt... +46: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt... +46: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt... +41: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt... +41: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt... +41: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt... +41: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt... +41: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt... +55: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt... +55: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt... +55: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt... +55: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt... +55: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt... +47: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt... +47: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt... +47: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt... +47: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt... +47: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt... +45: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt... +45: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt... +45: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt... +37: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt... +37: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt... +37: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt... +37: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt... +37: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt... +40: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt... +40: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt... +40: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt... +40: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt... +40: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt... +42: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt... +42: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt... +42: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt... +42: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt... +42: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt... +57: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt... +57: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt... +57: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt... +57: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt... +57: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt... + 0: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +54: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt... +54: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt... +56: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt... +56: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt... +52: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt... +61: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt... +63: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt... +63: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt... +63: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt... +53: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt... +33: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt... +33: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt... +33: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt... +33: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt... +33: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt... +59: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt... +59: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt... +59: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt... +62: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt... +62: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt... +62: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt... +62: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt... +62: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt... +58: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt... +38: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt... +38: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt... +44: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt... +44: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt... +44: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt... +48: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt... +48: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt... +34: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt... +43: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt... +36: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt... +36: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt... +35: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt... +39: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt... +39: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt... +39: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt... +39: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt... +39: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt... +50: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt... +50: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt... +32: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt... +51: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt... +60: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt... +60: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt... +60: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt... +49: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt... +46: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt... +41: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt... +41: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt... +41: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt... +55: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt... +47: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt... +47: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt... +47: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt... +45: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt... +45: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt... +40: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt... +40: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt... +42: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt... +42: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt... +57: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt... +57: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt... +54: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt... +56: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt... +52: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt... +52: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt... +61: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt... +61: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt... +53: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt... +33: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt... +33: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt... +58: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt... +58: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt... +38: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt... +48: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt... +34: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt... +43: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt... +36: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt... +35: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt... +35: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt... +39: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt... +50: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt... +32: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt... +51: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt... +51: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt... +49: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt... +46: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt... +55: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt... +45: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt... +37: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt... +37: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt... +40: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt... +42: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt... +57: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt... + 0: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +53: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt... +33: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt... +34: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt... +43: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt... +32: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt... +49: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt... +46: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt... +46: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt... +55: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt... + 8: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... +45: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt... +37: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt... + 0: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 7: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +19: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +20: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +15: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... + 1: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +11: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... + 5: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +10: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +28: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +22: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +12: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +18: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +26: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... + 9: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 2: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +25: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... + 4: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 6: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +13: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +31: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +49: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt... +46: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt... + 3: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +27: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... + 8: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +16: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +14: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +17: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +29: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +45: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt... +30: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +24: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +23: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +21: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... + 0: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 7: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +19: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +20: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +15: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... + 1: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +11: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... + 5: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +10: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +28: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +22: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +12: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +18: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +26: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... + 9: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 2: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +25: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... + 4: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 6: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +13: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +31: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... + 3: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +27: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... + 8: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... +16: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +14: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +17: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +29: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +30: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +24: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +23: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +21: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... + 0: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 7: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +19: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +20: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +15: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... + 1: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +11: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... + 5: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +10: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +28: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +22: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +12: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +18: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +26: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... + 9: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 2: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +25: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... + 4: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 6: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +13: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +31: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... + 3: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +27: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... + 8: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... +16: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +14: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +17: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +29: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +30: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +24: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +23: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +21: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... + 0: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 7: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +19: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +20: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +15: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... + 1: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +11: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 5: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +10: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +28: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +22: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +12: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +18: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +26: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... + 9: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 2: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +25: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... + 4: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 6: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +13: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... + 3: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +27: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... + 8: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... +16: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +14: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +17: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +29: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +30: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +24: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +23: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +21: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... + 0: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 7: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +19: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +20: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +15: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... + 1: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +11: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... + 5: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +10: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +28: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +22: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +12: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +18: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +26: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... + 9: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 2: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +25: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... + 6: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +13: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... + 3: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +27: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... + 8: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... +16: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +14: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +17: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +29: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +30: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +24: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +23: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +21: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... + 7: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +19: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +20: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... + 1: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +11: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... + 5: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +28: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +12: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +18: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +26: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... + 9: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 2: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +25: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... + 6: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 3: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +27: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... + 8: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +16: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +17: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +29: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +30: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +24: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +23: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +21: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +19: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +20: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +11: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... + 5: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +28: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +12: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +18: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +25: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +31: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... + 8: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... +16: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +17: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +30: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +23: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +21: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +19: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +30: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +26: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... + 9: [2022-12-03 10:45:51,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 0: [2022-12-03 10:45:51,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +32: [2022-12-03 10:45:51,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt. +32: [2022-12-03 10:45:51,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt +32: [2022-12-03 10:45:51,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 0: [2022-12-03 10:45:51,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-12-03 10:45:51,551] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-12-03 10:45:51,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 0: [2022-12-03 10:45:51,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-12-03 10:45:51,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-12-03 10:45:51,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 0: [2022-12-03 10:45:51,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-12-03 10:45:51,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-12-03 10:45:51,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +32: [2022-12-03 10:45:51,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt. +32: [2022-12-03 10:45:51,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt. +32: [2022-12-03 10:45:51,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt +32: [2022-12-03 10:45:51,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt +32: [2022-12-03 10:45:51,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +32: [2022-12-03 10:45:51,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 0: [2022-12-03 10:45:51,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-12-03 10:45:51,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-12-03 10:45:51,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 0: [2022-12-03 10:45:51,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-12-03 10:45:51,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-12-03 10:45:51,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 0: [2022-12-03 10:45:51,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-12-03 10:45:51,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-12-03 10:45:51,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 7: [2022-12-03 10:45:51,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +27: [2022-12-03 10:45:51,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-12-03 10:45:51,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt + 7: [2022-12-03 10:45:51,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +27: [2022-12-03 10:45:51,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 7: [2022-12-03 10:45:51,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +32: [2022-12-03 10:45:51,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt. +32: [2022-12-03 10:45:51,576] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt +32: [2022-12-03 10:45:51,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +16: [2022-12-03 10:45:51,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-12-03 10:45:51,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-12-03 10:45:51,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +24: [2022-12-03 10:45:51,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-12-03 10:45:51,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-12-03 10:45:51,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +42: [2022-12-03 10:45:51,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt. +42: [2022-12-03 10:45:51,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt +42: [2022-12-03 10:45:51,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +42: [2022-12-03 10:45:51,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt. +42: [2022-12-03 10:45:51,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt. +42: [2022-12-03 10:45:51,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt +42: [2022-12-03 10:45:51,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +53: [2022-12-03 10:45:51,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt. +42: [2022-12-03 10:45:51,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt +53: [2022-12-03 10:45:51,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt +53: [2022-12-03 10:45:51,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +42: [2022-12-03 10:45:51,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +25: [2022-12-03 10:45:51,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-12-03 10:45:51,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-12-03 10:45:51,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +34: [2022-12-03 10:45:51,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt. +12: [2022-12-03 10:45:51,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-12-03 10:45:51,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-12-03 10:45:51,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +30: [2022-12-03 10:45:51,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-12-03 10:45:51,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-12-03 10:45:51,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +49: [2022-12-03 10:45:51,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt. +49: [2022-12-03 10:45:51,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt +59: [2022-12-03 10:45:51,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt. +34: [2022-12-03 10:45:51,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt +49: [2022-12-03 10:45:51,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +34: [2022-12-03 10:45:51,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +60: [2022-12-03 10:45:51,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt. +60: [2022-12-03 10:45:51,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt +60: [2022-12-03 10:45:51,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +21: [2022-12-03 10:45:51,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-12-03 10:45:51,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-12-03 10:45:51,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +26: [2022-12-03 10:45:51,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-12-03 10:45:51,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +49: [2022-12-03 10:45:51,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt. +26: [2022-12-03 10:45:51,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-12-03 10:45:51,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +49: [2022-12-03 10:45:51,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt +23: [2022-12-03 10:45:51,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +26: [2022-12-03 10:45:51,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +26: [2022-12-03 10:45:51,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +49: [2022-12-03 10:45:51,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +23: [2022-12-03 10:45:51,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-12-03 10:45:51,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +49: [2022-12-03 10:45:51,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt. +49: [2022-12-03 10:45:51,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt +49: [2022-12-03 10:45:51,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +23: [2022-12-03 10:45:51,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-12-03 10:45:51,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-12-03 10:45:51,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +60: [2022-12-03 10:45:51,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt. +60: [2022-12-03 10:45:51,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt. +60: [2022-12-03 10:45:51,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt +23: [2022-12-03 10:45:51,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +60: [2022-12-03 10:45:51,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +60: [2022-12-03 10:45:51,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt +26: [2022-12-03 10:45:51,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +23: [2022-12-03 10:45:51,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +26: [2022-12-03 10:45:51,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +60: [2022-12-03 10:45:51,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +23: [2022-12-03 10:45:51,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +26: [2022-12-03 10:45:51,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +17: [2022-12-03 10:45:51,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-12-03 10:45:51,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-12-03 10:45:51,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +10: [2022-12-03 10:45:51,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-12-03 10:45:51,587] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-12-03 10:45:51,587] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 7: [2022-12-03 10:45:51,587] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-12-03 10:45:51,587] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-12-03 10:45:51,588] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +60: [2022-12-03 10:45:51,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt. + 7: [2022-12-03 10:45:51,587] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-12-03 10:45:51,588] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-12-03 10:45:51,588] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +44: [2022-12-03 10:45:51,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt. +60: [2022-12-03 10:45:51,588] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt + 7: [2022-12-03 10:45:51,588] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 7: [2022-12-03 10:45:51,588] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +44: [2022-12-03 10:45:51,588] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt +60: [2022-12-03 10:45:51,588] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 7: [2022-12-03 10:45:51,588] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +44: [2022-12-03 10:45:51,588] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +37: [2022-12-03 10:45:51,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt. +37: [2022-12-03 10:45:51,588] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt +44: [2022-12-03 10:45:51,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt. +37: [2022-12-03 10:45:51,588] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +44: [2022-12-03 10:45:51,588] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt +44: [2022-12-03 10:45:51,588] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +34: [2022-12-03 10:45:51,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt. +34: [2022-12-03 10:45:51,588] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt +34: [2022-12-03 10:45:51,588] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +27: [2022-12-03 10:45:51,589] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-12-03 10:45:51,589] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-12-03 10:45:51,589] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +37: [2022-12-03 10:45:51,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt. +37: [2022-12-03 10:45:51,590] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt +12: [2022-12-03 10:45:51,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-12-03 10:45:51,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-12-03 10:45:51,590] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +37: [2022-12-03 10:45:51,590] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +12: [2022-12-03 10:45:51,590] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-12-03 10:45:51,590] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +32: [2022-12-03 10:45:51,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt. +16: [2022-12-03 10:45:51,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +12: [2022-12-03 10:45:51,590] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +32: [2022-12-03 10:45:51,590] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt +16: [2022-12-03 10:45:51,590] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +32: [2022-12-03 10:45:51,590] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +16: [2022-12-03 10:45:51,590] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +32: [2022-12-03 10:45:51,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt. +32: [2022-12-03 10:45:51,590] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt +22: [2022-12-03 10:45:51,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-12-03 10:45:51,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-12-03 10:45:51,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-12-03 10:45:51,590] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-12-03 10:45:51,590] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-12-03 10:45:51,590] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +22: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +22: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +27: [2022-12-03 10:45:51,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-12-03 10:45:51,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +29: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +32: [2022-12-03 10:45:51,590] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +53: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt. +32: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt. +29: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +32: [2022-12-03 10:45:51,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt +29: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +53: [2022-12-03 10:45:51,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt +32: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +29: [2022-12-03 10:45:51,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +53: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +29: [2022-12-03 10:45:51,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +29: [2022-12-03 10:45:51,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +29: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +11: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-12-03 10:45:51,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-12-03 10:45:51,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +11: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +53: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt. +53: [2022-12-03 10:45:51,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt +53: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +18: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. + 6: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +18: [2022-12-03 10:45:51,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt + 6: [2022-12-03 10:45:51,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-12-03 10:45:51,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +18: [2022-12-03 10:45:51,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt + 6: [2022-12-03 10:45:51,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +18: [2022-12-03 10:45:51,592] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +18: [2022-12-03 10:45:51,592] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 6: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 6: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 6: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +37: [2022-12-03 10:45:51,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt. +37: [2022-12-03 10:45:51,592] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt +37: [2022-12-03 10:45:51,592] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +10: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-12-03 10:45:51,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +44: [2022-12-03 10:45:51,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt. +44: [2022-12-03 10:45:51,592] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt +44: [2022-12-03 10:45:51,592] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +21: [2022-12-03 10:45:51,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-12-03 10:45:51,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt + 3: [2022-12-03 10:45:51,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +21: [2022-12-03 10:45:51,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 3: [2022-12-03 10:45:51,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-12-03 10:45:51,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +21: [2022-12-03 10:45:51,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-12-03 10:45:51,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-12-03 10:45:51,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +16: [2022-12-03 10:45:51,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-12-03 10:45:51,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-12-03 10:45:51,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-12-03 10:45:51,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-12-03 10:45:51,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +16: [2022-12-03 10:45:51,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 3: [2022-12-03 10:45:51,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-12-03 10:45:51,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +11: [2022-12-03 10:45:51,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. + 3: [2022-12-03 10:45:51,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +11: [2022-12-03 10:45:51,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-12-03 10:45:51,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +18: [2022-12-03 10:45:51,594] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-12-03 10:45:51,594] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-12-03 10:45:51,594] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +33: [2022-12-03 10:45:51,594] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt. +33: [2022-12-03 10:45:51,594] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt. +33: [2022-12-03 10:45:51,594] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt. +33: [2022-12-03 10:45:51,594] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt. +33: [2022-12-03 10:45:51,594] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt +33: [2022-12-03 10:45:51,594] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt +33: [2022-12-03 10:45:51,594] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt +33: [2022-12-03 10:45:51,594] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt +33: [2022-12-03 10:45:51,594] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +33: [2022-12-03 10:45:51,594] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +33: [2022-12-03 10:45:51,594] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +33: [2022-12-03 10:45:51,594] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +10: [2022-12-03 10:45:51,594] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. + 3: [2022-12-03 10:45:51,594] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-12-03 10:45:51,595] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-12-03 10:45:51,595] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +13: [2022-12-03 10:45:51,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-12-03 10:45:51,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-12-03 10:45:51,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-12-03 10:45:51,595] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-12-03 10:45:51,595] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-12-03 10:45:51,595] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-12-03 10:45:51,595] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +13: [2022-12-03 10:45:51,595] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +13: [2022-12-03 10:45:51,595] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +10: [2022-12-03 10:45:51,594] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-12-03 10:45:51,594] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +28: [2022-12-03 10:45:51,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +54: [2022-12-03 10:45:51,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt. +54: [2022-12-03 10:45:51,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt. +28: [2022-12-03 10:45:51,595] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-12-03 10:45:51,595] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +54: [2022-12-03 10:45:51,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt. +54: [2022-12-03 10:45:51,595] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt +54: [2022-12-03 10:45:51,595] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt +54: [2022-12-03 10:45:51,595] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt +54: [2022-12-03 10:45:51,595] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +54: [2022-12-03 10:45:51,595] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +54: [2022-12-03 10:45:51,596] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 8: [2022-12-03 10:45:51,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-12-03 10:45:51,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. +30: [2022-12-03 10:45:51,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-12-03 10:45:51,596] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-12-03 10:45:51,596] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +30: [2022-12-03 10:45:51,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-12-03 10:45:51,596] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-12-03 10:45:51,596] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +28: [2022-12-03 10:45:51,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-12-03 10:45:51,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-12-03 10:45:51,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +28: [2022-12-03 10:45:51,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-12-03 10:45:51,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +37: [2022-12-03 10:45:51,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt. +28: [2022-12-03 10:45:51,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +34: [2022-12-03 10:45:51,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt. +34: [2022-12-03 10:45:51,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt. +37: [2022-12-03 10:45:51,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt +34: [2022-12-03 10:45:51,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt +34: [2022-12-03 10:45:51,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt +34: [2022-12-03 10:45:51,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +34: [2022-12-03 10:45:51,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +37: [2022-12-03 10:45:51,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +17: [2022-12-03 10:45:51,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +50: [2022-12-03 10:45:51,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt. +17: [2022-12-03 10:45:51,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-12-03 10:45:51,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 8: [2022-12-03 10:45:51,596] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-12-03 10:45:51,596] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-12-03 10:45:51,596] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +17: [2022-12-03 10:45:51,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. + 8: [2022-12-03 10:45:51,596] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +25: [2022-12-03 10:45:51,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. + 8: [2022-12-03 10:45:51,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. +17: [2022-12-03 10:45:51,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt + 8: [2022-12-03 10:45:51,596] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt +25: [2022-12-03 10:45:51,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt + 8: [2022-12-03 10:45:51,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +17: [2022-12-03 10:45:51,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +25: [2022-12-03 10:45:51,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +41: [2022-12-03 10:45:51,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt. +41: [2022-12-03 10:45:51,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt. +41: [2022-12-03 10:45:51,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt. +41: [2022-12-03 10:45:51,599] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt +41: [2022-12-03 10:45:51,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +41: [2022-12-03 10:45:51,599] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt +41: [2022-12-03 10:45:51,599] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt +41: [2022-12-03 10:45:51,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +41: [2022-12-03 10:45:51,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +50: [2022-12-03 10:45:51,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt +50: [2022-12-03 10:45:51,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +50: [2022-12-03 10:45:51,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt. +50: [2022-12-03 10:45:51,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt +50: [2022-12-03 10:45:51,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +50: [2022-12-03 10:45:51,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt. +50: [2022-12-03 10:45:51,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt. +50: [2022-12-03 10:45:51,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt +50: [2022-12-03 10:45:51,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt +50: [2022-12-03 10:45:51,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +50: [2022-12-03 10:45:51,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 2: [2022-12-03 10:45:51,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-12-03 10:45:51,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 2: [2022-12-03 10:45:51,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-12-03 10:45:51,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-12-03 10:45:51,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-12-03 10:45:51,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 2: [2022-12-03 10:45:51,600] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 2: [2022-12-03 10:45:51,600] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 2: [2022-12-03 10:45:51,600] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +19: [2022-12-03 10:45:51,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-12-03 10:45:51,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-12-03 10:45:51,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-12-03 10:45:51,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-12-03 10:45:51,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +57: [2022-12-03 10:45:51,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt. +57: [2022-12-03 10:45:51,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt. +57: [2022-12-03 10:45:51,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt. +19: [2022-12-03 10:45:51,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-12-03 10:45:51,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +19: [2022-12-03 10:45:51,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +19: [2022-12-03 10:45:51,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +31: [2022-12-03 10:45:51,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-12-03 10:45:51,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-12-03 10:45:51,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-12-03 10:45:51,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-12-03 10:45:51,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-12-03 10:45:51,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-12-03 10:45:51,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +31: [2022-12-03 10:45:51,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +31: [2022-12-03 10:45:51,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +57: [2022-12-03 10:45:51,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt +57: [2022-12-03 10:45:51,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt +57: [2022-12-03 10:45:51,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt +57: [2022-12-03 10:45:51,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +57: [2022-12-03 10:45:51,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +57: [2022-12-03 10:45:51,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +25: [2022-12-03 10:45:51,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-12-03 10:45:51,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-12-03 10:45:51,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +63: [2022-12-03 10:45:51,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt. +63: [2022-12-03 10:45:51,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt. +63: [2022-12-03 10:45:51,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt. +63: [2022-12-03 10:45:51,604] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt +63: [2022-12-03 10:45:51,604] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt +63: [2022-12-03 10:45:51,604] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt +63: [2022-12-03 10:45:51,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt. +63: [2022-12-03 10:45:51,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +63: [2022-12-03 10:45:51,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +63: [2022-12-03 10:45:51,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +63: [2022-12-03 10:45:51,604] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt +63: [2022-12-03 10:45:51,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 1: [2022-12-03 10:45:51,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-12-03 10:45:51,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-12-03 10:45:51,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-12-03 10:45:51,604] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-12-03 10:45:51,604] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-12-03 10:45:51,604] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-12-03 10:45:51,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 1: [2022-12-03 10:45:51,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 1: [2022-12-03 10:45:51,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +59: [2022-12-03 10:45:51,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt +59: [2022-12-03 10:45:51,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +59: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt. +59: [2022-12-03 10:45:51,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt +59: [2022-12-03 10:45:51,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +59: [2022-12-03 10:45:51,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt. +59: [2022-12-03 10:45:51,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt +59: [2022-12-03 10:45:51,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +59: [2022-12-03 10:45:51,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt. +59: [2022-12-03 10:45:51,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt +59: [2022-12-03 10:45:51,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +61: [2022-12-03 10:45:51,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt. +61: [2022-12-03 10:45:51,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt. +46: [2022-12-03 10:45:51,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt. +46: [2022-12-03 10:45:51,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt. +46: [2022-12-03 10:45:51,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt. +46: [2022-12-03 10:45:51,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt. +61: [2022-12-03 10:45:51,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt +46: [2022-12-03 10:45:51,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt +46: [2022-12-03 10:45:51,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt +46: [2022-12-03 10:45:51,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt +61: [2022-12-03 10:45:51,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt +46: [2022-12-03 10:45:51,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt +61: [2022-12-03 10:45:51,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +61: [2022-12-03 10:45:51,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +46: [2022-12-03 10:45:51,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +46: [2022-12-03 10:45:51,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +46: [2022-12-03 10:45:51,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +46: [2022-12-03 10:45:51,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +61: [2022-12-03 10:45:51,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt. +61: [2022-12-03 10:45:51,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt. +61: [2022-12-03 10:45:51,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt +61: [2022-12-03 10:45:51,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt +61: [2022-12-03 10:45:51,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +61: [2022-12-03 10:45:51,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +43: [2022-12-03 10:45:51,606] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt. +43: [2022-12-03 10:45:51,607] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt +43: [2022-12-03 10:45:51,607] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +56: [2022-12-03 10:45:51,608] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt. +56: [2022-12-03 10:45:51,608] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt. +43: [2022-12-03 10:45:51,610] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt. +43: [2022-12-03 10:45:51,610] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt +43: [2022-12-03 10:45:51,610] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +56: [2022-12-03 10:45:51,608] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt +56: [2022-12-03 10:45:51,608] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt +56: [2022-12-03 10:45:51,608] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +56: [2022-12-03 10:45:51,608] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +56: [2022-12-03 10:45:51,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt. +56: [2022-12-03 10:45:51,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt. +56: [2022-12-03 10:45:51,609] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt +56: [2022-12-03 10:45:51,609] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt +56: [2022-12-03 10:45:51,609] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +56: [2022-12-03 10:45:51,609] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +47: [2022-12-03 10:45:51,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt. +47: [2022-12-03 10:45:51,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt. +47: [2022-12-03 10:45:51,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt. +47: [2022-12-03 10:45:51,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt. +47: [2022-12-03 10:45:51,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt +47: [2022-12-03 10:45:51,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt +47: [2022-12-03 10:45:51,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt +47: [2022-12-03 10:45:51,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt +47: [2022-12-03 10:45:51,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +47: [2022-12-03 10:45:51,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +15: [2022-12-03 10:45:51,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +47: [2022-12-03 10:45:51,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +47: [2022-12-03 10:45:51,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +15: [2022-12-03 10:45:51,613] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-12-03 10:45:51,613] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +15: [2022-12-03 10:45:51,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-12-03 10:45:51,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-12-03 10:45:51,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +15: [2022-12-03 10:45:51,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-12-03 10:45:51,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-12-03 10:45:51,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +48: [2022-12-03 10:45:51,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt. +48: [2022-12-03 10:45:51,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt. +48: [2022-12-03 10:45:51,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt. +48: [2022-12-03 10:45:51,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt. +48: [2022-12-03 10:45:51,615] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt +48: [2022-12-03 10:45:51,615] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt +48: [2022-12-03 10:45:51,615] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt +48: [2022-12-03 10:45:51,615] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt +48: [2022-12-03 10:45:51,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +48: [2022-12-03 10:45:51,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +48: [2022-12-03 10:45:51,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +48: [2022-12-03 10:45:51,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +51: [2022-12-03 10:45:51,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt. +51: [2022-12-03 10:45:51,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt. +51: [2022-12-03 10:45:51,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt. +51: [2022-12-03 10:45:51,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt. +51: [2022-12-03 10:45:51,616] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt +51: [2022-12-03 10:45:51,616] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt +51: [2022-12-03 10:45:51,616] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt +51: [2022-12-03 10:45:51,616] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt +51: [2022-12-03 10:45:51,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +51: [2022-12-03 10:45:51,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +51: [2022-12-03 10:45:51,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +51: [2022-12-03 10:45:51,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +14: [2022-12-03 10:45:51,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +43: [2022-12-03 10:45:51,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt. +14: [2022-12-03 10:45:51,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-12-03 10:45:51,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-12-03 10:45:51,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +43: [2022-12-03 10:45:51,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt +14: [2022-12-03 10:45:51,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-12-03 10:45:51,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +43: [2022-12-03 10:45:51,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +14: [2022-12-03 10:45:51,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +14: [2022-12-03 10:45:51,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-12-03 10:45:51,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +39: [2022-12-03 10:45:51,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt. +39: [2022-12-03 10:45:51,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt. +39: [2022-12-03 10:45:51,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt. +39: [2022-12-03 10:45:51,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt. +39: [2022-12-03 10:45:51,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt +39: [2022-12-03 10:45:51,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +39: [2022-12-03 10:45:51,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt +39: [2022-12-03 10:45:51,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt +39: [2022-12-03 10:45:51,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt +39: [2022-12-03 10:45:51,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +39: [2022-12-03 10:45:51,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +39: [2022-12-03 10:45:51,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +36: [2022-12-03 10:45:51,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt. +36: [2022-12-03 10:45:51,618] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt +36: [2022-12-03 10:45:51,618] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +20: [2022-12-03 10:45:51,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +36: [2022-12-03 10:45:51,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt. +20: [2022-12-03 10:45:51,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-12-03 10:45:51,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-12-03 10:45:51,618] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +36: [2022-12-03 10:45:51,618] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt +20: [2022-12-03 10:45:51,618] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-12-03 10:45:51,618] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-12-03 10:45:51,618] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +36: [2022-12-03 10:45:51,618] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +20: [2022-12-03 10:45:51,618] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +20: [2022-12-03 10:45:51,618] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +43: [2022-12-03 10:45:51,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt. +43: [2022-12-03 10:45:51,618] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt +36: [2022-12-03 10:45:51,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt. +43: [2022-12-03 10:45:51,618] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +36: [2022-12-03 10:45:51,618] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt +36: [2022-12-03 10:45:51,618] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +24: [2022-12-03 10:45:51,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-12-03 10:45:51,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-12-03 10:45:51,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +36: [2022-12-03 10:45:51,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt. +36: [2022-12-03 10:45:51,621] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt +36: [2022-12-03 10:45:51,621] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +62: [2022-12-03 10:45:51,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt. +62: [2022-12-03 10:45:51,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt. +62: [2022-12-03 10:45:51,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt. +62: [2022-12-03 10:45:51,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt. +62: [2022-12-03 10:45:51,622] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt +24: [2022-12-03 10:45:51,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +62: [2022-12-03 10:45:51,622] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt +62: [2022-12-03 10:45:51,622] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt +24: [2022-12-03 10:45:51,622] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +62: [2022-12-03 10:45:51,622] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt +24: [2022-12-03 10:45:51,622] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +62: [2022-12-03 10:45:51,622] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +62: [2022-12-03 10:45:51,622] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +62: [2022-12-03 10:45:51,622] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +62: [2022-12-03 10:45:51,622] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 9: [2022-12-03 10:45:51,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-12-03 10:45:51,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-12-03 10:45:51,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-12-03 10:45:51,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-12-03 10:45:51,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-12-03 10:45:51,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-12-03 10:45:51,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 9: [2022-12-03 10:45:51,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 9: [2022-12-03 10:45:51,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 4: [2022-12-03 10:45:51,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-12-03 10:45:51,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-12-03 10:45:51,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-12-03 10:45:51,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-12-03 10:45:51,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-12-03 10:45:51,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 4: [2022-12-03 10:45:51,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 4: [2022-12-03 10:45:51,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-12-03 10:45:51,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +58: [2022-12-03 10:45:51,632] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt. +58: [2022-12-03 10:45:51,632] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt. +58: [2022-12-03 10:45:51,632] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt. +58: [2022-12-03 10:45:51,632] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt. +52: [2022-12-03 10:45:51,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt. +52: [2022-12-03 10:45:51,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt. +52: [2022-12-03 10:45:51,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt. +52: [2022-12-03 10:45:51,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt. +52: [2022-12-03 10:45:51,638] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt +52: [2022-12-03 10:45:51,638] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt +52: [2022-12-03 10:45:51,638] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt +52: [2022-12-03 10:45:51,638] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +52: [2022-12-03 10:45:51,638] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt +52: [2022-12-03 10:45:51,638] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +52: [2022-12-03 10:45:51,638] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +52: [2022-12-03 10:45:51,638] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +55: [2022-12-03 10:45:51,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt. +55: [2022-12-03 10:45:51,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt. +38: [2022-12-03 10:45:51,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt. +38: [2022-12-03 10:45:51,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt. +38: [2022-12-03 10:45:51,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt. +38: [2022-12-03 10:45:51,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt +55: [2022-12-03 10:45:51,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt. +55: [2022-12-03 10:45:51,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt. +38: [2022-12-03 10:45:51,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt +38: [2022-12-03 10:45:51,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt +55: [2022-12-03 10:45:51,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt +38: [2022-12-03 10:45:51,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +38: [2022-12-03 10:45:51,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +38: [2022-12-03 10:45:51,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +55: [2022-12-03 10:45:51,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt +55: [2022-12-03 10:45:51,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +55: [2022-12-03 10:45:51,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt +55: [2022-12-03 10:45:51,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt +55: [2022-12-03 10:45:51,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +55: [2022-12-03 10:45:51,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +55: [2022-12-03 10:45:51,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +58: [2022-12-03 10:45:51,632] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt. +58: [2022-12-03 10:45:51,632] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt. +58: [2022-12-03 10:45:51,632] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt. +58: [2022-12-03 10:45:51,632] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt +58: [2022-12-03 10:45:51,632] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt +58: [2022-12-03 10:45:51,632] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt +58: [2022-12-03 10:45:51,632] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt +58: [2022-12-03 10:45:51,632] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt +58: [2022-12-03 10:45:51,632] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt +58: [2022-12-03 10:45:51,632] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt +58: [2022-12-03 10:45:51,632] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +58: [2022-12-03 10:45:51,632] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +58: [2022-12-03 10:45:51,632] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +58: [2022-12-03 10:45:51,632] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +58: [2022-12-03 10:45:51,632] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +58: [2022-12-03 10:45:51,632] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +58: [2022-12-03 10:45:51,632] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +45: [2022-12-03 10:45:51,657] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt. +45: [2022-12-03 10:45:51,657] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt. +45: [2022-12-03 10:45:51,657] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt. +45: [2022-12-03 10:45:51,657] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt. +45: [2022-12-03 10:45:51,657] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt +45: [2022-12-03 10:45:51,657] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt +45: [2022-12-03 10:45:51,657] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt +45: [2022-12-03 10:45:51,657] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt +45: [2022-12-03 10:45:51,658] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +45: [2022-12-03 10:45:51,658] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +45: [2022-12-03 10:45:51,658] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +45: [2022-12-03 10:45:51,658] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +40: [2022-12-03 10:45:51,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt. +40: [2022-12-03 10:45:51,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt. +40: [2022-12-03 10:45:51,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt. +40: [2022-12-03 10:45:51,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt +40: [2022-12-03 10:45:51,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt +40: [2022-12-03 10:45:51,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt +40: [2022-12-03 10:45:51,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +40: [2022-12-03 10:45:51,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +40: [2022-12-03 10:45:51,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +40: [2022-12-03 10:45:51,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt. +40: [2022-12-03 10:45:51,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt +40: [2022-12-03 10:45:51,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +40: [2022-12-03 10:45:51,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt. +40: [2022-12-03 10:45:51,677] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt +40: [2022-12-03 10:45:51,677] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +17: [2022-12-03 10:45:51,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-12-03 10:45:51,693] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-12-03 10:45:51,693] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 0: [2022-12-03 10:45:51,695] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-12-03 10:45:51,695] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +35: [2022-12-03 10:45:51,695] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt. +35: [2022-12-03 10:45:51,695] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt. +35: [2022-12-03 10:45:51,695] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt +35: [2022-12-03 10:45:51,695] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt. +35: [2022-12-03 10:45:51,695] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +35: [2022-12-03 10:45:51,695] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt +35: [2022-12-03 10:45:51,695] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt +35: [2022-12-03 10:45:51,695] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +35: [2022-12-03 10:45:51,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +20: [2022-12-03 10:45:51,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-12-03 10:45:51,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-12-03 10:45:51,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +35: [2022-12-03 10:45:51,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt. +35: [2022-12-03 10:45:51,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt +35: [2022-12-03 10:45:51,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +35: [2022-12-03 10:45:51,697] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt. +35: [2022-12-03 10:45:51,697] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt +35: [2022-12-03 10:45:51,697] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +34: [2022-12-03 10:45:51,699] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt. +34: [2022-12-03 10:45:51,699] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt +34: [2022-12-03 10:45:51,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +32: [2022-12-03 10:45:51,702] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt. +32: [2022-12-03 10:45:51,702] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt +32: [2022-12-03 10:45:51,702] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +41: [2022-12-03 10:45:51,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt. +41: [2022-12-03 10:45:51,704] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt +41: [2022-12-03 10:45:51,704] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +27: [2022-12-03 10:45:51,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-12-03 10:45:51,704] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-12-03 10:45:51,704] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 0: [2022-12-03 10:45:51,706] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-12-03 10:45:51,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-12-03 10:45:51,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +44: [2022-12-03 10:45:51,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt. +44: [2022-12-03 10:45:51,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt +44: [2022-12-03 10:45:51,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +26: [2022-12-03 10:45:51,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-12-03 10:45:51,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-12-03 10:45:51,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +42: [2022-12-03 10:45:51,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt. +42: [2022-12-03 10:45:51,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt +42: [2022-12-03 10:45:51,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +24: [2022-12-03 10:45:51,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-12-03 10:45:51,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-12-03 10:45:51,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +22: [2022-12-03 10:45:51,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-12-03 10:45:51,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-12-03 10:45:51,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +11: [2022-12-03 10:45:51,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-12-03 10:45:51,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-12-03 10:45:51,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +14: [2022-12-03 10:45:51,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-12-03 10:45:51,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-12-03 10:45:51,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +46: [2022-12-03 10:45:51,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt. +46: [2022-12-03 10:45:51,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt +46: [2022-12-03 10:45:51,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 6: [2022-12-03 10:45:51,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-12-03 10:45:51,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-12-03 10:45:51,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 5: [2022-12-03 10:45:51,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-12-03 10:45:51,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-12-03 10:45:51,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-12-03 10:45:51,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-12-03 10:45:51,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-12-03 10:45:51,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-12-03 10:45:51,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-12-03 10:45:51,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-12-03 10:45:51,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-12-03 10:45:51,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-12-03 10:45:51,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-12-03 10:45:51,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-12-03 10:45:51,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-12-03 10:45:51,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-12-03 10:45:51,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-12-03 10:45:51,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-12-03 10:45:51,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 5: [2022-12-03 10:45:51,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 5: [2022-12-03 10:45:51,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 5: [2022-12-03 10:45:51,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 5: [2022-12-03 10:45:51,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 5: [2022-12-03 10:45:51,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 5: [2022-12-03 10:45:51,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 5: [2022-12-03 10:45:51,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +54: [2022-12-03 10:45:51,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt. +54: [2022-12-03 10:45:51,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt +54: [2022-12-03 10:45:51,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +57: [2022-12-03 10:45:51,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt. +57: [2022-12-03 10:45:51,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt +57: [2022-12-03 10:45:51,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +30: [2022-12-03 10:45:51,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-12-03 10:45:51,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-12-03 10:45:51,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +13: [2022-12-03 10:45:51,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-12-03 10:45:51,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-12-03 10:45:51,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +49: [2022-12-03 10:45:51,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt. +49: [2022-12-03 10:45:51,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt +49: [2022-12-03 10:45:51,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +15: [2022-12-03 10:45:51,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-12-03 10:45:51,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-12-03 10:45:51,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +37: [2022-12-03 10:45:51,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt. +37: [2022-12-03 10:45:51,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt +37: [2022-12-03 10:45:51,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 2: [2022-12-03 10:45:51,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-12-03 10:45:51,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-12-03 10:45:51,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +50: [2022-12-03 10:45:51,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt. +50: [2022-12-03 10:45:51,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt +50: [2022-12-03 10:45:51,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +51: [2022-12-03 10:45:51,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt. +51: [2022-12-03 10:45:51,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt +51: [2022-12-03 10:45:51,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +59: [2022-12-03 10:45:51,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt. +59: [2022-12-03 10:45:51,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt +59: [2022-12-03 10:45:51,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +36: [2022-12-03 10:45:51,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt. +36: [2022-12-03 10:45:51,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt +36: [2022-12-03 10:45:51,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 8: [2022-12-03 10:45:51,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-12-03 10:45:51,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-12-03 10:45:51,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +40: [2022-12-03 10:45:51,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt. +40: [2022-12-03 10:45:51,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt +40: [2022-12-03 10:45:51,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +12: [2022-12-03 10:45:51,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-12-03 10:45:51,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-12-03 10:45:51,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +60: [2022-12-03 10:45:51,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt. +60: [2022-12-03 10:45:51,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt +60: [2022-12-03 10:45:51,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +10: [2022-12-03 10:45:51,733] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-12-03 10:45:51,733] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-12-03 10:45:51,733] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +33: [2022-12-03 10:45:51,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt. +33: [2022-12-03 10:45:51,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt +33: [2022-12-03 10:45:51,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +56: [2022-12-03 10:45:51,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt. +56: [2022-12-03 10:45:51,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt +56: [2022-12-03 10:45:51,738] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +63: [2022-12-03 10:45:51,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt. +48: [2022-12-03 10:45:51,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt. +63: [2022-12-03 10:45:51,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt +48: [2022-12-03 10:45:51,739] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt +63: [2022-12-03 10:45:51,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +48: [2022-12-03 10:45:51,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +29: [2022-12-03 10:45:51,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-12-03 10:45:51,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-12-03 10:45:51,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +23: [2022-12-03 10:45:51,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-12-03 10:45:51,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-12-03 10:45:51,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +53: [2022-12-03 10:45:51,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt. +53: [2022-12-03 10:45:51,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt +53: [2022-12-03 10:45:51,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +61: [2022-12-03 10:45:51,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt. +61: [2022-12-03 10:45:51,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt +61: [2022-12-03 10:45:51,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +25: [2022-12-03 10:45:51,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-12-03 10:45:51,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-12-03 10:45:51,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 4: [2022-12-03 10:45:51,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-12-03 10:45:51,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-12-03 10:45:51,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 7: [2022-12-03 10:45:51,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-12-03 10:45:51,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-12-03 10:45:51,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +21: [2022-12-03 10:45:51,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-12-03 10:45:51,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-12-03 10:45:51,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +52: [2022-12-03 10:45:51,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt. +52: [2022-12-03 10:45:51,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt +52: [2022-12-03 10:45:51,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +39: [2022-12-03 10:45:51,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt. +39: [2022-12-03 10:45:51,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt +39: [2022-12-03 10:45:51,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 3: [2022-12-03 10:45:51,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-12-03 10:45:51,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-12-03 10:45:51,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +43: [2022-12-03 10:45:51,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt. +43: [2022-12-03 10:45:51,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt +43: [2022-12-03 10:45:51,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +38: [2022-12-03 10:45:51,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt. +38: [2022-12-03 10:45:51,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt +38: [2022-12-03 10:45:51,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +16: [2022-12-03 10:45:51,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-12-03 10:45:51,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-12-03 10:45:51,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +45: [2022-12-03 10:45:51,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt. +45: [2022-12-03 10:45:51,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt +45: [2022-12-03 10:45:51,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 1: [2022-12-03 10:45:51,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-12-03 10:45:51,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-12-03 10:45:51,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 9: [2022-12-03 10:45:51,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-12-03 10:45:51,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-12-03 10:45:51,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +47: [2022-12-03 10:45:51,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt. +47: [2022-12-03 10:45:51,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt +47: [2022-12-03 10:45:51,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +28: [2022-12-03 10:45:51,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-12-03 10:45:51,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-12-03 10:45:51,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +31: [2022-12-03 10:45:51,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-12-03 10:45:51,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-12-03 10:45:51,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +58: [2022-12-03 10:45:51,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt. +58: [2022-12-03 10:45:51,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt +19: [2022-12-03 10:45:51,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +58: [2022-12-03 10:45:51,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +55: [2022-12-03 10:45:51,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt. +55: [2022-12-03 10:45:51,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt +55: [2022-12-03 10:45:51,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +34: [2022-12-03 10:45:51,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt. +34: [2022-12-03 10:45:51,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt +34: [2022-12-03 10:45:51,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +62: [2022-12-03 10:45:51,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt. +62: [2022-12-03 10:45:51,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt +18: [2022-12-03 10:45:51,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +62: [2022-12-03 10:45:51,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +18: [2022-12-03 10:45:51,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-12-03 10:45:51,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +35: [2022-12-03 10:45:51,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt. +35: [2022-12-03 10:45:51,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt +35: [2022-12-03 10:45:51,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +19: [2022-12-03 10:45:51,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-12-03 10:45:51,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +20: [2022-12-03 10:45:51,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-12-03 10:45:51,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-12-03 10:45:51,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +51: [2022-12-03 10:45:51,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt. +51: [2022-12-03 10:45:51,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt +51: [2022-12-03 10:45:51,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +46: [2022-12-03 10:45:51,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt. +46: [2022-12-03 10:45:51,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt +46: [2022-12-03 10:45:51,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +26: [2022-12-03 10:45:51,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-12-03 10:45:51,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-12-03 10:45:51,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +42: [2022-12-03 10:45:51,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt. +42: [2022-12-03 10:45:51,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt +42: [2022-12-03 10:45:51,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +24: [2022-12-03 10:45:51,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-12-03 10:45:51,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-12-03 10:45:51,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +44: [2022-12-03 10:45:51,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt. +44: [2022-12-03 10:45:51,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt +44: [2022-12-03 10:45:51,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +27: [2022-12-03 10:45:51,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-12-03 10:45:51,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-12-03 10:45:51,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +17: [2022-12-03 10:45:51,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +30: [2022-12-03 10:45:51,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +17: [2022-12-03 10:45:51,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +30: [2022-12-03 10:45:51,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +17: [2022-12-03 10:45:51,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +30: [2022-12-03 10:45:51,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +11: [2022-12-03 10:45:51,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-12-03 10:45:51,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-12-03 10:45:51,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +41: [2022-12-03 10:45:51,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt. +41: [2022-12-03 10:45:51,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt +41: [2022-12-03 10:45:51,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +14: [2022-12-03 10:45:51,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-12-03 10:45:51,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-12-03 10:45:51,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +49: [2022-12-03 10:45:51,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt. +49: [2022-12-03 10:45:51,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt +49: [2022-12-03 10:45:51,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 6: [2022-12-03 10:45:51,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-12-03 10:45:51,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-12-03 10:45:51,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +22: [2022-12-03 10:45:51,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-12-03 10:45:51,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-12-03 10:45:51,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +54: [2022-12-03 10:45:51,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt. +54: [2022-12-03 10:45:51,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt +54: [2022-12-03 10:45:51,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +36: [2022-12-03 10:45:51,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt. +36: [2022-12-03 10:45:51,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt +36: [2022-12-03 10:45:51,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +59: [2022-12-03 10:45:51,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt. +59: [2022-12-03 10:45:51,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt +59: [2022-12-03 10:45:51,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +33: [2022-12-03 10:45:51,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt. +33: [2022-12-03 10:45:51,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt +33: [2022-12-03 10:45:51,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +60: [2022-12-03 10:45:51,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt. +60: [2022-12-03 10:45:51,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt +60: [2022-12-03 10:45:51,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +23: [2022-12-03 10:45:51,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-12-03 10:45:51,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-12-03 10:45:51,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +56: [2022-12-03 10:45:51,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt. +56: [2022-12-03 10:45:51,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt +56: [2022-12-03 10:45:51,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +13: [2022-12-03 10:45:51,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-12-03 10:45:51,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-12-03 10:45:51,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +48: [2022-12-03 10:45:51,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt. +48: [2022-12-03 10:45:51,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt +48: [2022-12-03 10:45:51,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +53: [2022-12-03 10:45:51,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt. +53: [2022-12-03 10:45:51,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt +50: [2022-12-03 10:45:51,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt. +53: [2022-12-03 10:45:51,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +50: [2022-12-03 10:45:51,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt +50: [2022-12-03 10:45:51,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 2: [2022-12-03 10:45:51,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +12: [2022-12-03 10:45:51,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. + 2: [2022-12-03 10:45:51,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-12-03 10:45:51,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +12: [2022-12-03 10:45:51,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-12-03 10:45:51,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +10: [2022-12-03 10:45:51,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-12-03 10:45:51,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-12-03 10:45:51,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +63: [2022-12-03 10:45:51,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt. +63: [2022-12-03 10:45:51,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt +63: [2022-12-03 10:45:51,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +37: [2022-12-03 10:45:51,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt. +37: [2022-12-03 10:45:51,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt +37: [2022-12-03 10:45:51,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +40: [2022-12-03 10:45:51,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt. +40: [2022-12-03 10:45:51,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt +40: [2022-12-03 10:45:51,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +29: [2022-12-03 10:45:51,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-12-03 10:45:51,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-12-03 10:45:51,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +61: [2022-12-03 10:45:51,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt. +61: [2022-12-03 10:45:51,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt +61: [2022-12-03 10:45:51,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +57: [2022-12-03 10:45:51,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt. +57: [2022-12-03 10:45:51,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt +57: [2022-12-03 10:45:51,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 8: [2022-12-03 10:45:51,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. +15: [2022-12-03 10:45:51,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-12-03 10:45:51,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-12-03 10:45:51,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +52: [2022-12-03 10:45:51,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt. +52: [2022-12-03 10:45:51,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt +52: [2022-12-03 10:45:51,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +25: [2022-12-03 10:45:51,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-12-03 10:45:51,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-12-03 10:45:51,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 4: [2022-12-03 10:45:51,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-12-03 10:45:51,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-12-03 10:45:51,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 8: [2022-12-03 10:45:51,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-12-03 10:45:51,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 9: [2022-12-03 10:45:51,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-12-03 10:45:51,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-12-03 10:45:51,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +43: [2022-12-03 10:45:51,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt. +43: [2022-12-03 10:45:51,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt +43: [2022-12-03 10:45:51,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +39: [2022-12-03 10:45:51,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt. +39: [2022-12-03 10:45:51,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt +39: [2022-12-03 10:45:51,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +19: [2022-12-03 10:45:51,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +55: [2022-12-03 10:45:51,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt. +19: [2022-12-03 10:45:51,804] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +55: [2022-12-03 10:45:51,804] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt +19: [2022-12-03 10:45:51,804] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +55: [2022-12-03 10:45:51,804] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +18: [2022-12-03 10:45:51,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-12-03 10:45:51,804] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-12-03 10:45:51,804] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +47: [2022-12-03 10:45:51,805] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt. +47: [2022-12-03 10:45:51,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt +47: [2022-12-03 10:45:51,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +45: [2022-12-03 10:45:51,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt. +45: [2022-12-03 10:45:51,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt +45: [2022-12-03 10:45:51,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +28: [2022-12-03 10:45:51,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-12-03 10:45:51,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-12-03 10:45:51,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +31: [2022-12-03 10:45:51,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-12-03 10:45:51,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-12-03 10:45:51,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +38: [2022-12-03 10:45:51,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt. +38: [2022-12-03 10:45:51,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt +38: [2022-12-03 10:45:51,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 7: [2022-12-03 10:45:51,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-12-03 10:45:51,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-12-03 10:45:51,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +16: [2022-12-03 10:45:51,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. + 3: [2022-12-03 10:45:51,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +16: [2022-12-03 10:45:51,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt + 3: [2022-12-03 10:45:51,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +16: [2022-12-03 10:45:51,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 3: [2022-12-03 10:45:51,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 1: [2022-12-03 10:45:51,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-12-03 10:45:51,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-12-03 10:45:51,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +34: [2022-12-03 10:45:51,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt. +34: [2022-12-03 10:45:51,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt +34: [2022-12-03 10:45:51,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +27: [2022-12-03 10:45:51,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-12-03 10:45:51,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-12-03 10:45:51,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +46: [2022-12-03 10:45:51,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt. +46: [2022-12-03 10:45:51,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt +46: [2022-12-03 10:45:51,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +20: [2022-12-03 10:45:51,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +62: [2022-12-03 10:45:51,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt. +62: [2022-12-03 10:45:51,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt +20: [2022-12-03 10:45:51,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +62: [2022-12-03 10:45:51,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +20: [2022-12-03 10:45:51,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +21: [2022-12-03 10:45:51,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-12-03 10:45:51,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-12-03 10:45:51,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +30: [2022-12-03 10:45:51,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-12-03 10:45:51,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-12-03 10:45:51,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +26: [2022-12-03 10:45:51,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-12-03 10:45:51,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-12-03 10:45:51,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +44: [2022-12-03 10:45:51,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt. +44: [2022-12-03 10:45:51,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt +44: [2022-12-03 10:45:51,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +24: [2022-12-03 10:45:51,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-12-03 10:45:51,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-12-03 10:45:51,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +11: [2022-12-03 10:45:51,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-12-03 10:45:51,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-12-03 10:45:51,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +41: [2022-12-03 10:45:51,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt. +41: [2022-12-03 10:45:51,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt +41: [2022-12-03 10:45:51,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +51: [2022-12-03 10:45:51,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt. +51: [2022-12-03 10:45:51,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt +51: [2022-12-03 10:45:51,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +42: [2022-12-03 10:45:51,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt. +42: [2022-12-03 10:45:51,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt +42: [2022-12-03 10:45:51,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +35: [2022-12-03 10:45:51,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt. +35: [2022-12-03 10:45:51,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt +35: [2022-12-03 10:45:51,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +14: [2022-12-03 10:45:51,828] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-12-03 10:45:51,828] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-12-03 10:45:51,828] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +54: [2022-12-03 10:45:51,828] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt. +54: [2022-12-03 10:45:51,828] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt +54: [2022-12-03 10:45:51,828] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +49: [2022-12-03 10:45:51,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt. +49: [2022-12-03 10:45:51,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt +49: [2022-12-03 10:45:51,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +22: [2022-12-03 10:45:51,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +22: [2022-12-03 10:45:51,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +22: [2022-12-03 10:45:51,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +17: [2022-12-03 10:45:51,833] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-12-03 10:45:51,833] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-12-03 10:45:51,833] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +59: [2022-12-03 10:45:51,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt. +59: [2022-12-03 10:45:51,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt +59: [2022-12-03 10:45:51,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +50: [2022-12-03 10:45:51,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt. +50: [2022-12-03 10:45:51,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt +50: [2022-12-03 10:45:51,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 6: [2022-12-03 10:45:51,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-12-03 10:45:51,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-12-03 10:45:51,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +36: [2022-12-03 10:45:51,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt. +36: [2022-12-03 10:45:51,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt +36: [2022-12-03 10:45:51,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +48: [2022-12-03 10:45:51,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt. +48: [2022-12-03 10:45:51,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt +48: [2022-12-03 10:45:51,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +37: [2022-12-03 10:45:51,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt. +37: [2022-12-03 10:45:51,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt +37: [2022-12-03 10:45:51,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 8: [2022-12-03 10:45:51,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-12-03 10:45:51,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-12-03 10:45:51,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +57: [2022-12-03 10:45:51,840] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt. +57: [2022-12-03 10:45:51,840] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt +57: [2022-12-03 10:45:51,840] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +43: [2022-12-03 10:45:51,840] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt. +43: [2022-12-03 10:45:51,840] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt +43: [2022-12-03 10:45:51,840] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +13: [2022-12-03 10:45:51,840] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-12-03 10:45:51,841] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-12-03 10:45:51,841] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +23: [2022-12-03 10:45:51,841] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-12-03 10:45:51,842] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-12-03 10:45:51,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 2: [2022-12-03 10:45:51,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +63: [2022-12-03 10:45:51,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt. + 2: [2022-12-03 10:45:51,842] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +63: [2022-12-03 10:45:51,842] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt + 2: [2022-12-03 10:45:51,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +63: [2022-12-03 10:45:51,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +60: [2022-12-03 10:45:51,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt. +60: [2022-12-03 10:45:51,842] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt +60: [2022-12-03 10:45:51,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +10: [2022-12-03 10:45:51,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-12-03 10:45:51,844] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-12-03 10:45:51,844] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +12: [2022-12-03 10:45:51,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-12-03 10:45:51,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-12-03 10:45:51,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +25: [2022-12-03 10:45:51,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +56: [2022-12-03 10:45:51,846] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt. +56: [2022-12-03 10:45:51,846] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt +56: [2022-12-03 10:45:51,846] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +55: [2022-12-03 10:45:51,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt. +55: [2022-12-03 10:45:51,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt +55: [2022-12-03 10:45:51,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +40: [2022-12-03 10:45:51,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt. +40: [2022-12-03 10:45:51,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt +40: [2022-12-03 10:45:51,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +53: [2022-12-03 10:45:51,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt. +53: [2022-12-03 10:45:51,849] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt +53: [2022-12-03 10:45:51,849] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +25: [2022-12-03 10:45:51,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-12-03 10:45:51,846] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +15: [2022-12-03 10:45:51,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-12-03 10:45:51,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-12-03 10:45:51,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +47: [2022-12-03 10:45:51,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt. +47: [2022-12-03 10:45:51,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt +61: [2022-12-03 10:45:51,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt. +47: [2022-12-03 10:45:51,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +61: [2022-12-03 10:45:51,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt +61: [2022-12-03 10:45:51,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 4: [2022-12-03 10:45:51,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-12-03 10:45:51,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-12-03 10:45:51,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +29: [2022-12-03 10:45:51,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-12-03 10:45:51,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-12-03 10:45:51,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +39: [2022-12-03 10:45:51,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt. +39: [2022-12-03 10:45:51,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt +39: [2022-12-03 10:45:51,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +31: [2022-12-03 10:45:51,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-12-03 10:45:51,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-12-03 10:45:51,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 7: [2022-12-03 10:45:51,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-12-03 10:45:51,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-12-03 10:45:51,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +19: [2022-12-03 10:45:51,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +52: [2022-12-03 10:45:51,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt. +52: [2022-12-03 10:45:51,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt +52: [2022-12-03 10:45:51,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +38: [2022-12-03 10:45:51,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt. +16: [2022-12-03 10:45:51,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +38: [2022-12-03 10:45:51,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt +38: [2022-12-03 10:45:51,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +16: [2022-12-03 10:45:51,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-12-03 10:45:51,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 9: [2022-12-03 10:45:51,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-12-03 10:45:51,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-12-03 10:45:51,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 3: [2022-12-03 10:45:51,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-12-03 10:45:51,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-12-03 10:45:51,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +35: [2022-12-03 10:45:51,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt. +62: [2022-12-03 10:45:51,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt. +62: [2022-12-03 10:45:51,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt +35: [2022-12-03 10:45:51,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt +62: [2022-12-03 10:45:51,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +35: [2022-12-03 10:45:51,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +45: [2022-12-03 10:45:51,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt. +45: [2022-12-03 10:45:51,865] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt +45: [2022-12-03 10:45:51,865] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +18: [2022-12-03 10:45:51,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-12-03 10:45:51,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-12-03 10:45:51,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +19: [2022-12-03 10:45:51,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-12-03 10:45:51,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +33: [2022-12-03 10:45:51,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt. +33: [2022-12-03 10:45:51,867] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt +33: [2022-12-03 10:45:51,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 1: [2022-12-03 10:45:51,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-12-03 10:45:51,868] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-12-03 10:45:51,868] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +46: [2022-12-03 10:45:51,874] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt. +46: [2022-12-03 10:45:51,874] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt +46: [2022-12-03 10:45:51,874] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +34: [2022-12-03 10:45:51,877] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt. +34: [2022-12-03 10:45:51,877] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt +34: [2022-12-03 10:45:51,877] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +17: [2022-12-03 10:45:51,877] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-12-03 10:45:51,877] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-12-03 10:45:51,877] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +30: [2022-12-03 10:45:51,880] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +51: [2022-12-03 10:45:51,881] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt. +51: [2022-12-03 10:45:51,881] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt +51: [2022-12-03 10:45:51,881] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +24: [2022-12-03 10:45:51,882] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-12-03 10:45:51,882] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-12-03 10:45:51,882] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +30: [2022-12-03 10:45:51,880] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-12-03 10:45:51,880] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +28: [2022-12-03 10:45:51,883] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-12-03 10:45:51,883] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-12-03 10:45:51,883] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +41: [2022-12-03 10:45:51,886] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt. +41: [2022-12-03 10:45:51,886] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt +41: [2022-12-03 10:45:51,886] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +42: [2022-12-03 10:45:51,886] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt. +42: [2022-12-03 10:45:51,887] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt +42: [2022-12-03 10:45:51,887] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +27: [2022-12-03 10:45:51,887] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-12-03 10:45:51,887] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-12-03 10:45:51,887] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +54: [2022-12-03 10:45:51,886] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt. +54: [2022-12-03 10:45:51,886] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt +54: [2022-12-03 10:45:51,886] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +11: [2022-12-03 10:45:51,889] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-12-03 10:45:51,889] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-12-03 10:45:51,889] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +21: [2022-12-03 10:45:51,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-12-03 10:45:51,891] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-12-03 10:45:51,891] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +26: [2022-12-03 10:45:51,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +48: [2022-12-03 10:45:51,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt. +26: [2022-12-03 10:45:51,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +48: [2022-12-03 10:45:51,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt +26: [2022-12-03 10:45:51,893] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +48: [2022-12-03 10:45:51,892] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +44: [2022-12-03 10:45:51,893] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt. +44: [2022-12-03 10:45:51,893] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt +44: [2022-12-03 10:45:51,893] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +14: [2022-12-03 10:45:51,898] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-12-03 10:45:51,898] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-12-03 10:45:51,898] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +59: [2022-12-03 10:45:51,900] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt. +59: [2022-12-03 10:45:51,900] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt +59: [2022-12-03 10:45:51,900] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +50: [2022-12-03 10:45:51,900] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt. +50: [2022-12-03 10:45:51,900] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt +50: [2022-12-03 10:45:51,900] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 2: [2022-12-03 10:45:51,902] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-12-03 10:45:51,902] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-12-03 10:45:51,902] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 6: [2022-12-03 10:45:51,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-12-03 10:45:51,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-12-03 10:45:51,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +60: [2022-12-03 10:45:51,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt. +63: [2022-12-03 10:45:51,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt. +36: [2022-12-03 10:45:51,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt. +60: [2022-12-03 10:45:51,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt +63: [2022-12-03 10:45:51,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt +36: [2022-12-03 10:45:51,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt +60: [2022-12-03 10:45:51,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +63: [2022-12-03 10:45:51,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +36: [2022-12-03 10:45:51,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +49: [2022-12-03 10:45:51,905] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt. +49: [2022-12-03 10:45:51,905] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt +49: [2022-12-03 10:45:51,905] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +37: [2022-12-03 10:45:51,906] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt. +37: [2022-12-03 10:45:51,906] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt +37: [2022-12-03 10:45:51,906] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +12: [2022-12-03 10:45:51,906] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-12-03 10:45:51,906] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-12-03 10:45:51,906] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +33: [2022-12-03 10:45:51,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt. +33: [2022-12-03 10:45:51,907] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt +33: [2022-12-03 10:45:51,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +53: [2022-12-03 10:45:51,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt. +19: [2022-12-03 10:45:51,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +53: [2022-12-03 10:45:51,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt +53: [2022-12-03 10:45:51,908] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +56: [2022-12-03 10:45:51,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt. +56: [2022-12-03 10:45:51,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt +56: [2022-12-03 10:45:51,908] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +61: [2022-12-03 10:45:51,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt. +61: [2022-12-03 10:45:51,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt +61: [2022-12-03 10:45:51,908] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +39: [2022-12-03 10:45:51,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt. +39: [2022-12-03 10:45:51,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt +39: [2022-12-03 10:45:51,909] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +19: [2022-12-03 10:45:51,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-12-03 10:45:51,908] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 9: [2022-12-03 10:45:51,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-12-03 10:45:51,909] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-12-03 10:45:51,909] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +23: [2022-12-03 10:45:51,910] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-12-03 10:45:51,910] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-12-03 10:45:51,910] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +43: [2022-12-03 10:45:51,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt. +43: [2022-12-03 10:45:51,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt +43: [2022-12-03 10:45:51,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +55: [2022-12-03 10:45:51,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt. +20: [2022-12-03 10:45:51,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +55: [2022-12-03 10:45:51,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt +55: [2022-12-03 10:45:51,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +20: [2022-12-03 10:45:51,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-12-03 10:45:51,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 7: [2022-12-03 10:45:51,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-12-03 10:45:51,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-12-03 10:45:51,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +13: [2022-12-03 10:45:51,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-12-03 10:45:51,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-12-03 10:45:51,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +53: [2022-12-03 10:45:51,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt. +53: [2022-12-03 10:45:51,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt +53: [2022-12-03 10:45:51,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +52: [2022-12-03 10:45:51,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt. +52: [2022-12-03 10:45:51,914] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt +52: [2022-12-03 10:45:51,914] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +15: [2022-12-03 10:45:51,914] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-12-03 10:45:51,914] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-12-03 10:45:51,914] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +19: [2022-12-03 10:45:51,914] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-12-03 10:45:51,914] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-12-03 10:45:51,914] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +25: [2022-12-03 10:45:51,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-12-03 10:45:51,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-12-03 10:45:51,915] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +21: [2022-12-03 10:45:51,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-12-03 10:45:51,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-12-03 10:45:51,915] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +20: [2022-12-03 10:45:51,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-12-03 10:45:51,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-12-03 10:45:51,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +10: [2022-12-03 10:45:51,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-12-03 10:45:51,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-12-03 10:45:51,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +16: [2022-12-03 10:45:51,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +49: [2022-12-03 10:45:51,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt. +16: [2022-12-03 10:45:51,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +49: [2022-12-03 10:45:51,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt +49: [2022-12-03 10:45:51,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +16: [2022-12-03 10:45:51,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +44: [2022-12-03 10:45:51,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt. +47: [2022-12-03 10:45:51,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt. +47: [2022-12-03 10:45:51,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt +26: [2022-12-03 10:45:51,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +44: [2022-12-03 10:45:51,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt +47: [2022-12-03 10:45:51,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +26: [2022-12-03 10:45:51,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +44: [2022-12-03 10:45:51,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +26: [2022-12-03 10:45:51,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 6: [2022-12-03 10:45:51,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-12-03 10:45:51,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-12-03 10:45:51,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 8: [2022-12-03 10:45:51,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-12-03 10:45:51,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-12-03 10:45:51,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +24: [2022-12-03 10:45:51,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-12-03 10:45:51,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-12-03 10:45:51,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +28: [2022-12-03 10:45:51,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-12-03 10:45:51,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-12-03 10:45:51,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +27: [2022-12-03 10:45:51,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-12-03 10:45:51,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +42: [2022-12-03 10:45:51,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt. +27: [2022-12-03 10:45:51,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +57: [2022-12-03 10:45:51,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt. +42: [2022-12-03 10:45:51,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt +57: [2022-12-03 10:45:51,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt +57: [2022-12-03 10:45:51,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +42: [2022-12-03 10:45:51,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +22: [2022-12-03 10:45:51,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-12-03 10:45:51,919] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-12-03 10:45:51,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +21: [2022-12-03 10:45:51,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-12-03 10:45:51,919] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-12-03 10:45:51,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +29: [2022-12-03 10:45:51,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +54: [2022-12-03 10:45:51,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt. +54: [2022-12-03 10:45:51,919] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt +54: [2022-12-03 10:45:51,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +29: [2022-12-03 10:45:51,919] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-12-03 10:45:51,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +10: [2022-12-03 10:45:51,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-12-03 10:45:51,919] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +29: [2022-12-03 10:45:51,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +10: [2022-12-03 10:45:51,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +29: [2022-12-03 10:45:51,919] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-12-03 10:45:51,920] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +23: [2022-12-03 10:45:51,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +12: [2022-12-03 10:45:51,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +23: [2022-12-03 10:45:51,920] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-12-03 10:45:51,920] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +12: [2022-12-03 10:45:51,920] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +30: [2022-12-03 10:45:51,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +12: [2022-12-03 10:45:51,920] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +30: [2022-12-03 10:45:51,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-12-03 10:45:51,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +38: [2022-12-03 10:45:51,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt. +38: [2022-12-03 10:45:51,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt. +38: [2022-12-03 10:45:51,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt +38: [2022-12-03 10:45:51,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt +38: [2022-12-03 10:45:51,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +38: [2022-12-03 10:45:51,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +41: [2022-12-03 10:45:51,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt. +41: [2022-12-03 10:45:51,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt +41: [2022-12-03 10:45:51,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 9: [2022-12-03 10:45:51,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-12-03 10:45:51,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-12-03 10:45:51,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 4: [2022-12-03 10:45:51,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-12-03 10:45:51,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-12-03 10:45:51,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +45: [2022-12-03 10:45:51,923] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt. +45: [2022-12-03 10:45:51,923] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt +45: [2022-12-03 10:45:51,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +62: [2022-12-03 10:45:51,923] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt. +62: [2022-12-03 10:45:51,923] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt +62: [2022-12-03 10:45:51,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 3: [2022-12-03 10:45:51,924] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-12-03 10:45:51,924] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-12-03 10:45:51,924] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +11: [2022-12-03 10:45:51,924] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-12-03 10:45:51,925] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-12-03 10:45:51,925] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +14: [2022-12-03 10:45:51,925] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. + 2: [2022-12-03 10:45:51,925] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +14: [2022-12-03 10:45:51,925] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt + 2: [2022-12-03 10:45:51,925] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-12-03 10:45:51,925] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +14: [2022-12-03 10:45:51,925] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +31: [2022-12-03 10:45:51,926] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-12-03 10:45:51,926] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +18: [2022-12-03 10:45:51,926] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +31: [2022-12-03 10:45:51,926] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-12-03 10:45:51,926] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +18: [2022-12-03 10:45:51,926] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +31: [2022-12-03 10:45:51,926] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +18: [2022-12-03 10:45:51,926] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +31: [2022-12-03 10:45:51,926] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +28: [2022-12-03 10:45:51,926] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-12-03 10:45:51,926] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-12-03 10:45:51,926] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +25: [2022-12-03 10:45:51,926] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-12-03 10:45:51,927] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-12-03 10:45:51,927] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +15: [2022-12-03 10:45:51,927] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +18: [2022-12-03 10:45:51,926] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +15: [2022-12-03 10:45:51,927] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +18: [2022-12-03 10:45:51,927] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +15: [2022-12-03 10:45:51,927] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +18: [2022-12-03 10:45:51,927] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 8: [2022-12-03 10:45:51,927] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-12-03 10:45:51,927] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-12-03 10:45:51,927] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +57: [2022-12-03 10:45:51,928] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt. +57: [2022-12-03 10:45:51,928] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt +57: [2022-12-03 10:45:51,928] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +13: [2022-12-03 10:45:51,928] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-12-03 10:45:51,928] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-12-03 10:45:51,928] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 1: [2022-12-03 10:45:51,928] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-12-03 10:45:51,929] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-12-03 10:45:51,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 3: [2022-12-03 10:45:51,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-12-03 10:45:51,929] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-12-03 10:45:51,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 4: [2022-12-03 10:45:51,930] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +17: [2022-12-03 10:45:51,930] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. + 4: [2022-12-03 10:45:51,930] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-12-03 10:45:51,930] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +17: [2022-12-03 10:45:51,930] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-12-03 10:45:51,930] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 1: [2022-12-03 10:45:51,930] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-12-03 10:45:51,930] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-12-03 10:45:51,930] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +22: [2022-12-03 10:45:51,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-12-03 10:45:51,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977boscar/global_step73814/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-12-03 10:45:51,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 0: successfully saved checkpoint at iteration 73814 to checkpoints_3b977boscar +63: ------------------------------------------------------------------------------------------------------------ +63: test loss at the end of training for test data | lm loss value: 1.857570E+00 | lm loss PPL: 6.408148E+00 | +63: ------------------------------------------------------------------------------------------------------------ +END 2096637: Sat Dec 3 10:46:10 EET 2022 diff --git a/3b977b77b/sbatch_3b9_77b_oscar.sh b/3b977b77b/sbatch_3b9_77b_oscar.sh new file mode 100644 index 0000000000000000000000000000000000000000..9f69a691ef731c96efc793f25174ae2fc5974b13 --- /dev/null +++ b/3b977b77b/sbatch_3b9_77b_oscar.sh @@ -0,0 +1,159 @@ +#!/bin/bash +#SBATCH --exclude=nid007571,nid007112,nid006774,nid007502,nid007506,nid007507,nid005145,nid006692,nid007218,nid007123,nid006124,nid006123,nid007496,nid007237,nid006852,nid007206,nid006947,nid007212,nid006977,nid007222,nid005444,nid007219,nid007493,nid007221,nid005300,nid005619,nid006118,nid005203,nid006113,nid006481,nid007077,nid005208,nid005207,nid005879,nid005901 +#SBATCH --nodes=64 +#SBATCH --ntasks-per-node=1 +#SBATCH --cpus-per-task=32 +#SBATCH --mem=256G +#SBATCH -p pilot +#SBATCH -t 48:00:00 +#SBATCH --gpus-per-node=mi250:8 +#SBATCH --exclusive=user +#SBATCH --hint=nomultithread +#SBATCH --account=project_462000119 +#SBATCH -o logs/%j.out +#SBATCH -e logs/%j.err + +VARIANT=3b977boscar + +# if run without sbatch, invoke here +if [ -z $SLURM_JOB_ID ]; then + mkdir -p logs + sbatch "$0" + exit +fi + +set -euo pipefail + +# symlink logs/latest.out and logs/latest.err +ln -f -s $SLURM_JOB_ID.out logs/latest.out +ln -f -s $SLURM_JOB_ID.err logs/latest.err + +KILL_SWITCH_PATH=kill-switch-$VARIANT +CHECKPOINT_PATH=checkpoints_$VARIANT +TENSORBOARD_PATH=tensorboard_$VARIANT + +# Data +VOCAB_FILE="gpt2/vocab.json" +MERGE_FILE="gpt2/merges.txt" +DATA_PATH="/scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document" + +PP_SIZE=2 +TP_SIZE=1 + +MICRO_BATCH_SIZE=1 +GRADIENT_ACCUMULATION_STEPS=1 +WORLD_SIZE=$((SLURM_GPUS_ON_NODE*SLURM_JOB_NUM_NODES)) +GLOBAL_BATCH_SIZE=$((MICRO_BATCH_SIZE*WORLD_SIZE*GRADIENT_ACCUMULATION_STEPS)) + +# Model parameters +source model_params.sh +MODEL_PARAM=("${PARAM_4084M[@]}") +NHIDDEN=${MODEL_PARAM[0]} +FFN_HIDDEN_SIZE=${MODEL_PARAM[1]} +KV_SIZE=${MODEL_PARAM[2]} +NHEADS=${MODEL_PARAM[3]} +NLAYERS=${MODEL_PARAM[4]} +SEQ_LEN=2048 + +echo "Model parameters: d_model $NHIDDEN ffw_size $FFN_HIDDEN_SIZE kv_size $KV_SIZE n_heads $NHEADS n_layers $NLAYERS" + +SAVE_INTERVAL=10000 + +# Tokens: 77_400_000_000 +# -> Samples: 37792969 +TRAIN_SAMPLES=37_792_969 + +OPTIMIZER_ARGS=" \ + --optimizer adam \ + --adam-beta1 0.9 \ + --adam-beta2 0.999 \ + --adam-eps 1e-8 \ + --lr 2e-4 \ + --min-lr 2e-5 \ + --lr-decay-style cosine \ + --lr-decay-samples $TRAIN_SAMPLES \ + --lr-warmup-samples 377_930 \ + --clip-grad 1.0 \ + --weight-decay 1e-1 \ + " + +GPT_ARGS=" \ + --num-layers $NLAYERS \ + --hidden-size $NHIDDEN \ + --num-attention-heads $NHEADS \ + --kv-channels $KV_SIZE \ + --ffn-hidden-size $FFN_HIDDEN_SIZE \ + --seq-length $SEQ_LEN \ + --max-position-embeddings $SEQ_LEN \ + --micro-batch-size $MICRO_BATCH_SIZE \ + --global-batch-size $GLOBAL_BATCH_SIZE \ + --train-samples $TRAIN_SAMPLES \ + --vocab-file $VOCAB_FILE \ + --merge-file $MERGE_FILE \ + --clip-grad 1.0 \ + --kill-switch-path $KILL_SWITCH_PATH \ + --bf16 \ + $OPTIMIZER_ARGS \ + " + +OUTPUT_ARGS=" \ + --log-interval 10 \ + --save-interval $SAVE_INTERVAL \ + --eval-interval 1000 \ + --eval-iters 1 \ + --tensorboard-dir $TENSORBOARD_PATH \ + --tensorboard-queue-size 5 \ + --log-timers-to-tensorboard \ + --log-batch-size-to-tensorboard \ + --log-validation-ppl-to-tensorboard \ + " + +ZERO_STAGE=0 + +mkdir -p ds_configs +DS_CONFIG_PATH="ds_configs/$SLURM_JOB_ID.json" + +cat < $DS_CONFIG_PATH +{ + "train_micro_batch_size_per_gpu": $MICRO_BATCH_SIZE, + "train_batch_size": $GLOBAL_BATCH_SIZE, + "gradient_clipping": 1.0, + "zero_optimization": { + "stage": $ZERO_STAGE + }, + "bf16": { + "enabled": true + }, + "steps_per_print": 2000, + "wall_clock_breakdown": false +} +EOF + +DEEPSPEED_ARGS=" \ + --deepspeed \ + --deepspeed_config $DS_CONFIG_PATH \ + --zero-stage $ZERO_STAGE \ + " + +CMD=" \ + Megatron-DeepSpeed/pretrain_gpt.py \ + --tensor-model-parallel-size $TP_SIZE \ + --pipeline-model-parallel-size $PP_SIZE \ + $GPT_ARGS \ + $OUTPUT_ARGS \ + --save $CHECKPOINT_PATH \ + --load $CHECKPOINT_PATH \ + --data-path $DATA_PATH \ + --data-impl mmap \ + --split 949,50,1 \ + $DEEPSPEED_ARGS \ + " + +echo $CMD + +echo "START $SLURM_JOBID: $(date)" + +# bash launch_srun.sh $CMD +srun --label launch.sh $CMD + +echo "END $SLURM_JOBID: $(date)" diff --git a/3b977b77b/tensorboard/events.out.tfevents.1669792928.nid006015.87434.0 b/3b977b77b/tensorboard/events.out.tfevents.1669792928.nid006015.87434.0 new file mode 100644 index 0000000000000000000000000000000000000000..5e6f481be951aa93a16ee1c3d371aa362be7baaa --- /dev/null +++ b/3b977b77b/tensorboard/events.out.tfevents.1669792928.nid006015.87434.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc207bb1543c71f6b809d995d90ee2f3548ae2a7f389b277c4698667bb5695ee +size 19370 diff --git a/3b977b77b/tensorboard/events.out.tfevents.1669794558.nid006740.125659.0 b/3b977b77b/tensorboard/events.out.tfevents.1669794558.nid006740.125659.0 new file mode 100644 index 0000000000000000000000000000000000000000..084183a6bfa7a77c66bb7d87da6f713a66535b07 --- /dev/null +++ b/3b977b77b/tensorboard/events.out.tfevents.1669794558.nid006740.125659.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44a0199500cc3230eee296367e4c2f44aa7464703763df6060ec0a088a084921 +size 19370 diff --git a/3b977b77b/tensorboard/events.out.tfevents.1669887515.nid007234.93167.0 b/3b977b77b/tensorboard/events.out.tfevents.1669887515.nid007234.93167.0 new file mode 100644 index 0000000000000000000000000000000000000000..3bd77c5fc61c291772690b273372aec393d649e7 --- /dev/null +++ b/3b977b77b/tensorboard/events.out.tfevents.1669887515.nid007234.93167.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b59fdd6b60bfd5b15fe1b46a95f9ec118d4dad592dcf1da7e88730a6bdcd41a +size 132346689 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..183463d5c94101ddebca72bc9d9e731c3d95a81a --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb89244718cf5e28d4ab8c56a8979c88502b5081924be77506979576178d89b1 +size 78980887 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e716f21b13b170e85d5051ee7c385f160eb3e397 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1825740d6e26f2490e176947b4d031398191e36f8fc42c8ade7be32629e9a2a +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..17d837e8960fb1ddd039ae16ccc532d9df2149e3 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb6a9828c7e5d645d752abf26108d31e45daa0a3d1a136a901fc59942926acbe +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e40a5bd5a18f113a0401f9926c0a1d1068a3833a --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f8d17f3accd88d0bc26202c2c5508743d5b1c75abd98b2cd57b801b6fcf63f8 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c5a93b2e2a47667d51ce02dbef53d2e38b6467ef --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82792f6706eaf74e7fcd8010e293b774648cc3b10ccd56f259a10ebcf00f981a +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dd6f08e205cdb348f82d9b045a1acf7600f37c7f --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49e553965f3cc38ea516b4b1e7097cbee014b9658eea79dbb8efcca8a94b3bdf +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b158da2f3b214f16364cea1ae31832e3e188752e --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:454f8e0d1790c150e95db82e670ef648616e9d7a9bc3d7b69510e9f9a431ddf0 +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1ff0faef842474aa69e29983bf2dd3906e217f7c --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ffac306babed6b5e9c476c433df3ca768411df38679ad6892862d0bad6f95a4 +size 78980834 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4eba1805968b392acdc11b9867cdd42d560efe3c --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85f93cf96c8ddfee4a7ce7b9600d6ad115bebcd6c3beb6d472c42cdde2e7e551 +size 78981090 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5f5481efe710d9dbd98df38392a0508ae797da16 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94116197c5b2c73e63216a00af5a3f5269ebcf3d4018a04097f50e2de65b3a1a +size 78981026 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..292ae17b23c82c4c3a04b7785b7d54cc5e807296 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa4ea89fae8a54f6f5e8afd084d4a87105d7148c008e272a2fdec5d8829f1928 +size 78981026 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..390530432c536234142934d21b7c6b15b145bf9b --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b54a9a5aea001fc41fa0e4303ab4a12b144972d2eec0b5c5c3accf0e050f4a0 +size 78980951 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..067d5fbacffbe005946a5fa03b27317b091e75e0 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a2587d6cfb0fb39e5aad1eb7a655058bd8d41e451a38e9b68bea9813d8d2987 +size 78980834 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e23180331ac53329ef88ea052c7754ae64067b26 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d4bc250f542594cd0544bfd4d85560eddbfa1c6d5f6eab4c5fa663762cbdf8a +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..308dac4804bcfe6545decb0e2338db10384769e7 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fabdee8ec2d23c52a0475c0a0cf08f20a72fcfec9f3640c8d50503425f4790fc +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0fa7ccc850039c54a0ece2b6111499e0b6a54d46 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cba4a41fcd4f43938167d5e8d334121b6d495bb027a5e026e9dc81bdfb85efc +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5cfa78ae2da09ff20a7db6199eff1fcd808d4f73 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d3b6ce71e7083cce1a88f8914fdc679d94babca0bc8e10c158362279a3329a1 +size 78981026 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..937210d77a500d3758266a612b3916338f3a5ca3 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0f54c0bd9f77f6da880f58f5713c01bd2e9c5734b71f79ac4dc0c48182c8e57 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..80f287e5fc81b34541e2da2294d2c4d3c98cc6ae --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00632a7edcede0828767aae1daa2ef785ea5869dbfb08cb61df62ec896bcfd3c +size 78981026 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b63d194865707b75ae940c3e6003e0bfb3b493b7 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab4ebd24e65ed5310fe05ab327eb754f6e0a387dcba556552118f25d1cd71285 +size 78980834 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d181edce9c699e7a59fae8c11fb24c6762ebd49d --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cfba841b7cf501188c164716f0dab067eb415051d636e056a19f189f861c0ab +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9a3fbec9e92fec3797fa405cff22cf56a51ec136 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b94d2ef29f01d0459cd9de3aa6eb83590bf8311fafa65b9cd8288476afd647e0 +size 78981026 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8fcce7d8d9e67e1a5d07e096648085d6b96cad96 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56e1985044e4f29c4f7231fcdbfe92cf9a4b82bb8024004bba3b9c6c4038b8e0 +size 78980887 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c9d01152f843419ae50733e1e89cdb999ba01234 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:478e23c366a6315000e4623310b2ffd4ba7fb3ba8e09a95363d5c27a824c8439 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..39a6cf631f1a6ea50f265c24f1f309fb1d8f62d7 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a163e80ae02a16dc88345a2852774bdf0c38d454961c69ca86e1a56cb22838f +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c6b8c9c44634b1b8bfac378cb1c1d9f5441cf556 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec217bb4ab300d489abd865a99e4c7fcf5ee8339e3f943f116d2f771535c6d10 +size 78980834 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..34f357b4775128af482727fc349c8fe01dd3f616 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:926e81e85e3862bbbd41d3c8a49da1e0e33cdddf5cd241e8a10bdf9215038fe4 +size 78981090 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4b92660b6d265b725b466ea31a9bc3dbbb09b5a0 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e4361c317434c5e340cbd53ab349fd0b4a10c26d8c878d8ecd8386266692f9f +size 78980834 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9f25398759f7b0ce799e65f886ac16dc830a36f8 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1532537448d01bb40ce58a5b74c5130489fb8a8be4c84b026c0a1d5ca2fdea3 +size 78981026 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a2fb1d8100561178231344d76d1cf0fdb29fc52b --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db1b2b8d55caa27f2b9fdec482ce02a6484143d0387e3d018abb551dfb984a06 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dfcd91a64f0bc702d80a732f459f9960d6cce77a --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95e0991f721a2b0e49740bfc2c72c5792609829acf72176cdcf6894a3183426e +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4cbe264301fdeb59db7290dd9c966991fafa9be4 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e79905337996e7c4195a55066cc446a6c0307f9a505d9cfae2443960ebd9380 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6eae2f6f5fa85534eba12f2fdb5abb4007f834ae --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62020511c36fbd6d2c2b868a020ea3f912ddde167b6ab4936b9756b3a084efdf +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..47886433c7de5d3cc82c4a6a4f535244428e38bb --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2029694ea52e9720d0d51f8c593d5410a0556b6dffd963fedb2f04bef2fe4bb1 +size 78980887 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..82972643f5e491f70ac889cc7698450ad6d54e9b --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66f18b01c1eab89d75b0da1012cb2d9b1d5439c0d3beebf6c8dfabc50b9687a6 +size 78981090 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7f0384cd89ce56f83171bfc6888dd73d8fbeed43 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31d0c79d2827cac728aa8f483b2a1e0709d783423784861499aca5f24ed2acce +size 78980834 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d6f2c1fb708c06f589f6d88edd207da47a5aecdf --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb7950e60efd412a3bc0c79020ec508b93f58ed9cd20493261e5baf76fa27ee0 +size 78981026 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fdc9d50be65f8f91369c561d7c1c5284cd4cb5e0 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:879688c565efaf0bd97f16aeedcf4ce6a6b14716afd5e2c46f749ba151656988 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..36cc16c45846d59c5a3134f49e64b886d8cb8a3b --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e14b085173d973f67779098c8b44fc26a65f7ea248da2a61d1cfc818ae74017a +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..286fb0b9bda25689722362e28871ba3b48199580 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb20bcfe2ff579606ab5aef6c54edc4769ece29299e9d1cec923cbe24e8a7a0a +size 78981090 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6eca9c409b8cb318fd29cffa1700be2289591581 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16da84d6d8f76febc78a4d58dce82ac5bcd176a39bb6456aed163109c2f16c4e +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..670122f6c47caf7bd3d63a7dc1bd95acc8810b93 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ffe81f4dca8cbb6789b3d77225451a9426e603674265a26f0e0b65d2b8d4e0f +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..868404bc798856bdf76e054e24f0360497c7e846 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c00bae6b146baac9e4b603998a464630873619ecd804009330852bc17df50b0b +size 78980770 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..960f07c93e3dcfb588c6aa6fd88a1eeae97763ea --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3559bb34eca6b2162c9402d4c831f1583ac5cefc4f6b416c2b7ac49105064db8 +size 78981026 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..441482ff3255c51575c806fad7799d52e372f184 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bce09b952af6643a797387b0734e1af45510702ad0cc976f70aa17969005ab24 +size 78980951 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8efbfcd1b4978de5114698b6179d5de1c010ab78 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfa34de1c78213d0238b6d16b7cd9b760646f7396cf7936832cbab8b229c6067 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..50ab653b82be643497ac965e9af0bd9f842421dd --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:404f9095a09d11709b9c6bb035876c72b3428a93375aad10426a2207d5d90cbc +size 78981026 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..041030d67b235cf4d6f42799a4967ecab0851f51 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1923c58a132a969d8d3f4edc41e43ccd7dd3b9243b6d79575865ec0c59c176a5 +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8b47fd4ffa16b127c6230058ed073915c624a26c --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8099859ce0db0d90bd7400e01152acf8ee437f9683135b3780ad02ca031f802d +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..edda2a51c12bea61e03ed760fad250f89bc25e29 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9e4a47ce93add477a7ef8bbc378cbc0e8869c91bff249e8f6fa31f279e74958 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ba1a9d5557f0247fd87c598dbcac161e701b378b --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de0e126e58f84c201fbbbb3448b33bf0b0f5dea2c4f43a75555ff103303373ae +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9cdaaa38c80126be97f03ac0f518cb2040547df7 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c5b92b00122b32e9eb0abd1132507f6f48daf858be982be0593aad2681aba93 +size 78981090 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d927c3e2e35b432b9e9eb6ca207ea6298432e6b8 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64ec5321ed3d2bc42c8a14c60d512a412c5ddef8c7aa7be434ce0f2d3016480b +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ca61c1f7868b486170db34503c1f54c1cf01dda3 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46fe157f21186c6b1115c7376fe1185aff848a390e32f6658902a2842a04cf51 +size 78981026 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c2879a82a9e6e57b6233065f2485d470b223352e --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:141da832e3a69b99c9119aad83e5c527a56c12f3b04057b152093649f7bd7e04 +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a37ad10daa910ed3af77332be3543c29b6f18a11 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b4f4ea4aea114f08811a30e0f6d94493458e520fa21ae4bdf7eb365abc84126 +size 78980887 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cf3457dad6fd46cb2266a14c6452d0bceee05315 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e80b4fe471289c0a36f95a1bcd70bf4245c91a0c537f8ca2a24c6c9d6a5ff21 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..566cd0bab0a8e3da153165f478c9db58e871f8e9 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd13894ef1a3c77aade69f0c839792b57a2bcf6900739f57d57450822335a829 +size 78981090 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4129c303e29107cf80814afbda8770b9868b6c2a --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:460c6292da318f84a05535ac2677bd17d3c9455300ec3be35cc4b6e5f6575b1c +size 78980834 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5b36d96a6b7899526933f8f695edcfee6e26b7fb --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c685de07dd32769874e132922d347f6893a845e3c599917931589ed4aa2ae940 +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..acf2a8c66f2400d77d50b2fedf97699cae413cb5 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfdc96b129a08bcf67c3fa245988af45b972a1abec199decb21a0e64fbdfeb00 +size 78980823 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6b5a0c9c0d2e6d4babc7a31ac4565412c70ab93a --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a525d29dd7be02eb802aa6c4854f7635d1f97ad1405205a82a043f45b4f87176 +size 78980887 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c106145a0ab0bf0758516343a0da1ed6e373112e --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c1a2f1c3f4724a1182e002dbf544d1925977169184ea1a3a8400732bd22f37c +size 78980951 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4fc1851f47a27975b5b763394ecd73a8d9634051 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc07f29cfaa51c1177b872e74fc2e24e8014253540cf0e086708cf06068ce89d +size 78980887 diff --git a/421m3b93b9/global_step7508/layer_01-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_01-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..78a137fcc27b2e66b4fc115cb9ceae1db7329ee3 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_01-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecce6134608ddec737746cebefacca6c81ead902a13da24f2ee293657d00c771 +size 134022403 diff --git a/421m3b93b9/global_step7508/layer_03-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_03-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4401195bbaf0033106beb8f69eff22e6946cdeb7 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_03-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f99e923fa3afe1395591a94d69400e49cb6cd2cbb2168acd82e95c38c8652b8 +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_04-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_04-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..80f95ef3e7290dd1d09f3a74d5de0eb496724d1b --- /dev/null +++ b/421m3b93b9/global_step7508/layer_04-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71b756b57b486125bc69736ce3b970e4325a8967b7b170bd7e63f11b32864556 +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_05-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_05-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5034a7e4c521e57395495e0497ab9522cfd6d6b5 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_05-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a87fa3bcaeed55fdceeacb5cf9c59958cd78ab8230068d917d45e120abd93b0c +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_06-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_06-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..725764b192a40c1794b4d7d5b071e6b9137dad63 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_06-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:592002ed2fcfc715c37951071cfdeca6829be5d2a5f9a5a20452d36c277c7deb +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_07-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_07-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6aa44580eb336d15c6eacefac2f7d4775a02c1f8 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_07-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ff1927e74f3c3367deb2d84cdef12e38fcdb74e47cb0c9987ad2ad8a8870896 +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_08-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_08-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..492cf91928123ddd3a41fdf386f19b2f854767bd --- /dev/null +++ b/421m3b93b9/global_step7508/layer_08-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10fe016a3d890c0eb6385d68494b922b0d1512d80b35682af553798cbfc726fc +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_09-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_09-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..87bfd380d1e952a3a4b5d4b584b8608f2fce95d2 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_09-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf0177a421058b03617d5cef91c89c5cb040925382baf6ae724e27997246d923 +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_10-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_10-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..eaefedd77f37f25024266df508089c50ab84eb11 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_10-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:803234b99a35233300d9c1c6d912eba71c3f4db3dd3176ab830cf9c25bb88bf1 +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_11-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_11-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2a606fa660406d0f91ab8d22ce60a77d62440bf7 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_11-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02de3b0e281f4aabc91950fccabdc50b52104fa5ff513ad351a1f3afac691672 +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_12-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_12-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..975769060182a7def98e5237e116841788895b31 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_12-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4ff9507d87881c71bc48cc7b911f3e766d97faf1858a875d528fc9b4b62b4d3 +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_13-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_13-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2a9a9982648b50bbf4fc4b4cda6cd15b3d99e907 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_13-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fa2562cf8b5ac148f038b1176fc1af30cdf019223785278967b9d4ef7e3edd9 +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_14-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_14-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c291afb390a1e67bfcc361e254d206741c7608f1 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_14-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fca38b7b8af65e1cbc20a528aeb9ac1704f36b2d962dc7ff21b5ba0be6ee2e0 +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_15-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_15-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4740962f4eb1b93170812e2dd7306409ad66137a --- /dev/null +++ b/421m3b93b9/global_step7508/layer_15-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74e600b8c960b5fa890e761a41bf03648268fb5a9dd07dcce2238dc9bf495add +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_16-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_16-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b1021ba6b9f9eb382e75c06afd6b0b68b262b8b3 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_16-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8de359f253b47ae77ca9a3a0479309b2af3778e5e18286850e4c6b9294370f02 +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_17-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_17-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c9b2e5d22a2640fdec3904ed6099abcd586f64db --- /dev/null +++ b/421m3b93b9/global_step7508/layer_17-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:347e1bb65e6dd9acc49b148e1f1708cfc61f3d9acdeb8ecc3e66f08b5ba0f2e0 +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_18-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_18-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..34c8c117212cefe40aec60f860fc1fe8f8cd4a2a --- /dev/null +++ b/421m3b93b9/global_step7508/layer_18-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fd64e5b52f2927514a251d42581c014a04bbb1b6525bcdfa72482c2841eb6b0 +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_19-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_19-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dd3cf919d82b8215f56bf73ec6b75291a87479f5 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_19-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e989fd2e39bcc6492157f208aae24227e6aa9ee469a0e44a75db27838ee971c +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_20-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_20-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ae8802ef258463afb526b287dbeb180e04a957dd --- /dev/null +++ b/421m3b93b9/global_step7508/layer_20-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60bfa9751346155abd69796ae10d5e0d548f63e9a03466ed1d72df2104a6b9d1 +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_22-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_22-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5f2e874e743d704fcf52d90fff3309183b559ef2 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_22-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2399a6a9cde05c947b4baf207c42abcd2a41fc9d85a176715f0422bb98aa89ed +size 6339 diff --git a/421m3b93b9/global_step7508/mp_rank_00_model_states.pt b/421m3b93b9/global_step7508/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7e7e7ded526fda49a2b647d1924062864aa21598 --- /dev/null +++ b/421m3b93b9/global_step7508/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95b679e36ea48e4ad8b367780d61332dd070c9aece183449b94cc394a5bf92b8 +size 37427 diff --git a/421m3b93b9/launch.sh b/421m3b93b9/launch.sh new file mode 100755 index 0000000000000000000000000000000000000000..6c3445845a5dae614feb4b8a1206322cd7bd9050 --- /dev/null +++ b/421m3b93b9/launch.sh @@ -0,0 +1,53 @@ +#!/bin/bash + +# Launch script using torch.distributed.run(). Used by slurm +# scripts, don't invoke directly. + +# Samuel's fix for apparent error in SLURM initialization +if [ $SLURM_LOCALID -eq 0 ]; then + rm -rf /dev/shm/* + rocm-smi || true +else + sleep 2 +fi + +export NCCL_SOCKET_IFNAME=hsn0,hsn1,hsn2,hsn3 +export OMP_NUM_THREADS=$SLURM_CPUS_PER_TASK +export FI_CXI_DEFAULT_CQ_SIZE=131072 + +# debugging (noisy) +#export NCCL_DEBUG=INFO +#export RCCL_KERNEL_COLL_TRACE_ENABLE=1 +#export NCCL_DEBUG_SUBSYS=INIT,COLL + +module --quiet purge +module load cray-python + +module load CrayEnv +module load PrgEnv-cray/8.3.3 +module load craype-accel-amd-gfx90a +module load cray-python + +module use /pfs/lustrep2/projappl/project_462000125/samantao-public/mymodules +module load suse-repo-deps/sam-default +module load rocm/sam-5.2.3.lua +module load rccl/sam-develop.lua +module load aws-ofi-rccl/sam-default.lua + +source venv/bin/activate + +MASTER_NODE=$(scontrol show hostnames "$SLURM_JOB_NODELIST" | head -n 1) +MASTER_PORT=9999 + +echo "Launching on $SLURMD_NODENAME ($SLURM_PROCID/$SLURM_JOB_NUM_NODES)," \ + "master $MASTER_NODE port $MASTER_PORT," \ + "GPUs $SLURM_GPUS_ON_NODE," \ + "CUDA: $(python -c 'import torch; print(torch.cuda.is_available())')" + +python -u -m torch.distributed.run \ + --nnodes $SLURM_JOB_NUM_NODES \ + --nproc_per_node $SLURM_GPUS_ON_NODE \ + --node_rank=$SLURM_PROCID \ + --master_addr $MASTER_NODE \ + --master_port $MASTER_PORT \ + "$@" diff --git a/421m3b93b9/logs/2085607.err b/421m3b93b9/logs/2085607.err new file mode 100644 index 0000000000000000000000000000000000000000..f1fc7b98dddd9e5cbc627a3166f78f3ad15a1f69 --- /dev/null +++ b/421m3b93b9/logs/2085607.err @@ -0,0 +1,483 @@ +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module scaled_upper_triang_masked_softmax_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module scaled_upper_triang_masked_softmax_cuda... +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module scaled_masked_softmax_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module scaled_masked_softmax_cuda... +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module fused_mix_prec_layer_norm_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module fused_mix_prec_layer_norm_cuda... +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +1: Successfully preprocessed all matching files. +1: Successfully preprocessed all matching files. +1: Successfully preprocessed all matching files. +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja... +1: Building extension module utils... +1: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +1: Loading extension module utils... +0: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: +4: +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: +4: +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: +6: +6: +6: +6: +6: +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja... +0: Building extension module utils... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module utils... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +2: Loading extension module utils... +5: Loading extension module utils... +3: Loading extension module utils... +7: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils...Loading extension module utils...Loading extension module utils... +0: +0: +0: Loading extension module utils...Loading extension module utils... +0: +1: Loading extension module utils... +1: Loading extension module utils...Loading extension module utils...Loading extension module utils...Loading extension module utils... +1: +1: +1: +1: Loading extension module utils... +1: Loading extension module utils... +3: Loading extension module utils... +2: Loading extension module utils... +3: Loading extension module utils... +3: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +3: Loading extension module utils... +3: Loading extension module utils... +3: Loading extension module utils... +3: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +7: Loading extension module utils... +4: Loading extension module utils... +7: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +6: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +7: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +6: Loading extension module utils... +5: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +7: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +3: +3: Loading extension module utils... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +3: +3: Loading extension module utils... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +2: +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...No modifications detected for re-loaded extension module utils, skipping build step... +5: +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +6: +6: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +6: +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +4: +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +4: +4: Loading extension module utils...Loading extension module utils... +4: +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/utils.py:349: UserWarning: Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings +0: warnings.warn("Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings") diff --git a/421m3b93b9/logs/2085607.out b/421m3b93b9/logs/2085607.out new file mode 100644 index 0000000000000000000000000000000000000000..c406bee7adc336823fc0e11796e30c63a2aacf0c --- /dev/null +++ b/421m3b93b9/logs/2085607.out @@ -0,0 +1,4089 @@ +Model parameters: d_model 1280 ffw_size 5120 kv_size 128 n_heads 10 n_layers 18 +Megatron-DeepSpeed/pretrain_gpt.py --tensor-model-parallel-size 1 --pipeline-model-parallel-size 1 --num-layers 18 --hidden-size 1280 --num-attention-heads 10 --kv-channels 128 --ffn-hidden-size 5120 --seq-length 2048 --max-position-embeddings 2048 --micro-batch-size 4 --global-batch-size 256 --train-samples 1_922_149 --vocab-file gpt2/vocab.json --merge-file gpt2/merges.txt --clip-grad 1.0 --kill-switch-path kill-switch-421moscar --bf16 --optimizer adam --adam-beta1 0.9 --adam-beta2 0.999 --adam-eps 1e-8 --lr 2e-4 --min-lr 2e-5 --lr-decay-style cosine --lr-decay-samples 1_922_149 --lr-warmup-samples 19_221 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_421moscar --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_421moscar --load checkpoints_421moscar --data-path /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2085607.json --zero-stage 0 +START 2085607: Tue Nov 29 16:52:43 EET 2022 +0: +0: +0: ======================= ROCm System Management Interface ======================= +0: ================================= Concise Info ================================= +0: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +0: 0 47.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 1 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 2 42.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 4 45.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 6 40.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: ================================================================================ +0: ============================= End of ROCm SMI Log ============================== +1: +1: +1: ======================= ROCm System Management Interface ======================= +1: ================================= Concise Info ================================= +1: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +1: 0 44.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 2 45.0c 82.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 4 43.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 6 39.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: ================================================================================ +1: ============================= End of ROCm SMI Log ============================== +2: +2: +2: ======================= ROCm System Management Interface ======================= +2: ================================= Concise Info ================================= +2: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +2: 0 48.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 2 35.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 4 40.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 6 40.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: ================================================================================ +2: ============================= End of ROCm SMI Log ============================== +6: +6: +6: ======================= ROCm System Management Interface ======================= +6: ================================= Concise Info ================================= +6: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +6: 0 45.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 2 43.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 4 38.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 6 40.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: ================================================================================ +6: ============================= End of ROCm SMI Log ============================== +4: +4: +4: ======================= ROCm System Management Interface ======================= +4: ================================= Concise Info ================================= +4: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +4: 0 48.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 2 40.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 4 45.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 6 43.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: ================================================================================ +4: ============================= End of ROCm SMI Log ============================== +7: +7: +7: ======================= ROCm System Management Interface ======================= +7: ================================= Concise Info ================================= +7: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +7: 0 47.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 2 43.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 4 42.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 6 43.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 7 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: ================================================================================ +7: ============================= End of ROCm SMI Log ============================== +3: +3: +3: ======================= ROCm System Management Interface ======================= +3: ================================= Concise Info ================================= +3: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +3: 0 49.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 2 38.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 3 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 4 39.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 6 42.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: ================================================================================ +3: ============================= End of ROCm SMI Log ============================== +5: +5: +5: ======================= ROCm System Management Interface ======================= +5: ================================= Concise Info ================================= +5: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +5: 0 43.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 2 39.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 3 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 4 45.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 6 44.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: ================================================================================ +5: ============================= End of ROCm SMI Log ============================== +4: Launching on nid007221 (4/8), master nid005655 port 9999, GPUs 8, CUDA: True +7: Launching on nid007493 (7/8), master nid005655 port 9999, GPUs 8, CUDA: True +3: Launching on nid006698 (3/8), master nid005655 port 9999, GPUs 8, CUDA: True +6: Launching on nid007362 (6/8), master nid005655 port 9999, GPUs 8, CUDA: True +0: Launching on nid005655 (0/8), master nid005655 port 9999, GPUs 8, CUDA: True +5: Launching on nid007222 (5/8), master nid005655 port 9999, GPUs 8, CUDA: True +1: Launching on nid005958 (1/8), master nid005655 port 9999, GPUs 8, CUDA: True +2: Launching on nid006681 (2/8), master nid005655 port 9999, GPUs 8, CUDA: True +0: using world size: 64, data-parallel-size: 64, tensor-model-parallel size: 1, pipeline-model-parallel size: 1 +0: accumulate and all-reduce gradients in fp32 for bfloat16 data type. +0: using torch.bfloat16 for parameters ... +0: ------------------------ arguments ------------------------ +0: abort_on_unmet_fused_kernel_constraints ......... False +0: accumulate_allreduce_grads_in_fp32 .............. True +0: adam_beta1 ...................................... 0.9 +0: adam_beta2 ...................................... 0.999 +0: adam_eps ........................................ 1e-08 +0: adlr_autoresume ................................. False +0: adlr_autoresume_interval ........................ 1000 +0: apply_query_key_layer_scaling ................... True +0: apply_residual_connection_post_layernorm ........ False +0: attention_dropout ............................... 0.1 +0: attention_softmax_in_fp32 ....................... False +0: bert_binary_head ................................ True +0: bert_load ....................................... None +0: bf16 ............................................ True +0: bias_dropout_fusion ............................. True +0: bias_gelu_fusion ................................ True +0: biencoder_projection_dim ........................ 0 +0: biencoder_shared_query_context_model ............ False +0: block_data_path ................................. None +0: checkpoint_activations .......................... False +0: checkpoint_in_cpu ............................... False +0: checkpoint_num_layers ........................... 1 +0: clip_grad ....................................... 1.0 +0: codecarbon_dir .................................. None +0: consumed_train_samples .......................... 0 +0: consumed_train_tokens ........................... 0 +0: consumed_valid_samples .......................... 0 +0: contigious_checkpointing ........................ False +0: cpu_optimizer ................................... False +0: cpu_torch_adam .................................. False +0: curriculum_learning ............................. False +0: data_impl ....................................... mmap +0: data_parallel_size .............................. 64 +0: data_path ....................................... ['/scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document'] +0: dataloader_type ................................. single +0: DDP_impl ........................................ local +0: decoder_seq_length .............................. None +0: deepscale ....................................... False +0: deepscale_config ................................ None +0: deepspeed ....................................... True +0: deepspeed_activation_checkpointing .............. False +0: deepspeed_config ................................ ds_configs/2085607.json +0: deepspeed_mpi ................................... False +0: distribute_checkpointed_activations ............. False +0: distributed_backend ............................. nccl +0: embed_layernorm ................................. False +0: embedding_path .................................. None +0: encoder_seq_length .............................. 2048 +0: eod_mask_loss ................................... False +0: eval_interval ................................... 1000 +0: eval_iters ...................................... 1 +0: eval_only ....................................... None +0: evidence_data_path .............................. None +0: exit_duration_in_mins ........................... None +0: exit_interval ................................... None +0: ffn_hidden_size ................................. 5120 +0: finetune ........................................ False +0: fp16 ............................................ False +0: fp16_lm_cross_entropy ........................... False +0: fp32_residual_connection ........................ False +0: gigaflos_no_embeds .............................. 0 +0: global_batch_size ............................... 256 +0: glu_activation .................................. None +0: hidden_dropout .................................. 0.1 +0: hidden_size ..................................... 1280 +0: hysteresis ...................................... 2 +0: ict_head_size ................................... None +0: ict_load ........................................ None +0: img_dim ......................................... 224 +0: indexer_batch_size .............................. 128 +0: indexer_log_interval ............................ 1000 +0: inference ....................................... False +0: init_method_std ................................. 0.02 +0: init_method_xavier_uniform ...................... False +0: initial_loss_scale .............................. 4294967296 +0: kill_switch_path ................................ kill-switch-421moscar +0: kv_channels ..................................... 128 +0: layer_norm_fusion ............................... True +0: layernorm_epsilon ............................... 1e-05 +0: lazy_mpu_init ................................... None +0: load ............................................ checkpoints_421moscar +0: local_rank ...................................... None +0: log_batch_size_to_tensorboard ................... True +0: log_interval .................................... 10 +0: log_learning_rate_to_tensorboard ................ True +0: log_level ....................................... None +0: log_level_replica ............................... None +0: log_loss_scale_to_tensorboard ................... True +0: log_num_zeros_in_grad ........................... False +0: log_params_norm ................................. False +0: log_path ........................................ None +0: log_timers_to_tensorboard ....................... True +0: log_validation_ppl_to_tensorboard ............... True +0: loss_on_targets_only ............................ False +0: loss_scale ...................................... None +0: loss_scale_window ............................... 1000 +0: lr .............................................. 0.0002 +0: lr_decay_iters .................................. None +0: lr_decay_samples ................................ 1922149 +0: lr_decay_style .................................. cosine +0: lr_decay_tokens ................................. None +0: lr_warmup_fraction .............................. None +0: lr_warmup_iters ................................. 0 +0: lr_warmup_samples ............................... 19221 +0: make_vocab_size_divisible_by .................... 128 +0: mask_prob ....................................... 0.15 +0: masked_softmax_fusion ........................... True +0: max_position_embeddings ......................... 2048 +0: mean_noise_span_length .......................... None +0: memory_centric_tiled_linear ..................... False +0: merge_file ...................................... gpt2/merges.txt +0: micro_batch_size ................................ 4 +0: min_loss_scale .................................. 1.0 +0: min_lr .......................................... 2e-05 +0: mmap_warmup ..................................... False +0: no_load_optim ................................... None +0: no_load_rng ..................................... None +0: no_save_optim ................................... None +0: no_save_rng ..................................... None +0: noise_density ................................... None +0: num_attention_heads ............................. 10 +0: num_channels .................................... 3 +0: num_classes ..................................... 1000 +0: num_layers ...................................... 18 +0: num_layers_per_virtual_pipeline_stage ........... None +0: num_workers ..................................... 2 +0: onnx_safe ....................................... None +0: openai_gelu ..................................... False +0: optimizer ....................................... adam +0: optimizer_fusion ................................ True +0: override_lr_scheduler ........................... False +0: pad_vocab_size_to ............................... None +0: params_dtype .................................... torch.bfloat16 +0: partition_activations ........................... False +0: patch_dim ....................................... 16 +0: pipeline_model_parallel_size .................... 1 +0: position_embedding_type ......................... PositionEmbeddingType.absolute +0: pp_partition_method ............................. None +0: profile_backward ................................ False +0: query_in_block_prob ............................. 0.1 +0: rampup_batch_size ............................... None +0: rank ............................................ 0 +0: remote_device ................................... none +0: reset_attention_mask ............................ False +0: reset_position_ids .............................. False +0: retriever_report_topk_accuracies ................ [] +0: retriever_score_scaling ......................... False +0: retriever_seq_length ............................ 256 +0: reweight_loss_based_on_position_frequency ....... False +0: sample_rate ..................................... 1.0 +0: save ............................................ checkpoints_421moscar +0: save_interval ................................... 1000 +0: scatter_gather_tensors_in_pipeline .............. True +0: scattered_embeddings ............................ False +0: seed ............................................ 1234 +0: seq_length ...................................... 2048 +0: sgd_momentum .................................... 0.9 +0: short_seq_prob .................................. 0.1 +0: skip_train_iteration_range ...................... None +0: split ........................................... 949,50,1 +0: split_transformers .............................. False +0: sync_tp_duplicated_parameters ................... False +0: synchronize_each_layer .......................... False +0: tensor_model_parallel_size ...................... 1 +0: tensorboard_dir ................................. tensorboard_421moscar +0: tensorboard_log_interval ........................ 1 +0: tensorboard_queue_size .......................... 5 +0: test_weighted_split_names ....................... None +0: test_weighted_split_paths ....................... None +0: test_weighted_split_paths_path .................. None +0: test_weighted_split_splits ...................... None +0: test_weighted_split_weights ..................... None +0: tile_factor ..................................... 1 +0: titles_data_path ................................ None +0: tokenizer_name_or_path .......................... None +0: tokenizer_type .................................. GPT2BPETokenizer +0: train_iters ..................................... None +0: train_samples ................................... 1922149 +0: train_tokens .................................... None +0: train_weighted_split_paths ...................... None +0: train_weighted_split_paths_path ................. None +0: universal_checkpoint ............................ False +0: use_bnb_optimizer ............................... False +0: use_checkpoint_lr_scheduler ..................... False +0: use_contiguous_buffers_in_ddp ................... True +0: use_cpu_initialization .......................... None +0: use_one_sent_docs ............................... False +0: use_pin_memory .................................. False +0: valid_num_workers ............................... 2 +0: valid_weighted_split_names ...................... None +0: valid_weighted_split_paths ...................... None +0: valid_weighted_split_paths_path ................. None +0: valid_weighted_split_splits ..................... None +0: valid_weighted_split_weights .................... None +0: virtual_pipeline_model_parallel_size ............ None +0: vocab_extra_ids ................................. 0 +0: vocab_file ...................................... gpt2/vocab.json +0: weight_decay .................................... 0.1 +0: world_size ...................................... 64 +0: zero_allgather_bucket_size ...................... 0.0 +0: zero_contigious_gradients ....................... False +0: zero_reduce_bucket_size ......................... 0.0 +0: zero_reduce_scatter ............................. False +0: zero_stage ...................................... 0 +0: -------------------- end of arguments --------------------- +0: setting number of micro-batches to constant 1 +0: > building GPT2BPETokenizer tokenizer ... +0: > padded vocab (size: 50257) with 47 dummy tokens (new size: 50304) +0: DeepSpeed general environment info: +0: torch install path ............... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch'] +0: torch version .................... 1.13.0+rocm5.2 +0: torch cuda version ............... None +0: torch hip version ................ 5.2.21151-afdc89f8 +0: nvcc version ..................... None +0: deepspeed install path ........... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed'] +0: deepspeed info ................... 0.7.5, unknown, unknown +0: deepspeed wheel compiled w. ...... torch 1.13, hip 5.1 +0: **** Git info for Megatron: git_hash=unknown git_branch=unknown **** +0: > initializing torch distributed ... +0: [2022-11-29 16:53:04,954] [INFO] [comm.py:633:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +7: > setting tensorboard ... +0: > initializing tensor model parallel with size 1 +0: > initializing pipeline model parallel with size 1 +0: > setting random seeds to 1234 ... +0: > initializing model parallel cuda seeds on global rank 0, model parallel rank 0, and data parallel rank 0 with model parallel seed: 3952 and data parallel seed: 1234 +0: > compiling dataset index builder ... +0: make: Entering directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' +0: make: Nothing to be done for 'default'. +0: make: Leaving directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' +0: >>> done with dataset index builder. Compilation time: 0.104 seconds +0: > compiling and loading fused kernels ... +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.cpp [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 87 +0: [1/1] c++ scaled_upper_triang_masked_softmax_hip.cuda.o scaled_upper_triang_masked_softmax_hip.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib -lamdhip64 -o scaled_upper_triang_masked_softmax_cuda.so +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.cpp [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 63 +0: [1/1] c++ scaled_masked_softmax_hip.cuda.o scaled_masked_softmax_hip.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib -lamdhip64 -o scaled_masked_softmax_cuda.so +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda_kernel.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_hip_kernel.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 67 +0: [1/1] c++ layer_norm_hip_kernel.cuda.o layer_norm_cuda.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib -lamdhip64 -o fused_mix_prec_layer_norm_cuda.so +0: >>> done with compiling and loading fused kernels. Compilation time: 17.879 seconds +0: time to initialize megatron (seconds): -25.498 +0: [after megatron is initialized] datetime: 2022-11-29 16:53:26 +0: building GPT model ... +0: [2022-11-29 16:53:26,556] [INFO] [utils.py:827:see_memory_usage] Before Building Model +0: [2022-11-29 16:53:26,557] [INFO] [utils.py:828:see_memory_usage] MA 0.0 GB Max_MA 0.0 GB CA 0.0 GB Max_CA 0 GB +0: [2022-11-29 16:53:26,557] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 40.89 GB, percent = 8.1% +0: SEED_LAYERS=False BASE_SEED=1234 SEED_FN=None +0: Using topology: {ProcessCoord(pipe=0, data=0, model=0): 0, ProcessCoord(pipe=0, data=1, model=0): 1, ProcessCoord(pipe=0, data=2, model=0): 2, ProcessCoord(pipe=0, data=3, model=0): 3, ProcessCoord(pipe=0, data=4, model=0): 4, ProcessCoord(pipe=0, data=5, model=0): 5, ProcessCoord(pipe=0, data=6, model=0): 6, ProcessCoord(pipe=0, data=7, model=0): 7, ProcessCoord(pipe=0, data=8, model=0): 8, ProcessCoord(pipe=0, data=9, model=0): 9, ProcessCoord(pipe=0, data=10, model=0): 10, ProcessCoord(pipe=0, data=11, model=0): 11, ProcessCoord(pipe=0, data=12, model=0): 12, ProcessCoord(pipe=0, data=13, model=0): 13, ProcessCoord(pipe=0, data=14, model=0): 14, ProcessCoord(pipe=0, data=15, model=0): 15, ProcessCoord(pipe=0, data=16, model=0): 16, ProcessCoord(pipe=0, data=17, model=0): 17, ProcessCoord(pipe=0, data=18, model=0): 18, ProcessCoord(pipe=0, data=19, model=0): 19, ProcessCoord(pipe=0, data=20, model=0): 20, ProcessCoord(pipe=0, data=21, model=0): 21, ProcessCoord(pipe=0, data=22, model=0): 22, ProcessCoord(pi +0: pe=0, data=23, model=0): 23, ProcessCoord(pipe=0, data=24, model=0): 24, ProcessCoord(pipe=0, data=25, model=0): 25, ProcessCoord(pipe=0, data=26, model=0): 26, ProcessCoord(pipe=0, data=27, model=0): 27, ProcessCoord(pipe=0, data=28, model=0): 28, ProcessCoord(pipe=0, data=29, model=0): 29, ProcessCoord(pipe=0, data=30, model=0): 30, ProcessCoord(pipe=0, data=31, model=0): 31, ProcessCoord(pipe=0, data=32, model=0): 32, ProcessCoord(pipe=0, data=33, model=0): 33, ProcessCoord(pipe=0, data=34, model=0): 34, ProcessCoord(pipe=0, data=35, model=0): 35, ProcessCoord(pipe=0, data=36, model=0): 36, ProcessCoord(pipe=0, data=37, model=0): 37, ProcessCoord(pipe=0, data=38, model=0): 38, ProcessCoord(pipe=0, data=39, model=0): 39, ProcessCoord(pipe=0, data=40, model=0): 40, ProcessCoord(pipe=0, data=41, model=0): 41, ProcessCoord(pipe=0, data=42, model=0): 42, ProcessCoord(pipe=0, data=43, model=0): 43, ProcessCoord(pipe=0, data=44, model=0): 44, ProcessCoord(pipe=0, data=45, model=0): 45, ProcessCoord(pipe=0, data=4 +0: 6, model=0): 46, ProcessCoord(pipe=0, data=47, model=0): 47, ProcessCoord(pipe=0, data=48, model=0): 48, ProcessCoord(pipe=0, data=49, model=0): 49, ProcessCoord(pipe=0, data=50, model=0): 50, ProcessCoord(pipe=0, data=51, model=0): 51, ProcessCoord(pipe=0, data=52, model=0): 52, ProcessCoord(pipe=0, data=53, model=0): 53, ProcessCoord(pipe=0, data=54, model=0): 54, ProcessCoord(pipe=0, data=55, model=0): 55, ProcessCoord(pipe=0, data=56, model=0): 56, ProcessCoord(pipe=0, data=57, model=0): 57, ProcessCoord(pipe=0, data=58, model=0): 58, ProcessCoord(pipe=0, data=59, model=0): 59, ProcessCoord(pipe=0, data=60, model=0): 60, ProcessCoord(pipe=0, data=61, model=0): 61, ProcessCoord(pipe=0, data=62, model=0): 62, ProcessCoord(pipe=0, data=63, model=0): 63} +0: [2022-11-29 16:53:28,558] [INFO] [module.py:366:_partition_layers] Partitioning pipeline stages with method type:transformer +0: stage=0 layers=25 +0: 0: _to_float16 +0: 1: EmbeddingPipe +0: 2: +0: 3: ParallelTransformerLayerPipe +0: 4: ParallelTransformerLayerPipe +0: 5: ParallelTransformerLayerPipe +0: 6: ParallelTransformerLayerPipe +0: 7: ParallelTransformerLayerPipe +0: 8: ParallelTransformerLayerPipe +0: 9: ParallelTransformerLayerPipe +0: 10: ParallelTransformerLayerPipe +0: 11: ParallelTransformerLayerPipe +0: 12: ParallelTransformerLayerPipe +0: 13: ParallelTransformerLayerPipe +0: 14: ParallelTransformerLayerPipe +0: 15: ParallelTransformerLayerPipe +0: 16: ParallelTransformerLayerPipe +0: 17: ParallelTransformerLayerPipe +0: 18: ParallelTransformerLayerPipe +0: 19: ParallelTransformerLayerPipe +0: 20: ParallelTransformerLayerPipe +0: 21: undo +0: 22: MixedFusedLayerNorm +0: 23: EmbeddingPipe +0: 24: float16_to_fp32 +0: loss: CrossEntropy +0: [2022-11-29 16:53:28,714] [INFO] [utils.py:827:see_memory_usage] After Building Model +0: [2022-11-29 16:53:28,714] [INFO] [utils.py:828:see_memory_usage] MA 0.79 GB Max_MA 0.79 GB CA 0.86 GB Max_CA 1 GB +0: [2022-11-29 16:53:28,714] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 40.91 GB, percent = 8.1% +0: setting training iterations to 7508 +0: > learning rate decay style: cosine +0: DeepSpeed is enabled. +0: [2022-11-29 16:53:28,716] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed info: version=0.7.5, git-hash=unknown, git-branch=unknown +0: [2022-11-29 16:53:41,217] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False +0: [2022-11-29 16:53:41,217] [INFO] [logging.py:68:log_dist] [Rank 0] Removing param_group that has no 'params' in the client Optimizer +0: [2022-11-29 16:53:41,217] [INFO] [logging.py:68:log_dist] [Rank 0] Using client Optimizer as basic optimizer +0: [2022-11-29 16:53:41,223] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Basic Optimizer = FusedAdam +0: [2022-11-29 16:53:41,223] [INFO] [logging.py:68:log_dist] [Rank 0] Creating BF16 optimizer +0: [2022-11-29 16:53:41,265] [INFO] [utils.py:827:see_memory_usage] begin bf16_optimizer +0: [2022-11-29 16:53:41,266] [INFO] [utils.py:828:see_memory_usage] MA 0.78 GB Max_MA 0.79 GB CA 0.88 GB Max_CA 1 GB +0: [2022-11-29 16:53:41,266] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.57 GB, percent = 8.3% +1: ninja: no work to do. +1: Time to load utils op: 0.2361443042755127 seconds +0: Time to load utils op: 0.2090761661529541 seconds +0: [2022-11-29 16:53:41,512] [INFO] [utils.py:827:see_memory_usage] before initializing group 0 +0: [2022-11-29 16:53:41,512] [INFO] [utils.py:828:see_memory_usage] MA 0.78 GB Max_MA 0.78 GB CA 0.88 GB Max_CA 1 GB +0: [2022-11-29 16:53:41,513] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.57 GB, percent = 8.3% +0: [2022-11-29 16:53:41,583] [INFO] [utils.py:827:see_memory_usage] after initializing group 0 +0: [2022-11-29 16:53:41,583] [INFO] [utils.py:828:see_memory_usage] MA 1.68 GB Max_MA 1.68 GB CA 2.21 GB Max_CA 2 GB +0: [2022-11-29 16:53:41,584] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.58 GB, percent = 8.3% +0: ninja: no work to do. +0: [2022-11-29 16:53:41,614] [INFO] [utils.py:827:see_memory_usage] before initializing group 1 +0: [2022-11-29 16:53:41,615] [INFO] [utils.py:828:see_memory_usage] MA 1.68 GB Max_MA 1.68 GB CA 2.21 GB Max_CA 2 GB +0: [2022-11-29 16:53:41,615] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.58 GB, percent = 8.3% +0: Time to load utils op: 0.12143182754516602 seconds +1: Time to load utils op: 0.00048828125 seconds +0: Time to load utils op: 0.0005598068237304688 seconds +0: [2022-11-29 16:53:41,648] [INFO] [utils.py:827:see_memory_usage] after initializing group 1 +0: [2022-11-29 16:53:41,649] [INFO] [utils.py:828:see_memory_usage] MA 2.38 GB Max_MA 2.38 GB CA 3.23 GB Max_CA 3 GB +0: [2022-11-29 16:53:41,649] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.58 GB, percent = 8.3% +2: Time to load utils op: 0.410921573638916 seconds +5: Time to load utils op: 0.41174793243408203 seconds +3: Time to load utils op: 0.41187047958374023 seconds +7: Time to load utils op: 0.41039466857910156 seconds +0: [2022-11-29 16:53:41,680] [INFO] [utils.py:827:see_memory_usage] before initializing group 2 +0: [2022-11-29 16:53:41,681] [INFO] [utils.py:828:see_memory_usage] MA 2.38 GB Max_MA 2.38 GB CA 3.23 GB Max_CA 3 GB +0: [2022-11-29 16:53:41,681] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.6 GB, percent = 8.3% +0: Time to load utils op: 0.2028818130493164 secondsTime to load utils op: 0.20264053344726562 seconds +0: +0: Time to load utils op: 0.20287799835205078 seconds +0: Time to load utils op: 0.20269155502319336 seconds +0: Time to load utils op: 0.20176267623901367 seconds +1: Time to load utils op: 0.20329737663269043 seconds +0: Time to load utils op: 0.20236730575561523 seconds +1: Time to load utils op: 0.2028052806854248 secondsTime to load utils op: 0.20283937454223633 secondsTime to load utils op: 0.20318222045898438 seconds +1: Time to load utils op: 0.20346593856811523 seconds +1: +1: +1: Time to load utils op: 0.20406699180603027 seconds +1: Time to load utils op: 0.20372295379638672 seconds +3: Time to load utils op: 0.20284056663513184 seconds +2: Time to load utils op: 0.20302343368530273 seconds +3: Time to load utils op: 0.20286273956298828 seconds +3: Time to load utils op: 0.20293712615966797 seconds +3: Time to load utils op: 0.20300602912902832 seconds +2: Time to load utils op: 0.20328783988952637 seconds +3: Time to load utils op: 0.20300626754760742 secondsTime to load utils op: 0.2030937671661377 seconds +3: +2: Time to load utils op: 0.20229530334472656 seconds +3: Time to load utils op: 0.20365023612976074 seconds +2: Time to load utils op: 0.20223665237426758 seconds +2: Time to load utils op: 0.20183253288269043 seconds +2: Time to load utils op: 0.20245361328125 seconds +2: Time to load utils op: 0.202239990234375 seconds +7: Time to load utils op: 0.20261168479919434 seconds +7: Time to load utils op: 0.20272040367126465 seconds +7: Time to load utils op: 0.2023329734802246 seconds +7: Time to load utils op: 0.20244860649108887 seconds +7: Time to load utils op: 0.202925443649292 seconds +5: Time to load utils op: 0.20285391807556152 seconds +5: Time to load utils op: 0.20301175117492676 seconds +5: Time to load utils op: 0.2034158706665039 seconds +7: Time to load utils op: 0.20249295234680176 seconds +5: Time to load utils op: 0.20380783081054688 seconds +5: Time to load utils op: 0.20360803604125977 seconds +7: Time to load utils op: 0.20236563682556152 seconds +0: Time to load utils op: 0.00040340423583984375 seconds +0: Time to load utils op: 0.0003647804260253906 seconds +5: Time to load utils op: 0.202681303024292 seconds +1: Time to load utils op: 0.0003364086151123047 seconds +1: Time to load utils op: 0.0004086494445800781 seconds +5: Time to load utils op: 0.2024998664855957 seconds +0: Time to load utils op: 0.0003726482391357422 seconds +1: Time to load utils op: 0.0003147125244140625 seconds +0: [2022-11-29 16:53:41,717] [INFO] [utils.py:827:see_memory_usage] after initializing group 2 +0: Time to load utils op: 0.0003719329833984375 seconds +1: Time to load utils op: 0.0003077983856201172 seconds +0: Time to load utils op: 0.00039649009704589844 seconds +4: Time to load utils op: 0.2108149528503418 secondsTime to load utils op: 0.2108440399169922 seconds +4: +4: Time to load utils op: 0.21083998680114746 seconds +4: Time to load utils op: 0.210845947265625 seconds +4: Time to load utils op: 0.21084833145141602 secondsTime to load utils op: 0.21087384223937988 seconds +4: +4: Time to load utils op: 0.21088910102844238 secondsTime to load utils op: 0.21088290214538574 seconds +4: +0: Time to load utils op: 0.00044417381286621094 seconds +1: Time to load utils op: 0.0003643035888671875 seconds +0: [2022-11-29 16:53:41,718] [INFO] [utils.py:828:see_memory_usage] MA 2.38 GB Max_MA 2.38 GB CA 3.23 GB Max_CA 3 GB +1: Time to load utils op: 0.0003597736358642578 seconds +0: [2022-11-29 16:53:41,718] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.6 GB, percent = 8.3% +1: Time to load utils op: 0.0003857612609863281 seconds +6: Time to load utils op: 0.21180105209350586 seconds +6: Time to load utils op: 0.21180033683776855 seconds +6: Time to load utils op: 0.21181988716125488 seconds +6: Time to load utils op: 0.21182680130004883 seconds +6: Time to load utils op: 0.21184158325195312 seconds +6: Time to load utils op: 0.21184635162353516 seconds +6: Time to load utils op: 0.2118525505065918 seconds +6: Time to load utils op: 0.2110283374786377 seconds +3: Time to load utils op: 0.0004076957702636719 seconds +3: Time to load utils op: 0.00047516822814941406 secondsTime to load utils op: 0.00041675567626953125 seconds +3: +3: Time to load utils op: 0.0004918575286865234 seconds +3: Time to load utils op: 0.0005178451538085938 seconds +3: Time to load utils op: 0.0005388259887695312 secondsTime to load utils op: 0.0005249977111816406 seconds +3: +3: Time to load utils op: 0.0005662441253662109 seconds +7: Time to load utils op: 0.0005364418029785156 seconds +2: Time to load utils op: 0.000576019287109375 seconds +2: Time to load utils op: 0.00052642822265625 seconds +2: Time to load utils op: 0.00039958953857421875 seconds +2: Time to load utils op: 0.00039505958557128906 seconds +2: Time to load utils op: 0.00040268898010253906 seconds +2: Time to load utils op: 0.00039768218994140625 seconds +5: Time to load utils op: 0.0005838871002197266 seconds +7: Time to load utils op: 0.0003452301025390625 seconds +2: Time to load utils op: 0.0003819465637207031 seconds +2: Time to load utils op: 0.0004134178161621094 seconds +7: Time to load utils op: 0.0003523826599121094 seconds +7: Time to load utils op: 0.0003554821014404297 seconds +7: Time to load utils op: 0.00037980079650878906 seconds +7: Time to load utils op: 0.0003540515899658203 seconds +7: Time to load utils op: 0.0003609657287597656 seconds +7: Time to load utils op: 0.0003597736358642578 seconds +5: Time to load utils op: 0.00033354759216308594 seconds +5: Time to load utils op: 0.00047135353088378906 seconds +5: Time to load utils op: 0.0004603862762451172 seconds +5: Time to load utils op: 0.00040721893310546875 seconds +5: Time to load utils op: 0.00047087669372558594 seconds +5: Time to load utils op: 0.0004055500030517578 seconds +5: Time to load utils op: 0.00046181678771972656 seconds +0: [2022-11-29 16:53:41,761] [INFO] [utils.py:827:see_memory_usage] before initialize_optimizer +0: [2022-11-29 16:53:41,762] [INFO] [utils.py:828:see_memory_usage] MA 2.38 GB Max_MA 2.38 GB CA 3.23 GB Max_CA 3 GB +0: [2022-11-29 16:53:41,762] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.72 GB, percent = 8.3% +6: Time to load utils op: 0.0007486343383789062 seconds +6: Time to load utils op: 0.0007789134979248047 seconds +6: Time to load utils op: 0.000942230224609375 secondsTime to load utils op: 0.0009853839874267578 seconds +6: +6: Time to load utils op: 0.001138925552368164 seconds +6: Time to load utils op: 0.0012326240539550781 seconds +6: Time to load utils op: 0.001117706298828125 seconds +6: Time to load utils op: 0.0013277530670166016 seconds +4: Time to load utils op: 0.0008478164672851562 seconds +4: Time to load utils op: 0.0011157989501953125 seconds +4: Time to load utils op: 0.0012993812561035156 seconds +4: Time to load utils op: 0.0013990402221679688 seconds +4: Time to load utils op: 0.0014119148254394531 seconds +4: Time to load utils op: 0.0014052391052246094 seconds +4: Time to load utils op: 0.0014026165008544922 seconds +4: Time to load utils op: 0.0014007091522216797 seconds +0: [2022-11-29 16:53:41,803] [INFO] [utils.py:827:see_memory_usage] end initialize_optimizer +0: [2022-11-29 16:53:41,803] [INFO] [utils.py:828:see_memory_usage] MA 2.43 GB Max_MA 2.43 GB CA 3.23 GB Max_CA 3 GB +0: [2022-11-29 16:53:41,803] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.72 GB, percent = 8.3% +0: [2022-11-29 16:53:41,836] [INFO] [utils.py:827:see_memory_usage] end bf16_optimizer +0: [2022-11-29 16:53:41,836] [INFO] [utils.py:828:see_memory_usage] MA 2.43 GB Max_MA 2.43 GB CA 3.23 GB Max_CA 3 GB +0: [2022-11-29 16:53:41,836] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.72 GB, percent = 8.3% +0: [2022-11-29 16:53:41,836] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Final Optimizer = FusedAdam +0: [2022-11-29 16:53:41,837] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed using client LR scheduler +0: [2022-11-29 16:53:41,837] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed LR Scheduler = +0: [2022-11-29 16:53:41,837] [INFO] [logging.py:68:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0, 0.0, 0.0], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +0: [2022-11-29 16:53:41,837] [INFO] [config.py:1007:print] DeepSpeedEngine configuration: +0: [2022-11-29 16:53:41,837] [INFO] [config.py:1011:print] activation_checkpointing_config { +0: "partition_activations": false, +0: "contiguous_memory_optimization": false, +0: "cpu_checkpointing": false, +0: "number_checkpoints": null, +0: "synchronize_checkpoint_boundary": false, +0: "profile": false +0: } +0: [2022-11-29 16:53:41,837] [INFO] [config.py:1011:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True} +0: [2022-11-29 16:53:41,837] [INFO] [config.py:1011:print] amp_enabled .................. False +0: [2022-11-29 16:53:41,837] [INFO] [config.py:1011:print] amp_params ................... False +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] autotuning_config ............ { +0: "enabled": false, +0: "start_step": null, +0: "end_step": null, +0: "metric_path": null, +0: "arg_mappings": null, +0: "metric": "throughput", +0: "model_info": null, +0: "results_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_results", +0: "exps_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_exps", +0: "overwrite": true, +0: "fast": true, +0: "start_profile_step": 3, +0: "end_profile_step": 5, +0: "tuner_type": "gridsearch", +0: "tuner_early_stopping": 5, +0: "tuner_num_trials": 50, +0: "model_info_path": null, +0: "mp_size": 1, +0: "max_train_batch_size": null, +0: "min_train_batch_size": 1, +0: "max_train_micro_batch_size_per_gpu": 1.024000e+03, +0: "min_train_micro_batch_size_per_gpu": 1, +0: "num_tuning_micro_batch_sizes": 3 +0: } +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] bfloat16_enabled ............. True +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] checkpoint_parallel_write_pipeline False +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] checkpoint_tag_validation_enabled True +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] checkpoint_tag_validation_fail False +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] comms_config ................. +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] communication_data_type ...... None +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] compression_config ........... {'weight_quantization': {'shared_parameters': {'enabled': False, 'quantizer_kernel': False, 'schedule_offset': 0, 'quantize_groups': 1, 'quantize_verbose': False, 'quantization_type': 'symmetric', 'quantize_weight_in_forward': False, 'rounding': 'nearest', 'fp16_mixed_quantize': False, 'quantize_change_ratio': 0.001}, 'different_groups': {}}, 'activation_quantization': {'shared_parameters': {'enabled': False, 'quantization_type': 'symmetric', 'range_calibration': 'dynamic', 'schedule_offset': 1000}, 'different_groups': {}}, 'sparse_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'row_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'head_pruning': {'shared_parameters': {'enabled': False, 'method': 'topk', 'schedule_offset': 1000}, 'different_groups': {}}, 'channel_pruning': {'shared_pa +0: rameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'layer_reduction': {'enabled': False}} +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] curriculum_enabled ........... False +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] curriculum_params ............ False +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] dataloader_drop_last ......... False +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] disable_allgather ............ False +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] dump_state ................... False +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] dynamic_loss_scale_args ...... None +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] eigenvalue_enabled ........... False +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] eigenvalue_gas_boundary_resolution 1 +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] eigenvalue_layer_name ........ bert.encoder.layer +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] eigenvalue_layer_num ......... 0 +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] eigenvalue_max_iter .......... 100 +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] eigenvalue_stability ......... 1e-06 +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] eigenvalue_tol ............... 0.01 +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] eigenvalue_verbose ........... False +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] elasticity_enabled ........... False +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] flops_profiler_config ........ { +0: "enabled": false, +0: "profile_step": 1, +0: "module_depth": -1, +0: "top_modules": 1, +0: "detailed": true, +0: "output_file": null +0: } +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] fp16_auto_cast ............... None +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] fp16_enabled ................. False +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] fp16_master_weights_and_gradients False +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] global_rank .................. 0 +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] gradient_accumulation_steps .. 1 +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] gradient_clipping ............ 1.0 +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] gradient_predivide_factor .... 1.0 +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] initial_dynamic_scale ........ 1 +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] load_universal_checkpoint .... False +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] loss_scale ................... 1.0 +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] memory_breakdown ............. False +0: [2022-11-29 16:53:41,838] [INFO] [config.py:1011:print] monitor_config ............... +0: [2022-11-29 16:53:41,839] [INFO] [config.py:1011:print] nebula_config ................ { +0: "enabled": false, +0: "persistent_storage_path": null, +0: "persistent_time_interval": 100, +0: "num_of_version_in_retention": 2, +0: "enable_nebula_load": true, +0: "load_path": null +0: } +0: [2022-11-29 16:53:41,839] [INFO] [config.py:1011:print] optimizer_legacy_fusion ...... False +0: [2022-11-29 16:53:41,839] [INFO] [config.py:1011:print] optimizer_name ............... None +0: [2022-11-29 16:53:41,839] [INFO] [config.py:1011:print] optimizer_params ............. None +0: [2022-11-29 16:53:41,839] [INFO] [config.py:1011:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0} +0: [2022-11-29 16:53:41,839] [INFO] [config.py:1011:print] pld_enabled .................. False +0: [2022-11-29 16:53:41,839] [INFO] [config.py:1011:print] pld_params ................... False +0: [2022-11-29 16:53:41,839] [INFO] [config.py:1011:print] prescale_gradients ........... False +0: [2022-11-29 16:53:41,839] [INFO] [config.py:1011:print] scheduler_name ............... None +0: [2022-11-29 16:53:41,839] [INFO] [config.py:1011:print] scheduler_params ............. None +0: [2022-11-29 16:53:41,839] [INFO] [config.py:1011:print] sparse_attention ............. None +0: [2022-11-29 16:53:41,839] [INFO] [config.py:1011:print] sparse_gradients_enabled ..... False +0: [2022-11-29 16:53:41,839] [INFO] [config.py:1011:print] steps_per_print .............. 2000 +0: [2022-11-29 16:53:41,839] [INFO] [config.py:1011:print] train_batch_size ............. 256 +0: [2022-11-29 16:53:41,839] [INFO] [config.py:1011:print] train_micro_batch_size_per_gpu 4 +0: [2022-11-29 16:53:41,839] [INFO] [config.py:1011:print] use_node_local_storage ....... False +0: [2022-11-29 16:53:41,839] [INFO] [config.py:1011:print] wall_clock_breakdown ......... False +0: [2022-11-29 16:53:41,839] [INFO] [config.py:1011:print] world_size ................... 64 +0: [2022-11-29 16:53:41,839] [INFO] [config.py:1011:print] zero_allow_untested_optimizer False +0: [2022-11-29 16:53:41,839] [INFO] [config.py:1011:print] zero_config .................. stage=0 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=500000000 allgather_partitions=True allgather_bucket_size=500000000 overlap_comm=False load_from_fp32_weights=True elastic_checkpoint=False offload_param=None offload_optimizer=None sub_group_size=1000000000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=50000000 param_persistence_threshold=100000 model_persistence_threshold=9223372036854775807 max_live_parameters=1000000000 max_reuse_distance=1000000000 gather_16bit_weights_on_model_save=False stage3_gather_fp16_weights_on_model_save=False ignore_unused_parameters=True legacy_stage1=False round_robin_gradients=False +0: [2022-11-29 16:53:41,839] [INFO] [config.py:1011:print] zero_enabled ................. False +0: [2022-11-29 16:53:41,839] [INFO] [config.py:1011:print] zero_optimization_stage ...... 0 +0: [2022-11-29 16:53:41,839] [INFO] [config.py:996:print_user_config] json = { +0: "train_micro_batch_size_per_gpu": 4, +0: "train_batch_size": 256, +0: "gradient_clipping": 1.0, +0: "zero_optimization": { +0: "stage": 0 +0: }, +0: "bf16": { +0: "enabled": true +0: }, +0: "steps_per_print": 2.000000e+03, +0: "wall_clock_breakdown": false +0: } +0: Time to load utils op: 0.00039124488830566406 seconds +0: [2022-11-29 16:53:41,840] [INFO] [engine.py:87:__init__] CONFIG: micro_batches=1 micro_batch_size=4 +0: [2022-11-29 16:53:41,866] [INFO] [engine.py:145:__init__] RANK=0 STAGE=0 LAYERS=25 [0, 25) STAGE_PARAMS=421207040 (421.207M) TOTAL_PARAMS=421207040 (421.207M) UNIQUE_PARAMS=421207040 (421.207M) +6: [2022-11-29 16:53:41,871] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 16:53:41,871] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:53:41,871] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:53:41,871] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 16:53:41,871] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 16:53:41,871] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 16:53:41,871] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: WARNING: could not find the metadata file checkpoints_421moscar +0: will not load any checkpoints and will start from random +4: [2022-11-29 16:53:41,871] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 16:53:41,871] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 16:53:41,871] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 16:53:41,871] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:53:41,871] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 16:53:41,871] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:53:41,871] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:53:41,872] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:53:41,873] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:53:41,873] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: time (ms) | load-checkpoint: 7.27 +0: estimated model parameters: 0.42120704 +0: estimated model parameters without embeddings: 0.35419648 +0: [after model, optimizer, and learning rate scheduler are built] datetime: 2022-11-29 16:53:42 +0: > building train, validation, and test datasets ... +0: > datasets target sizes (minimum size): +0: train: 1922149 +0: validation: 2048 +0: test: 256 +0: > building train, validation, and test datasets for GPT ... +0: > building dataset index ... +0: reading sizes... +0: reading pointers... +0: reading document index... +0: creating numpy buffer of mmap... +0: creating memory view of numpy buffer... +0: > finished creating indexed dataset in 0.019735 seconds +0: number of documents: 431992659 +0: > dataset split: +0: train: +0: document indices in [0, 409961033) total of 409961033 documents +0: validation: +0: document indices in [409961033, 431560666) total of 21599633 documents +0: test: +0: document indices in [431560666, 431992659) total of 431993 documents +0: > WARNING: could not find index map files, building the indices on rank 0 ... +0: > only one epoch required, setting separate_last_epoch to False +0: > elasped time to build and save doc-idx mapping (seconds): 31.309405 +0: using: +0: number of documents: 409961033 +0: number of epochs: 1 +0: sequence length: 2048 +0: total number of samples: 262636457 +0: > elasped time to build and save sample-idx mapping (seconds): 7.720821 +0: > building shuffle index with split [0, 262636457) and [262636457, 262636457) ... +0: > elasped time to build and save shuffle-idx mapping (seconds): 16.104907 +0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_1922149ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_1922149ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_1922149ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.382 seconds +0: total number of samples: 262636458 +0: total number of epochs: 1 +0: > WARNING: could not find index map files, building the indices on rank 0 ... +0: > only one epoch required, setting separate_last_epoch to False +0: > elasped time to build and save doc-idx mapping (seconds): 1.171745 +0: using: +0: number of documents: 21599633 +0: number of epochs: 1 +0: sequence length: 2048 +0: total number of samples: 13852049 +0: > elasped time to build and save sample-idx mapping (seconds): 0.415211 +0: > building shuffle index with split [0, 13852049) and [13852049, 13852049) ... +0: > elasped time to build and save shuffle-idx mapping (seconds): 0.476429 +0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_2048ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_2048ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_2048ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.036 seconds +0: total number of samples: 13852050 +0: total number of epochs: 1 +0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_256ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_256ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_256ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.033 seconds +0: total number of samples: 276852 +0: total number of epochs: 1 +0: > finished creating GPT datasets ... +0: [after dataloaders are built] datetime: 2022-11-29 16:55:08 +0: done with setup ... +0: training ... +0: Number of parameters: [tensor rank - pipeline rank] w/ and w/o embeddings: +7: time (ms) | model-and-optimizer-setup: 15534.67 | train/valid/test-data-iterators-setup: 86357.56 +0: [000-000] 0.4212B / 0.3542B +0: [before the start of training step] datetime: 2022-11-29 16:55:08 +0: [Rank 0] (after 10 iterations) memory (MB) | allocated: 4873.00537109375 | max allocated: 27817.7919921875 | reserved: 29816.0 | max reserved: 29816.0 +7: iteration 10/ 7508 | consumed samples: 2560 | consumed tokens: 5242880 | elapsed time per iteration (s): 1.74 | learning rate: 2.664E-05 | global batch size: 256 | lm loss: 1.011599E+01 | grad norm: 3.685 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 147.190 | TFLOPs: 14.03 | +7: iteration 20/ 7508 | consumed samples: 5120 | consumed tokens: 10485760 | elapsed time per iteration (s): 0.58 | learning rate: 5.328E-05 | global batch size: 256 | lm loss: 9.053841E+00 | grad norm: 1.769 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.119 | TFLOPs: 41.96 | +7: iteration 30/ 7508 | consumed samples: 7680 | consumed tokens: 15728640 | elapsed time per iteration (s): 0.58 | learning rate: 7.991E-05 | global batch size: 256 | lm loss: 8.513687E+00 | grad norm: 1.866 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.471 | TFLOPs: 41.90 | +7: iteration 40/ 7508 | consumed samples: 10240 | consumed tokens: 20971520 | elapsed time per iteration (s): 0.58 | learning rate: 1.066E-04 | global batch size: 256 | lm loss: 7.765112E+00 | grad norm: 1.513 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.806 | TFLOPs: 42.41 | +7: iteration 50/ 7508 | consumed samples: 12800 | consumed tokens: 26214400 | elapsed time per iteration (s): 0.58 | learning rate: 1.332E-04 | global batch size: 256 | lm loss: 7.414233E+00 | grad norm: 0.635 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.062 | TFLOPs: 41.96 | +7: iteration 60/ 7508 | consumed samples: 15360 | consumed tokens: 31457280 | elapsed time per iteration (s): 0.61 | learning rate: 1.598E-04 | global batch size: 256 | lm loss: 7.184543E+00 | grad norm: 1.678 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 418.910 | TFLOPs: 39.94 | +7: iteration 70/ 7508 | consumed samples: 17920 | consumed tokens: 36700160 | elapsed time per iteration (s): 0.59 | learning rate: 1.865E-04 | global batch size: 256 | lm loss: 7.002280E+00 | grad norm: 0.899 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.493 | TFLOPs: 41.71 | +7: iteration 80/ 7508 | consumed samples: 20480 | consumed tokens: 41943040 | elapsed time per iteration (s): 0.57 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.871595E+00 | grad norm: 1.048 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.537 | TFLOPs: 42.86 | +7: iteration 90/ 7508 | consumed samples: 23040 | consumed tokens: 47185920 | elapsed time per iteration (s): 0.57 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.669206E+00 | grad norm: 0.784 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.072 | TFLOPs: 42.72 | +7: iteration 100/ 7508 | consumed samples: 25600 | consumed tokens: 52428800 | elapsed time per iteration (s): 0.58 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.565200E+00 | grad norm: 0.496 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.211 | TFLOPs: 42.26 | +7: iteration 110/ 7508 | consumed samples: 28160 | consumed tokens: 57671680 | elapsed time per iteration (s): 0.58 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.461543E+00 | grad norm: 0.938 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.867 | TFLOPs: 42.13 | +7: iteration 120/ 7508 | consumed samples: 30720 | consumed tokens: 62914560 | elapsed time per iteration (s): 0.59 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.419253E+00 | grad norm: 0.557 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 430.799 | TFLOPs: 41.07 | +7: iteration 130/ 7508 | consumed samples: 33280 | consumed tokens: 68157440 | elapsed time per iteration (s): 0.59 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.299912E+00 | grad norm: 0.581 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.871 | TFLOPs: 41.46 | +7: iteration 140/ 7508 | consumed samples: 35840 | consumed tokens: 73400320 | elapsed time per iteration (s): 0.60 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.251768E+00 | grad norm: 0.574 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 428.042 | TFLOPs: 40.81 | +7: iteration 150/ 7508 | consumed samples: 38400 | consumed tokens: 78643200 | elapsed time per iteration (s): 0.60 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.175555E+00 | grad norm: 0.648 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 426.924 | TFLOPs: 40.70 | +7: iteration 160/ 7508 | consumed samples: 40960 | consumed tokens: 83886080 | elapsed time per iteration (s): 0.56 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 6.163150E+00 | grad norm: 0.682 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.840 | TFLOPs: 43.46 | +7: iteration 170/ 7508 | consumed samples: 43520 | consumed tokens: 89128960 | elapsed time per iteration (s): 0.58 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 6.106737E+00 | grad norm: 0.477 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.946 | TFLOPs: 42.33 | +7: iteration 180/ 7508 | consumed samples: 46080 | consumed tokens: 94371840 | elapsed time per iteration (s): 0.57 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 6.059523E+00 | grad norm: 0.888 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.168 | TFLOPs: 42.92 | +7: iteration 190/ 7508 | consumed samples: 48640 | consumed tokens: 99614720 | elapsed time per iteration (s): 0.58 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 6.033111E+00 | grad norm: 0.472 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.521 | TFLOPs: 42.00 | +7: iteration 200/ 7508 | consumed samples: 51200 | consumed tokens: 104857600 | elapsed time per iteration (s): 0.59 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 6.008368E+00 | grad norm: 0.515 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 433.448 | TFLOPs: 41.32 | +7: iteration 210/ 7508 | consumed samples: 53760 | consumed tokens: 110100480 | elapsed time per iteration (s): 0.57 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.931927E+00 | grad norm: 0.789 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.941 | TFLOPs: 42.61 | +7: iteration 220/ 7508 | consumed samples: 56320 | consumed tokens: 115343360 | elapsed time per iteration (s): 0.56 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.913456E+00 | grad norm: 0.729 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.605 | TFLOPs: 43.25 | +7: iteration 230/ 7508 | consumed samples: 58880 | consumed tokens: 120586240 | elapsed time per iteration (s): 0.57 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.841859E+00 | grad norm: 0.607 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.295 | TFLOPs: 42.84 | +7: iteration 240/ 7508 | consumed samples: 61440 | consumed tokens: 125829120 | elapsed time per iteration (s): 0.59 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.778090E+00 | grad norm: 0.926 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 430.330 | TFLOPs: 41.03 | +7: iteration 250/ 7508 | consumed samples: 64000 | consumed tokens: 131072000 | elapsed time per iteration (s): 0.57 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.808302E+00 | grad norm: 0.650 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.230 | TFLOPs: 42.64 | +7: iteration 260/ 7508 | consumed samples: 66560 | consumed tokens: 136314880 | elapsed time per iteration (s): 0.57 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 5.777892E+00 | grad norm: 0.516 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.121 | TFLOPs: 42.53 | +7: iteration 270/ 7508 | consumed samples: 69120 | consumed tokens: 141557760 | elapsed time per iteration (s): 0.57 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 5.692069E+00 | grad norm: 0.938 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.248 | TFLOPs: 42.54 | +7: iteration 280/ 7508 | consumed samples: 71680 | consumed tokens: 146800640 | elapsed time per iteration (s): 0.61 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 5.695877E+00 | grad norm: 0.581 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 422.650 | TFLOPs: 40.30 | +7: iteration 290/ 7508 | consumed samples: 74240 | consumed tokens: 152043520 | elapsed time per iteration (s): 0.58 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 5.641705E+00 | grad norm: 1.072 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.808 | TFLOPs: 41.84 | +7: iteration 300/ 7508 | consumed samples: 76800 | consumed tokens: 157286400 | elapsed time per iteration (s): 0.58 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 5.596622E+00 | grad norm: 0.533 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.075 | TFLOPs: 41.96 | +7: iteration 310/ 7508 | consumed samples: 79360 | consumed tokens: 162529280 | elapsed time per iteration (s): 0.59 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 5.545544E+00 | grad norm: 0.903 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.855 | TFLOPs: 41.46 | +7: iteration 320/ 7508 | consumed samples: 81920 | consumed tokens: 167772160 | elapsed time per iteration (s): 0.58 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 5.523584E+00 | grad norm: 0.808 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.563 | TFLOPs: 41.81 | +7: iteration 330/ 7508 | consumed samples: 84480 | consumed tokens: 173015040 | elapsed time per iteration (s): 0.59 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 5.511876E+00 | grad norm: 0.578 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 430.342 | TFLOPs: 41.03 | +7: iteration 340/ 7508 | consumed samples: 87040 | consumed tokens: 178257920 | elapsed time per iteration (s): 0.58 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 5.458582E+00 | grad norm: 0.741 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.602 | TFLOPs: 42.01 | +7: iteration 350/ 7508 | consumed samples: 89600 | consumed tokens: 183500800 | elapsed time per iteration (s): 0.58 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 5.413711E+00 | grad norm: 0.780 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.495 | TFLOPs: 42.28 | +7: iteration 360/ 7508 | consumed samples: 92160 | consumed tokens: 188743680 | elapsed time per iteration (s): 0.57 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 5.386201E+00 | grad norm: 0.634 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.442 | TFLOPs: 42.66 | +7: iteration 370/ 7508 | consumed samples: 94720 | consumed tokens: 193986560 | elapsed time per iteration (s): 0.57 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 5.353096E+00 | grad norm: 0.735 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.181 | TFLOPs: 42.63 | +7: iteration 380/ 7508 | consumed samples: 97280 | consumed tokens: 199229440 | elapsed time per iteration (s): 0.58 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 5.280307E+00 | grad norm: 0.691 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.923 | TFLOPs: 42.23 | +7: iteration 390/ 7508 | consumed samples: 99840 | consumed tokens: 204472320 | elapsed time per iteration (s): 0.58 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 5.270271E+00 | grad norm: 1.041 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.703 | TFLOPs: 42.02 | +7: iteration 400/ 7508 | consumed samples: 102400 | consumed tokens: 209715200 | elapsed time per iteration (s): 0.57 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 5.233796E+00 | grad norm: 0.616 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.383 | TFLOPs: 42.75 | +7: iteration 410/ 7508 | consumed samples: 104960 | consumed tokens: 214958080 | elapsed time per iteration (s): 0.58 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 5.195114E+00 | grad norm: 0.883 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.020 | TFLOPs: 42.24 | +7: iteration 420/ 7508 | consumed samples: 107520 | consumed tokens: 220200960 | elapsed time per iteration (s): 0.56 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 5.177555E+00 | grad norm: 0.558 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.197 | TFLOPs: 43.21 | +7: iteration 430/ 7508 | consumed samples: 110080 | consumed tokens: 225443840 | elapsed time per iteration (s): 0.58 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 5.108966E+00 | grad norm: 0.797 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.639 | TFLOPs: 42.01 | +7: iteration 440/ 7508 | consumed samples: 112640 | consumed tokens: 230686720 | elapsed time per iteration (s): 0.58 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 5.085802E+00 | grad norm: 0.872 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.050 | TFLOPs: 42.05 | +7: iteration 450/ 7508 | consumed samples: 115200 | consumed tokens: 235929600 | elapsed time per iteration (s): 0.58 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 5.051328E+00 | grad norm: 0.723 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.786 | TFLOPs: 42.31 | +7: iteration 460/ 7508 | consumed samples: 117760 | consumed tokens: 241172480 | elapsed time per iteration (s): 0.57 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 5.049822E+00 | grad norm: 0.847 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.476 | TFLOPs: 42.47 | +7: iteration 470/ 7508 | consumed samples: 120320 | consumed tokens: 246415360 | elapsed time per iteration (s): 0.58 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 4.998730E+00 | grad norm: 0.854 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.106 | TFLOPs: 41.86 | +7: iteration 480/ 7508 | consumed samples: 122880 | consumed tokens: 251658240 | elapsed time per iteration (s): 0.58 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 4.986995E+00 | grad norm: 0.692 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.555 | TFLOPs: 42.00 | +7: iteration 490/ 7508 | consumed samples: 125440 | consumed tokens: 256901120 | elapsed time per iteration (s): 0.58 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 4.936140E+00 | grad norm: 0.819 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.839 | TFLOPs: 42.12 | +7: iteration 500/ 7508 | consumed samples: 128000 | consumed tokens: 262144000 | elapsed time per iteration (s): 0.59 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 4.915062E+00 | grad norm: 0.774 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.419 | TFLOPs: 41.61 | +7: iteration 510/ 7508 | consumed samples: 130560 | consumed tokens: 267386880 | elapsed time per iteration (s): 0.58 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 4.881478E+00 | grad norm: 0.787 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.474 | TFLOPs: 41.99 | +7: iteration 520/ 7508 | consumed samples: 133120 | consumed tokens: 272629760 | elapsed time per iteration (s): 0.58 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 4.800521E+00 | grad norm: 0.600 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.852 | TFLOPs: 42.03 | +7: iteration 530/ 7508 | consumed samples: 135680 | consumed tokens: 277872640 | elapsed time per iteration (s): 0.58 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 4.776206E+00 | grad norm: 0.835 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.718 | TFLOPs: 42.11 | +7: iteration 540/ 7508 | consumed samples: 138240 | consumed tokens: 283115520 | elapsed time per iteration (s): 0.57 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 4.777618E+00 | grad norm: 0.879 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.964 | TFLOPs: 42.80 | +7: iteration 550/ 7508 | consumed samples: 140800 | consumed tokens: 288358400 | elapsed time per iteration (s): 0.58 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 4.710006E+00 | grad norm: 1.024 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.560 | TFLOPs: 42.10 | +7: iteration 560/ 7508 | consumed samples: 143360 | consumed tokens: 293601280 | elapsed time per iteration (s): 0.58 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 4.669544E+00 | grad norm: 0.827 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.986 | TFLOPs: 42.42 | +7: iteration 570/ 7508 | consumed samples: 145920 | consumed tokens: 298844160 | elapsed time per iteration (s): 0.58 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 4.604503E+00 | grad norm: 0.834 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.013 | TFLOPs: 41.76 | +7: iteration 580/ 7508 | consumed samples: 148480 | consumed tokens: 304087040 | elapsed time per iteration (s): 0.58 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 4.554647E+00 | grad norm: 0.900 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.934 | TFLOPs: 42.32 | +7: iteration 590/ 7508 | consumed samples: 151040 | consumed tokens: 309329920 | elapsed time per iteration (s): 0.58 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 4.522474E+00 | grad norm: 0.929 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.405 | TFLOPs: 41.80 | +7: iteration 600/ 7508 | consumed samples: 153600 | consumed tokens: 314572800 | elapsed time per iteration (s): 0.58 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 4.464238E+00 | grad norm: 0.727 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.312 | TFLOPs: 42.36 | +7: iteration 610/ 7508 | consumed samples: 156160 | consumed tokens: 319815680 | elapsed time per iteration (s): 0.57 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 4.429767E+00 | grad norm: 0.621 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.939 | TFLOPs: 42.52 | +7: iteration 620/ 7508 | consumed samples: 158720 | consumed tokens: 325058560 | elapsed time per iteration (s): 0.57 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 4.390846E+00 | grad norm: 0.782 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.994 | TFLOPs: 42.90 | +7: iteration 630/ 7508 | consumed samples: 161280 | consumed tokens: 330301440 | elapsed time per iteration (s): 0.57 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 4.368159E+00 | grad norm: 0.715 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.051 | TFLOPs: 42.62 | +7: iteration 640/ 7508 | consumed samples: 163840 | consumed tokens: 335544320 | elapsed time per iteration (s): 0.57 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 4.350128E+00 | grad norm: 0.710 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.690 | TFLOPs: 42.59 | +7: iteration 650/ 7508 | consumed samples: 166400 | consumed tokens: 340787200 | elapsed time per iteration (s): 0.56 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 4.297277E+00 | grad norm: 0.634 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.806 | TFLOPs: 43.36 | +7: iteration 660/ 7508 | consumed samples: 168960 | consumed tokens: 346030080 | elapsed time per iteration (s): 0.59 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 4.286876E+00 | grad norm: 0.560 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.324 | TFLOPs: 41.60 | +7: iteration 670/ 7508 | consumed samples: 171520 | consumed tokens: 351272960 | elapsed time per iteration (s): 0.56 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 4.241048E+00 | grad norm: 0.772 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.875 | TFLOPs: 43.27 | +7: iteration 680/ 7508 | consumed samples: 174080 | consumed tokens: 356515840 | elapsed time per iteration (s): 0.57 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 4.234269E+00 | grad norm: 0.618 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.750 | TFLOPs: 43.16 | +7: iteration 690/ 7508 | consumed samples: 176640 | consumed tokens: 361758720 | elapsed time per iteration (s): 0.58 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 4.213050E+00 | grad norm: 0.747 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.853 | TFLOPs: 41.84 | +7: iteration 700/ 7508 | consumed samples: 179200 | consumed tokens: 367001600 | elapsed time per iteration (s): 0.57 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 4.215577E+00 | grad norm: 0.675 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.727 | TFLOPs: 42.59 | +7: iteration 710/ 7508 | consumed samples: 181760 | consumed tokens: 372244480 | elapsed time per iteration (s): 0.58 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 4.161447E+00 | grad norm: 0.601 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.374 | TFLOPs: 41.89 | +7: iteration 720/ 7508 | consumed samples: 184320 | consumed tokens: 377487360 | elapsed time per iteration (s): 0.58 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 4.169796E+00 | grad norm: 0.468 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.100 | TFLOPs: 42.05 | +7: iteration 730/ 7508 | consumed samples: 186880 | consumed tokens: 382730240 | elapsed time per iteration (s): 0.58 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 4.147791E+00 | grad norm: 0.562 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.940 | TFLOPs: 42.23 | +7: iteration 740/ 7508 | consumed samples: 189440 | consumed tokens: 387973120 | elapsed time per iteration (s): 0.58 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 4.135317E+00 | grad norm: 0.650 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.837 | TFLOPs: 42.03 | +7: iteration 750/ 7508 | consumed samples: 192000 | consumed tokens: 393216000 | elapsed time per iteration (s): 0.57 | learning rate: 1.964E-04 | global batch size: 256 | lm loss: 4.097876E+00 | grad norm: 0.717 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.772 | TFLOPs: 42.50 | +7: iteration 760/ 7508 | consumed samples: 194560 | consumed tokens: 398458880 | elapsed time per iteration (s): 0.57 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 4.095400E+00 | grad norm: 0.524 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.026 | TFLOPs: 42.71 | +7: iteration 770/ 7508 | consumed samples: 197120 | consumed tokens: 403701760 | elapsed time per iteration (s): 0.58 | learning rate: 1.961E-04 | global batch size: 256 | lm loss: 4.085460E+00 | grad norm: 1.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.833 | TFLOPs: 42.31 | +7: iteration 780/ 7508 | consumed samples: 199680 | consumed tokens: 408944640 | elapsed time per iteration (s): 0.57 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 4.091854E+00 | grad norm: 0.678 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.924 | TFLOPs: 42.80 | +7: iteration 790/ 7508 | consumed samples: 202240 | consumed tokens: 414187520 | elapsed time per iteration (s): 0.57 | learning rate: 1.959E-04 | global batch size: 256 | lm loss: 4.060580E+00 | grad norm: 0.566 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.607 | TFLOPs: 42.58 | +7: iteration 800/ 7508 | consumed samples: 204800 | consumed tokens: 419430400 | elapsed time per iteration (s): 0.59 | learning rate: 1.958E-04 | global batch size: 256 | lm loss: 4.066114E+00 | grad norm: 0.586 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.084 | TFLOPs: 41.48 | +7: iteration 810/ 7508 | consumed samples: 207360 | consumed tokens: 424673280 | elapsed time per iteration (s): 0.58 | learning rate: 1.957E-04 | global batch size: 256 | lm loss: 4.026172E+00 | grad norm: 0.454 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.314 | TFLOPs: 42.36 | +7: iteration 820/ 7508 | consumed samples: 209920 | consumed tokens: 429916160 | elapsed time per iteration (s): 0.57 | learning rate: 1.956E-04 | global batch size: 256 | lm loss: 3.986280E+00 | grad norm: 0.638 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.573 | TFLOPs: 42.96 | +7: iteration 830/ 7508 | consumed samples: 212480 | consumed tokens: 435159040 | elapsed time per iteration (s): 0.56 | learning rate: 1.955E-04 | global batch size: 256 | lm loss: 4.052116E+00 | grad norm: 0.528 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.615 | TFLOPs: 43.44 | +7: iteration 840/ 7508 | consumed samples: 215040 | consumed tokens: 440401920 | elapsed time per iteration (s): 0.57 | learning rate: 1.953E-04 | global batch size: 256 | lm loss: 4.058575E+00 | grad norm: 0.893 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.768 | TFLOPs: 42.59 | +7: iteration 850/ 7508 | consumed samples: 217600 | consumed tokens: 445644800 | elapsed time per iteration (s): 0.57 | learning rate: 1.952E-04 | global batch size: 256 | lm loss: 4.007571E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.926 | TFLOPs: 42.61 | +7: iteration 860/ 7508 | consumed samples: 220160 | consumed tokens: 450887680 | elapsed time per iteration (s): 0.56 | learning rate: 1.951E-04 | global batch size: 256 | lm loss: 3.974209E+00 | grad norm: 0.606 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.054 | TFLOPs: 43.29 | +7: iteration 870/ 7508 | consumed samples: 222720 | consumed tokens: 456130560 | elapsed time per iteration (s): 0.58 | learning rate: 1.950E-04 | global batch size: 256 | lm loss: 3.963317E+00 | grad norm: 0.525 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.828 | TFLOPs: 42.12 | +7: iteration 880/ 7508 | consumed samples: 225280 | consumed tokens: 461373440 | elapsed time per iteration (s): 0.58 | learning rate: 1.948E-04 | global batch size: 256 | lm loss: 3.937642E+00 | grad norm: 0.423 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.711 | TFLOPs: 41.73 | +7: iteration 890/ 7508 | consumed samples: 227840 | consumed tokens: 466616320 | elapsed time per iteration (s): 0.57 | learning rate: 1.947E-04 | global batch size: 256 | lm loss: 3.921901E+00 | grad norm: 0.476 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.620 | TFLOPs: 42.68 | +7: iteration 900/ 7508 | consumed samples: 230400 | consumed tokens: 471859200 | elapsed time per iteration (s): 0.56 | learning rate: 1.946E-04 | global batch size: 256 | lm loss: 3.957717E+00 | grad norm: 0.440 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.773 | TFLOPs: 43.45 | +7: iteration 910/ 7508 | consumed samples: 232960 | consumed tokens: 477102080 | elapsed time per iteration (s): 0.59 | learning rate: 1.945E-04 | global batch size: 256 | lm loss: 3.939356E+00 | grad norm: 0.481 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.095 | TFLOPs: 41.58 | +7: iteration 920/ 7508 | consumed samples: 235520 | consumed tokens: 482344960 | elapsed time per iteration (s): 0.60 | learning rate: 1.943E-04 | global batch size: 256 | lm loss: 3.887627E+00 | grad norm: 0.463 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 427.414 | TFLOPs: 40.75 | +7: iteration 930/ 7508 | consumed samples: 238080 | consumed tokens: 487587840 | elapsed time per iteration (s): 0.56 | learning rate: 1.942E-04 | global batch size: 256 | lm loss: 3.889836E+00 | grad norm: 0.475 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.314 | TFLOPs: 43.60 | +7: iteration 940/ 7508 | consumed samples: 240640 | consumed tokens: 492830720 | elapsed time per iteration (s): 0.59 | learning rate: 1.941E-04 | global batch size: 256 | lm loss: 3.857352E+00 | grad norm: 0.447 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.842 | TFLOPs: 41.65 | +7: iteration 950/ 7508 | consumed samples: 243200 | consumed tokens: 498073600 | elapsed time per iteration (s): 0.57 | learning rate: 1.939E-04 | global batch size: 256 | lm loss: 3.869463E+00 | grad norm: 0.665 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.420 | TFLOPs: 42.85 | +7: iteration 960/ 7508 | consumed samples: 245760 | consumed tokens: 503316480 | elapsed time per iteration (s): 0.57 | learning rate: 1.938E-04 | global batch size: 256 | lm loss: 3.896463E+00 | grad norm: 0.517 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.671 | TFLOPs: 43.16 | +7: iteration 970/ 7508 | consumed samples: 248320 | consumed tokens: 508559360 | elapsed time per iteration (s): 0.57 | learning rate: 1.936E-04 | global batch size: 256 | lm loss: 3.889107E+00 | grad norm: 0.505 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.743 | TFLOPs: 42.50 | +7: iteration 980/ 7508 | consumed samples: 250880 | consumed tokens: 513802240 | elapsed time per iteration (s): 0.57 | learning rate: 1.935E-04 | global batch size: 256 | lm loss: 3.865255E+00 | grad norm: 0.394 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.843 | TFLOPs: 42.51 | +7: iteration 990/ 7508 | consumed samples: 253440 | consumed tokens: 519045120 | elapsed time per iteration (s): 0.59 | learning rate: 1.934E-04 | global batch size: 256 | lm loss: 3.826718E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.324 | TFLOPs: 41.41 | +7: iteration 1000/ 7508 | consumed samples: 256000 | consumed tokens: 524288000 | elapsed time per iteration (s): 0.58 | learning rate: 1.932E-04 | global batch size: 256 | lm loss: 3.850665E+00 | grad norm: 0.496 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.375 | TFLOPs: 41.79 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 1000 | lm loss value: 3.699024E+00 | lm loss PPL: 4.040786E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 1000 to checkpoints_421moscar +0: [2022-11-29 17:04:58,769] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step1000 is begin to save! +0: [2022-11-29 17:04:58,789] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:04:58,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:04:58,938] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:04:58,979] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:04:58,980] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:04:59,022] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:04:59,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:04:59,065] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:04:59,065] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:04:59,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:04:59,105] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:04:59,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:04:59,146] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:04:59,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:04:59,185] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:04:59,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:04:59,225] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:04:59,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:04:59,265] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:04:59,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:04:59,304] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:04:59,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:04:59,344] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:04:59,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:04:59,384] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:04:59,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:04:59,423] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:04:59,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:04:59,462] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:04:59,501] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:04:59,502] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:04:59,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:04:59,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/layer_18-model_00-model_states.pt... +0: [2022-11-29 17:04:59,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/layer_18-model_00-model_states.pt. +0: [2022-11-29 17:04:59,582] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:04:59,622] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:04:59,622] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/layer_20-model_00-model_states.pt... +0: [2022-11-29 17:04:59,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/layer_20-model_00-model_states.pt. +0: [2022-11-29 17:04:59,663] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/layer_22-model_00-model_states.pt... +0: [2022-11-29 17:04:59,666] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/layer_22-model_00-model_states.pt. +0: [2022-11-29 17:04:59,667] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_421moscar/global_step1000/mp_rank_00_model_states.pt +0: [2022-11-29 17:04:59,667] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:04:59,670] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:04:59,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:04:59,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:04:59,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:04:59,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:04:59,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:04:59,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:04:59,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:04:59,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:04:59,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:04:59,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:04:59,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:04:59,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:04:59,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:04:59,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:04:59,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:04:59,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:04:59,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:04:59,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:04:59,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:04:59,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:04:59,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:04:59,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:04:59,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:04:59,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:04:59,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:04:59,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:04:59,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:04:59,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:04:59,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:04:59,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:04:59,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:04:59,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:04:59,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:04:59,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:04:59,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:04:59,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:04:59,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:04:59,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:04:59,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:04:59,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:04:59,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:04:59,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:04:59,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:04:59,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:04:59,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:04:59,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:04:59,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:04:59,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:04:59,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:04:59,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:04:59,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:04:59,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:04:59,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:04:59,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:04:59,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:04:59,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:04:59,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:04:59,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:04:59,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:04:59,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:04:59,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:04:59,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:04:59,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:04:59,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:04:59,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:04:59,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:04:59,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:04:59,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:04:59,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:04:59,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:04:59,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:04:59,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:04:59,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:04:59,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:04:59,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:04:59,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:04:59,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:04:59,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:04:59,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:04:59,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:04:59,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:04:59,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:04:59,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:04:59,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:04:59,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:04:59,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:04:59,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:04:59,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:04:59,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:04:59,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:04:59,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:04:59,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:04:59,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:04:59,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:04:59,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:04:59,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:04:59,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:04:59,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:04:59,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:04:59,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:04:59,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:04:59,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:04:59,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:04:59,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:04:59,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:04:59,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:04:59,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:04:59,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:04:59,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:04:59,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:04:59,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:04:59,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:04:59,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:04:59,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:04:59,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:04:59,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:04:59,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:04:59,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:04:59,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:04:59,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:04:59,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:04:59,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:04:59,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:04:59,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:04:59,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:04:59,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:04:59,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:04:59,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:04:59,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:04:59,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:04:59,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:04:59,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:04:59,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:04:59,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:04:59,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:04:59,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:04:59,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:04:59,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:04:59,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:04:59,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:04:59,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:04:59,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:04:59,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:04:59,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:04:59,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:04:59,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:04:59,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:04:59,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:04:59,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:04:59,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:04:59,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:04:59,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:04:59,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:04:59,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:04:59,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:04:59,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:04:59,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:04:59,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:04:59,876] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:04:59,876] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:04:59,876] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:04:59,877] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:04:59,877] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:04:59,877] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:04:59,877] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:04:59,877] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:04:59,877] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:04:59,880] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:04:59,880] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:04:59,880] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:04:59,880] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:04:59,880] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:04:59,880] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:04:59,880] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:04:59,880] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:04:59,880] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:04:59,880] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:04:59,880] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:04:59,880] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:04:59,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:04:59,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:04:59,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:04:59,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:04:59,888] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:04:59,888] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:04:59,888] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:04:59,888] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:04:59,888] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:04:59,888] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:04:59,888] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:04:59,888] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:04:59,893] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:04:59,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: successfully saved checkpoint at iteration 1000 to checkpoints_421moscar +7: time (ms) | save-checkpoint: 1137.20 +7: iteration 1010/ 7508 | consumed samples: 258560 | consumed tokens: 529530880 | elapsed time per iteration (s): 0.69 | learning rate: 1.931E-04 | global batch size: 256 | lm loss: 3.812946E+00 | grad norm: 0.380 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 372.542 | TFLOPs: 35.52 | +7: iteration 1020/ 7508 | consumed samples: 261120 | consumed tokens: 534773760 | elapsed time per iteration (s): 0.58 | learning rate: 1.929E-04 | global batch size: 256 | lm loss: 3.816032E+00 | grad norm: 0.510 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.139 | TFLOPs: 41.87 | +7: iteration 1030/ 7508 | consumed samples: 263680 | consumed tokens: 540016640 | elapsed time per iteration (s): 0.57 | learning rate: 1.928E-04 | global batch size: 256 | lm loss: 3.804195E+00 | grad norm: 0.390 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.412 | TFLOPs: 42.56 | +7: iteration 1040/ 7508 | consumed samples: 266240 | consumed tokens: 545259520 | elapsed time per iteration (s): 0.58 | learning rate: 1.926E-04 | global batch size: 256 | lm loss: 3.772643E+00 | grad norm: 0.482 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.356 | TFLOPs: 41.89 | +7: iteration 1050/ 7508 | consumed samples: 268800 | consumed tokens: 550502400 | elapsed time per iteration (s): 0.57 | learning rate: 1.925E-04 | global batch size: 256 | lm loss: 3.783342E+00 | grad norm: 0.452 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.053 | TFLOPs: 42.62 | +7: iteration 1060/ 7508 | consumed samples: 271360 | consumed tokens: 555745280 | elapsed time per iteration (s): 0.58 | learning rate: 1.923E-04 | global batch size: 256 | lm loss: 3.792322E+00 | grad norm: 0.477 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.583 | TFLOPs: 42.29 | +7: iteration 1070/ 7508 | consumed samples: 273920 | consumed tokens: 560988160 | elapsed time per iteration (s): 0.58 | learning rate: 1.922E-04 | global batch size: 256 | lm loss: 3.759330E+00 | grad norm: 0.380 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.604 | TFLOPs: 42.20 | +7: iteration 1080/ 7508 | consumed samples: 276480 | consumed tokens: 566231040 | elapsed time per iteration (s): 0.58 | learning rate: 1.920E-04 | global batch size: 256 | lm loss: 3.760675E+00 | grad norm: 0.465 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.830 | TFLOPs: 42.31 | +7: iteration 1090/ 7508 | consumed samples: 279040 | consumed tokens: 571473920 | elapsed time per iteration (s): 0.57 | learning rate: 1.918E-04 | global batch size: 256 | lm loss: 3.764798E+00 | grad norm: 0.527 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.255 | TFLOPs: 42.83 | +7: iteration 1100/ 7508 | consumed samples: 281600 | consumed tokens: 576716800 | elapsed time per iteration (s): 0.57 | learning rate: 1.917E-04 | global batch size: 256 | lm loss: 3.754591E+00 | grad norm: 0.397 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.946 | TFLOPs: 42.80 | +7: iteration 1110/ 7508 | consumed samples: 284160 | consumed tokens: 581959680 | elapsed time per iteration (s): 0.57 | learning rate: 1.915E-04 | global batch size: 256 | lm loss: 3.712647E+00 | grad norm: 0.567 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.615 | TFLOPs: 43.06 | +7: iteration 1120/ 7508 | consumed samples: 286720 | consumed tokens: 587202560 | elapsed time per iteration (s): 0.56 | learning rate: 1.914E-04 | global batch size: 256 | lm loss: 3.725897E+00 | grad norm: 0.567 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.352 | TFLOPs: 43.51 | +7: iteration 1130/ 7508 | consumed samples: 289280 | consumed tokens: 592445440 | elapsed time per iteration (s): 0.59 | learning rate: 1.912E-04 | global batch size: 256 | lm loss: 3.721237E+00 | grad norm: 0.554 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.580 | TFLOPs: 41.62 | +7: iteration 1140/ 7508 | consumed samples: 291840 | consumed tokens: 597688320 | elapsed time per iteration (s): 0.58 | learning rate: 1.910E-04 | global batch size: 256 | lm loss: 3.730838E+00 | grad norm: 0.445 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.419 | TFLOPs: 42.28 | +7: iteration 1150/ 7508 | consumed samples: 294400 | consumed tokens: 602931200 | elapsed time per iteration (s): 0.58 | learning rate: 1.909E-04 | global batch size: 256 | lm loss: 3.708297E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.037 | TFLOPs: 42.43 | +7: iteration 1160/ 7508 | consumed samples: 296960 | consumed tokens: 608174080 | elapsed time per iteration (s): 0.56 | learning rate: 1.907E-04 | global batch size: 256 | lm loss: 3.726886E+00 | grad norm: 0.405 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.267 | TFLOPs: 43.21 | +7: iteration 1170/ 7508 | consumed samples: 299520 | consumed tokens: 613416960 | elapsed time per iteration (s): 0.57 | learning rate: 1.905E-04 | global batch size: 256 | lm loss: 3.715210E+00 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.032 | TFLOPs: 43.00 | +7: iteration 1180/ 7508 | consumed samples: 302080 | consumed tokens: 618659840 | elapsed time per iteration (s): 0.58 | learning rate: 1.904E-04 | global batch size: 256 | lm loss: 3.702241E+00 | grad norm: 0.778 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.730 | TFLOPs: 42.30 | +7: iteration 1190/ 7508 | consumed samples: 304640 | consumed tokens: 623902720 | elapsed time per iteration (s): 0.57 | learning rate: 1.902E-04 | global batch size: 256 | lm loss: 3.773890E+00 | grad norm: 0.673 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.564 | TFLOPs: 42.48 | +7: iteration 1200/ 7508 | consumed samples: 307200 | consumed tokens: 629145600 | elapsed time per iteration (s): 0.59 | learning rate: 1.900E-04 | global batch size: 256 | lm loss: 3.708602E+00 | grad norm: 0.396 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 430.952 | TFLOPs: 41.09 | +7: iteration 1210/ 7508 | consumed samples: 309760 | consumed tokens: 634388480 | elapsed time per iteration (s): 0.58 | learning rate: 1.898E-04 | global batch size: 256 | lm loss: 3.686135E+00 | grad norm: 0.418 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.427 | TFLOPs: 41.80 | +7: iteration 1220/ 7508 | consumed samples: 312320 | consumed tokens: 639631360 | elapsed time per iteration (s): 0.57 | learning rate: 1.897E-04 | global batch size: 256 | lm loss: 3.687551E+00 | grad norm: 0.403 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.882 | TFLOPs: 42.70 | +7: iteration 1230/ 7508 | consumed samples: 314880 | consumed tokens: 644874240 | elapsed time per iteration (s): 0.59 | learning rate: 1.895E-04 | global batch size: 256 | lm loss: 3.679284E+00 | grad norm: 0.421 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.735 | TFLOPs: 41.64 | +7: iteration 1240/ 7508 | consumed samples: 317440 | consumed tokens: 650117120 | elapsed time per iteration (s): 0.57 | learning rate: 1.893E-04 | global batch size: 256 | lm loss: 3.702387E+00 | grad norm: 0.486 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.980 | TFLOPs: 42.90 | +7: iteration 1250/ 7508 | consumed samples: 320000 | consumed tokens: 655360000 | elapsed time per iteration (s): 0.59 | learning rate: 1.891E-04 | global batch size: 256 | lm loss: 3.672065E+00 | grad norm: 0.404 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.496 | TFLOPs: 41.42 | +7: iteration 1260/ 7508 | consumed samples: 322560 | consumed tokens: 660602880 | elapsed time per iteration (s): 0.57 | learning rate: 1.889E-04 | global batch size: 256 | lm loss: 3.673933E+00 | grad norm: 0.464 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.152 | TFLOPs: 43.11 | +7: iteration 1270/ 7508 | consumed samples: 325120 | consumed tokens: 665845760 | elapsed time per iteration (s): 0.57 | learning rate: 1.888E-04 | global batch size: 256 | lm loss: 3.668316E+00 | grad norm: 0.436 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.508 | TFLOPs: 42.86 | +7: iteration 1280/ 7508 | consumed samples: 327680 | consumed tokens: 671088640 | elapsed time per iteration (s): 0.57 | learning rate: 1.886E-04 | global batch size: 256 | lm loss: 3.656165E+00 | grad norm: 0.415 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.427 | TFLOPs: 42.47 | +7: iteration 1290/ 7508 | consumed samples: 330240 | consumed tokens: 676331520 | elapsed time per iteration (s): 0.58 | learning rate: 1.884E-04 | global batch size: 256 | lm loss: 3.645383E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.794 | TFLOPs: 42.41 | +7: iteration 1300/ 7508 | consumed samples: 332800 | consumed tokens: 681574400 | elapsed time per iteration (s): 0.57 | learning rate: 1.882E-04 | global batch size: 256 | lm loss: 3.661362E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.224 | TFLOPs: 42.73 | +7: iteration 1310/ 7508 | consumed samples: 335360 | consumed tokens: 686817280 | elapsed time per iteration (s): 0.58 | learning rate: 1.880E-04 | global batch size: 256 | lm loss: 3.645021E+00 | grad norm: 0.411 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.091 | TFLOPs: 42.34 | +7: iteration 1320/ 7508 | consumed samples: 337920 | consumed tokens: 692060160 | elapsed time per iteration (s): 0.57 | learning rate: 1.878E-04 | global batch size: 256 | lm loss: 3.638952E+00 | grad norm: 0.391 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.232 | TFLOPs: 43.02 | +7: iteration 1330/ 7508 | consumed samples: 340480 | consumed tokens: 697303040 | elapsed time per iteration (s): 0.57 | learning rate: 1.876E-04 | global batch size: 256 | lm loss: 3.611470E+00 | grad norm: 0.556 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.103 | TFLOPs: 42.63 | +7: iteration 1340/ 7508 | consumed samples: 343040 | consumed tokens: 702545920 | elapsed time per iteration (s): 0.56 | learning rate: 1.874E-04 | global batch size: 256 | lm loss: 3.611716E+00 | grad norm: 0.614 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.158 | TFLOPs: 43.30 | +7: iteration 1350/ 7508 | consumed samples: 345600 | consumed tokens: 707788800 | elapsed time per iteration (s): 0.57 | learning rate: 1.872E-04 | global batch size: 256 | lm loss: 3.616335E+00 | grad norm: 0.473 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.481 | TFLOPs: 42.76 | +7: iteration 1360/ 7508 | consumed samples: 348160 | consumed tokens: 713031680 | elapsed time per iteration (s): 0.58 | learning rate: 1.871E-04 | global batch size: 256 | lm loss: 3.610891E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.211 | TFLOPs: 42.26 | +7: iteration 1370/ 7508 | consumed samples: 350720 | consumed tokens: 718274560 | elapsed time per iteration (s): 0.57 | learning rate: 1.869E-04 | global batch size: 256 | lm loss: 3.594296E+00 | grad norm: 0.473 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.298 | TFLOPs: 42.64 | +7: iteration 1380/ 7508 | consumed samples: 353280 | consumed tokens: 723517440 | elapsed time per iteration (s): 0.56 | learning rate: 1.867E-04 | global batch size: 256 | lm loss: 3.590308E+00 | grad norm: 0.440 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.505 | TFLOPs: 43.43 | +7: iteration 1390/ 7508 | consumed samples: 355840 | consumed tokens: 728760320 | elapsed time per iteration (s): 0.58 | learning rate: 1.865E-04 | global batch size: 256 | lm loss: 3.587461E+00 | grad norm: 0.418 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.684 | TFLOPs: 42.11 | +7: iteration 1400/ 7508 | consumed samples: 358400 | consumed tokens: 734003200 | elapsed time per iteration (s): 0.57 | learning rate: 1.863E-04 | global batch size: 256 | lm loss: 3.603316E+00 | grad norm: 0.434 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.409 | TFLOPs: 42.46 | +7: iteration 1410/ 7508 | consumed samples: 360960 | consumed tokens: 739246080 | elapsed time per iteration (s): 0.56 | learning rate: 1.861E-04 | global batch size: 256 | lm loss: 3.584620E+00 | grad norm: 0.426 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.623 | TFLOPs: 43.72 | +7: iteration 1420/ 7508 | consumed samples: 363520 | consumed tokens: 744488960 | elapsed time per iteration (s): 0.56 | learning rate: 1.858E-04 | global batch size: 256 | lm loss: 3.566558E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.828 | TFLOPs: 43.55 | +7: iteration 1430/ 7508 | consumed samples: 366080 | consumed tokens: 749731840 | elapsed time per iteration (s): 0.57 | learning rate: 1.856E-04 | global batch size: 256 | lm loss: 3.608897E+00 | grad norm: 0.468 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.551 | TFLOPs: 42.57 | +7: iteration 1440/ 7508 | consumed samples: 368640 | consumed tokens: 754974720 | elapsed time per iteration (s): 0.58 | learning rate: 1.854E-04 | global batch size: 256 | lm loss: 3.569450E+00 | grad norm: 0.404 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.350 | TFLOPs: 42.08 | +7: iteration 1450/ 7508 | consumed samples: 371200 | consumed tokens: 760217600 | elapsed time per iteration (s): 0.57 | learning rate: 1.852E-04 | global batch size: 256 | lm loss: 3.590588E+00 | grad norm: 0.565 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.891 | TFLOPs: 42.51 | +7: iteration 1460/ 7508 | consumed samples: 373760 | consumed tokens: 765460480 | elapsed time per iteration (s): 0.58 | learning rate: 1.850E-04 | global batch size: 256 | lm loss: 3.573000E+00 | grad norm: 0.439 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.960 | TFLOPs: 41.95 | +7: iteration 1470/ 7508 | consumed samples: 376320 | consumed tokens: 770703360 | elapsed time per iteration (s): 0.57 | learning rate: 1.848E-04 | global batch size: 256 | lm loss: 3.583730E+00 | grad norm: 0.441 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.736 | TFLOPs: 43.07 | +7: iteration 1480/ 7508 | consumed samples: 378880 | consumed tokens: 775946240 | elapsed time per iteration (s): 0.57 | learning rate: 1.846E-04 | global batch size: 256 | lm loss: 3.590928E+00 | grad norm: 0.458 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.241 | TFLOPs: 42.93 | +7: iteration 1490/ 7508 | consumed samples: 381440 | consumed tokens: 781189120 | elapsed time per iteration (s): 0.57 | learning rate: 1.844E-04 | global batch size: 256 | lm loss: 3.536751E+00 | grad norm: 0.402 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.433 | TFLOPs: 43.04 | +7: iteration 1500/ 7508 | consumed samples: 384000 | consumed tokens: 786432000 | elapsed time per iteration (s): 0.58 | learning rate: 1.842E-04 | global batch size: 256 | lm loss: 3.552866E+00 | grad norm: 0.381 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.641 | TFLOPs: 42.30 | +7: iteration 1510/ 7508 | consumed samples: 386560 | consumed tokens: 791674880 | elapsed time per iteration (s): 0.56 | learning rate: 1.840E-04 | global batch size: 256 | lm loss: 3.569149E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.129 | TFLOPs: 43.20 | +7: iteration 1520/ 7508 | consumed samples: 389120 | consumed tokens: 796917760 | elapsed time per iteration (s): 0.56 | learning rate: 1.837E-04 | global batch size: 256 | lm loss: 3.539315E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.413 | TFLOPs: 43.32 | +7: iteration 1530/ 7508 | consumed samples: 391680 | consumed tokens: 802160640 | elapsed time per iteration (s): 0.58 | learning rate: 1.835E-04 | global batch size: 256 | lm loss: 3.522298E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.440 | TFLOPs: 42.18 | +7: iteration 1540/ 7508 | consumed samples: 394240 | consumed tokens: 807403520 | elapsed time per iteration (s): 0.57 | learning rate: 1.833E-04 | global batch size: 256 | lm loss: 3.561707E+00 | grad norm: 0.417 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.607 | TFLOPs: 42.48 | +7: iteration 1550/ 7508 | consumed samples: 396800 | consumed tokens: 812646400 | elapsed time per iteration (s): 0.56 | learning rate: 1.831E-04 | global batch size: 256 | lm loss: 3.519994E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.488 | TFLOPs: 43.33 | +7: iteration 1560/ 7508 | consumed samples: 399360 | consumed tokens: 817889280 | elapsed time per iteration (s): 0.56 | learning rate: 1.829E-04 | global batch size: 256 | lm loss: 3.513391E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.407 | TFLOPs: 43.61 | +7: iteration 1570/ 7508 | consumed samples: 401920 | consumed tokens: 823132160 | elapsed time per iteration (s): 0.57 | learning rate: 1.826E-04 | global batch size: 256 | lm loss: 3.511028E+00 | grad norm: 0.414 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.323 | TFLOPs: 42.65 | +7: iteration 1580/ 7508 | consumed samples: 404480 | consumed tokens: 828375040 | elapsed time per iteration (s): 0.56 | learning rate: 1.824E-04 | global batch size: 256 | lm loss: 3.486781E+00 | grad norm: 0.388 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.072 | TFLOPs: 43.39 | +7: iteration 1590/ 7508 | consumed samples: 407040 | consumed tokens: 833617920 | elapsed time per iteration (s): 0.56 | learning rate: 1.822E-04 | global batch size: 256 | lm loss: 3.493272E+00 | grad norm: 0.501 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.648 | TFLOPs: 43.73 | +7: iteration 1600/ 7508 | consumed samples: 409600 | consumed tokens: 838860800 | elapsed time per iteration (s): 0.56 | learning rate: 1.819E-04 | global batch size: 256 | lm loss: 3.533421E+00 | grad norm: 0.440 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.666 | TFLOPs: 43.35 | +7: iteration 1610/ 7508 | consumed samples: 412160 | consumed tokens: 844103680 | elapsed time per iteration (s): 0.56 | learning rate: 1.817E-04 | global batch size: 256 | lm loss: 3.502800E+00 | grad norm: 0.383 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.755 | TFLOPs: 43.26 | +7: iteration 1620/ 7508 | consumed samples: 414720 | consumed tokens: 849346560 | elapsed time per iteration (s): 0.58 | learning rate: 1.815E-04 | global batch size: 256 | lm loss: 3.515357E+00 | grad norm: 0.417 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.885 | TFLOPs: 42.03 | +7: iteration 1630/ 7508 | consumed samples: 417280 | consumed tokens: 854589440 | elapsed time per iteration (s): 0.56 | learning rate: 1.813E-04 | global batch size: 256 | lm loss: 3.515889E+00 | grad norm: 0.405 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.348 | TFLOPs: 43.41 | +7: iteration 1640/ 7508 | consumed samples: 419840 | consumed tokens: 859832320 | elapsed time per iteration (s): 0.57 | learning rate: 1.810E-04 | global batch size: 256 | lm loss: 3.504137E+00 | grad norm: 0.412 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.478 | TFLOPs: 42.95 | +7: iteration 1650/ 7508 | consumed samples: 422400 | consumed tokens: 865075200 | elapsed time per iteration (s): 0.56 | learning rate: 1.808E-04 | global batch size: 256 | lm loss: 3.513897E+00 | grad norm: 0.387 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.653 | TFLOPs: 43.25 | +7: iteration 1660/ 7508 | consumed samples: 424960 | consumed tokens: 870318080 | elapsed time per iteration (s): 0.56 | learning rate: 1.806E-04 | global batch size: 256 | lm loss: 3.507077E+00 | grad norm: 0.414 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.115 | TFLOPs: 43.29 | +7: iteration 1670/ 7508 | consumed samples: 427520 | consumed tokens: 875560960 | elapsed time per iteration (s): 0.56 | learning rate: 1.803E-04 | global batch size: 256 | lm loss: 3.497956E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.960 | TFLOPs: 43.28 | +7: iteration 1680/ 7508 | consumed samples: 430080 | consumed tokens: 880803840 | elapsed time per iteration (s): 0.56 | learning rate: 1.801E-04 | global batch size: 256 | lm loss: 3.472168E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.715 | TFLOPs: 43.45 | +7: iteration 1690/ 7508 | consumed samples: 432640 | consumed tokens: 886046720 | elapsed time per iteration (s): 0.57 | learning rate: 1.798E-04 | global batch size: 256 | lm loss: 3.511734E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.829 | TFLOPs: 42.50 | +7: iteration 1700/ 7508 | consumed samples: 435200 | consumed tokens: 891289600 | elapsed time per iteration (s): 0.56 | learning rate: 1.796E-04 | global batch size: 256 | lm loss: 3.471716E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 459.330 | TFLOPs: 43.79 | +7: iteration 1710/ 7508 | consumed samples: 437760 | consumed tokens: 896532480 | elapsed time per iteration (s): 0.56 | learning rate: 1.794E-04 | global batch size: 256 | lm loss: 3.463609E+00 | grad norm: 0.421 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.627 | TFLOPs: 43.63 | +7: iteration 1720/ 7508 | consumed samples: 440320 | consumed tokens: 901775360 | elapsed time per iteration (s): 0.57 | learning rate: 1.791E-04 | global batch size: 256 | lm loss: 3.488567E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.979 | TFLOPs: 42.90 | +7: iteration 1730/ 7508 | consumed samples: 442880 | consumed tokens: 907018240 | elapsed time per iteration (s): 0.58 | learning rate: 1.789E-04 | global batch size: 256 | lm loss: 3.465752E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.154 | TFLOPs: 41.77 | +7: iteration 1740/ 7508 | consumed samples: 445440 | consumed tokens: 912261120 | elapsed time per iteration (s): 0.57 | learning rate: 1.786E-04 | global batch size: 256 | lm loss: 3.478069E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.856 | TFLOPs: 42.79 | +7: iteration 1750/ 7508 | consumed samples: 448000 | consumed tokens: 917504000 | elapsed time per iteration (s): 0.57 | learning rate: 1.784E-04 | global batch size: 256 | lm loss: 3.482950E+00 | grad norm: 0.383 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.719 | TFLOPs: 43.16 | +7: iteration 1760/ 7508 | consumed samples: 450560 | consumed tokens: 922746880 | elapsed time per iteration (s): 0.56 | learning rate: 1.781E-04 | global batch size: 256 | lm loss: 3.441369E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.049 | TFLOPs: 43.86 | +7: iteration 1770/ 7508 | consumed samples: 453120 | consumed tokens: 927989760 | elapsed time per iteration (s): 0.56 | learning rate: 1.779E-04 | global batch size: 256 | lm loss: 3.462075E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.225 | TFLOPs: 43.21 | +7: iteration 1780/ 7508 | consumed samples: 455680 | consumed tokens: 933232640 | elapsed time per iteration (s): 0.58 | learning rate: 1.776E-04 | global batch size: 256 | lm loss: 3.459929E+00 | grad norm: 0.380 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.472 | TFLOPs: 42.09 | +7: iteration 1790/ 7508 | consumed samples: 458240 | consumed tokens: 938475520 | elapsed time per iteration (s): 0.56 | learning rate: 1.774E-04 | global batch size: 256 | lm loss: 3.462190E+00 | grad norm: 0.500 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.296 | TFLOPs: 43.60 | +7: iteration 1800/ 7508 | consumed samples: 460800 | consumed tokens: 943718400 | elapsed time per iteration (s): 0.56 | learning rate: 1.771E-04 | global batch size: 256 | lm loss: 3.474185E+00 | grad norm: 0.381 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.782 | TFLOPs: 43.26 | +7: iteration 1810/ 7508 | consumed samples: 463360 | consumed tokens: 948961280 | elapsed time per iteration (s): 0.56 | learning rate: 1.769E-04 | global batch size: 256 | lm loss: 3.452007E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.859 | TFLOPs: 43.46 | +7: iteration 1820/ 7508 | consumed samples: 465920 | consumed tokens: 954204160 | elapsed time per iteration (s): 0.57 | learning rate: 1.766E-04 | global batch size: 256 | lm loss: 3.433862E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.715 | TFLOPs: 43.16 | +7: iteration 1830/ 7508 | consumed samples: 468480 | consumed tokens: 959447040 | elapsed time per iteration (s): 0.57 | learning rate: 1.764E-04 | global batch size: 256 | lm loss: 3.478546E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.142 | TFLOPs: 42.53 | +7: iteration 1840/ 7508 | consumed samples: 471040 | consumed tokens: 964689920 | elapsed time per iteration (s): 0.58 | learning rate: 1.761E-04 | global batch size: 256 | lm loss: 3.451704E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.265 | TFLOPs: 42.17 | +7: iteration 1850/ 7508 | consumed samples: 473600 | consumed tokens: 969932800 | elapsed time per iteration (s): 0.56 | learning rate: 1.758E-04 | global batch size: 256 | lm loss: 3.441322E+00 | grad norm: 0.469 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.566 | TFLOPs: 43.72 | +7: iteration 1860/ 7508 | consumed samples: 476160 | consumed tokens: 975175680 | elapsed time per iteration (s): 0.56 | learning rate: 1.756E-04 | global batch size: 256 | lm loss: 3.438990E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.171 | TFLOPs: 43.87 | +7: iteration 1870/ 7508 | consumed samples: 478720 | consumed tokens: 980418560 | elapsed time per iteration (s): 0.57 | learning rate: 1.753E-04 | global batch size: 256 | lm loss: 3.402691E+00 | grad norm: 0.397 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.325 | TFLOPs: 43.03 | +7: iteration 1880/ 7508 | consumed samples: 481280 | consumed tokens: 985661440 | elapsed time per iteration (s): 0.57 | learning rate: 1.751E-04 | global batch size: 256 | lm loss: 3.410888E+00 | grad norm: 0.396 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.332 | TFLOPs: 42.93 | +7: iteration 1890/ 7508 | consumed samples: 483840 | consumed tokens: 990904320 | elapsed time per iteration (s): 0.55 | learning rate: 1.748E-04 | global batch size: 256 | lm loss: 3.431595E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 463.146 | TFLOPs: 44.16 | +7: iteration 1900/ 7508 | consumed samples: 486400 | consumed tokens: 996147200 | elapsed time per iteration (s): 0.56 | learning rate: 1.745E-04 | global batch size: 256 | lm loss: 3.422196E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.508 | TFLOPs: 43.43 | +7: iteration 1910/ 7508 | consumed samples: 488960 | consumed tokens: 1001390080 | elapsed time per iteration (s): 0.57 | learning rate: 1.743E-04 | global batch size: 256 | lm loss: 3.436362E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.032 | TFLOPs: 43.19 | +7: iteration 1920/ 7508 | consumed samples: 491520 | consumed tokens: 1006632960 | elapsed time per iteration (s): 0.57 | learning rate: 1.740E-04 | global batch size: 256 | lm loss: 3.395719E+00 | grad norm: 0.367 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.699 | TFLOPs: 43.06 | +7: iteration 1930/ 7508 | consumed samples: 494080 | consumed tokens: 1011875840 | elapsed time per iteration (s): 0.57 | learning rate: 1.737E-04 | global batch size: 256 | lm loss: 3.407957E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.853 | TFLOPs: 43.17 | +7: iteration 1940/ 7508 | consumed samples: 496640 | consumed tokens: 1017118720 | elapsed time per iteration (s): 0.56 | learning rate: 1.735E-04 | global batch size: 256 | lm loss: 3.433319E+00 | grad norm: 0.387 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.129 | TFLOPs: 43.87 | +7: iteration 1950/ 7508 | consumed samples: 499200 | consumed tokens: 1022361600 | elapsed time per iteration (s): 0.57 | learning rate: 1.732E-04 | global batch size: 256 | lm loss: 3.429270E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.435 | TFLOPs: 43.04 | +7: iteration 1960/ 7508 | consumed samples: 501760 | consumed tokens: 1027604480 | elapsed time per iteration (s): 0.58 | learning rate: 1.729E-04 | global batch size: 256 | lm loss: 3.428686E+00 | grad norm: 0.381 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.651 | TFLOPs: 41.82 | +7: iteration 1970/ 7508 | consumed samples: 504320 | consumed tokens: 1032847360 | elapsed time per iteration (s): 0.57 | learning rate: 1.726E-04 | global batch size: 256 | lm loss: 3.427985E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.379 | TFLOPs: 43.13 | +7: iteration 1980/ 7508 | consumed samples: 506880 | consumed tokens: 1038090240 | elapsed time per iteration (s): 0.57 | learning rate: 1.724E-04 | global batch size: 256 | lm loss: 3.410099E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.561 | TFLOPs: 42.57 | +7: iteration 1990/ 7508 | consumed samples: 509440 | consumed tokens: 1043333120 | elapsed time per iteration (s): 0.57 | learning rate: 1.721E-04 | global batch size: 256 | lm loss: 3.396257E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.664 | TFLOPs: 43.06 | +0: [2022-11-29 17:14:29,648] [INFO] [logging.py:68:log_dist] [Rank 0] step=2000, skipped=0, lr=[0.00017182361507925355, 0.00017182361507925355, 0.00017182361507925355], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 2000/ 7508 | consumed samples: 512000 | consumed tokens: 1048576000 | elapsed time per iteration (s): 0.56 | learning rate: 1.718E-04 | global batch size: 256 | lm loss: 3.404842E+00 | grad norm: 0.441 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.183 | TFLOPs: 43.49 | +0: steps: 2000 loss: 3.4049 iter time (s): 0.578 samples/sec: 443.265 +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 2000 | lm loss value: 3.297268E+00 | lm loss PPL: 2.703867E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 2000 to checkpoints_421moscar +0: [2022-11-29 17:14:29,851] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step2000 is begin to save! +0: [2022-11-29 17:14:29,855] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:14:29,994] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:14:29,995] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:14:30,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:14:30,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:14:30,076] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:14:30,077] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:14:30,114] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:14:30,115] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:14:30,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:14:30,154] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:14:30,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:14:30,195] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:14:30,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:14:30,234] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:14:30,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:14:30,274] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:14:30,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:14:30,313] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:14:30,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:14:30,352] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:14:30,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:14:30,392] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:14:30,431] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:14:30,431] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:14:30,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:14:30,471] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:14:30,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:14:30,511] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:14:30,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:14:30,550] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:14:30,589] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:14:30,590] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/layer_18-model_00-model_states.pt... +0: [2022-11-29 17:14:30,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/layer_18-model_00-model_states.pt. +0: [2022-11-29 17:14:30,628] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:14:30,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:14:30,668] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/layer_20-model_00-model_states.pt... +0: [2022-11-29 17:14:30,706] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/layer_20-model_00-model_states.pt. +0: [2022-11-29 17:14:30,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/layer_22-model_00-model_states.pt... +0: [2022-11-29 17:14:30,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/layer_22-model_00-model_states.pt. +0: [2022-11-29 17:14:30,711] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_421moscar/global_step2000/mp_rank_00_model_states.pt +0: [2022-11-29 17:14:30,711] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:14:30,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:14:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:14:30,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:14:30,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:14:30,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:14:30,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:14:30,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:14:30,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:14:30,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:14:30,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:14:30,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:14:30,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:14:30,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:14:30,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:14:30,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:14:30,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:14:30,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:14:30,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:14:30,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:14:30,828] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:14:30,828] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:14:30,828] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:14:30,828] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:14:30,829] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:14:30,829] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:14:30,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:14:30,829] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:14:30,829] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:14:30,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:14:30,829] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:14:30,829] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:14:30,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:14:30,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:14:30,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:14:30,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:14:30,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:14:30,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:14:30,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:14:30,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +4: [2022-11-29 17:14:30,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:14:30,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:14:30,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:14:30,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:14:30,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:14:30,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:14:30,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:14:30,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:14:30,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:14:30,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:14:30,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:14:30,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:14:30,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:14:30,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:14:30,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:14:30,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:14:30,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:14:30,832] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:14:30,832] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:14:30,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:14:30,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:14:30,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:14:30,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:14:30,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:14:30,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:14:30,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:14:30,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:14:30,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:14:30,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:14:30,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:14:30,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:14:30,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:14:30,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:14:30,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:14:30,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:14:30,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:14:30,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:14:30,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:14:30,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:14:30,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:14:30,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:14:30,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:14:30,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:14:30,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:14:30,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:14:30,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:14:30,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:14:30,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:14:30,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:14:30,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:14:30,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:14:30,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:14:30,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:14:30,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:14:30,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:14:30,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:14:30,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:14:30,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:14:30,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:14:30,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:14:30,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:14:30,841] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:14:30,841] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:14:30,841] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:14:30,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:14:30,844] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:14:30,844] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:14:30,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:14:30,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:14:30,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:14:30,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:14:30,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:14:30,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:14:30,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:14:30,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:14:30,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:14:30,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:14:30,828] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:14:30,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:14:30,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:14:30,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:14:30,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:14:30,842] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:14:30,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:14:30,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:14:30,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:14:30,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:14:30,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:14:30,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:14:30,864] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +5: [2022-11-29 17:14:30,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:14:30,865] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:14:30,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:14:30,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:14:30,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:14:30,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:14:30,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:14:30,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:14:30,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:14:30,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:14:30,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:14:30,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:14:30,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:14:30,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:14:30,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:14:30,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:14:30,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:14:30,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:14:30,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:14:30,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:14:30,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:14:30,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:14:30,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:14:30,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:14:30,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:14:30,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:14:30,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:14:30,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:14:30,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:14:30,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:14:30,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:14:30,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:14:30,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:14:30,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:14:30,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:14:30,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:14:30,828] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:14:30,828] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:14:30,828] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:14:30,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:14:30,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:14:30,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:14:30,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:14:30,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:14:30,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:14:30,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:14:30,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:14:30,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:14:30,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:14:30,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:14:30,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:14:30,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:14:30,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:14:30,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:14:30,893] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:14:30,893] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:14:30,893] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:14:30,900] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:14:30,900] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:14:30,900] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:14:30,920] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:14:30,920] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:14:30,957] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:14:30,957] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:14:30,958] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: successfully saved checkpoint at iteration 2000 to checkpoints_421moscar +7: time (ms) | save-checkpoint: 1111.34 +7: iteration 2010/ 7508 | consumed samples: 514560 | consumed tokens: 1053818880 | elapsed time per iteration (s): 0.69 | learning rate: 1.715E-04 | global batch size: 256 | lm loss: 3.390011E+00 | grad norm: 0.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 368.405 | TFLOPs: 35.12 | +7: iteration 2020/ 7508 | consumed samples: 517120 | consumed tokens: 1059061760 | elapsed time per iteration (s): 0.56 | learning rate: 1.713E-04 | global batch size: 256 | lm loss: 3.391814E+00 | grad norm: 0.411 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.216 | TFLOPs: 43.69 | +7: iteration 2030/ 7508 | consumed samples: 519680 | consumed tokens: 1064304640 | elapsed time per iteration (s): 0.56 | learning rate: 1.710E-04 | global batch size: 256 | lm loss: 3.403981E+00 | grad norm: 0.389 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.006 | TFLOPs: 43.48 | +7: iteration 2040/ 7508 | consumed samples: 522240 | consumed tokens: 1069547520 | elapsed time per iteration (s): 0.58 | learning rate: 1.707E-04 | global batch size: 256 | lm loss: 3.371955E+00 | grad norm: 0.451 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.809 | TFLOPs: 42.12 | +7: iteration 2050/ 7508 | consumed samples: 524800 | consumed tokens: 1074790400 | elapsed time per iteration (s): 0.57 | learning rate: 1.704E-04 | global batch size: 256 | lm loss: 3.378664E+00 | grad norm: 0.435 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.012 | TFLOPs: 43.00 | +7: iteration 2060/ 7508 | consumed samples: 527360 | consumed tokens: 1080033280 | elapsed time per iteration (s): 0.57 | learning rate: 1.701E-04 | global batch size: 256 | lm loss: 3.377085E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.757 | TFLOPs: 42.97 | +7: iteration 2070/ 7508 | consumed samples: 529920 | consumed tokens: 1085276160 | elapsed time per iteration (s): 0.57 | learning rate: 1.699E-04 | global batch size: 256 | lm loss: 3.360523E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.599 | TFLOPs: 43.15 | +7: iteration 2080/ 7508 | consumed samples: 532480 | consumed tokens: 1090519040 | elapsed time per iteration (s): 0.57 | learning rate: 1.696E-04 | global batch size: 256 | lm loss: 3.369624E+00 | grad norm: 0.445 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.205 | TFLOPs: 42.64 | +7: iteration 2090/ 7508 | consumed samples: 535040 | consumed tokens: 1095761920 | elapsed time per iteration (s): 0.56 | learning rate: 1.693E-04 | global batch size: 256 | lm loss: 3.349948E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.153 | TFLOPs: 43.49 | +7: iteration 2100/ 7508 | consumed samples: 537600 | consumed tokens: 1101004800 | elapsed time per iteration (s): 0.57 | learning rate: 1.690E-04 | global batch size: 256 | lm loss: 3.372674E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.729 | TFLOPs: 42.69 | +7: iteration 2110/ 7508 | consumed samples: 540160 | consumed tokens: 1106247680 | elapsed time per iteration (s): 0.57 | learning rate: 1.687E-04 | global batch size: 256 | lm loss: 3.386343E+00 | grad norm: 0.415 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.315 | TFLOPs: 42.46 | +7: iteration 2120/ 7508 | consumed samples: 542720 | consumed tokens: 1111490560 | elapsed time per iteration (s): 0.57 | learning rate: 1.684E-04 | global batch size: 256 | lm loss: 3.363240E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.220 | TFLOPs: 42.54 | +7: iteration 2130/ 7508 | consumed samples: 545280 | consumed tokens: 1116733440 | elapsed time per iteration (s): 0.56 | learning rate: 1.681E-04 | global batch size: 256 | lm loss: 3.356987E+00 | grad norm: 0.383 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.122 | TFLOPs: 43.39 | +7: iteration 2140/ 7508 | consumed samples: 547840 | consumed tokens: 1121976320 | elapsed time per iteration (s): 0.57 | learning rate: 1.678E-04 | global batch size: 256 | lm loss: 3.369801E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.570 | TFLOPs: 42.77 | +7: iteration 2150/ 7508 | consumed samples: 550400 | consumed tokens: 1127219200 | elapsed time per iteration (s): 0.58 | learning rate: 1.676E-04 | global batch size: 256 | lm loss: 3.363717E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.463 | TFLOPs: 41.90 | +7: iteration 2160/ 7508 | consumed samples: 552960 | consumed tokens: 1132462080 | elapsed time per iteration (s): 0.59 | learning rate: 1.673E-04 | global batch size: 256 | lm loss: 3.386611E+00 | grad norm: 0.367 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.396 | TFLOPs: 41.70 | +7: iteration 2170/ 7508 | consumed samples: 555520 | consumed tokens: 1137704960 | elapsed time per iteration (s): 0.57 | learning rate: 1.670E-04 | global batch size: 256 | lm loss: 3.362263E+00 | grad norm: 0.377 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.657 | TFLOPs: 42.77 | +7: iteration 2180/ 7508 | consumed samples: 558080 | consumed tokens: 1142947840 | elapsed time per iteration (s): 0.58 | learning rate: 1.667E-04 | global batch size: 256 | lm loss: 3.357027E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.800 | TFLOPs: 41.83 | +7: iteration 2190/ 7508 | consumed samples: 560640 | consumed tokens: 1148190720 | elapsed time per iteration (s): 0.56 | learning rate: 1.664E-04 | global batch size: 256 | lm loss: 3.356084E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.891 | TFLOPs: 43.27 | +7: iteration 2200/ 7508 | consumed samples: 563200 | consumed tokens: 1153433600 | elapsed time per iteration (s): 0.56 | learning rate: 1.661E-04 | global batch size: 256 | lm loss: 3.349191E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.495 | TFLOPs: 43.24 | +7: iteration 2210/ 7508 | consumed samples: 565760 | consumed tokens: 1158676480 | elapsed time per iteration (s): 0.58 | learning rate: 1.658E-04 | global batch size: 256 | lm loss: 3.347779E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.625 | TFLOPs: 42.29 | +7: iteration 2220/ 7508 | consumed samples: 568320 | consumed tokens: 1163919360 | elapsed time per iteration (s): 0.57 | learning rate: 1.655E-04 | global batch size: 256 | lm loss: 3.353388E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.901 | TFLOPs: 42.80 | +7: iteration 2230/ 7508 | consumed samples: 570880 | consumed tokens: 1169162240 | elapsed time per iteration (s): 0.57 | learning rate: 1.652E-04 | global batch size: 256 | lm loss: 3.336145E+00 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.522 | TFLOPs: 42.76 | +7: iteration 2240/ 7508 | consumed samples: 573440 | consumed tokens: 1174405120 | elapsed time per iteration (s): 0.57 | learning rate: 1.649E-04 | global batch size: 256 | lm loss: 3.363124E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.295 | TFLOPs: 42.74 | +7: iteration 2250/ 7508 | consumed samples: 576000 | consumed tokens: 1179648000 | elapsed time per iteration (s): 0.56 | learning rate: 1.646E-04 | global batch size: 256 | lm loss: 3.347157E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.952 | TFLOPs: 43.47 | +7: iteration 2260/ 7508 | consumed samples: 578560 | consumed tokens: 1184890880 | elapsed time per iteration (s): 0.56 | learning rate: 1.643E-04 | global batch size: 256 | lm loss: 3.333178E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.964 | TFLOPs: 43.38 | +7: iteration 2270/ 7508 | consumed samples: 581120 | consumed tokens: 1190133760 | elapsed time per iteration (s): 0.57 | learning rate: 1.640E-04 | global batch size: 256 | lm loss: 3.330810E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.601 | TFLOPs: 42.96 | +7: iteration 2280/ 7508 | consumed samples: 583680 | consumed tokens: 1195376640 | elapsed time per iteration (s): 0.56 | learning rate: 1.637E-04 | global batch size: 256 | lm loss: 3.342937E+00 | grad norm: 0.367 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.886 | TFLOPs: 43.94 | +7: iteration 2290/ 7508 | consumed samples: 586240 | consumed tokens: 1200619520 | elapsed time per iteration (s): 0.56 | learning rate: 1.634E-04 | global batch size: 256 | lm loss: 3.348915E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.827 | TFLOPs: 43.55 | +7: iteration 2300/ 7508 | consumed samples: 588800 | consumed tokens: 1205862400 | elapsed time per iteration (s): 0.55 | learning rate: 1.631E-04 | global batch size: 256 | lm loss: 3.318779E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 462.400 | TFLOPs: 44.08 | +7: iteration 2310/ 7508 | consumed samples: 591360 | consumed tokens: 1211105280 | elapsed time per iteration (s): 0.55 | learning rate: 1.627E-04 | global batch size: 256 | lm loss: 3.328281E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 462.048 | TFLOPs: 44.05 | +7: iteration 2320/ 7508 | consumed samples: 593920 | consumed tokens: 1216348160 | elapsed time per iteration (s): 0.56 | learning rate: 1.624E-04 | global batch size: 256 | lm loss: 3.310418E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.911 | TFLOPs: 43.28 | +7: iteration 2330/ 7508 | consumed samples: 596480 | consumed tokens: 1221591040 | elapsed time per iteration (s): 0.56 | learning rate: 1.621E-04 | global batch size: 256 | lm loss: 3.339315E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.059 | TFLOPs: 43.86 | +7: iteration 2340/ 7508 | consumed samples: 599040 | consumed tokens: 1226833920 | elapsed time per iteration (s): 0.56 | learning rate: 1.618E-04 | global batch size: 256 | lm loss: 3.327718E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.165 | TFLOPs: 43.20 | +7: iteration 2350/ 7508 | consumed samples: 601600 | consumed tokens: 1232076800 | elapsed time per iteration (s): 0.56 | learning rate: 1.615E-04 | global batch size: 256 | lm loss: 3.341915E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.053 | TFLOPs: 43.86 | +7: iteration 2360/ 7508 | consumed samples: 604160 | consumed tokens: 1237319680 | elapsed time per iteration (s): 0.57 | learning rate: 1.612E-04 | global batch size: 256 | lm loss: 3.306520E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.162 | TFLOPs: 42.82 | +7: iteration 2370/ 7508 | consumed samples: 606720 | consumed tokens: 1242562560 | elapsed time per iteration (s): 0.58 | learning rate: 1.609E-04 | global batch size: 256 | lm loss: 3.287401E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.277 | TFLOPs: 42.36 | +7: iteration 2380/ 7508 | consumed samples: 609280 | consumed tokens: 1247805440 | elapsed time per iteration (s): 0.56 | learning rate: 1.606E-04 | global batch size: 256 | lm loss: 3.291170E+00 | grad norm: 0.406 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.392 | TFLOPs: 43.32 | +7: iteration 2390/ 7508 | consumed samples: 611840 | consumed tokens: 1253048320 | elapsed time per iteration (s): 0.58 | learning rate: 1.603E-04 | global batch size: 256 | lm loss: 3.339131E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.833 | TFLOPs: 42.12 | +7: iteration 2400/ 7508 | consumed samples: 614400 | consumed tokens: 1258291200 | elapsed time per iteration (s): 0.56 | learning rate: 1.599E-04 | global batch size: 256 | lm loss: 3.296612E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 459.870 | TFLOPs: 43.84 | +7: iteration 2410/ 7508 | consumed samples: 616960 | consumed tokens: 1263534080 | elapsed time per iteration (s): 0.56 | learning rate: 1.596E-04 | global batch size: 256 | lm loss: 3.320082E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.133 | TFLOPs: 43.30 | +7: iteration 2420/ 7508 | consumed samples: 619520 | consumed tokens: 1268776960 | elapsed time per iteration (s): 0.58 | learning rate: 1.593E-04 | global batch size: 256 | lm loss: 3.294624E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.478 | TFLOPs: 42.28 | +7: iteration 2430/ 7508 | consumed samples: 622080 | consumed tokens: 1274019840 | elapsed time per iteration (s): 0.57 | learning rate: 1.590E-04 | global batch size: 256 | lm loss: 3.320169E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.532 | TFLOPs: 42.86 | +7: iteration 2440/ 7508 | consumed samples: 624640 | consumed tokens: 1279262720 | elapsed time per iteration (s): 0.56 | learning rate: 1.587E-04 | global batch size: 256 | lm loss: 3.300963E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.592 | TFLOPs: 43.25 | +7: iteration 2450/ 7508 | consumed samples: 627200 | consumed tokens: 1284505600 | elapsed time per iteration (s): 0.57 | learning rate: 1.583E-04 | global batch size: 256 | lm loss: 3.311911E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.060 | TFLOPs: 43.00 | +7: iteration 2460/ 7508 | consumed samples: 629760 | consumed tokens: 1289748480 | elapsed time per iteration (s): 0.57 | learning rate: 1.580E-04 | global batch size: 256 | lm loss: 3.287400E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.642 | TFLOPs: 43.15 | +7: iteration 2470/ 7508 | consumed samples: 632320 | consumed tokens: 1294991360 | elapsed time per iteration (s): 0.56 | learning rate: 1.577E-04 | global batch size: 256 | lm loss: 3.309516E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.992 | TFLOPs: 43.47 | +7: iteration 2480/ 7508 | consumed samples: 634880 | consumed tokens: 1300234240 | elapsed time per iteration (s): 0.58 | learning rate: 1.574E-04 | global batch size: 256 | lm loss: 3.312620E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.806 | TFLOPs: 42.41 | +7: iteration 2490/ 7508 | consumed samples: 637440 | consumed tokens: 1305477120 | elapsed time per iteration (s): 0.56 | learning rate: 1.571E-04 | global batch size: 256 | lm loss: 3.301789E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.741 | TFLOPs: 43.64 | +7: iteration 2500/ 7508 | consumed samples: 640000 | consumed tokens: 1310720000 | elapsed time per iteration (s): 0.57 | learning rate: 1.567E-04 | global batch size: 256 | lm loss: 3.327293E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.146 | TFLOPs: 42.92 | +7: iteration 2510/ 7508 | consumed samples: 642560 | consumed tokens: 1315962880 | elapsed time per iteration (s): 0.56 | learning rate: 1.564E-04 | global batch size: 256 | lm loss: 3.325815E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 459.006 | TFLOPs: 43.76 | +7: iteration 2520/ 7508 | consumed samples: 645120 | consumed tokens: 1321205760 | elapsed time per iteration (s): 0.57 | learning rate: 1.561E-04 | global batch size: 256 | lm loss: 3.308050E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.220 | TFLOPs: 43.11 | +7: iteration 2530/ 7508 | consumed samples: 647680 | consumed tokens: 1326448640 | elapsed time per iteration (s): 0.58 | learning rate: 1.558E-04 | global batch size: 256 | lm loss: 3.302916E+00 | grad norm: 0.416 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.065 | TFLOPs: 41.76 | +7: iteration 2540/ 7508 | consumed samples: 650240 | consumed tokens: 1331691520 | elapsed time per iteration (s): 0.57 | learning rate: 1.554E-04 | global batch size: 256 | lm loss: 3.320892E+00 | grad norm: 4.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.640 | TFLOPs: 42.87 | +7: iteration 2550/ 7508 | consumed samples: 652800 | consumed tokens: 1336934400 | elapsed time per iteration (s): 0.57 | learning rate: 1.551E-04 | global batch size: 256 | lm loss: 3.485365E+00 | grad norm: 3.070 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.688 | TFLOPs: 42.59 | +7: iteration 2560/ 7508 | consumed samples: 655360 | consumed tokens: 1342177280 | elapsed time per iteration (s): 0.57 | learning rate: 1.548E-04 | global batch size: 256 | lm loss: 3.561911E+00 | grad norm: 1.623 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.107 | TFLOPs: 42.91 | +7: iteration 2570/ 7508 | consumed samples: 657920 | consumed tokens: 1347420160 | elapsed time per iteration (s): 0.57 | learning rate: 1.544E-04 | global batch size: 256 | lm loss: 3.448870E+00 | grad norm: 0.484 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.749 | TFLOPs: 43.16 | +7: iteration 2580/ 7508 | consumed samples: 660480 | consumed tokens: 1352663040 | elapsed time per iteration (s): 0.56 | learning rate: 1.541E-04 | global batch size: 256 | lm loss: 3.376186E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.684 | TFLOPs: 43.35 | +7: iteration 2590/ 7508 | consumed samples: 663040 | consumed tokens: 1357905920 | elapsed time per iteration (s): 0.56 | learning rate: 1.538E-04 | global batch size: 256 | lm loss: 3.322602E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.792 | TFLOPs: 43.45 | +7: iteration 2600/ 7508 | consumed samples: 665600 | consumed tokens: 1363148800 | elapsed time per iteration (s): 0.57 | learning rate: 1.534E-04 | global batch size: 256 | lm loss: 3.312434E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.740 | TFLOPs: 42.50 | +7: iteration 2610/ 7508 | consumed samples: 668160 | consumed tokens: 1368391680 | elapsed time per iteration (s): 0.57 | learning rate: 1.531E-04 | global batch size: 256 | lm loss: 3.302349E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.182 | TFLOPs: 42.63 | +7: iteration 2620/ 7508 | consumed samples: 670720 | consumed tokens: 1373634560 | elapsed time per iteration (s): 0.57 | learning rate: 1.528E-04 | global batch size: 256 | lm loss: 3.302140E+00 | grad norm: 0.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.728 | TFLOPs: 42.97 | +7: iteration 2630/ 7508 | consumed samples: 673280 | consumed tokens: 1378877440 | elapsed time per iteration (s): 0.56 | learning rate: 1.524E-04 | global batch size: 256 | lm loss: 3.283564E+00 | grad norm: 0.391 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.037 | TFLOPs: 43.38 | +7: iteration 2640/ 7508 | consumed samples: 675840 | consumed tokens: 1384120320 | elapsed time per iteration (s): 0.57 | learning rate: 1.521E-04 | global batch size: 256 | lm loss: 3.307431E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.158 | TFLOPs: 43.01 | +7: iteration 2650/ 7508 | consumed samples: 678400 | consumed tokens: 1389363200 | elapsed time per iteration (s): 0.58 | learning rate: 1.518E-04 | global batch size: 256 | lm loss: 3.263707E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.601 | TFLOPs: 42.29 | +7: iteration 2660/ 7508 | consumed samples: 680960 | consumed tokens: 1394606080 | elapsed time per iteration (s): 0.58 | learning rate: 1.514E-04 | global batch size: 256 | lm loss: 3.335970E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.957 | TFLOPs: 42.33 | +7: iteration 2670/ 7508 | consumed samples: 683520 | consumed tokens: 1399848960 | elapsed time per iteration (s): 0.57 | learning rate: 1.511E-04 | global batch size: 256 | lm loss: 3.288815E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.866 | TFLOPs: 42.70 | +7: iteration 2680/ 7508 | consumed samples: 686080 | consumed tokens: 1405091840 | elapsed time per iteration (s): 0.60 | learning rate: 1.507E-04 | global batch size: 256 | lm loss: 3.263965E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 429.403 | TFLOPs: 40.94 | +7: iteration 2690/ 7508 | consumed samples: 688640 | consumed tokens: 1410334720 | elapsed time per iteration (s): 0.59 | learning rate: 1.504E-04 | global batch size: 256 | lm loss: 3.254529E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.853 | TFLOPs: 41.27 | +7: iteration 2700/ 7508 | consumed samples: 691200 | consumed tokens: 1415577600 | elapsed time per iteration (s): 0.56 | learning rate: 1.501E-04 | global batch size: 256 | lm loss: 3.276396E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.199 | TFLOPs: 43.59 | +7: iteration 2710/ 7508 | consumed samples: 693760 | consumed tokens: 1420820480 | elapsed time per iteration (s): 0.56 | learning rate: 1.497E-04 | global batch size: 256 | lm loss: 3.273547E+00 | grad norm: 0.383 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.273 | TFLOPs: 43.21 | +7: iteration 2720/ 7508 | consumed samples: 696320 | consumed tokens: 1426063360 | elapsed time per iteration (s): 0.57 | learning rate: 1.494E-04 | global batch size: 256 | lm loss: 3.259465E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.826 | TFLOPs: 43.08 | +7: iteration 2730/ 7508 | consumed samples: 698880 | consumed tokens: 1431306240 | elapsed time per iteration (s): 0.55 | learning rate: 1.490E-04 | global batch size: 256 | lm loss: 3.270351E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 463.433 | TFLOPs: 44.18 | +7: iteration 2740/ 7508 | consumed samples: 701440 | consumed tokens: 1436549120 | elapsed time per iteration (s): 0.57 | learning rate: 1.487E-04 | global batch size: 256 | lm loss: 3.248445E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.882 | TFLOPs: 43.18 | +7: iteration 2750/ 7508 | consumed samples: 704000 | consumed tokens: 1441792000 | elapsed time per iteration (s): 0.57 | learning rate: 1.484E-04 | global batch size: 256 | lm loss: 3.262076E+00 | grad norm: 0.606 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.645 | TFLOPs: 43.15 | +7: iteration 2760/ 7508 | consumed samples: 706560 | consumed tokens: 1447034880 | elapsed time per iteration (s): 0.58 | learning rate: 1.480E-04 | global batch size: 256 | lm loss: 3.294683E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.237 | TFLOPs: 42.16 | +7: iteration 2770/ 7508 | consumed samples: 709120 | consumed tokens: 1452277760 | elapsed time per iteration (s): 0.57 | learning rate: 1.477E-04 | global batch size: 256 | lm loss: 3.260179E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.538 | TFLOPs: 43.14 | +7: iteration 2780/ 7508 | consumed samples: 711680 | consumed tokens: 1457520640 | elapsed time per iteration (s): 0.57 | learning rate: 1.473E-04 | global batch size: 256 | lm loss: 3.250872E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.688 | TFLOPs: 42.78 | +7: iteration 2790/ 7508 | consumed samples: 714240 | consumed tokens: 1462763520 | elapsed time per iteration (s): 0.58 | learning rate: 1.470E-04 | global batch size: 256 | lm loss: 3.273694E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.157 | TFLOPs: 42.44 | +7: iteration 2800/ 7508 | consumed samples: 716800 | consumed tokens: 1468006400 | elapsed time per iteration (s): 0.57 | learning rate: 1.466E-04 | global batch size: 256 | lm loss: 3.231618E+00 | grad norm: 0.816 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.437 | TFLOPs: 42.85 | +7: iteration 2810/ 7508 | consumed samples: 719360 | consumed tokens: 1473249280 | elapsed time per iteration (s): 0.57 | learning rate: 1.463E-04 | global batch size: 256 | lm loss: 3.262796E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.701 | TFLOPs: 42.97 | +7: iteration 2820/ 7508 | consumed samples: 721920 | consumed tokens: 1478492160 | elapsed time per iteration (s): 0.57 | learning rate: 1.459E-04 | global batch size: 256 | lm loss: 3.260009E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.515 | TFLOPs: 42.95 | +7: iteration 2830/ 7508 | consumed samples: 724480 | consumed tokens: 1483735040 | elapsed time per iteration (s): 0.57 | learning rate: 1.456E-04 | global batch size: 256 | lm loss: 3.241673E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.588 | TFLOPs: 42.67 | +7: iteration 2840/ 7508 | consumed samples: 727040 | consumed tokens: 1488977920 | elapsed time per iteration (s): 0.58 | learning rate: 1.452E-04 | global batch size: 256 | lm loss: 3.251957E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.649 | TFLOPs: 42.39 | +7: iteration 2850/ 7508 | consumed samples: 729600 | consumed tokens: 1494220800 | elapsed time per iteration (s): 0.59 | learning rate: 1.449E-04 | global batch size: 256 | lm loss: 3.264837E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 433.742 | TFLOPs: 41.35 | +7: iteration 2860/ 7508 | consumed samples: 732160 | consumed tokens: 1499463680 | elapsed time per iteration (s): 0.56 | learning rate: 1.445E-04 | global batch size: 256 | lm loss: 3.247387E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.487 | TFLOPs: 43.71 | +7: iteration 2870/ 7508 | consumed samples: 734720 | consumed tokens: 1504706560 | elapsed time per iteration (s): 0.56 | learning rate: 1.442E-04 | global batch size: 256 | lm loss: 3.258736E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.456 | TFLOPs: 43.71 | +7: iteration 2880/ 7508 | consumed samples: 737280 | consumed tokens: 1509949440 | elapsed time per iteration (s): 0.57 | learning rate: 1.438E-04 | global batch size: 256 | lm loss: 3.228247E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.379 | TFLOPs: 42.84 | +7: iteration 2890/ 7508 | consumed samples: 739840 | consumed tokens: 1515192320 | elapsed time per iteration (s): 0.59 | learning rate: 1.435E-04 | global batch size: 256 | lm loss: 3.223417E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.601 | TFLOPs: 41.43 | +7: iteration 2900/ 7508 | consumed samples: 742400 | consumed tokens: 1520435200 | elapsed time per iteration (s): 0.56 | learning rate: 1.431E-04 | global batch size: 256 | lm loss: 3.248331E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.620 | TFLOPs: 43.53 | +7: iteration 2910/ 7508 | consumed samples: 744960 | consumed tokens: 1525678080 | elapsed time per iteration (s): 0.56 | learning rate: 1.428E-04 | global batch size: 256 | lm loss: 3.249603E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.159 | TFLOPs: 43.30 | +7: iteration 2920/ 7508 | consumed samples: 747520 | consumed tokens: 1530920960 | elapsed time per iteration (s): 0.56 | learning rate: 1.424E-04 | global batch size: 256 | lm loss: 3.231049E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.143 | TFLOPs: 43.20 | +7: iteration 2930/ 7508 | consumed samples: 750080 | consumed tokens: 1536163840 | elapsed time per iteration (s): 0.56 | learning rate: 1.421E-04 | global batch size: 256 | lm loss: 3.208722E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.611 | TFLOPs: 43.25 | +7: iteration 2940/ 7508 | consumed samples: 752640 | consumed tokens: 1541406720 | elapsed time per iteration (s): 0.57 | learning rate: 1.417E-04 | global batch size: 256 | lm loss: 3.269192E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.962 | TFLOPs: 42.61 | +7: iteration 2950/ 7508 | consumed samples: 755200 | consumed tokens: 1546649600 | elapsed time per iteration (s): 0.58 | learning rate: 1.413E-04 | global batch size: 256 | lm loss: 3.209320E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.999 | TFLOPs: 42.33 | +7: iteration 2960/ 7508 | consumed samples: 757760 | consumed tokens: 1551892480 | elapsed time per iteration (s): 0.56 | learning rate: 1.410E-04 | global batch size: 256 | lm loss: 3.207060E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.530 | TFLOPs: 43.33 | +7: iteration 2970/ 7508 | consumed samples: 760320 | consumed tokens: 1557135360 | elapsed time per iteration (s): 0.58 | learning rate: 1.406E-04 | global batch size: 256 | lm loss: 3.209820E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.728 | TFLOPs: 42.11 | +7: iteration 2980/ 7508 | consumed samples: 762880 | consumed tokens: 1562378240 | elapsed time per iteration (s): 0.57 | learning rate: 1.403E-04 | global batch size: 256 | lm loss: 3.268608E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.999 | TFLOPs: 43.09 | +7: iteration 2990/ 7508 | consumed samples: 765440 | consumed tokens: 1567621120 | elapsed time per iteration (s): 0.58 | learning rate: 1.399E-04 | global batch size: 256 | lm loss: 3.200533E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.747 | TFLOPs: 41.93 | +7: iteration 3000/ 7508 | consumed samples: 768000 | consumed tokens: 1572864000 | elapsed time per iteration (s): 0.56 | learning rate: 1.396E-04 | global batch size: 256 | lm loss: 3.206948E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.386 | TFLOPs: 43.89 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 3000 | lm loss value: 3.046074E+00 | lm loss PPL: 2.103261E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 3000 to checkpoints_421moscar +0: [2022-11-29 17:23:59,847] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step3000 is begin to save! +0: [2022-11-29 17:23:59,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:23:59,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:23:59,990] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:24:00,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:24:00,031] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:24:00,071] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:24:00,071] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:24:00,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:24:00,111] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:24:00,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:24:00,150] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:24:00,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:24:00,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:24:00,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:24:00,228] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:24:00,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:24:00,268] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:24:00,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:24:00,307] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:24:00,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:24:00,346] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:24:00,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:24:00,389] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:24:00,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:24:00,429] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:24:00,468] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:24:00,469] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:24:00,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:24:00,510] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:24:00,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:24:00,549] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:24:00,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:24:00,590] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/layer_18-model_00-model_states.pt... +0: [2022-11-29 17:24:00,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/layer_18-model_00-model_states.pt. +0: [2022-11-29 17:24:00,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:24:00,668] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:24:00,668] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/layer_20-model_00-model_states.pt... +0: [2022-11-29 17:24:00,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/layer_20-model_00-model_states.pt. +0: [2022-11-29 17:24:00,707] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/layer_22-model_00-model_states.pt... +0: [2022-11-29 17:24:00,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/layer_22-model_00-model_states.pt. +0: [2022-11-29 17:24:00,711] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_421moscar/global_step3000/mp_rank_00_model_states.pt +0: [2022-11-29 17:24:00,712] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:24:00,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:24:00,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:24:00,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:24:00,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:24:00,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:24:00,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:24:00,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:24:00,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:24:00,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:24:00,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:24:00,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:24:00,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:24:00,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:24:00,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:24:00,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:24:00,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:24:00,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:24:00,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:24:00,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:24:00,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:24:00,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:24:00,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:24:00,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:24:00,828] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:24:00,828] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:24:00,828] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:24:00,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:24:00,832] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:24:00,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:24:00,832] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:24:00,832] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:24:00,832] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:24:00,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:24:00,832] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:24:00,832] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:24:00,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:24:00,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:24:00,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:24:00,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:24:00,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:24:00,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:24:00,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:24:00,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:24:00,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:24:00,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:24:00,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:24:00,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:24:00,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:24:00,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:24:00,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:24:00,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:24:00,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:24:00,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:24:00,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:24:00,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:24:00,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:24:00,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:24:00,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:24:00,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:24:00,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:24:00,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:24:00,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:24:00,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +5: [2022-11-29 17:24:00,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:24:00,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:24:00,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +3: [2022-11-29 17:24:00,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:24:00,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:24:00,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +5: [2022-11-29 17:24:00,833] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:24:00,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:24:00,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +3: [2022-11-29 17:24:00,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:24:00,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:24:00,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +5: [2022-11-29 17:24:00,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:24:00,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:24:00,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +3: [2022-11-29 17:24:00,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:24:00,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:24:00,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +5: [2022-11-29 17:24:00,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:24:00,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:24:00,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:24:00,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:24:00,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:24:00,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:24:00,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:24:00,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:24:00,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:24:00,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:24:00,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:24:00,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:24:00,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:24:00,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:24:00,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:24:00,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:24:00,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:24:00,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:24:00,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:24:00,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:24:00,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:24:00,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:24:00,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:24:00,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:24:00,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:24:00,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:24:00,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:24:00,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:24:00,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:24:00,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:24:00,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +4: [2022-11-29 17:24:00,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +1: [2022-11-29 17:24:00,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:24:00,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:24:00,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:24:00,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:24:00,840] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:24:00,840] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:24:00,840] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:24:00,840] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:24:00,841] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:24:00,841] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:24:00,841] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:24:00,841] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:24:00,841] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:24:00,841] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:24:00,841] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:24:00,841] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:24:00,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:24:00,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:24:00,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:24:00,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:24:00,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:24:00,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:24:00,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:24:00,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:24:00,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:24:00,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:24:00,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:24:00,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:24:00,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:24:00,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:24:00,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:24:00,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:24:00,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:24:00,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:24:00,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:24:00,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:24:00,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:24:00,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:24:00,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:24:00,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:24:00,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:24:00,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:24:00,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:24:00,828] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:24:00,828] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:24:00,828] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:24:00,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:24:00,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:24:00,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:24:00,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:24:00,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:24:00,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:24:00,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:24:00,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:24:00,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:24:00,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:24:00,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:24:00,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:24:00,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:24:00,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:24:00,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:24:00,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:24:00,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:24:00,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:24:00,882] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:24:00,883] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:24:00,883] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:24:00,884] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:24:00,884] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:24:00,884] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:24:00,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:24:00,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:24:00,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:24:00,900] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:24:00,900] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:24:00,914] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:24:00,914] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:24:00,914] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:24:00,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:24:00,920] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:24:00,920] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: successfully saved checkpoint at iteration 3000 to checkpoints_421moscar +7: time (ms) | save-checkpoint: 1078.24 +7: iteration 3010/ 7508 | consumed samples: 770560 | consumed tokens: 1578106880 | elapsed time per iteration (s): 0.69 | learning rate: 1.392E-04 | global batch size: 256 | lm loss: 3.225602E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 371.826 | TFLOPs: 35.45 | +7: iteration 3020/ 7508 | consumed samples: 773120 | consumed tokens: 1583349760 | elapsed time per iteration (s): 0.57 | learning rate: 1.388E-04 | global batch size: 256 | lm loss: 3.232943E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.118 | TFLOPs: 42.72 | +7: iteration 3030/ 7508 | consumed samples: 775680 | consumed tokens: 1588592640 | elapsed time per iteration (s): 0.56 | learning rate: 1.385E-04 | global batch size: 256 | lm loss: 3.207411E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.772 | TFLOPs: 43.26 | +7: iteration 3040/ 7508 | consumed samples: 778240 | consumed tokens: 1593835520 | elapsed time per iteration (s): 0.56 | learning rate: 1.381E-04 | global batch size: 256 | lm loss: 3.231520E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.123 | TFLOPs: 43.39 | +7: iteration 3050/ 7508 | consumed samples: 780800 | consumed tokens: 1599078400 | elapsed time per iteration (s): 0.56 | learning rate: 1.378E-04 | global batch size: 256 | lm loss: 3.223892E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.902 | TFLOPs: 43.47 | +7: iteration 3060/ 7508 | consumed samples: 783360 | consumed tokens: 1604321280 | elapsed time per iteration (s): 0.56 | learning rate: 1.374E-04 | global batch size: 256 | lm loss: 3.193266E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.328 | TFLOPs: 43.51 | +7: iteration 3070/ 7508 | consumed samples: 785920 | consumed tokens: 1609564160 | elapsed time per iteration (s): 0.57 | learning rate: 1.370E-04 | global batch size: 256 | lm loss: 3.220886E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.787 | TFLOPs: 42.98 | +7: iteration 3080/ 7508 | consumed samples: 788480 | consumed tokens: 1614807040 | elapsed time per iteration (s): 0.57 | learning rate: 1.367E-04 | global batch size: 256 | lm loss: 3.229825E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.801 | TFLOPs: 42.69 | +7: iteration 3090/ 7508 | consumed samples: 791040 | consumed tokens: 1620049920 | elapsed time per iteration (s): 0.57 | learning rate: 1.363E-04 | global batch size: 256 | lm loss: 3.220149E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.838 | TFLOPs: 42.79 | +7: iteration 3100/ 7508 | consumed samples: 793600 | consumed tokens: 1625292800 | elapsed time per iteration (s): 0.57 | learning rate: 1.359E-04 | global batch size: 256 | lm loss: 3.207221E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.394 | TFLOPs: 42.56 | +7: iteration 3110/ 7508 | consumed samples: 796160 | consumed tokens: 1630535680 | elapsed time per iteration (s): 0.56 | learning rate: 1.356E-04 | global batch size: 256 | lm loss: 3.208154E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.942 | TFLOPs: 43.56 | +7: iteration 3120/ 7508 | consumed samples: 798720 | consumed tokens: 1635778560 | elapsed time per iteration (s): 0.57 | learning rate: 1.352E-04 | global batch size: 256 | lm loss: 3.223250E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.929 | TFLOPs: 43.09 | +7: iteration 3130/ 7508 | consumed samples: 801280 | consumed tokens: 1641021440 | elapsed time per iteration (s): 0.56 | learning rate: 1.348E-04 | global batch size: 256 | lm loss: 3.225422E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.795 | TFLOPs: 43.36 | +7: iteration 3140/ 7508 | consumed samples: 803840 | consumed tokens: 1646264320 | elapsed time per iteration (s): 0.56 | learning rate: 1.345E-04 | global batch size: 256 | lm loss: 3.199251E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.185 | TFLOPs: 43.21 | +7: iteration 3150/ 7508 | consumed samples: 806400 | consumed tokens: 1651507200 | elapsed time per iteration (s): 0.57 | learning rate: 1.341E-04 | global batch size: 256 | lm loss: 3.192194E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.067 | TFLOPs: 43.10 | +7: iteration 3160/ 7508 | consumed samples: 808960 | consumed tokens: 1656750080 | elapsed time per iteration (s): 0.58 | learning rate: 1.337E-04 | global batch size: 256 | lm loss: 3.190902E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.879 | TFLOPs: 41.94 | +7: iteration 3170/ 7508 | consumed samples: 811520 | consumed tokens: 1661992960 | elapsed time per iteration (s): 0.58 | learning rate: 1.334E-04 | global batch size: 256 | lm loss: 3.192649E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.582 | TFLOPs: 42.20 | +7: iteration 3180/ 7508 | consumed samples: 814080 | consumed tokens: 1667235840 | elapsed time per iteration (s): 0.55 | learning rate: 1.330E-04 | global batch size: 256 | lm loss: 3.212777E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 462.205 | TFLOPs: 44.07 | +7: iteration 3190/ 7508 | consumed samples: 816640 | consumed tokens: 1672478720 | elapsed time per iteration (s): 0.57 | learning rate: 1.326E-04 | global batch size: 256 | lm loss: 3.183294E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.650 | TFLOPs: 42.77 | +7: iteration 3200/ 7508 | consumed samples: 819200 | consumed tokens: 1677721600 | elapsed time per iteration (s): 0.57 | learning rate: 1.323E-04 | global batch size: 256 | lm loss: 3.226568E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.999 | TFLOPs: 42.62 | +7: iteration 3210/ 7508 | consumed samples: 821760 | consumed tokens: 1682964480 | elapsed time per iteration (s): 0.57 | learning rate: 1.319E-04 | global batch size: 256 | lm loss: 3.194293E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.408 | TFLOPs: 42.56 | +7: iteration 3220/ 7508 | consumed samples: 824320 | consumed tokens: 1688207360 | elapsed time per iteration (s): 0.56 | learning rate: 1.315E-04 | global batch size: 256 | lm loss: 3.199486E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.285 | TFLOPs: 43.41 | +7: iteration 3230/ 7508 | consumed samples: 826880 | consumed tokens: 1693450240 | elapsed time per iteration (s): 0.58 | learning rate: 1.312E-04 | global batch size: 256 | lm loss: 3.183058E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.525 | TFLOPs: 42.19 | +7: iteration 3240/ 7508 | consumed samples: 829440 | consumed tokens: 1698693120 | elapsed time per iteration (s): 0.56 | learning rate: 1.308E-04 | global batch size: 256 | lm loss: 3.185892E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.917 | TFLOPs: 43.47 | +7: iteration 3250/ 7508 | consumed samples: 832000 | consumed tokens: 1703936000 | elapsed time per iteration (s): 0.56 | learning rate: 1.304E-04 | global batch size: 256 | lm loss: 3.164134E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.405 | TFLOPs: 43.61 | +7: iteration 3260/ 7508 | consumed samples: 834560 | consumed tokens: 1709178880 | elapsed time per iteration (s): 0.56 | learning rate: 1.301E-04 | global batch size: 256 | lm loss: 3.159031E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 459.424 | TFLOPs: 43.80 | +7: iteration 3270/ 7508 | consumed samples: 837120 | consumed tokens: 1714421760 | elapsed time per iteration (s): 0.56 | learning rate: 1.297E-04 | global batch size: 256 | lm loss: 3.204600E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.124 | TFLOPs: 43.49 | +7: iteration 3280/ 7508 | consumed samples: 839680 | consumed tokens: 1719664640 | elapsed time per iteration (s): 0.56 | learning rate: 1.293E-04 | global batch size: 256 | lm loss: 3.184583E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.080 | TFLOPs: 43.39 | +7: iteration 3290/ 7508 | consumed samples: 842240 | consumed tokens: 1724907520 | elapsed time per iteration (s): 0.58 | learning rate: 1.289E-04 | global batch size: 256 | lm loss: 3.169680E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.162 | TFLOPs: 41.87 | +7: iteration 3300/ 7508 | consumed samples: 844800 | consumed tokens: 1730150400 | elapsed time per iteration (s): 0.59 | learning rate: 1.286E-04 | global batch size: 256 | lm loss: 3.187906E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.229 | TFLOPs: 41.59 | +7: iteration 3310/ 7508 | consumed samples: 847360 | consumed tokens: 1735393280 | elapsed time per iteration (s): 0.57 | learning rate: 1.282E-04 | global batch size: 256 | lm loss: 3.188167E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.269 | TFLOPs: 43.12 | +7: iteration 3320/ 7508 | consumed samples: 849920 | consumed tokens: 1740636160 | elapsed time per iteration (s): 0.57 | learning rate: 1.278E-04 | global batch size: 256 | lm loss: 3.162715E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.561 | TFLOPs: 42.67 | +7: iteration 3330/ 7508 | consumed samples: 852480 | consumed tokens: 1745879040 | elapsed time per iteration (s): 0.57 | learning rate: 1.275E-04 | global batch size: 256 | lm loss: 3.189956E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.751 | TFLOPs: 43.16 | +7: iteration 3340/ 7508 | consumed samples: 855040 | consumed tokens: 1751121920 | elapsed time per iteration (s): 0.57 | learning rate: 1.271E-04 | global batch size: 256 | lm loss: 3.191939E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.135 | TFLOPs: 42.53 | +7: iteration 3350/ 7508 | consumed samples: 857600 | consumed tokens: 1756364800 | elapsed time per iteration (s): 0.56 | learning rate: 1.267E-04 | global batch size: 256 | lm loss: 3.172893E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.016 | TFLOPs: 43.38 | +7: iteration 3360/ 7508 | consumed samples: 860160 | consumed tokens: 1761607680 | elapsed time per iteration (s): 0.56 | learning rate: 1.263E-04 | global batch size: 256 | lm loss: 3.160878E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.617 | TFLOPs: 43.63 | +7: iteration 3370/ 7508 | consumed samples: 862720 | consumed tokens: 1766850560 | elapsed time per iteration (s): 0.59 | learning rate: 1.260E-04 | global batch size: 256 | lm loss: 3.186474E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.412 | TFLOPs: 41.42 | +7: iteration 3380/ 7508 | consumed samples: 865280 | consumed tokens: 1772093440 | elapsed time per iteration (s): 0.56 | learning rate: 1.256E-04 | global batch size: 256 | lm loss: 3.176845E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.145 | TFLOPs: 43.20 | +7: iteration 3390/ 7508 | consumed samples: 867840 | consumed tokens: 1777336320 | elapsed time per iteration (s): 0.56 | learning rate: 1.252E-04 | global batch size: 256 | lm loss: 3.188671E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.401 | TFLOPs: 43.89 | +7: iteration 3400/ 7508 | consumed samples: 870400 | consumed tokens: 1782579200 | elapsed time per iteration (s): 0.57 | learning rate: 1.248E-04 | global batch size: 256 | lm loss: 3.147341E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.823 | TFLOPs: 43.17 | +7: iteration 3410/ 7508 | consumed samples: 872960 | consumed tokens: 1787822080 | elapsed time per iteration (s): 0.56 | learning rate: 1.245E-04 | global batch size: 256 | lm loss: 3.163446E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.280 | TFLOPs: 43.31 | +7: iteration 3420/ 7508 | consumed samples: 875520 | consumed tokens: 1793064960 | elapsed time per iteration (s): 0.56 | learning rate: 1.241E-04 | global batch size: 256 | lm loss: 3.138813E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.137 | TFLOPs: 43.49 | +7: iteration 3430/ 7508 | consumed samples: 878080 | consumed tokens: 1798307840 | elapsed time per iteration (s): 0.56 | learning rate: 1.237E-04 | global batch size: 256 | lm loss: 3.174379E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.997 | TFLOPs: 43.95 | +7: iteration 3440/ 7508 | consumed samples: 880640 | consumed tokens: 1803550720 | elapsed time per iteration (s): 0.56 | learning rate: 1.233E-04 | global batch size: 256 | lm loss: 3.177172E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.961 | TFLOPs: 43.38 | +7: iteration 3450/ 7508 | consumed samples: 883200 | consumed tokens: 1808793600 | elapsed time per iteration (s): 0.57 | learning rate: 1.230E-04 | global batch size: 256 | lm loss: 3.184731E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.453 | TFLOPs: 43.14 | +7: iteration 3460/ 7508 | consumed samples: 885760 | consumed tokens: 1814036480 | elapsed time per iteration (s): 0.56 | learning rate: 1.226E-04 | global batch size: 256 | lm loss: 3.161905E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.766 | TFLOPs: 43.36 | +7: iteration 3470/ 7508 | consumed samples: 888320 | consumed tokens: 1819279360 | elapsed time per iteration (s): 0.57 | learning rate: 1.222E-04 | global batch size: 256 | lm loss: 3.164964E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.993 | TFLOPs: 43.00 | +7: iteration 3480/ 7508 | consumed samples: 890880 | consumed tokens: 1824522240 | elapsed time per iteration (s): 0.57 | learning rate: 1.218E-04 | global batch size: 256 | lm loss: 3.172697E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.281 | TFLOPs: 42.55 | +7: iteration 3490/ 7508 | consumed samples: 893440 | consumed tokens: 1829765120 | elapsed time per iteration (s): 0.56 | learning rate: 1.214E-04 | global batch size: 256 | lm loss: 3.137758E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.202 | TFLOPs: 43.40 | +7: iteration 3500/ 7508 | consumed samples: 896000 | consumed tokens: 1835008000 | elapsed time per iteration (s): 0.56 | learning rate: 1.211E-04 | global batch size: 256 | lm loss: 3.182012E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.753 | TFLOPs: 43.74 | +7: iteration 3510/ 7508 | consumed samples: 898560 | consumed tokens: 1840250880 | elapsed time per iteration (s): 0.56 | learning rate: 1.207E-04 | global batch size: 256 | lm loss: 3.140066E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 459.556 | TFLOPs: 43.81 | +7: iteration 3520/ 7508 | consumed samples: 901120 | consumed tokens: 1845493760 | elapsed time per iteration (s): 0.57 | learning rate: 1.203E-04 | global batch size: 256 | lm loss: 3.158965E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.284 | TFLOPs: 42.83 | +7: iteration 3530/ 7508 | consumed samples: 903680 | consumed tokens: 1850736640 | elapsed time per iteration (s): 0.57 | learning rate: 1.199E-04 | global batch size: 256 | lm loss: 3.150394E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.939 | TFLOPs: 42.61 | +7: iteration 3540/ 7508 | consumed samples: 906240 | consumed tokens: 1855979520 | elapsed time per iteration (s): 0.56 | learning rate: 1.196E-04 | global batch size: 256 | lm loss: 3.162367E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.931 | TFLOPs: 43.56 | +7: iteration 3550/ 7508 | consumed samples: 908800 | consumed tokens: 1861222400 | elapsed time per iteration (s): 0.57 | learning rate: 1.192E-04 | global batch size: 256 | lm loss: 3.174954E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.697 | TFLOPs: 43.06 | +7: iteration 3560/ 7508 | consumed samples: 911360 | consumed tokens: 1866465280 | elapsed time per iteration (s): 0.57 | learning rate: 1.188E-04 | global batch size: 256 | lm loss: 3.132491E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.924 | TFLOPs: 43.09 | +7: iteration 3570/ 7508 | consumed samples: 913920 | consumed tokens: 1871708160 | elapsed time per iteration (s): 0.57 | learning rate: 1.184E-04 | global batch size: 256 | lm loss: 3.174811E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.276 | TFLOPs: 42.83 | +7: iteration 3580/ 7508 | consumed samples: 916480 | consumed tokens: 1876951040 | elapsed time per iteration (s): 0.56 | learning rate: 1.180E-04 | global batch size: 256 | lm loss: 3.146375E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.957 | TFLOPs: 43.66 | +7: iteration 3590/ 7508 | consumed samples: 919040 | consumed tokens: 1882193920 | elapsed time per iteration (s): 0.56 | learning rate: 1.177E-04 | global batch size: 256 | lm loss: 3.142975E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.303 | TFLOPs: 43.22 | +7: iteration 3600/ 7508 | consumed samples: 921600 | consumed tokens: 1887436800 | elapsed time per iteration (s): 0.57 | learning rate: 1.173E-04 | global batch size: 256 | lm loss: 3.159371E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.628 | TFLOPs: 42.68 | +7: iteration 3610/ 7508 | consumed samples: 924160 | consumed tokens: 1892679680 | elapsed time per iteration (s): 0.55 | learning rate: 1.169E-04 | global batch size: 256 | lm loss: 3.138197E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 462.195 | TFLOPs: 44.07 | +7: iteration 3620/ 7508 | consumed samples: 926720 | consumed tokens: 1897922560 | elapsed time per iteration (s): 0.56 | learning rate: 1.165E-04 | global batch size: 256 | lm loss: 3.148647E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.163 | TFLOPs: 43.30 | +7: iteration 3630/ 7508 | consumed samples: 929280 | consumed tokens: 1903165440 | elapsed time per iteration (s): 0.56 | learning rate: 1.161E-04 | global batch size: 256 | lm loss: 3.166543E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.072 | TFLOPs: 43.48 | +7: iteration 3640/ 7508 | consumed samples: 931840 | consumed tokens: 1908408320 | elapsed time per iteration (s): 0.57 | learning rate: 1.158E-04 | global batch size: 256 | lm loss: 3.131576E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.715 | TFLOPs: 42.68 | +7: iteration 3650/ 7508 | consumed samples: 934400 | consumed tokens: 1913651200 | elapsed time per iteration (s): 0.56 | learning rate: 1.154E-04 | global batch size: 256 | lm loss: 3.135140E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.686 | TFLOPs: 43.54 | +7: iteration 3660/ 7508 | consumed samples: 936960 | consumed tokens: 1918894080 | elapsed time per iteration (s): 0.57 | learning rate: 1.150E-04 | global batch size: 256 | lm loss: 3.152849E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.225 | TFLOPs: 42.83 | +7: iteration 3670/ 7508 | consumed samples: 939520 | consumed tokens: 1924136960 | elapsed time per iteration (s): 0.58 | learning rate: 1.146E-04 | global batch size: 256 | lm loss: 3.162427E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.972 | TFLOPs: 42.04 | +7: iteration 3680/ 7508 | consumed samples: 942080 | consumed tokens: 1929379840 | elapsed time per iteration (s): 0.58 | learning rate: 1.142E-04 | global batch size: 256 | lm loss: 3.122979E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.717 | TFLOPs: 41.73 | +7: iteration 3690/ 7508 | consumed samples: 944640 | consumed tokens: 1934622720 | elapsed time per iteration (s): 0.58 | learning rate: 1.139E-04 | global batch size: 256 | lm loss: 3.138215E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.391 | TFLOPs: 41.99 | +7: iteration 3700/ 7508 | consumed samples: 947200 | consumed tokens: 1939865600 | elapsed time per iteration (s): 0.56 | learning rate: 1.135E-04 | global batch size: 256 | lm loss: 3.148333E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.712 | TFLOPs: 43.54 | +7: iteration 3710/ 7508 | consumed samples: 949760 | consumed tokens: 1945108480 | elapsed time per iteration (s): 0.56 | learning rate: 1.131E-04 | global batch size: 256 | lm loss: 3.164355E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 459.097 | TFLOPs: 43.77 | +7: iteration 3720/ 7508 | consumed samples: 952320 | consumed tokens: 1950351360 | elapsed time per iteration (s): 0.57 | learning rate: 1.127E-04 | global batch size: 256 | lm loss: 3.152676E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.627 | TFLOPs: 42.96 | +7: iteration 3730/ 7508 | consumed samples: 954880 | consumed tokens: 1955594240 | elapsed time per iteration (s): 0.56 | learning rate: 1.123E-04 | global batch size: 256 | lm loss: 3.149700E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.747 | TFLOPs: 43.64 | +7: iteration 3740/ 7508 | consumed samples: 957440 | consumed tokens: 1960837120 | elapsed time per iteration (s): 0.55 | learning rate: 1.120E-04 | global batch size: 256 | lm loss: 3.113429E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.997 | TFLOPs: 44.05 | +7: iteration 3750/ 7508 | consumed samples: 960000 | consumed tokens: 1966080000 | elapsed time per iteration (s): 0.57 | learning rate: 1.116E-04 | global batch size: 256 | lm loss: 3.118960E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.499 | TFLOPs: 43.05 | +7: iteration 3760/ 7508 | consumed samples: 962560 | consumed tokens: 1971322880 | elapsed time per iteration (s): 0.56 | learning rate: 1.112E-04 | global batch size: 256 | lm loss: 3.121901E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.340 | TFLOPs: 43.51 | +7: iteration 3770/ 7508 | consumed samples: 965120 | consumed tokens: 1976565760 | elapsed time per iteration (s): 0.56 | learning rate: 1.108E-04 | global batch size: 256 | lm loss: 3.146084E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.012 | TFLOPs: 43.48 | +7: iteration 3780/ 7508 | consumed samples: 967680 | consumed tokens: 1981808640 | elapsed time per iteration (s): 0.56 | learning rate: 1.104E-04 | global batch size: 256 | lm loss: 3.137843E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.089 | TFLOPs: 43.39 | +7: iteration 3790/ 7508 | consumed samples: 970240 | consumed tokens: 1987051520 | elapsed time per iteration (s): 0.56 | learning rate: 1.101E-04 | global batch size: 256 | lm loss: 3.115147E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.584 | TFLOPs: 43.44 | +7: iteration 3800/ 7508 | consumed samples: 972800 | consumed tokens: 1992294400 | elapsed time per iteration (s): 0.56 | learning rate: 1.097E-04 | global batch size: 256 | lm loss: 3.153136E+00 | grad norm: 0.426 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.355 | TFLOPs: 43.70 | +7: iteration 3810/ 7508 | consumed samples: 975360 | consumed tokens: 1997537280 | elapsed time per iteration (s): 0.59 | learning rate: 1.093E-04 | global batch size: 256 | lm loss: 3.136713E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 431.573 | TFLOPs: 41.15 | +7: iteration 3820/ 7508 | consumed samples: 977920 | consumed tokens: 2002780160 | elapsed time per iteration (s): 0.56 | learning rate: 1.089E-04 | global batch size: 256 | lm loss: 3.131602E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.554 | TFLOPs: 43.62 | +7: iteration 3830/ 7508 | consumed samples: 980480 | consumed tokens: 2008023040 | elapsed time per iteration (s): 0.57 | learning rate: 1.085E-04 | global batch size: 256 | lm loss: 3.131060E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.708 | TFLOPs: 42.87 | +7: iteration 3840/ 7508 | consumed samples: 983040 | consumed tokens: 2013265920 | elapsed time per iteration (s): 0.56 | learning rate: 1.082E-04 | global batch size: 256 | lm loss: 3.136223E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.119 | TFLOPs: 43.68 | +7: iteration 3850/ 7508 | consumed samples: 985600 | consumed tokens: 2018508800 | elapsed time per iteration (s): 0.57 | learning rate: 1.078E-04 | global batch size: 256 | lm loss: 3.161945E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.443 | TFLOPs: 43.04 | +7: iteration 3860/ 7508 | consumed samples: 988160 | consumed tokens: 2023751680 | elapsed time per iteration (s): 0.56 | learning rate: 1.074E-04 | global batch size: 256 | lm loss: 3.119133E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.725 | TFLOPs: 43.93 | +7: iteration 3870/ 7508 | consumed samples: 990720 | consumed tokens: 2028994560 | elapsed time per iteration (s): 0.56 | learning rate: 1.070E-04 | global batch size: 256 | lm loss: 3.123623E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.075 | TFLOPs: 43.29 | +7: iteration 3880/ 7508 | consumed samples: 993280 | consumed tokens: 2034237440 | elapsed time per iteration (s): 0.57 | learning rate: 1.066E-04 | global batch size: 256 | lm loss: 3.114463E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.613 | TFLOPs: 43.06 | +7: iteration 3890/ 7508 | consumed samples: 995840 | consumed tokens: 2039480320 | elapsed time per iteration (s): 0.55 | learning rate: 1.063E-04 | global batch size: 256 | lm loss: 3.115380E+00 | grad norm: 1.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.483 | TFLOPs: 44.00 | +7: iteration 3900/ 7508 | consumed samples: 998400 | consumed tokens: 2044723200 | elapsed time per iteration (s): 0.56 | learning rate: 1.059E-04 | global batch size: 256 | lm loss: 3.114578E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.068 | TFLOPs: 43.96 | +7: iteration 3910/ 7508 | consumed samples: 1000960 | consumed tokens: 2049966080 | elapsed time per iteration (s): 0.55 | learning rate: 1.055E-04 | global batch size: 256 | lm loss: 3.105050E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.867 | TFLOPs: 44.03 | +7: iteration 3920/ 7508 | consumed samples: 1003520 | consumed tokens: 2055208960 | elapsed time per iteration (s): 0.56 | learning rate: 1.051E-04 | global batch size: 256 | lm loss: 3.106391E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.048 | TFLOPs: 43.96 | +7: iteration 3930/ 7508 | consumed samples: 1006080 | consumed tokens: 2060451840 | elapsed time per iteration (s): 0.59 | learning rate: 1.047E-04 | global batch size: 256 | lm loss: 3.112336E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.157 | TFLOPs: 41.58 | +7: iteration 3940/ 7508 | consumed samples: 1008640 | consumed tokens: 2065694720 | elapsed time per iteration (s): 0.56 | learning rate: 1.044E-04 | global batch size: 256 | lm loss: 3.114089E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.043 | TFLOPs: 43.48 | +7: iteration 3950/ 7508 | consumed samples: 1011200 | consumed tokens: 2070937600 | elapsed time per iteration (s): 0.58 | learning rate: 1.040E-04 | global batch size: 256 | lm loss: 3.125405E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.293 | TFLOPs: 42.36 | +7: iteration 3960/ 7508 | consumed samples: 1013760 | consumed tokens: 2076180480 | elapsed time per iteration (s): 0.56 | learning rate: 1.036E-04 | global batch size: 256 | lm loss: 3.093340E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.083 | TFLOPs: 43.67 | +7: iteration 3970/ 7508 | consumed samples: 1016320 | consumed tokens: 2081423360 | elapsed time per iteration (s): 0.55 | learning rate: 1.032E-04 | global batch size: 256 | lm loss: 3.122943E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 462.284 | TFLOPs: 44.07 | +7: iteration 3980/ 7508 | consumed samples: 1018880 | consumed tokens: 2086666240 | elapsed time per iteration (s): 0.56 | learning rate: 1.028E-04 | global batch size: 256 | lm loss: 3.110517E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.796 | TFLOPs: 43.26 | +7: iteration 3990/ 7508 | consumed samples: 1021440 | consumed tokens: 2091909120 | elapsed time per iteration (s): 0.58 | learning rate: 1.025E-04 | global batch size: 256 | lm loss: 3.116075E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.167 | TFLOPs: 42.44 | +0: [2022-11-29 17:33:26,734] [INFO] [logging.py:68:log_dist] [Rank 0] step=4000, skipped=0, lr=[0.00010208850566272403, 0.00010208850566272403, 0.00010208850566272403], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 4000/ 7508 | consumed samples: 1024000 | consumed tokens: 2097152000 | elapsed time per iteration (s): 0.56 | learning rate: 1.021E-04 | global batch size: 256 | lm loss: 3.107285E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.086 | TFLOPs: 43.96 | +0: steps: 4000 loss: 3.0982 iter time (s): 0.565 samples/sec: 453.219 +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 4000 | lm loss value: 2.971264E+00 | lm loss PPL: 1.951658E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 4000 to checkpoints_421moscar +0: [2022-11-29 17:33:26,938] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step4000 is begin to save! +0: [2022-11-29 17:33:26,943] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:33:27,084] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:33:27,085] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:33:27,125] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:33:27,126] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:33:27,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:33:27,170] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:33:27,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:33:27,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:33:27,248] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:33:27,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:33:27,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:33:27,287] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:33:27,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:33:27,329] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:33:27,366] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:33:27,366] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:33:27,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:33:27,406] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:33:27,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:33:27,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:33:27,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:33:27,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:33:27,524] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:33:27,525] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:33:27,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:33:27,566] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:33:27,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:33:27,608] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:33:27,647] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:33:27,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:33:27,688] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:33:27,688] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/layer_18-model_00-model_states.pt... +0: [2022-11-29 17:33:27,731] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/layer_18-model_00-model_states.pt. +0: [2022-11-29 17:33:27,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:33:27,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:33:27,771] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/layer_20-model_00-model_states.pt... +0: [2022-11-29 17:33:27,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/layer_20-model_00-model_states.pt. +0: [2022-11-29 17:33:27,811] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/layer_22-model_00-model_states.pt... +0: [2022-11-29 17:33:27,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/layer_22-model_00-model_states.pt. +0: [2022-11-29 17:33:27,815] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_421moscar/global_step4000/mp_rank_00_model_states.pt +0: [2022-11-29 17:33:27,815] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:33:27,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:33:27,894] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:33:27,981] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:33:27,985] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:27,985] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:27,986] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:33:27,986] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:33:27,986] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:27,986] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:27,986] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:33:27,988] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:33:27,988] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:27,988] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:33:27,991] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:27,991] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:33:27,991] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:33:27,992] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:27,992] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:33:27,992] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:33:27,993] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:27,993] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:33:27,993] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:33:27,981] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:27,981] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:33:27,992] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:33:27,992] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:27,992] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:33:27,993] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:33:27,993] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:27,993] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:33:27,995] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:33:27,995] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:27,996] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:33:27,996] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:27,996] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:33:27,996] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:33:27,996] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:33:27,996] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:27,996] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:27,996] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:33:27,996] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:27,996] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:27,996] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:33:27,996] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:33:27,996] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:33:27,996] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:33:27,997] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:27,997] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:33:27,997] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:33:27,999] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:28,000] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:33:28,000] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:33:28,000] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:28,000] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:28,000] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:33:27,999] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:27,999] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:33:27,999] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:33:28,001] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:33:28,002] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:28,002] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:33:28,003] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:28,003] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:28,003] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:33:28,003] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:33:28,003] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:33:28,003] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:28,003] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:33:28,003] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:33:28,003] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:33:28,004] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:33:28,004] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:28,004] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:33:28,004] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:33:28,004] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:28,004] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:33:28,004] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:33:28,004] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:28,005] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:33:28,006] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:28,006] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:28,006] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:33:28,006] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:28,006] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:33:28,006] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:33:28,006] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:28,006] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:28,006] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:33:28,006] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:28,006] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:33:28,006] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:33:28,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:28,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:33:28,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:33:28,013] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:28,013] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:33:28,013] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:33:28,014] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:28,014] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:33:28,014] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:33:27,996] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:27,996] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:33:27,997] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:33:27,997] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:27,997] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:33:27,999] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:33:27,999] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:27,999] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:33:28,000] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:33:28,000] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:28,000] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:33:28,016] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:33:28,016] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:28,016] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:33:27,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:28,021] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:28,021] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:28,021] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:33:28,025] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:28,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:28,028] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:28,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:33:28,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:33:28,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:33:28,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:33:28,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:28,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:33:28,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:33:28,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:28,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:33:28,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:33:28,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:33:28,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:33:28,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:33:28,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:33:28,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:33:28,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:33:27,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:27,990] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:27,990] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:33:27,992] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:27,993] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:27,993] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:33:27,998] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:27,998] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:27,998] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:33:28,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:28,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:28,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:28,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:28,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:33:28,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:28,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:28,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:28,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:33:28,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:33:28,025] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:28,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +2: [2022-11-29 17:33:28,025] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:33:28,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:33:28,015] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:33:28,015] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:33:28,015] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:33:28,071] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:28,071] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:33:28,071] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:33:28,071] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:33:28,071] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:33:28,071] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:33:27,991] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:33:27,991] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:33:28,002] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:33:28,002] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:33:28,002] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:33:28,002] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:33:28,002] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:33:28,002] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:33:28,004] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:33:28,004] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:33:28,004] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:33:28,022] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:33:28,022] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:33:28,022] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:33:28,023] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:33:28,023] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:33:28,023] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:33:28,023] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:33:28,023] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:33:28,023] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:33:28,023] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:33:28,023] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:33:28,023] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:33:28,093] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:33:28,093] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: successfully saved checkpoint at iteration 4000 to checkpoints_421moscar +7: time (ms) | save-checkpoint: 1165.62 +7: iteration 4010/ 7508 | consumed samples: 1026560 | consumed tokens: 2102394880 | elapsed time per iteration (s): 0.71 | learning rate: 1.017E-04 | global batch size: 256 | lm loss: 3.114522E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 361.508 | TFLOPs: 34.47 | +7: iteration 4020/ 7508 | consumed samples: 1029120 | consumed tokens: 2107637760 | elapsed time per iteration (s): 0.55 | learning rate: 1.013E-04 | global batch size: 256 | lm loss: 3.126841E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.283 | TFLOPs: 43.98 | +7: iteration 4030/ 7508 | consumed samples: 1031680 | consumed tokens: 2112880640 | elapsed time per iteration (s): 0.56 | learning rate: 1.010E-04 | global batch size: 256 | lm loss: 3.119012E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 459.876 | TFLOPs: 43.84 | +7: iteration 4040/ 7508 | consumed samples: 1034240 | consumed tokens: 2118123520 | elapsed time per iteration (s): 0.58 | learning rate: 1.006E-04 | global batch size: 256 | lm loss: 3.124234E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.170 | TFLOPs: 41.87 | +7: iteration 4050/ 7508 | consumed samples: 1036800 | consumed tokens: 2123366400 | elapsed time per iteration (s): 0.56 | learning rate: 1.002E-04 | global batch size: 256 | lm loss: 3.111638E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.980 | TFLOPs: 43.95 | +7: iteration 4060/ 7508 | consumed samples: 1039360 | consumed tokens: 2128609280 | elapsed time per iteration (s): 0.56 | learning rate: 9.982E-05 | global batch size: 256 | lm loss: 3.117637E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.868 | TFLOPs: 43.94 | +7: iteration 4070/ 7508 | consumed samples: 1041920 | consumed tokens: 2133852160 | elapsed time per iteration (s): 0.56 | learning rate: 9.944E-05 | global batch size: 256 | lm loss: 3.086178E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.143 | TFLOPs: 43.20 | +7: iteration 4080/ 7508 | consumed samples: 1044480 | consumed tokens: 2139095040 | elapsed time per iteration (s): 0.57 | learning rate: 9.906E-05 | global batch size: 256 | lm loss: 3.113878E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.025 | TFLOPs: 42.62 | +7: iteration 4090/ 7508 | consumed samples: 1047040 | consumed tokens: 2144337920 | elapsed time per iteration (s): 0.57 | learning rate: 9.868E-05 | global batch size: 256 | lm loss: 3.133576E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.238 | TFLOPs: 43.02 | +7: iteration 4100/ 7508 | consumed samples: 1049600 | consumed tokens: 2149580800 | elapsed time per iteration (s): 0.56 | learning rate: 9.831E-05 | global batch size: 256 | lm loss: 3.109291E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.145 | TFLOPs: 43.20 | +7: iteration 4110/ 7508 | consumed samples: 1052160 | consumed tokens: 2154823680 | elapsed time per iteration (s): 0.56 | learning rate: 9.793E-05 | global batch size: 256 | lm loss: 3.097786E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.045 | TFLOPs: 43.29 | +7: iteration 4120/ 7508 | consumed samples: 1054720 | consumed tokens: 2160066560 | elapsed time per iteration (s): 0.56 | learning rate: 9.755E-05 | global batch size: 256 | lm loss: 3.084142E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.101 | TFLOPs: 43.67 | +7: iteration 4130/ 7508 | consumed samples: 1057280 | consumed tokens: 2165309440 | elapsed time per iteration (s): 0.58 | learning rate: 9.718E-05 | global batch size: 256 | lm loss: 3.115983E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.010 | TFLOPs: 42.33 | +7: iteration 4140/ 7508 | consumed samples: 1059840 | consumed tokens: 2170552320 | elapsed time per iteration (s): 0.56 | learning rate: 9.680E-05 | global batch size: 256 | lm loss: 3.093224E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.149 | TFLOPs: 43.30 | +7: iteration 4150/ 7508 | consumed samples: 1062400 | consumed tokens: 2175795200 | elapsed time per iteration (s): 0.56 | learning rate: 9.642E-05 | global batch size: 256 | lm loss: 3.104148E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.409 | TFLOPs: 43.42 | +7: iteration 4160/ 7508 | consumed samples: 1064960 | consumed tokens: 2181038080 | elapsed time per iteration (s): 0.57 | learning rate: 9.605E-05 | global batch size: 256 | lm loss: 3.104629E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.900 | TFLOPs: 42.70 | +7: iteration 4170/ 7508 | consumed samples: 1067520 | consumed tokens: 2186280960 | elapsed time per iteration (s): 0.58 | learning rate: 9.567E-05 | global batch size: 256 | lm loss: 3.085221E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.609 | TFLOPs: 42.29 | +7: iteration 4180/ 7508 | consumed samples: 1070080 | consumed tokens: 2191523840 | elapsed time per iteration (s): 0.56 | learning rate: 9.530E-05 | global batch size: 256 | lm loss: 3.068704E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.036 | TFLOPs: 43.95 | +7: iteration 4190/ 7508 | consumed samples: 1072640 | consumed tokens: 2196766720 | elapsed time per iteration (s): 0.57 | learning rate: 9.492E-05 | global batch size: 256 | lm loss: 3.094536E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.026 | TFLOPs: 42.62 | +7: iteration 4200/ 7508 | consumed samples: 1075200 | consumed tokens: 2202009600 | elapsed time per iteration (s): 0.57 | learning rate: 9.455E-05 | global batch size: 256 | lm loss: 3.092012E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.461 | TFLOPs: 42.47 | +7: iteration 4210/ 7508 | consumed samples: 1077760 | consumed tokens: 2207252480 | elapsed time per iteration (s): 0.58 | learning rate: 9.417E-05 | global batch size: 256 | lm loss: 3.114637E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.393 | TFLOPs: 42.27 | +7: iteration 4220/ 7508 | consumed samples: 1080320 | consumed tokens: 2212495360 | elapsed time per iteration (s): 0.58 | learning rate: 9.380E-05 | global batch size: 256 | lm loss: 3.120522E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.441 | TFLOPs: 42.37 | +7: iteration 4230/ 7508 | consumed samples: 1082880 | consumed tokens: 2217738240 | elapsed time per iteration (s): 0.56 | learning rate: 9.342E-05 | global batch size: 256 | lm loss: 3.095565E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.651 | TFLOPs: 43.44 | +7: iteration 4240/ 7508 | consumed samples: 1085440 | consumed tokens: 2222981120 | elapsed time per iteration (s): 0.60 | learning rate: 9.305E-05 | global batch size: 256 | lm loss: 3.130831E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 428.752 | TFLOPs: 40.88 | +7: iteration 4250/ 7508 | consumed samples: 1088000 | consumed tokens: 2228224000 | elapsed time per iteration (s): 0.60 | learning rate: 9.268E-05 | global batch size: 256 | lm loss: 3.052501E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 428.558 | TFLOPs: 40.86 | +7: iteration 4260/ 7508 | consumed samples: 1090560 | consumed tokens: 2233466880 | elapsed time per iteration (s): 0.57 | learning rate: 9.230E-05 | global batch size: 256 | lm loss: 3.129826E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.395 | TFLOPs: 42.46 | +7: iteration 4270/ 7508 | consumed samples: 1093120 | consumed tokens: 2238709760 | elapsed time per iteration (s): 0.57 | learning rate: 9.193E-05 | global batch size: 256 | lm loss: 3.102592E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.519 | TFLOPs: 42.86 | +7: iteration 4280/ 7508 | consumed samples: 1095680 | consumed tokens: 2243952640 | elapsed time per iteration (s): 0.57 | learning rate: 9.156E-05 | global batch size: 256 | lm loss: 3.105665E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.660 | TFLOPs: 42.58 | +7: iteration 4290/ 7508 | consumed samples: 1098240 | consumed tokens: 2249195520 | elapsed time per iteration (s): 0.58 | learning rate: 9.119E-05 | global batch size: 256 | lm loss: 3.102555E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.795 | TFLOPs: 42.31 | +7: iteration 4300/ 7508 | consumed samples: 1100800 | consumed tokens: 2254438400 | elapsed time per iteration (s): 0.56 | learning rate: 9.082E-05 | global batch size: 256 | lm loss: 3.047635E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.387 | TFLOPs: 43.89 | +7: iteration 4310/ 7508 | consumed samples: 1103360 | consumed tokens: 2259681280 | elapsed time per iteration (s): 0.56 | learning rate: 9.044E-05 | global batch size: 256 | lm loss: 3.081774E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.533 | TFLOPs: 43.53 | +7: iteration 4320/ 7508 | consumed samples: 1105920 | consumed tokens: 2264924160 | elapsed time per iteration (s): 0.57 | learning rate: 9.007E-05 | global batch size: 256 | lm loss: 3.072964E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.097 | TFLOPs: 43.01 | +7: iteration 4330/ 7508 | consumed samples: 1108480 | consumed tokens: 2270167040 | elapsed time per iteration (s): 0.56 | learning rate: 8.970E-05 | global batch size: 256 | lm loss: 3.077864E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.416 | TFLOPs: 43.61 | +7: iteration 4340/ 7508 | consumed samples: 1111040 | consumed tokens: 2275409920 | elapsed time per iteration (s): 0.57 | learning rate: 8.933E-05 | global batch size: 256 | lm loss: 3.118719E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.213 | TFLOPs: 43.11 | +7: iteration 4350/ 7508 | consumed samples: 1113600 | consumed tokens: 2280652800 | elapsed time per iteration (s): 0.57 | learning rate: 8.896E-05 | global batch size: 256 | lm loss: 3.066290E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.284 | TFLOPs: 43.12 | +7: iteration 4360/ 7508 | consumed samples: 1116160 | consumed tokens: 2285895680 | elapsed time per iteration (s): 0.56 | learning rate: 8.859E-05 | global batch size: 256 | lm loss: 3.056250E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.996 | TFLOPs: 43.38 | +7: iteration 4370/ 7508 | consumed samples: 1118720 | consumed tokens: 2291138560 | elapsed time per iteration (s): 0.56 | learning rate: 8.822E-05 | global batch size: 256 | lm loss: 3.084569E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.998 | TFLOPs: 43.67 | +7: iteration 4380/ 7508 | consumed samples: 1121280 | consumed tokens: 2296381440 | elapsed time per iteration (s): 0.56 | learning rate: 8.785E-05 | global batch size: 256 | lm loss: 3.088601E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.944 | TFLOPs: 43.66 | +7: iteration 4390/ 7508 | consumed samples: 1123840 | consumed tokens: 2301624320 | elapsed time per iteration (s): 0.57 | learning rate: 8.749E-05 | global batch size: 256 | lm loss: 3.074684E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.268 | TFLOPs: 42.93 | +7: iteration 4400/ 7508 | consumed samples: 1126400 | consumed tokens: 2306867200 | elapsed time per iteration (s): 0.58 | learning rate: 8.712E-05 | global batch size: 256 | lm loss: 3.071076E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.543 | TFLOPs: 42.10 | +7: iteration 4410/ 7508 | consumed samples: 1128960 | consumed tokens: 2312110080 | elapsed time per iteration (s): 0.57 | learning rate: 8.675E-05 | global batch size: 256 | lm loss: 3.080358E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.268 | TFLOPs: 42.83 | +7: iteration 4420/ 7508 | consumed samples: 1131520 | consumed tokens: 2317352960 | elapsed time per iteration (s): 0.57 | learning rate: 8.638E-05 | global batch size: 256 | lm loss: 3.073763E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.206 | TFLOPs: 42.64 | +7: iteration 4430/ 7508 | consumed samples: 1134080 | consumed tokens: 2322595840 | elapsed time per iteration (s): 0.56 | learning rate: 8.602E-05 | global batch size: 256 | lm loss: 3.078170E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.604 | TFLOPs: 43.72 | +7: iteration 4440/ 7508 | consumed samples: 1136640 | consumed tokens: 2327838720 | elapsed time per iteration (s): 0.55 | learning rate: 8.565E-05 | global batch size: 256 | lm loss: 3.062812E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.567 | TFLOPs: 44.01 | +7: iteration 4450/ 7508 | consumed samples: 1139200 | consumed tokens: 2333081600 | elapsed time per iteration (s): 0.56 | learning rate: 8.528E-05 | global batch size: 256 | lm loss: 3.072509E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 459.017 | TFLOPs: 43.76 | +7: iteration 4460/ 7508 | consumed samples: 1141760 | consumed tokens: 2338324480 | elapsed time per iteration (s): 0.56 | learning rate: 8.492E-05 | global batch size: 256 | lm loss: 3.075376E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.635 | TFLOPs: 43.92 | +7: iteration 4470/ 7508 | consumed samples: 1144320 | consumed tokens: 2343567360 | elapsed time per iteration (s): 0.56 | learning rate: 8.455E-05 | global batch size: 256 | lm loss: 3.049478E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.672 | TFLOPs: 43.63 | +7: iteration 4480/ 7508 | consumed samples: 1146880 | consumed tokens: 2348810240 | elapsed time per iteration (s): 0.58 | learning rate: 8.419E-05 | global batch size: 256 | lm loss: 3.075216E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.114 | TFLOPs: 42.34 | +7: iteration 4490/ 7508 | consumed samples: 1149440 | consumed tokens: 2354053120 | elapsed time per iteration (s): 0.56 | learning rate: 8.382E-05 | global batch size: 256 | lm loss: 3.078852E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.418 | TFLOPs: 43.32 | +7: iteration 4500/ 7508 | consumed samples: 1152000 | consumed tokens: 2359296000 | elapsed time per iteration (s): 0.56 | learning rate: 8.346E-05 | global batch size: 256 | lm loss: 3.065884E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.069 | TFLOPs: 43.48 | +7: iteration 4510/ 7508 | consumed samples: 1154560 | consumed tokens: 2364538880 | elapsed time per iteration (s): 0.56 | learning rate: 8.310E-05 | global batch size: 256 | lm loss: 3.092347E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.353 | TFLOPs: 43.22 | +7: iteration 4520/ 7508 | consumed samples: 1157120 | consumed tokens: 2369781760 | elapsed time per iteration (s): 0.57 | learning rate: 8.273E-05 | global batch size: 256 | lm loss: 3.058681E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.122 | TFLOPs: 42.63 | +7: iteration 4530/ 7508 | consumed samples: 1159680 | consumed tokens: 2375024640 | elapsed time per iteration (s): 0.55 | learning rate: 8.237E-05 | global batch size: 256 | lm loss: 3.065742E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 462.438 | TFLOPs: 44.09 | +7: iteration 4540/ 7508 | consumed samples: 1162240 | consumed tokens: 2380267520 | elapsed time per iteration (s): 0.58 | learning rate: 8.201E-05 | global batch size: 256 | lm loss: 3.069703E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.798 | TFLOPs: 41.93 | +7: iteration 4550/ 7508 | consumed samples: 1164800 | consumed tokens: 2385510400 | elapsed time per iteration (s): 0.56 | learning rate: 8.165E-05 | global batch size: 256 | lm loss: 3.068055E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.669 | TFLOPs: 43.73 | +7: iteration 4560/ 7508 | consumed samples: 1167360 | consumed tokens: 2390753280 | elapsed time per iteration (s): 0.56 | learning rate: 8.129E-05 | global batch size: 256 | lm loss: 3.055194E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.896 | TFLOPs: 43.27 | +7: iteration 4570/ 7508 | consumed samples: 1169920 | consumed tokens: 2395996160 | elapsed time per iteration (s): 0.56 | learning rate: 8.093E-05 | global batch size: 256 | lm loss: 3.067536E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.059 | TFLOPs: 43.48 | +7: iteration 4580/ 7508 | consumed samples: 1172480 | consumed tokens: 2401239040 | elapsed time per iteration (s): 0.56 | learning rate: 8.057E-05 | global batch size: 256 | lm loss: 3.057001E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.854 | TFLOPs: 43.56 | +7: iteration 4590/ 7508 | consumed samples: 1175040 | consumed tokens: 2406481920 | elapsed time per iteration (s): 0.56 | learning rate: 8.021E-05 | global batch size: 256 | lm loss: 3.057006E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.781 | TFLOPs: 43.74 | +7: iteration 4600/ 7508 | consumed samples: 1177600 | consumed tokens: 2411724800 | elapsed time per iteration (s): 0.56 | learning rate: 7.985E-05 | global batch size: 256 | lm loss: 3.065248E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.886 | TFLOPs: 43.37 | +7: iteration 4610/ 7508 | consumed samples: 1180160 | consumed tokens: 2416967680 | elapsed time per iteration (s): 0.57 | learning rate: 7.949E-05 | global batch size: 256 | lm loss: 3.062206E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.682 | TFLOPs: 43.16 | +7: iteration 4620/ 7508 | consumed samples: 1182720 | consumed tokens: 2422210560 | elapsed time per iteration (s): 0.58 | learning rate: 7.913E-05 | global batch size: 256 | lm loss: 3.049471E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.180 | TFLOPs: 42.44 | +7: iteration 4630/ 7508 | consumed samples: 1185280 | consumed tokens: 2427453440 | elapsed time per iteration (s): 0.58 | learning rate: 7.878E-05 | global batch size: 256 | lm loss: 3.071543E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.649 | TFLOPs: 42.39 | +7: iteration 4640/ 7508 | consumed samples: 1187840 | consumed tokens: 2432696320 | elapsed time per iteration (s): 0.57 | learning rate: 7.842E-05 | global batch size: 256 | lm loss: 3.078993E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.605 | TFLOPs: 42.96 | +7: iteration 4650/ 7508 | consumed samples: 1190400 | consumed tokens: 2437939200 | elapsed time per iteration (s): 0.59 | learning rate: 7.807E-05 | global batch size: 256 | lm loss: 3.049907E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.539 | TFLOPs: 41.52 | +7: iteration 4660/ 7508 | consumed samples: 1192960 | consumed tokens: 2443182080 | elapsed time per iteration (s): 0.57 | learning rate: 7.771E-05 | global batch size: 256 | lm loss: 3.054586E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.883 | TFLOPs: 43.08 | +7: iteration 4670/ 7508 | consumed samples: 1195520 | consumed tokens: 2448424960 | elapsed time per iteration (s): 0.57 | learning rate: 7.736E-05 | global batch size: 256 | lm loss: 3.054727E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.273 | TFLOPs: 43.12 | +7: iteration 4680/ 7508 | consumed samples: 1198080 | consumed tokens: 2453667840 | elapsed time per iteration (s): 0.56 | learning rate: 7.700E-05 | global batch size: 256 | lm loss: 3.063568E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.446 | TFLOPs: 43.33 | +7: iteration 4690/ 7508 | consumed samples: 1200640 | consumed tokens: 2458910720 | elapsed time per iteration (s): 0.55 | learning rate: 7.665E-05 | global batch size: 256 | lm loss: 3.075947E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.688 | TFLOPs: 44.02 | +7: iteration 4700/ 7508 | consumed samples: 1203200 | consumed tokens: 2464153600 | elapsed time per iteration (s): 0.57 | learning rate: 7.629E-05 | global batch size: 256 | lm loss: 3.054345E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.902 | TFLOPs: 42.89 | +7: iteration 4710/ 7508 | consumed samples: 1205760 | consumed tokens: 2469396480 | elapsed time per iteration (s): 0.56 | learning rate: 7.594E-05 | global batch size: 256 | lm loss: 3.062561E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.302 | TFLOPs: 43.22 | +7: iteration 4720/ 7508 | consumed samples: 1208320 | consumed tokens: 2474639360 | elapsed time per iteration (s): 0.55 | learning rate: 7.559E-05 | global batch size: 256 | lm loss: 3.062631E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 462.581 | TFLOPs: 44.10 | +7: iteration 4730/ 7508 | consumed samples: 1210880 | consumed tokens: 2479882240 | elapsed time per iteration (s): 0.55 | learning rate: 7.524E-05 | global batch size: 256 | lm loss: 3.084381E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.964 | TFLOPs: 44.04 | +7: iteration 4740/ 7508 | consumed samples: 1213440 | consumed tokens: 2485125120 | elapsed time per iteration (s): 0.57 | learning rate: 7.489E-05 | global batch size: 256 | lm loss: 3.056094E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.580 | TFLOPs: 42.96 | +7: iteration 4750/ 7508 | consumed samples: 1216000 | consumed tokens: 2490368000 | elapsed time per iteration (s): 0.57 | learning rate: 7.454E-05 | global batch size: 256 | lm loss: 3.050927E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.002 | TFLOPs: 42.71 | +7: iteration 4760/ 7508 | consumed samples: 1218560 | consumed tokens: 2495610880 | elapsed time per iteration (s): 0.57 | learning rate: 7.419E-05 | global batch size: 256 | lm loss: 3.053820E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.908 | TFLOPs: 42.80 | +7: iteration 4770/ 7508 | consumed samples: 1221120 | consumed tokens: 2500853760 | elapsed time per iteration (s): 0.56 | learning rate: 7.384E-05 | global batch size: 256 | lm loss: 3.047942E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 459.139 | TFLOPs: 43.77 | +7: iteration 4780/ 7508 | consumed samples: 1223680 | consumed tokens: 2506096640 | elapsed time per iteration (s): 0.56 | learning rate: 7.349E-05 | global batch size: 256 | lm loss: 3.061385E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.150 | TFLOPs: 43.68 | +7: iteration 4790/ 7508 | consumed samples: 1226240 | consumed tokens: 2511339520 | elapsed time per iteration (s): 0.57 | learning rate: 7.315E-05 | global batch size: 256 | lm loss: 3.060983E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.610 | TFLOPs: 43.15 | +7: iteration 4800/ 7508 | consumed samples: 1228800 | consumed tokens: 2516582400 | elapsed time per iteration (s): 0.56 | learning rate: 7.280E-05 | global batch size: 256 | lm loss: 3.017683E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.738 | TFLOPs: 43.64 | +7: iteration 4810/ 7508 | consumed samples: 1231360 | consumed tokens: 2521825280 | elapsed time per iteration (s): 0.56 | learning rate: 7.245E-05 | global batch size: 256 | lm loss: 3.044481E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.488 | TFLOPs: 43.33 | +7: iteration 4820/ 7508 | consumed samples: 1233920 | consumed tokens: 2527068160 | elapsed time per iteration (s): 0.56 | learning rate: 7.211E-05 | global batch size: 256 | lm loss: 3.072107E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.991 | TFLOPs: 43.38 | +7: iteration 4830/ 7508 | consumed samples: 1236480 | consumed tokens: 2532311040 | elapsed time per iteration (s): 0.57 | learning rate: 7.176E-05 | global batch size: 256 | lm loss: 3.032426E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.559 | TFLOPs: 42.96 | +7: iteration 4840/ 7508 | consumed samples: 1239040 | consumed tokens: 2537553920 | elapsed time per iteration (s): 0.57 | learning rate: 7.142E-05 | global batch size: 256 | lm loss: 3.063377E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.835 | TFLOPs: 42.51 | +7: iteration 4850/ 7508 | consumed samples: 1241600 | consumed tokens: 2542796800 | elapsed time per iteration (s): 0.57 | learning rate: 7.108E-05 | global batch size: 256 | lm loss: 3.057552E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.252 | TFLOPs: 42.74 | +7: iteration 4860/ 7508 | consumed samples: 1244160 | consumed tokens: 2548039680 | elapsed time per iteration (s): 0.56 | learning rate: 7.073E-05 | global batch size: 256 | lm loss: 3.030808E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.820 | TFLOPs: 43.55 | +7: iteration 4870/ 7508 | consumed samples: 1246720 | consumed tokens: 2553282560 | elapsed time per iteration (s): 0.56 | learning rate: 7.039E-05 | global batch size: 256 | lm loss: 3.037318E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.549 | TFLOPs: 43.34 | +7: iteration 4880/ 7508 | consumed samples: 1249280 | consumed tokens: 2558525440 | elapsed time per iteration (s): 0.57 | learning rate: 7.005E-05 | global batch size: 256 | lm loss: 3.049381E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.022 | TFLOPs: 43.19 | +7: iteration 4890/ 7508 | consumed samples: 1251840 | consumed tokens: 2563768320 | elapsed time per iteration (s): 0.57 | learning rate: 6.971E-05 | global batch size: 256 | lm loss: 3.044379E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.897 | TFLOPs: 43.08 | +7: iteration 4900/ 7508 | consumed samples: 1254400 | consumed tokens: 2569011200 | elapsed time per iteration (s): 0.57 | learning rate: 6.937E-05 | global batch size: 256 | lm loss: 3.037666E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.717 | TFLOPs: 43.07 | +7: iteration 4910/ 7508 | consumed samples: 1256960 | consumed tokens: 2574254080 | elapsed time per iteration (s): 0.57 | learning rate: 6.903E-05 | global batch size: 256 | lm loss: 3.037605E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.752 | TFLOPs: 43.07 | +7: iteration 4920/ 7508 | consumed samples: 1259520 | consumed tokens: 2579496960 | elapsed time per iteration (s): 0.56 | learning rate: 6.869E-05 | global batch size: 256 | lm loss: 3.060104E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.981 | TFLOPs: 43.38 | +7: iteration 4930/ 7508 | consumed samples: 1262080 | consumed tokens: 2584739840 | elapsed time per iteration (s): 0.57 | learning rate: 6.835E-05 | global batch size: 256 | lm loss: 3.019411E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.752 | TFLOPs: 42.69 | +7: iteration 4940/ 7508 | consumed samples: 1264640 | consumed tokens: 2589982720 | elapsed time per iteration (s): 0.56 | learning rate: 6.802E-05 | global batch size: 256 | lm loss: 3.068993E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.692 | TFLOPs: 43.64 | +7: iteration 4950/ 7508 | consumed samples: 1267200 | consumed tokens: 2595225600 | elapsed time per iteration (s): 0.56 | learning rate: 6.768E-05 | global batch size: 256 | lm loss: 3.034330E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.743 | TFLOPs: 43.45 | +7: iteration 4960/ 7508 | consumed samples: 1269760 | consumed tokens: 2600468480 | elapsed time per iteration (s): 0.58 | learning rate: 6.735E-05 | global batch size: 256 | lm loss: 3.070744E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.663 | TFLOPs: 42.30 | +7: iteration 4970/ 7508 | consumed samples: 1272320 | consumed tokens: 2605711360 | elapsed time per iteration (s): 0.57 | learning rate: 6.701E-05 | global batch size: 256 | lm loss: 3.058860E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.221 | TFLOPs: 43.11 | +7: iteration 4980/ 7508 | consumed samples: 1274880 | consumed tokens: 2610954240 | elapsed time per iteration (s): 0.56 | learning rate: 6.668E-05 | global batch size: 256 | lm loss: 3.029410E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.017 | TFLOPs: 43.95 | +7: iteration 4990/ 7508 | consumed samples: 1277440 | consumed tokens: 2616197120 | elapsed time per iteration (s): 0.58 | learning rate: 6.634E-05 | global batch size: 256 | lm loss: 3.046268E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.740 | TFLOPs: 42.02 | +7: iteration 5000/ 7508 | consumed samples: 1280000 | consumed tokens: 2621440000 | elapsed time per iteration (s): 0.56 | learning rate: 6.601E-05 | global batch size: 256 | lm loss: 3.033295E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.234 | TFLOPs: 43.21 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 5000 | lm loss value: 3.010551E+00 | lm loss PPL: 2.029859E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 5000 to checkpoints_421moscar +0: [2022-11-29 17:42:54,713] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step5000 is begin to save! +0: [2022-11-29 17:42:54,717] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:42:54,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:42:54,861] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:42:54,901] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:42:54,902] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:42:54,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:42:54,945] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:42:54,983] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:42:54,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:42:55,023] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:42:55,023] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:42:55,062] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:42:55,063] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:42:55,102] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:42:55,103] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:42:55,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:42:55,142] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:42:55,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:42:55,185] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:42:55,222] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:42:55,223] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:42:55,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:42:55,264] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:42:55,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:42:55,304] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:42:55,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:42:55,344] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:42:55,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:42:55,384] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:42:55,427] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:42:55,428] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:42:55,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:42:55,465] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/layer_18-model_00-model_states.pt... +0: [2022-11-29 17:42:55,504] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/layer_18-model_00-model_states.pt. +0: [2022-11-29 17:42:55,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:42:55,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:42:55,543] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/layer_20-model_00-model_states.pt... +0: [2022-11-29 17:42:55,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/layer_20-model_00-model_states.pt. +0: [2022-11-29 17:42:55,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/layer_22-model_00-model_states.pt... +0: [2022-11-29 17:42:55,587] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/layer_22-model_00-model_states.pt. +0: [2022-11-29 17:42:55,588] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_421moscar/global_step5000/mp_rank_00_model_states.pt +0: [2022-11-29 17:42:55,588] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:42:55,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:42:55,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:42:55,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:42:55,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:42:55,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +4: [2022-11-29 17:42:55,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +2: [2022-11-29 17:42:55,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:42:55,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:42:55,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:42:55,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:42:55,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:42:55,702] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:42:55,702] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:42:55,702] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:42:55,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:42:55,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:42:55,705] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:42:55,705] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:42:55,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:42:55,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:42:55,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:42:55,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:42:55,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:42:55,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:42:55,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:42:55,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:42:55,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:42:55,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:42:55,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:42:55,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:42:55,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:42:55,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:42:55,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:42:55,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:42:55,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:42:55,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:42:55,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:42:55,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:42:55,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:42:55,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:42:55,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +2: [2022-11-29 17:42:55,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:42:55,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:42:55,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:42:55,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:42:55,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:42:55,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:42:55,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:42:55,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:42:55,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:42:55,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:42:55,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:42:55,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:42:55,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:42:55,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:42:55,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:42:55,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:42:55,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:42:55,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:42:55,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:42:55,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:42:55,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:42:55,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:42:55,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:42:55,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:42:55,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:42:55,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:42:55,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:42:55,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:42:55,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:42:55,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:42:55,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:42:55,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:42:55,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:42:55,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:42:55,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:42:55,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:42:55,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:42:55,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:42:55,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:42:55,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:42:55,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:42:55,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:42:55,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:42:55,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:42:55,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:42:55,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:42:55,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:42:55,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:42:55,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:42:55,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:42:55,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:42:55,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:42:55,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:42:55,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:42:55,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:42:55,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:42:55,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:42:55,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:42:55,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:42:55,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:42:55,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:42:55,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:42:55,727] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:42:55,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:42:55,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:42:55,727] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:42:55,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:42:55,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:42:55,728] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:42:55,728] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:42:55,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:42:55,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:42:55,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:42:55,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:42:55,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:42:55,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:42:55,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:42:55,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:42:55,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:42:55,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:42:55,735] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:42:55,735] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:42:55,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:42:55,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:42:55,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:42:55,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:42:55,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:42:55,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:42:55,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:42:55,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:42:55,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:42:55,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:42:55,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:42:55,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:42:55,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:42:55,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:42:55,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:42:55,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:42:55,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:42:55,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:42:55,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:42:55,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:42:55,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:42:55,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:42:55,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:42:55,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:42:55,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:42:55,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:42:55,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:42:55,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:42:55,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:42:55,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +5: [2022-11-29 17:42:55,702] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:42:55,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:42:55,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:42:55,702] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +3: [2022-11-29 17:42:55,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:42:55,702] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:42:55,725] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:42:55,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:42:55,725] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +5: [2022-11-29 17:42:55,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +3: [2022-11-29 17:42:55,725] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:42:55,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:42:55,725] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:42:55,725] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:42:55,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:42:55,725] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:42:55,725] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +5: [2022-11-29 17:42:55,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +3: [2022-11-29 17:42:55,725] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:42:55,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:42:55,725] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:42:55,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:42:55,731] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:42:55,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +3: [2022-11-29 17:42:55,731] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +5: [2022-11-29 17:42:55,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:42:55,731] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:42:55,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:42:55,731] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:42:55,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +3: [2022-11-29 17:42:55,731] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +5: [2022-11-29 17:42:55,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:42:55,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:42:55,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:42:55,728] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:42:55,728] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:42:55,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:42:55,728] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:42:55,728] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:42:55,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:42:55,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: successfully saved checkpoint at iteration 5000 to checkpoints_421moscar +7: time (ms) | save-checkpoint: 1095.31 +7: iteration 5010/ 7508 | consumed samples: 1282560 | consumed tokens: 2626682880 | elapsed time per iteration (s): 0.71 | learning rate: 6.568E-05 | global batch size: 256 | lm loss: 3.041396E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 360.642 | TFLOPs: 34.38 | +7: iteration 5020/ 7508 | consumed samples: 1285120 | consumed tokens: 2631925760 | elapsed time per iteration (s): 0.57 | learning rate: 6.535E-05 | global batch size: 256 | lm loss: 3.046171E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.812 | TFLOPs: 42.69 | +7: iteration 5030/ 7508 | consumed samples: 1287680 | consumed tokens: 2637168640 | elapsed time per iteration (s): 0.56 | learning rate: 6.502E-05 | global batch size: 256 | lm loss: 3.015382E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.424 | TFLOPs: 43.71 | +7: iteration 5040/ 7508 | consumed samples: 1290240 | consumed tokens: 2642411520 | elapsed time per iteration (s): 0.57 | learning rate: 6.469E-05 | global batch size: 256 | lm loss: 3.056819E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.065 | TFLOPs: 43.10 | +7: iteration 5050/ 7508 | consumed samples: 1292800 | consumed tokens: 2647654400 | elapsed time per iteration (s): 0.57 | learning rate: 6.436E-05 | global batch size: 256 | lm loss: 3.034401E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.825 | TFLOPs: 43.17 | +7: iteration 5060/ 7508 | consumed samples: 1295360 | consumed tokens: 2652897280 | elapsed time per iteration (s): 0.55 | learning rate: 6.404E-05 | global batch size: 256 | lm loss: 3.038684E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.868 | TFLOPs: 44.03 | +7: iteration 5070/ 7508 | consumed samples: 1297920 | consumed tokens: 2658140160 | elapsed time per iteration (s): 0.57 | learning rate: 6.371E-05 | global batch size: 256 | lm loss: 3.037035E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.105 | TFLOPs: 42.91 | +7: iteration 5080/ 7508 | consumed samples: 1300480 | consumed tokens: 2663383040 | elapsed time per iteration (s): 0.56 | learning rate: 6.338E-05 | global batch size: 256 | lm loss: 3.054399E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 459.182 | TFLOPs: 43.78 | +7: iteration 5090/ 7508 | consumed samples: 1303040 | consumed tokens: 2668625920 | elapsed time per iteration (s): 0.56 | learning rate: 6.306E-05 | global batch size: 256 | lm loss: 3.057043E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.012 | TFLOPs: 43.48 | +7: iteration 5100/ 7508 | consumed samples: 1305600 | consumed tokens: 2673868800 | elapsed time per iteration (s): 0.57 | learning rate: 6.273E-05 | global batch size: 256 | lm loss: 3.061097E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.416 | TFLOPs: 42.94 | +7: iteration 5110/ 7508 | consumed samples: 1308160 | consumed tokens: 2679111680 | elapsed time per iteration (s): 0.57 | learning rate: 6.241E-05 | global batch size: 256 | lm loss: 3.051705E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.356 | TFLOPs: 42.75 | +7: iteration 5120/ 7508 | consumed samples: 1310720 | consumed tokens: 2684354560 | elapsed time per iteration (s): 0.56 | learning rate: 6.209E-05 | global batch size: 256 | lm loss: 3.025942E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.238 | TFLOPs: 43.59 | +7: iteration 5130/ 7508 | consumed samples: 1313280 | consumed tokens: 2689597440 | elapsed time per iteration (s): 0.57 | learning rate: 6.177E-05 | global batch size: 256 | lm loss: 3.050431E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.576 | TFLOPs: 42.67 | +7: iteration 5140/ 7508 | consumed samples: 1315840 | consumed tokens: 2694840320 | elapsed time per iteration (s): 0.57 | learning rate: 6.145E-05 | global batch size: 256 | lm loss: 3.051023E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.813 | TFLOPs: 42.88 | +7: iteration 5150/ 7508 | consumed samples: 1318400 | consumed tokens: 2700083200 | elapsed time per iteration (s): 0.57 | learning rate: 6.113E-05 | global batch size: 256 | lm loss: 3.046274E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.605 | TFLOPs: 42.86 | +7: iteration 5160/ 7508 | consumed samples: 1320960 | consumed tokens: 2705326080 | elapsed time per iteration (s): 0.56 | learning rate: 6.081E-05 | global batch size: 256 | lm loss: 3.040669E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.330 | TFLOPs: 43.41 | +7: iteration 5170/ 7508 | consumed samples: 1323520 | consumed tokens: 2710568960 | elapsed time per iteration (s): 0.56 | learning rate: 6.049E-05 | global batch size: 256 | lm loss: 3.053841E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.482 | TFLOPs: 43.62 | +7: iteration 5180/ 7508 | consumed samples: 1326080 | consumed tokens: 2715811840 | elapsed time per iteration (s): 0.58 | learning rate: 6.017E-05 | global batch size: 256 | lm loss: 3.032410E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.109 | TFLOPs: 41.86 | +7: iteration 5190/ 7508 | consumed samples: 1328640 | consumed tokens: 2721054720 | elapsed time per iteration (s): 0.57 | learning rate: 5.986E-05 | global batch size: 256 | lm loss: 3.034900E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.220 | TFLOPs: 42.54 | +7: iteration 5200/ 7508 | consumed samples: 1331200 | consumed tokens: 2726297600 | elapsed time per iteration (s): 0.56 | learning rate: 5.954E-05 | global batch size: 256 | lm loss: 3.040169E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.929 | TFLOPs: 43.75 | +7: iteration 5210/ 7508 | consumed samples: 1333760 | consumed tokens: 2731540480 | elapsed time per iteration (s): 0.56 | learning rate: 5.923E-05 | global batch size: 256 | lm loss: 3.031647E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.925 | TFLOPs: 43.94 | +7: iteration 5220/ 7508 | consumed samples: 1336320 | consumed tokens: 2736783360 | elapsed time per iteration (s): 0.58 | learning rate: 5.891E-05 | global batch size: 256 | lm loss: 3.030108E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.627 | TFLOPs: 42.39 | +7: iteration 5230/ 7508 | consumed samples: 1338880 | consumed tokens: 2742026240 | elapsed time per iteration (s): 0.56 | learning rate: 5.860E-05 | global batch size: 256 | lm loss: 2.995861E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.283 | TFLOPs: 43.22 | +7: iteration 5240/ 7508 | consumed samples: 1341440 | consumed tokens: 2747269120 | elapsed time per iteration (s): 0.56 | learning rate: 5.829E-05 | global batch size: 256 | lm loss: 3.010943E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.959 | TFLOPs: 43.38 | +7: iteration 5250/ 7508 | consumed samples: 1344000 | consumed tokens: 2752512000 | elapsed time per iteration (s): 0.58 | learning rate: 5.798E-05 | global batch size: 256 | lm loss: 3.034743E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.499 | TFLOPs: 42.00 | +7: iteration 5260/ 7508 | consumed samples: 1346560 | consumed tokens: 2757754880 | elapsed time per iteration (s): 0.57 | learning rate: 5.767E-05 | global batch size: 256 | lm loss: 3.017117E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.514 | TFLOPs: 42.57 | +7: iteration 5270/ 7508 | consumed samples: 1349120 | consumed tokens: 2762997760 | elapsed time per iteration (s): 0.56 | learning rate: 5.736E-05 | global batch size: 256 | lm loss: 3.018555E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.133 | TFLOPs: 43.20 | +7: iteration 5280/ 7508 | consumed samples: 1351680 | consumed tokens: 2768240640 | elapsed time per iteration (s): 0.56 | learning rate: 5.705E-05 | global batch size: 256 | lm loss: 3.011363E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.302 | TFLOPs: 43.22 | +7: iteration 5290/ 7508 | consumed samples: 1354240 | consumed tokens: 2773483520 | elapsed time per iteration (s): 0.56 | learning rate: 5.674E-05 | global batch size: 256 | lm loss: 3.039140E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.643 | TFLOPs: 43.54 | +7: iteration 5300/ 7508 | consumed samples: 1356800 | consumed tokens: 2778726400 | elapsed time per iteration (s): 0.57 | learning rate: 5.644E-05 | global batch size: 256 | lm loss: 3.017864E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.160 | TFLOPs: 43.11 | +7: iteration 5310/ 7508 | consumed samples: 1359360 | consumed tokens: 2783969280 | elapsed time per iteration (s): 0.56 | learning rate: 5.613E-05 | global batch size: 256 | lm loss: 2.996675E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.629 | TFLOPs: 43.63 | +7: iteration 5320/ 7508 | consumed samples: 1361920 | consumed tokens: 2789212160 | elapsed time per iteration (s): 0.57 | learning rate: 5.583E-05 | global batch size: 256 | lm loss: 3.052552E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.448 | TFLOPs: 43.14 | +7: iteration 5330/ 7508 | consumed samples: 1364480 | consumed tokens: 2794455040 | elapsed time per iteration (s): 0.58 | learning rate: 5.552E-05 | global batch size: 256 | lm loss: 3.018910E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.406 | TFLOPs: 41.99 | +7: iteration 5340/ 7508 | consumed samples: 1367040 | consumed tokens: 2799697920 | elapsed time per iteration (s): 0.56 | learning rate: 5.522E-05 | global batch size: 256 | lm loss: 3.020988E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.043 | TFLOPs: 43.38 | +7: iteration 5350/ 7508 | consumed samples: 1369600 | consumed tokens: 2804940800 | elapsed time per iteration (s): 0.56 | learning rate: 5.492E-05 | global batch size: 256 | lm loss: 3.030653E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.559 | TFLOPs: 43.43 | +7: iteration 5360/ 7508 | consumed samples: 1372160 | consumed tokens: 2810183680 | elapsed time per iteration (s): 0.59 | learning rate: 5.462E-05 | global batch size: 256 | lm loss: 3.001297E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.147 | TFLOPs: 41.39 | +7: iteration 5370/ 7508 | consumed samples: 1374720 | consumed tokens: 2815426560 | elapsed time per iteration (s): 0.56 | learning rate: 5.432E-05 | global batch size: 256 | lm loss: 3.014642E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.271 | TFLOPs: 43.60 | +7: iteration 5380/ 7508 | consumed samples: 1377280 | consumed tokens: 2820669440 | elapsed time per iteration (s): 0.57 | learning rate: 5.402E-05 | global batch size: 256 | lm loss: 3.039616E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.249 | TFLOPs: 43.12 | +7: iteration 5390/ 7508 | consumed samples: 1379840 | consumed tokens: 2825912320 | elapsed time per iteration (s): 0.56 | learning rate: 5.373E-05 | global batch size: 256 | lm loss: 3.018637E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.367 | TFLOPs: 43.32 | +7: iteration 5400/ 7508 | consumed samples: 1382400 | consumed tokens: 2831155200 | elapsed time per iteration (s): 0.56 | learning rate: 5.343E-05 | global batch size: 256 | lm loss: 2.979512E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.302 | TFLOPs: 43.41 | +7: iteration 5410/ 7508 | consumed samples: 1384960 | consumed tokens: 2836398080 | elapsed time per iteration (s): 0.57 | learning rate: 5.313E-05 | global batch size: 256 | lm loss: 3.019490E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.116 | TFLOPs: 42.82 | +7: iteration 5420/ 7508 | consumed samples: 1387520 | consumed tokens: 2841640960 | elapsed time per iteration (s): 0.57 | learning rate: 5.284E-05 | global batch size: 256 | lm loss: 3.052625E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.835 | TFLOPs: 42.60 | +7: iteration 5430/ 7508 | consumed samples: 1390080 | consumed tokens: 2846883840 | elapsed time per iteration (s): 0.57 | learning rate: 5.255E-05 | global batch size: 256 | lm loss: 3.024893E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.183 | TFLOPs: 43.11 | +7: iteration 5440/ 7508 | consumed samples: 1392640 | consumed tokens: 2852126720 | elapsed time per iteration (s): 0.57 | learning rate: 5.225E-05 | global batch size: 256 | lm loss: 3.032243E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.686 | TFLOPs: 42.87 | +7: iteration 5450/ 7508 | consumed samples: 1395200 | consumed tokens: 2857369600 | elapsed time per iteration (s): 0.57 | learning rate: 5.196E-05 | global batch size: 256 | lm loss: 2.989022E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.313 | TFLOPs: 42.84 | +7: iteration 5460/ 7508 | consumed samples: 1397760 | consumed tokens: 2862612480 | elapsed time per iteration (s): 0.57 | learning rate: 5.167E-05 | global batch size: 256 | lm loss: 3.014968E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.442 | TFLOPs: 42.47 | +7: iteration 5470/ 7508 | consumed samples: 1400320 | consumed tokens: 2867855360 | elapsed time per iteration (s): 0.57 | learning rate: 5.138E-05 | global batch size: 256 | lm loss: 3.014103E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.297 | TFLOPs: 43.03 | +7: iteration 5480/ 7508 | consumed samples: 1402880 | consumed tokens: 2873098240 | elapsed time per iteration (s): 0.58 | learning rate: 5.109E-05 | global batch size: 256 | lm loss: 3.029781E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.696 | TFLOPs: 41.82 | +7: iteration 5490/ 7508 | consumed samples: 1405440 | consumed tokens: 2878341120 | elapsed time per iteration (s): 0.57 | learning rate: 5.081E-05 | global batch size: 256 | lm loss: 3.010789E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.461 | TFLOPs: 42.95 | +7: iteration 5500/ 7508 | consumed samples: 1408000 | consumed tokens: 2883584000 | elapsed time per iteration (s): 0.56 | learning rate: 5.052E-05 | global batch size: 256 | lm loss: 3.041424E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.304 | TFLOPs: 43.50 | +7: iteration 5510/ 7508 | consumed samples: 1410560 | consumed tokens: 2888826880 | elapsed time per iteration (s): 0.56 | learning rate: 5.024E-05 | global batch size: 256 | lm loss: 2.989238E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.889 | TFLOPs: 43.65 | +7: iteration 5520/ 7508 | consumed samples: 1413120 | consumed tokens: 2894069760 | elapsed time per iteration (s): 0.57 | learning rate: 4.995E-05 | global batch size: 256 | lm loss: 2.992597E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.573 | TFLOPs: 42.67 | +7: iteration 5530/ 7508 | consumed samples: 1415680 | consumed tokens: 2899312640 | elapsed time per iteration (s): 0.57 | learning rate: 4.967E-05 | global batch size: 256 | lm loss: 2.993801E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.399 | TFLOPs: 42.65 | +7: iteration 5540/ 7508 | consumed samples: 1418240 | consumed tokens: 2904555520 | elapsed time per iteration (s): 0.56 | learning rate: 4.939E-05 | global batch size: 256 | lm loss: 3.021950E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 459.205 | TFLOPs: 43.78 | +7: iteration 5550/ 7508 | consumed samples: 1420800 | consumed tokens: 2909798400 | elapsed time per iteration (s): 0.56 | learning rate: 4.911E-05 | global batch size: 256 | lm loss: 3.010030E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.417 | TFLOPs: 43.23 | +7: iteration 5560/ 7508 | consumed samples: 1423360 | consumed tokens: 2915041280 | elapsed time per iteration (s): 0.56 | learning rate: 4.883E-05 | global batch size: 256 | lm loss: 2.998322E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.992 | TFLOPs: 43.57 | +7: iteration 5570/ 7508 | consumed samples: 1425920 | consumed tokens: 2920284160 | elapsed time per iteration (s): 0.56 | learning rate: 4.855E-05 | global batch size: 256 | lm loss: 3.001571E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.288 | TFLOPs: 43.31 | +7: iteration 5580/ 7508 | consumed samples: 1428480 | consumed tokens: 2925527040 | elapsed time per iteration (s): 0.56 | learning rate: 4.827E-05 | global batch size: 256 | lm loss: 3.017180E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.161 | TFLOPs: 43.87 | +7: iteration 5590/ 7508 | consumed samples: 1431040 | consumed tokens: 2930769920 | elapsed time per iteration (s): 0.55 | learning rate: 4.800E-05 | global batch size: 256 | lm loss: 2.973859E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.441 | TFLOPs: 43.99 | +7: iteration 5600/ 7508 | consumed samples: 1433600 | consumed tokens: 2936012800 | elapsed time per iteration (s): 1.87 | learning rate: 4.772E-05 | global batch size: 256 | lm loss: 3.007170E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 137.228 | TFLOPs: 13.08 | +7: iteration 5610/ 7508 | consumed samples: 1436160 | consumed tokens: 2941255680 | elapsed time per iteration (s): 0.56 | learning rate: 4.745E-05 | global batch size: 256 | lm loss: 2.997447E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.669 | TFLOPs: 43.92 | +7: iteration 5620/ 7508 | consumed samples: 1438720 | consumed tokens: 2946498560 | elapsed time per iteration (s): 0.55 | learning rate: 4.717E-05 | global batch size: 256 | lm loss: 3.004913E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.431 | TFLOPs: 43.99 | +7: iteration 5630/ 7508 | consumed samples: 1441280 | consumed tokens: 2951741440 | elapsed time per iteration (s): 0.57 | learning rate: 4.690E-05 | global batch size: 256 | lm loss: 2.996018E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.871 | TFLOPs: 42.79 | +7: iteration 5640/ 7508 | consumed samples: 1443840 | consumed tokens: 2956984320 | elapsed time per iteration (s): 0.56 | learning rate: 4.663E-05 | global batch size: 256 | lm loss: 3.008030E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.245 | TFLOPs: 43.97 | +7: iteration 5650/ 7508 | consumed samples: 1446400 | consumed tokens: 2962227200 | elapsed time per iteration (s): 0.58 | learning rate: 4.636E-05 | global batch size: 256 | lm loss: 3.029536E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.132 | TFLOPs: 41.87 | +7: iteration 5660/ 7508 | consumed samples: 1448960 | consumed tokens: 2967470080 | elapsed time per iteration (s): 0.57 | learning rate: 4.609E-05 | global batch size: 256 | lm loss: 3.026993E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.070 | TFLOPs: 42.81 | +7: iteration 5670/ 7508 | consumed samples: 1451520 | consumed tokens: 2972712960 | elapsed time per iteration (s): 0.55 | learning rate: 4.583E-05 | global batch size: 256 | lm loss: 2.997848E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.383 | TFLOPs: 43.99 | +7: iteration 5680/ 7508 | consumed samples: 1454080 | consumed tokens: 2977955840 | elapsed time per iteration (s): 0.57 | learning rate: 4.556E-05 | global batch size: 256 | lm loss: 3.007464E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.989 | TFLOPs: 43.19 | +7: iteration 5690/ 7508 | consumed samples: 1456640 | consumed tokens: 2983198720 | elapsed time per iteration (s): 0.55 | learning rate: 4.530E-05 | global batch size: 256 | lm loss: 2.988613E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.973 | TFLOPs: 44.04 | +7: iteration 5700/ 7508 | consumed samples: 1459200 | consumed tokens: 2988441600 | elapsed time per iteration (s): 0.56 | learning rate: 4.503E-05 | global batch size: 256 | lm loss: 3.012907E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 459.815 | TFLOPs: 43.84 | +7: iteration 5710/ 7508 | consumed samples: 1461760 | consumed tokens: 2993684480 | elapsed time per iteration (s): 0.56 | learning rate: 4.477E-05 | global batch size: 256 | lm loss: 3.010942E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.655 | TFLOPs: 43.54 | +7: iteration 5720/ 7508 | consumed samples: 1464320 | consumed tokens: 2998927360 | elapsed time per iteration (s): 0.56 | learning rate: 4.451E-05 | global batch size: 256 | lm loss: 2.989182E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.175 | TFLOPs: 43.59 | +7: iteration 5730/ 7508 | consumed samples: 1466880 | consumed tokens: 3004170240 | elapsed time per iteration (s): 0.56 | learning rate: 4.425E-05 | global batch size: 256 | lm loss: 2.979213E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.744 | TFLOPs: 43.74 | +7: iteration 5740/ 7508 | consumed samples: 1469440 | consumed tokens: 3009413120 | elapsed time per iteration (s): 0.56 | learning rate: 4.399E-05 | global batch size: 256 | lm loss: 3.008508E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.728 | TFLOPs: 43.93 | +7: iteration 5750/ 7508 | consumed samples: 1472000 | consumed tokens: 3014656000 | elapsed time per iteration (s): 0.56 | learning rate: 4.373E-05 | global batch size: 256 | lm loss: 2.997910E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.374 | TFLOPs: 43.89 | +7: iteration 5760/ 7508 | consumed samples: 1474560 | consumed tokens: 3019898880 | elapsed time per iteration (s): 0.55 | learning rate: 4.347E-05 | global batch size: 256 | lm loss: 2.977054E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.794 | TFLOPs: 44.03 | +7: iteration 5770/ 7508 | consumed samples: 1477120 | consumed tokens: 3025141760 | elapsed time per iteration (s): 0.55 | learning rate: 4.322E-05 | global batch size: 256 | lm loss: 3.010169E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 462.430 | TFLOPs: 44.09 | +7: iteration 5780/ 7508 | consumed samples: 1479680 | consumed tokens: 3030384640 | elapsed time per iteration (s): 0.55 | learning rate: 4.296E-05 | global batch size: 256 | lm loss: 2.992875E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.908 | TFLOPs: 44.04 | +7: iteration 5790/ 7508 | consumed samples: 1482240 | consumed tokens: 3035627520 | elapsed time per iteration (s): 0.58 | learning rate: 4.271E-05 | global batch size: 256 | lm loss: 3.020855E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.630 | TFLOPs: 42.20 | +7: iteration 5800/ 7508 | consumed samples: 1484800 | consumed tokens: 3040870400 | elapsed time per iteration (s): 0.55 | learning rate: 4.246E-05 | global batch size: 256 | lm loss: 2.995771E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.471 | TFLOPs: 44.00 | +7: iteration 5810/ 7508 | consumed samples: 1487360 | consumed tokens: 3046113280 | elapsed time per iteration (s): 0.56 | learning rate: 4.221E-05 | global batch size: 256 | lm loss: 3.015191E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.417 | TFLOPs: 43.90 | +7: iteration 5820/ 7508 | consumed samples: 1489920 | consumed tokens: 3051356160 | elapsed time per iteration (s): 0.56 | learning rate: 4.196E-05 | global batch size: 256 | lm loss: 2.998772E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.414 | TFLOPs: 43.32 | +7: iteration 5830/ 7508 | consumed samples: 1492480 | consumed tokens: 3056599040 | elapsed time per iteration (s): 0.57 | learning rate: 4.171E-05 | global batch size: 256 | lm loss: 2.978312E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.246 | TFLOPs: 43.12 | +7: iteration 5840/ 7508 | consumed samples: 1495040 | consumed tokens: 3061841920 | elapsed time per iteration (s): 0.56 | learning rate: 4.146E-05 | global batch size: 256 | lm loss: 2.992640E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.744 | TFLOPs: 43.45 | +7: iteration 5850/ 7508 | consumed samples: 1497600 | consumed tokens: 3067084800 | elapsed time per iteration (s): 0.57 | learning rate: 4.122E-05 | global batch size: 256 | lm loss: 3.020593E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.539 | TFLOPs: 42.86 | +7: iteration 5860/ 7508 | consumed samples: 1500160 | consumed tokens: 3072327680 | elapsed time per iteration (s): 0.55 | learning rate: 4.097E-05 | global batch size: 256 | lm loss: 2.978775E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.903 | TFLOPs: 44.04 | +7: iteration 5870/ 7508 | consumed samples: 1502720 | consumed tokens: 3077570560 | elapsed time per iteration (s): 0.57 | learning rate: 4.073E-05 | global batch size: 256 | lm loss: 2.999161E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.815 | TFLOPs: 42.60 | +7: iteration 5880/ 7508 | consumed samples: 1505280 | consumed tokens: 3082813440 | elapsed time per iteration (s): 0.56 | learning rate: 4.049E-05 | global batch size: 256 | lm loss: 2.990177E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.818 | TFLOPs: 43.55 | +7: iteration 5890/ 7508 | consumed samples: 1507840 | consumed tokens: 3088056320 | elapsed time per iteration (s): 0.56 | learning rate: 4.025E-05 | global batch size: 256 | lm loss: 2.971812E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.654 | TFLOPs: 43.63 | +7: iteration 5900/ 7508 | consumed samples: 1510400 | consumed tokens: 3093299200 | elapsed time per iteration (s): 0.56 | learning rate: 4.001E-05 | global batch size: 256 | lm loss: 2.964516E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.212 | TFLOPs: 43.40 | +7: iteration 5910/ 7508 | consumed samples: 1512960 | consumed tokens: 3098542080 | elapsed time per iteration (s): 0.56 | learning rate: 3.977E-05 | global batch size: 256 | lm loss: 3.012907E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.852 | TFLOPs: 43.56 | +7: iteration 5920/ 7508 | consumed samples: 1515520 | consumed tokens: 3103784960 | elapsed time per iteration (s): 0.58 | learning rate: 3.953E-05 | global batch size: 256 | lm loss: 2.991883E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.664 | TFLOPs: 42.20 | +7: iteration 5930/ 7508 | consumed samples: 1518080 | consumed tokens: 3109027840 | elapsed time per iteration (s): 0.57 | learning rate: 3.929E-05 | global batch size: 256 | lm loss: 3.008112E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.995 | TFLOPs: 42.81 | +7: iteration 5940/ 7508 | consumed samples: 1520640 | consumed tokens: 3114270720 | elapsed time per iteration (s): 0.57 | learning rate: 3.906E-05 | global batch size: 256 | lm loss: 3.004879E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.573 | TFLOPs: 42.67 | +7: iteration 5950/ 7508 | consumed samples: 1523200 | consumed tokens: 3119513600 | elapsed time per iteration (s): 0.57 | learning rate: 3.883E-05 | global batch size: 256 | lm loss: 3.002111E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.899 | TFLOPs: 43.08 | +7: iteration 5960/ 7508 | consumed samples: 1525760 | consumed tokens: 3124756480 | elapsed time per iteration (s): 0.55 | learning rate: 3.859E-05 | global batch size: 256 | lm loss: 3.001822E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.700 | TFLOPs: 44.02 | +7: iteration 5970/ 7508 | consumed samples: 1528320 | consumed tokens: 3129999360 | elapsed time per iteration (s): 0.58 | learning rate: 3.836E-05 | global batch size: 256 | lm loss: 2.996395E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.477 | TFLOPs: 41.99 | +7: iteration 5980/ 7508 | consumed samples: 1530880 | consumed tokens: 3135242240 | elapsed time per iteration (s): 0.55 | learning rate: 3.813E-05 | global batch size: 256 | lm loss: 2.979263E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.505 | TFLOPs: 44.00 | +7: iteration 5990/ 7508 | consumed samples: 1533440 | consumed tokens: 3140485120 | elapsed time per iteration (s): 0.58 | learning rate: 3.790E-05 | global batch size: 256 | lm loss: 3.013696E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.194 | TFLOPs: 42.06 | +0: [2022-11-29 17:52:34,022] [INFO] [logging.py:68:log_dist] [Rank 0] step=6000, skipped=0, lr=[3.76774148080129e-05, 3.76774148080129e-05, 3.76774148080129e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 6000/ 7508 | consumed samples: 1536000 | consumed tokens: 3145728000 | elapsed time per iteration (s): 0.57 | learning rate: 3.768E-05 | global batch size: 256 | lm loss: 2.985151E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.086 | TFLOPs: 42.72 | +0: steps: 6000 loss: 2.9404 iter time (s): 0.570 samples/sec: 449.352 +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 6000 | lm loss value: 2.879395E+00 | lm loss PPL: 1.780351E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 6000 to checkpoints_421moscar +0: [2022-11-29 17:52:34,282] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step6000 is begin to save! +0: [2022-11-29 17:52:34,299] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:52:34,443] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:52:34,443] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:52:34,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:52:34,487] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:52:34,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:52:34,530] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:52:34,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:52:34,572] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:52:34,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:52:34,614] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:52:34,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:52:34,656] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:52:34,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:52:34,695] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:52:34,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:52:34,739] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:52:34,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:52:34,776] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:52:34,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:52:34,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:52:34,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:52:34,859] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:52:34,898] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:52:34,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:52:34,938] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:52:34,938] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:52:34,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:52:34,978] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:52:35,017] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:52:35,017] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:52:35,058] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:52:35,058] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/layer_18-model_00-model_states.pt... +0: [2022-11-29 17:52:35,098] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/layer_18-model_00-model_states.pt. +0: [2022-11-29 17:52:35,099] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:52:35,139] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:52:35,139] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/layer_20-model_00-model_states.pt... +0: [2022-11-29 17:52:35,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/layer_20-model_00-model_states.pt. +0: [2022-11-29 17:52:35,180] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/layer_22-model_00-model_states.pt... +0: [2022-11-29 17:52:35,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/layer_22-model_00-model_states.pt. +0: [2022-11-29 17:52:35,185] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_421moscar/global_step6000/mp_rank_00_model_states.pt +0: [2022-11-29 17:52:35,185] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:52:35,187] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:52:35,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:52:35,292] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:52:35,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:52:35,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:52:35,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:52:35,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:52:35,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:52:35,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:52:35,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:52:35,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:52:35,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:52:35,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:52:35,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:52:35,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:52:35,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:52:35,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:52:35,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:52:35,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:52:35,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:52:35,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:52:35,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:52:35,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:52:35,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:52:35,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:52:35,305] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:52:35,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:52:35,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:52:35,305] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:52:35,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:52:35,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:52:35,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:52:35,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:52:35,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:52:35,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:52:35,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:52:35,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:52:35,311] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:52:35,311] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:52:35,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:52:35,311] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:52:35,311] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:52:35,314] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:52:35,314] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:52:35,314] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:52:35,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:52:35,317] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:52:35,317] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:52:35,317] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:52:35,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:52:35,318] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:52:35,318] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:52:35,320] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:52:35,320] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:52:35,320] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:52:35,320] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:52:35,320] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:52:35,320] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:52:35,320] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:52:35,321] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:52:35,321] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:52:35,321] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:52:35,321] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +7: [2022-11-29 17:52:35,321] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:52:35,321] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:52:35,321] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:52:35,321] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:52:35,321] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:52:35,321] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:52:35,321] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +7: [2022-11-29 17:52:35,321] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:52:35,321] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:52:35,321] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:52:35,292] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:52:35,292] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:52:35,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:52:35,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:52:35,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:52:35,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:52:35,305] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:52:35,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:52:35,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:52:35,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:52:35,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:52:35,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:52:35,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:52:35,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:52:35,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:52:35,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:52:35,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:52:35,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:52:35,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:52:35,311] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:52:35,324] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:52:35,324] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:52:35,324] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:52:35,324] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:52:35,324] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:52:35,324] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:52:35,324] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:52:35,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:52:35,325] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:52:35,325] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:52:35,325] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:52:35,325] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:52:35,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:52:35,305] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:52:35,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:52:35,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:52:35,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:52:35,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:52:35,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:52:35,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:52:35,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:52:35,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:52:35,312] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:52:35,312] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:52:35,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:52:35,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:52:35,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:52:35,321] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:52:35,322] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:52:35,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:52:35,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:52:35,322] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:52:35,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:52:35,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:52:35,322] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:52:35,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:52:35,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:52:35,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:52:35,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:52:35,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:52:35,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:52:35,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:52:35,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:52:35,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:52:35,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:52:35,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:52:35,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:52:35,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:52:35,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:52:35,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:52:35,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:52:35,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:52:35,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:52:35,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:52:35,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:52:35,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:52:35,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:52:35,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:52:35,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:52:35,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:52:35,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:52:35,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:52:35,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:52:35,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:52:35,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:52:35,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:52:35,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:52:35,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:52:35,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:52:35,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:52:35,353] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:52:35,353] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:52:35,353] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:52:35,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:52:35,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:52:35,364] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:52:35,364] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:52:35,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:52:35,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:52:35,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:52:35,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:52:35,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:52:35,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:52:35,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:52:35,528] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:52:35,528] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:52:35,528] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:52:35,528] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:52:35,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:52:35,528] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:52:35,528] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:52:35,528] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:52:35,528] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:52:35,528] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:52:35,528] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:52:35,528] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:52:35,528] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:52:35,528] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:52:35,528] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:52:35,528] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step6000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:52:35,528] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: successfully saved checkpoint at iteration 6000 to checkpoints_421moscar +7: time (ms) | save-checkpoint: 1300.64 +7: iteration 6010/ 7508 | consumed samples: 1538560 | consumed tokens: 3150970880 | elapsed time per iteration (s): 0.72 | learning rate: 3.745E-05 | global batch size: 256 | lm loss: 3.000943E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 356.035 | TFLOPs: 33.94 | +7: iteration 6020/ 7508 | consumed samples: 1541120 | consumed tokens: 3156213760 | elapsed time per iteration (s): 0.56 | learning rate: 3.723E-05 | global batch size: 256 | lm loss: 3.009396E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.934 | TFLOPs: 43.37 | +7: iteration 6030/ 7508 | consumed samples: 1543680 | consumed tokens: 3161456640 | elapsed time per iteration (s): 0.55 | learning rate: 3.700E-05 | global batch size: 256 | lm loss: 3.019036E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 462.052 | TFLOPs: 44.05 | +7: iteration 6040/ 7508 | consumed samples: 1546240 | consumed tokens: 3166699520 | elapsed time per iteration (s): 0.55 | learning rate: 3.678E-05 | global batch size: 256 | lm loss: 2.966092E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.745 | TFLOPs: 44.02 | +7: iteration 6050/ 7508 | consumed samples: 1548800 | consumed tokens: 3171942400 | elapsed time per iteration (s): 0.57 | learning rate: 3.656E-05 | global batch size: 256 | lm loss: 2.968461E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.355 | TFLOPs: 43.03 | +7: iteration 6060/ 7508 | consumed samples: 1551360 | consumed tokens: 3177185280 | elapsed time per iteration (s): 0.57 | learning rate: 3.634E-05 | global batch size: 256 | lm loss: 2.985555E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.504 | TFLOPs: 42.95 | +7: iteration 6070/ 7508 | consumed samples: 1553920 | consumed tokens: 3182428160 | elapsed time per iteration (s): 0.56 | learning rate: 3.612E-05 | global batch size: 256 | lm loss: 3.013208E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.515 | TFLOPs: 43.91 | +7: iteration 6080/ 7508 | consumed samples: 1556480 | consumed tokens: 3187671040 | elapsed time per iteration (s): 0.56 | learning rate: 3.591E-05 | global batch size: 256 | lm loss: 2.970066E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.031 | TFLOPs: 43.48 | +7: iteration 6090/ 7508 | consumed samples: 1559040 | consumed tokens: 3192913920 | elapsed time per iteration (s): 0.57 | learning rate: 3.569E-05 | global batch size: 256 | lm loss: 3.034248E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.658 | TFLOPs: 43.16 | +7: iteration 6100/ 7508 | consumed samples: 1561600 | consumed tokens: 3198156800 | elapsed time per iteration (s): 0.55 | learning rate: 3.548E-05 | global batch size: 256 | lm loss: 2.991923E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.443 | TFLOPs: 43.99 | +7: iteration 6110/ 7508 | consumed samples: 1564160 | consumed tokens: 3203399680 | elapsed time per iteration (s): 0.56 | learning rate: 3.527E-05 | global batch size: 256 | lm loss: 3.003359E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.330 | TFLOPs: 43.41 | +7: iteration 6120/ 7508 | consumed samples: 1566720 | consumed tokens: 3208642560 | elapsed time per iteration (s): 0.56 | learning rate: 3.505E-05 | global batch size: 256 | lm loss: 2.987024E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.534 | TFLOPs: 43.43 | +7: iteration 6130/ 7508 | consumed samples: 1569280 | consumed tokens: 3213885440 | elapsed time per iteration (s): 0.56 | learning rate: 3.484E-05 | global batch size: 256 | lm loss: 2.982756E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.656 | TFLOPs: 43.44 | +7: iteration 6140/ 7508 | consumed samples: 1571840 | consumed tokens: 3219128320 | elapsed time per iteration (s): 0.56 | learning rate: 3.464E-05 | global batch size: 256 | lm loss: 2.958490E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.534 | TFLOPs: 43.33 | +7: iteration 6150/ 7508 | consumed samples: 1574400 | consumed tokens: 3224371200 | elapsed time per iteration (s): 0.57 | learning rate: 3.443E-05 | global batch size: 256 | lm loss: 2.982700E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.486 | TFLOPs: 43.04 | +7: iteration 6160/ 7508 | consumed samples: 1576960 | consumed tokens: 3229614080 | elapsed time per iteration (s): 0.56 | learning rate: 3.422E-05 | global batch size: 256 | lm loss: 2.989894E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.800 | TFLOPs: 43.93 | +7: iteration 6170/ 7508 | consumed samples: 1579520 | consumed tokens: 3234856960 | elapsed time per iteration (s): 0.56 | learning rate: 3.402E-05 | global batch size: 256 | lm loss: 2.992690E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.085 | TFLOPs: 43.58 | +7: iteration 6180/ 7508 | consumed samples: 1582080 | consumed tokens: 3240099840 | elapsed time per iteration (s): 0.57 | learning rate: 3.382E-05 | global batch size: 256 | lm loss: 2.993463E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.480 | TFLOPs: 43.14 | +7: iteration 6190/ 7508 | consumed samples: 1584640 | consumed tokens: 3245342720 | elapsed time per iteration (s): 0.56 | learning rate: 3.361E-05 | global batch size: 256 | lm loss: 2.969316E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.364 | TFLOPs: 43.89 | +7: iteration 6200/ 7508 | consumed samples: 1587200 | consumed tokens: 3250585600 | elapsed time per iteration (s): 0.55 | learning rate: 3.341E-05 | global batch size: 256 | lm loss: 2.984440E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 462.300 | TFLOPs: 44.08 | +7: iteration 6210/ 7508 | consumed samples: 1589760 | consumed tokens: 3255828480 | elapsed time per iteration (s): 0.56 | learning rate: 3.321E-05 | global batch size: 256 | lm loss: 2.958535E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.592 | TFLOPs: 43.72 | +7: iteration 6220/ 7508 | consumed samples: 1592320 | consumed tokens: 3261071360 | elapsed time per iteration (s): 0.56 | learning rate: 3.302E-05 | global batch size: 256 | lm loss: 2.999872E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.959 | TFLOPs: 43.28 | +7: iteration 6230/ 7508 | consumed samples: 1594880 | consumed tokens: 3266314240 | elapsed time per iteration (s): 0.56 | learning rate: 3.282E-05 | global batch size: 256 | lm loss: 2.978899E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.971 | TFLOPs: 43.28 | +7: iteration 6240/ 7508 | consumed samples: 1597440 | consumed tokens: 3271557120 | elapsed time per iteration (s): 0.56 | learning rate: 3.262E-05 | global batch size: 256 | lm loss: 2.978226E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.699 | TFLOPs: 43.64 | +7: iteration 6250/ 7508 | consumed samples: 1600000 | consumed tokens: 3276800000 | elapsed time per iteration (s): 0.56 | learning rate: 3.243E-05 | global batch size: 256 | lm loss: 2.980676E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.084 | TFLOPs: 43.48 | +7: iteration 6260/ 7508 | consumed samples: 1602560 | consumed tokens: 3282042880 | elapsed time per iteration (s): 0.56 | learning rate: 3.224E-05 | global batch size: 256 | lm loss: 2.993855E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.520 | TFLOPs: 43.71 | +7: iteration 6270/ 7508 | consumed samples: 1605120 | consumed tokens: 3287285760 | elapsed time per iteration (s): 0.56 | learning rate: 3.205E-05 | global batch size: 256 | lm loss: 3.005446E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.181 | TFLOPs: 43.59 | +7: iteration 6280/ 7508 | consumed samples: 1607680 | consumed tokens: 3292528640 | elapsed time per iteration (s): 0.56 | learning rate: 3.186E-05 | global batch size: 256 | lm loss: 2.972415E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 459.079 | TFLOPs: 43.77 | +7: iteration 6290/ 7508 | consumed samples: 1610240 | consumed tokens: 3297771520 | elapsed time per iteration (s): 0.57 | learning rate: 3.167E-05 | global batch size: 256 | lm loss: 2.975639E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.468 | TFLOPs: 42.85 | +7: iteration 6300/ 7508 | consumed samples: 1612800 | consumed tokens: 3303014400 | elapsed time per iteration (s): 0.56 | learning rate: 3.148E-05 | global batch size: 256 | lm loss: 2.989141E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.943 | TFLOPs: 43.66 | +7: iteration 6310/ 7508 | consumed samples: 1615360 | consumed tokens: 3308257280 | elapsed time per iteration (s): 0.56 | learning rate: 3.130E-05 | global batch size: 256 | lm loss: 2.963395E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.983 | TFLOPs: 43.38 | +7: iteration 6320/ 7508 | consumed samples: 1617920 | consumed tokens: 3313500160 | elapsed time per iteration (s): 0.58 | learning rate: 3.112E-05 | global batch size: 256 | lm loss: 2.965170E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.722 | TFLOPs: 41.73 | +7: iteration 6330/ 7508 | consumed samples: 1620480 | consumed tokens: 3318743040 | elapsed time per iteration (s): 0.56 | learning rate: 3.093E-05 | global batch size: 256 | lm loss: 2.965648E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.730 | TFLOPs: 43.54 | +7: iteration 6340/ 7508 | consumed samples: 1623040 | consumed tokens: 3323985920 | elapsed time per iteration (s): 0.56 | learning rate: 3.075E-05 | global batch size: 256 | lm loss: 2.973683E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.589 | TFLOPs: 43.63 | +7: iteration 6350/ 7508 | consumed samples: 1625600 | consumed tokens: 3329228800 | elapsed time per iteration (s): 0.57 | learning rate: 3.057E-05 | global batch size: 256 | lm loss: 3.005300E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.365 | TFLOPs: 42.75 | +7: iteration 6360/ 7508 | consumed samples: 1628160 | consumed tokens: 3334471680 | elapsed time per iteration (s): 0.56 | learning rate: 3.039E-05 | global batch size: 256 | lm loss: 2.956441E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.359 | TFLOPs: 43.60 | +7: iteration 6370/ 7508 | consumed samples: 1630720 | consumed tokens: 3339714560 | elapsed time per iteration (s): 0.56 | learning rate: 3.022E-05 | global batch size: 256 | lm loss: 2.977809E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.123 | TFLOPs: 43.30 | +7: iteration 6380/ 7508 | consumed samples: 1633280 | consumed tokens: 3344957440 | elapsed time per iteration (s): 0.57 | learning rate: 3.004E-05 | global batch size: 256 | lm loss: 2.975270E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.554 | TFLOPs: 42.76 | +7: iteration 6390/ 7508 | consumed samples: 1635840 | consumed tokens: 3350200320 | elapsed time per iteration (s): 0.56 | learning rate: 2.987E-05 | global batch size: 256 | lm loss: 2.981961E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.799 | TFLOPs: 43.65 | +7: iteration 6400/ 7508 | consumed samples: 1638400 | consumed tokens: 3355443200 | elapsed time per iteration (s): 0.56 | learning rate: 2.970E-05 | global batch size: 256 | lm loss: 3.003817E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.678 | TFLOPs: 43.63 | +7: iteration 6410/ 7508 | consumed samples: 1640960 | consumed tokens: 3360686080 | elapsed time per iteration (s): 0.57 | learning rate: 2.952E-05 | global batch size: 256 | lm loss: 2.981057E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.364 | TFLOPs: 42.56 | +7: iteration 6420/ 7508 | consumed samples: 1643520 | consumed tokens: 3365928960 | elapsed time per iteration (s): 0.56 | learning rate: 2.936E-05 | global batch size: 256 | lm loss: 2.987903E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.395 | TFLOPs: 43.89 | +7: iteration 6430/ 7508 | consumed samples: 1646080 | consumed tokens: 3371171840 | elapsed time per iteration (s): 0.56 | learning rate: 2.919E-05 | global batch size: 256 | lm loss: 2.987609E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.398 | TFLOPs: 43.42 | +7: iteration 6440/ 7508 | consumed samples: 1648640 | consumed tokens: 3376414720 | elapsed time per iteration (s): 0.57 | learning rate: 2.902E-05 | global batch size: 256 | lm loss: 2.979124E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.145 | TFLOPs: 43.01 | +7: iteration 6450/ 7508 | consumed samples: 1651200 | consumed tokens: 3381657600 | elapsed time per iteration (s): 0.57 | learning rate: 2.886E-05 | global batch size: 256 | lm loss: 2.988988E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.163 | TFLOPs: 42.73 | +7: iteration 6460/ 7508 | consumed samples: 1653760 | consumed tokens: 3386900480 | elapsed time per iteration (s): 0.56 | learning rate: 2.869E-05 | global batch size: 256 | lm loss: 2.977044E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.934 | TFLOPs: 43.37 | +7: iteration 6470/ 7508 | consumed samples: 1656320 | consumed tokens: 3392143360 | elapsed time per iteration (s): 0.56 | learning rate: 2.853E-05 | global batch size: 256 | lm loss: 3.003443E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.727 | TFLOPs: 43.54 | +7: iteration 6480/ 7508 | consumed samples: 1658880 | consumed tokens: 3397386240 | elapsed time per iteration (s): 0.56 | learning rate: 2.837E-05 | global batch size: 256 | lm loss: 2.976949E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.289 | TFLOPs: 43.60 | +7: iteration 6490/ 7508 | consumed samples: 1661440 | consumed tokens: 3402629120 | elapsed time per iteration (s): 0.56 | learning rate: 2.821E-05 | global batch size: 256 | lm loss: 2.984031E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.354 | TFLOPs: 43.32 | +7: iteration 6500/ 7508 | consumed samples: 1664000 | consumed tokens: 3407872000 | elapsed time per iteration (s): 0.56 | learning rate: 2.805E-05 | global batch size: 256 | lm loss: 2.980750E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.666 | TFLOPs: 43.44 | +7: iteration 6510/ 7508 | consumed samples: 1666560 | consumed tokens: 3413114880 | elapsed time per iteration (s): 0.56 | learning rate: 2.789E-05 | global batch size: 256 | lm loss: 2.962226E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.659 | TFLOPs: 43.35 | +7: iteration 6520/ 7508 | consumed samples: 1669120 | consumed tokens: 3418357760 | elapsed time per iteration (s): 0.56 | learning rate: 2.774E-05 | global batch size: 256 | lm loss: 2.964520E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.096 | TFLOPs: 43.29 | +7: iteration 6530/ 7508 | consumed samples: 1671680 | consumed tokens: 3423600640 | elapsed time per iteration (s): 0.58 | learning rate: 2.759E-05 | global batch size: 256 | lm loss: 2.946256E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.655 | TFLOPs: 41.82 | +7: iteration 6540/ 7508 | consumed samples: 1674240 | consumed tokens: 3428843520 | elapsed time per iteration (s): 0.57 | learning rate: 2.743E-05 | global batch size: 256 | lm loss: 2.960185E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.041 | TFLOPs: 43.10 | +7: iteration 6550/ 7508 | consumed samples: 1676800 | consumed tokens: 3434086400 | elapsed time per iteration (s): 0.57 | learning rate: 2.728E-05 | global batch size: 256 | lm loss: 2.985470E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.281 | TFLOPs: 43.02 | +7: iteration 6560/ 7508 | consumed samples: 1679360 | consumed tokens: 3439329280 | elapsed time per iteration (s): 0.59 | learning rate: 2.713E-05 | global batch size: 256 | lm loss: 2.958564E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.073 | TFLOPs: 41.57 | +7: iteration 6570/ 7508 | consumed samples: 1681920 | consumed tokens: 3444572160 | elapsed time per iteration (s): 0.59 | learning rate: 2.699E-05 | global batch size: 256 | lm loss: 2.965214E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 430.322 | TFLOPs: 41.03 | +7: iteration 6580/ 7508 | consumed samples: 1684480 | consumed tokens: 3449815040 | elapsed time per iteration (s): 0.62 | learning rate: 2.684E-05 | global batch size: 256 | lm loss: 2.991188E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 410.110 | TFLOPs: 39.10 | +7: iteration 6590/ 7508 | consumed samples: 1687040 | consumed tokens: 3455057920 | elapsed time per iteration (s): 0.70 | learning rate: 2.669E-05 | global batch size: 256 | lm loss: 2.981313E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 367.248 | TFLOPs: 35.01 | +7: iteration 6600/ 7508 | consumed samples: 1689600 | consumed tokens: 3460300800 | elapsed time per iteration (s): 0.60 | learning rate: 2.655E-05 | global batch size: 256 | lm loss: 3.010211E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 429.684 | TFLOPs: 40.97 | +7: iteration 6610/ 7508 | consumed samples: 1692160 | consumed tokens: 3465543680 | elapsed time per iteration (s): 0.56 | learning rate: 2.641E-05 | global batch size: 256 | lm loss: 2.984510E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.786 | TFLOPs: 43.55 | +7: iteration 6620/ 7508 | consumed samples: 1694720 | consumed tokens: 3470786560 | elapsed time per iteration (s): 0.59 | learning rate: 2.627E-05 | global batch size: 256 | lm loss: 2.951047E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.551 | TFLOPs: 41.43 | +7: iteration 6630/ 7508 | consumed samples: 1697280 | consumed tokens: 3476029440 | elapsed time per iteration (s): 0.61 | learning rate: 2.613E-05 | global batch size: 256 | lm loss: 2.978027E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 417.458 | TFLOPs: 39.80 | +7: iteration 6640/ 7508 | consumed samples: 1699840 | consumed tokens: 3481272320 | elapsed time per iteration (s): 0.56 | learning rate: 2.599E-05 | global batch size: 256 | lm loss: 2.960755E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.513 | TFLOPs: 43.43 | +7: iteration 6650/ 7508 | consumed samples: 1702400 | consumed tokens: 3486515200 | elapsed time per iteration (s): 0.69 | learning rate: 2.586E-05 | global batch size: 256 | lm loss: 2.965673E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 371.631 | TFLOPs: 35.43 | +7: iteration 6660/ 7508 | consumed samples: 1704960 | consumed tokens: 3491758080 | elapsed time per iteration (s): 0.63 | learning rate: 2.572E-05 | global batch size: 256 | lm loss: 2.987079E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 409.387 | TFLOPs: 39.03 | +7: iteration 6670/ 7508 | consumed samples: 1707520 | consumed tokens: 3497000960 | elapsed time per iteration (s): 0.57 | learning rate: 2.559E-05 | global batch size: 256 | lm loss: 2.967545E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.612 | TFLOPs: 42.87 | +7: iteration 6680/ 7508 | consumed samples: 1710080 | consumed tokens: 3502243840 | elapsed time per iteration (s): 0.57 | learning rate: 2.546E-05 | global batch size: 256 | lm loss: 2.978930E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.448 | TFLOPs: 43.04 | +7: iteration 6690/ 7508 | consumed samples: 1712640 | consumed tokens: 3507486720 | elapsed time per iteration (s): 0.56 | learning rate: 2.533E-05 | global batch size: 256 | lm loss: 2.978386E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.246 | TFLOPs: 43.31 | +7: iteration 6700/ 7508 | consumed samples: 1715200 | consumed tokens: 3512729600 | elapsed time per iteration (s): 0.58 | learning rate: 2.520E-05 | global batch size: 256 | lm loss: 2.956943E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.428 | TFLOPs: 42.37 | +7: iteration 6710/ 7508 | consumed samples: 1717760 | consumed tokens: 3517972480 | elapsed time per iteration (s): 0.58 | learning rate: 2.508E-05 | global batch size: 256 | lm loss: 2.980929E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.071 | TFLOPs: 41.96 | +7: iteration 6720/ 7508 | consumed samples: 1720320 | consumed tokens: 3523215360 | elapsed time per iteration (s): 0.57 | learning rate: 2.495E-05 | global batch size: 256 | lm loss: 2.958115E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.555 | TFLOPs: 42.76 | +7: iteration 6730/ 7508 | consumed samples: 1722880 | consumed tokens: 3528458240 | elapsed time per iteration (s): 0.56 | learning rate: 2.483E-05 | global batch size: 256 | lm loss: 2.973613E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.513 | TFLOPs: 43.62 | +7: iteration 6740/ 7508 | consumed samples: 1725440 | consumed tokens: 3533701120 | elapsed time per iteration (s): 0.56 | learning rate: 2.470E-05 | global batch size: 256 | lm loss: 2.988783E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.134 | TFLOPs: 43.96 | +7: iteration 6750/ 7508 | consumed samples: 1728000 | consumed tokens: 3538944000 | elapsed time per iteration (s): 0.57 | learning rate: 2.458E-05 | global batch size: 256 | lm loss: 2.985939E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.372 | TFLOPs: 43.13 | +7: iteration 6760/ 7508 | consumed samples: 1730560 | consumed tokens: 3544186880 | elapsed time per iteration (s): 0.56 | learning rate: 2.446E-05 | global batch size: 256 | lm loss: 2.968943E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.950 | TFLOPs: 43.66 | +7: iteration 6770/ 7508 | consumed samples: 1733120 | consumed tokens: 3549429760 | elapsed time per iteration (s): 0.56 | learning rate: 2.435E-05 | global batch size: 256 | lm loss: 3.003178E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.948 | TFLOPs: 43.76 | +7: iteration 6780/ 7508 | consumed samples: 1735680 | consumed tokens: 3554672640 | elapsed time per iteration (s): 0.56 | learning rate: 2.423E-05 | global batch size: 256 | lm loss: 2.949305E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.117 | TFLOPs: 43.96 | +7: iteration 6790/ 7508 | consumed samples: 1738240 | consumed tokens: 3559915520 | elapsed time per iteration (s): 0.70 | learning rate: 2.412E-05 | global batch size: 256 | lm loss: 2.964761E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 367.142 | TFLOPs: 35.00 | +7: iteration 6800/ 7508 | consumed samples: 1740800 | consumed tokens: 3565158400 | elapsed time per iteration (s): 0.65 | learning rate: 2.400E-05 | global batch size: 256 | lm loss: 3.014590E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 396.298 | TFLOPs: 37.78 | +7: iteration 6810/ 7508 | consumed samples: 1743360 | consumed tokens: 3570401280 | elapsed time per iteration (s): 0.59 | learning rate: 2.389E-05 | global batch size: 256 | lm loss: 2.945099E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.529 | TFLOPs: 41.62 | +7: iteration 6820/ 7508 | consumed samples: 1745920 | consumed tokens: 3575644160 | elapsed time per iteration (s): 0.57 | learning rate: 2.378E-05 | global batch size: 256 | lm loss: 2.980190E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.152 | TFLOPs: 42.82 | +7: iteration 6830/ 7508 | consumed samples: 1748480 | consumed tokens: 3580887040 | elapsed time per iteration (s): 0.56 | learning rate: 2.367E-05 | global batch size: 256 | lm loss: 2.971993E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.993 | TFLOPs: 43.28 | +7: iteration 6840/ 7508 | consumed samples: 1751040 | consumed tokens: 3586129920 | elapsed time per iteration (s): 0.57 | learning rate: 2.357E-05 | global batch size: 256 | lm loss: 2.980289E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.373 | TFLOPs: 43.13 | +7: iteration 6850/ 7508 | consumed samples: 1753600 | consumed tokens: 3591372800 | elapsed time per iteration (s): 0.57 | learning rate: 2.346E-05 | global batch size: 256 | lm loss: 2.959142E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.228 | TFLOPs: 42.92 | +7: iteration 6860/ 7508 | consumed samples: 1756160 | consumed tokens: 3596615680 | elapsed time per iteration (s): 0.56 | learning rate: 2.336E-05 | global batch size: 256 | lm loss: 2.942008E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.459 | TFLOPs: 43.71 | +7: iteration 6870/ 7508 | consumed samples: 1758720 | consumed tokens: 3601858560 | elapsed time per iteration (s): 0.56 | learning rate: 2.326E-05 | global batch size: 256 | lm loss: 2.955273E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.485 | TFLOPs: 43.71 | +7: iteration 6880/ 7508 | consumed samples: 1761280 | consumed tokens: 3607101440 | elapsed time per iteration (s): 0.57 | learning rate: 2.316E-05 | global batch size: 256 | lm loss: 2.951917E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.587 | TFLOPs: 43.05 | +7: iteration 6890/ 7508 | consumed samples: 1763840 | consumed tokens: 3612344320 | elapsed time per iteration (s): 0.56 | learning rate: 2.306E-05 | global batch size: 256 | lm loss: 2.974718E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.577 | TFLOPs: 43.91 | +7: iteration 6900/ 7508 | consumed samples: 1766400 | consumed tokens: 3617587200 | elapsed time per iteration (s): 0.87 | learning rate: 2.296E-05 | global batch size: 256 | lm loss: 2.977376E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 295.369 | TFLOPs: 28.16 | +7: iteration 6910/ 7508 | consumed samples: 1768960 | consumed tokens: 3622830080 | elapsed time per iteration (s): 0.56 | learning rate: 2.286E-05 | global batch size: 256 | lm loss: 2.963410E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.288 | TFLOPs: 43.22 | +7: iteration 6920/ 7508 | consumed samples: 1771520 | consumed tokens: 3628072960 | elapsed time per iteration (s): 0.57 | learning rate: 2.277E-05 | global batch size: 256 | lm loss: 2.973555E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.224 | TFLOPs: 43.11 | +7: iteration 6930/ 7508 | consumed samples: 1774080 | consumed tokens: 3633315840 | elapsed time per iteration (s): 0.56 | learning rate: 2.268E-05 | global batch size: 256 | lm loss: 2.957263E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.149 | TFLOPs: 43.30 | +7: iteration 6940/ 7508 | consumed samples: 1776640 | consumed tokens: 3638558720 | elapsed time per iteration (s): 0.57 | learning rate: 2.258E-05 | global batch size: 256 | lm loss: 2.951806E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.966 | TFLOPs: 42.90 | +7: iteration 6950/ 7508 | consumed samples: 1779200 | consumed tokens: 3643801600 | elapsed time per iteration (s): 0.56 | learning rate: 2.249E-05 | global batch size: 256 | lm loss: 2.971831E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.416 | TFLOPs: 43.42 | +7: iteration 6960/ 7508 | consumed samples: 1781760 | consumed tokens: 3649044480 | elapsed time per iteration (s): 0.56 | learning rate: 2.241E-05 | global batch size: 256 | lm loss: 2.946022E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.571 | TFLOPs: 43.91 | +7: iteration 6970/ 7508 | consumed samples: 1784320 | consumed tokens: 3654287360 | elapsed time per iteration (s): 0.57 | learning rate: 2.232E-05 | global batch size: 256 | lm loss: 2.962206E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.865 | TFLOPs: 43.08 | +7: iteration 6980/ 7508 | consumed samples: 1786880 | consumed tokens: 3659530240 | elapsed time per iteration (s): 0.57 | learning rate: 2.223E-05 | global batch size: 256 | lm loss: 2.921258E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.031 | TFLOPs: 42.62 | +7: iteration 6990/ 7508 | consumed samples: 1789440 | consumed tokens: 3664773120 | elapsed time per iteration (s): 0.56 | learning rate: 2.215E-05 | global batch size: 256 | lm loss: 2.952674E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.341 | TFLOPs: 43.51 | +7: iteration 7000/ 7508 | consumed samples: 1792000 | consumed tokens: 3670016000 | elapsed time per iteration (s): 0.57 | learning rate: 2.207E-05 | global batch size: 256 | lm loss: 2.966997E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.556 | TFLOPs: 43.05 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 7000 | lm loss value: 2.858569E+00 | lm loss PPL: 1.743656E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 7000 to checkpoints_421moscar +0: [2022-11-29 18:02:10,261] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step7000 is begin to save! +0: [2022-11-29 18:02:10,326] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:02:10,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:02:10,723] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:02:10,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:02:10,768] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:02:10,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:02:10,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:02:10,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:02:10,856] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:02:10,899] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:02:10,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:02:10,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:02:10,943] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:02:10,988] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:02:10,988] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:02:11,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:02:11,033] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:02:11,079] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:02:11,079] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:02:11,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:02:11,119] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:02:11,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:02:11,162] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/layer_13-model_00-model_states.pt... +0: [2022-11-29 18:02:11,205] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/layer_13-model_00-model_states.pt. +0: [2022-11-29 18:02:11,205] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:02:11,248] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:02:11,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/layer_15-model_00-model_states.pt... +0: [2022-11-29 18:02:11,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/layer_15-model_00-model_states.pt. +0: [2022-11-29 18:02:11,291] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/layer_16-model_00-model_states.pt... +0: [2022-11-29 18:02:11,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/layer_16-model_00-model_states.pt. +0: [2022-11-29 18:02:11,334] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/layer_17-model_00-model_states.pt... +0: [2022-11-29 18:02:11,377] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/layer_17-model_00-model_states.pt. +0: [2022-11-29 18:02:11,377] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/layer_18-model_00-model_states.pt... +0: [2022-11-29 18:02:11,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/layer_18-model_00-model_states.pt. +0: [2022-11-29 18:02:11,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/layer_19-model_00-model_states.pt... +0: [2022-11-29 18:02:11,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/layer_19-model_00-model_states.pt. +0: [2022-11-29 18:02:11,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/layer_20-model_00-model_states.pt... +0: [2022-11-29 18:02:11,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/layer_20-model_00-model_states.pt. +0: [2022-11-29 18:02:11,505] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/layer_22-model_00-model_states.pt... +0: [2022-11-29 18:02:11,509] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/layer_22-model_00-model_states.pt. +0: [2022-11-29 18:02:11,510] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_421moscar/global_step7000/mp_rank_00_model_states.pt +0: [2022-11-29 18:02:11,510] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:02:11,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:02:11,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:02:11,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:02:11,659] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:02:11,659] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:02:11,659] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 18:02:11,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:02:11,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:02:11,661] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:02:11,661] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 18:02:11,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:02:11,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 18:02:11,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:02:11,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:02:11,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 18:02:11,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:02:11,661] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:02:11,661] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 18:02:11,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:02:11,662] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:02:11,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 18:02:11,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:02:11,676] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:02:11,676] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 18:02:11,684] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:02:11,684] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:02:11,684] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:02:11,684] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:02:11,684] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 18:02:11,684] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 18:02:11,686] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:02:11,686] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:02:11,686] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 18:02:11,686] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:02:11,686] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:02:11,686] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 18:02:11,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:02:11,665] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:02:11,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 18:02:11,669] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:02:11,669] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:02:11,669] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 18:02:11,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:02:11,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:02:11,671] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 18:02:11,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:02:11,676] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:02:11,676] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 18:02:11,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:02:11,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:02:11,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 18:02:11,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:02:11,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:02:11,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 18:02:11,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:02:11,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:02:11,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 18:02:11,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:02:11,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:02:11,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 18:02:11,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:02:11,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:02:11,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 18:02:11,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:02:11,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:02:11,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 18:02:11,733] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:02:11,733] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:02:11,733] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:02:11,733] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:02:11,733] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 18:02:11,733] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 18:02:11,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:02:11,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:02:11,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:02:11,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:02:11,735] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:02:11,735] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:02:11,735] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:02:11,735] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 18:02:11,735] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:02:11,735] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 18:02:11,735] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 18:02:11,735] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 18:02:11,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:02:11,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:02:11,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:02:11,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:02:11,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:02:11,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:02:11,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 18:02:11,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 18:02:11,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 18:02:11,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:02:11,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:02:11,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 18:02:11,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:02:11,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:02:11,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:02:11,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:02:11,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:02:11,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:02:11,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 18:02:11,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:02:11,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:02:11,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 18:02:11,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 18:02:11,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 18:02:11,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:02:11,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:02:11,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:02:11,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:02:11,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:02:11,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:02:11,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:02:11,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:02:11,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 18:02:11,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 18:02:11,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 18:02:11,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 18:02:11,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:02:11,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:02:11,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:02:11,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:02:11,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:02:11,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:02:11,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:02:11,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:02:11,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:02:11,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:02:11,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:02:11,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:02:11,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:02:11,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:02:11,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:02:11,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:02:11,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 18:02:11,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 18:02:11,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 18:02:11,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 18:02:11,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 18:02:11,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 18:02:11,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 18:02:11,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 18:02:11,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:02:11,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 18:02:11,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:02:11,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:02:11,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:02:11,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:02:11,865] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:02:11,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:02:11,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:02:11,865] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:02:11,865] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 18:02:11,865] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:02:11,865] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:02:11,865] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:02:11,865] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:02:11,865] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 18:02:11,865] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 18:02:11,865] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 18:02:11,865] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 18:02:11,865] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 18:02:11,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:02:11,865] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:02:11,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 18:02:11,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:02:11,867] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:02:11,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 18:02:11,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:02:11,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:02:11,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:02:11,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:02:11,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:02:11,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:02:11,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:02:11,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:02:11,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:02:11,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:02:11,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:02:11,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:02:11,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:02:11,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:02:11,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:02:11,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:02:11,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 18:02:11,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 18:02:11,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 18:02:11,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 18:02:11,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 18:02:11,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 18:02:11,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 18:02:11,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: successfully saved checkpoint at iteration 7000 to checkpoints_421moscar +7: time (ms) | save-checkpoint: 1722.62 +7: iteration 7010/ 7508 | consumed samples: 1794560 | consumed tokens: 3675258880 | elapsed time per iteration (s): 0.76 | learning rate: 2.199E-05 | global batch size: 256 | lm loss: 2.981154E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.926 | TFLOPs: 32.22 | +7: iteration 7020/ 7508 | consumed samples: 1797120 | consumed tokens: 3680501760 | elapsed time per iteration (s): 0.56 | learning rate: 2.191E-05 | global batch size: 256 | lm loss: 2.958582E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 459.461 | TFLOPs: 43.80 | +7: iteration 7030/ 7508 | consumed samples: 1799680 | consumed tokens: 3685744640 | elapsed time per iteration (s): 0.56 | learning rate: 2.183E-05 | global batch size: 256 | lm loss: 2.964995E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 459.134 | TFLOPs: 43.77 | +7: iteration 7040/ 7508 | consumed samples: 1802240 | consumed tokens: 3690987520 | elapsed time per iteration (s): 0.55 | learning rate: 2.176E-05 | global batch size: 256 | lm loss: 2.969609E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.452 | TFLOPs: 43.99 | +7: iteration 7050/ 7508 | consumed samples: 1804800 | consumed tokens: 3696230400 | elapsed time per iteration (s): 0.56 | learning rate: 2.168E-05 | global batch size: 256 | lm loss: 2.976188E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.812 | TFLOPs: 43.93 | +7: iteration 7060/ 7508 | consumed samples: 1807360 | consumed tokens: 3701473280 | elapsed time per iteration (s): 0.57 | learning rate: 2.161E-05 | global batch size: 256 | lm loss: 2.984895E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.561 | TFLOPs: 42.77 | +7: iteration 7070/ 7508 | consumed samples: 1809920 | consumed tokens: 3706716160 | elapsed time per iteration (s): 0.70 | learning rate: 2.154E-05 | global batch size: 256 | lm loss: 2.941167E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 364.903 | TFLOPs: 34.79 | +7: iteration 7080/ 7508 | consumed samples: 1812480 | consumed tokens: 3711959040 | elapsed time per iteration (s): 0.60 | learning rate: 2.147E-05 | global batch size: 256 | lm loss: 2.962628E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 423.853 | TFLOPs: 40.41 | +7: iteration 7090/ 7508 | consumed samples: 1815040 | consumed tokens: 3717201920 | elapsed time per iteration (s): 0.57 | learning rate: 2.140E-05 | global batch size: 256 | lm loss: 2.960954E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.384 | TFLOPs: 42.75 | +7: iteration 7100/ 7508 | consumed samples: 1817600 | consumed tokens: 3722444800 | elapsed time per iteration (s): 0.56 | learning rate: 2.134E-05 | global batch size: 256 | lm loss: 2.960176E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.934 | TFLOPs: 43.37 | +7: iteration 7110/ 7508 | consumed samples: 1820160 | consumed tokens: 3727687680 | elapsed time per iteration (s): 0.56 | learning rate: 2.127E-05 | global batch size: 256 | lm loss: 2.978084E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.253 | TFLOPs: 43.21 | +7: iteration 7120/ 7508 | consumed samples: 1822720 | consumed tokens: 3732930560 | elapsed time per iteration (s): 0.56 | learning rate: 2.121E-05 | global batch size: 256 | lm loss: 2.979277E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.285 | TFLOPs: 43.69 | +7: iteration 7130/ 7508 | consumed samples: 1825280 | consumed tokens: 3738173440 | elapsed time per iteration (s): 0.57 | learning rate: 2.115E-05 | global batch size: 256 | lm loss: 2.983127E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.313 | TFLOPs: 42.55 | +7: iteration 7140/ 7508 | consumed samples: 1827840 | consumed tokens: 3743416320 | elapsed time per iteration (s): 0.57 | learning rate: 2.109E-05 | global batch size: 256 | lm loss: 2.973146E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.750 | TFLOPs: 42.69 | +7: iteration 7150/ 7508 | consumed samples: 1830400 | consumed tokens: 3748659200 | elapsed time per iteration (s): 0.58 | learning rate: 2.103E-05 | global batch size: 256 | lm loss: 2.979718E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.176 | TFLOPs: 42.44 | +7: iteration 7160/ 7508 | consumed samples: 1832960 | consumed tokens: 3753902080 | elapsed time per iteration (s): 0.58 | learning rate: 2.097E-05 | global batch size: 256 | lm loss: 2.957079E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.829 | TFLOPs: 42.31 | +7: iteration 7170/ 7508 | consumed samples: 1835520 | consumed tokens: 3759144960 | elapsed time per iteration (s): 0.56 | learning rate: 2.092E-05 | global batch size: 256 | lm loss: 2.949294E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.779 | TFLOPs: 43.55 | +7: iteration 7180/ 7508 | consumed samples: 1838080 | consumed tokens: 3764387840 | elapsed time per iteration (s): 0.56 | learning rate: 2.087E-05 | global batch size: 256 | lm loss: 2.959209E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 461.031 | TFLOPs: 43.95 | +7: iteration 7190/ 7508 | consumed samples: 1840640 | consumed tokens: 3769630720 | elapsed time per iteration (s): 0.57 | learning rate: 2.081E-05 | global batch size: 256 | lm loss: 2.982593E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.050 | TFLOPs: 42.81 | +7: iteration 7200/ 7508 | consumed samples: 1843200 | consumed tokens: 3774873600 | elapsed time per iteration (s): 0.56 | learning rate: 2.076E-05 | global batch size: 256 | lm loss: 2.922289E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.833 | TFLOPs: 43.27 | +7: iteration 7210/ 7508 | consumed samples: 1845760 | consumed tokens: 3780116480 | elapsed time per iteration (s): 0.57 | learning rate: 2.071E-05 | global batch size: 256 | lm loss: 2.987403E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.456 | TFLOPs: 42.95 | +7: iteration 7220/ 7508 | consumed samples: 1848320 | consumed tokens: 3785359360 | elapsed time per iteration (s): 0.56 | learning rate: 2.067E-05 | global batch size: 256 | lm loss: 2.965555E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.001 | TFLOPs: 43.47 | +7: iteration 7230/ 7508 | consumed samples: 1850880 | consumed tokens: 3790602240 | elapsed time per iteration (s): 0.64 | learning rate: 2.062E-05 | global batch size: 256 | lm loss: 2.958902E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 398.564 | TFLOPs: 38.00 | +7: iteration 7240/ 7508 | consumed samples: 1853440 | consumed tokens: 3795845120 | elapsed time per iteration (s): 0.56 | learning rate: 2.058E-05 | global batch size: 256 | lm loss: 2.944448E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.691 | TFLOPs: 43.25 | +7: iteration 7250/ 7508 | consumed samples: 1856000 | consumed tokens: 3801088000 | elapsed time per iteration (s): 0.58 | learning rate: 2.054E-05 | global batch size: 256 | lm loss: 2.970836E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.428 | TFLOPs: 42.09 | +7: iteration 7260/ 7508 | consumed samples: 1858560 | consumed tokens: 3806330880 | elapsed time per iteration (s): 0.56 | learning rate: 2.050E-05 | global batch size: 256 | lm loss: 2.952397E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.561 | TFLOPs: 43.43 | +7: iteration 7270/ 7508 | consumed samples: 1861120 | consumed tokens: 3811573760 | elapsed time per iteration (s): 0.56 | learning rate: 2.046E-05 | global batch size: 256 | lm loss: 2.977472E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 459.490 | TFLOPs: 43.81 | +7: iteration 7280/ 7508 | consumed samples: 1863680 | consumed tokens: 3816816640 | elapsed time per iteration (s): 0.56 | learning rate: 2.042E-05 | global batch size: 256 | lm loss: 2.943424E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 460.715 | TFLOPs: 43.92 | +7: iteration 7290/ 7508 | consumed samples: 1866240 | consumed tokens: 3822059520 | elapsed time per iteration (s): 0.56 | learning rate: 2.038E-05 | global batch size: 256 | lm loss: 2.956812E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.802 | TFLOPs: 43.36 | +7: iteration 7300/ 7508 | consumed samples: 1868800 | consumed tokens: 3827302400 | elapsed time per iteration (s): 0.57 | learning rate: 2.035E-05 | global batch size: 256 | lm loss: 2.976246E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.886 | TFLOPs: 42.89 | +7: iteration 7310/ 7508 | consumed samples: 1871360 | consumed tokens: 3832545280 | elapsed time per iteration (s): 0.58 | learning rate: 2.032E-05 | global batch size: 256 | lm loss: 2.964425E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.053 | TFLOPs: 42.43 | +7: iteration 7320/ 7508 | consumed samples: 1873920 | consumed tokens: 3837788160 | elapsed time per iteration (s): 0.57 | learning rate: 2.029E-05 | global batch size: 256 | lm loss: 2.964277E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.699 | TFLOPs: 42.87 | +7: iteration 7330/ 7508 | consumed samples: 1876480 | consumed tokens: 3843031040 | elapsed time per iteration (s): 0.58 | learning rate: 2.026E-05 | global batch size: 256 | lm loss: 2.952487E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.930 | TFLOPs: 41.75 | +7: iteration 7340/ 7508 | consumed samples: 1879040 | consumed tokens: 3848273920 | elapsed time per iteration (s): 0.57 | learning rate: 2.023E-05 | global batch size: 256 | lm loss: 2.940125E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.240 | TFLOPs: 42.54 | +7: iteration 7350/ 7508 | consumed samples: 1881600 | consumed tokens: 3853516800 | elapsed time per iteration (s): 0.56 | learning rate: 2.020E-05 | global batch size: 256 | lm loss: 2.990954E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.151 | TFLOPs: 43.20 | +7: iteration 7360/ 7508 | consumed samples: 1884160 | consumed tokens: 3858759680 | elapsed time per iteration (s): 0.57 | learning rate: 2.018E-05 | global batch size: 256 | lm loss: 2.981512E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.492 | TFLOPs: 42.95 | +7: iteration 7370/ 7508 | consumed samples: 1886720 | consumed tokens: 3864002560 | elapsed time per iteration (s): 0.57 | learning rate: 2.015E-05 | global batch size: 256 | lm loss: 2.949195E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.971 | TFLOPs: 42.61 | +7: iteration 7380/ 7508 | consumed samples: 1889280 | consumed tokens: 3869245440 | elapsed time per iteration (s): 0.56 | learning rate: 2.013E-05 | global batch size: 256 | lm loss: 2.952882E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.212 | TFLOPs: 43.69 | +7: iteration 7390/ 7508 | consumed samples: 1891840 | consumed tokens: 3874488320 | elapsed time per iteration (s): 0.58 | learning rate: 2.011E-05 | global batch size: 256 | lm loss: 2.937130E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.812 | TFLOPs: 42.22 | +7: iteration 7400/ 7508 | consumed samples: 1894400 | consumed tokens: 3879731200 | elapsed time per iteration (s): 0.57 | learning rate: 2.009E-05 | global batch size: 256 | lm loss: 2.955361E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.122 | TFLOPs: 43.01 | +7: iteration 7410/ 7508 | consumed samples: 1896960 | consumed tokens: 3884974080 | elapsed time per iteration (s): 0.56 | learning rate: 2.008E-05 | global batch size: 256 | lm loss: 2.943304E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.483 | TFLOPs: 43.33 | +7: iteration 7420/ 7508 | consumed samples: 1899520 | consumed tokens: 3890216960 | elapsed time per iteration (s): 0.57 | learning rate: 2.006E-05 | global batch size: 256 | lm loss: 2.954021E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.905 | TFLOPs: 42.89 | +7: iteration 7430/ 7508 | consumed samples: 1902080 | consumed tokens: 3895459840 | elapsed time per iteration (s): 0.56 | learning rate: 2.005E-05 | global batch size: 256 | lm loss: 2.958958E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.433 | TFLOPs: 43.42 | +7: iteration 7440/ 7508 | consumed samples: 1904640 | consumed tokens: 3900702720 | elapsed time per iteration (s): 0.56 | learning rate: 2.004E-05 | global batch size: 256 | lm loss: 2.956088E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.301 | TFLOPs: 43.22 | +7: iteration 7450/ 7508 | consumed samples: 1907200 | consumed tokens: 3905945600 | elapsed time per iteration (s): 0.59 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 2.967162E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.927 | TFLOPs: 41.56 | +7: iteration 7460/ 7508 | consumed samples: 1909760 | consumed tokens: 3911188480 | elapsed time per iteration (s): 0.56 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 2.972096E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.495 | TFLOPs: 43.24 | +7: iteration 7470/ 7508 | consumed samples: 1912320 | consumed tokens: 3916431360 | elapsed time per iteration (s): 0.57 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.952355E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.295 | TFLOPs: 43.03 | +7: iteration 7480/ 7508 | consumed samples: 1914880 | consumed tokens: 3921674240 | elapsed time per iteration (s): 0.57 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.930433E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.389 | TFLOPs: 42.65 | +7: iteration 7490/ 7508 | consumed samples: 1917440 | consumed tokens: 3926917120 | elapsed time per iteration (s): 0.56 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.949854E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.524 | TFLOPs: 43.43 | +7: iteration 7500/ 7508 | consumed samples: 1920000 | consumed tokens: 3932160000 | elapsed time per iteration (s): 0.56 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.966339E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.494 | TFLOPs: 43.24 | +0: [after training is done] datetime: 2022-11-29 18:07:02 +0: saving checkpoint at iteration 7508 to checkpoints_421moscar +7: ------------------------------------------------------------------------------------------------------------ +7: valid loss at the end of training for val data | lm loss value: 2.990056E+00 | lm loss PPL: 1.988679E+01 | +7: ------------------------------------------------------------------------------------------------------------ +0: [2022-11-29 18:07:02,387] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step7508 is begin to save! +0: [2022-11-29 18:07:02,391] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:07:02,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:07:02,549] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:07:02,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:07:02,593] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:07:02,636] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:07:02,637] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:07:02,678] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:07:02,678] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:07:02,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:07:02,723] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:07:02,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:07:02,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:07:02,806] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:07:02,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:07:02,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:07:02,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:07:02,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:07:02,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:07:02,933] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:07:02,934] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:07:02,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:07:02,977] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/layer_13-model_00-model_states.pt... +0: [2022-11-29 18:07:03,020] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/layer_13-model_00-model_states.pt. +0: [2022-11-29 18:07:03,020] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:07:03,064] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:07:03,064] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/layer_15-model_00-model_states.pt... +0: [2022-11-29 18:07:03,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/layer_15-model_00-model_states.pt. +0: [2022-11-29 18:07:03,105] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/layer_16-model_00-model_states.pt... +0: [2022-11-29 18:07:03,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/layer_16-model_00-model_states.pt. +0: [2022-11-29 18:07:03,148] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/layer_17-model_00-model_states.pt... +0: [2022-11-29 18:07:03,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/layer_17-model_00-model_states.pt. +0: [2022-11-29 18:07:03,190] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/layer_18-model_00-model_states.pt... +0: [2022-11-29 18:07:03,232] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/layer_18-model_00-model_states.pt. +0: [2022-11-29 18:07:03,233] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/layer_19-model_00-model_states.pt... +0: [2022-11-29 18:07:03,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/layer_19-model_00-model_states.pt. +0: [2022-11-29 18:07:03,275] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/layer_20-model_00-model_states.pt... +0: [2022-11-29 18:07:03,317] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/layer_20-model_00-model_states.pt. +0: [2022-11-29 18:07:03,317] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/layer_22-model_00-model_states.pt... +0: [2022-11-29 18:07:03,321] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/layer_22-model_00-model_states.pt. +0: [2022-11-29 18:07:03,322] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_421moscar/global_step7508/mp_rank_00_model_states.pt +0: [2022-11-29 18:07:03,322] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/mp_rank_00_model_states.pt... +0: [2022-11-29 18:07:03,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/mp_rank_00_model_states.pt. +0: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:07:03,345] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:07:03,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:07:03,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:07:03,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +0: [2022-11-29 18:07:03,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:07:03,435] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:07:03,441] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:07:03,441] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:07:03,441] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +6: [2022-11-29 18:07:03,441] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:07:03,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:07:03,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +0: [2022-11-29 18:07:03,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:07:03,443] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:07:03,443] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +6: [2022-11-29 18:07:03,443] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:07:03,443] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:07:03,443] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +6: [2022-11-29 18:07:03,443] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:07:03,443] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:07:03,443] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +6: [2022-11-29 18:07:03,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:07:03,444] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:07:03,444] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +1: [2022-11-29 18:07:03,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:07:03,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:07:03,444] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:07:03,444] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:07:03,444] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +1: [2022-11-29 18:07:03,444] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +7: [2022-11-29 18:07:03,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:07:03,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:07:03,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +7: [2022-11-29 18:07:03,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:07:03,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:07:03,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +7: [2022-11-29 18:07:03,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:07:03,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:07:03,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +6: [2022-11-29 18:07:03,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:07:03,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:07:03,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +7: [2022-11-29 18:07:03,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:07:03,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:07:03,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +7: [2022-11-29 18:07:03,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:07:03,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:07:03,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +1: [2022-11-29 18:07:03,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:07:03,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:07:03,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +4: [2022-11-29 18:07:03,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:07:03,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:07:03,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:07:03,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:07:03,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:07:03,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:07:03,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:07:03,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +4: [2022-11-29 18:07:03,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +4: [2022-11-29 18:07:03,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:07:03,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:07:03,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:07:03,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +4: [2022-11-29 18:07:03,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +4: [2022-11-29 18:07:03,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +1: [2022-11-29 18:07:03,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:07:03,450] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +4: [2022-11-29 18:07:03,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:07:03,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +4: [2022-11-29 18:07:03,450] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:07:03,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:07:03,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +4: [2022-11-29 18:07:03,450] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:07:03,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +6: [2022-11-29 18:07:03,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:07:03,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:07:03,451] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +6: [2022-11-29 18:07:03,451] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:07:03,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +1: [2022-11-29 18:07:03,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +0: [2022-11-29 18:07:03,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:07:03,453] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:07:03,453] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +0: [2022-11-29 18:07:03,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:07:03,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:07:03,453] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:07:03,453] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +0: [2022-11-29 18:07:03,453] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:07:03,453] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +0: [2022-11-29 18:07:03,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:07:03,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:07:03,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:07:03,454] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:07:03,454] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:07:03,454] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +2: [2022-11-29 18:07:03,435] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +0: [2022-11-29 18:07:03,454] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +2: [2022-11-29 18:07:03,435] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +0: [2022-11-29 18:07:03,454] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +0: [2022-11-29 18:07:03,454] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +2: [2022-11-29 18:07:03,441] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:07:03,441] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:07:03,441] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +2: [2022-11-29 18:07:03,441] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:07:03,441] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:07:03,441] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +2: [2022-11-29 18:07:03,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:07:03,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:07:03,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +2: [2022-11-29 18:07:03,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:07:03,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:07:03,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +2: [2022-11-29 18:07:03,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:07:03,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:07:03,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +2: [2022-11-29 18:07:03,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:07:03,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:07:03,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +4: [2022-11-29 18:07:03,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:07:03,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:07:03,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +1: [2022-11-29 18:07:03,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:07:03,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:07:03,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +1: [2022-11-29 18:07:03,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:07:03,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:07:03,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +1: [2022-11-29 18:07:03,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:07:03,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:07:03,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +7: [2022-11-29 18:07:03,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:07:03,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:07:03,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:07:03,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:07:03,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +7: [2022-11-29 18:07:03,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +6: [2022-11-29 18:07:03,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:07:03,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:07:03,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:07:03,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:07:03,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +6: [2022-11-29 18:07:03,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +3: [2022-11-29 18:07:03,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:07:03,438] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:07:03,438] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:07:03,438] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +5: [2022-11-29 18:07:03,443] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:07:03,443] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:07:03,443] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +5: [2022-11-29 18:07:03,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:07:03,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:07:03,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +5: [2022-11-29 18:07:03,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:07:03,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:07:03,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +5: [2022-11-29 18:07:03,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:07:03,450] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:07:03,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +5: [2022-11-29 18:07:03,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:07:03,451] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:07:03,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +5: [2022-11-29 18:07:03,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:07:03,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:07:03,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +5: [2022-11-29 18:07:03,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:07:03,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:07:03,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +3: [2022-11-29 18:07:03,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:07:03,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:07:03,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +3: [2022-11-29 18:07:03,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:07:03,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +3: [2022-11-29 18:07:03,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:07:03,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:07:03,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:07:03,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:07:03,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +3: [2022-11-29 18:07:03,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +3: [2022-11-29 18:07:03,498] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:07:03,498] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:07:03,498] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +3: [2022-11-29 18:07:03,498] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:07:03,499] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:07:03,499] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +3: [2022-11-29 18:07:03,499] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:07:03,499] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:07:03,499] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +3: [2022-11-29 18:07:03,499] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:07:03,499] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:07:03,499] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +0: [2022-11-29 18:07:03,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421moscar/global_step7508/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:07:03,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +0: successfully saved checkpoint at iteration 7508 to checkpoints_421moscar +7: ------------------------------------------------------------------------------------------------------------ +7: test loss at the end of training for test data | lm loss value: 2.876468E+00 | lm loss PPL: 1.775146E+01 | +7: ------------------------------------------------------------------------------------------------------------ +END 2085607: Tue Nov 29 18:07:15 EET 2022 diff --git a/421m3b93b9/sbatch_421m_oscar.sh b/421m3b93b9/sbatch_421m_oscar.sh new file mode 100644 index 0000000000000000000000000000000000000000..f76698eec8092951c467da110ba84c436594d807 --- /dev/null +++ b/421m3b93b9/sbatch_421m_oscar.sh @@ -0,0 +1,161 @@ +#!/bin/bash +#SBATCH --nodes=8 +#SBATCH --ntasks-per-node=1 +#SBATCH --cpus-per-task=32 +#SBATCH --mem=256G +#SBATCH -p pilot +#SBATCH -t 48:00:00 +#SBATCH --gpus-per-node=mi250:8 +#SBATCH --exclusive=user +#SBATCH --hint=nomultithread +#SBATCH --account=project_462000119 +#SBATCH -o logs/%j.out +#SBATCH -e logs/%j.err + +VARIANT=421moscar + +# if run without sbatch, invoke here +if [ -z $SLURM_JOB_ID ]; then + mkdir -p logs + sbatch "$0" + exit +fi + +set -euo pipefail + +# symlink logs/latest.out and logs/latest.err +ln -f -s $SLURM_JOB_ID.out logs/latest.out +ln -f -s $SLURM_JOB_ID.err logs/latest.err + +KILL_SWITCH_PATH=kill-switch-$VARIANT +CHECKPOINT_PATH=checkpoints_$VARIANT +TENSORBOARD_PATH=tensorboard_$VARIANT +# Start from scratch +rm -rf "$CHECKPOINT_PATH" "$TENSORBOARD_PATH" + +# Data +VOCAB_FILE="gpt2/vocab.json" +MERGE_FILE="gpt2/merges.txt" +DATA_PATH="/scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document" +DATA_PATH="/scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document" + +PP_SIZE=1 +TP_SIZE=1 + +MICRO_BATCH_SIZE=4 +GRADIENT_ACCUMULATION_STEPS=1 +WORLD_SIZE=$((SLURM_GPUS_ON_NODE*SLURM_JOB_NUM_NODES)) +GLOBAL_BATCH_SIZE=$((MICRO_BATCH_SIZE*WORLD_SIZE*GRADIENT_ACCUMULATION_STEPS)) + +# Model parameters +source model_params.sh +MODEL_PARAM=("${PARAM_425M[@]}") +NHIDDEN=${MODEL_PARAM[0]} +FFN_HIDDEN_SIZE=${MODEL_PARAM[1]} +KV_SIZE=${MODEL_PARAM[2]} +NHEADS=${MODEL_PARAM[3]} +NLAYERS=${MODEL_PARAM[4]} +SEQ_LEN=2048 + +echo "Model parameters: d_model $NHIDDEN ffw_size $FFN_HIDDEN_SIZE kv_size $KV_SIZE n_heads $NHEADS n_layers $NLAYERS" + +SAVE_INTERVAL=1000 + +# Tokens: 3936562000 +# -> Samples: 1_922_149 +TRAIN_SAMPLES=1_922_149 + +OPTIMIZER_ARGS=" \ + --optimizer adam \ + --adam-beta1 0.9 \ + --adam-beta2 0.999 \ + --adam-eps 1e-8 \ + --lr 2e-4 \ + --min-lr 2e-5 \ + --lr-decay-style cosine \ + --lr-decay-samples $TRAIN_SAMPLES \ + --lr-warmup-samples 19_221 \ + --clip-grad 1.0 \ + --weight-decay 1e-1 \ + " + +GPT_ARGS=" \ + --num-layers $NLAYERS \ + --hidden-size $NHIDDEN \ + --num-attention-heads $NHEADS \ + --kv-channels $KV_SIZE \ + --ffn-hidden-size $FFN_HIDDEN_SIZE \ + --seq-length $SEQ_LEN \ + --max-position-embeddings $SEQ_LEN \ + --micro-batch-size $MICRO_BATCH_SIZE \ + --global-batch-size $GLOBAL_BATCH_SIZE \ + --train-samples $TRAIN_SAMPLES \ + --vocab-file $VOCAB_FILE \ + --merge-file $MERGE_FILE \ + --clip-grad 1.0 \ + --kill-switch-path $KILL_SWITCH_PATH \ + --bf16 \ + $OPTIMIZER_ARGS \ + " + +OUTPUT_ARGS=" \ + --log-interval 10 \ + --save-interval $SAVE_INTERVAL \ + --eval-interval 1000 \ + --eval-iters 1 \ + --tensorboard-dir $TENSORBOARD_PATH \ + --tensorboard-queue-size 5 \ + --log-timers-to-tensorboard \ + --log-batch-size-to-tensorboard \ + --log-validation-ppl-to-tensorboard \ + " + +ZERO_STAGE=0 + +mkdir -p ds_configs +DS_CONFIG_PATH="ds_configs/$SLURM_JOB_ID.json" + +cat < $DS_CONFIG_PATH +{ + "train_micro_batch_size_per_gpu": $MICRO_BATCH_SIZE, + "train_batch_size": $GLOBAL_BATCH_SIZE, + "gradient_clipping": 1.0, + "zero_optimization": { + "stage": $ZERO_STAGE + }, + "bf16": { + "enabled": true + }, + "steps_per_print": 2000, + "wall_clock_breakdown": false +} +EOF + +DEEPSPEED_ARGS=" \ + --deepspeed \ + --deepspeed_config $DS_CONFIG_PATH \ + --zero-stage $ZERO_STAGE \ + " + +CMD=" \ + Megatron-DeepSpeed/pretrain_gpt.py \ + --tensor-model-parallel-size $TP_SIZE \ + --pipeline-model-parallel-size $PP_SIZE \ + $GPT_ARGS \ + $OUTPUT_ARGS \ + --save $CHECKPOINT_PATH \ + --load $CHECKPOINT_PATH \ + --data-path $DATA_PATH \ + --data-impl mmap \ + --split 949,50,1 \ + $DEEPSPEED_ARGS \ + " + +echo $CMD + +echo "START $SLURM_JOBID: $(date)" + +# bash launch_srun.sh $CMD +srun --label launch.sh $CMD + +echo "END $SLURM_JOBID: $(date)" diff --git a/421m3b93b9/tensorboard/events.out.tfevents.1669733585.nid007493.11948.0 b/421m3b93b9/tensorboard/events.out.tfevents.1669733585.nid007493.11948.0 new file mode 100644 index 0000000000000000000000000000000000000000..a280e34293bba54201937ef9a5390d8227521145 --- /dev/null +++ b/421m3b93b9/tensorboard/events.out.tfevents.1669733585.nid007493.11948.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11f5e218b0bccdfd6296dadece304220913959ba0b2a67e317e3d17cbba0a99a +size 13359421 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e6d5efce75b29e3ef8e42ec51b1916699adbe06f --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65ccedf4272cf1d5f7e762407c16568de0562d3a4066bfdce64d28251e1e1324 +size 116013719 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..864ef6584d5a7773935ae5ddaafd735f6ac12098 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3021b3812ff4dea338c17f13afce4b8022a183ef4edccfc56086c2dc91c06750 +size 116013666 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..eaa4f0d1b6b1c85abc7c4f1baffc6ab464c97e9a --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30e13a01ab1e8c9f0237347bdaefa93ce08e26421a3772a9d807cef3b0bfdfc8 +size 116013794 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6f1786941bed3eb4978957b40f3e2f0626868d54 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba595fa149f3f15735028c0e4f3ee629fec1bf1c2274daf3b0f13c79cc2f8220 +size 116013602 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..712c4139078ba6d0d85ee19be74892c08df56ea0 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f15e90d9a28a417f441db233a101efe9af56992a6d08190a2436922be6faf7d +size 116013858 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4b4c1b26acc60b52acfc901baa043fb4bd2bd0f0 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41ab35d8da96ffd81e37a3d8fc3473c064f09e4e4fc79c51cf3cc0d911a47797 +size 116013730 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a31e4354ae4b32807926c7e13f9dbe0e4fa163c --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c2dc0f85ad2db1286357de3bf87fd776670e61d390cece79854c746974f81e2 +size 116013794 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fea2a194e8bee652470f4b38fd6f20c0c535738e --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ce0dbd78b1adedef7c15e29df51c709926d1eec2c3a49949a4cbebad487d5b3 +size 116013794 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1372ccf35b436626fb92e026870da829f9420f4f --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d11e9a3611f733098537eb3dee663f55019f4587f313c4738ccfee51489d2ee +size 116013602 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5ee1822178ccb47d0207a48e4c1fa7cd08d0df0e --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4394c406e9b87856fa8abbb5578e589211331c27c293a647759b57bc85b94eb7 +size 116013794 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..76c0728151de2cfc725c03a7fe50c37c0378be4d --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d099a8305b3e57c026a344828f5ed667b27a6ad73a2593d4a0ccbd77ababa3a +size 116013666 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..09d2f4305b42fdff2b01ec1880f572df33b4b8e6 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2978d98b56786d7a1df45ed2abeecea790b24b9fd168b7661758e0364418cbb2 +size 116013719 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..339e1904a0af270913cf7da517ed893630538b58 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dba55dc3ba851fbf6a7b9db9b5a94449cbedc107216984db4f942719cd3cef38 +size 116013794 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cd134a45207cbe9badbc5fb132dce7152e8cb54c --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d6ddaa3163c1a3499a98deac4f8bb1c61173f0c4db122404769ac6dbe59879b +size 116013794 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..aa854244252c0f434d7033b16bc2e8778e693f11 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96fd06d9ed8561f58981b8b14fcd320bb415ca4ff279bb49e6c044e042b0d68b +size 116013666 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..33e644e61f10aea98177bbc5b6d16deb64be9471 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e41db678318fb63d9f7718cba4386f582c0e4f59572efc973a629e565d6a0007 +size 116013794 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a4a39e905c7b1b23eed2a5d60882f52a0807cf54 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b79e350d7f20820c2508ce730b5321f21e522ddfb3054a44542bb885acdad51c +size 116013730 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a81cbd07ad31036b86350bd94589a90435b96795 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43dcd95c50fa1fc054f0b8dbd64df1e544c181450fed90f99f6a48bedec8d31f +size 116013730 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a4040b5cd6411ccf9cbf868dd4eba86af30e0cee --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:769cfc59719ad4536cf26a3c91cca56c87f21e70803a99bdff5030059252824f +size 116013858 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bf6f7379dd9eaa0b6a0ca16d6947135fe51ce5d4 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:957be1bbdb233b660eb8cedcf55586ba8753e2d1711573fe5ee0a4fdb6375f54 +size 116013666 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5acd11819221d949097faad1915a952e91769879 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:059f20d7df00003c0743a1908d2e34ddc34efc448faccc9bc33e2fe21d0c63f9 +size 116013794 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b99994553a9fa8a6f11ff6dad4cd68e11505df85 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:120f9080d0f4d3dca4afc9bbf6750dff21d4658fcf7d1ab384aca44eaed5738d +size 116013602 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ea9d7183bd9b358852aca928ae86437ac4e6414f --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b1d07741f7daeeaacdab40cf06d0465437afd85923d6a9417edb61c70bbbc1b +size 116013655 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8263f5db07d8dd6392727e4197012a35e0b49987 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f6b6e82449dec901bb3508b4832a2d93e38b3f0cf3fff574b140fb877cdce3d +size 116013730 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..be5ec863db0fc1f4d1e57f05c388ab90cde1c654 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6193b0ee219a7d79647ff84c8d39a5b424d209f6c7df7c7e157520e93c3e30f3 +size 116013794 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a36e0684a946c3a3a27767ecb680d5e50a27c705 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:413b7b0a385c004b90dcd94ded43355035cd96efc791f20e36fa6561009bfcdf +size 116013794 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9774e7ceb9469f662fed7fadd634ec9f0aa55573 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbce0c7e16977d30300252bb7fa27ed1df5d51251f6ff87d0f11d8286d7332ed +size 116013794 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7bdeb85110cbe1769a7cf26b430b8aabc838fd2f --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0f1ff350328057e00709701b23ae1b23cdce13b0d74d3ca57a42192060f1cc3 +size 116013730 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2e3afeb7227081d2e953e35c885501c1469ffd3e --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42d23b3aede9a36283ce49467568c7e8f1b3cbf46c62c7a215d8a32c2bc2d25d +size 116013666 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..381415927f8e4d408fdb8b844b7732c3937fb290 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a132acb98934420e28443964f38e29d8c119e1c7b9a33068769b2a67ea9441ba +size 116013666 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..376e29570c5be08b9f37e9a670b6b82f8b5e2d28 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7093917f5917f939a77f201103fc9f954ecd16453e7a25e6a9f03700cf5450c3 +size 116013858 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1f20009c82a7fc08ae900782233c2e8633f7d581 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fd3ea447b5c02b788b10e3b8b57379594c4e331109cb5289bea4551d9abd189 +size 116013794 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8c4cf992f9b8bc3d3d4a8f16adda1b8222ac3881 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60d814f456246417af7ab5c037961b66d0d22eb074f8e876a0e44b43116fc24d +size 116013730 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f27b6b8a195210a406d07b19a9b1e44840c771e8 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:486d7e5a2fe1a7d4807e0c707a7778ca4c637c3d2ed443214982614e5c74e6aa +size 116013719 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c960ca22c24ea98745fc1d14306db21684f6c13a --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd7c9249b37856904c0a64cf93b673887eede9e8e3d5dc7d42e66ac83806a1ce +size 116013666 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a3d67b2bd1d2c66156a80477a9427e4d129532f2 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9865fd0a1a067e6ee4ebb836b63d380c01c6c973c6cc55930a50f7296fda53f3 +size 116013794 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..68c0ba7a20d1b782873e25df9b81d8706fe43d3f --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61c97132798b5ec721fbebd8860fc16961b8bb90a40bbc75dafaf6c9cb88eba8 +size 116013730 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4c1c37588fa69e03ceb90446a0322b37d7d78f87 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c906ec7d4ad2e7f5b17b585ab37b3ddf94471f745e9db2f0856f22bde97cdc4d +size 116013794 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ae3bb8da59df6a29c565a6a9e9550c24e9ade159 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:187f07adc78abd816396e8d365a9f2fcb194ad63460329dc6b3d15cab36205e4 +size 116013730 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..917c31100792794b475dffb5fb26ea1e549535c2 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1454575f0feeaa51f02f9b12a59d2ceace49902ee940b8de43dfe732481942c2 +size 116013794 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8367d31b8b1d7aaaf201b0a8da0480acfb7290c0 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abf36b098838b1bd19bd84f10a9a66fc2131995cdfc01875ef1b03aeca7a581c +size 116013730 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..03c42e098e349e4880abda880949b55cebfa9a50 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6030a1e58c0e0e0c9280485ca80044e3737183dedf820b05bfd3c4e9133bb5a +size 116013666 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ae8c2f22fb60a55d59895b570b925120e114499c --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55a64706a6917293aa94117a73ee3bd2fd929f24111db1729dca50929e8a34ac +size 116013922 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..08226ef4eaea9091dab9d338438bac6ca909c3a9 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9143d3975c990488d4f913871ebf108fb9e4bcca74ea624bf0cc9ad3935fdd1b +size 116013538 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fddbb6baf6a285ce04ee08eac8c0d0a8ea8b788f --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6da7eb4183d4cf428290afcee8538fe35aa9fefb7b1e8d0b34f8253976b291ca +size 116013719 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7b463e23494b78c962f2d2381646fd06be08f0c5 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72c94cf790e94e6672cd6ccbbd87fe0475cd7ad04f30b134ddc7b1fe5fe22c5b +size 116013794 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f4956e3da434d801c4a6081ea321d5bcd4d2e643 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6adbe9e123f6db3e9fb1cc4788b8d4ef2b8dedd0af725fc3e31fd5d0925352aa +size 116013730 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e882f6f6d630eb467a482a1c0be74b512d73fd58 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf9754eac456b591729ac2bf14a0af09af68605ca1188820c0e5739290b8d79d +size 116013730 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6267d11e7870735cf0ba6b5e31e587dcab35b50a --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fda1168138d0d547094bc4ed71c6aafa72f0c6067e861a599817dbbaf02e7dc6 +size 116013922 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..237a30929d2cdf9971d37834027552f043ab1263 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f2cf261a31db0c210fdce1a9f5121dd4628f4943db9de1f361da877fba9b773 +size 116013602 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9137c76c79782892fc6fb2adcb037ca9355b3a6f --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfce4b26383d53685bbc53add9808042e67ef7698c725f416ec3692293370f41 +size 116013794 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2156d30de4c06da9d2f2f6a3b0a9361781a9c90a --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5de1c145137be8e820a08cba8b6c6a400ca321d21e442342715ac04bb64c8162 +size 116013602 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..890014de672a7dc652c9f716a81be177191a62b6 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e6a7521e843857e18c116a3d62461dfa43d42d5229e240df8a2ddd199b79a96 +size 116013794 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..44584ab4ae7fa622a50777d49ec87da9770b7224 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cac6a2b711273b81d758dbdbe3135b0342804149d41b7e6d8cb2648bf8091ada +size 116013858 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..49f77ae82013f02b56ce4cbc3af32ff73bb45992 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c71a4851a3850fefb0eb5035279407edb7c5a4d360daf9e3b2302c9825079442 +size 116013794 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..67b84997f22dd969ec443b5f74c2fe08147ef2db --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:740780e9a9ed4c0fb5f465d172fad806e319920e7f13ed7377fe203d3223c094 +size 116013655 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4d0c70271334bdcb8b8c070695da99a29a0883f3 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:271c01dec76bfd6a4cb1037dc601d56d5b0c54942f680e11f828d78b8a54f591 +size 116013730 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7311c770a2b63cb0608835698f8ec6e194f0531c --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ae6c7cd249bc9b93fcb6888cbde1db0da966d3006186db1aaa69d17d6ab14f9 +size 116013794 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..00acd0345738a2759dc7ce4fe13d98a7b890a94d --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b46922a4d52ed143a47cf2b9b169bee3539d9b8499739b7628c67f20bcc6d73a +size 116013666 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..099f586ecca45b66f603b8c612bf4057eadd2ae5 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ef6f808d26f67c824f81d7caa66d972d9daf39097f9486237e33d4279158239 +size 116013666 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e3fb48f03ee55c89dbc83c8d5d74d3dd3d96b228 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8b9605c7d8786f0758608d12e6309478759db7c1c5d6ffa53cdd13bb6269d95 +size 116013719 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..77cd014b912ef9cdfe05ed5c4fb15bb385d21fda --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93cba0d86d90c2c738b6138e3199e82dab518f461df870ef25f79a8b117a081d +size 116013719 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6c630e6fa3787d533815664caca091770b69996c --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e170bab0b5b339f3ac91b72d5793ebe01ae06b124b362538286a0d3affdeb5c9 +size 116013655 diff --git a/619m2b72b7/global_step5111/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt b/619m2b72b7/global_step5111/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..978d9ff5ea652412f20523899b200d6da5ab2499 --- /dev/null +++ b/619m2b72b7/global_step5111/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8801a36974a524b856feafba32fc0a98ffaa6d2d63c419e40ab8c4213e92e3cd +size 116013591 diff --git a/619m2b72b7/global_step5111/layer_01-model_00-model_states.pt b/619m2b72b7/global_step5111/layer_01-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4269dd847b99f1da71d1d59dff945d3d8db56db6 --- /dev/null +++ b/619m2b72b7/global_step5111/layer_01-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:046cbe53d93b41ed5ab5d3a8682bf6268014b08eb121e77b662d0f708f0b70a1 +size 160826627 diff --git a/619m2b72b7/global_step5111/layer_03-model_00-model_states.pt b/619m2b72b7/global_step5111/layer_03-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..feec185f04260111640aaa0d9b43df9b5297c6ad --- /dev/null +++ b/619m2b72b7/global_step5111/layer_03-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eeb8ad5aa064092d029215570c7953cc95a151d28b31a8e3505a823c7080c58 +size 56667395 diff --git a/619m2b72b7/global_step5111/layer_04-model_00-model_states.pt b/619m2b72b7/global_step5111/layer_04-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5588f65494983e11e4a024179dfe725ce7255bbf --- /dev/null +++ b/619m2b72b7/global_step5111/layer_04-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94d4a6c0e4eccc12d413bae82697b0b6f293f5639baedf1c474c6f3d042ac8ce +size 56667395 diff --git a/619m2b72b7/global_step5111/layer_05-model_00-model_states.pt b/619m2b72b7/global_step5111/layer_05-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..70a7126ec5a706debde2bfb3f03a48fe75de54cd --- /dev/null +++ b/619m2b72b7/global_step5111/layer_05-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f15b252b83e65a48c350f1d843d4136b0327fb302044467ca20ccc16530a2a5 +size 56667395 diff --git a/619m2b72b7/global_step5111/layer_06-model_00-model_states.pt b/619m2b72b7/global_step5111/layer_06-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8c480609cefb52ea2051b2d4419e8d23e2996a10 --- /dev/null +++ b/619m2b72b7/global_step5111/layer_06-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3394b68e8866841a7abeefa62c2f6bac75c545d303a58b75467da74a32a95922 +size 56667395 diff --git a/619m2b72b7/global_step5111/layer_07-model_00-model_states.pt b/619m2b72b7/global_step5111/layer_07-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..85b859aba99d841b5cd3acbac013c583125fb377 --- /dev/null +++ b/619m2b72b7/global_step5111/layer_07-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:993652a97dfcc67ca1e45618844d5756bbd11037b28a35a9181c53cae81773d6 +size 56667395 diff --git a/619m2b72b7/global_step5111/layer_08-model_00-model_states.pt b/619m2b72b7/global_step5111/layer_08-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e2f21c0ca231d47379f6f89fadcb000faf0c09a0 --- /dev/null +++ b/619m2b72b7/global_step5111/layer_08-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd326a46bf6913bfa8e1431e9ef071067c34ed8fc4bb693ed6511b0988a925dd +size 56667395 diff --git a/619m2b72b7/global_step5111/layer_09-model_00-model_states.pt b/619m2b72b7/global_step5111/layer_09-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..53e6efcb22bf97413da681ef1c81adb20073df58 --- /dev/null +++ b/619m2b72b7/global_step5111/layer_09-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9e9d648867d7416beaf1afe046e02661759aaa736a3d01f38de02c24e1568f7 +size 56667395 diff --git a/619m2b72b7/global_step5111/layer_10-model_00-model_states.pt b/619m2b72b7/global_step5111/layer_10-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a9fb5d55a2287f846196910ddbfd108184b5bdbf --- /dev/null +++ b/619m2b72b7/global_step5111/layer_10-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c1202e949fd7a554e622cc854b2f7546b80200f12f9e36f655b282ccfe33588 +size 56667395 diff --git a/619m2b72b7/global_step5111/layer_11-model_00-model_states.pt b/619m2b72b7/global_step5111/layer_11-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..05ae2c38f933c8822db8c645f97412971be492f3 --- /dev/null +++ b/619m2b72b7/global_step5111/layer_11-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1143bad670be246f2961f8a7bcea068297f04b2470fc2b3d39d8dda07cf06da +size 56667395 diff --git a/619m2b72b7/global_step5111/layer_12-model_00-model_states.pt b/619m2b72b7/global_step5111/layer_12-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c0171708a67b5caf76a720c166bef26199e2e90b --- /dev/null +++ b/619m2b72b7/global_step5111/layer_12-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32fb020a92b63a79d06444654b0b785ba96b3d6db6f5d252a690833ee46363c0 +size 56667395 diff --git a/619m2b72b7/global_step5111/layer_13-model_00-model_states.pt b/619m2b72b7/global_step5111/layer_13-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c6ba44e48fbd9e07d88d52530034778e40c92c99 --- /dev/null +++ b/619m2b72b7/global_step5111/layer_13-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:501aed19b4c0f87f0dfb17022b08ce89cd1417680097b6a0e88186acf836b52f +size 56667395 diff --git a/619m2b72b7/global_step5111/layer_14-model_00-model_states.pt b/619m2b72b7/global_step5111/layer_14-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7f88afd6e8cbbd4dac4f1f9f52905ece82f5ee18 --- /dev/null +++ b/619m2b72b7/global_step5111/layer_14-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd56816b14d79b8e765fb50e11e1432d823488e67929b0ae877708b6b5d44c57 +size 56667395 diff --git a/619m2b72b7/global_step5111/layer_15-model_00-model_states.pt b/619m2b72b7/global_step5111/layer_15-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8ea436d1ff844c06ef2843f03d626b7ce8251c7e --- /dev/null +++ b/619m2b72b7/global_step5111/layer_15-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3bccad25baba60082b5b81f7d2b41c352d7acb306326b819c6535f934ec3bd7 +size 56667395 diff --git a/619m2b72b7/global_step5111/layer_16-model_00-model_states.pt b/619m2b72b7/global_step5111/layer_16-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..614e368dd7d27927a88957c12de656e9ce57686d --- /dev/null +++ b/619m2b72b7/global_step5111/layer_16-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:820c96b75abb279039401087a8b8a29a2bdd15f7b31c4a40006686804d83dea9 +size 56667395 diff --git a/619m2b72b7/global_step5111/layer_17-model_00-model_states.pt b/619m2b72b7/global_step5111/layer_17-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5a40d2462d87a3e8d1e6b5437144b1381637f0f2 --- /dev/null +++ b/619m2b72b7/global_step5111/layer_17-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dc125da0a5a8b6eef61b2af7ad58e951194711740c025bfc32971a9271d6778 +size 56667395 diff --git a/619m2b72b7/global_step5111/layer_18-model_00-model_states.pt b/619m2b72b7/global_step5111/layer_18-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ffbe3dcea9f4efc07d7898bdb6a9d72ee8ef4161 --- /dev/null +++ b/619m2b72b7/global_step5111/layer_18-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f8730e5bb54df5ed9b7ef1f1d9c3e0012d064e26d5b9f701eac32363416f8f9 +size 56667395 diff --git a/619m2b72b7/global_step5111/layer_19-model_00-model_states.pt b/619m2b72b7/global_step5111/layer_19-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0cbac190dde06ccbadca240503cf51e864cd9fa6 --- /dev/null +++ b/619m2b72b7/global_step5111/layer_19-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4b613d6a0b4c75c4b65ac4de4c974f022a77c9b24421982caf4880be89a727e +size 56667395 diff --git a/619m2b72b7/global_step5111/layer_20-model_00-model_states.pt b/619m2b72b7/global_step5111/layer_20-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6bcec2d4103ac847d0719d8884542edec4c4f456 --- /dev/null +++ b/619m2b72b7/global_step5111/layer_20-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fb5eeb1198700cf33e3a780fa90a89407af933edc3da757364905f036d3bd40 +size 56667395 diff --git a/619m2b72b7/global_step5111/layer_21-model_00-model_states.pt b/619m2b72b7/global_step5111/layer_21-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6b0e3743b746b981183b32d3ca08104ae8f27544 --- /dev/null +++ b/619m2b72b7/global_step5111/layer_21-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2922eff5238b20a45eae310a180b2fb4c4ab5021963e761d389a67ba7cd53de9 +size 56667395 diff --git a/619m2b72b7/global_step5111/layer_23-model_00-model_states.pt b/619m2b72b7/global_step5111/layer_23-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2c600f03d19f650d8223ea12351d38f0021e6695 --- /dev/null +++ b/619m2b72b7/global_step5111/layer_23-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:301333580a1ba1f552d8cefed44e74f25a715d4e7451926bfbffb7f9b31c42d9 +size 7363 diff --git a/619m2b72b7/global_step5111/mp_rank_00_model_states.pt b/619m2b72b7/global_step5111/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0058acedb18e52b105321a966fd5b991a1e61f77 --- /dev/null +++ b/619m2b72b7/global_step5111/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6be4bb72b88df366b261587b78e6d8eae1e6aa7b035dcd02c8725ad6a535b838 +size 38195 diff --git a/619m2b72b7/launch.sh b/619m2b72b7/launch.sh new file mode 100755 index 0000000000000000000000000000000000000000..6c3445845a5dae614feb4b8a1206322cd7bd9050 --- /dev/null +++ b/619m2b72b7/launch.sh @@ -0,0 +1,53 @@ +#!/bin/bash + +# Launch script using torch.distributed.run(). Used by slurm +# scripts, don't invoke directly. + +# Samuel's fix for apparent error in SLURM initialization +if [ $SLURM_LOCALID -eq 0 ]; then + rm -rf /dev/shm/* + rocm-smi || true +else + sleep 2 +fi + +export NCCL_SOCKET_IFNAME=hsn0,hsn1,hsn2,hsn3 +export OMP_NUM_THREADS=$SLURM_CPUS_PER_TASK +export FI_CXI_DEFAULT_CQ_SIZE=131072 + +# debugging (noisy) +#export NCCL_DEBUG=INFO +#export RCCL_KERNEL_COLL_TRACE_ENABLE=1 +#export NCCL_DEBUG_SUBSYS=INIT,COLL + +module --quiet purge +module load cray-python + +module load CrayEnv +module load PrgEnv-cray/8.3.3 +module load craype-accel-amd-gfx90a +module load cray-python + +module use /pfs/lustrep2/projappl/project_462000125/samantao-public/mymodules +module load suse-repo-deps/sam-default +module load rocm/sam-5.2.3.lua +module load rccl/sam-develop.lua +module load aws-ofi-rccl/sam-default.lua + +source venv/bin/activate + +MASTER_NODE=$(scontrol show hostnames "$SLURM_JOB_NODELIST" | head -n 1) +MASTER_PORT=9999 + +echo "Launching on $SLURMD_NODENAME ($SLURM_PROCID/$SLURM_JOB_NUM_NODES)," \ + "master $MASTER_NODE port $MASTER_PORT," \ + "GPUs $SLURM_GPUS_ON_NODE," \ + "CUDA: $(python -c 'import torch; print(torch.cuda.is_available())')" + +python -u -m torch.distributed.run \ + --nnodes $SLURM_JOB_NUM_NODES \ + --nproc_per_node $SLURM_GPUS_ON_NODE \ + --node_rank=$SLURM_PROCID \ + --master_addr $MASTER_NODE \ + --master_port $MASTER_PORT \ + "$@" diff --git a/619m2b72b7/logs/2085652.err b/619m2b72b7/logs/2085652.err new file mode 100644 index 0000000000000000000000000000000000000000..07e9c42c629b1ec52bf8f87e3c261705fe126ff9 --- /dev/null +++ b/619m2b72b7/logs/2085652.err @@ -0,0 +1,486 @@ +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module scaled_upper_triang_masked_softmax_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module scaled_upper_triang_masked_softmax_cuda... +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module scaled_masked_softmax_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module scaled_masked_softmax_cuda... +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module fused_mix_prec_layer_norm_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module fused_mix_prec_layer_norm_cuda... +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +7: Successfully preprocessed all matching files. +7: Successfully preprocessed all matching files. +7: Successfully preprocessed all matching files. +7: Successfully preprocessed all matching files. +5: Successfully preprocessed all matching files. +6: Successfully preprocessed all matching files. +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja... +0: Building extension module utils... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module utils... +0: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: +1: +1: +1: +1: +1: +1: +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: +2: +2: +2: +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: +6: +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: +4: +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: +4: +4: +4: +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja... +0: Building extension module utils... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Loading extension module utils... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +3: Loading extension module utils... +3: Loading extension module utils... +3: Loading extension module utils... +1: Loading extension module utils... +3: Loading extension module utils... +3: Loading extension module utils... +2: Loading extension module utils... +3: Loading extension module utils... +2: Loading extension module utils... +6: Loading extension module utils... +3: Loading extension module utils... +7: Loading extension module utils... +1: Loading extension module utils... +6: Loading extension module utils... +2: Loading extension module utils... +0: Loading extension module utils... +6: Loading extension module utils... +7: Loading extension module utils... +1: Loading extension module utils... +2: Loading extension module utils... +6: Loading extension module utils... +7: Loading extension module utils... +2: Loading extension module utils... +3: Loading extension module utils... +2: Loading extension module utils... +1: Loading extension module utils... +6: Loading extension module utils... +0: Loading extension module utils... +7: Loading extension module utils... +0: Loading extension module utils...Loading extension module utils... +0: +2: Loading extension module utils... +1: Loading extension module utils... +6: Loading extension module utils... +2: Loading extension module utils... +1: Loading extension module utils... +6: Loading extension module utils... +7: Loading extension module utils... +1: Loading extension module utils... +6: Loading extension module utils... +7: Loading extension module utils... +1: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +1: +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: No modifications detected for re-loaded extension module utils, skipping build step... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Loading extension module utils... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +7: +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +6: +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: +4: +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +3: +3: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/utils.py:349: UserWarning: Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings +0: warnings.warn("Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings") diff --git a/619m2b72b7/logs/2085652.out b/619m2b72b7/logs/2085652.out new file mode 100644 index 0000000000000000000000000000000000000000..7a3d2ee180daa6a8cfe6693d4df2b0503582af20 --- /dev/null +++ b/619m2b72b7/logs/2085652.out @@ -0,0 +1,3249 @@ +Model parameters: d_model 1536 ffw_size 6144 kv_size 128 n_heads 12 n_layers 19 +Megatron-DeepSpeed/pretrain_gpt.py --tensor-model-parallel-size 1 --pipeline-model-parallel-size 1 --num-layers 19 --hidden-size 1536 --num-attention-heads 12 --kv-channels 128 --ffn-hidden-size 6144 --seq-length 2048 --max-position-embeddings 2048 --micro-batch-size 4 --global-batch-size 256 --train-samples 1_308_594 --vocab-file gpt2/vocab.json --merge-file gpt2/merges.txt --clip-grad 1.0 --kill-switch-path kill-switch-619moscar --bf16 --optimizer adam --adam-beta1 0.9 --adam-beta2 0.999 --adam-eps 1e-8 --lr 2e-4 --min-lr 2e-5 --lr-decay-style cosine --lr-decay-samples 1_308_594 --lr-warmup-samples 13_086 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_619moscar --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_619moscar --load checkpoints_619moscar --data-path /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2085652.json --zero-stage 0 +START 2085652: Tue Nov 29 17:02:55 EET 2022 +0: +0: +0: ======================= ROCm System Management Interface ======================= +0: ================================= Concise Info ================================= +0: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +0: 0 45.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 2 43.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 4 40.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 5 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 6 43.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: ================================================================================ +0: ============================= End of ROCm SMI Log ============================== +6: +6: +6: ======================= ROCm System Management Interface ======================= +6: ================================= Concise Info ================================= +6: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +6: 0 47.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 2 44.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 4 44.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 6 43.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: ================================================================================ +6: ============================= End of ROCm SMI Log ============================== +3: +3: +3: ======================= ROCm System Management Interface ======================= +3: ================================= Concise Info ================================= +3: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +3: 0 45.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 2 40.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 3 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 4 41.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 6 40.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: ================================================================================ +3: ============================= End of ROCm SMI Log ============================== +4: +4: +4: ======================= ROCm System Management Interface ======================= +4: ================================= Concise Info ================================= +4: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +4: 0 48.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 2 43.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 3 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 4 41.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 6 41.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: ================================================================================ +4: ============================= End of ROCm SMI Log ============================== +7: +7: +7: ======================= ROCm System Management Interface ======================= +7: ================================= Concise Info ================================= +7: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +7: 0 48.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 2 42.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 4 45.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 6 41.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: ================================================================================ +7: ============================= End of ROCm SMI Log ============================== +1: +1: +1: ======================= ROCm System Management Interface ======================= +1: ================================= Concise Info ================================= +1: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +1: 0 39.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 2 42.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 4 43.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 6 43.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: ================================================================================ +1: ============================= End of ROCm SMI Log ============================== +2: +2: +2: ======================= ROCm System Management Interface ======================= +2: ================================= Concise Info ================================= +2: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +2: 0 38.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 2 42.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 4 45.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 6 41.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: ================================================================================ +2: ============================= End of ROCm SMI Log ============================== +5: +5: +5: ======================= ROCm System Management Interface ======================= +5: ================================= Concise Info ================================= +5: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +5: 0 44.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 2 41.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 4 46.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 6 43.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: ================================================================================ +5: ============================= End of ROCm SMI Log ============================== +5: Launching on nid005057 (5/8), master nid005052 port 9999, GPUs 8, CUDA: True +6: Launching on nid005058 (6/8), master nid005052 port 9999, GPUs 8, CUDA: True +1: Launching on nid005053 (1/8), master nid005052 port 9999, GPUs 8, CUDA: True +2: Launching on nid005054 (2/8), master nid005052 port 9999, GPUs 8, CUDA: True +3: Launching on nid005055 (3/8), master nid005052 port 9999, GPUs 8, CUDA: True +0: Launching on nid005052 (0/8), master nid005052 port 9999, GPUs 8, CUDA: True +4: Launching on nid005056 (4/8), master nid005052 port 9999, GPUs 8, CUDA: True +7: Launching on nid005059 (7/8), master nid005052 port 9999, GPUs 8, CUDA: True +0: using world size: 64, data-parallel-size: 64, tensor-model-parallel size: 1, pipeline-model-parallel size: 1 +0: accumulate and all-reduce gradients in fp32 for bfloat16 data type. +0: using torch.bfloat16 for parameters ... +0: ------------------------ arguments ------------------------ +0: abort_on_unmet_fused_kernel_constraints ......... False +0: accumulate_allreduce_grads_in_fp32 .............. True +0: adam_beta1 ...................................... 0.9 +0: adam_beta2 ...................................... 0.999 +0: adam_eps ........................................ 1e-08 +0: adlr_autoresume ................................. False +0: adlr_autoresume_interval ........................ 1000 +0: apply_query_key_layer_scaling ................... True +0: apply_residual_connection_post_layernorm ........ False +0: attention_dropout ............................... 0.1 +0: attention_softmax_in_fp32 ....................... False +0: bert_binary_head ................................ True +0: bert_load ....................................... None +0: bf16 ............................................ True +0: bias_dropout_fusion ............................. True +0: bias_gelu_fusion ................................ True +0: biencoder_projection_dim ........................ 0 +0: biencoder_shared_query_context_model ............ False +0: block_data_path ................................. None +0: checkpoint_activations .......................... False +0: checkpoint_in_cpu ............................... False +0: checkpoint_num_layers ........................... 1 +0: clip_grad ....................................... 1.0 +0: codecarbon_dir .................................. None +0: consumed_train_samples .......................... 0 +0: consumed_train_tokens ........................... 0 +0: consumed_valid_samples .......................... 0 +0: contigious_checkpointing ........................ False +0: cpu_optimizer ................................... False +0: cpu_torch_adam .................................. False +0: curriculum_learning ............................. False +0: data_impl ....................................... mmap +0: data_parallel_size .............................. 64 +0: data_path ....................................... ['/scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document'] +0: dataloader_type ................................. single +0: DDP_impl ........................................ local +0: decoder_seq_length .............................. None +0: deepscale ....................................... False +0: deepscale_config ................................ None +0: deepspeed ....................................... True +0: deepspeed_activation_checkpointing .............. False +0: deepspeed_config ................................ ds_configs/2085652.json +0: deepspeed_mpi ................................... False +0: distribute_checkpointed_activations ............. False +0: distributed_backend ............................. nccl +0: embed_layernorm ................................. False +0: embedding_path .................................. None +0: encoder_seq_length .............................. 2048 +0: eod_mask_loss ................................... False +0: eval_interval ................................... 1000 +0: eval_iters ...................................... 1 +0: eval_only ....................................... None +0: evidence_data_path .............................. None +0: exit_duration_in_mins ........................... None +0: exit_interval ................................... None +0: ffn_hidden_size ................................. 6144 +0: finetune ........................................ False +0: fp16 ............................................ False +0: fp16_lm_cross_entropy ........................... False +0: fp32_residual_connection ........................ False +0: gigaflos_no_embeds .............................. 0 +0: global_batch_size ............................... 256 +0: glu_activation .................................. None +0: hidden_dropout .................................. 0.1 +0: hidden_size ..................................... 1536 +0: hysteresis ...................................... 2 +0: ict_head_size ................................... None +0: ict_load ........................................ None +0: img_dim ......................................... 224 +0: indexer_batch_size .............................. 128 +0: indexer_log_interval ............................ 1000 +0: inference ....................................... False +0: init_method_std ................................. 0.02 +0: init_method_xavier_uniform ...................... False +0: initial_loss_scale .............................. 4294967296 +0: kill_switch_path ................................ kill-switch-619moscar +0: kv_channels ..................................... 128 +0: layer_norm_fusion ............................... True +0: layernorm_epsilon ............................... 1e-05 +0: lazy_mpu_init ................................... None +0: load ............................................ checkpoints_619moscar +0: local_rank ...................................... None +0: log_batch_size_to_tensorboard ................... True +0: log_interval .................................... 10 +0: log_learning_rate_to_tensorboard ................ True +0: log_level ....................................... None +0: log_level_replica ............................... None +0: log_loss_scale_to_tensorboard ................... True +0: log_num_zeros_in_grad ........................... False +0: log_params_norm ................................. False +0: log_path ........................................ None +0: log_timers_to_tensorboard ....................... True +0: log_validation_ppl_to_tensorboard ............... True +0: loss_on_targets_only ............................ False +0: loss_scale ...................................... None +0: loss_scale_window ............................... 1000 +0: lr .............................................. 0.0002 +0: lr_decay_iters .................................. None +0: lr_decay_samples ................................ 1308594 +0: lr_decay_style .................................. cosine +0: lr_decay_tokens ................................. None +0: lr_warmup_fraction .............................. None +0: lr_warmup_iters ................................. 0 +0: lr_warmup_samples ............................... 13086 +0: make_vocab_size_divisible_by .................... 128 +0: mask_prob ....................................... 0.15 +0: masked_softmax_fusion ........................... True +0: max_position_embeddings ......................... 2048 +0: mean_noise_span_length .......................... None +0: memory_centric_tiled_linear ..................... False +0: merge_file ...................................... gpt2/merges.txt +0: micro_batch_size ................................ 4 +0: min_loss_scale .................................. 1.0 +0: min_lr .......................................... 2e-05 +0: mmap_warmup ..................................... False +0: no_load_optim ................................... None +0: no_load_rng ..................................... None +0: no_save_optim ................................... None +0: no_save_rng ..................................... None +0: noise_density ................................... None +0: num_attention_heads ............................. 12 +0: num_channels .................................... 3 +0: num_classes ..................................... 1000 +0: num_layers ...................................... 19 +0: num_layers_per_virtual_pipeline_stage ........... None +0: num_workers ..................................... 2 +0: onnx_safe ....................................... None +0: openai_gelu ..................................... False +0: optimizer ....................................... adam +0: optimizer_fusion ................................ True +0: override_lr_scheduler ........................... False +0: pad_vocab_size_to ............................... None +0: params_dtype .................................... torch.bfloat16 +0: partition_activations ........................... False +0: patch_dim ....................................... 16 +0: pipeline_model_parallel_size .................... 1 +0: position_embedding_type ......................... PositionEmbeddingType.absolute +0: pp_partition_method ............................. None +0: profile_backward ................................ False +0: query_in_block_prob ............................. 0.1 +0: rampup_batch_size ............................... None +0: rank ............................................ 0 +0: remote_device ................................... none +0: reset_attention_mask ............................ False +0: reset_position_ids .............................. False +0: retriever_report_topk_accuracies ................ [] +0: retriever_score_scaling ......................... False +0: retriever_seq_length ............................ 256 +0: reweight_loss_based_on_position_frequency ....... False +0: sample_rate ..................................... 1.0 +0: save ............................................ checkpoints_619moscar +0: save_interval ................................... 1000 +0: scatter_gather_tensors_in_pipeline .............. True +0: scattered_embeddings ............................ False +0: seed ............................................ 1234 +0: seq_length ...................................... 2048 +0: sgd_momentum .................................... 0.9 +0: short_seq_prob .................................. 0.1 +0: skip_train_iteration_range ...................... None +0: split ........................................... 949,50,1 +0: split_transformers .............................. False +0: sync_tp_duplicated_parameters ................... False +0: synchronize_each_layer .......................... False +0: tensor_model_parallel_size ...................... 1 +0: tensorboard_dir ................................. tensorboard_619moscar +0: tensorboard_log_interval ........................ 1 +0: tensorboard_queue_size .......................... 5 +0: test_weighted_split_names ....................... None +0: test_weighted_split_paths ....................... None +0: test_weighted_split_paths_path .................. None +0: test_weighted_split_splits ...................... None +0: test_weighted_split_weights ..................... None +0: tile_factor ..................................... 1 +0: titles_data_path ................................ None +0: tokenizer_name_or_path .......................... None +0: tokenizer_type .................................. GPT2BPETokenizer +0: train_iters ..................................... None +0: train_samples ................................... 1308594 +0: train_tokens .................................... None +0: train_weighted_split_paths ...................... None +0: train_weighted_split_paths_path ................. None +0: universal_checkpoint ............................ False +0: use_bnb_optimizer ............................... False +0: use_checkpoint_lr_scheduler ..................... False +0: use_contiguous_buffers_in_ddp ................... True +0: use_cpu_initialization .......................... None +0: use_one_sent_docs ............................... False +0: use_pin_memory .................................. False +0: valid_num_workers ............................... 2 +0: valid_weighted_split_names ...................... None +0: valid_weighted_split_paths ...................... None +0: valid_weighted_split_paths_path ................. None +0: valid_weighted_split_splits ..................... None +0: valid_weighted_split_weights .................... None +0: virtual_pipeline_model_parallel_size ............ None +0: vocab_extra_ids ................................. 0 +0: vocab_file ...................................... gpt2/vocab.json +0: weight_decay .................................... 0.1 +0: world_size ...................................... 64 +0: zero_allgather_bucket_size ...................... 0.0 +0: zero_contigious_gradients ....................... False +0: zero_reduce_bucket_size ......................... 0.0 +0: zero_reduce_scatter ............................. False +0: zero_stage ...................................... 0 +0: -------------------- end of arguments --------------------- +0: setting number of micro-batches to constant 1 +0: > building GPT2BPETokenizer tokenizer ... +0: > padded vocab (size: 50257) with 47 dummy tokens (new size: 50304) +0: DeepSpeed general environment info: +0: torch install path ............... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch'] +0: torch version .................... 1.13.0+rocm5.2 +0: torch cuda version ............... None +0: torch hip version ................ 5.2.21151-afdc89f8 +0: nvcc version ..................... None +0: deepspeed install path ........... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed'] +0: deepspeed info ................... 0.7.5, unknown, unknown +0: deepspeed wheel compiled w. ...... torch 1.13, hip 5.1 +0: **** Git info for Megatron: git_hash=unknown git_branch=unknown **** +0: > initializing torch distributed ... +0: [2022-11-29 17:04:44,640] [INFO] [comm.py:633:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +7: > setting tensorboard ... +0: > initializing tensor model parallel with size 1 +0: > initializing pipeline model parallel with size 1 +0: > setting random seeds to 1234 ... +0: > initializing model parallel cuda seeds on global rank 0, model parallel rank 0, and data parallel rank 0 with model parallel seed: 3952 and data parallel seed: 1234 +0: > compiling dataset index builder ... +0: make: Entering directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' +0: make: Nothing to be done for 'default'. +0: make: Leaving directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' +0: >>> done with dataset index builder. Compilation time: 0.114 seconds +0: > compiling and loading fused kernels ... +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.cpp [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 87 +0: [1/1] c++ scaled_upper_triang_masked_softmax_hip.o scaled_upper_triang_masked_softmax_hip.cuda.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib -lamdhip64 -o scaled_upper_triang_masked_softmax_cuda.so +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.cpp [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 63 +0: ninja: no work to do. +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda_kernel.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_hip_kernel.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 67 +0: [1/1] c++ layer_norm_hip_kernel.cuda.o layer_norm_cuda.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib -lamdhip64 -o fused_mix_prec_layer_norm_cuda.so +0: >>> done with compiling and loading fused kernels. Compilation time: 22.814 seconds +0: time to initialize megatron (seconds): 40.414 +0: [after megatron is initialized] datetime: 2022-11-29 17:05:12 +0: building GPT model ... +0: [2022-11-29 17:05:12,467] [INFO] [utils.py:827:see_memory_usage] Before Building Model +0: [2022-11-29 17:05:12,468] [INFO] [utils.py:828:see_memory_usage] MA 0.0 GB Max_MA 0.0 GB CA 0.0 GB Max_CA 0 GB +0: [2022-11-29 17:05:12,468] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 29.98 GB, percent = 6.0% +0: SEED_LAYERS=False BASE_SEED=1234 SEED_FN=None +0: Using topology: {ProcessCoord(pipe=0, data=0, model=0): 0, ProcessCoord(pipe=0, data=1, model=0): 1, ProcessCoord(pipe=0, data=2, model=0): 2, ProcessCoord(pipe=0, data=3, model=0): 3, ProcessCoord(pipe=0, data=4, model=0): 4, ProcessCoord(pipe=0, data=5, model=0): 5, ProcessCoord(pipe=0, data=6, model=0): 6, ProcessCoord(pipe=0, data=7, model=0): 7, ProcessCoord(pipe=0, data=8, model=0): 8, ProcessCoord(pipe=0, data=9, model=0): 9, ProcessCoord(pipe=0, data=10, model=0): 10, ProcessCoord(pipe=0, data=11, model=0): 11, ProcessCoord(pipe=0, data=12, model=0): 12, ProcessCoord(pipe=0, data=13, model=0): 13, ProcessCoord(pipe=0, data=14, model=0): 14, ProcessCoord(pipe=0, data=15, model=0): 15, ProcessCoord(pipe=0, data=16, model=0): 16, ProcessCoord(pipe=0, data=17, model=0): 17, ProcessCoord(pipe=0, data=18, model=0): 18, ProcessCoord(pipe=0, data=19, model=0): 19, ProcessCoord(pipe=0, data=20, model=0): 20, ProcessCoord(pipe=0, data=21, model=0): 21, ProcessCoord(pipe=0, data=22, model=0): 22, ProcessCoord(pi +0: pe=0, data=23, model=0): 23, ProcessCoord(pipe=0, data=24, model=0): 24, ProcessCoord(pipe=0, data=25, model=0): 25, ProcessCoord(pipe=0, data=26, model=0): 26, ProcessCoord(pipe=0, data=27, model=0): 27, ProcessCoord(pipe=0, data=28, model=0): 28, ProcessCoord(pipe=0, data=29, model=0): 29, ProcessCoord(pipe=0, data=30, model=0): 30, ProcessCoord(pipe=0, data=31, model=0): 31, ProcessCoord(pipe=0, data=32, model=0): 32, ProcessCoord(pipe=0, data=33, model=0): 33, ProcessCoord(pipe=0, data=34, model=0): 34, ProcessCoord(pipe=0, data=35, model=0): 35, ProcessCoord(pipe=0, data=36, model=0): 36, ProcessCoord(pipe=0, data=37, model=0): 37, ProcessCoord(pipe=0, data=38, model=0): 38, ProcessCoord(pipe=0, data=39, model=0): 39, ProcessCoord(pipe=0, data=40, model=0): 40, ProcessCoord(pipe=0, data=41, model=0): 41, ProcessCoord(pipe=0, data=42, model=0): 42, ProcessCoord(pipe=0, data=43, model=0): 43, ProcessCoord(pipe=0, data=44, model=0): 44, ProcessCoord(pipe=0, data=45, model=0): 45, ProcessCoord(pipe=0, data=4 +0: 6, model=0): 46, ProcessCoord(pipe=0, data=47, model=0): 47, ProcessCoord(pipe=0, data=48, model=0): 48, ProcessCoord(pipe=0, data=49, model=0): 49, ProcessCoord(pipe=0, data=50, model=0): 50, ProcessCoord(pipe=0, data=51, model=0): 51, ProcessCoord(pipe=0, data=52, model=0): 52, ProcessCoord(pipe=0, data=53, model=0): 53, ProcessCoord(pipe=0, data=54, model=0): 54, ProcessCoord(pipe=0, data=55, model=0): 55, ProcessCoord(pipe=0, data=56, model=0): 56, ProcessCoord(pipe=0, data=57, model=0): 57, ProcessCoord(pipe=0, data=58, model=0): 58, ProcessCoord(pipe=0, data=59, model=0): 59, ProcessCoord(pipe=0, data=60, model=0): 60, ProcessCoord(pipe=0, data=61, model=0): 61, ProcessCoord(pipe=0, data=62, model=0): 62, ProcessCoord(pipe=0, data=63, model=0): 63} +0: [2022-11-29 17:05:14,473] [INFO] [module.py:366:_partition_layers] Partitioning pipeline stages with method type:transformer +0: stage=0 layers=26 +0: 0: _to_float16 +0: 1: EmbeddingPipe +0: 2: +0: 3: ParallelTransformerLayerPipe +0: 4: ParallelTransformerLayerPipe +0: 5: ParallelTransformerLayerPipe +0: 6: ParallelTransformerLayerPipe +0: 7: ParallelTransformerLayerPipe +0: 8: ParallelTransformerLayerPipe +0: 9: ParallelTransformerLayerPipe +0: 10: ParallelTransformerLayerPipe +0: 11: ParallelTransformerLayerPipe +0: 12: ParallelTransformerLayerPipe +0: 13: ParallelTransformerLayerPipe +0: 14: ParallelTransformerLayerPipe +0: 15: ParallelTransformerLayerPipe +0: 16: ParallelTransformerLayerPipe +0: 17: ParallelTransformerLayerPipe +0: 18: ParallelTransformerLayerPipe +0: 19: ParallelTransformerLayerPipe +0: 20: ParallelTransformerLayerPipe +0: 21: ParallelTransformerLayerPipe +0: 22: undo +0: 23: MixedFusedLayerNorm +0: 24: EmbeddingPipe +0: 25: float16_to_fp32 +0: loss: CrossEntropy +0: [2022-11-29 17:05:14,719] [INFO] [utils.py:827:see_memory_usage] After Building Model +0: [2022-11-29 17:05:14,720] [INFO] [utils.py:828:see_memory_usage] MA 1.16 GB Max_MA 1.16 GB CA 1.2 GB Max_CA 1 GB +0: [2022-11-29 17:05:14,720] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.02 GB, percent = 6.0% +0: setting training iterations to 5111 +0: > learning rate decay style: cosine +0: DeepSpeed is enabled. +0: [2022-11-29 17:05:14,721] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed info: version=0.7.5, git-hash=unknown, git-branch=unknown +0: [2022-11-29 17:05:27,107] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False +0: [2022-11-29 17:05:27,107] [INFO] [logging.py:68:log_dist] [Rank 0] Removing param_group that has no 'params' in the client Optimizer +0: [2022-11-29 17:05:27,107] [INFO] [logging.py:68:log_dist] [Rank 0] Using client Optimizer as basic optimizer +0: [2022-11-29 17:05:27,114] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Basic Optimizer = FusedAdam +0: [2022-11-29 17:05:27,114] [INFO] [logging.py:68:log_dist] [Rank 0] Creating BF16 optimizer +0: [2022-11-29 17:05:27,159] [INFO] [utils.py:827:see_memory_usage] begin bf16_optimizer +0: [2022-11-29 17:05:27,161] [INFO] [utils.py:828:see_memory_usage] MA 1.15 GB Max_MA 1.17 GB CA 1.22 GB Max_CA 1 GB +0: [2022-11-29 17:05:27,161] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.71 GB, percent = 6.1% +0: ninja: no work to do. +0: Time to load utils op: 0.23923659324645996 seconds +0: Time to load utils op: 0.2769949436187744 seconds +0: [2022-11-29 17:05:27,454] [INFO] [utils.py:827:see_memory_usage] before initializing group 0 +0: [2022-11-29 17:05:27,455] [INFO] [utils.py:828:see_memory_usage] MA 1.15 GB Max_MA 1.15 GB CA 1.22 GB Max_CA 1 GB +0: [2022-11-29 17:05:27,456] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.71 GB, percent = 6.1% +0: ninja: no work to do. +0: Time to load utils op: 0.15818262100219727 seconds +0: Time to load utils op: 0.0007307529449462891 seconds +0: Time to load utils op: 0.0005490779876708984 seconds +5: Time to load utils op: 0.4204225540161133 seconds +0: [2022-11-29 17:05:27,562] [INFO] [utils.py:827:see_memory_usage] after initializing group 0 +0: [2022-11-29 17:05:27,563] [INFO] [utils.py:828:see_memory_usage] MA 2.45 GB Max_MA 2.45 GB CA 3.13 GB Max_CA 3 GB +0: [2022-11-29 17:05:27,563] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.75 GB, percent = 6.1% +0: Time to load utils op: 0.20317506790161133 seconds +5: Time to load utils op: 0.20449018478393555 secondsTime to load utils op: 0.20424532890319824 seconds +5: +5: Time to load utils op: 0.20424318313598633 seconds +5: Time to load utils op: 0.20472264289855957 seconds +5: Time to load utils op: 0.2042849063873291 seconds +5: Time to load utils op: 0.20470809936523438 seconds +5: Time to load utils op: 0.20441603660583496 seconds +0: Time to load utils op: 0.20237493515014648 seconds +0: Time to load utils op: 0.20305705070495605 seconds +0: Time to load utils op: 0.20304298400878906 seconds +0: Time to load utils op: 0.20318913459777832 seconds +3: Time to load utils op: 0.22121047973632812 seconds +3: Time to load utils op: 0.22118306159973145 secondsTime to load utils op: 0.21889185905456543 seconds +3: +3: Time to load utils op: 0.2172684669494629 seconds +3: Time to load utils op: 0.21871089935302734 secondsTime to load utils op: 0.21891260147094727 seconds +3: +3: Time to load utils op: 0.21897554397583008 seconds +3: Time to load utils op: 0.21863412857055664 seconds +1: Time to load utils op: 0.22211670875549316 seconds +1: Time to load utils op: 0.2221219539642334 seconds +1: Time to load utils op: 0.22214698791503906 seconds +1: Time to load utils op: 0.22215938568115234 secondsTime to load utils op: 0.22216033935546875 seconds +1: +1: Time to load utils op: 0.22217822074890137 seconds +1: Time to load utils op: 0.2221841812133789 secondsTime to load utils op: 0.22218847274780273 seconds +1: +0: Time to load utils op: 0.0004937648773193359 seconds +7: Time to load utils op: 0.22124409675598145 seconds +7: Time to load utils op: 0.22247314453125 seconds +7: Time to load utils op: 0.2215743064880371 seconds +7: Time to load utils op: 0.22178053855895996 seconds +7: Time to load utils op: 0.2217094898223877 seconds +7: Time to load utils op: 0.22177338600158691 secondsTime to load utils op: 0.22238659858703613 seconds +7: +7: Time to load utils op: 0.22222185134887695 seconds +6: Time to load utils op: 0.22248578071594238 seconds +6: Time to load utils op: 0.22318553924560547 secondsTime to load utils op: 0.22334671020507812 seconds +6: +6: Time to load utils op: 0.22211813926696777 seconds +6: Time to load utils op: 0.22350549697875977 secondsTime to load utils op: 0.22212481498718262 seconds +6: +6: Time to load utils op: 0.22267889976501465 seconds +6: Time to load utils op: 0.22285723686218262 seconds +2: Time to load utils op: 0.223876953125 seconds +2: Time to load utils op: 0.2238624095916748 seconds +2: Time to load utils op: 0.2238938808441162 seconds +2: Time to load utils op: 0.2239089012145996 seconds +2: Time to load utils op: 0.22389960289001465 seconds +2: Time to load utils op: 0.22391891479492188 seconds +2: Time to load utils op: 0.22392964363098145 seconds +2: Time to load utils op: 0.22394704818725586 seconds +4: Time to load utils op: 0.22228169441223145 seconds +4: Time to load utils op: 0.2223060131072998 seconds +4: Time to load utils op: 0.22228598594665527 seconds +4: Time to load utils op: 0.22230911254882812 seconds +4: Time to load utils op: 0.22231721878051758 seconds +4: Time to load utils op: 0.2223217487335205 secondsTime to load utils op: 0.22235107421875 seconds +4: Time to load utils op: 0.22235393524169922 seconds +4: +0: Time to load utils op: 0.000408172607421875 seconds +0: Time to load utils op: 0.000431060791015625 seconds +0: Time to load utils op: 0.0005269050598144531 seconds +0: Time to load utils op: 0.0004076957702636719 seconds +0: [2022-11-29 17:05:27,604] [INFO] [utils.py:827:see_memory_usage] before initializing group 1 +0: [2022-11-29 17:05:27,605] [INFO] [utils.py:828:see_memory_usage] MA 2.45 GB Max_MA 2.45 GB CA 3.13 GB Max_CA 3 GB +0: [2022-11-29 17:05:27,605] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.76 GB, percent = 6.1% +5: Time to load utils op: 0.0004763603210449219 seconds +5: Time to load utils op: 0.00048804283142089844 seconds +5: Time to load utils op: 0.0005421638488769531 seconds +5: Time to load utils op: 0.0005602836608886719 seconds +5: Time to load utils op: 0.0005719661712646484 seconds +5: Time to load utils op: 0.0006406307220458984 seconds +5: Time to load utils op: 0.0006363391876220703 seconds +5: Time to load utils op: 0.0006296634674072266 seconds +1: Time to load utils op: 0.0009486675262451172 seconds +1: Time to load utils op: 0.0009388923645019531 seconds +1: Time to load utils op: 0.0012998580932617188 seconds +1: Time to load utils op: 0.001233816146850586 seconds +1: Time to load utils op: 0.0012042522430419922 seconds +1: Time to load utils op: 0.0011398792266845703 seconds +1: Time to load utils op: 0.0012044906616210938 seconds +1: Time to load utils op: 0.0012979507446289062 seconds +0: [2022-11-29 17:05:27,649] [INFO] [utils.py:827:see_memory_usage] after initializing group 1 +0: [2022-11-29 17:05:27,650] [INFO] [utils.py:828:see_memory_usage] MA 3.49 GB Max_MA 3.49 GB CA 4.68 GB Max_CA 5 GB +0: [2022-11-29 17:05:27,650] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.84 GB, percent = 6.1% +7: Time to load utils op: 0.0009188652038574219 seconds +7: Time to load utils op: 0.000965118408203125 seconds +7: Time to load utils op: 0.001119852066040039 seconds +7: Time to load utils op: 0.000942230224609375 seconds +7: Time to load utils op: 0.001224517822265625 seconds +7: Time to load utils op: 0.0011625289916992188 seconds +7: Time to load utils op: 0.001155853271484375 seconds +7: Time to load utils op: 0.0012578964233398438 seconds +6: Time to load utils op: 0.0009272098541259766 seconds +6: Time to load utils op: 0.0009024143218994141 seconds +6: Time to load utils op: 0.0011000633239746094 seconds +6: Time to load utils op: 0.0012493133544921875 seconds +6: Time to load utils op: 0.0013763904571533203 seconds +6: Time to load utils op: 0.0013034343719482422 seconds +6: Time to load utils op: 0.0013003349304199219 seconds +6: Time to load utils op: 0.0013685226440429688 seconds +2: Time to load utils op: 0.0008676052093505859 seconds +2: Time to load utils op: 0.0011906623840332031 seconds +2: Time to load utils op: 0.0014727115631103516 seconds +2: Time to load utils op: 0.0015339851379394531 seconds +2: Time to load utils op: 0.0013835430145263672 seconds +2: Time to load utils op: 0.0014662742614746094 secondsTime to load utils op: 0.0014259815216064453 seconds +2: +2: Time to load utils op: 0.0015251636505126953 seconds +0: [2022-11-29 17:05:27,687] [INFO] [utils.py:827:see_memory_usage] before initializing group 2 +0: [2022-11-29 17:05:27,688] [INFO] [utils.py:828:see_memory_usage] MA 3.49 GB Max_MA 3.49 GB CA 4.68 GB Max_CA 5 GB +0: [2022-11-29 17:05:27,688] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.86 GB, percent = 6.1% +4: Time to load utils op: 0.0011224746704101562 seconds +4: Time to load utils op: 0.0012004375457763672 seconds +4: Time to load utils op: 0.0012459754943847656 seconds +4: Time to load utils op: 0.001306772232055664 seconds +4: Time to load utils op: 0.001314401626586914 seconds +4: Time to load utils op: 0.0012781620025634766 seconds +4: Time to load utils op: 0.0012860298156738281 seconds +4: Time to load utils op: 0.0013110637664794922 seconds +3: Time to load utils op: 0.0004649162292480469 seconds +3: Time to load utils op: 0.00038361549377441406 seconds +3: Time to load utils op: 0.00042319297790527344 seconds +3: Time to load utils op: 0.0004131793975830078 seconds +3: Time to load utils op: 0.0004229545593261719 seconds +3: Time to load utils op: 0.0003972053527832031 seconds +3: Time to load utils op: 0.0003955364227294922 seconds +3: Time to load utils op: 0.00036454200744628906 seconds +0: [2022-11-29 17:05:27,724] [INFO] [utils.py:827:see_memory_usage] after initializing group 2 +0: [2022-11-29 17:05:27,724] [INFO] [utils.py:828:see_memory_usage] MA 3.49 GB Max_MA 3.49 GB CA 4.68 GB Max_CA 5 GB +0: [2022-11-29 17:05:27,724] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.86 GB, percent = 6.1% +0: [2022-11-29 17:05:27,756] [INFO] [utils.py:827:see_memory_usage] before initialize_optimizer +0: [2022-11-29 17:05:27,757] [INFO] [utils.py:828:see_memory_usage] MA 3.49 GB Max_MA 3.49 GB CA 4.68 GB Max_CA 5 GB +0: [2022-11-29 17:05:27,757] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.86 GB, percent = 6.1% +0: [2022-11-29 17:05:27,793] [INFO] [utils.py:827:see_memory_usage] end initialize_optimizer +0: [2022-11-29 17:05:27,794] [INFO] [utils.py:828:see_memory_usage] MA 3.57 GB Max_MA 3.57 GB CA 4.68 GB Max_CA 5 GB +0: [2022-11-29 17:05:27,794] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.86 GB, percent = 6.1% +0: [2022-11-29 17:05:27,827] [INFO] [utils.py:827:see_memory_usage] end bf16_optimizer +0: [2022-11-29 17:05:27,827] [INFO] [utils.py:828:see_memory_usage] MA 3.57 GB Max_MA 3.57 GB CA 4.68 GB Max_CA 5 GB +0: [2022-11-29 17:05:27,827] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 30.86 GB, percent = 6.1% +0: [2022-11-29 17:05:27,828] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Final Optimizer = FusedAdam +0: [2022-11-29 17:05:27,828] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed using client LR scheduler +0: [2022-11-29 17:05:27,828] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed LR Scheduler = +0: [2022-11-29 17:05:27,828] [INFO] [logging.py:68:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0, 0.0, 0.0], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +0: [2022-11-29 17:05:27,828] [INFO] [config.py:1007:print] DeepSpeedEngine configuration: +0: [2022-11-29 17:05:27,828] [INFO] [config.py:1011:print] activation_checkpointing_config { +0: "partition_activations": false, +0: "contiguous_memory_optimization": false, +0: "cpu_checkpointing": false, +0: "number_checkpoints": null, +0: "synchronize_checkpoint_boundary": false, +0: "profile": false +0: } +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True} +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] amp_enabled .................. False +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] amp_params ................... False +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] autotuning_config ............ { +0: "enabled": false, +0: "start_step": null, +0: "end_step": null, +0: "metric_path": null, +0: "arg_mappings": null, +0: "metric": "throughput", +0: "model_info": null, +0: "results_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_results", +0: "exps_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_exps", +0: "overwrite": true, +0: "fast": true, +0: "start_profile_step": 3, +0: "end_profile_step": 5, +0: "tuner_type": "gridsearch", +0: "tuner_early_stopping": 5, +0: "tuner_num_trials": 50, +0: "model_info_path": null, +0: "mp_size": 1, +0: "max_train_batch_size": null, +0: "min_train_batch_size": 1, +0: "max_train_micro_batch_size_per_gpu": 1.024000e+03, +0: "min_train_micro_batch_size_per_gpu": 1, +0: "num_tuning_micro_batch_sizes": 3 +0: } +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] bfloat16_enabled ............. True +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] checkpoint_parallel_write_pipeline False +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] checkpoint_tag_validation_enabled True +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] checkpoint_tag_validation_fail False +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] comms_config ................. +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] communication_data_type ...... None +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] compression_config ........... {'weight_quantization': {'shared_parameters': {'enabled': False, 'quantizer_kernel': False, 'schedule_offset': 0, 'quantize_groups': 1, 'quantize_verbose': False, 'quantization_type': 'symmetric', 'quantize_weight_in_forward': False, 'rounding': 'nearest', 'fp16_mixed_quantize': False, 'quantize_change_ratio': 0.001}, 'different_groups': {}}, 'activation_quantization': {'shared_parameters': {'enabled': False, 'quantization_type': 'symmetric', 'range_calibration': 'dynamic', 'schedule_offset': 1000}, 'different_groups': {}}, 'sparse_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'row_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'head_pruning': {'shared_parameters': {'enabled': False, 'method': 'topk', 'schedule_offset': 1000}, 'different_groups': {}}, 'channel_pruning': {'shared_pa +0: rameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'layer_reduction': {'enabled': False}} +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] curriculum_enabled ........... False +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] curriculum_params ............ False +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] dataloader_drop_last ......... False +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] disable_allgather ............ False +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] dump_state ................... False +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] dynamic_loss_scale_args ...... None +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] eigenvalue_enabled ........... False +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] eigenvalue_gas_boundary_resolution 1 +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] eigenvalue_layer_name ........ bert.encoder.layer +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] eigenvalue_layer_num ......... 0 +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] eigenvalue_max_iter .......... 100 +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] eigenvalue_stability ......... 1e-06 +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] eigenvalue_tol ............... 0.01 +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] eigenvalue_verbose ........... False +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] elasticity_enabled ........... False +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] flops_profiler_config ........ { +0: "enabled": false, +0: "profile_step": 1, +0: "module_depth": -1, +0: "top_modules": 1, +0: "detailed": true, +0: "output_file": null +0: } +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] fp16_auto_cast ............... None +0: [2022-11-29 17:05:27,829] [INFO] [config.py:1011:print] fp16_enabled ................. False +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] fp16_master_weights_and_gradients False +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] global_rank .................. 0 +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] gradient_accumulation_steps .. 1 +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] gradient_clipping ............ 1.0 +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] gradient_predivide_factor .... 1.0 +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] initial_dynamic_scale ........ 1 +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] load_universal_checkpoint .... False +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] loss_scale ................... 1.0 +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] memory_breakdown ............. False +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] monitor_config ............... +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] nebula_config ................ { +0: "enabled": false, +0: "persistent_storage_path": null, +0: "persistent_time_interval": 100, +0: "num_of_version_in_retention": 2, +0: "enable_nebula_load": true, +0: "load_path": null +0: } +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] optimizer_legacy_fusion ...... False +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] optimizer_name ............... None +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] optimizer_params ............. None +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0} +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] pld_enabled .................. False +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] pld_params ................... False +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] prescale_gradients ........... False +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] scheduler_name ............... None +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] scheduler_params ............. None +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] sparse_attention ............. None +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] sparse_gradients_enabled ..... False +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] steps_per_print .............. 2000 +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] train_batch_size ............. 256 +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] train_micro_batch_size_per_gpu 4 +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] use_node_local_storage ....... False +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] wall_clock_breakdown ......... False +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] world_size ................... 64 +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] zero_allow_untested_optimizer False +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] zero_config .................. stage=0 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=500000000 allgather_partitions=True allgather_bucket_size=500000000 overlap_comm=False load_from_fp32_weights=True elastic_checkpoint=False offload_param=None offload_optimizer=None sub_group_size=1000000000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=50000000 param_persistence_threshold=100000 model_persistence_threshold=9223372036854775807 max_live_parameters=1000000000 max_reuse_distance=1000000000 gather_16bit_weights_on_model_save=False stage3_gather_fp16_weights_on_model_save=False ignore_unused_parameters=True legacy_stage1=False round_robin_gradients=False +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] zero_enabled ................. False +0: [2022-11-29 17:05:27,830] [INFO] [config.py:1011:print] zero_optimization_stage ...... 0 +0: [2022-11-29 17:05:27,830] [INFO] [config.py:996:print_user_config] json = { +0: "train_micro_batch_size_per_gpu": 4, +0: "train_batch_size": 256, +0: "gradient_clipping": 1.0, +0: "zero_optimization": { +0: "stage": 0 +0: }, +0: "bf16": { +0: "enabled": true +0: }, +0: "steps_per_print": 2.000000e+03, +0: "wall_clock_breakdown": false +0: } +0: Time to load utils op: 0.00040984153747558594 seconds +0: [2022-11-29 17:05:27,831] [INFO] [engine.py:87:__init__] CONFIG: micro_batches=1 micro_batch_size=4 +0: [2022-11-29 17:05:27,881] [INFO] [engine.py:145:__init__] RANK=0 STAGE=0 LAYERS=26 [0, 26) STAGE_PARAMS=618714624 (618.715M) TOTAL_PARAMS=618714624 (618.715M) UNIQUE_PARAMS=618714624 (618.715M) +0: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: WARNING: could not find the metadata file checkpoints_619moscar [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: +0: will not load any checkpoints and will start from random +6: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:05:27,890] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 17:05:27,891] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_619moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: time (ms) | load-checkpoint: 8.07 +0: estimated model parameters: 0.618714624 +0: estimated model parameters without embeddings: 0.538301952 +0: [after model, optimizer, and learning rate scheduler are built] datetime: 2022-11-29 17:05:28 +0: > building train, validation, and test datasets ... +0: > datasets target sizes (minimum size): +0: train: 1308594 +0: validation: 1536 +0: test: 256 +0: > building train, validation, and test datasets for GPT ... +0: > building dataset index ... +0: reading sizes... +0: reading pointers... +0: reading document index... +0: creating numpy buffer of mmap... +0: creating memory view of numpy buffer... +0: > finished creating indexed dataset in 0.028244 seconds +0: number of documents: 431992659 +0: > dataset split: +0: train: +0: document indices in [0, 409961033) total of 409961033 documents +0: validation: +0: document indices in [409961033, 431560666) total of 21599633 documents +0: test: +0: document indices in [431560666, 431992659) total of 431993 documents +0: > WARNING: could not find index map files, building the indices on rank 0 ... +0: > only one epoch required, setting separate_last_epoch to False +0: > elasped time to build and save doc-idx mapping (seconds): 31.404293 +0: using: +0: number of documents: 409961033 +0: number of epochs: 1 +0: sequence length: 2048 +0: total number of samples: 262636457 +0: > elasped time to build and save sample-idx mapping (seconds): 7.827846 +0: > building shuffle index with split [0, 262636457) and [262636457, 262636457) ... +0: > elasped time to build and save shuffle-idx mapping (seconds): 16.150886 +0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_1308594ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_1308594ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_1308594ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 1.242 seconds +0: total number of samples: 262636458 +0: total number of epochs: 1 +0: > WARNING: could not find index map files, building the indices on rank 0 ... +0: > only one epoch required, setting separate_last_epoch to False +0: > elasped time to build and save doc-idx mapping (seconds): 1.150332 +0: using: +0: number of documents: 21599633 +0: number of epochs: 1 +0: sequence length: 2048 +0: total number of samples: 13852049 +0: > elasped time to build and save sample-idx mapping (seconds): 0.421503 +0: > building shuffle index with split [0, 13852049) and [13852049, 13852049) ... +0: > elasped time to build and save shuffle-idx mapping (seconds): 0.479258 +0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_1536ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_1536ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_1536ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.063 seconds +0: total number of samples: 13852050 +0: total number of epochs: 1 +0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_256ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_256ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_256ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.061 seconds +0: total number of samples: 276852 +0: total number of epochs: 1 +0: > finished creating GPT datasets ... +0: [after dataloaders are built] datetime: 2022-11-29 17:06:51 +0: done with setup ... +0: training ... +0: Number of parameters: [tensor rank - pipeline rank] w/ and w/o embeddings: +7: time (ms) | model-and-optimizer-setup: 15987.64 | train/valid/test-data-iterators-setup: 83278.21 +0: [000-000] 0.6187B / 0.5383B +0: [before the start of training step] datetime: 2022-11-29 17:06:51 +0: [Rank 0] (after 10 iterations) memory (MB) | allocated: 6409.56689453125 | max allocated: 34826.62890625 | reserved: 38832.0 | max reserved: 38832.0 +7: iteration 10/ 5111 | consumed samples: 2560 | consumed tokens: 5242880 | elapsed time per iteration (s): 3.29 | learning rate: 3.913E-05 | global batch size: 256 | lm loss: 1.002173E+01 | grad norm: 4.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 77.827 | TFLOPs: 10.69 | +7: iteration 20/ 5111 | consumed samples: 5120 | consumed tokens: 10485760 | elapsed time per iteration (s): 0.75 | learning rate: 7.825E-05 | global batch size: 256 | lm loss: 8.830676E+00 | grad norm: 1.879 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.220 | TFLOPs: 46.73 | +7: iteration 30/ 5111 | consumed samples: 7680 | consumed tokens: 15728640 | elapsed time per iteration (s): 0.77 | learning rate: 1.174E-04 | global batch size: 256 | lm loss: 8.052920E+00 | grad norm: 0.896 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.949 | TFLOPs: 45.46 | +7: iteration 40/ 5111 | consumed samples: 10240 | consumed tokens: 20971520 | elapsed time per iteration (s): 0.78 | learning rate: 1.565E-04 | global batch size: 256 | lm loss: 7.647610E+00 | grad norm: 1.932 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.501 | TFLOPs: 45.26 | +7: iteration 50/ 5111 | consumed samples: 12800 | consumed tokens: 26214400 | elapsed time per iteration (s): 0.75 | learning rate: 1.956E-04 | global batch size: 256 | lm loss: 7.428722E+00 | grad norm: 1.797 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.355 | TFLOPs: 46.61 | +7: iteration 60/ 5111 | consumed samples: 15360 | consumed tokens: 31457280 | elapsed time per iteration (s): 0.76 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 7.202071E+00 | grad norm: 1.098 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.310 | TFLOPs: 46.33 | +7: iteration 70/ 5111 | consumed samples: 17920 | consumed tokens: 36700160 | elapsed time per iteration (s): 0.77 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 7.013801E+00 | grad norm: 0.602 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.458 | TFLOPs: 45.94 | +7: iteration 80/ 5111 | consumed samples: 20480 | consumed tokens: 41943040 | elapsed time per iteration (s): 0.76 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.898230E+00 | grad norm: 0.617 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.167 | TFLOPs: 46.18 | +7: iteration 90/ 5111 | consumed samples: 23040 | consumed tokens: 47185920 | elapsed time per iteration (s): 0.76 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.719425E+00 | grad norm: 0.853 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.379 | TFLOPs: 46.20 | +7: iteration 100/ 5111 | consumed samples: 25600 | consumed tokens: 52428800 | elapsed time per iteration (s): 0.77 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.638956E+00 | grad norm: 0.638 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.133 | TFLOPs: 45.76 | +7: iteration 110/ 5111 | consumed samples: 28160 | consumed tokens: 57671680 | elapsed time per iteration (s): 0.75 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 6.547971E+00 | grad norm: 0.498 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.555 | TFLOPs: 46.78 | +7: iteration 120/ 5111 | consumed samples: 30720 | consumed tokens: 62914560 | elapsed time per iteration (s): 0.76 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 6.489710E+00 | grad norm: 0.797 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.020 | TFLOPs: 46.16 | +7: iteration 130/ 5111 | consumed samples: 33280 | consumed tokens: 68157440 | elapsed time per iteration (s): 0.76 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 6.390199E+00 | grad norm: 0.491 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.924 | TFLOPs: 46.14 | +7: iteration 140/ 5111 | consumed samples: 35840 | consumed tokens: 73400320 | elapsed time per iteration (s): 0.75 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 6.349360E+00 | grad norm: 1.066 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.401 | TFLOPs: 46.62 | +7: iteration 150/ 5111 | consumed samples: 38400 | consumed tokens: 78643200 | elapsed time per iteration (s): 0.77 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 6.282593E+00 | grad norm: 0.622 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.454 | TFLOPs: 45.67 | +7: iteration 160/ 5111 | consumed samples: 40960 | consumed tokens: 83886080 | elapsed time per iteration (s): 0.76 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 6.244477E+00 | grad norm: 0.518 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.100 | TFLOPs: 46.17 | +7: iteration 170/ 5111 | consumed samples: 43520 | consumed tokens: 89128960 | elapsed time per iteration (s): 0.77 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 6.198322E+00 | grad norm: 0.647 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.330 | TFLOPs: 45.92 | +7: iteration 180/ 5111 | consumed samples: 46080 | consumed tokens: 94371840 | elapsed time per iteration (s): 0.75 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 6.140799E+00 | grad norm: 0.620 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.837 | TFLOPs: 46.95 | +7: iteration 190/ 5111 | consumed samples: 48640 | consumed tokens: 99614720 | elapsed time per iteration (s): 0.75 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 6.103164E+00 | grad norm: 0.880 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.822 | TFLOPs: 46.81 | +7: iteration 200/ 5111 | consumed samples: 51200 | consumed tokens: 104857600 | elapsed time per iteration (s): 0.76 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 6.100035E+00 | grad norm: 0.529 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.803 | TFLOPs: 45.99 | +7: iteration 210/ 5111 | consumed samples: 53760 | consumed tokens: 110100480 | elapsed time per iteration (s): 0.76 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 6.021029E+00 | grad norm: 0.964 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.305 | TFLOPs: 46.19 | +7: iteration 220/ 5111 | consumed samples: 56320 | consumed tokens: 115343360 | elapsed time per iteration (s): 0.75 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 6.011663E+00 | grad norm: 0.501 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.967 | TFLOPs: 46.70 | +7: iteration 230/ 5111 | consumed samples: 58880 | consumed tokens: 120586240 | elapsed time per iteration (s): 0.75 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 5.915787E+00 | grad norm: 0.768 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.457 | TFLOPs: 46.76 | +7: iteration 240/ 5111 | consumed samples: 61440 | consumed tokens: 125829120 | elapsed time per iteration (s): 0.76 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 5.869847E+00 | grad norm: 0.650 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.920 | TFLOPs: 46.42 | +7: iteration 250/ 5111 | consumed samples: 64000 | consumed tokens: 131072000 | elapsed time per iteration (s): 0.78 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 5.849192E+00 | grad norm: 0.907 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.643 | TFLOPs: 45.28 | +7: iteration 260/ 5111 | consumed samples: 66560 | consumed tokens: 136314880 | elapsed time per iteration (s): 0.77 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 5.836254E+00 | grad norm: 1.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.551 | TFLOPs: 45.82 | +7: iteration 270/ 5111 | consumed samples: 69120 | consumed tokens: 141557760 | elapsed time per iteration (s): 0.76 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 5.816767E+00 | grad norm: 0.532 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.187 | TFLOPs: 46.04 | +7: iteration 280/ 5111 | consumed samples: 71680 | consumed tokens: 146800640 | elapsed time per iteration (s): 0.77 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 5.763723E+00 | grad norm: 0.612 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.398 | TFLOPs: 45.93 | +7: iteration 290/ 5111 | consumed samples: 74240 | consumed tokens: 152043520 | elapsed time per iteration (s): 0.78 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 5.712501E+00 | grad norm: 0.492 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.897 | TFLOPs: 45.04 | +7: iteration 300/ 5111 | consumed samples: 76800 | consumed tokens: 157286400 | elapsed time per iteration (s): 0.75 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 5.643123E+00 | grad norm: 0.529 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.914 | TFLOPs: 46.69 | +7: iteration 310/ 5111 | consumed samples: 79360 | consumed tokens: 162529280 | elapsed time per iteration (s): 0.77 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 5.613233E+00 | grad norm: 0.843 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.444 | TFLOPs: 45.80 | +7: iteration 320/ 5111 | consumed samples: 81920 | consumed tokens: 167772160 | elapsed time per iteration (s): 0.78 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 5.583235E+00 | grad norm: 0.728 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.308 | TFLOPs: 45.23 | +7: iteration 330/ 5111 | consumed samples: 84480 | consumed tokens: 173015040 | elapsed time per iteration (s): 0.77 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 5.569402E+00 | grad norm: 0.558 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.889 | TFLOPs: 45.59 | +7: iteration 340/ 5111 | consumed samples: 87040 | consumed tokens: 178257920 | elapsed time per iteration (s): 0.75 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 5.510612E+00 | grad norm: 0.745 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.705 | TFLOPs: 46.94 | +7: iteration 350/ 5111 | consumed samples: 89600 | consumed tokens: 183500800 | elapsed time per iteration (s): 0.76 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 5.478490E+00 | grad norm: 0.545 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.584 | TFLOPs: 46.37 | +7: iteration 360/ 5111 | consumed samples: 92160 | consumed tokens: 188743680 | elapsed time per iteration (s): 0.76 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 5.457864E+00 | grad norm: 0.507 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.768 | TFLOPs: 45.98 | +7: iteration 370/ 5111 | consumed samples: 94720 | consumed tokens: 193986560 | elapsed time per iteration (s): 0.76 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 5.400141E+00 | grad norm: 0.569 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.857 | TFLOPs: 46.27 | +7: iteration 380/ 5111 | consumed samples: 97280 | consumed tokens: 199229440 | elapsed time per iteration (s): 0.76 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 5.342245E+00 | grad norm: 0.581 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.055 | TFLOPs: 46.16 | +7: iteration 390/ 5111 | consumed samples: 99840 | consumed tokens: 204472320 | elapsed time per iteration (s): 0.76 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 5.335765E+00 | grad norm: 0.546 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.207 | TFLOPs: 46.46 | +7: iteration 400/ 5111 | consumed samples: 102400 | consumed tokens: 209715200 | elapsed time per iteration (s): 0.75 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 5.271832E+00 | grad norm: 0.665 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.940 | TFLOPs: 46.69 | +7: iteration 410/ 5111 | consumed samples: 104960 | consumed tokens: 214958080 | elapsed time per iteration (s): 0.77 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 5.225074E+00 | grad norm: 0.621 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.611 | TFLOPs: 45.82 | +7: iteration 420/ 5111 | consumed samples: 107520 | consumed tokens: 220200960 | elapsed time per iteration (s): 0.76 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 5.205478E+00 | grad norm: 0.629 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.859 | TFLOPs: 46.55 | +7: iteration 430/ 5111 | consumed samples: 110080 | consumed tokens: 225443840 | elapsed time per iteration (s): 0.75 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 5.161177E+00 | grad norm: 0.864 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.822 | TFLOPs: 46.95 | +7: iteration 440/ 5111 | consumed samples: 112640 | consumed tokens: 230686720 | elapsed time per iteration (s): 0.76 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 5.149526E+00 | grad norm: 0.603 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.364 | TFLOPs: 46.06 | +7: iteration 450/ 5111 | consumed samples: 115200 | consumed tokens: 235929600 | elapsed time per iteration (s): 0.76 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 5.085698E+00 | grad norm: 0.692 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.972 | TFLOPs: 46.29 | +7: iteration 460/ 5111 | consumed samples: 117760 | consumed tokens: 241172480 | elapsed time per iteration (s): 0.76 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 5.104781E+00 | grad norm: 0.558 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.738 | TFLOPs: 46.53 | +7: iteration 470/ 5111 | consumed samples: 120320 | consumed tokens: 246415360 | elapsed time per iteration (s): 0.77 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 5.022173E+00 | grad norm: 0.695 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.135 | TFLOPs: 45.90 | +7: iteration 480/ 5111 | consumed samples: 122880 | consumed tokens: 251658240 | elapsed time per iteration (s): 0.78 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 5.019775E+00 | grad norm: 0.726 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.087 | TFLOPs: 45.34 | +7: iteration 490/ 5111 | consumed samples: 125440 | consumed tokens: 256901120 | elapsed time per iteration (s): 0.74 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 4.987070E+00 | grad norm: 0.649 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.636 | TFLOPs: 47.20 | +7: iteration 500/ 5111 | consumed samples: 128000 | consumed tokens: 262144000 | elapsed time per iteration (s): 0.77 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 4.931116E+00 | grad norm: 0.755 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.426 | TFLOPs: 45.52 | +7: iteration 510/ 5111 | consumed samples: 130560 | consumed tokens: 267386880 | elapsed time per iteration (s): 0.77 | learning rate: 1.964E-04 | global batch size: 256 | lm loss: 4.883297E+00 | grad norm: 0.790 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.070 | TFLOPs: 45.89 | +7: iteration 520/ 5111 | consumed samples: 133120 | consumed tokens: 272629760 | elapsed time per iteration (s): 0.76 | learning rate: 1.962E-04 | global batch size: 256 | lm loss: 4.839327E+00 | grad norm: 0.991 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.651 | TFLOPs: 46.38 | +7: iteration 530/ 5111 | consumed samples: 135680 | consumed tokens: 277872640 | elapsed time per iteration (s): 0.76 | learning rate: 1.961E-04 | global batch size: 256 | lm loss: 4.835258E+00 | grad norm: 0.792 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.741 | TFLOPs: 45.98 | +7: iteration 540/ 5111 | consumed samples: 138240 | consumed tokens: 283115520 | elapsed time per iteration (s): 0.76 | learning rate: 1.959E-04 | global batch size: 256 | lm loss: 4.823607E+00 | grad norm: 1.061 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.753 | TFLOPs: 46.39 | +7: iteration 550/ 5111 | consumed samples: 140800 | consumed tokens: 288358400 | elapsed time per iteration (s): 0.76 | learning rate: 1.957E-04 | global batch size: 256 | lm loss: 4.766069E+00 | grad norm: 0.814 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.934 | TFLOPs: 46.42 | +7: iteration 560/ 5111 | consumed samples: 143360 | consumed tokens: 293601280 | elapsed time per iteration (s): 0.76 | learning rate: 1.955E-04 | global batch size: 256 | lm loss: 4.692715E+00 | grad norm: 0.543 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.484 | TFLOPs: 46.49 | +7: iteration 570/ 5111 | consumed samples: 145920 | consumed tokens: 298844160 | elapsed time per iteration (s): 0.76 | learning rate: 1.954E-04 | global batch size: 256 | lm loss: 4.628288E+00 | grad norm: 0.853 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.668 | TFLOPs: 46.24 | +7: iteration 580/ 5111 | consumed samples: 148480 | consumed tokens: 304087040 | elapsed time per iteration (s): 0.77 | learning rate: 1.952E-04 | global batch size: 256 | lm loss: 4.585346E+00 | grad norm: 0.691 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.885 | TFLOPs: 45.72 | +7: iteration 590/ 5111 | consumed samples: 151040 | consumed tokens: 309329920 | elapsed time per iteration (s): 0.77 | learning rate: 1.950E-04 | global batch size: 256 | lm loss: 4.547835E+00 | grad norm: 0.638 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.929 | TFLOPs: 45.59 | +7: iteration 600/ 5111 | consumed samples: 153600 | consumed tokens: 314572800 | elapsed time per iteration (s): 0.77 | learning rate: 1.948E-04 | global batch size: 256 | lm loss: 4.493588E+00 | grad norm: 0.992 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.860 | TFLOPs: 45.45 | +7: iteration 610/ 5111 | consumed samples: 156160 | consumed tokens: 319815680 | elapsed time per iteration (s): 0.76 | learning rate: 1.946E-04 | global batch size: 256 | lm loss: 4.460758E+00 | grad norm: 0.844 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.489 | TFLOPs: 46.08 | +7: iteration 620/ 5111 | consumed samples: 158720 | consumed tokens: 325058560 | elapsed time per iteration (s): 0.77 | learning rate: 1.944E-04 | global batch size: 256 | lm loss: 4.440316E+00 | grad norm: 0.632 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.264 | TFLOPs: 45.91 | +7: iteration 630/ 5111 | consumed samples: 161280 | consumed tokens: 330301440 | elapsed time per iteration (s): 0.76 | learning rate: 1.943E-04 | global batch size: 256 | lm loss: 4.383992E+00 | grad norm: 0.489 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.894 | TFLOPs: 46.14 | +7: iteration 640/ 5111 | consumed samples: 163840 | consumed tokens: 335544320 | elapsed time per iteration (s): 0.77 | learning rate: 1.941E-04 | global batch size: 256 | lm loss: 4.363723E+00 | grad norm: 0.564 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.682 | TFLOPs: 45.70 | +7: iteration 650/ 5111 | consumed samples: 166400 | consumed tokens: 340787200 | elapsed time per iteration (s): 0.76 | learning rate: 1.939E-04 | global batch size: 256 | lm loss: 4.286814E+00 | grad norm: 0.520 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.612 | TFLOPs: 46.10 | +7: iteration 660/ 5111 | consumed samples: 168960 | consumed tokens: 346030080 | elapsed time per iteration (s): 0.75 | learning rate: 1.936E-04 | global batch size: 256 | lm loss: 4.282188E+00 | grad norm: 0.542 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.887 | TFLOPs: 46.69 | +7: iteration 670/ 5111 | consumed samples: 171520 | consumed tokens: 351272960 | elapsed time per iteration (s): 0.75 | learning rate: 1.934E-04 | global batch size: 256 | lm loss: 4.238626E+00 | grad norm: 0.641 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.689 | TFLOPs: 46.66 | +7: iteration 680/ 5111 | consumed samples: 174080 | consumed tokens: 356515840 | elapsed time per iteration (s): 0.76 | learning rate: 1.932E-04 | global batch size: 256 | lm loss: 4.223129E+00 | grad norm: 0.640 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.471 | TFLOPs: 46.35 | +7: iteration 690/ 5111 | consumed samples: 176640 | consumed tokens: 361758720 | elapsed time per iteration (s): 0.77 | learning rate: 1.930E-04 | global batch size: 256 | lm loss: 4.260840E+00 | grad norm: 0.688 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.071 | TFLOPs: 45.75 | +7: iteration 700/ 5111 | consumed samples: 179200 | consumed tokens: 367001600 | elapsed time per iteration (s): 0.75 | learning rate: 1.928E-04 | global batch size: 256 | lm loss: 4.220367E+00 | grad norm: 0.595 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.536 | TFLOPs: 46.64 | +7: iteration 710/ 5111 | consumed samples: 181760 | consumed tokens: 372244480 | elapsed time per iteration (s): 0.75 | learning rate: 1.926E-04 | global batch size: 256 | lm loss: 4.149709E+00 | grad norm: 0.469 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.993 | TFLOPs: 46.70 | +7: iteration 720/ 5111 | consumed samples: 184320 | consumed tokens: 377487360 | elapsed time per iteration (s): 0.75 | learning rate: 1.924E-04 | global batch size: 256 | lm loss: 4.158878E+00 | grad norm: 0.525 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.547 | TFLOPs: 46.78 | +7: iteration 730/ 5111 | consumed samples: 186880 | consumed tokens: 382730240 | elapsed time per iteration (s): 0.75 | learning rate: 1.921E-04 | global batch size: 256 | lm loss: 4.140413E+00 | grad norm: 0.558 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.825 | TFLOPs: 46.68 | +7: iteration 740/ 5111 | consumed samples: 189440 | consumed tokens: 387973120 | elapsed time per iteration (s): 0.76 | learning rate: 1.919E-04 | global batch size: 256 | lm loss: 4.122210E+00 | grad norm: 0.451 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.292 | TFLOPs: 46.33 | +7: iteration 750/ 5111 | consumed samples: 192000 | consumed tokens: 393216000 | elapsed time per iteration (s): 0.75 | learning rate: 1.917E-04 | global batch size: 256 | lm loss: 4.080987E+00 | grad norm: 0.476 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.258 | TFLOPs: 46.87 | +7: iteration 760/ 5111 | consumed samples: 194560 | consumed tokens: 398458880 | elapsed time per iteration (s): 0.75 | learning rate: 1.914E-04 | global batch size: 256 | lm loss: 4.071053E+00 | grad norm: 0.580 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.770 | TFLOPs: 46.81 | +7: iteration 770/ 5111 | consumed samples: 197120 | consumed tokens: 403701760 | elapsed time per iteration (s): 0.75 | learning rate: 1.912E-04 | global batch size: 256 | lm loss: 4.085012E+00 | grad norm: 0.709 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.366 | TFLOPs: 46.75 | +7: iteration 780/ 5111 | consumed samples: 199680 | consumed tokens: 408944640 | elapsed time per iteration (s): 0.76 | learning rate: 1.909E-04 | global batch size: 256 | lm loss: 4.078230E+00 | grad norm: 0.540 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.545 | TFLOPs: 46.50 | +7: iteration 790/ 5111 | consumed samples: 202240 | consumed tokens: 414187520 | elapsed time per iteration (s): 0.75 | learning rate: 1.907E-04 | global batch size: 256 | lm loss: 4.042562E+00 | grad norm: 0.656 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.698 | TFLOPs: 46.66 | +7: iteration 800/ 5111 | consumed samples: 204800 | consumed tokens: 419430400 | elapsed time per iteration (s): 0.74 | learning rate: 1.904E-04 | global batch size: 256 | lm loss: 4.041742E+00 | grad norm: 0.476 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.184 | TFLOPs: 47.28 | +7: iteration 810/ 5111 | consumed samples: 207360 | consumed tokens: 424673280 | elapsed time per iteration (s): 0.75 | learning rate: 1.902E-04 | global batch size: 256 | lm loss: 3.993091E+00 | grad norm: 0.492 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.460 | TFLOPs: 47.18 | +7: iteration 820/ 5111 | consumed samples: 209920 | consumed tokens: 429916160 | elapsed time per iteration (s): 0.75 | learning rate: 1.899E-04 | global batch size: 256 | lm loss: 3.958693E+00 | grad norm: 0.504 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.688 | TFLOPs: 46.80 | +7: iteration 830/ 5111 | consumed samples: 212480 | consumed tokens: 435159040 | elapsed time per iteration (s): 0.75 | learning rate: 1.897E-04 | global batch size: 256 | lm loss: 4.010392E+00 | grad norm: 0.485 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.217 | TFLOPs: 46.73 | +7: iteration 840/ 5111 | consumed samples: 215040 | consumed tokens: 440401920 | elapsed time per iteration (s): 0.75 | learning rate: 1.894E-04 | global batch size: 256 | lm loss: 3.989401E+00 | grad norm: 0.368 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.817 | TFLOPs: 46.81 | +7: iteration 850/ 5111 | consumed samples: 217600 | consumed tokens: 445644800 | elapsed time per iteration (s): 0.75 | learning rate: 1.892E-04 | global batch size: 256 | lm loss: 3.953146E+00 | grad norm: 0.430 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.263 | TFLOPs: 46.60 | +7: iteration 860/ 5111 | consumed samples: 220160 | consumed tokens: 450887680 | elapsed time per iteration (s): 0.75 | learning rate: 1.889E-04 | global batch size: 256 | lm loss: 3.943749E+00 | grad norm: 0.491 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.553 | TFLOPs: 46.92 | +7: iteration 870/ 5111 | consumed samples: 222720 | consumed tokens: 456130560 | elapsed time per iteration (s): 0.75 | learning rate: 1.886E-04 | global batch size: 256 | lm loss: 3.941771E+00 | grad norm: 0.461 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.069 | TFLOPs: 46.71 | +7: iteration 880/ 5111 | consumed samples: 225280 | consumed tokens: 461373440 | elapsed time per iteration (s): 0.78 | learning rate: 1.883E-04 | global batch size: 256 | lm loss: 3.895723E+00 | grad norm: 0.441 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.997 | TFLOPs: 45.33 | +7: iteration 890/ 5111 | consumed samples: 227840 | consumed tokens: 466616320 | elapsed time per iteration (s): 0.77 | learning rate: 1.881E-04 | global batch size: 256 | lm loss: 3.884980E+00 | grad norm: 0.548 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.075 | TFLOPs: 45.89 | +7: iteration 900/ 5111 | consumed samples: 230400 | consumed tokens: 471859200 | elapsed time per iteration (s): 0.78 | learning rate: 1.878E-04 | global batch size: 256 | lm loss: 3.923432E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.309 | TFLOPs: 45.23 | +7: iteration 910/ 5111 | consumed samples: 232960 | consumed tokens: 477102080 | elapsed time per iteration (s): 0.76 | learning rate: 1.875E-04 | global batch size: 256 | lm loss: 3.901632E+00 | grad norm: 0.428 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.564 | TFLOPs: 46.37 | +7: iteration 920/ 5111 | consumed samples: 235520 | consumed tokens: 482344960 | elapsed time per iteration (s): 0.75 | learning rate: 1.872E-04 | global batch size: 256 | lm loss: 3.849860E+00 | grad norm: 0.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.329 | TFLOPs: 46.88 | +7: iteration 930/ 5111 | consumed samples: 238080 | consumed tokens: 487587840 | elapsed time per iteration (s): 0.75 | learning rate: 1.869E-04 | global batch size: 256 | lm loss: 3.838226E+00 | grad norm: 0.459 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.560 | TFLOPs: 46.78 | +7: iteration 940/ 5111 | consumed samples: 240640 | consumed tokens: 492830720 | elapsed time per iteration (s): 0.76 | learning rate: 1.866E-04 | global batch size: 256 | lm loss: 3.810245E+00 | grad norm: 0.526 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.772 | TFLOPs: 46.40 | +7: iteration 950/ 5111 | consumed samples: 243200 | consumed tokens: 498073600 | elapsed time per iteration (s): 0.78 | learning rate: 1.863E-04 | global batch size: 256 | lm loss: 3.818677E+00 | grad norm: 0.386 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.007 | TFLOPs: 45.19 | +7: iteration 960/ 5111 | consumed samples: 245760 | consumed tokens: 503316480 | elapsed time per iteration (s): 0.75 | learning rate: 1.860E-04 | global batch size: 256 | lm loss: 3.817852E+00 | grad norm: 0.478 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.268 | TFLOPs: 47.01 | +7: iteration 970/ 5111 | consumed samples: 248320 | consumed tokens: 508559360 | elapsed time per iteration (s): 0.75 | learning rate: 1.857E-04 | global batch size: 256 | lm loss: 3.835239E+00 | grad norm: 0.755 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.095 | TFLOPs: 46.58 | +7: iteration 980/ 5111 | consumed samples: 250880 | consumed tokens: 513802240 | elapsed time per iteration (s): 0.76 | learning rate: 1.854E-04 | global batch size: 256 | lm loss: 3.846029E+00 | grad norm: 0.454 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.636 | TFLOPs: 46.10 | +7: iteration 990/ 5111 | consumed samples: 253440 | consumed tokens: 519045120 | elapsed time per iteration (s): 0.76 | learning rate: 1.851E-04 | global batch size: 256 | lm loss: 3.879024E+00 | grad norm: 1.464 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.164 | TFLOPs: 46.17 | +7: iteration 1000/ 5111 | consumed samples: 256000 | consumed tokens: 524288000 | elapsed time per iteration (s): 0.75 | learning rate: 1.848E-04 | global batch size: 256 | lm loss: 3.914204E+00 | grad norm: 0.686 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.755 | TFLOPs: 46.67 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 1000 | lm loss value: 3.741934E+00 | lm loss PPL: 4.217948E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 1000 to checkpoints_619moscar +0: [2022-11-29 17:19:57,562] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step1000 is begin to save! +0: [2022-11-29 17:19:57,724] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:19:57,951] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:19:57,952] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:19:58,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:19:58,036] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:19:58,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:19:58,118] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:19:58,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:19:58,196] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:19:58,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:19:58,279] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:19:58,357] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:19:58,358] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:19:58,424] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:19:58,424] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:19:58,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:19:58,480] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:19:58,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:19:58,538] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:19:58,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:19:58,597] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:19:58,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:19:58,654] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:19:58,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:19:58,713] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:19:58,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:19:58,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:19:58,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:19:58,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:19:58,885] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:19:58,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:19:58,942] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:19:58,942] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/layer_18-model_00-model_states.pt... +0: [2022-11-29 17:19:59,002] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/layer_18-model_00-model_states.pt. +0: [2022-11-29 17:19:59,002] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:19:59,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:19:59,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/layer_20-model_00-model_states.pt... +0: [2022-11-29 17:19:59,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/layer_20-model_00-model_states.pt. +0: [2022-11-29 17:19:59,118] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/layer_21-model_00-model_states.pt... +0: [2022-11-29 17:19:59,174] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/layer_21-model_00-model_states.pt. +0: [2022-11-29 17:19:59,174] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/layer_23-model_00-model_states.pt... +0: [2022-11-29 17:19:59,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/layer_23-model_00-model_states.pt. +0: [2022-11-29 17:19:59,179] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_619moscar/global_step1000/mp_rank_00_model_states.pt +0: [2022-11-29 17:19:59,179] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:19:59,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:19:59,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:19:59,354] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:19:59,361] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:19:59,361] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:19:59,361] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:19:59,373] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:19:59,373] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:19:59,373] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:19:59,373] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:19:59,373] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:19:59,373] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:19:59,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:19:59,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:19:59,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:19:59,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:19:59,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:19:59,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:19:59,377] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:19:59,377] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:19:59,377] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:19:59,377] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:19:59,377] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +6: [2022-11-29 17:19:59,377] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:19:59,377] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:19:59,377] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:19:59,377] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:19:59,377] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +6: [2022-11-29 17:19:59,377] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:19:59,377] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:19:59,377] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:19:59,377] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:19:59,377] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:19:59,377] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +0: [2022-11-29 17:19:59,377] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:19:59,377] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:19:59,377] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:19:59,377] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:19:59,377] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:19:59,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:19:59,378] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:19:59,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:19:59,380] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:19:59,380] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:19:59,380] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:19:59,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:19:59,382] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:19:59,383] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:19:59,384] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:19:59,384] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:19:59,384] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:19:59,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:19:59,388] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:19:59,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:19:59,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:19:59,388] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:19:59,389] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:19:59,390] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:19:59,390] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:19:59,390] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:19:59,391] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:19:59,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:19:59,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:19:59,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:19:59,395] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +3: [2022-11-29 17:19:59,395] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:19:59,395] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:19:59,395] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:19:59,395] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:19:59,395] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:19:59,398] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:19:59,398] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:19:59,398] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:19:59,400] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:19:59,401] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:19:59,401] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:19:59,401] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:19:59,401] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:19:59,401] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:19:59,403] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:19:59,404] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:19:59,404] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:19:59,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:19:59,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:19:59,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:19:59,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:19:59,409] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:19:59,409] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:19:59,411] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:19:59,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:19:59,412] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:19:59,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:19:59,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:19:59,412] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:19:59,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:19:59,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:19:59,412] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:19:59,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:19:59,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:19:59,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:19:59,391] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:19:59,391] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:19:59,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:19:59,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:19:59,393] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:19:59,394] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:19:59,394] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:19:59,394] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:19:59,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:19:59,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:19:59,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:19:59,400] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:19:59,400] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:19:59,400] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:19:59,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:19:59,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:19:59,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:19:59,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:19:59,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:19:59,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:19:59,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:19:59,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:19:59,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:19:59,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:19:59,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:19:59,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:19:59,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:19:59,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:19:59,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:19:59,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:19:59,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:19:59,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:19:59,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:19:59,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:19:59,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +6: [2022-11-29 17:19:59,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:19:59,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:19:59,382] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:19:59,382] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:19:59,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:19:59,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:19:59,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:19:59,425] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:19:59,425] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:19:59,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:19:59,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:19:59,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:19:59,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:19:59,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:19:59,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:19:59,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:19:59,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:19:59,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:19:59,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:19:59,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:19:59,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:19:59,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:19:59,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:19:59,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:19:59,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:19:59,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:19:59,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:19:59,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:19:59,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:19:59,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:19:59,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:19:59,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:19:59,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:19:59,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:19:59,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:19:59,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:19:59,507] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:19:59,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:19:59,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:19:59,507] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:19:59,507] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:19:59,507] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:19:59,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:19:59,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:19:59,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:19:59,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:19:59,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:19:59,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:19:59,512] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:19:59,512] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:19:59,512] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:19:59,512] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:19:59,512] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:19:59,512] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:19:59,513] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:19:59,513] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:19:59,513] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:19:59,530] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:19:59,530] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: successfully saved checkpoint at iteration 1000 to checkpoints_619moscar +7: time (ms) | save-checkpoint: 1978.23 +7: iteration 1010/ 5111 | consumed samples: 258560 | consumed tokens: 529530880 | elapsed time per iteration (s): 1.02 | learning rate: 1.845E-04 | global batch size: 256 | lm loss: 3.835496E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 250.675 | TFLOPs: 34.43 | +7: iteration 1020/ 5111 | consumed samples: 261120 | consumed tokens: 534773760 | elapsed time per iteration (s): 0.76 | learning rate: 1.842E-04 | global batch size: 256 | lm loss: 3.806410E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.257 | TFLOPs: 46.19 | +7: iteration 1030/ 5111 | consumed samples: 263680 | consumed tokens: 540016640 | elapsed time per iteration (s): 0.76 | learning rate: 1.839E-04 | global batch size: 256 | lm loss: 3.780796E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.453 | TFLOPs: 46.49 | +7: iteration 1040/ 5111 | consumed samples: 266240 | consumed tokens: 545259520 | elapsed time per iteration (s): 0.75 | learning rate: 1.836E-04 | global batch size: 256 | lm loss: 3.742289E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.448 | TFLOPs: 46.63 | +7: iteration 1050/ 5111 | consumed samples: 268800 | consumed tokens: 550502400 | elapsed time per iteration (s): 0.77 | learning rate: 1.832E-04 | global batch size: 256 | lm loss: 3.749243E+00 | grad norm: 0.391 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.545 | TFLOPs: 45.54 | +7: iteration 1060/ 5111 | consumed samples: 271360 | consumed tokens: 555745280 | elapsed time per iteration (s): 0.76 | learning rate: 1.829E-04 | global batch size: 256 | lm loss: 3.750302E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.365 | TFLOPs: 46.20 | +7: iteration 1070/ 5111 | consumed samples: 273920 | consumed tokens: 560988160 | elapsed time per iteration (s): 0.76 | learning rate: 1.826E-04 | global batch size: 256 | lm loss: 3.720180E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.985 | TFLOPs: 46.42 | +7: iteration 1080/ 5111 | consumed samples: 276480 | consumed tokens: 566231040 | elapsed time per iteration (s): 0.76 | learning rate: 1.823E-04 | global batch size: 256 | lm loss: 3.718463E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.399 | TFLOPs: 46.07 | +7: iteration 1090/ 5111 | consumed samples: 279040 | consumed tokens: 571473920 | elapsed time per iteration (s): 0.76 | learning rate: 1.819E-04 | global batch size: 256 | lm loss: 3.722684E+00 | grad norm: 0.390 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.089 | TFLOPs: 46.03 | +7: iteration 1100/ 5111 | consumed samples: 281600 | consumed tokens: 576716800 | elapsed time per iteration (s): 0.77 | learning rate: 1.816E-04 | global batch size: 256 | lm loss: 3.706431E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.283 | TFLOPs: 45.92 | +7: iteration 1110/ 5111 | consumed samples: 284160 | consumed tokens: 581959680 | elapsed time per iteration (s): 0.75 | learning rate: 1.812E-04 | global batch size: 256 | lm loss: 3.666109E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.992 | TFLOPs: 46.70 | +7: iteration 1120/ 5111 | consumed samples: 286720 | consumed tokens: 587202560 | elapsed time per iteration (s): 0.76 | learning rate: 1.809E-04 | global batch size: 256 | lm loss: 3.681937E+00 | grad norm: 0.424 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.590 | TFLOPs: 46.10 | +7: iteration 1130/ 5111 | consumed samples: 289280 | consumed tokens: 592445440 | elapsed time per iteration (s): 0.78 | learning rate: 1.806E-04 | global batch size: 256 | lm loss: 3.674803E+00 | grad norm: 0.399 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.169 | TFLOPs: 45.08 | +7: iteration 1140/ 5111 | consumed samples: 291840 | consumed tokens: 597688320 | elapsed time per iteration (s): 0.76 | learning rate: 1.802E-04 | global batch size: 256 | lm loss: 3.684035E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.121 | TFLOPs: 46.31 | +7: iteration 1150/ 5111 | consumed samples: 294400 | consumed tokens: 602931200 | elapsed time per iteration (s): 0.78 | learning rate: 1.799E-04 | global batch size: 256 | lm loss: 3.663050E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.310 | TFLOPs: 45.10 | +7: iteration 1160/ 5111 | consumed samples: 296960 | consumed tokens: 608174080 | elapsed time per iteration (s): 0.77 | learning rate: 1.795E-04 | global batch size: 256 | lm loss: 3.680218E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.627 | TFLOPs: 45.96 | +7: iteration 1170/ 5111 | consumed samples: 299520 | consumed tokens: 613416960 | elapsed time per iteration (s): 0.77 | learning rate: 1.791E-04 | global batch size: 256 | lm loss: 3.672005E+00 | grad norm: 0.439 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.007 | TFLOPs: 45.60 | +7: iteration 1180/ 5111 | consumed samples: 302080 | consumed tokens: 618659840 | elapsed time per iteration (s): 0.76 | learning rate: 1.788E-04 | global batch size: 256 | lm loss: 3.666794E+00 | grad norm: 1.536 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.486 | TFLOPs: 46.22 | +7: iteration 1190/ 5111 | consumed samples: 304640 | consumed tokens: 623902720 | elapsed time per iteration (s): 0.77 | learning rate: 1.784E-04 | global batch size: 256 | lm loss: 3.756565E+00 | grad norm: 0.589 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.903 | TFLOPs: 45.86 | +7: iteration 1200/ 5111 | consumed samples: 307200 | consumed tokens: 629145600 | elapsed time per iteration (s): 0.78 | learning rate: 1.781E-04 | global batch size: 256 | lm loss: 3.672084E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 328.668 | TFLOPs: 45.15 | +7: iteration 1210/ 5111 | consumed samples: 309760 | consumed tokens: 634388480 | elapsed time per iteration (s): 0.76 | learning rate: 1.777E-04 | global batch size: 256 | lm loss: 3.645463E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.764 | TFLOPs: 46.39 | +7: iteration 1220/ 5111 | consumed samples: 312320 | consumed tokens: 639631360 | elapsed time per iteration (s): 0.76 | learning rate: 1.773E-04 | global batch size: 256 | lm loss: 3.645656E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.585 | TFLOPs: 46.10 | +7: iteration 1230/ 5111 | consumed samples: 314880 | consumed tokens: 644874240 | elapsed time per iteration (s): 0.75 | learning rate: 1.770E-04 | global batch size: 256 | lm loss: 3.636095E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.160 | TFLOPs: 47.00 | +7: iteration 1240/ 5111 | consumed samples: 317440 | consumed tokens: 650117120 | elapsed time per iteration (s): 0.76 | learning rate: 1.766E-04 | global batch size: 256 | lm loss: 3.658230E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.365 | TFLOPs: 46.48 | +7: iteration 1250/ 5111 | consumed samples: 320000 | consumed tokens: 655360000 | elapsed time per iteration (s): 0.76 | learning rate: 1.762E-04 | global batch size: 256 | lm loss: 3.625042E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.755 | TFLOPs: 46.26 | +7: iteration 1260/ 5111 | consumed samples: 322560 | consumed tokens: 660602880 | elapsed time per iteration (s): 0.75 | learning rate: 1.758E-04 | global batch size: 256 | lm loss: 3.628746E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.737 | TFLOPs: 46.94 | +7: iteration 1270/ 5111 | consumed samples: 325120 | consumed tokens: 665845760 | elapsed time per iteration (s): 0.77 | learning rate: 1.754E-04 | global batch size: 256 | lm loss: 3.619805E+00 | grad norm: 0.786 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.823 | TFLOPs: 45.72 | +7: iteration 1280/ 5111 | consumed samples: 327680 | consumed tokens: 671088640 | elapsed time per iteration (s): 0.76 | learning rate: 1.751E-04 | global batch size: 256 | lm loss: 3.646887E+00 | grad norm: 0.564 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.057 | TFLOPs: 46.57 | +7: iteration 1290/ 5111 | consumed samples: 330240 | consumed tokens: 676331520 | elapsed time per iteration (s): 0.75 | learning rate: 1.747E-04 | global batch size: 256 | lm loss: 3.620454E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.529 | TFLOPs: 47.05 | +7: iteration 1300/ 5111 | consumed samples: 332800 | consumed tokens: 681574400 | elapsed time per iteration (s): 0.75 | learning rate: 1.743E-04 | global batch size: 256 | lm loss: 3.628559E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.134 | TFLOPs: 47.13 | +7: iteration 1310/ 5111 | consumed samples: 335360 | consumed tokens: 686817280 | elapsed time per iteration (s): 0.77 | learning rate: 1.739E-04 | global batch size: 256 | lm loss: 3.606344E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.736 | TFLOPs: 45.84 | +7: iteration 1320/ 5111 | consumed samples: 337920 | consumed tokens: 692060160 | elapsed time per iteration (s): 0.75 | learning rate: 1.735E-04 | global batch size: 256 | lm loss: 3.598988E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.523 | TFLOPs: 47.19 | +7: iteration 1330/ 5111 | consumed samples: 340480 | consumed tokens: 697303040 | elapsed time per iteration (s): 0.77 | learning rate: 1.731E-04 | global batch size: 256 | lm loss: 3.566336E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.192 | TFLOPs: 45.77 | +7: iteration 1340/ 5111 | consumed samples: 343040 | consumed tokens: 702545920 | elapsed time per iteration (s): 0.76 | learning rate: 1.727E-04 | global batch size: 256 | lm loss: 3.565640E+00 | grad norm: 0.397 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.058 | TFLOPs: 46.16 | +7: iteration 1350/ 5111 | consumed samples: 345600 | consumed tokens: 707788800 | elapsed time per iteration (s): 0.76 | learning rate: 1.723E-04 | global batch size: 256 | lm loss: 3.572108E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.768 | TFLOPs: 46.26 | +7: iteration 1360/ 5111 | consumed samples: 348160 | consumed tokens: 713031680 | elapsed time per iteration (s): 0.76 | learning rate: 1.719E-04 | global batch size: 256 | lm loss: 3.565349E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.800 | TFLOPs: 45.99 | +7: iteration 1370/ 5111 | consumed samples: 350720 | consumed tokens: 718274560 | elapsed time per iteration (s): 0.77 | learning rate: 1.715E-04 | global batch size: 256 | lm loss: 3.545375E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.149 | TFLOPs: 45.62 | +7: iteration 1380/ 5111 | consumed samples: 353280 | consumed tokens: 723517440 | elapsed time per iteration (s): 0.75 | learning rate: 1.711E-04 | global batch size: 256 | lm loss: 3.547037E+00 | grad norm: 0.373 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.487 | TFLOPs: 46.91 | +7: iteration 1390/ 5111 | consumed samples: 355840 | consumed tokens: 728760320 | elapsed time per iteration (s): 0.76 | learning rate: 1.707E-04 | global batch size: 256 | lm loss: 3.542545E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.053 | TFLOPs: 46.57 | +7: iteration 1400/ 5111 | consumed samples: 358400 | consumed tokens: 734003200 | elapsed time per iteration (s): 0.76 | learning rate: 1.702E-04 | global batch size: 256 | lm loss: 3.557781E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.479 | TFLOPs: 46.49 | +7: iteration 1410/ 5111 | consumed samples: 360960 | consumed tokens: 739246080 | elapsed time per iteration (s): 0.76 | learning rate: 1.698E-04 | global batch size: 256 | lm loss: 3.538318E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.367 | TFLOPs: 46.07 | +7: iteration 1420/ 5111 | consumed samples: 363520 | consumed tokens: 744488960 | elapsed time per iteration (s): 0.76 | learning rate: 1.694E-04 | global batch size: 256 | lm loss: 3.521310E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.704 | TFLOPs: 46.39 | +7: iteration 1430/ 5111 | consumed samples: 366080 | consumed tokens: 749731840 | elapsed time per iteration (s): 0.77 | learning rate: 1.690E-04 | global batch size: 256 | lm loss: 3.560927E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.397 | TFLOPs: 45.52 | +7: iteration 1440/ 5111 | consumed samples: 368640 | consumed tokens: 754974720 | elapsed time per iteration (s): 0.75 | learning rate: 1.686E-04 | global batch size: 256 | lm loss: 3.518486E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.836 | TFLOPs: 46.82 | +7: iteration 1450/ 5111 | consumed samples: 371200 | consumed tokens: 760217600 | elapsed time per iteration (s): 0.76 | learning rate: 1.681E-04 | global batch size: 256 | lm loss: 3.540577E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.500 | TFLOPs: 46.50 | +7: iteration 1460/ 5111 | consumed samples: 373760 | consumed tokens: 765460480 | elapsed time per iteration (s): 0.76 | learning rate: 1.677E-04 | global batch size: 256 | lm loss: 3.523500E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.285 | TFLOPs: 46.05 | +7: iteration 1470/ 5111 | consumed samples: 376320 | consumed tokens: 770703360 | elapsed time per iteration (s): 0.75 | learning rate: 1.673E-04 | global batch size: 256 | lm loss: 3.535294E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.823 | TFLOPs: 46.95 | +7: iteration 1480/ 5111 | consumed samples: 378880 | consumed tokens: 775946240 | elapsed time per iteration (s): 0.75 | learning rate: 1.669E-04 | global batch size: 256 | lm loss: 3.541623E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.862 | TFLOPs: 46.82 | +7: iteration 1490/ 5111 | consumed samples: 381440 | consumed tokens: 781189120 | elapsed time per iteration (s): 0.77 | learning rate: 1.664E-04 | global batch size: 256 | lm loss: 3.485831E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.549 | TFLOPs: 45.68 | +7: iteration 1500/ 5111 | consumed samples: 384000 | consumed tokens: 786432000 | elapsed time per iteration (s): 0.78 | learning rate: 1.660E-04 | global batch size: 256 | lm loss: 3.505611E+00 | grad norm: 0.388 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.563 | TFLOPs: 45.27 | +7: iteration 1510/ 5111 | consumed samples: 386560 | consumed tokens: 791674880 | elapsed time per iteration (s): 0.75 | learning rate: 1.655E-04 | global batch size: 256 | lm loss: 3.520278E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.219 | TFLOPs: 46.59 | +7: iteration 1520/ 5111 | consumed samples: 389120 | consumed tokens: 796917760 | elapsed time per iteration (s): 0.75 | learning rate: 1.651E-04 | global batch size: 256 | lm loss: 3.491185E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.057 | TFLOPs: 46.98 | +7: iteration 1530/ 5111 | consumed samples: 391680 | consumed tokens: 802160640 | elapsed time per iteration (s): 0.76 | learning rate: 1.647E-04 | global batch size: 256 | lm loss: 3.475681E+00 | grad norm: 0.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.334 | TFLOPs: 46.20 | +7: iteration 1540/ 5111 | consumed samples: 394240 | consumed tokens: 807403520 | elapsed time per iteration (s): 0.75 | learning rate: 1.642E-04 | global batch size: 256 | lm loss: 3.514730E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.463 | TFLOPs: 47.18 | +7: iteration 1550/ 5111 | consumed samples: 396800 | consumed tokens: 812646400 | elapsed time per iteration (s): 0.75 | learning rate: 1.638E-04 | global batch size: 256 | lm loss: 3.469597E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.436 | TFLOPs: 46.62 | +7: iteration 1560/ 5111 | consumed samples: 399360 | consumed tokens: 817889280 | elapsed time per iteration (s): 0.76 | learning rate: 1.633E-04 | global batch size: 256 | lm loss: 3.464254E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.824 | TFLOPs: 46.13 | +7: iteration 1570/ 5111 | consumed samples: 401920 | consumed tokens: 823132160 | elapsed time per iteration (s): 0.76 | learning rate: 1.629E-04 | global batch size: 256 | lm loss: 3.463934E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.057 | TFLOPs: 46.43 | +7: iteration 1580/ 5111 | consumed samples: 404480 | consumed tokens: 828375040 | elapsed time per iteration (s): 0.75 | learning rate: 1.624E-04 | global batch size: 256 | lm loss: 3.437990E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.360 | TFLOPs: 46.61 | +7: iteration 1590/ 5111 | consumed samples: 407040 | consumed tokens: 833617920 | elapsed time per iteration (s): 0.75 | learning rate: 1.620E-04 | global batch size: 256 | lm loss: 3.442807E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.157 | TFLOPs: 46.72 | +7: iteration 1600/ 5111 | consumed samples: 409600 | consumed tokens: 838860800 | elapsed time per iteration (s): 0.75 | learning rate: 1.615E-04 | global batch size: 256 | lm loss: 3.481001E+00 | grad norm: 0.392 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.425 | TFLOPs: 47.03 | +7: iteration 1610/ 5111 | consumed samples: 412160 | consumed tokens: 844103680 | elapsed time per iteration (s): 0.76 | learning rate: 1.610E-04 | global batch size: 256 | lm loss: 3.452333E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.033 | TFLOPs: 46.16 | +7: iteration 1620/ 5111 | consumed samples: 414720 | consumed tokens: 849346560 | elapsed time per iteration (s): 0.76 | learning rate: 1.606E-04 | global batch size: 256 | lm loss: 3.464567E+00 | grad norm: 0.367 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.514 | TFLOPs: 46.36 | +7: iteration 1630/ 5111 | consumed samples: 417280 | consumed tokens: 854589440 | elapsed time per iteration (s): 0.76 | learning rate: 1.601E-04 | global batch size: 256 | lm loss: 3.464526E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.274 | TFLOPs: 46.46 | +7: iteration 1640/ 5111 | consumed samples: 419840 | consumed tokens: 859832320 | elapsed time per iteration (s): 0.76 | learning rate: 1.597E-04 | global batch size: 256 | lm loss: 3.453073E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.088 | TFLOPs: 46.44 | +7: iteration 1650/ 5111 | consumed samples: 422400 | consumed tokens: 865075200 | elapsed time per iteration (s): 0.75 | learning rate: 1.592E-04 | global batch size: 256 | lm loss: 3.465565E+00 | grad norm: 0.387 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.252 | TFLOPs: 46.87 | +7: iteration 1660/ 5111 | consumed samples: 424960 | consumed tokens: 870318080 | elapsed time per iteration (s): 0.76 | learning rate: 1.587E-04 | global batch size: 256 | lm loss: 3.458067E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.914 | TFLOPs: 46.55 | +7: iteration 1670/ 5111 | consumed samples: 427520 | consumed tokens: 875560960 | elapsed time per iteration (s): 0.75 | learning rate: 1.582E-04 | global batch size: 256 | lm loss: 3.449116E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.386 | TFLOPs: 46.89 | +7: iteration 1680/ 5111 | consumed samples: 430080 | consumed tokens: 880803840 | elapsed time per iteration (s): 0.76 | learning rate: 1.578E-04 | global batch size: 256 | lm loss: 3.421984E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.048 | TFLOPs: 46.43 | +7: iteration 1690/ 5111 | consumed samples: 432640 | consumed tokens: 886046720 | elapsed time per iteration (s): 0.78 | learning rate: 1.573E-04 | global batch size: 256 | lm loss: 3.460947E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.868 | TFLOPs: 45.04 | +7: iteration 1700/ 5111 | consumed samples: 435200 | consumed tokens: 891289600 | elapsed time per iteration (s): 0.79 | learning rate: 1.568E-04 | global batch size: 256 | lm loss: 3.420499E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.513 | TFLOPs: 44.57 | +7: iteration 1710/ 5111 | consumed samples: 437760 | consumed tokens: 896532480 | elapsed time per iteration (s): 0.75 | learning rate: 1.563E-04 | global batch size: 256 | lm loss: 3.414526E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.546 | TFLOPs: 46.78 | +7: iteration 1720/ 5111 | consumed samples: 440320 | consumed tokens: 901775360 | elapsed time per iteration (s): 0.76 | learning rate: 1.559E-04 | global batch size: 256 | lm loss: 3.437425E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.909 | TFLOPs: 46.41 | +7: iteration 1730/ 5111 | consumed samples: 442880 | consumed tokens: 907018240 | elapsed time per iteration (s): 0.76 | learning rate: 1.554E-04 | global batch size: 256 | lm loss: 3.416056E+00 | grad norm: 0.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.477 | TFLOPs: 46.36 | +7: iteration 1740/ 5111 | consumed samples: 445440 | consumed tokens: 912261120 | elapsed time per iteration (s): 0.75 | learning rate: 1.549E-04 | global batch size: 256 | lm loss: 3.428180E+00 | grad norm: 1.061 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.188 | TFLOPs: 47.00 | +7: iteration 1750/ 5111 | consumed samples: 448000 | consumed tokens: 917504000 | elapsed time per iteration (s): 0.76 | learning rate: 1.544E-04 | global batch size: 256 | lm loss: 3.442287E+00 | grad norm: 0.476 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.266 | TFLOPs: 46.33 | +7: iteration 1760/ 5111 | consumed samples: 450560 | consumed tokens: 922746880 | elapsed time per iteration (s): 0.76 | learning rate: 1.539E-04 | global batch size: 256 | lm loss: 3.398748E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.152 | TFLOPs: 46.17 | +7: iteration 1770/ 5111 | consumed samples: 453120 | consumed tokens: 927989760 | elapsed time per iteration (s): 0.76 | learning rate: 1.534E-04 | global batch size: 256 | lm loss: 3.414504E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.727 | TFLOPs: 46.53 | +7: iteration 1780/ 5111 | consumed samples: 455680 | consumed tokens: 933232640 | elapsed time per iteration (s): 0.75 | learning rate: 1.530E-04 | global batch size: 256 | lm loss: 3.416196E+00 | grad norm: 0.426 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.261 | TFLOPs: 46.74 | +7: iteration 1790/ 5111 | consumed samples: 458240 | consumed tokens: 938475520 | elapsed time per iteration (s): 0.76 | learning rate: 1.525E-04 | global batch size: 256 | lm loss: 3.418620E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.656 | TFLOPs: 46.24 | +7: iteration 1800/ 5111 | consumed samples: 460800 | consumed tokens: 943718400 | elapsed time per iteration (s): 0.80 | learning rate: 1.520E-04 | global batch size: 256 | lm loss: 3.427786E+00 | grad norm: 0.443 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 319.792 | TFLOPs: 43.93 | +7: iteration 1810/ 5111 | consumed samples: 463360 | consumed tokens: 948961280 | elapsed time per iteration (s): 0.76 | learning rate: 1.515E-04 | global batch size: 256 | lm loss: 3.404294E+00 | grad norm: 0.405 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.589 | TFLOPs: 46.37 | +7: iteration 1820/ 5111 | consumed samples: 465920 | consumed tokens: 954204160 | elapsed time per iteration (s): 0.76 | learning rate: 1.510E-04 | global batch size: 256 | lm loss: 3.385003E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.847 | TFLOPs: 46.54 | +7: iteration 1830/ 5111 | consumed samples: 468480 | consumed tokens: 959447040 | elapsed time per iteration (s): 0.76 | learning rate: 1.505E-04 | global batch size: 256 | lm loss: 3.431296E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.552 | TFLOPs: 46.37 | +7: iteration 1840/ 5111 | consumed samples: 471040 | consumed tokens: 964689920 | elapsed time per iteration (s): 0.78 | learning rate: 1.500E-04 | global batch size: 256 | lm loss: 3.402955E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.171 | TFLOPs: 44.94 | +7: iteration 1850/ 5111 | consumed samples: 473600 | consumed tokens: 969932800 | elapsed time per iteration (s): 0.75 | learning rate: 1.495E-04 | global batch size: 256 | lm loss: 3.396128E+00 | grad norm: 0.407 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.148 | TFLOPs: 46.72 | +7: iteration 1860/ 5111 | consumed samples: 476160 | consumed tokens: 975175680 | elapsed time per iteration (s): 0.75 | learning rate: 1.490E-04 | global batch size: 256 | lm loss: 3.392726E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.467 | TFLOPs: 46.90 | +7: iteration 1870/ 5111 | consumed samples: 478720 | consumed tokens: 980418560 | elapsed time per iteration (s): 0.75 | learning rate: 1.485E-04 | global batch size: 256 | lm loss: 3.356157E+00 | grad norm: 0.738 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.469 | TFLOPs: 46.77 | +7: iteration 1880/ 5111 | consumed samples: 481280 | consumed tokens: 985661440 | elapsed time per iteration (s): 0.76 | learning rate: 1.480E-04 | global batch size: 256 | lm loss: 3.364562E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.845 | TFLOPs: 46.41 | +7: iteration 1890/ 5111 | consumed samples: 483840 | consumed tokens: 990904320 | elapsed time per iteration (s): 0.77 | learning rate: 1.475E-04 | global batch size: 256 | lm loss: 3.384713E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.493 | TFLOPs: 45.67 | +7: iteration 1900/ 5111 | consumed samples: 486400 | consumed tokens: 996147200 | elapsed time per iteration (s): 0.76 | learning rate: 1.469E-04 | global batch size: 256 | lm loss: 3.373698E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.185 | TFLOPs: 46.18 | +7: iteration 1910/ 5111 | consumed samples: 488960 | consumed tokens: 1001390080 | elapsed time per iteration (s): 0.76 | learning rate: 1.464E-04 | global batch size: 256 | lm loss: 3.389396E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.391 | TFLOPs: 46.48 | +7: iteration 1920/ 5111 | consumed samples: 491520 | consumed tokens: 1006632960 | elapsed time per iteration (s): 0.75 | learning rate: 1.459E-04 | global batch size: 256 | lm loss: 3.349580E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.336 | TFLOPs: 47.16 | +7: iteration 1930/ 5111 | consumed samples: 494080 | consumed tokens: 1011875840 | elapsed time per iteration (s): 0.75 | learning rate: 1.454E-04 | global batch size: 256 | lm loss: 3.365863E+00 | grad norm: 0.435 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.443 | TFLOPs: 46.90 | +7: iteration 1940/ 5111 | consumed samples: 496640 | consumed tokens: 1017118720 | elapsed time per iteration (s): 0.76 | learning rate: 1.449E-04 | global batch size: 256 | lm loss: 3.390994E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.873 | TFLOPs: 46.13 | +7: iteration 1950/ 5111 | consumed samples: 499200 | consumed tokens: 1022361600 | elapsed time per iteration (s): 0.75 | learning rate: 1.444E-04 | global batch size: 256 | lm loss: 3.382515E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.021 | TFLOPs: 46.70 | +7: iteration 1960/ 5111 | consumed samples: 501760 | consumed tokens: 1027604480 | elapsed time per iteration (s): 0.75 | learning rate: 1.439E-04 | global batch size: 256 | lm loss: 3.382496E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.158 | TFLOPs: 46.72 | +7: iteration 1970/ 5111 | consumed samples: 504320 | consumed tokens: 1032847360 | elapsed time per iteration (s): 0.77 | learning rate: 1.433E-04 | global batch size: 256 | lm loss: 3.379280E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.379 | TFLOPs: 45.52 | +7: iteration 1980/ 5111 | consumed samples: 506880 | consumed tokens: 1038090240 | elapsed time per iteration (s): 0.76 | learning rate: 1.428E-04 | global batch size: 256 | lm loss: 3.362263E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.486 | TFLOPs: 46.22 | +7: iteration 1990/ 5111 | consumed samples: 509440 | consumed tokens: 1043333120 | elapsed time per iteration (s): 0.76 | learning rate: 1.423E-04 | global batch size: 256 | lm loss: 3.347859E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.160 | TFLOPs: 46.04 | +0: [2022-11-29 17:32:39,823] [INFO] [logging.py:68:log_dist] [Rank 0] step=2000, skipped=0, lr=[0.00014178345342766413, 0.00014178345342766413, 0.00014178345342766413], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 2000/ 5111 | consumed samples: 512000 | consumed tokens: 1048576000 | elapsed time per iteration (s): 0.76 | learning rate: 1.418E-04 | global batch size: 256 | lm loss: 3.352945E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.678 | TFLOPs: 46.25 | +0: steps: 2000 loss: 3.3523 iter time (s): 0.770 samples/sec: 332.317 +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 2000 | lm loss value: 3.246904E+00 | lm loss PPL: 2.571061E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 2000 to checkpoints_619moscar +0: [2022-11-29 17:32:40,088] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step2000 is begin to save! +0: [2022-11-29 17:32:40,093] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:32:40,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:32:40,261] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:32:40,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:32:40,316] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:32:40,370] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:32:40,370] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:32:40,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:32:40,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:32:40,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:32:40,482] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:32:40,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:32:40,540] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:32:40,594] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:32:40,595] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:32:40,651] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:32:40,651] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:32:40,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:32:40,707] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:32:40,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:32:40,762] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:32:40,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:32:40,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:32:40,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:32:40,874] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:32:40,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:32:40,929] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:32:40,984] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:32:40,985] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:32:41,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:32:41,042] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:32:41,095] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:32:41,096] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/layer_18-model_00-model_states.pt... +0: [2022-11-29 17:32:41,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/layer_18-model_00-model_states.pt. +0: [2022-11-29 17:32:41,152] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:32:41,206] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:32:41,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/layer_20-model_00-model_states.pt... +0: [2022-11-29 17:32:41,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/layer_20-model_00-model_states.pt. +0: [2022-11-29 17:32:41,264] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/layer_21-model_00-model_states.pt... +0: [2022-11-29 17:32:41,320] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/layer_21-model_00-model_states.pt. +0: [2022-11-29 17:32:41,321] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/layer_23-model_00-model_states.pt... +0: [2022-11-29 17:32:41,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/layer_23-model_00-model_states.pt. +0: [2022-11-29 17:32:41,323] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_619moscar/global_step2000/mp_rank_00_model_states.pt +0: [2022-11-29 17:32:41,323] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:32:41,326] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:32:41,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:32:41,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:32:41,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:32:41,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:32:41,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:32:41,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:32:41,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:32:41,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:32:41,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:32:41,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:32:41,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:32:41,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:32:41,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:32:41,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:32:41,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:32:41,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:32:41,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:32:41,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:32:41,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:32:41,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:32:41,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:32:41,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:32:41,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:32:41,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:32:41,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:32:41,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:32:41,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:32:41,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:32:41,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:32:41,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:32:41,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:32:41,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:32:41,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:32:41,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:32:41,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:32:41,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:32:41,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:32:41,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +2: [2022-11-29 17:32:41,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:32:41,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:32:41,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:32:41,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:32:41,491] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:32:41,491] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:32:41,491] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:32:41,491] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:32:41,491] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:32:41,491] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:32:41,495] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:32:41,495] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:32:41,495] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:32:41,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:32:41,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:32:41,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:32:41,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:32:41,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:32:41,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:32:41,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:32:41,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:32:41,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:32:41,498] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:32:41,498] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:32:41,498] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:32:41,499] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:32:41,499] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:32:41,499] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:32:41,500] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:32:41,500] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:32:41,500] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:32:41,500] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:32:41,500] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:32:41,500] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:32:41,501] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:32:41,501] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:32:41,502] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:32:41,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:32:41,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:32:41,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:32:41,507] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:32:41,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:32:41,507] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:32:41,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:32:41,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:32:41,507] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:32:41,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:32:41,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:32:41,511] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:32:41,511] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:32:41,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:32:41,512] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:32:41,513] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:32:41,513] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:32:41,513] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:32:41,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:32:41,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:32:41,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:32:41,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:32:41,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:32:41,509] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:32:41,509] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:32:41,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:32:41,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:32:41,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:32:41,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:32:41,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:32:41,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:32:41,506] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:32:41,506] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:32:41,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:32:41,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:32:41,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:32:41,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:32:41,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:32:41,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:32:41,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:32:41,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:32:41,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:32:41,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:32:41,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:32:41,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:32:41,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:32:41,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:32:41,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:32:41,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:32:41,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:32:41,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:32:41,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:32:41,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:32:41,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:32:41,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:32:41,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:32:41,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:32:41,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:32:41,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:32:41,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:32:41,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:32:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:32:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:32:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:32:41,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:32:41,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:32:41,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:32:41,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:32:41,605] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:32:41,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:32:41,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:32:41,644] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:32:41,644] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:32:41,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:32:41,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:32:41,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:32:41,679] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:32:41,679] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:32:41,679] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:32:41,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:32:41,705] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:32:41,705] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:32:41,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:32:41,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:32:41,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:32:41,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:32:41,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:32:41,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:32:41,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:32:41,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:32:41,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:32:41,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:32:41,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:32:41,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:32:41,725] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:32:41,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:32:41,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:32:41,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:32:41,727] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:32:41,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:32:41,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:32:41,728] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:32:41,728] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:32:41,734] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:32:41,734] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:32:41,734] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:32:41,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:32:41,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:32:41,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:32:41,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:32:41,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:32:41,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:32:41,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:32:41,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:32:41,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:32:41,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:32:41,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:32:41,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: successfully saved checkpoint at iteration 2000 to checkpoints_619moscar +7: time (ms) | save-checkpoint: 1718.68 +7: iteration 2010/ 5111 | consumed samples: 514560 | consumed tokens: 1053818880 | elapsed time per iteration (s): 0.97 | learning rate: 1.413E-04 | global batch size: 256 | lm loss: 3.339148E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 265.107 | TFLOPs: 36.41 | +7: iteration 2020/ 5111 | consumed samples: 517120 | consumed tokens: 1059061760 | elapsed time per iteration (s): 0.75 | learning rate: 1.407E-04 | global batch size: 256 | lm loss: 3.339874E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.263 | TFLOPs: 47.15 | +7: iteration 2030/ 5111 | consumed samples: 519680 | consumed tokens: 1064304640 | elapsed time per iteration (s): 0.76 | learning rate: 1.402E-04 | global batch size: 256 | lm loss: 3.354098E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.953 | TFLOPs: 46.56 | +7: iteration 2040/ 5111 | consumed samples: 522240 | consumed tokens: 1069547520 | elapsed time per iteration (s): 0.77 | learning rate: 1.397E-04 | global batch size: 256 | lm loss: 3.320094E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.313 | TFLOPs: 45.92 | +7: iteration 2050/ 5111 | consumed samples: 524800 | consumed tokens: 1074790400 | elapsed time per iteration (s): 0.76 | learning rate: 1.392E-04 | global batch size: 256 | lm loss: 3.325367E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.196 | TFLOPs: 46.45 | +7: iteration 2060/ 5111 | consumed samples: 527360 | consumed tokens: 1080033280 | elapsed time per iteration (s): 0.75 | learning rate: 1.386E-04 | global batch size: 256 | lm loss: 3.322867E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.808 | TFLOPs: 46.95 | +7: iteration 2070/ 5111 | consumed samples: 529920 | consumed tokens: 1085276160 | elapsed time per iteration (s): 0.75 | learning rate: 1.381E-04 | global batch size: 256 | lm loss: 3.307778E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.502 | TFLOPs: 46.91 | +7: iteration 2080/ 5111 | consumed samples: 532480 | consumed tokens: 1090519040 | elapsed time per iteration (s): 0.76 | learning rate: 1.376E-04 | global batch size: 256 | lm loss: 3.318077E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.740 | TFLOPs: 46.53 | +7: iteration 2090/ 5111 | consumed samples: 535040 | consumed tokens: 1095761920 | elapsed time per iteration (s): 0.75 | learning rate: 1.370E-04 | global batch size: 256 | lm loss: 3.300783E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.660 | TFLOPs: 47.07 | +7: iteration 2100/ 5111 | consumed samples: 537600 | consumed tokens: 1101004800 | elapsed time per iteration (s): 0.76 | learning rate: 1.365E-04 | global batch size: 256 | lm loss: 3.323903E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.857 | TFLOPs: 46.54 | +7: iteration 2110/ 5111 | consumed samples: 540160 | consumed tokens: 1106247680 | elapsed time per iteration (s): 0.75 | learning rate: 1.360E-04 | global batch size: 256 | lm loss: 3.354566E+00 | grad norm: 0.697 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.378 | TFLOPs: 46.75 | +7: iteration 2120/ 5111 | consumed samples: 542720 | consumed tokens: 1111490560 | elapsed time per iteration (s): 0.75 | learning rate: 1.354E-04 | global batch size: 256 | lm loss: 3.337229E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.776 | TFLOPs: 46.95 | +7: iteration 2130/ 5111 | consumed samples: 545280 | consumed tokens: 1116733440 | elapsed time per iteration (s): 0.75 | learning rate: 1.349E-04 | global batch size: 256 | lm loss: 3.318621E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.160 | TFLOPs: 47.14 | +7: iteration 2140/ 5111 | consumed samples: 547840 | consumed tokens: 1121976320 | elapsed time per iteration (s): 0.76 | learning rate: 1.344E-04 | global batch size: 256 | lm loss: 3.325727E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.288 | TFLOPs: 46.47 | +7: iteration 2150/ 5111 | consumed samples: 550400 | consumed tokens: 1127219200 | elapsed time per iteration (s): 0.76 | learning rate: 1.338E-04 | global batch size: 256 | lm loss: 3.316576E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.328 | TFLOPs: 46.20 | +7: iteration 2160/ 5111 | consumed samples: 552960 | consumed tokens: 1132462080 | elapsed time per iteration (s): 0.75 | learning rate: 1.333E-04 | global batch size: 256 | lm loss: 3.339444E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.478 | TFLOPs: 46.90 | +7: iteration 2170/ 5111 | consumed samples: 555520 | consumed tokens: 1137704960 | elapsed time per iteration (s): 0.75 | learning rate: 1.327E-04 | global batch size: 256 | lm loss: 3.311592E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.065 | TFLOPs: 46.99 | +7: iteration 2180/ 5111 | consumed samples: 558080 | consumed tokens: 1142947840 | elapsed time per iteration (s): 0.75 | learning rate: 1.322E-04 | global batch size: 256 | lm loss: 3.303490E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.262 | TFLOPs: 46.88 | +7: iteration 2190/ 5111 | consumed samples: 560640 | consumed tokens: 1148190720 | elapsed time per iteration (s): 0.75 | learning rate: 1.317E-04 | global batch size: 256 | lm loss: 3.306535E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.904 | TFLOPs: 46.69 | +7: iteration 2200/ 5111 | consumed samples: 563200 | consumed tokens: 1153433600 | elapsed time per iteration (s): 0.75 | learning rate: 1.311E-04 | global batch size: 256 | lm loss: 3.300140E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.952 | TFLOPs: 46.70 | +7: iteration 2210/ 5111 | consumed samples: 565760 | consumed tokens: 1158676480 | elapsed time per iteration (s): 0.76 | learning rate: 1.306E-04 | global batch size: 256 | lm loss: 3.300035E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.051 | TFLOPs: 46.30 | +7: iteration 2220/ 5111 | consumed samples: 568320 | consumed tokens: 1163919360 | elapsed time per iteration (s): 0.76 | learning rate: 1.300E-04 | global batch size: 256 | lm loss: 3.304564E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.998 | TFLOPs: 46.43 | +7: iteration 2230/ 5111 | consumed samples: 570880 | consumed tokens: 1169162240 | elapsed time per iteration (s): 0.76 | learning rate: 1.295E-04 | global batch size: 256 | lm loss: 3.286304E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.956 | TFLOPs: 46.28 | +7: iteration 2240/ 5111 | consumed samples: 573440 | consumed tokens: 1174405120 | elapsed time per iteration (s): 0.75 | learning rate: 1.289E-04 | global batch size: 256 | lm loss: 3.313428E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.195 | TFLOPs: 46.59 | +7: iteration 2250/ 5111 | consumed samples: 576000 | consumed tokens: 1179648000 | elapsed time per iteration (s): 0.76 | learning rate: 1.284E-04 | global batch size: 256 | lm loss: 3.296807E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.879 | TFLOPs: 46.00 | +7: iteration 2260/ 5111 | consumed samples: 578560 | consumed tokens: 1184890880 | elapsed time per iteration (s): 0.76 | learning rate: 1.278E-04 | global batch size: 256 | lm loss: 3.281841E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.627 | TFLOPs: 46.38 | +7: iteration 2270/ 5111 | consumed samples: 581120 | consumed tokens: 1190133760 | elapsed time per iteration (s): 0.75 | learning rate: 1.273E-04 | global batch size: 256 | lm loss: 3.281209E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.833 | TFLOPs: 46.82 | +7: iteration 2280/ 5111 | consumed samples: 583680 | consumed tokens: 1195376640 | elapsed time per iteration (s): 0.76 | learning rate: 1.267E-04 | global batch size: 256 | lm loss: 3.294724E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.234 | TFLOPs: 46.05 | +7: iteration 2290/ 5111 | consumed samples: 586240 | consumed tokens: 1200619520 | elapsed time per iteration (s): 0.75 | learning rate: 1.262E-04 | global batch size: 256 | lm loss: 3.298811E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.782 | TFLOPs: 46.95 | +7: iteration 2300/ 5111 | consumed samples: 588800 | consumed tokens: 1205862400 | elapsed time per iteration (s): 0.77 | learning rate: 1.256E-04 | global batch size: 256 | lm loss: 3.269610E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.648 | TFLOPs: 45.69 | +7: iteration 2310/ 5111 | consumed samples: 591360 | consumed tokens: 1211105280 | elapsed time per iteration (s): 0.75 | learning rate: 1.251E-04 | global batch size: 256 | lm loss: 3.278566E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.077 | TFLOPs: 46.85 | +7: iteration 2320/ 5111 | consumed samples: 593920 | consumed tokens: 1216348160 | elapsed time per iteration (s): 0.75 | learning rate: 1.245E-04 | global batch size: 256 | lm loss: 3.258897E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.643 | TFLOPs: 46.79 | +7: iteration 2330/ 5111 | consumed samples: 596480 | consumed tokens: 1221591040 | elapsed time per iteration (s): 0.75 | learning rate: 1.240E-04 | global batch size: 256 | lm loss: 3.287956E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.737 | TFLOPs: 46.67 | +7: iteration 2340/ 5111 | consumed samples: 599040 | consumed tokens: 1226833920 | elapsed time per iteration (s): 0.75 | learning rate: 1.234E-04 | global batch size: 256 | lm loss: 3.276577E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.818 | TFLOPs: 47.09 | +7: iteration 2350/ 5111 | consumed samples: 601600 | consumed tokens: 1232076800 | elapsed time per iteration (s): 0.76 | learning rate: 1.229E-04 | global batch size: 256 | lm loss: 3.290366E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.796 | TFLOPs: 46.40 | +7: iteration 2360/ 5111 | consumed samples: 604160 | consumed tokens: 1237319680 | elapsed time per iteration (s): 0.76 | learning rate: 1.223E-04 | global batch size: 256 | lm loss: 3.251630E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.956 | TFLOPs: 46.28 | +7: iteration 2370/ 5111 | consumed samples: 606720 | consumed tokens: 1242562560 | elapsed time per iteration (s): 0.74 | learning rate: 1.218E-04 | global batch size: 256 | lm loss: 3.231941E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.069 | TFLOPs: 47.26 | +7: iteration 2380/ 5111 | consumed samples: 609280 | consumed tokens: 1247805440 | elapsed time per iteration (s): 0.76 | learning rate: 1.212E-04 | global batch size: 256 | lm loss: 3.236805E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.621 | TFLOPs: 46.37 | +7: iteration 2390/ 5111 | consumed samples: 611840 | consumed tokens: 1253048320 | elapsed time per iteration (s): 0.76 | learning rate: 1.207E-04 | global batch size: 256 | lm loss: 3.280304E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.657 | TFLOPs: 46.52 | +7: iteration 2400/ 5111 | consumed samples: 614400 | consumed tokens: 1258291200 | elapsed time per iteration (s): 0.75 | learning rate: 1.201E-04 | global batch size: 256 | lm loss: 3.238954E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.142 | TFLOPs: 46.86 | +7: iteration 2410/ 5111 | consumed samples: 616960 | consumed tokens: 1263534080 | elapsed time per iteration (s): 0.75 | learning rate: 1.196E-04 | global batch size: 256 | lm loss: 3.268679E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.167 | TFLOPs: 46.59 | +7: iteration 2420/ 5111 | consumed samples: 619520 | consumed tokens: 1268776960 | elapsed time per iteration (s): 0.75 | learning rate: 1.190E-04 | global batch size: 256 | lm loss: 3.245691E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.034 | TFLOPs: 47.12 | +7: iteration 2430/ 5111 | consumed samples: 622080 | consumed tokens: 1274019840 | elapsed time per iteration (s): 0.76 | learning rate: 1.184E-04 | global batch size: 256 | lm loss: 3.270460E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.178 | TFLOPs: 46.45 | +7: iteration 2440/ 5111 | consumed samples: 624640 | consumed tokens: 1279262720 | elapsed time per iteration (s): 0.75 | learning rate: 1.179E-04 | global batch size: 256 | lm loss: 3.250480E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.521 | TFLOPs: 47.05 | +7: iteration 2450/ 5111 | consumed samples: 627200 | consumed tokens: 1284505600 | elapsed time per iteration (s): 0.76 | learning rate: 1.173E-04 | global batch size: 256 | lm loss: 3.262238E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.822 | TFLOPs: 46.54 | +7: iteration 2460/ 5111 | consumed samples: 629760 | consumed tokens: 1289748480 | elapsed time per iteration (s): 0.75 | learning rate: 1.168E-04 | global batch size: 256 | lm loss: 3.238959E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.950 | TFLOPs: 47.11 | +7: iteration 2470/ 5111 | consumed samples: 632320 | consumed tokens: 1294991360 | elapsed time per iteration (s): 0.75 | learning rate: 1.162E-04 | global batch size: 256 | lm loss: 3.259750E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.623 | TFLOPs: 46.65 | +7: iteration 2480/ 5111 | consumed samples: 634880 | consumed tokens: 1300234240 | elapsed time per iteration (s): 0.74 | learning rate: 1.157E-04 | global batch size: 256 | lm loss: 3.260479E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.850 | TFLOPs: 47.23 | +7: iteration 2490/ 5111 | consumed samples: 637440 | consumed tokens: 1305477120 | elapsed time per iteration (s): 0.75 | learning rate: 1.151E-04 | global batch size: 256 | lm loss: 3.249510E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.332 | TFLOPs: 46.75 | +7: iteration 2500/ 5111 | consumed samples: 640000 | consumed tokens: 1310720000 | elapsed time per iteration (s): 0.76 | learning rate: 1.145E-04 | global batch size: 256 | lm loss: 3.272220E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.717 | TFLOPs: 46.39 | +7: iteration 2510/ 5111 | consumed samples: 642560 | consumed tokens: 1315962880 | elapsed time per iteration (s): 0.75 | learning rate: 1.140E-04 | global batch size: 256 | lm loss: 3.270697E+00 | grad norm: 0.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.456 | TFLOPs: 46.76 | +7: iteration 2520/ 5111 | consumed samples: 645120 | consumed tokens: 1321205760 | elapsed time per iteration (s): 0.76 | learning rate: 1.134E-04 | global batch size: 256 | lm loss: 3.254284E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.293 | TFLOPs: 46.33 | +7: iteration 2530/ 5111 | consumed samples: 647680 | consumed tokens: 1326448640 | elapsed time per iteration (s): 0.75 | learning rate: 1.129E-04 | global batch size: 256 | lm loss: 3.246981E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.266 | TFLOPs: 46.60 | +7: iteration 2540/ 5111 | consumed samples: 650240 | consumed tokens: 1331691520 | elapsed time per iteration (s): 0.75 | learning rate: 1.123E-04 | global batch size: 256 | lm loss: 3.247028E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.552 | TFLOPs: 46.78 | +7: iteration 2550/ 5111 | consumed samples: 652800 | consumed tokens: 1336934400 | elapsed time per iteration (s): 0.75 | learning rate: 1.118E-04 | global batch size: 256 | lm loss: 3.253305E+00 | grad norm: 0.368 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.343 | TFLOPs: 46.75 | +7: iteration 2560/ 5111 | consumed samples: 655360 | consumed tokens: 1342177280 | elapsed time per iteration (s): 0.75 | learning rate: 1.112E-04 | global batch size: 256 | lm loss: 3.250311E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.564 | TFLOPs: 47.19 | +7: iteration 2570/ 5111 | consumed samples: 657920 | consumed tokens: 1347420160 | elapsed time per iteration (s): 0.75 | learning rate: 1.106E-04 | global batch size: 256 | lm loss: 3.243518E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.195 | TFLOPs: 46.87 | +7: iteration 2580/ 5111 | consumed samples: 660480 | consumed tokens: 1352663040 | elapsed time per iteration (s): 0.75 | learning rate: 1.101E-04 | global batch size: 256 | lm loss: 3.246718E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.672 | TFLOPs: 46.79 | +7: iteration 2590/ 5111 | consumed samples: 663040 | consumed tokens: 1357905920 | elapsed time per iteration (s): 0.76 | learning rate: 1.095E-04 | global batch size: 256 | lm loss: 3.222816E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.873 | TFLOPs: 46.00 | +7: iteration 2600/ 5111 | consumed samples: 665600 | consumed tokens: 1363148800 | elapsed time per iteration (s): 0.75 | learning rate: 1.090E-04 | global batch size: 256 | lm loss: 3.220594E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.062 | TFLOPs: 46.85 | +7: iteration 2610/ 5111 | consumed samples: 668160 | consumed tokens: 1368391680 | elapsed time per iteration (s): 0.78 | learning rate: 1.084E-04 | global batch size: 256 | lm loss: 3.219902E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.013 | TFLOPs: 45.19 | +7: iteration 2620/ 5111 | consumed samples: 670720 | consumed tokens: 1373634560 | elapsed time per iteration (s): 0.75 | learning rate: 1.078E-04 | global batch size: 256 | lm loss: 3.224007E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.381 | TFLOPs: 47.03 | +7: iteration 2630/ 5111 | consumed samples: 673280 | consumed tokens: 1378877440 | elapsed time per iteration (s): 0.75 | learning rate: 1.073E-04 | global batch size: 256 | lm loss: 3.208368E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.592 | TFLOPs: 46.78 | +7: iteration 2640/ 5111 | consumed samples: 675840 | consumed tokens: 1384120320 | elapsed time per iteration (s): 0.77 | learning rate: 1.067E-04 | global batch size: 256 | lm loss: 3.236165E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.768 | TFLOPs: 45.71 | +7: iteration 2650/ 5111 | consumed samples: 678400 | consumed tokens: 1389363200 | elapsed time per iteration (s): 0.77 | learning rate: 1.062E-04 | global batch size: 256 | lm loss: 3.195971E+00 | grad norm: 0.508 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.329 | TFLOPs: 45.92 | +7: iteration 2660/ 5111 | consumed samples: 680960 | consumed tokens: 1394606080 | elapsed time per iteration (s): 0.75 | learning rate: 1.056E-04 | global batch size: 256 | lm loss: 3.266798E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.423 | TFLOPs: 46.62 | +7: iteration 2670/ 5111 | consumed samples: 683520 | consumed tokens: 1399848960 | elapsed time per iteration (s): 0.76 | learning rate: 1.051E-04 | global batch size: 256 | lm loss: 3.220483E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.535 | TFLOPs: 46.50 | +7: iteration 2680/ 5111 | consumed samples: 686080 | consumed tokens: 1405091840 | elapsed time per iteration (s): 0.75 | learning rate: 1.045E-04 | global batch size: 256 | lm loss: 3.196742E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.068 | TFLOPs: 46.71 | +7: iteration 2690/ 5111 | consumed samples: 688640 | consumed tokens: 1410334720 | elapsed time per iteration (s): 0.75 | learning rate: 1.039E-04 | global batch size: 256 | lm loss: 3.192284E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.439 | TFLOPs: 46.90 | +7: iteration 2700/ 5111 | consumed samples: 691200 | consumed tokens: 1415577600 | elapsed time per iteration (s): 0.77 | learning rate: 1.034E-04 | global batch size: 256 | lm loss: 3.209785E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.582 | TFLOPs: 45.82 | +7: iteration 2710/ 5111 | consumed samples: 693760 | consumed tokens: 1420820480 | elapsed time per iteration (s): 0.75 | learning rate: 1.028E-04 | global batch size: 256 | lm loss: 3.209158E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.377 | TFLOPs: 46.75 | +7: iteration 2720/ 5111 | consumed samples: 696320 | consumed tokens: 1426063360 | elapsed time per iteration (s): 0.77 | learning rate: 1.023E-04 | global batch size: 256 | lm loss: 3.194061E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.403 | TFLOPs: 45.52 | +7: iteration 2730/ 5111 | consumed samples: 698880 | consumed tokens: 1431306240 | elapsed time per iteration (s): 0.75 | learning rate: 1.017E-04 | global batch size: 256 | lm loss: 3.207217E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.677 | TFLOPs: 47.07 | +7: iteration 2740/ 5111 | consumed samples: 701440 | consumed tokens: 1436549120 | elapsed time per iteration (s): 0.75 | learning rate: 1.012E-04 | global batch size: 256 | lm loss: 3.187718E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.559 | TFLOPs: 46.92 | +7: iteration 2750/ 5111 | consumed samples: 704000 | consumed tokens: 1441792000 | elapsed time per iteration (s): 0.76 | learning rate: 1.006E-04 | global batch size: 256 | lm loss: 3.197805E+00 | grad norm: 0.539 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.759 | TFLOPs: 46.53 | +7: iteration 2760/ 5111 | consumed samples: 706560 | consumed tokens: 1447034880 | elapsed time per iteration (s): 0.76 | learning rate: 1.000E-04 | global batch size: 256 | lm loss: 3.229074E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.503 | TFLOPs: 46.50 | +7: iteration 2770/ 5111 | consumed samples: 709120 | consumed tokens: 1452277760 | elapsed time per iteration (s): 0.75 | learning rate: 9.949E-05 | global batch size: 256 | lm loss: 3.198982E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.344 | TFLOPs: 47.02 | +7: iteration 2780/ 5111 | consumed samples: 711680 | consumed tokens: 1457520640 | elapsed time per iteration (s): 0.76 | learning rate: 9.893E-05 | global batch size: 256 | lm loss: 3.190417E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.473 | TFLOPs: 46.49 | +7: iteration 2790/ 5111 | consumed samples: 714240 | consumed tokens: 1462763520 | elapsed time per iteration (s): 0.77 | learning rate: 9.838E-05 | global batch size: 256 | lm loss: 3.211803E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.298 | TFLOPs: 45.64 | +7: iteration 2800/ 5111 | consumed samples: 716800 | consumed tokens: 1468006400 | elapsed time per iteration (s): 0.76 | learning rate: 9.782E-05 | global batch size: 256 | lm loss: 3.162518E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.695 | TFLOPs: 45.97 | +7: iteration 2810/ 5111 | consumed samples: 719360 | consumed tokens: 1473249280 | elapsed time per iteration (s): 0.78 | learning rate: 9.727E-05 | global batch size: 256 | lm loss: 3.190660E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.154 | TFLOPs: 45.35 | +7: iteration 2820/ 5111 | consumed samples: 721920 | consumed tokens: 1478492160 | elapsed time per iteration (s): 0.76 | learning rate: 9.672E-05 | global batch size: 256 | lm loss: 3.197194E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.207 | TFLOPs: 46.18 | +7: iteration 2830/ 5111 | consumed samples: 724480 | consumed tokens: 1483735040 | elapsed time per iteration (s): 0.75 | learning rate: 9.617E-05 | global batch size: 256 | lm loss: 3.176500E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.183 | TFLOPs: 46.86 | +7: iteration 2840/ 5111 | consumed samples: 727040 | consumed tokens: 1488977920 | elapsed time per iteration (s): 0.75 | learning rate: 9.561E-05 | global batch size: 256 | lm loss: 3.192611E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.846 | TFLOPs: 46.82 | +7: iteration 2850/ 5111 | consumed samples: 729600 | consumed tokens: 1494220800 | elapsed time per iteration (s): 0.74 | learning rate: 9.506E-05 | global batch size: 256 | lm loss: 3.208068E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.708 | TFLOPs: 47.21 | +7: iteration 2860/ 5111 | consumed samples: 732160 | consumed tokens: 1499463680 | elapsed time per iteration (s): 0.75 | learning rate: 9.451E-05 | global batch size: 256 | lm loss: 3.189607E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.593 | TFLOPs: 46.92 | +7: iteration 2870/ 5111 | consumed samples: 734720 | consumed tokens: 1504706560 | elapsed time per iteration (s): 0.76 | learning rate: 9.396E-05 | global batch size: 256 | lm loss: 3.202270E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.924 | TFLOPs: 46.55 | +7: iteration 2880/ 5111 | consumed samples: 737280 | consumed tokens: 1509949440 | elapsed time per iteration (s): 0.76 | learning rate: 9.341E-05 | global batch size: 256 | lm loss: 3.170928E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.376 | TFLOPs: 46.20 | +7: iteration 2890/ 5111 | consumed samples: 739840 | consumed tokens: 1515192320 | elapsed time per iteration (s): 0.76 | learning rate: 9.286E-05 | global batch size: 256 | lm loss: 3.167513E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.824 | TFLOPs: 46.40 | +7: iteration 2900/ 5111 | consumed samples: 742400 | consumed tokens: 1520435200 | elapsed time per iteration (s): 0.75 | learning rate: 9.232E-05 | global batch size: 256 | lm loss: 3.192402E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.539 | TFLOPs: 47.05 | +7: iteration 2910/ 5111 | consumed samples: 744960 | consumed tokens: 1525678080 | elapsed time per iteration (s): 0.76 | learning rate: 9.177E-05 | global batch size: 256 | lm loss: 3.191056E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.886 | TFLOPs: 46.55 | +7: iteration 2920/ 5111 | consumed samples: 747520 | consumed tokens: 1530920960 | elapsed time per iteration (s): 0.75 | learning rate: 9.122E-05 | global batch size: 256 | lm loss: 3.173017E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.828 | TFLOPs: 46.82 | +7: iteration 2930/ 5111 | consumed samples: 750080 | consumed tokens: 1536163840 | elapsed time per iteration (s): 0.75 | learning rate: 9.068E-05 | global batch size: 256 | lm loss: 3.147209E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.495 | TFLOPs: 46.91 | +7: iteration 2940/ 5111 | consumed samples: 752640 | consumed tokens: 1541406720 | elapsed time per iteration (s): 0.77 | learning rate: 9.013E-05 | global batch size: 256 | lm loss: 3.210669E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.422 | TFLOPs: 45.66 | +7: iteration 2950/ 5111 | consumed samples: 755200 | consumed tokens: 1546649600 | elapsed time per iteration (s): 0.75 | learning rate: 8.959E-05 | global batch size: 256 | lm loss: 3.154646E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.416 | TFLOPs: 47.03 | +7: iteration 2960/ 5111 | consumed samples: 757760 | consumed tokens: 1551892480 | elapsed time per iteration (s): 0.75 | learning rate: 8.904E-05 | global batch size: 256 | lm loss: 3.150537E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.988 | TFLOPs: 46.70 | +7: iteration 2970/ 5111 | consumed samples: 760320 | consumed tokens: 1557135360 | elapsed time per iteration (s): 0.75 | learning rate: 8.850E-05 | global batch size: 256 | lm loss: 3.153581E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.711 | TFLOPs: 47.07 | +7: iteration 2980/ 5111 | consumed samples: 762880 | consumed tokens: 1562378240 | elapsed time per iteration (s): 0.75 | learning rate: 8.796E-05 | global batch size: 256 | lm loss: 3.213158E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.988 | TFLOPs: 47.11 | +7: iteration 2990/ 5111 | consumed samples: 765440 | consumed tokens: 1567621120 | elapsed time per iteration (s): 0.77 | learning rate: 8.742E-05 | global batch size: 256 | lm loss: 3.142105E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.120 | TFLOPs: 45.76 | +7: iteration 3000/ 5111 | consumed samples: 768000 | consumed tokens: 1572864000 | elapsed time per iteration (s): 0.74 | learning rate: 8.687E-05 | global batch size: 256 | lm loss: 3.151249E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.821 | TFLOPs: 47.23 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 3000 | lm loss value: 2.997254E+00 | lm loss PPL: 2.003045E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 3000 to checkpoints_619moscar +0: [2022-11-29 17:45:16,903] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step3000 is begin to save! +0: [2022-11-29 17:45:16,907] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:45:17,078] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:45:17,078] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:45:17,135] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:45:17,136] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:45:17,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:45:17,190] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:45:17,244] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:45:17,245] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:45:17,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:45:17,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:45:17,357] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:45:17,357] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:45:17,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:45:17,412] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:45:17,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:45:17,472] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:45:17,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:45:17,529] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:45:17,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:45:17,585] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:45:17,642] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:45:17,642] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:45:17,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:45:17,699] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:45:17,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:45:17,756] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:45:17,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:45:17,810] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:45:17,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:45:17,865] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:45:17,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:45:17,922] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/layer_18-model_00-model_states.pt... +0: [2022-11-29 17:45:17,978] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/layer_18-model_00-model_states.pt. +0: [2022-11-29 17:45:17,978] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:45:18,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:45:18,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/layer_20-model_00-model_states.pt... +0: [2022-11-29 17:45:18,090] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/layer_20-model_00-model_states.pt. +0: [2022-11-29 17:45:18,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/layer_21-model_00-model_states.pt... +0: [2022-11-29 17:45:18,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/layer_21-model_00-model_states.pt. +0: [2022-11-29 17:45:18,147] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/layer_23-model_00-model_states.pt... +0: [2022-11-29 17:45:18,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/layer_23-model_00-model_states.pt. +0: [2022-11-29 17:45:18,151] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_619moscar/global_step3000/mp_rank_00_model_states.pt +0: [2022-11-29 17:45:18,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:45:18,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:45:18,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:45:18,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:45:18,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:45:18,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:45:18,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:45:18,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:45:18,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:45:18,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:45:18,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:45:18,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:45:18,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:45:18,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:45:18,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:45:18,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:45:18,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:45:18,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:45:18,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:45:18,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:45:18,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:45:18,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:45:18,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:45:18,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +3: [2022-11-29 17:45:18,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:45:18,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:45:18,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:45:18,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:45:18,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:45:18,312] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:45:18,312] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:45:18,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:45:18,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:45:18,314] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:45:18,314] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:45:18,314] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:45:18,314] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:45:18,314] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:45:18,314] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:45:18,314] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:45:18,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:45:18,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:45:18,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:45:18,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:45:18,315] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:45:18,315] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:45:18,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:45:18,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:45:18,316] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:45:18,316] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:45:18,316] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:45:18,316] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:45:18,317] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:45:18,317] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:45:18,317] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:45:18,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:45:18,318] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:45:18,318] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:45:18,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:45:18,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:45:18,318] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:45:18,318] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +0: [2022-11-29 17:45:18,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:45:18,318] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:45:18,318] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:45:18,318] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:45:18,318] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:45:18,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:45:18,318] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:45:18,318] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:45:18,319] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:45:18,319] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:45:18,319] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:45:18,320] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:45:18,320] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +2: [2022-11-29 17:45:18,320] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:45:18,320] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:45:18,320] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:45:18,320] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:45:18,320] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:45:18,320] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:45:18,320] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:45:18,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:45:18,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:45:18,322] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:45:18,322] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:45:18,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:45:18,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:45:18,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:45:18,323] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:45:18,323] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:45:18,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:45:18,324] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:45:18,324] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:45:18,324] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:45:18,324] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:45:18,324] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:45:18,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:45:18,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:45:18,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:45:18,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:45:18,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:45:18,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:45:18,318] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:45:18,318] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:45:18,318] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:45:18,318] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:45:18,327] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:45:18,327] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:45:18,327] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:45:18,327] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:45:18,327] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:45:18,327] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:45:18,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:45:18,328] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:45:18,328] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:45:18,330] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:45:18,330] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:45:18,330] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:45:18,330] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:45:18,330] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:45:18,330] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:45:18,330] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:45:18,331] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:45:18,331] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:45:18,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:45:18,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:45:18,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:45:18,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:45:18,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:45:18,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:45:18,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:45:18,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:45:18,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:45:18,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:45:18,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:45:18,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:45:18,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:45:18,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:45:18,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:45:18,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:45:18,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:45:18,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:45:18,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:45:18,314] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:45:18,314] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:45:18,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:45:18,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:45:18,325] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:45:18,325] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:45:18,325] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:45:18,325] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:45:18,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:45:18,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:45:18,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:45:18,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:45:18,347] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:45:18,347] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:45:18,347] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:45:18,347] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:45:18,347] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:45:18,347] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:45:18,347] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:45:18,347] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:45:18,325] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:45:18,325] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:45:18,327] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:45:18,328] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:45:18,328] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:45:18,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:45:18,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:45:18,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:45:18,364] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:45:18,364] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:45:18,364] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:45:18,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:45:18,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:45:18,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:45:18,377] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:45:18,377] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:45:18,377] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:45:18,377] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:45:18,377] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:45:18,377] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:45:18,377] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:45:18,377] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:45:18,377] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:45:18,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:45:18,382] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:45:18,382] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:45:18,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:45:18,383] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:45:18,383] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:45:18,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:45:18,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: successfully saved checkpoint at iteration 3000 to checkpoints_619moscar +7: time (ms) | save-checkpoint: 1552.59 +7: iteration 3010/ 5111 | consumed samples: 770560 | consumed tokens: 1578106880 | elapsed time per iteration (s): 0.93 | learning rate: 8.634E-05 | global batch size: 256 | lm loss: 3.171758E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 273.909 | TFLOPs: 37.62 | +7: iteration 3020/ 5111 | consumed samples: 773120 | consumed tokens: 1583349760 | elapsed time per iteration (s): 0.74 | learning rate: 8.580E-05 | global batch size: 256 | lm loss: 3.178700E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.964 | TFLOPs: 47.25 | +7: iteration 3030/ 5111 | consumed samples: 775680 | consumed tokens: 1588592640 | elapsed time per iteration (s): 0.76 | learning rate: 8.526E-05 | global batch size: 256 | lm loss: 3.153703E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.134 | TFLOPs: 46.31 | +7: iteration 3040/ 5111 | consumed samples: 778240 | consumed tokens: 1593835520 | elapsed time per iteration (s): 0.77 | learning rate: 8.472E-05 | global batch size: 256 | lm loss: 3.178893E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.699 | TFLOPs: 45.42 | +7: iteration 3050/ 5111 | consumed samples: 780800 | consumed tokens: 1599078400 | elapsed time per iteration (s): 0.75 | learning rate: 8.419E-05 | global batch size: 256 | lm loss: 3.170125E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.666 | TFLOPs: 46.79 | +7: iteration 3060/ 5111 | consumed samples: 783360 | consumed tokens: 1604321280 | elapsed time per iteration (s): 0.75 | learning rate: 8.365E-05 | global batch size: 256 | lm loss: 3.139808E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.034 | TFLOPs: 47.12 | +7: iteration 3070/ 5111 | consumed samples: 785920 | consumed tokens: 1609564160 | elapsed time per iteration (s): 0.75 | learning rate: 8.312E-05 | global batch size: 256 | lm loss: 3.164627E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.888 | TFLOPs: 46.96 | +7: iteration 3080/ 5111 | consumed samples: 788480 | consumed tokens: 1614807040 | elapsed time per iteration (s): 0.77 | learning rate: 8.259E-05 | global batch size: 256 | lm loss: 3.175015E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.124 | TFLOPs: 45.89 | +7: iteration 3090/ 5111 | consumed samples: 791040 | consumed tokens: 1620049920 | elapsed time per iteration (s): 0.76 | learning rate: 8.205E-05 | global batch size: 256 | lm loss: 3.164398E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.549 | TFLOPs: 46.37 | +7: iteration 3100/ 5111 | consumed samples: 793600 | consumed tokens: 1625292800 | elapsed time per iteration (s): 0.76 | learning rate: 8.152E-05 | global batch size: 256 | lm loss: 3.152755E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.797 | TFLOPs: 46.40 | +7: iteration 3110/ 5111 | consumed samples: 796160 | consumed tokens: 1630535680 | elapsed time per iteration (s): 0.75 | learning rate: 8.099E-05 | global batch size: 256 | lm loss: 3.154049E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.068 | TFLOPs: 46.99 | +7: iteration 3120/ 5111 | consumed samples: 798720 | consumed tokens: 1635778560 | elapsed time per iteration (s): 0.75 | learning rate: 8.047E-05 | global batch size: 256 | lm loss: 3.169444E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.194 | TFLOPs: 46.73 | +7: iteration 3130/ 5111 | consumed samples: 801280 | consumed tokens: 1641021440 | elapsed time per iteration (s): 0.75 | learning rate: 7.994E-05 | global batch size: 256 | lm loss: 3.172725E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.310 | TFLOPs: 47.02 | +7: iteration 3140/ 5111 | consumed samples: 803840 | consumed tokens: 1646264320 | elapsed time per iteration (s): 0.75 | learning rate: 7.941E-05 | global batch size: 256 | lm loss: 3.146635E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.904 | TFLOPs: 46.96 | +7: iteration 3150/ 5111 | consumed samples: 806400 | consumed tokens: 1651507200 | elapsed time per iteration (s): 0.75 | learning rate: 7.889E-05 | global batch size: 256 | lm loss: 3.139007E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.380 | TFLOPs: 47.03 | +7: iteration 3160/ 5111 | consumed samples: 808960 | consumed tokens: 1656750080 | elapsed time per iteration (s): 0.75 | learning rate: 7.836E-05 | global batch size: 256 | lm loss: 3.138052E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.421 | TFLOPs: 46.90 | +7: iteration 3170/ 5111 | consumed samples: 811520 | consumed tokens: 1661992960 | elapsed time per iteration (s): 0.75 | learning rate: 7.784E-05 | global batch size: 256 | lm loss: 3.140143E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.439 | TFLOPs: 46.90 | +7: iteration 3180/ 5111 | consumed samples: 814080 | consumed tokens: 1667235840 | elapsed time per iteration (s): 0.75 | learning rate: 7.732E-05 | global batch size: 256 | lm loss: 3.161715E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.223 | TFLOPs: 47.01 | +7: iteration 3190/ 5111 | consumed samples: 816640 | consumed tokens: 1672478720 | elapsed time per iteration (s): 0.76 | learning rate: 7.680E-05 | global batch size: 256 | lm loss: 3.130198E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.791 | TFLOPs: 46.54 | +7: iteration 3200/ 5111 | consumed samples: 819200 | consumed tokens: 1677721600 | elapsed time per iteration (s): 0.76 | learning rate: 7.628E-05 | global batch size: 256 | lm loss: 3.171877E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.793 | TFLOPs: 46.54 | +7: iteration 3210/ 5111 | consumed samples: 821760 | consumed tokens: 1682964480 | elapsed time per iteration (s): 0.76 | learning rate: 7.576E-05 | global batch size: 256 | lm loss: 3.140280E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.187 | TFLOPs: 46.45 | +7: iteration 3220/ 5111 | consumed samples: 824320 | consumed tokens: 1688207360 | elapsed time per iteration (s): 0.78 | learning rate: 7.525E-05 | global batch size: 256 | lm loss: 3.146169E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 326.875 | TFLOPs: 44.90 | +7: iteration 3230/ 5111 | consumed samples: 826880 | consumed tokens: 1693450240 | elapsed time per iteration (s): 0.75 | learning rate: 7.473E-05 | global batch size: 256 | lm loss: 3.128731E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.172 | TFLOPs: 47.00 | +7: iteration 3240/ 5111 | consumed samples: 829440 | consumed tokens: 1698693120 | elapsed time per iteration (s): 0.76 | learning rate: 7.422E-05 | global batch size: 256 | lm loss: 3.133347E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.081 | TFLOPs: 46.44 | +7: iteration 3250/ 5111 | consumed samples: 832000 | consumed tokens: 1703936000 | elapsed time per iteration (s): 0.76 | learning rate: 7.371E-05 | global batch size: 256 | lm loss: 3.111102E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.500 | TFLOPs: 46.50 | +7: iteration 3260/ 5111 | consumed samples: 834560 | consumed tokens: 1709178880 | elapsed time per iteration (s): 0.76 | learning rate: 7.320E-05 | global batch size: 256 | lm loss: 3.104453E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.824 | TFLOPs: 45.99 | +7: iteration 3270/ 5111 | consumed samples: 837120 | consumed tokens: 1714421760 | elapsed time per iteration (s): 0.77 | learning rate: 7.269E-05 | global batch size: 256 | lm loss: 3.153448E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 330.486 | TFLOPs: 45.39 | +7: iteration 3280/ 5111 | consumed samples: 839680 | consumed tokens: 1719664640 | elapsed time per iteration (s): 0.75 | learning rate: 7.218E-05 | global batch size: 256 | lm loss: 3.133191E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.011 | TFLOPs: 46.70 | +7: iteration 3290/ 5111 | consumed samples: 842240 | consumed tokens: 1724907520 | elapsed time per iteration (s): 0.75 | learning rate: 7.167E-05 | global batch size: 256 | lm loss: 3.117057E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.319 | TFLOPs: 47.02 | +7: iteration 3300/ 5111 | consumed samples: 844800 | consumed tokens: 1730150400 | elapsed time per iteration (s): 0.77 | learning rate: 7.117E-05 | global batch size: 256 | lm loss: 3.134641E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.067 | TFLOPs: 45.89 | +7: iteration 3310/ 5111 | consumed samples: 847360 | consumed tokens: 1735393280 | elapsed time per iteration (s): 0.78 | learning rate: 7.067E-05 | global batch size: 256 | lm loss: 3.137915E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.473 | TFLOPs: 44.98 | +7: iteration 3320/ 5111 | consumed samples: 849920 | consumed tokens: 1740636160 | elapsed time per iteration (s): 0.75 | learning rate: 7.016E-05 | global batch size: 256 | lm loss: 3.111090E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.280 | TFLOPs: 46.88 | +7: iteration 3330/ 5111 | consumed samples: 852480 | consumed tokens: 1745879040 | elapsed time per iteration (s): 0.76 | learning rate: 6.966E-05 | global batch size: 256 | lm loss: 3.139039E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.795 | TFLOPs: 46.40 | +7: iteration 3340/ 5111 | consumed samples: 855040 | consumed tokens: 1751121920 | elapsed time per iteration (s): 0.75 | learning rate: 6.917E-05 | global batch size: 256 | lm loss: 3.137617E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.581 | TFLOPs: 47.06 | +7: iteration 3350/ 5111 | consumed samples: 857600 | consumed tokens: 1756364800 | elapsed time per iteration (s): 0.76 | learning rate: 6.867E-05 | global batch size: 256 | lm loss: 3.119880E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.478 | TFLOPs: 46.22 | +7: iteration 3360/ 5111 | consumed samples: 860160 | consumed tokens: 1761607680 | elapsed time per iteration (s): 0.75 | learning rate: 6.817E-05 | global batch size: 256 | lm loss: 3.108307E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.345 | TFLOPs: 46.75 | +7: iteration 3370/ 5111 | consumed samples: 862720 | consumed tokens: 1766850560 | elapsed time per iteration (s): 0.76 | learning rate: 6.768E-05 | global batch size: 256 | lm loss: 3.133707E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.601 | TFLOPs: 46.37 | +7: iteration 3380/ 5111 | consumed samples: 865280 | consumed tokens: 1772093440 | elapsed time per iteration (s): 0.77 | learning rate: 6.719E-05 | global batch size: 256 | lm loss: 3.123920E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.107 | TFLOPs: 45.48 | +7: iteration 3390/ 5111 | consumed samples: 867840 | consumed tokens: 1777336320 | elapsed time per iteration (s): 0.75 | learning rate: 6.670E-05 | global batch size: 256 | lm loss: 3.137653E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.590 | TFLOPs: 47.06 | +7: iteration 3400/ 5111 | consumed samples: 870400 | consumed tokens: 1782579200 | elapsed time per iteration (s): 0.76 | learning rate: 6.621E-05 | global batch size: 256 | lm loss: 3.097324E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.622 | TFLOPs: 46.24 | +7: iteration 3410/ 5111 | consumed samples: 872960 | consumed tokens: 1787822080 | elapsed time per iteration (s): 0.76 | learning rate: 6.572E-05 | global batch size: 256 | lm loss: 3.111511E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.642 | TFLOPs: 46.10 | +7: iteration 3420/ 5111 | consumed samples: 875520 | consumed tokens: 1793064960 | elapsed time per iteration (s): 0.76 | learning rate: 6.523E-05 | global batch size: 256 | lm loss: 3.089127E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.167 | TFLOPs: 46.31 | +7: iteration 3430/ 5111 | consumed samples: 878080 | consumed tokens: 1798307840 | elapsed time per iteration (s): 0.76 | learning rate: 6.475E-05 | global batch size: 256 | lm loss: 3.122866E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.066 | TFLOPs: 46.57 | +7: iteration 3440/ 5111 | consumed samples: 880640 | consumed tokens: 1803550720 | elapsed time per iteration (s): 0.75 | learning rate: 6.427E-05 | global batch size: 256 | lm loss: 3.126286E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.537 | TFLOPs: 46.91 | +7: iteration 3450/ 5111 | consumed samples: 883200 | consumed tokens: 1808793600 | elapsed time per iteration (s): 0.75 | learning rate: 6.379E-05 | global batch size: 256 | lm loss: 3.132756E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.364 | TFLOPs: 47.16 | +7: iteration 3460/ 5111 | consumed samples: 885760 | consumed tokens: 1814036480 | elapsed time per iteration (s): 0.75 | learning rate: 6.331E-05 | global batch size: 256 | lm loss: 3.111697E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.148 | TFLOPs: 46.58 | +7: iteration 3470/ 5111 | consumed samples: 888320 | consumed tokens: 1819279360 | elapsed time per iteration (s): 0.76 | learning rate: 6.283E-05 | global batch size: 256 | lm loss: 3.114856E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.502 | TFLOPs: 46.50 | +7: iteration 3480/ 5111 | consumed samples: 890880 | consumed tokens: 1824522240 | elapsed time per iteration (s): 0.75 | learning rate: 6.236E-05 | global batch size: 256 | lm loss: 3.122474E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.630 | TFLOPs: 46.93 | +7: iteration 3490/ 5111 | consumed samples: 893440 | consumed tokens: 1829765120 | elapsed time per iteration (s): 0.77 | learning rate: 6.188E-05 | global batch size: 256 | lm loss: 3.087769E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.647 | TFLOPs: 45.55 | +7: iteration 3500/ 5111 | consumed samples: 896000 | consumed tokens: 1835008000 | elapsed time per iteration (s): 0.75 | learning rate: 6.141E-05 | global batch size: 256 | lm loss: 3.131302E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.699 | TFLOPs: 46.94 | +7: iteration 3510/ 5111 | consumed samples: 898560 | consumed tokens: 1840250880 | elapsed time per iteration (s): 0.75 | learning rate: 6.094E-05 | global batch size: 256 | lm loss: 3.090648E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.895 | TFLOPs: 46.82 | +7: iteration 3520/ 5111 | consumed samples: 901120 | consumed tokens: 1845493760 | elapsed time per iteration (s): 0.76 | learning rate: 6.048E-05 | global batch size: 256 | lm loss: 3.109345E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.981 | TFLOPs: 46.56 | +7: iteration 3530/ 5111 | consumed samples: 903680 | consumed tokens: 1850736640 | elapsed time per iteration (s): 0.77 | learning rate: 6.001E-05 | global batch size: 256 | lm loss: 3.099528E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.222 | TFLOPs: 45.77 | +7: iteration 3540/ 5111 | consumed samples: 906240 | consumed tokens: 1855979520 | elapsed time per iteration (s): 0.76 | learning rate: 5.955E-05 | global batch size: 256 | lm loss: 3.111215E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.036 | TFLOPs: 46.57 | +7: iteration 3550/ 5111 | consumed samples: 908800 | consumed tokens: 1861222400 | elapsed time per iteration (s): 0.75 | learning rate: 5.909E-05 | global batch size: 256 | lm loss: 3.125321E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.350 | TFLOPs: 47.02 | +7: iteration 3560/ 5111 | consumed samples: 911360 | consumed tokens: 1866465280 | elapsed time per iteration (s): 0.76 | learning rate: 5.863E-05 | global batch size: 256 | lm loss: 3.083322E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.806 | TFLOPs: 46.40 | +7: iteration 3570/ 5111 | consumed samples: 913920 | consumed tokens: 1871708160 | elapsed time per iteration (s): 0.76 | learning rate: 5.817E-05 | global batch size: 256 | lm loss: 3.125963E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.749 | TFLOPs: 46.53 | +7: iteration 3580/ 5111 | consumed samples: 916480 | consumed tokens: 1876951040 | elapsed time per iteration (s): 0.75 | learning rate: 5.771E-05 | global batch size: 256 | lm loss: 3.096863E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.938 | TFLOPs: 46.69 | +7: iteration 3590/ 5111 | consumed samples: 919040 | consumed tokens: 1882193920 | elapsed time per iteration (s): 0.77 | learning rate: 5.726E-05 | global batch size: 256 | lm loss: 3.093891E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.541 | TFLOPs: 45.54 | +7: iteration 3600/ 5111 | consumed samples: 921600 | consumed tokens: 1887436800 | elapsed time per iteration (s): 0.75 | learning rate: 5.681E-05 | global batch size: 256 | lm loss: 3.111177E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.252 | TFLOPs: 46.74 | +7: iteration 3610/ 5111 | consumed samples: 924160 | consumed tokens: 1892679680 | elapsed time per iteration (s): 0.75 | learning rate: 5.636E-05 | global batch size: 256 | lm loss: 3.088924E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.559 | TFLOPs: 46.64 | +7: iteration 3620/ 5111 | consumed samples: 926720 | consumed tokens: 1897922560 | elapsed time per iteration (s): 0.75 | learning rate: 5.591E-05 | global batch size: 256 | lm loss: 3.100727E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.856 | TFLOPs: 46.82 | +7: iteration 3630/ 5111 | consumed samples: 929280 | consumed tokens: 1903165440 | elapsed time per iteration (s): 0.75 | learning rate: 5.546E-05 | global batch size: 256 | lm loss: 3.119284E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.256 | TFLOPs: 47.01 | +7: iteration 3640/ 5111 | consumed samples: 931840 | consumed tokens: 1908408320 | elapsed time per iteration (s): 0.75 | learning rate: 5.502E-05 | global batch size: 256 | lm loss: 3.082815E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.712 | TFLOPs: 47.07 | +7: iteration 3650/ 5111 | consumed samples: 934400 | consumed tokens: 1913651200 | elapsed time per iteration (s): 0.76 | learning rate: 5.458E-05 | global batch size: 256 | lm loss: 3.088071E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.768 | TFLOPs: 45.98 | +7: iteration 3660/ 5111 | consumed samples: 936960 | consumed tokens: 1918894080 | elapsed time per iteration (s): 0.74 | learning rate: 5.414E-05 | global batch size: 256 | lm loss: 3.103170E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.671 | TFLOPs: 47.21 | +7: iteration 3670/ 5111 | consumed samples: 939520 | consumed tokens: 1924136960 | elapsed time per iteration (s): 0.75 | learning rate: 5.370E-05 | global batch size: 256 | lm loss: 3.114399E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.292 | TFLOPs: 46.88 | +7: iteration 3680/ 5111 | consumed samples: 942080 | consumed tokens: 1929379840 | elapsed time per iteration (s): 0.77 | learning rate: 5.327E-05 | global batch size: 256 | lm loss: 3.076187E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.026 | TFLOPs: 45.47 | +7: iteration 3690/ 5111 | consumed samples: 944640 | consumed tokens: 1934622720 | elapsed time per iteration (s): 0.75 | learning rate: 5.284E-05 | global batch size: 256 | lm loss: 3.091864E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.240 | TFLOPs: 47.01 | +7: iteration 3700/ 5111 | consumed samples: 947200 | consumed tokens: 1939865600 | elapsed time per iteration (s): 0.76 | learning rate: 5.241E-05 | global batch size: 256 | lm loss: 3.100683E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.672 | TFLOPs: 46.38 | +7: iteration 3710/ 5111 | consumed samples: 949760 | consumed tokens: 1945108480 | elapsed time per iteration (s): 0.77 | learning rate: 5.198E-05 | global batch size: 256 | lm loss: 3.118059E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.263 | TFLOPs: 45.50 | +7: iteration 3720/ 5111 | consumed samples: 952320 | consumed tokens: 1950351360 | elapsed time per iteration (s): 0.75 | learning rate: 5.155E-05 | global batch size: 256 | lm loss: 3.106513E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.206 | TFLOPs: 46.87 | +7: iteration 3730/ 5111 | consumed samples: 954880 | consumed tokens: 1955594240 | elapsed time per iteration (s): 0.77 | learning rate: 5.113E-05 | global batch size: 256 | lm loss: 3.101078E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.422 | TFLOPs: 45.52 | +7: iteration 3740/ 5111 | consumed samples: 957440 | consumed tokens: 1960837120 | elapsed time per iteration (s): 0.74 | learning rate: 5.071E-05 | global batch size: 256 | lm loss: 3.066647E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 344.070 | TFLOPs: 47.26 | +7: iteration 3750/ 5111 | consumed samples: 960000 | consumed tokens: 1966080000 | elapsed time per iteration (s): 0.75 | learning rate: 5.029E-05 | global batch size: 256 | lm loss: 3.071364E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.362 | TFLOPs: 46.89 | +7: iteration 3760/ 5111 | consumed samples: 962560 | consumed tokens: 1971322880 | elapsed time per iteration (s): 0.76 | learning rate: 4.987E-05 | global batch size: 256 | lm loss: 3.075986E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.243 | TFLOPs: 46.46 | +7: iteration 3770/ 5111 | consumed samples: 965120 | consumed tokens: 1976565760 | elapsed time per iteration (s): 0.74 | learning rate: 4.946E-05 | global batch size: 256 | lm loss: 3.099953E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.731 | TFLOPs: 47.21 | +7: iteration 3780/ 5111 | consumed samples: 967680 | consumed tokens: 1981808640 | elapsed time per iteration (s): 0.75 | learning rate: 4.904E-05 | global batch size: 256 | lm loss: 3.091156E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.046 | TFLOPs: 46.98 | +7: iteration 3790/ 5111 | consumed samples: 970240 | consumed tokens: 1987051520 | elapsed time per iteration (s): 0.75 | learning rate: 4.863E-05 | global batch size: 256 | lm loss: 3.069053E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.840 | TFLOPs: 46.68 | +7: iteration 3800/ 5111 | consumed samples: 972800 | consumed tokens: 1992294400 | elapsed time per iteration (s): 0.76 | learning rate: 4.823E-05 | global batch size: 256 | lm loss: 3.106071E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.950 | TFLOPs: 46.56 | +7: iteration 3810/ 5111 | consumed samples: 975360 | consumed tokens: 1997537280 | elapsed time per iteration (s): 0.76 | learning rate: 4.782E-05 | global batch size: 256 | lm loss: 3.088531E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.653 | TFLOPs: 46.52 | +7: iteration 3820/ 5111 | consumed samples: 977920 | consumed tokens: 2002780160 | elapsed time per iteration (s): 0.75 | learning rate: 4.742E-05 | global batch size: 256 | lm loss: 3.084668E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.009 | TFLOPs: 46.70 | +7: iteration 3830/ 5111 | consumed samples: 980480 | consumed tokens: 2008023040 | elapsed time per iteration (s): 0.76 | learning rate: 4.702E-05 | global batch size: 256 | lm loss: 3.085593E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.355 | TFLOPs: 46.34 | +7: iteration 3840/ 5111 | consumed samples: 983040 | consumed tokens: 2013265920 | elapsed time per iteration (s): 0.78 | learning rate: 4.662E-05 | global batch size: 256 | lm loss: 3.091405E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 329.382 | TFLOPs: 45.24 | +7: iteration 3850/ 5111 | consumed samples: 985600 | consumed tokens: 2018508800 | elapsed time per iteration (s): 0.77 | learning rate: 4.622E-05 | global batch size: 256 | lm loss: 3.116562E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.042 | TFLOPs: 45.75 | +7: iteration 3860/ 5111 | consumed samples: 988160 | consumed tokens: 2023751680 | elapsed time per iteration (s): 0.75 | learning rate: 4.583E-05 | global batch size: 256 | lm loss: 3.073994E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.591 | TFLOPs: 46.65 | +7: iteration 3870/ 5111 | consumed samples: 990720 | consumed tokens: 2028994560 | elapsed time per iteration (s): 0.77 | learning rate: 4.544E-05 | global batch size: 256 | lm loss: 3.079441E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.008 | TFLOPs: 45.88 | +7: iteration 3880/ 5111 | consumed samples: 993280 | consumed tokens: 2034237440 | elapsed time per iteration (s): 0.76 | learning rate: 4.505E-05 | global batch size: 256 | lm loss: 3.067249E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.805 | TFLOPs: 46.40 | +7: iteration 3890/ 5111 | consumed samples: 995840 | consumed tokens: 2039480320 | elapsed time per iteration (s): 0.76 | learning rate: 4.467E-05 | global batch size: 256 | lm loss: 3.067431E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.069 | TFLOPs: 46.57 | +7: iteration 3900/ 5111 | consumed samples: 998400 | consumed tokens: 2044723200 | elapsed time per iteration (s): 0.75 | learning rate: 4.428E-05 | global batch size: 256 | lm loss: 3.067662E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.211 | TFLOPs: 46.87 | +7: iteration 3910/ 5111 | consumed samples: 1000960 | consumed tokens: 2049966080 | elapsed time per iteration (s): 0.76 | learning rate: 4.390E-05 | global batch size: 256 | lm loss: 3.058901E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.944 | TFLOPs: 46.42 | +7: iteration 3920/ 5111 | consumed samples: 1003520 | consumed tokens: 2055208960 | elapsed time per iteration (s): 0.75 | learning rate: 4.353E-05 | global batch size: 256 | lm loss: 3.060954E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.427 | TFLOPs: 46.62 | +7: iteration 3930/ 5111 | consumed samples: 1006080 | consumed tokens: 2060451840 | elapsed time per iteration (s): 0.77 | learning rate: 4.315E-05 | global batch size: 256 | lm loss: 3.067773E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.093 | TFLOPs: 45.62 | +7: iteration 3940/ 5111 | consumed samples: 1008640 | consumed tokens: 2065694720 | elapsed time per iteration (s): 0.75 | learning rate: 4.278E-05 | global batch size: 256 | lm loss: 3.068537E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.665 | TFLOPs: 46.93 | +7: iteration 3950/ 5111 | consumed samples: 1011200 | consumed tokens: 2070937600 | elapsed time per iteration (s): 0.79 | learning rate: 4.241E-05 | global batch size: 256 | lm loss: 3.082029E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 325.751 | TFLOPs: 44.74 | +7: iteration 3960/ 5111 | consumed samples: 1013760 | consumed tokens: 2076180480 | elapsed time per iteration (s): 0.76 | learning rate: 4.204E-05 | global batch size: 256 | lm loss: 3.049997E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.742 | TFLOPs: 46.53 | +7: iteration 3970/ 5111 | consumed samples: 1016320 | consumed tokens: 2081423360 | elapsed time per iteration (s): 0.75 | learning rate: 4.167E-05 | global batch size: 256 | lm loss: 3.079661E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.668 | TFLOPs: 46.93 | +7: iteration 3980/ 5111 | consumed samples: 1018880 | consumed tokens: 2086666240 | elapsed time per iteration (s): 0.75 | learning rate: 4.131E-05 | global batch size: 256 | lm loss: 3.067838E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.948 | TFLOPs: 47.11 | +7: iteration 3990/ 5111 | consumed samples: 1021440 | consumed tokens: 2091909120 | elapsed time per iteration (s): 0.75 | learning rate: 4.095E-05 | global batch size: 256 | lm loss: 3.073401E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.131 | TFLOPs: 46.58 | +0: [2022-11-29 17:57:55,183] [INFO] [logging.py:68:log_dist] [Rank 0] step=4000, skipped=0, lr=[4.0595726162397195e-05, 4.0595726162397195e-05, 4.0595726162397195e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 4000/ 5111 | consumed samples: 1024000 | consumed tokens: 2097152000 | elapsed time per iteration (s): 0.78 | learning rate: 4.060E-05 | global batch size: 256 | lm loss: 3.064584E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 327.927 | TFLOPs: 45.04 | +0: steps: 4000 loss: 3.0527 iter time (s): 0.753 samples/sec: 339.986 +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 4000 | lm loss value: 2.931630E+00 | lm loss PPL: 1.875819E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 4000 to checkpoints_619moscar +0: [2022-11-29 17:57:55,449] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step4000 is begin to save! +0: [2022-11-29 17:57:55,454] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:57:55,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:57:55,620] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:57:55,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:57:55,675] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:57:55,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:57:55,730] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:57:55,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:57:55,785] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:57:55,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:57:55,843] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:57:55,898] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:57:55,899] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:57:55,953] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:57:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:57:56,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:57:56,010] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:57:56,065] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:57:56,065] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:57:56,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:57:56,121] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:57:56,175] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:57:56,176] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/layer_13-model_00-model_states.pt... +0: [2022-11-29 17:57:56,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/layer_13-model_00-model_states.pt. +0: [2022-11-29 17:57:56,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:57:56,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:57:56,286] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/layer_15-model_00-model_states.pt... +0: [2022-11-29 17:57:56,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/layer_15-model_00-model_states.pt. +0: [2022-11-29 17:57:56,344] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/layer_16-model_00-model_states.pt... +0: [2022-11-29 17:57:56,399] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/layer_16-model_00-model_states.pt. +0: [2022-11-29 17:57:56,400] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/layer_17-model_00-model_states.pt... +0: [2022-11-29 17:57:56,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/layer_17-model_00-model_states.pt. +0: [2022-11-29 17:57:56,454] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/layer_18-model_00-model_states.pt... +0: [2022-11-29 17:57:56,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/layer_18-model_00-model_states.pt. +0: [2022-11-29 17:57:56,509] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/layer_19-model_00-model_states.pt... +0: [2022-11-29 17:57:56,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/layer_19-model_00-model_states.pt. +0: [2022-11-29 17:57:56,566] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/layer_20-model_00-model_states.pt... +0: [2022-11-29 17:57:56,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/layer_20-model_00-model_states.pt. +0: [2022-11-29 17:57:56,621] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/layer_21-model_00-model_states.pt... +0: [2022-11-29 17:57:56,678] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/layer_21-model_00-model_states.pt. +0: [2022-11-29 17:57:56,678] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/layer_23-model_00-model_states.pt... +0: [2022-11-29 17:57:56,682] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/layer_23-model_00-model_states.pt. +0: [2022-11-29 17:57:56,683] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_619moscar/global_step4000/mp_rank_00_model_states.pt +0: [2022-11-29 17:57:56,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:57:56,685] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:57:56,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:57:56,924] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:57:56,928] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:57:56,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:57:56,929] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:57:56,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:57:56,932] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:57:56,932] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:57:56,933] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:57:56,935] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:57:56,935] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:57:56,935] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:57:56,935] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:57:56,935] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:57:56,935] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:57:56,935] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:57:56,935] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:57:56,935] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:57:56,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:57:56,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:57:56,936] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:57:56,936] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:57:56,936] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:57:56,936] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:57:56,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:57:56,938] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:57:56,938] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:57:56,938] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:57:56,938] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:57:56,938] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:57:56,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:57:56,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:57:56,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:57:56,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:57:56,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:57:56,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:57:56,941] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:57:56,941] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:57:56,941] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:57:56,941] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:57:56,941] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:57:56,941] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:57:56,942] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:57:56,942] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:57:56,942] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:57:56,942] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:57:56,942] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:57:56,942] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:57:56,942] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:57:56,942] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:57:56,942] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +2: [2022-11-29 17:57:56,942] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:57:56,942] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:57:56,942] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:57:56,942] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:57:56,943] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:57:56,943] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:57:56,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:57:56,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:57:56,943] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +7: [2022-11-29 17:57:56,943] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +2: [2022-11-29 17:57:56,943] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:57:56,943] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:57:56,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:57:56,943] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:57:56,943] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:57:56,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:57:56,943] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:57:56,943] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:57:56,944] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:57:56,944] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:57:56,944] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:57:56,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:57:56,945] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:57:56,945] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:57:56,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:57:56,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:57:56,945] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:57:56,945] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:57:56,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:57:56,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:57:56,945] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:57:56,945] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:57:56,945] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:57:56,945] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:57:56,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:57:56,945] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:57:56,945] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:57:56,945] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:57:56,946] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:57:56,928] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:57:56,928] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:57:56,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:57:56,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:57:56,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:57:56,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:57:56,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +0: [2022-11-29 17:57:56,948] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:57:56,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:57:56,941] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:57:56,941] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:57:56,941] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:57:56,948] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:57:56,948] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:57:56,948] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:57:56,948] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:57:56,949] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:57:56,949] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:57:56,949] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:57:56,949] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:57:56,949] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:57:56,949] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:57:56,949] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:57:56,949] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:57:56,949] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:57:56,949] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:57:56,949] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:57:56,949] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:57:56,950] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:57:56,950] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:57:56,954] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:57:56,954] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:57:56,954] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:57:56,942] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:57:56,942] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:57:56,943] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:57:56,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:57:56,943] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:57:56,943] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:57:56,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:57:56,943] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:57:56,943] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:57:56,955] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:57:56,955] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:57:56,955] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:57:56,955] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:57:56,956] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:57:56,956] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:57:56,956] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:57:56,956] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:57:56,956] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:57:56,956] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:57:56,956] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:57:56,956] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:57:56,956] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:57:56,956] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:57:56,956] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:57:56,958] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:57:56,958] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:57:56,958] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:57:56,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:57:56,959] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:57:56,959] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:57:56,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:57:56,959] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:57:56,959] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:57:56,944] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:57:56,944] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:57:56,944] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:57:56,944] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:57:56,944] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:57:56,944] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:57:56,944] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:57:56,944] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:57:56,944] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:57:56,958] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:57:56,958] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:57:56,958] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:57:56,949] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:57:56,949] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:57:56,950] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:57:56,950] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:57:56,950] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:57:56,974] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:57:56,988] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:57:56,988] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:57:56,989] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:57:56,974] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:57:56,974] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:57:56,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:57:56,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:57:56,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:57:56,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:57:56,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:57:56,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:57:56,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:57:56,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:57:56,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:57:56,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:57:56,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:57:56,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:57:57,089] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:57:57,089] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: successfully saved checkpoint at iteration 4000 to checkpoints_619moscar +7: time (ms) | save-checkpoint: 1651.34 +7: iteration 4010/ 5111 | consumed samples: 1026560 | consumed tokens: 2102394880 | elapsed time per iteration (s): 0.96 | learning rate: 4.024E-05 | global batch size: 256 | lm loss: 3.073008E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 267.359 | TFLOPs: 36.72 | +7: iteration 4020/ 5111 | consumed samples: 1029120 | consumed tokens: 2107637760 | elapsed time per iteration (s): 0.75 | learning rate: 3.989E-05 | global batch size: 256 | lm loss: 3.084740E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.546 | TFLOPs: 47.05 | +7: iteration 4030/ 5111 | consumed samples: 1031680 | consumed tokens: 2112880640 | elapsed time per iteration (s): 0.75 | learning rate: 3.954E-05 | global batch size: 256 | lm loss: 3.077655E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.391 | TFLOPs: 46.62 | +7: iteration 4040/ 5111 | consumed samples: 1034240 | consumed tokens: 2118123520 | elapsed time per iteration (s): 0.75 | learning rate: 3.919E-05 | global batch size: 256 | lm loss: 3.081484E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.341 | TFLOPs: 46.61 | +7: iteration 4050/ 5111 | consumed samples: 1036800 | consumed tokens: 2123366400 | elapsed time per iteration (s): 0.75 | learning rate: 3.885E-05 | global batch size: 256 | lm loss: 3.071541E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.470 | TFLOPs: 46.90 | +7: iteration 4060/ 5111 | consumed samples: 1039360 | consumed tokens: 2128609280 | elapsed time per iteration (s): 0.76 | learning rate: 3.851E-05 | global batch size: 256 | lm loss: 3.076340E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.172 | TFLOPs: 46.04 | +7: iteration 4070/ 5111 | consumed samples: 1041920 | consumed tokens: 2133852160 | elapsed time per iteration (s): 0.76 | learning rate: 3.817E-05 | global batch size: 256 | lm loss: 3.045898E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.135 | TFLOPs: 46.45 | +7: iteration 4080/ 5111 | consumed samples: 1044480 | consumed tokens: 2139095040 | elapsed time per iteration (s): 0.75 | learning rate: 3.784E-05 | global batch size: 256 | lm loss: 3.073382E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.461 | TFLOPs: 46.77 | +7: iteration 4090/ 5111 | consumed samples: 1047040 | consumed tokens: 2144337920 | elapsed time per iteration (s): 0.75 | learning rate: 3.750E-05 | global batch size: 256 | lm loss: 3.093890E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.825 | TFLOPs: 47.09 | +7: iteration 4100/ 5111 | consumed samples: 1049600 | consumed tokens: 2149580800 | elapsed time per iteration (s): 0.74 | learning rate: 3.717E-05 | global batch size: 256 | lm loss: 3.068567E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.887 | TFLOPs: 47.24 | +7: iteration 4110/ 5111 | consumed samples: 1052160 | consumed tokens: 2154823680 | elapsed time per iteration (s): 0.75 | learning rate: 3.685E-05 | global batch size: 256 | lm loss: 3.057940E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.090 | TFLOPs: 46.99 | +7: iteration 4120/ 5111 | consumed samples: 1054720 | consumed tokens: 2160066560 | elapsed time per iteration (s): 0.75 | learning rate: 3.652E-05 | global batch size: 256 | lm loss: 3.045570E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.612 | TFLOPs: 46.79 | +7: iteration 4130/ 5111 | consumed samples: 1057280 | consumed tokens: 2165309440 | elapsed time per iteration (s): 0.75 | learning rate: 3.620E-05 | global batch size: 256 | lm loss: 3.076852E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.480 | TFLOPs: 47.04 | +7: iteration 4140/ 5111 | consumed samples: 1059840 | consumed tokens: 2170552320 | elapsed time per iteration (s): 0.76 | learning rate: 3.588E-05 | global batch size: 256 | lm loss: 3.054226E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.781 | TFLOPs: 46.40 | +7: iteration 4150/ 5111 | consumed samples: 1062400 | consumed tokens: 2175795200 | elapsed time per iteration (s): 0.76 | learning rate: 3.557E-05 | global batch size: 256 | lm loss: 3.065909E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.178 | TFLOPs: 46.31 | +7: iteration 4160/ 5111 | consumed samples: 1064960 | consumed tokens: 2181038080 | elapsed time per iteration (s): 0.75 | learning rate: 3.526E-05 | global batch size: 256 | lm loss: 3.067292E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.703 | TFLOPs: 46.66 | +7: iteration 4170/ 5111 | consumed samples: 1067520 | consumed tokens: 2186280960 | elapsed time per iteration (s): 0.76 | learning rate: 3.495E-05 | global batch size: 256 | lm loss: 3.046807E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.801 | TFLOPs: 46.40 | +7: iteration 4180/ 5111 | consumed samples: 1070080 | consumed tokens: 2191523840 | elapsed time per iteration (s): 0.76 | learning rate: 3.464E-05 | global batch size: 256 | lm loss: 3.030487E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.627 | TFLOPs: 46.51 | +7: iteration 4190/ 5111 | consumed samples: 1072640 | consumed tokens: 2196766720 | elapsed time per iteration (s): 0.75 | learning rate: 3.434E-05 | global batch size: 256 | lm loss: 3.056150E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.112 | TFLOPs: 46.58 | +7: iteration 4200/ 5111 | consumed samples: 1075200 | consumed tokens: 2202009600 | elapsed time per iteration (s): 0.76 | learning rate: 3.403E-05 | global batch size: 256 | lm loss: 3.052922E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.093 | TFLOPs: 46.17 | +7: iteration 4210/ 5111 | consumed samples: 1077760 | consumed tokens: 2207252480 | elapsed time per iteration (s): 0.75 | learning rate: 3.374E-05 | global batch size: 256 | lm loss: 3.077686E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.414 | TFLOPs: 47.17 | +7: iteration 4220/ 5111 | consumed samples: 1080320 | consumed tokens: 2212495360 | elapsed time per iteration (s): 0.76 | learning rate: 3.344E-05 | global batch size: 256 | lm loss: 3.082868E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.901 | TFLOPs: 46.55 | +7: iteration 4230/ 5111 | consumed samples: 1082880 | consumed tokens: 2217738240 | elapsed time per iteration (s): 0.77 | learning rate: 3.315E-05 | global batch size: 256 | lm loss: 3.057926E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.363 | TFLOPs: 45.93 | +7: iteration 4240/ 5111 | consumed samples: 1085440 | consumed tokens: 2222981120 | elapsed time per iteration (s): 0.74 | learning rate: 3.286E-05 | global batch size: 256 | lm loss: 3.093639E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.961 | TFLOPs: 47.25 | +7: iteration 4250/ 5111 | consumed samples: 1088000 | consumed tokens: 2228224000 | elapsed time per iteration (s): 0.76 | learning rate: 3.257E-05 | global batch size: 256 | lm loss: 3.015603E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.693 | TFLOPs: 46.52 | +7: iteration 4260/ 5111 | consumed samples: 1090560 | consumed tokens: 2233466880 | elapsed time per iteration (s): 1.17 | learning rate: 3.229E-05 | global batch size: 256 | lm loss: 3.092188E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.217 | TFLOPs: 30.11 | +7: iteration 4270/ 5111 | consumed samples: 1093120 | consumed tokens: 2238709760 | elapsed time per iteration (s): 0.75 | learning rate: 3.201E-05 | global batch size: 256 | lm loss: 3.065760E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.583 | TFLOPs: 47.06 | +7: iteration 4280/ 5111 | consumed samples: 1095680 | consumed tokens: 2243952640 | elapsed time per iteration (s): 0.75 | learning rate: 3.173E-05 | global batch size: 256 | lm loss: 3.070057E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.802 | TFLOPs: 46.81 | +7: iteration 4290/ 5111 | consumed samples: 1098240 | consumed tokens: 2249195520 | elapsed time per iteration (s): 0.74 | learning rate: 3.146E-05 | global batch size: 256 | lm loss: 3.067685E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.966 | TFLOPs: 47.25 | +7: iteration 4300/ 5111 | consumed samples: 1100800 | consumed tokens: 2254438400 | elapsed time per iteration (s): 0.76 | learning rate: 3.119E-05 | global batch size: 256 | lm loss: 3.012049E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.800 | TFLOPs: 46.26 | +7: iteration 4310/ 5111 | consumed samples: 1103360 | consumed tokens: 2259681280 | elapsed time per iteration (s): 0.75 | learning rate: 3.092E-05 | global batch size: 256 | lm loss: 3.046395E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.912 | TFLOPs: 47.10 | +7: iteration 4320/ 5111 | consumed samples: 1105920 | consumed tokens: 2264924160 | elapsed time per iteration (s): 0.76 | learning rate: 3.065E-05 | global batch size: 256 | lm loss: 3.038378E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.257 | TFLOPs: 46.46 | +7: iteration 4330/ 5111 | consumed samples: 1108480 | consumed tokens: 2270167040 | elapsed time per iteration (s): 0.75 | learning rate: 3.039E-05 | global batch size: 256 | lm loss: 3.042727E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.194 | TFLOPs: 47.00 | +7: iteration 4340/ 5111 | consumed samples: 1111040 | consumed tokens: 2275409920 | elapsed time per iteration (s): 0.75 | learning rate: 3.013E-05 | global batch size: 256 | lm loss: 3.083668E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.486 | TFLOPs: 46.77 | +7: iteration 4350/ 5111 | consumed samples: 1113600 | consumed tokens: 2280652800 | elapsed time per iteration (s): 0.75 | learning rate: 2.988E-05 | global batch size: 256 | lm loss: 3.031536E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.231 | TFLOPs: 46.60 | +7: iteration 4360/ 5111 | consumed samples: 1116160 | consumed tokens: 2285895680 | elapsed time per iteration (s): 0.75 | learning rate: 2.962E-05 | global batch size: 256 | lm loss: 3.020508E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.471 | TFLOPs: 46.77 | +7: iteration 4370/ 5111 | consumed samples: 1118720 | consumed tokens: 2291138560 | elapsed time per iteration (s): 0.76 | learning rate: 2.937E-05 | global batch size: 256 | lm loss: 3.049235E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.533 | TFLOPs: 46.23 | +7: iteration 4380/ 5111 | consumed samples: 1121280 | consumed tokens: 2296381440 | elapsed time per iteration (s): 0.75 | learning rate: 2.913E-05 | global batch size: 256 | lm loss: 3.054029E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.103 | TFLOPs: 46.58 | +7: iteration 4390/ 5111 | consumed samples: 1123840 | consumed tokens: 2301624320 | elapsed time per iteration (s): 0.79 | learning rate: 2.888E-05 | global batch size: 256 | lm loss: 3.040176E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 323.496 | TFLOPs: 44.43 | +7: iteration 4400/ 5111 | consumed samples: 1126400 | consumed tokens: 2306867200 | elapsed time per iteration (s): 0.75 | learning rate: 2.864E-05 | global batch size: 256 | lm loss: 3.036931E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.158 | TFLOPs: 46.86 | +7: iteration 4410/ 5111 | consumed samples: 1128960 | consumed tokens: 2312110080 | elapsed time per iteration (s): 0.74 | learning rate: 2.840E-05 | global batch size: 256 | lm loss: 3.046665E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.725 | TFLOPs: 47.21 | +7: iteration 4420/ 5111 | consumed samples: 1131520 | consumed tokens: 2317352960 | elapsed time per iteration (s): 0.76 | learning rate: 2.817E-05 | global batch size: 256 | lm loss: 3.040671E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.648 | TFLOPs: 46.38 | +7: iteration 4430/ 5111 | consumed samples: 1134080 | consumed tokens: 2322595840 | elapsed time per iteration (s): 0.75 | learning rate: 2.794E-05 | global batch size: 256 | lm loss: 3.045714E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.488 | TFLOPs: 46.63 | +7: iteration 4440/ 5111 | consumed samples: 1136640 | consumed tokens: 2327838720 | elapsed time per iteration (s): 0.75 | learning rate: 2.771E-05 | global batch size: 256 | lm loss: 3.030274E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.353 | TFLOPs: 46.89 | +7: iteration 4450/ 5111 | consumed samples: 1139200 | consumed tokens: 2333081600 | elapsed time per iteration (s): 0.76 | learning rate: 2.749E-05 | global batch size: 256 | lm loss: 3.040020E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.706 | TFLOPs: 46.52 | +7: iteration 4460/ 5111 | consumed samples: 1141760 | consumed tokens: 2338324480 | elapsed time per iteration (s): 0.75 | learning rate: 2.727E-05 | global batch size: 256 | lm loss: 3.044662E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.453 | TFLOPs: 46.63 | +7: iteration 4470/ 5111 | consumed samples: 1144320 | consumed tokens: 2343567360 | elapsed time per iteration (s): 0.75 | learning rate: 2.705E-05 | global batch size: 256 | lm loss: 3.018946E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.003 | TFLOPs: 46.98 | +7: iteration 4480/ 5111 | consumed samples: 1146880 | consumed tokens: 2348810240 | elapsed time per iteration (s): 0.75 | learning rate: 2.683E-05 | global batch size: 256 | lm loss: 3.043784E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.052 | TFLOPs: 46.71 | +7: iteration 4490/ 5111 | consumed samples: 1149440 | consumed tokens: 2354053120 | elapsed time per iteration (s): 0.76 | learning rate: 2.662E-05 | global batch size: 256 | lm loss: 3.046910E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.549 | TFLOPs: 46.37 | +7: iteration 4500/ 5111 | consumed samples: 1152000 | consumed tokens: 2359296000 | elapsed time per iteration (s): 0.75 | learning rate: 2.641E-05 | global batch size: 256 | lm loss: 3.034030E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.780 | TFLOPs: 47.08 | +7: iteration 4510/ 5111 | consumed samples: 1154560 | consumed tokens: 2364538880 | elapsed time per iteration (s): 0.77 | learning rate: 2.621E-05 | global batch size: 256 | lm loss: 3.060968E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.989 | TFLOPs: 45.88 | +7: iteration 4520/ 5111 | consumed samples: 1157120 | consumed tokens: 2369781760 | elapsed time per iteration (s): 0.77 | learning rate: 2.600E-05 | global batch size: 256 | lm loss: 3.028070E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 333.314 | TFLOPs: 45.78 | +7: iteration 4530/ 5111 | consumed samples: 1159680 | consumed tokens: 2375024640 | elapsed time per iteration (s): 0.75 | learning rate: 2.580E-05 | global batch size: 256 | lm loss: 3.035182E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.957 | TFLOPs: 46.97 | +7: iteration 4540/ 5111 | consumed samples: 1162240 | consumed tokens: 2380267520 | elapsed time per iteration (s): 0.75 | learning rate: 2.561E-05 | global batch size: 256 | lm loss: 3.039873E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.043 | TFLOPs: 46.71 | +7: iteration 4550/ 5111 | consumed samples: 1164800 | consumed tokens: 2385510400 | elapsed time per iteration (s): 0.75 | learning rate: 2.542E-05 | global batch size: 256 | lm loss: 3.039252E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.624 | TFLOPs: 47.20 | +7: iteration 4560/ 5111 | consumed samples: 1167360 | consumed tokens: 2390753280 | elapsed time per iteration (s): 0.75 | learning rate: 2.523E-05 | global batch size: 256 | lm loss: 3.026034E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.561 | TFLOPs: 47.19 | +7: iteration 4570/ 5111 | consumed samples: 1169920 | consumed tokens: 2395996160 | elapsed time per iteration (s): 0.76 | learning rate: 2.504E-05 | global batch size: 256 | lm loss: 3.039157E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.754 | TFLOPs: 46.39 | +7: iteration 4580/ 5111 | consumed samples: 1172480 | consumed tokens: 2401239040 | elapsed time per iteration (s): 0.77 | learning rate: 2.486E-05 | global batch size: 256 | lm loss: 3.028629E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.978 | TFLOPs: 45.74 | +7: iteration 4590/ 5111 | consumed samples: 1175040 | consumed tokens: 2406481920 | elapsed time per iteration (s): 0.76 | learning rate: 2.468E-05 | global batch size: 256 | lm loss: 3.028180E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.428 | TFLOPs: 46.49 | +7: iteration 4600/ 5111 | consumed samples: 1177600 | consumed tokens: 2411724800 | elapsed time per iteration (s): 0.75 | learning rate: 2.450E-05 | global batch size: 256 | lm loss: 3.037612E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.967 | TFLOPs: 46.70 | +7: iteration 4610/ 5111 | consumed samples: 1180160 | consumed tokens: 2416967680 | elapsed time per iteration (s): 0.76 | learning rate: 2.433E-05 | global batch size: 256 | lm loss: 3.034123E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.996 | TFLOPs: 46.56 | +7: iteration 4620/ 5111 | consumed samples: 1182720 | consumed tokens: 2422210560 | elapsed time per iteration (s): 0.75 | learning rate: 2.416E-05 | global batch size: 256 | lm loss: 3.023082E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.200 | TFLOPs: 46.73 | +7: iteration 4630/ 5111 | consumed samples: 1185280 | consumed tokens: 2427453440 | elapsed time per iteration (s): 0.76 | learning rate: 2.399E-05 | global batch size: 256 | lm loss: 3.044272E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.999 | TFLOPs: 46.56 | +7: iteration 4640/ 5111 | consumed samples: 1187840 | consumed tokens: 2432696320 | elapsed time per iteration (s): 0.77 | learning rate: 2.383E-05 | global batch size: 256 | lm loss: 3.052419E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.755 | TFLOPs: 45.57 | +7: iteration 4650/ 5111 | consumed samples: 1190400 | consumed tokens: 2437939200 | elapsed time per iteration (s): 0.75 | learning rate: 2.367E-05 | global batch size: 256 | lm loss: 3.022015E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.783 | TFLOPs: 46.95 | +7: iteration 4660/ 5111 | consumed samples: 1192960 | consumed tokens: 2443182080 | elapsed time per iteration (s): 0.76 | learning rate: 2.352E-05 | global batch size: 256 | lm loss: 3.029052E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.608 | TFLOPs: 46.10 | +7: iteration 4670/ 5111 | consumed samples: 1195520 | consumed tokens: 2448424960 | elapsed time per iteration (s): 0.75 | learning rate: 2.336E-05 | global batch size: 256 | lm loss: 3.028983E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.798 | TFLOPs: 46.81 | +7: iteration 4680/ 5111 | consumed samples: 1198080 | consumed tokens: 2453667840 | elapsed time per iteration (s): 0.75 | learning rate: 2.321E-05 | global batch size: 256 | lm loss: 3.038163E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.021 | TFLOPs: 46.84 | +7: iteration 4690/ 5111 | consumed samples: 1200640 | consumed tokens: 2458910720 | elapsed time per iteration (s): 0.75 | learning rate: 2.307E-05 | global batch size: 256 | lm loss: 3.052024E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.775 | TFLOPs: 46.67 | +7: iteration 4700/ 5111 | consumed samples: 1203200 | consumed tokens: 2464153600 | elapsed time per iteration (s): 0.76 | learning rate: 2.292E-05 | global batch size: 256 | lm loss: 3.029460E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.025 | TFLOPs: 46.02 | +7: iteration 4710/ 5111 | consumed samples: 1205760 | consumed tokens: 2469396480 | elapsed time per iteration (s): 0.76 | learning rate: 2.278E-05 | global batch size: 256 | lm loss: 3.037361E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.952 | TFLOPs: 46.28 | +7: iteration 4720/ 5111 | consumed samples: 1208320 | consumed tokens: 2474639360 | elapsed time per iteration (s): 0.75 | learning rate: 2.265E-05 | global batch size: 256 | lm loss: 3.037001E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.999 | TFLOPs: 46.84 | +7: iteration 4730/ 5111 | consumed samples: 1210880 | consumed tokens: 2479882240 | elapsed time per iteration (s): 0.75 | learning rate: 2.251E-05 | global batch size: 256 | lm loss: 3.060060E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.226 | TFLOPs: 46.73 | +7: iteration 4740/ 5111 | consumed samples: 1213440 | consumed tokens: 2485125120 | elapsed time per iteration (s): 0.76 | learning rate: 2.239E-05 | global batch size: 256 | lm loss: 3.032057E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.957 | TFLOPs: 46.15 | +7: iteration 4750/ 5111 | consumed samples: 1216000 | consumed tokens: 2490368000 | elapsed time per iteration (s): 0.77 | learning rate: 2.226E-05 | global batch size: 256 | lm loss: 3.026586E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 332.842 | TFLOPs: 45.72 | +7: iteration 4760/ 5111 | consumed samples: 1218560 | consumed tokens: 2495610880 | elapsed time per iteration (s): 0.76 | learning rate: 2.214E-05 | global batch size: 256 | lm loss: 3.030715E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.551 | TFLOPs: 46.50 | +7: iteration 4770/ 5111 | consumed samples: 1221120 | consumed tokens: 2500853760 | elapsed time per iteration (s): 0.76 | learning rate: 2.202E-05 | global batch size: 256 | lm loss: 3.025907E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.429 | TFLOPs: 46.21 | +7: iteration 4780/ 5111 | consumed samples: 1223680 | consumed tokens: 2506096640 | elapsed time per iteration (s): 0.76 | learning rate: 2.190E-05 | global batch size: 256 | lm loss: 3.038031E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 336.849 | TFLOPs: 46.27 | +7: iteration 4790/ 5111 | consumed samples: 1226240 | consumed tokens: 2511339520 | elapsed time per iteration (s): 0.76 | learning rate: 2.179E-05 | global batch size: 256 | lm loss: 3.039086E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.572 | TFLOPs: 46.09 | +7: iteration 4800/ 5111 | consumed samples: 1228800 | consumed tokens: 2516582400 | elapsed time per iteration (s): 0.77 | learning rate: 2.168E-05 | global batch size: 256 | lm loss: 2.996341E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.300 | TFLOPs: 45.92 | +7: iteration 4810/ 5111 | consumed samples: 1231360 | consumed tokens: 2521825280 | elapsed time per iteration (s): 0.76 | learning rate: 2.157E-05 | global batch size: 256 | lm loss: 3.022989E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.705 | TFLOPs: 46.52 | +7: iteration 4820/ 5111 | consumed samples: 1233920 | consumed tokens: 2527068160 | elapsed time per iteration (s): 0.77 | learning rate: 2.147E-05 | global batch size: 256 | lm loss: 3.050504E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.803 | TFLOPs: 45.58 | +7: iteration 4830/ 5111 | consumed samples: 1236480 | consumed tokens: 2532311040 | elapsed time per iteration (s): 0.75 | learning rate: 2.137E-05 | global batch size: 256 | lm loss: 3.011161E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.153 | TFLOPs: 46.86 | +7: iteration 4840/ 5111 | consumed samples: 1239040 | consumed tokens: 2537553920 | elapsed time per iteration (s): 0.76 | learning rate: 2.128E-05 | global batch size: 256 | lm loss: 3.041938E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.113 | TFLOPs: 46.31 | +7: iteration 4850/ 5111 | consumed samples: 1241600 | consumed tokens: 2542796800 | elapsed time per iteration (s): 0.76 | learning rate: 2.119E-05 | global batch size: 256 | lm loss: 3.037234E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.388 | TFLOPs: 46.07 | +7: iteration 4860/ 5111 | consumed samples: 1244160 | consumed tokens: 2548039680 | elapsed time per iteration (s): 0.76 | learning rate: 2.110E-05 | global batch size: 256 | lm loss: 3.010183E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 337.386 | TFLOPs: 46.34 | +7: iteration 4870/ 5111 | consumed samples: 1246720 | consumed tokens: 2553282560 | elapsed time per iteration (s): 0.75 | learning rate: 2.101E-05 | global batch size: 256 | lm loss: 3.017266E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.817 | TFLOPs: 46.81 | +7: iteration 4880/ 5111 | consumed samples: 1249280 | consumed tokens: 2558525440 | elapsed time per iteration (s): 0.76 | learning rate: 2.093E-05 | global batch size: 256 | lm loss: 3.029485E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.339 | TFLOPs: 46.47 | +7: iteration 4890/ 5111 | consumed samples: 1251840 | consumed tokens: 2563768320 | elapsed time per iteration (s): 0.75 | learning rate: 2.085E-05 | global batch size: 256 | lm loss: 3.025699E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.666 | TFLOPs: 46.66 | +7: iteration 4900/ 5111 | consumed samples: 1254400 | consumed tokens: 2569011200 | elapsed time per iteration (s): 0.75 | learning rate: 2.078E-05 | global batch size: 256 | lm loss: 3.018486E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.701 | TFLOPs: 47.07 | +7: iteration 4910/ 5111 | consumed samples: 1256960 | consumed tokens: 2574254080 | elapsed time per iteration (s): 0.85 | learning rate: 2.070E-05 | global batch size: 256 | lm loss: 3.018011E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 302.352 | TFLOPs: 41.53 | +7: iteration 4920/ 5111 | consumed samples: 1259520 | consumed tokens: 2579496960 | elapsed time per iteration (s): 0.77 | learning rate: 2.064E-05 | global batch size: 256 | lm loss: 3.042224E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 331.838 | TFLOPs: 45.58 | +7: iteration 4930/ 5111 | consumed samples: 1262080 | consumed tokens: 2584739840 | elapsed time per iteration (s): 0.76 | learning rate: 2.057E-05 | global batch size: 256 | lm loss: 3.001370E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.001 | TFLOPs: 46.56 | +7: iteration 4940/ 5111 | consumed samples: 1264640 | consumed tokens: 2589982720 | elapsed time per iteration (s): 0.75 | learning rate: 2.051E-05 | global batch size: 256 | lm loss: 3.051648E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 339.205 | TFLOPs: 46.59 | +7: iteration 4950/ 5111 | consumed samples: 1267200 | consumed tokens: 2595225600 | elapsed time per iteration (s): 0.92 | learning rate: 2.045E-05 | global batch size: 256 | lm loss: 3.015661E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 279.725 | TFLOPs: 38.42 | +7: iteration 4960/ 5111 | consumed samples: 1269760 | consumed tokens: 2600468480 | elapsed time per iteration (s): 0.75 | learning rate: 2.040E-05 | global batch size: 256 | lm loss: 3.053419E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.376 | TFLOPs: 47.03 | +7: iteration 4970/ 5111 | consumed samples: 1272320 | consumed tokens: 2605711360 | elapsed time per iteration (s): 0.91 | learning rate: 2.035E-05 | global batch size: 256 | lm loss: 3.042449E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 282.672 | TFLOPs: 38.83 | +7: iteration 4980/ 5111 | consumed samples: 1274880 | consumed tokens: 2610954240 | elapsed time per iteration (s): 0.76 | learning rate: 2.030E-05 | global batch size: 256 | lm loss: 3.012030E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.603 | TFLOPs: 46.51 | +7: iteration 4990/ 5111 | consumed samples: 1277440 | consumed tokens: 2616197120 | elapsed time per iteration (s): 0.85 | learning rate: 2.026E-05 | global batch size: 256 | lm loss: 3.030630E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 300.798 | TFLOPs: 41.32 | +7: iteration 5000/ 5111 | consumed samples: 1280000 | consumed tokens: 2621440000 | elapsed time per iteration (s): 0.79 | learning rate: 2.022E-05 | global batch size: 256 | lm loss: 3.018192E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 324.312 | TFLOPs: 44.55 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 5000 | lm loss value: 3.001338E+00 | lm loss PPL: 2.011243E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 5000 to checkpoints_619moscar +0: [2022-11-29 18:10:42,462] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step5000 is begin to save! +0: [2022-11-29 18:10:42,469] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:10:42,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:10:42,739] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:10:42,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:10:42,794] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:10:42,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:10:42,851] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:10:42,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:10:42,908] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:10:42,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:10:42,966] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:10:43,021] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:10:43,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:10:43,077] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:10:43,077] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:10:43,133] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:10:43,133] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:10:43,188] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:10:43,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:10:43,245] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:10:43,245] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:10:43,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:10:43,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/layer_13-model_00-model_states.pt... +0: [2022-11-29 18:10:43,356] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/layer_13-model_00-model_states.pt. +0: [2022-11-29 18:10:43,356] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:10:43,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:10:43,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/layer_15-model_00-model_states.pt... +0: [2022-11-29 18:10:43,468] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/layer_15-model_00-model_states.pt. +0: [2022-11-29 18:10:43,469] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/layer_16-model_00-model_states.pt... +0: [2022-11-29 18:10:43,524] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/layer_16-model_00-model_states.pt. +0: [2022-11-29 18:10:43,525] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/layer_17-model_00-model_states.pt... +0: [2022-11-29 18:10:43,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/layer_17-model_00-model_states.pt. +0: [2022-11-29 18:10:43,581] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/layer_18-model_00-model_states.pt... +0: [2022-11-29 18:10:43,636] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/layer_18-model_00-model_states.pt. +0: [2022-11-29 18:10:43,637] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/layer_19-model_00-model_states.pt... +0: [2022-11-29 18:10:43,692] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/layer_19-model_00-model_states.pt. +0: [2022-11-29 18:10:43,693] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/layer_20-model_00-model_states.pt... +0: [2022-11-29 18:10:43,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/layer_20-model_00-model_states.pt. +0: [2022-11-29 18:10:43,748] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/layer_21-model_00-model_states.pt... +0: [2022-11-29 18:10:43,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/layer_21-model_00-model_states.pt. +0: [2022-11-29 18:10:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/layer_23-model_00-model_states.pt... +0: [2022-11-29 18:10:43,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/layer_23-model_00-model_states.pt. +0: [2022-11-29 18:10:43,810] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_619moscar/global_step5000/mp_rank_00_model_states.pt +0: [2022-11-29 18:10:43,810] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:10:43,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:10:43,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:10:43,962] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:10:43,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:10:43,963] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 18:10:43,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:10:43,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:10:43,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 18:10:43,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:10:43,974] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:10:43,974] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 18:10:43,974] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:10:43,974] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:10:43,974] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 18:10:43,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:10:43,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:10:43,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 18:10:43,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:10:43,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:10:43,976] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 18:10:43,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:10:43,977] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:10:43,977] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 18:10:43,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:10:43,977] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:10:43,978] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 18:10:43,978] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:10:43,978] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:10:43,978] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 18:10:43,983] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:10:43,983] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:10:43,983] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 18:10:43,987] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:10:43,987] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:10:43,987] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 18:10:43,987] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:10:43,987] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:10:43,987] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 18:10:43,987] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:10:43,988] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:10:43,988] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 18:10:43,989] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:10:43,989] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:10:43,989] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 18:10:43,992] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:10:43,992] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:10:43,992] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:10:43,992] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:10:43,992] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 18:10:43,992] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 18:10:43,992] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:10:43,992] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:10:43,992] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 18:10:43,993] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:10:43,993] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:10:43,993] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 18:10:43,993] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:10:43,993] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:10:43,993] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 18:10:43,994] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:10:43,994] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:10:43,994] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 18:10:43,994] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:10:43,994] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:10:43,994] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 18:10:43,997] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:10:43,997] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:10:43,998] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 18:10:44,000] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:10:44,000] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:10:44,000] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 18:10:44,001] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:10:44,001] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:10:44,001] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 18:10:44,011] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:10:44,012] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:10:44,012] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 18:10:44,012] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:10:44,012] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:10:44,012] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 18:10:44,013] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:10:44,013] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:10:44,013] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 18:10:44,014] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:10:44,014] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:10:44,015] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 18:10:44,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:10:44,033] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:10:44,033] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 18:10:44,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:10:44,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:10:44,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:10:44,033] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:10:44,034] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:10:44,034] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 18:10:44,034] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 18:10:44,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:10:44,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:10:44,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 18:10:44,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:10:44,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:10:44,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 18:10:44,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:10:44,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:10:44,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 18:10:44,075] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:10:44,075] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:10:44,075] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 18:10:44,075] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:10:44,076] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:10:44,076] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 18:10:44,076] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:10:44,076] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:10:44,076] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 18:10:44,076] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:10:44,076] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:10:44,076] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 18:10:44,076] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:10:44,076] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:10:44,076] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 18:10:44,100] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:10:44,100] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:10:44,100] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:10:44,100] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:10:44,100] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:10:44,100] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:10:44,100] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:10:44,100] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:10:44,100] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:10:44,100] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:10:44,100] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:10:44,100] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:10:44,100] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:10:44,100] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:10:44,100] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 18:10:44,100] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 18:10:44,100] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 18:10:44,100] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:10:44,100] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:10:44,100] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 18:10:44,100] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 18:10:44,100] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 18:10:44,100] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 18:10:44,100] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 18:10:44,098] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:10:44,098] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:10:44,098] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:10:44,098] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:10:44,098] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:10:44,098] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:10:44,098] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:10:44,098] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:10:44,098] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 18:10:44,098] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 18:10:44,098] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 18:10:44,098] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 18:10:44,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:10:44,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:10:44,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:10:44,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:10:44,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 18:10:44,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:10:44,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:10:44,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:10:44,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 18:10:44,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 18:10:44,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:10:44,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 18:10:44,136] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:10:44,136] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 18:10:44,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:10:44,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:10:44,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:10:44,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:10:44,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:10:44,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:10:44,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:10:44,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:10:44,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:10:44,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:10:44,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:10:44,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:10:44,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:10:44,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:10:44,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:10:44,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:10:44,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 18:10:44,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 18:10:44,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 18:10:44,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 18:10:44,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 18:10:44,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 18:10:44,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 18:10:44,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: successfully saved checkpoint at iteration 5000 to checkpoints_619moscar +7: time (ms) | save-checkpoint: 1833.98 +7: iteration 5010/ 5111 | consumed samples: 1282560 | consumed tokens: 2626682880 | elapsed time per iteration (s): 0.95 | learning rate: 2.018E-05 | global batch size: 256 | lm loss: 3.025436E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 268.599 | TFLOPs: 36.89 | +7: iteration 5020/ 5111 | consumed samples: 1285120 | consumed tokens: 2631925760 | elapsed time per iteration (s): 0.74 | learning rate: 2.015E-05 | global batch size: 256 | lm loss: 3.030830E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.787 | TFLOPs: 47.22 | +7: iteration 5030/ 5111 | consumed samples: 1287680 | consumed tokens: 2637168640 | elapsed time per iteration (s): 0.75 | learning rate: 2.012E-05 | global batch size: 256 | lm loss: 2.999503E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 342.500 | TFLOPs: 47.05 | +7: iteration 5040/ 5111 | consumed samples: 1290240 | consumed tokens: 2642411520 | elapsed time per iteration (s): 0.75 | learning rate: 2.009E-05 | global batch size: 256 | lm loss: 3.041848E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 343.422 | TFLOPs: 47.17 | +7: iteration 5050/ 5111 | consumed samples: 1292800 | consumed tokens: 2647654400 | elapsed time per iteration (s): 0.76 | learning rate: 2.007E-05 | global batch size: 256 | lm loss: 3.020209E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 335.965 | TFLOPs: 46.15 | +7: iteration 5060/ 5111 | consumed samples: 1295360 | consumed tokens: 2652897280 | elapsed time per iteration (s): 0.75 | learning rate: 2.005E-05 | global batch size: 256 | lm loss: 3.024218E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 341.619 | TFLOPs: 46.92 | +7: iteration 5070/ 5111 | consumed samples: 1297920 | consumed tokens: 2658140160 | elapsed time per iteration (s): 0.76 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 3.023050E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.364 | TFLOPs: 46.48 | +7: iteration 5080/ 5111 | consumed samples: 1300480 | consumed tokens: 2663383040 | elapsed time per iteration (s): 0.75 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 3.041426E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 340.280 | TFLOPs: 46.74 | +7: iteration 5090/ 5111 | consumed samples: 1303040 | consumed tokens: 2668625920 | elapsed time per iteration (s): 0.76 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 3.042552E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 338.295 | TFLOPs: 46.47 | +7: iteration 5100/ 5111 | consumed samples: 1305600 | consumed tokens: 2673868800 | elapsed time per iteration (s): 0.82 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 3.048474E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 311.516 | TFLOPs: 42.79 | +7: iteration 5110/ 5111 | consumed samples: 1308160 | consumed tokens: 2679111680 | elapsed time per iteration (s): 0.76 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 3.039153E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 334.864 | TFLOPs: 46.00 | +0: [after training is done] datetime: 2022-11-29 18:12:08 +0: saving checkpoint at iteration 5111 to checkpoints_619moscar +7: ------------------------------------------------------------------------------------------------------------ +7: valid loss at the end of training for val data | lm loss value: 2.912877E+00 | lm loss PPL: 1.840968E+01 | +7: ------------------------------------------------------------------------------------------------------------ +0: [2022-11-29 18:12:08,709] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step5111 is begin to save! +0: [2022-11-29 18:12:08,714] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:12:08,924] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:12:08,925] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:12:08,981] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:12:08,981] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:12:09,039] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:12:09,039] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:12:09,095] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:12:09,095] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:12:09,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:12:09,150] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:12:09,205] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:12:09,205] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:12:09,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:12:09,260] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:12:09,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:12:09,316] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:12:09,373] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:12:09,373] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:12:09,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:12:09,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:12:09,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:12:09,487] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/layer_13-model_00-model_states.pt... +0: [2022-11-29 18:12:09,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/layer_13-model_00-model_states.pt. +0: [2022-11-29 18:12:09,541] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:12:09,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:12:09,597] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/layer_15-model_00-model_states.pt... +0: [2022-11-29 18:12:09,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/layer_15-model_00-model_states.pt. +0: [2022-11-29 18:12:09,655] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/layer_16-model_00-model_states.pt... +0: [2022-11-29 18:12:09,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/layer_16-model_00-model_states.pt. +0: [2022-11-29 18:12:09,711] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/layer_17-model_00-model_states.pt... +0: [2022-11-29 18:12:09,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/layer_17-model_00-model_states.pt. +0: [2022-11-29 18:12:09,767] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/layer_18-model_00-model_states.pt... +0: [2022-11-29 18:12:09,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/layer_18-model_00-model_states.pt. +0: [2022-11-29 18:12:09,825] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/layer_19-model_00-model_states.pt... +0: [2022-11-29 18:12:09,880] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/layer_19-model_00-model_states.pt. +0: [2022-11-29 18:12:09,880] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/layer_20-model_00-model_states.pt... +0: [2022-11-29 18:12:09,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/layer_20-model_00-model_states.pt. +0: [2022-11-29 18:12:09,936] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/layer_21-model_00-model_states.pt... +0: [2022-11-29 18:12:09,991] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/layer_21-model_00-model_states.pt. +0: [2022-11-29 18:12:09,991] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/layer_23-model_00-model_states.pt... +0: [2022-11-29 18:12:09,996] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/layer_23-model_00-model_states.pt. +0: [2022-11-29 18:12:09,997] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_619moscar/global_step5111/mp_rank_00_model_states.pt +0: [2022-11-29 18:12:09,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/mp_rank_00_model_states.pt... +0: [2022-11-29 18:12:09,999] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/mp_rank_00_model_states.pt. +0: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:12:10,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:12:10,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:12:10,150] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:12:10,150] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +0: [2022-11-29 18:12:10,155] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:12:10,155] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:12:10,155] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +7: [2022-11-29 18:12:10,158] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:12:10,158] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:12:10,158] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +0: [2022-11-29 18:12:10,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:12:10,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:12:10,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +7: [2022-11-29 18:12:10,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:12:10,162] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:12:10,162] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +3: [2022-11-29 18:12:10,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:12:10,165] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:12:10,165] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +3: [2022-11-29 18:12:10,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:12:10,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:12:10,165] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:12:10,165] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:12:10,165] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +3: [2022-11-29 18:12:10,165] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +4: [2022-11-29 18:12:10,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:12:10,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:12:10,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +4: [2022-11-29 18:12:10,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:12:10,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:12:10,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:12:10,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:12:10,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +4: [2022-11-29 18:12:10,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +4: [2022-11-29 18:12:10,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:12:10,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:12:10,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +4: [2022-11-29 18:12:10,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:12:10,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:12:10,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +2: [2022-11-29 18:12:10,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:12:10,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:12:10,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +2: [2022-11-29 18:12:10,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:12:10,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:12:10,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +2: [2022-11-29 18:12:10,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:12:10,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:12:10,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +4: [2022-11-29 18:12:10,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:12:10,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:12:10,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +4: [2022-11-29 18:12:10,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:12:10,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:12:10,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +0: [2022-11-29 18:12:10,171] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:12:10,171] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +5: [2022-11-29 18:12:10,171] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:12:10,171] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +0: [2022-11-29 18:12:10,171] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:12:10,172] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:12:10,172] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +0: [2022-11-29 18:12:10,172] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:12:10,172] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:12:10,172] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +0: [2022-11-29 18:12:10,172] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:12:10,172] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:12:10,173] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +3: [2022-11-29 18:12:10,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:12:10,173] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:12:10,173] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +3: [2022-11-29 18:12:10,174] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:12:10,174] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:12:10,174] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +3: [2022-11-29 18:12:10,175] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:12:10,175] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:12:10,175] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +7: [2022-11-29 18:12:10,176] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:12:10,176] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:12:10,176] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:12:10,176] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:12:10,176] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +7: [2022-11-29 18:12:10,176] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +3: [2022-11-29 18:12:10,176] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:12:10,176] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:12:10,176] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +7: [2022-11-29 18:12:10,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:12:10,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:12:10,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +7: [2022-11-29 18:12:10,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:12:10,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:12:10,179] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:12:10,179] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:12:10,179] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +7: [2022-11-29 18:12:10,179] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +5: [2022-11-29 18:12:10,171] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:12:10,171] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +5: [2022-11-29 18:12:10,171] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:12:10,171] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:12:10,171] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +2: [2022-11-29 18:12:10,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:12:10,180] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:12:10,180] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +2: [2022-11-29 18:12:10,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:12:10,180] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:12:10,180] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +2: [2022-11-29 18:12:10,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:12:10,180] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:12:10,180] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +5: [2022-11-29 18:12:10,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:12:10,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:12:10,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:12:10,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:12:10,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:12:10,180] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:12:10,180] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:12:10,180] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:12:10,180] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:12:10,180] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:12:10,180] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +5: [2022-11-29 18:12:10,180] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +1: [2022-11-29 18:12:10,152] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:12:10,180] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +5: [2022-11-29 18:12:10,180] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +5: [2022-11-29 18:12:10,180] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +1: [2022-11-29 18:12:10,152] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:12:10,152] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +1: [2022-11-29 18:12:10,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:12:10,154] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:12:10,154] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +1: [2022-11-29 18:12:10,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:12:10,157] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:12:10,157] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +1: [2022-11-29 18:12:10,158] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:12:10,158] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:12:10,158] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +1: [2022-11-29 18:12:10,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:12:10,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:12:10,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +1: [2022-11-29 18:12:10,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:12:10,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:12:10,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +5: [2022-11-29 18:12:10,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:12:10,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:12:10,186] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:12:10,186] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +2: [2022-11-29 18:12:10,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:12:10,189] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:12:10,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +2: [2022-11-29 18:12:10,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:12:10,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:12:10,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +3: [2022-11-29 18:12:10,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:12:10,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:12:10,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +6: [2022-11-29 18:12:10,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:12:10,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:12:10,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:12:10,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +0: [2022-11-29 18:12:10,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:12:10,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:12:10,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:12:10,186] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:12:10,186] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:12:10,186] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +1: [2022-11-29 18:12:10,186] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +5: [2022-11-29 18:12:10,185] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:12:10,185] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +0: [2022-11-29 18:12:10,325] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:12:10,325] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +6: [2022-11-29 18:12:10,162] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:12:10,162] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +6: [2022-11-29 18:12:10,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:12:10,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:12:10,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +6: [2022-11-29 18:12:10,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:12:10,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:12:10,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:12:10,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +6: [2022-11-29 18:12:10,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:12:10,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +6: [2022-11-29 18:12:10,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:12:10,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:12:10,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:12:10,212] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:12:10,212] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:12:10,212] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:12:10,212] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +6: [2022-11-29 18:12:10,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:12:10,212] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +6: [2022-11-29 18:12:10,212] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +6: [2022-11-29 18:12:10,212] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_619moscar/global_step5111/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:12:10,212] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5111 is ready now! +0: successfully saved checkpoint at iteration 5111 to checkpoints_619moscar +7: ------------------------------------------------------------------------------------------------------------ +7: test loss at the end of training for test data | lm loss value: 2.950273E+00 | lm loss PPL: 1.911117E+01 | +7: ------------------------------------------------------------------------------------------------------------ +END 2085652: Tue Nov 29 18:12:20 EET 2022 diff --git a/619m2b72b7/sbatch_619m_oscar.sh b/619m2b72b7/sbatch_619m_oscar.sh new file mode 100644 index 0000000000000000000000000000000000000000..b0b42531976b43572f40067fdc3f4e807466a107 --- /dev/null +++ b/619m2b72b7/sbatch_619m_oscar.sh @@ -0,0 +1,160 @@ +#!/bin/bash +#SBATCH --nodes=8 +#SBATCH --ntasks-per-node=1 +#SBATCH --cpus-per-task=32 +#SBATCH --mem=256G +#SBATCH -p eap +#SBATCH -t 48:00:00 +#SBATCH --gpus-per-node=mi250:8 +#SBATCH --exclusive=user +#SBATCH --hint=nomultithread +#SBATCH --account=project_462000119 +#SBATCH -o logs/%j.out +#SBATCH -e logs/%j.err + +VARIANT=619moscar + +# if run without sbatch, invoke here +if [ -z $SLURM_JOB_ID ]; then + mkdir -p logs + sbatch "$0" + exit +fi + +set -euo pipefail + +# symlink logs/latest.out and logs/latest.err +ln -f -s $SLURM_JOB_ID.out logs/latest.out +ln -f -s $SLURM_JOB_ID.err logs/latest.err + +KILL_SWITCH_PATH=kill-switch-$VARIANT +CHECKPOINT_PATH=checkpoints_$VARIANT +TENSORBOARD_PATH=tensorboard_$VARIANT +# Start from scratch +rm -rf "$CHECKPOINT_PATH" "$TENSORBOARD_PATH" + +# Data +VOCAB_FILE="gpt2/vocab.json" +MERGE_FILE="gpt2/merges.txt" +DATA_PATH="/scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document" +DATA_PATH="/scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document" +PP_SIZE=1 +TP_SIZE=1 + +MICRO_BATCH_SIZE=4 +GRADIENT_ACCUMULATION_STEPS=1 +WORLD_SIZE=$((SLURM_GPUS_ON_NODE*SLURM_JOB_NUM_NODES)) +GLOBAL_BATCH_SIZE=$((MICRO_BATCH_SIZE*WORLD_SIZE*GRADIENT_ACCUMULATION_STEPS)) + +# Model parameters +source model_params.sh +MODEL_PARAM=("${PARAM_632M[@]}") +NHIDDEN=${MODEL_PARAM[0]} +FFN_HIDDEN_SIZE=${MODEL_PARAM[1]} +KV_SIZE=${MODEL_PARAM[2]} +NHEADS=${MODEL_PARAM[3]} +NLAYERS=${MODEL_PARAM[4]} +SEQ_LEN=2048 + +echo "Model parameters: d_model $NHIDDEN ffw_size $FFN_HIDDEN_SIZE kv_size $KV_SIZE n_heads $NHEADS n_layers $NLAYERS" + +SAVE_INTERVAL=1000 + +# Tokens: 2680000000 +# -> Samples: 1_308_594 +TRAIN_SAMPLES=1_308_594 + +OPTIMIZER_ARGS=" \ + --optimizer adam \ + --adam-beta1 0.9 \ + --adam-beta2 0.999 \ + --adam-eps 1e-8 \ + --lr 2e-4 \ + --min-lr 2e-5 \ + --lr-decay-style cosine \ + --lr-decay-samples $TRAIN_SAMPLES \ + --lr-warmup-samples 13_086 \ + --clip-grad 1.0 \ + --weight-decay 1e-1 \ + " + +GPT_ARGS=" \ + --num-layers $NLAYERS \ + --hidden-size $NHIDDEN \ + --num-attention-heads $NHEADS \ + --kv-channels $KV_SIZE \ + --ffn-hidden-size $FFN_HIDDEN_SIZE \ + --seq-length $SEQ_LEN \ + --max-position-embeddings $SEQ_LEN \ + --micro-batch-size $MICRO_BATCH_SIZE \ + --global-batch-size $GLOBAL_BATCH_SIZE \ + --train-samples $TRAIN_SAMPLES \ + --vocab-file $VOCAB_FILE \ + --merge-file $MERGE_FILE \ + --clip-grad 1.0 \ + --kill-switch-path $KILL_SWITCH_PATH \ + --bf16 \ + $OPTIMIZER_ARGS \ + " + +OUTPUT_ARGS=" \ + --log-interval 10 \ + --save-interval $SAVE_INTERVAL \ + --eval-interval 1000 \ + --eval-iters 1 \ + --tensorboard-dir $TENSORBOARD_PATH \ + --tensorboard-queue-size 5 \ + --log-timers-to-tensorboard \ + --log-batch-size-to-tensorboard \ + --log-validation-ppl-to-tensorboard \ + " + +ZERO_STAGE=0 + +mkdir -p ds_configs +DS_CONFIG_PATH="ds_configs/$SLURM_JOB_ID.json" + +cat < $DS_CONFIG_PATH +{ + "train_micro_batch_size_per_gpu": $MICRO_BATCH_SIZE, + "train_batch_size": $GLOBAL_BATCH_SIZE, + "gradient_clipping": 1.0, + "zero_optimization": { + "stage": $ZERO_STAGE + }, + "bf16": { + "enabled": true + }, + "steps_per_print": 2000, + "wall_clock_breakdown": false +} +EOF + +DEEPSPEED_ARGS=" \ + --deepspeed \ + --deepspeed_config $DS_CONFIG_PATH \ + --zero-stage $ZERO_STAGE \ + " + +CMD=" \ + Megatron-DeepSpeed/pretrain_gpt.py \ + --tensor-model-parallel-size $TP_SIZE \ + --pipeline-model-parallel-size $PP_SIZE \ + $GPT_ARGS \ + $OUTPUT_ARGS \ + --save $CHECKPOINT_PATH \ + --load $CHECKPOINT_PATH \ + --data-path $DATA_PATH \ + --data-impl mmap \ + --split 949,50,1 \ + $DEEPSPEED_ARGS \ + " + +echo $CMD + +echo "START $SLURM_JOBID: $(date)" + +# bash launch_srun.sh $CMD +srun --label launch.sh $CMD + +echo "END $SLURM_JOBID: $(date)" diff --git a/619m2b72b7/tensorboard/events.out.tfevents.1669734286.nid005059.110332.0 b/619m2b72b7/tensorboard/events.out.tfevents.1669734286.nid005059.110332.0 new file mode 100644 index 0000000000000000000000000000000000000000..42cc847f2dad6c3bb8e2deec1ef60cc2623194d7 --- /dev/null +++ b/619m2b72b7/tensorboard/events.out.tfevents.1669734286.nid005059.110332.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:164b33638f3b1e3e1f4c6f4634ab1604d4266d3b3fe23434ed03b6a902b2a9db +size 9100371 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8ced1bc00c48854d3b3116849d238aa37a524b93 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef9ec9f74f9775df64e1427677ef329b2cc0212640b6bf819725d24f0a2b9e49 +size 15518743 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a91de55d24f201cbecde3b6c0faf07c0c9dddbbe --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97154709f32073c42acb17a320719fceeb426f42f9bd6c13887f42a6003c6a7d +size 15518690 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cbeb8a60b316341636bb72de9d518c5661e5ef3a --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6dbd994119cb1df1a020064b26b1f27b2bf4a662299015a6fa5b412d2e5e9df +size 15518626 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c7d7e08b93b20400539b1e7f4f70c9116294d343 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f2ba662f3d8d93330f3044e2d7dfa6c2f7fb10e1ba76ee6bdfa1fab797faf63 +size 15518690 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..51f18064920545e3a43dc2065db49ba2aa5c15fb --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4346ec52d64c0fac3baf0198d549a1d1c0c001e9ae5b9377151885aba61a03e +size 15518754 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..37fb9bc27f3880bae47e780d0aac44b1c7eab0f2 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cc8e17d7901ea1527b1716e05007940e95b53f17b4ed690bfd0d7c1e70642e5 +size 15518626 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5c1fc9b22cb827cf20da0945272ad8044103fc44 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13766efd3cb29c3b689cde5782cf5bf4e1fc10d3c991d428f51202b1aa2e5887 +size 15518754 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3ab6dc14ee4b092edae1e0a59b3f03a41cdf8b70 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:324adc33aa55e016098ceb7c9f66ab020ce3022dc22033ec0231c5ad77fb3d50 +size 15518690 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..32107b36bcf74fbe3ee9eb3f54f1c486ebd235ce --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1209a278802996235bd6abf676730a1f1ff7c5e1b5cfff8de536577802d7a78d +size 15518626 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..36e87bf57b3f618923c83ab9b829aff1cf3057f3 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eda0a793c4b5ead8e6e993267ea6f3ef4ac00a8351652a09845f17d27eb2ceee +size 15518754 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f209d6c68ca20d07d6cf300cdb1abc33f02aa5de --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e62d8f7bbad84425e68a2bb8dfe6a8ef5076d798d66e0b18c08a668fb2bfa4e8 +size 15518754 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e7bb83f203591a50aee208b4e8930c09796dd5c4 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8dda618d7631b780fc056f0a3b9efa4a0f7faee75338d41c38d046e0bdcfc42 +size 15518615 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..40041a700c90e3677f90ad3124f95ba8c53e82e1 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2219d0083d74722ece045a59c8f7e7238a9761b764ba73ccb55c0ddec3d3da10 +size 15518626 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a802ea80b9287bd03d2c0789aa7fd9f395d35dfe --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:890bd85d4d421e34dcb873fafe9104e5eb5dd59bca0cbf07b440e470e76c0796 +size 15518754 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b2f30e1266f05d8d7261c9348d9b2cd097d11850 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a2a2179b54d19ede5196dafa1d2946e18000d51d4f09f6e8b43586a81b0d464 +size 15518754 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dbc8bc973e1b3cd54a589df9713d0164d0b48946 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00a270d1f7d6e4df0df9fc30af11897da5f81961552316b7220b4db279cf5710 +size 15518626 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..053d20ed8c1e84de898d7ca09e80dc843d7fe47c --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c885da045b8899f1cf261ee0b4c3228e7a667a002a365e9ab6f14ae8b8655cd +size 15518690 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1d85788eea2d331603ba66ffbe7b8d78a10b5e72 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6db8a65353d982d9743f0a6ac43b0a066d99418435e3ce1ae20bfe406515af81 +size 15518690 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..502b8909643d6029510356e0a0d953a32a7ce5a9 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9b745da9dbc812e27a9c051d59bc5ae58eaba96bcb31a574155fb90b58a9ce9 +size 15518690 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cec11584fb46e224df1c2f18a233925bb7ac4131 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2521daa976fb0aa821d940e7cb58a8c8fadf5e296b4902053db89ccb96786b59 +size 15518690 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c8c2e8caa6c9e274ef964c3e4b565878267aefd7 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faa44116f28f3a702615e167fecccb2c64b2a3d99d519fa2af0f81b12f95920e +size 15518754 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..529a51a6c1d99a4ecd5adf34655c45e693b6643d --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88ea4754b05ef5f13d60149b4b7feecf10e53a52696374e8919a4435912948e8 +size 15518690 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..78292b9e4775f205ee4bbafc717a308a4e137528 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecdb51c4eca189cccf85746e1123da0057daeeb19ae0b09eab7c44a01b852dd2 +size 15518743 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3e5c2e178a79282c6e090504e165f8f146c2ec43 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72aac86465f61ca1bd636b791b597d7bfd081c66fc6531cc889d4217982b57ee +size 15518626 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6a314238bc4b4275576717a007ba892d9509c7bf --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b069c384e73f4010d572ec33ed1db10333ccbffea41ab3c8812f9d0ac90c608 +size 15518690 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..df049306f0145392dca8570814355af538784109 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f7d0013c305680e3a4cc5e63e11909191054174b5c780316c51934b8e3b4695 +size 15518690 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3f3fa34ea70e6d3aa303c5207eb5d73f9f5fa220 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1cbcc8ac284d8c258353c9c3d4bca11da8dd77ce0f616ae74f17155e063af9f +size 15518690 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..18157cc7cbcdf23622565a4f6208ffe8dbdb2595 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec70a4bd80b45970cc29b6d60788c5c98a60356ed886b2c72d3f3b92f24195a5 +size 15518754 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a58b966c5ec22ab275866ce5428f65624286cf67 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b84393c7e69008dbb8364c382be5627509d4fc44d6fbd7b65f5b300c5c9c0dac +size 15518690 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0e7b0d11e203185dc013665063bd1d09c982dd39 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6e9694c332d7cbed869421f6989c76a7071764dc3f441e6cfd6a9d795ceb90a +size 15518690 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4b4d63e3950817fc672f4f355fa7d84111cf3851 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:278fea33c0353646ef08bd3b80fe512ad3733c4a361a52e25dcaf4b2153ce148 +size 15518818 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7212e890a989286d0327f92577e7f8be39165379 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:016810a6f56215f088296d05fdc5f9161103348ad6fb50baba2e80f329d8d031 +size 15518754 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..34ecf3211fe2ab874944d6986637c889ef1eb190 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13c1ccbc4ee5ea1d22f7a745861161d94ea26082685d32ad63457a37dda9052c +size 15518754 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..40fb12754ee94d839c5bd84fb14a350d57db28ce --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0385728ed61c12aa724f42b4549d80f447a28df974e5b9beb8b77297956b8f0a +size 15518743 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..71b1141a9d678ed5b38f2a37076a92a91fe2b7a9 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9040b8392a5b59b216e8a89fc43c62c8dd9ceb2ba42944b44a247c67bfab05e +size 15518754 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d83e4fabfbdf6194227c397607630cf7091a77e7 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc64aab27cd57d71402f4f36793eafef6ae956dbee61612bcb23a419251e8963 +size 15518818 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..36be16e1727bd81edb18e525b09c520d3d64d9c0 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:799c69a708243059d550eaeabf589c55726e08ea0a4b87b6c3fc55037a43f716 +size 15518626 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..60df0c91f266e5f3166d23078680c103ff01a02b --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0747ac7438809b24a408be9757049fe8b7fd7bce011a6877f1787ce8380c0854 +size 15518754 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1d4e62d19377a829ac15f05aa3153d42c32a4b6c --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28d4a66f27122083d9b3439493ff9e2b801fb3f821986f7de1297c9dd1b5c6b5 +size 15518754 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..81c8e7ff57f4b85b1e1c22ad59151412bae472a1 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2211ced85b91beef45e627787c0fea82ed208eee9cf5baba924c1067a7435dd6 +size 15518690 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2b9efa55df602f0afaf7c4fa95c6bf1da232110b --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12fbfb895137c00b656b4a9f8560e9de572b41cbe4dddce45f7965cf4c7210ac +size 15518690 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..db77b9dda20d8b3ca7ce49de5e0bde11eaae0288 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f969d48741b748d15f67e8ce8ee419f60b2827211e6d694a1911303e66caef8 +size 15518754 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a40e6b0056c931e04a2f67c4fb9d6dc49e27bd1e --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5e6494b85a0f269886126a3ca40784382102589cf38f4939a455bd8fe1bdf75 +size 15518562 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b892a6cbc8f1ed0690e4c864760af53b01a98f28 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdb019bc211ccc2a47e9e0e9daf9a2254af815be620d92e1d842d624cf4a6545 +size 15518690 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9a72089380ac8875ed852137165fc615383eb916 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a113116acd4dac0cec81f5a3749ce6689bb918646d13107718ac64a13e60e43 +size 15518615 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9e805c7b3e540ac53c02e801eaef93076f5f27b7 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8027a7ed509e2d5a15af2e943f71fa6bfe92b8af0fb01ac4f70f904bb988636 +size 15518818 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..54ad2868e559506a80899d1521b20b1346f9e57a --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99b2cc6a10ddc625bc5cb546e7da96dd60f82c34d2a87967c4090441ac1b7558 +size 15518690 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..805f732698e158a85b98e54207c3762d73f23b20 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b063ee1f2887b5195e06fca9f866b034840ab754a4a5a42a082a5213208008df +size 15518754 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..45de33399f95c64cc5059bdd05e271ce1a00fff2 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf107843f124242b8bc250999bbcd75cdc2be8f7b4866f9de171d26573933f1e +size 15518754 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a23945027864a14dea75798167d071459aab7e2f --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cac0d4a1a17d2a01f2e1e13330217dcbc26fbb2cc03cefd76b371cb7a2de44d4 +size 15518754 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e482de28b272b78ae7882fd89b1b7e85bef396de --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05ac65f3d5fd40fbebd1e0202ea39b8b510429c1ecd66e8dfbcee52b215e42f4 +size 15518626 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d76e72066e529ec52f0f7479d4f74bb3eac9411d --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c882ae70b7c161ee8e3b1f2f4853f45de0e02b02285c2aac503277d77ebd715 +size 15518818 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a9862933226740002d8e58c101c62370ca6fad5e --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db6fda5bb414f95b9ef86d468282326b5ce175243b0dd65da22b141442712129 +size 15518690 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..24918b6bf6119b5e1a56f2199c692eee3f8189af --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3abb9b39c7be68b4cabdf9e7b628d0e83d6a90e5a28d0431f366cd50e789d8f +size 15518690 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..94fe6ac3766042b2e013caf6bf2de578ed9b8910 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97d25b0ac7435c16d2ab184d291bca10428ad9cef9e06dba562d6b66618e1924 +size 15518754 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..471a945388cd7e79959b68847253c68cbb43eb0b --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e99c2f0bc48c6b440f3aecfa957758b26da8937d4ea6fa8f18fe265d2504005 +size 15518679 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fceb8741252de36b2077dca4b9ae027680a163f7 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4f0f1c7994c7fe9b9c3aef1eb38dcd0671ea27bcf2156fdae2329d017c31577 +size 15518818 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..910ede7b3330dddc70dbc0cd9a5f003b97c473c0 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0249fa595b248702e89d76658d23ebdb5a645c6a23507bd39e4b9b1efc4cb97 +size 15518690 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6ff63df188825bc0f5a30bf2ea05cd29bd592f6c --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31a506fcffd02e2b1fa4b65cc7cbab36a1a3021066438857534b7583917d64c5 +size 15518690 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c8cf00af173d4c4432f80439fde5d780d2fe152d --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:770d6cbea619656e1fce64a751529b99b5e697a9bf67f000485873fe7f237760 +size 15518690 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..662e0165f0a1584505f8e2377588d6a9422fa23b --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db06829f22e97a3fdde4d35c97ed16596c8c2bda2e77b054f6f4a0787ff4de82 +size 15518743 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b4a3c7c28bb96a3d11c6c03de3e969d1e12c66a1 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83e16bf542f81363ab9d6f24507eaabad51777a5a4fcc447891f05a8bcc12fe1 +size 15518679 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..be3027653eb4430b0ad404c174159bcf4f006e67 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a84cc46f64a24815ea413780aca548bb6572086e8e025c3fdff35345b564400 +size 15518679 diff --git a/83m20b20b/global_step37905/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt b/83m20b20b/global_step37905/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..abfb49b66ab3e943b95d7ef9ba9f3d60cd87af05 --- /dev/null +++ b/83m20b20b/global_step37905/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b84015a7408e5c5d8992e770c1a71d5166e3545086c288d62d82bc6dd055066 +size 15518743 diff --git a/83m20b20b/global_step37905/layer_01-model_00-model_states.pt b/83m20b20b/global_step37905/layer_01-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..56cb890f1bb420562fe62f243dca1f09148f20d2 --- /dev/null +++ b/83m20b20b/global_step37905/layer_01-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:186d556928fa5f54206687adf5c0b13f7996bd6e328ef50c3f84820467c87a9f +size 67011843 diff --git a/83m20b20b/global_step37905/layer_03-model_00-model_states.pt b/83m20b20b/global_step37905/layer_03-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a5d6242deea19e1803edbff9d2091c0d24f3cbf --- /dev/null +++ b/83m20b20b/global_step37905/layer_03-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4f73e48b701eab110d65addbebf78154bd1f09e51bb198a433f698534f51177 +size 9851395 diff --git a/83m20b20b/global_step37905/layer_04-model_00-model_states.pt b/83m20b20b/global_step37905/layer_04-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3c2a46d64a3a53260d45d4599ace5dbedd5abf3c --- /dev/null +++ b/83m20b20b/global_step37905/layer_04-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82d14cdc5c66c9efdcc70843916fc25902c110e72686fd91d19b1c548fdb3e60 +size 9851395 diff --git a/83m20b20b/global_step37905/layer_05-model_00-model_states.pt b/83m20b20b/global_step37905/layer_05-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..608fb7acdf4baad59875a722b85ae49a31da3238 --- /dev/null +++ b/83m20b20b/global_step37905/layer_05-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f77b12e8ba633d89b6c4814b9aa0dc6dcdd5b8d3423a9708646bac18778a0c1 +size 9851395 diff --git a/83m20b20b/global_step37905/layer_06-model_00-model_states.pt b/83m20b20b/global_step37905/layer_06-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8e7a7a9ae5a7b88994087ad7408ae07e691d8952 --- /dev/null +++ b/83m20b20b/global_step37905/layer_06-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caf8a4db676db7391e167d0d437f87c6ba124b33bab3ed3f5c4a531f0b06b866 +size 9851395 diff --git a/83m20b20b/global_step37905/layer_07-model_00-model_states.pt b/83m20b20b/global_step37905/layer_07-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6b5e89794372179c7a2571518f61ef344d01ba13 --- /dev/null +++ b/83m20b20b/global_step37905/layer_07-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5e9b9c0e6c8f48c9870d0bac6a52ae97589aebd1d45c65106bc12a0ee159087 +size 9851395 diff --git a/83m20b20b/global_step37905/layer_08-model_00-model_states.pt b/83m20b20b/global_step37905/layer_08-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8b8df4b3140c03bbacd95430e7472231a31946e6 --- /dev/null +++ b/83m20b20b/global_step37905/layer_08-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae8f64e17e4f6b06826ad425fa85bb60238742cb71841480122a0c0bedbd3e48 +size 9851395 diff --git a/83m20b20b/global_step37905/layer_09-model_00-model_states.pt b/83m20b20b/global_step37905/layer_09-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5d3a3ec9dd59c7e7a79b1fbe978784d90e060dd5 --- /dev/null +++ b/83m20b20b/global_step37905/layer_09-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:200b0e4a81c1419b9453a481ebb665deb437947e8c70cff3a3e19503874ca0b1 +size 9851395 diff --git a/83m20b20b/global_step37905/layer_10-model_00-model_states.pt b/83m20b20b/global_step37905/layer_10-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..34343f6ea6bc25fd1389edd294de0be69109df34 --- /dev/null +++ b/83m20b20b/global_step37905/layer_10-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f61c4e69317c90a06cf47eb61e96a4e4ef05c937686cf0681d400cd948d562f +size 9851395 diff --git a/83m20b20b/global_step37905/layer_11-model_00-model_states.pt b/83m20b20b/global_step37905/layer_11-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..09e21405e11b93680e30d11183169bbbf01c6611 --- /dev/null +++ b/83m20b20b/global_step37905/layer_11-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50441c342ef5a66704f1a72fe4cf83b6570fab8c3085c7450a562018af94c9e4 +size 9851395 diff --git a/83m20b20b/global_step37905/layer_12-model_00-model_states.pt b/83m20b20b/global_step37905/layer_12-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5a9af1d92cc18e8652f4a5a2b4e34aa31e607fce --- /dev/null +++ b/83m20b20b/global_step37905/layer_12-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9c058600fd13be9a981c199e02cbb9fba47e15311e684dbd5b2e719af1cd4f0 +size 9851395 diff --git a/83m20b20b/global_step37905/layer_14-model_00-model_states.pt b/83m20b20b/global_step37905/layer_14-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7701427ac1fb8283ad9715d0133238a645916533 --- /dev/null +++ b/83m20b20b/global_step37905/layer_14-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:362f4c782775c9db7c9906097cd1bd4867a951cf04a81b01910dba362f02c184 +size 3779 diff --git a/83m20b20b/global_step37905/mp_rank_00_model_states.pt b/83m20b20b/global_step37905/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c2894ed33b44669445618700c6476d4cbe0cfda3 --- /dev/null +++ b/83m20b20b/global_step37905/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c8bbe33a7ad58964ec70ceea7636c606fbdc6a679f4e4f6f424043b8ca660de +size 31347 diff --git a/83m20b20b/logs/2085611.err b/83m20b20b/logs/2085611.err new file mode 100644 index 0000000000000000000000000000000000000000..c2cd2a0cb4f7a910a8d7c718411cd43aa141b8ab --- /dev/null +++ b/83m20b20b/logs/2085611.err @@ -0,0 +1,483 @@ +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module scaled_upper_triang_masked_softmax_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module scaled_upper_triang_masked_softmax_cuda... +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module scaled_masked_softmax_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module scaled_masked_softmax_cuda... +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module fused_mix_prec_layer_norm_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module fused_mix_prec_layer_norm_cuda... +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +7: Successfully preprocessed all matching files. +4: Successfully preprocessed all matching files. +4: Successfully preprocessed all matching files. +4: Successfully preprocessed all matching files. +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja... +4: Building extension module utils... +4: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +4: Loading extension module utils... +3: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: +1: +1: +1: +1: +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: +2: +2: +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: +2: +2: +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: +5: +5: +5: +5: +5: +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: +6: +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: +6: +6: +0: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja... +0: Building extension module utils... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +7: Loading extension module utils... +5: Loading extension module utils... +7: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +7: Loading extension module utils... +5: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +5: Loading extension module utils... +7: Loading extension module utils... +5: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +6: +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +5: +5: Loading extension module utils... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +6: +6: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +0: Loading extension module utils...Loading extension module utils...Loading extension module utils... +0: +0: +0: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: +7: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +7: +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils...Loading extension module utils... +4: Loading extension module utils...Loading extension module utils... +4: +4: +4: Loading extension module utils... +3: Loading extension module utils...Loading extension module utils...Loading extension module utils...Loading extension module utils... +3: +3: +3: +3: Loading extension module utils...Loading extension module utils...Loading extension module utils... +3: +3: +0: Loading extension module utils... +1: Loading extension module utils... +2: Loading extension module utils... +1: Loading extension module utils... +2: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +2: Loading extension module utils... +1: Loading extension module utils... +2: Loading extension module utils... +1: Loading extension module utils... +2: Loading extension module utils... +1: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: +3: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +3: +3: Loading extension module utils...Loading extension module utils... +3: +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +1: +1: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +1: +1: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +2: +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/utils.py:349: UserWarning: Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings +0: warnings.warn("Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings") diff --git a/83m20b20b/logs/2085611.out b/83m20b20b/logs/2085611.out new file mode 100644 index 0000000000000000000000000000000000000000..266da3fed14e09de331bcd0c74c7521589b25acc --- /dev/null +++ b/83m20b20b/logs/2085611.out @@ -0,0 +1,15728 @@ +Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +Megatron-DeepSpeed/pretrain_gpt.py --tensor-model-parallel-size 1 --pipeline-model-parallel-size 1 --num-layers 10 --hidden-size 640 --num-attention-heads 10 --kv-channels 64 --ffn-hidden-size 2560 --seq-length 2048 --max-position-embeddings 2048 --micro-batch-size 4 --global-batch-size 256 --train-samples 9_703_701 --vocab-file gpt2/vocab.json --merge-file gpt2/merges.txt --loss-scale 12 --clip-grad 1.0 --kill-switch-path kill-switch-83moscar --bf16 --checkpoint-activations --optimizer adam --adam-beta1 0.9 --adam-beta2 0.999 --adam-eps 1e-8 --lr 2e-4 --min-lr 2e-5 --lr-decay-style cosine --lr-decay-samples 9_703_701 --lr-warmup-samples 97_037 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83moscar --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83moscar --load checkpoints_83moscar --data-path /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2085611.json --zero-stage 0 +START 2085611: Tue Nov 29 16:53:40 EET 2022 +0: +0: +0: ======================= ROCm System Management Interface ======================= +0: ================================= Concise Info ================================= +0: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +0: 0 42.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 2 43.0c 81.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 3 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 4 40.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 6 42.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: ================================================================================ +0: ============================= End of ROCm SMI Log ============================== +2: +2: +2: ======================= ROCm System Management Interface ======================= +2: ================================= Concise Info ================================= +2: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +2: 0 48.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 2 44.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 3 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 4 42.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 6 45.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 7 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: ================================================================================ +2: ============================= End of ROCm SMI Log ============================== +1: +1: +1: ======================= ROCm System Management Interface ======================= +1: ================================= Concise Info ================================= +1: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +1: 0 47.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 2 44.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 4 42.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 6 40.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: ================================================================================ +1: ============================= End of ROCm SMI Log ============================== +3: +3: +3: ======================= ROCm System Management Interface ======================= +3: ================================= Concise Info ================================= +3: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +3: 0 44.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 1 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 2 42.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 4 39.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 6 43.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 7 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: ================================================================================ +3: ============================= End of ROCm SMI Log ============================== +7: +7: +7: ======================= ROCm System Management Interface ======================= +7: ================================= Concise Info ================================= +7: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +7: 0 44.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 2 46.0c 98.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 4 40.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 6 39.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 7 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: ================================================================================ +7: ============================= End of ROCm SMI Log ============================== +4: +4: +4: ======================= ROCm System Management Interface ======================= +4: ================================= Concise Info ================================= +4: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +4: 0 43.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 2 40.0c 81.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 4 45.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 6 41.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: ================================================================================ +4: ============================= End of ROCm SMI Log ============================== +6: +6: +6: ======================= ROCm System Management Interface ======================= +6: ================================= Concise Info ================================= +6: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +6: 0 44.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 2 40.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 4 44.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 6 40.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: ================================================================================ +6: ============================= End of ROCm SMI Log ============================== +5: +5: +5: ======================= ROCm System Management Interface ======================= +5: ================================= Concise Info ================================= +5: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +5: 0 46.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 2 42.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 4 43.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 6 38.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: ================================================================================ +5: ============================= End of ROCm SMI Log ============================== +1: Launching on nid005118 (1/8), master nid005117 port 9999, GPUs 8, CUDA: True +6: Launching on nid006655 (6/8), master nid005117 port 9999, GPUs 8, CUDA: True +0: Launching on nid005117 (0/8), master nid005117 port 9999, GPUs 8, CUDA: True +7: Launching on nid006656 (7/8), master nid005117 port 9999, GPUs 8, CUDA: True +4: Launching on nid005596 (4/8), master nid005117 port 9999, GPUs 8, CUDA: True +2: Launching on nid005350 (2/8), master nid005117 port 9999, GPUs 8, CUDA: True +3: Launching on nid005351 (3/8), master nid005117 port 9999, GPUs 8, CUDA: True +5: Launching on nid005597 (5/8), master nid005117 port 9999, GPUs 8, CUDA: True +0: using world size: 64, data-parallel-size: 64, tensor-model-parallel size: 1, pipeline-model-parallel size: 1 +0: accumulate and all-reduce gradients in fp32 for bfloat16 data type. +0: using torch.bfloat16 for parameters ... +0: ------------------------ arguments ------------------------ +0: abort_on_unmet_fused_kernel_constraints ......... False +0: accumulate_allreduce_grads_in_fp32 .............. True +0: adam_beta1 ...................................... 0.9 +0: adam_beta2 ...................................... 0.999 +0: adam_eps ........................................ 1e-08 +0: adlr_autoresume ................................. False +0: adlr_autoresume_interval ........................ 1000 +0: apply_query_key_layer_scaling ................... True +0: apply_residual_connection_post_layernorm ........ False +0: attention_dropout ............................... 0.1 +0: attention_softmax_in_fp32 ....................... False +0: bert_binary_head ................................ True +0: bert_load ....................................... None +0: bf16 ............................................ True +0: bias_dropout_fusion ............................. True +0: bias_gelu_fusion ................................ True +0: biencoder_projection_dim ........................ 0 +0: biencoder_shared_query_context_model ............ False +0: block_data_path ................................. None +0: checkpoint_activations .......................... True +0: checkpoint_in_cpu ............................... False +0: checkpoint_num_layers ........................... 1 +0: clip_grad ....................................... 1.0 +0: codecarbon_dir .................................. None +0: consumed_train_samples .......................... 0 +0: consumed_train_tokens ........................... 0 +0: consumed_valid_samples .......................... 0 +0: contigious_checkpointing ........................ False +0: cpu_optimizer ................................... False +0: cpu_torch_adam .................................. False +0: curriculum_learning ............................. False +0: data_impl ....................................... mmap +0: data_parallel_size .............................. 64 +0: data_path ....................................... ['/scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document'] +0: dataloader_type ................................. single +0: DDP_impl ........................................ local +0: decoder_seq_length .............................. None +0: deepscale ....................................... False +0: deepscale_config ................................ None +0: deepspeed ....................................... True +0: deepspeed_activation_checkpointing .............. False +0: deepspeed_config ................................ ds_configs/2085611.json +0: deepspeed_mpi ................................... False +0: distribute_checkpointed_activations ............. False +0: distributed_backend ............................. nccl +0: embed_layernorm ................................. False +0: embedding_path .................................. None +0: encoder_seq_length .............................. 2048 +0: eod_mask_loss ................................... False +0: eval_interval ................................... 1000 +0: eval_iters ...................................... 1 +0: eval_only ....................................... None +0: evidence_data_path .............................. None +0: exit_duration_in_mins ........................... None +0: exit_interval ................................... None +0: ffn_hidden_size ................................. 2560 +0: finetune ........................................ False +0: fp16 ............................................ False +0: fp16_lm_cross_entropy ........................... False +0: fp32_residual_connection ........................ False +0: gigaflos_no_embeds .............................. 0 +0: global_batch_size ............................... 256 +0: glu_activation .................................. None +0: hidden_dropout .................................. 0.1 +0: hidden_size ..................................... 640 +0: hysteresis ...................................... 2 +0: ict_head_size ................................... None +0: ict_load ........................................ None +0: img_dim ......................................... 224 +0: indexer_batch_size .............................. 128 +0: indexer_log_interval ............................ 1000 +0: inference ....................................... False +0: init_method_std ................................. 0.02 +0: init_method_xavier_uniform ...................... False +0: initial_loss_scale .............................. 4294967296 +0: kill_switch_path ................................ kill-switch-83moscar +0: kv_channels ..................................... 64 +0: layer_norm_fusion ............................... True +0: layernorm_epsilon ............................... 1e-05 +0: lazy_mpu_init ................................... None +0: load ............................................ checkpoints_83moscar +0: local_rank ...................................... None +0: log_batch_size_to_tensorboard ................... True +0: log_interval .................................... 10 +0: log_learning_rate_to_tensorboard ................ True +0: log_level ....................................... None +0: log_level_replica ............................... None +0: log_loss_scale_to_tensorboard ................... True +0: log_num_zeros_in_grad ........................... False +0: log_params_norm ................................. False +0: log_path ........................................ None +0: log_timers_to_tensorboard ....................... True +0: log_validation_ppl_to_tensorboard ............... True +0: loss_on_targets_only ............................ False +0: loss_scale ...................................... 12.0 +0: loss_scale_window ............................... 1000 +0: lr .............................................. 0.0002 +0: lr_decay_iters .................................. None +0: lr_decay_samples ................................ 9703701 +0: lr_decay_style .................................. cosine +0: lr_decay_tokens ................................. None +0: lr_warmup_fraction .............................. None +0: lr_warmup_iters ................................. 0 +0: lr_warmup_samples ............................... 97037 +0: make_vocab_size_divisible_by .................... 128 +0: mask_prob ....................................... 0.15 +0: masked_softmax_fusion ........................... True +0: max_position_embeddings ......................... 2048 +0: mean_noise_span_length .......................... None +0: memory_centric_tiled_linear ..................... False +0: merge_file ...................................... gpt2/merges.txt +0: micro_batch_size ................................ 4 +0: min_loss_scale .................................. 1.0 +0: min_lr .......................................... 2e-05 +0: mmap_warmup ..................................... False +0: no_load_optim ................................... None +0: no_load_rng ..................................... None +0: no_save_optim ................................... None +0: no_save_rng ..................................... None +0: noise_density ................................... None +0: num_attention_heads ............................. 10 +0: num_channels .................................... 3 +0: num_classes ..................................... 1000 +0: num_layers ...................................... 10 +0: num_layers_per_virtual_pipeline_stage ........... None +0: num_workers ..................................... 2 +0: onnx_safe ....................................... None +0: openai_gelu ..................................... False +0: optimizer ....................................... adam +0: optimizer_fusion ................................ True +0: override_lr_scheduler ........................... False +0: pad_vocab_size_to ............................... None +0: params_dtype .................................... torch.bfloat16 +0: partition_activations ........................... False +0: patch_dim ....................................... 16 +0: pipeline_model_parallel_size .................... 1 +0: position_embedding_type ......................... PositionEmbeddingType.absolute +0: pp_partition_method ............................. None +0: profile_backward ................................ False +0: query_in_block_prob ............................. 0.1 +0: rampup_batch_size ............................... None +0: rank ............................................ 0 +0: remote_device ................................... none +0: reset_attention_mask ............................ False +0: reset_position_ids .............................. False +0: retriever_report_topk_accuracies ................ [] +0: retriever_score_scaling ......................... False +0: retriever_seq_length ............................ 256 +0: reweight_loss_based_on_position_frequency ....... False +0: sample_rate ..................................... 1.0 +0: save ............................................ checkpoints_83moscar +0: save_interval ................................... 1000 +0: scatter_gather_tensors_in_pipeline .............. True +0: scattered_embeddings ............................ False +0: seed ............................................ 1234 +0: seq_length ...................................... 2048 +0: sgd_momentum .................................... 0.9 +0: short_seq_prob .................................. 0.1 +0: skip_train_iteration_range ...................... None +0: split ........................................... 949,50,1 +0: split_transformers .............................. False +0: sync_tp_duplicated_parameters ................... False +0: synchronize_each_layer .......................... False +0: tensor_model_parallel_size ...................... 1 +0: tensorboard_dir ................................. tensorboard_83moscar +0: tensorboard_log_interval ........................ 1 +0: tensorboard_queue_size .......................... 5 +0: test_weighted_split_names ....................... None +0: test_weighted_split_paths ....................... None +0: test_weighted_split_paths_path .................. None +0: test_weighted_split_splits ...................... None +0: test_weighted_split_weights ..................... None +0: tile_factor ..................................... 1 +0: titles_data_path ................................ None +0: tokenizer_name_or_path .......................... None +0: tokenizer_type .................................. GPT2BPETokenizer +0: train_iters ..................................... None +0: train_samples ................................... 9703701 +0: train_tokens .................................... None +0: train_weighted_split_paths ...................... None +0: train_weighted_split_paths_path ................. None +0: universal_checkpoint ............................ False +0: use_bnb_optimizer ............................... False +0: use_checkpoint_lr_scheduler ..................... False +0: use_contiguous_buffers_in_ddp ................... True +0: use_cpu_initialization .......................... None +0: use_one_sent_docs ............................... False +0: use_pin_memory .................................. False +0: valid_num_workers ............................... 2 +0: valid_weighted_split_names ...................... None +0: valid_weighted_split_paths ...................... None +0: valid_weighted_split_paths_path ................. None +0: valid_weighted_split_splits ..................... None +0: valid_weighted_split_weights .................... None +0: virtual_pipeline_model_parallel_size ............ None +0: vocab_extra_ids ................................. 0 +0: vocab_file ...................................... gpt2/vocab.json +0: weight_decay .................................... 0.1 +0: world_size ...................................... 64 +0: zero_allgather_bucket_size ...................... 0.0 +0: zero_contigious_gradients ....................... False +0: zero_reduce_bucket_size ......................... 0.0 +0: zero_reduce_scatter ............................. False +0: zero_stage ...................................... 0 +0: -------------------- end of arguments --------------------- +0: setting number of micro-batches to constant 1 +0: > building GPT2BPETokenizer tokenizer ... +0: > padded vocab (size: 50257) with 47 dummy tokens (new size: 50304) +0: DeepSpeed general environment info: +0: torch install path ............... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch'] +0: torch version .................... 1.13.0+rocm5.2 +0: torch cuda version ............... None +0: torch hip version ................ 5.2.21151-afdc89f8 +0: nvcc version ..................... None +0: deepspeed install path ........... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed'] +0: deepspeed info ................... 0.7.5, unknown, unknown +0: deepspeed wheel compiled w. ...... torch 1.13, hip 5.1 +0: **** Git info for Megatron: git_hash=unknown git_branch=unknown **** +0: > initializing torch distributed ... +0: [2022-11-29 16:54:02,467] [INFO] [comm.py:633:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +7: > setting tensorboard ... +0: > initializing tensor model parallel with size 1 +0: > initializing pipeline model parallel with size 1 +0: > setting random seeds to 1234 ... +0: > initializing model parallel cuda seeds on global rank 0, model parallel rank 0, and data parallel rank 0 with model parallel seed: 3952 and data parallel seed: 1234 +0: > compiling dataset index builder ... +0: make: Entering directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' +0: make: Nothing to be done for 'default'. +0: make: Leaving directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' +0: >>> done with dataset index builder. Compilation time: 0.098 seconds +0: > compiling and loading fused kernels ... +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.cpp [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 87 +0: [1/1] c++ scaled_upper_triang_masked_softmax_hip.cuda.o scaled_upper_triang_masked_softmax_hip.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib -lamdhip64 -o scaled_upper_triang_masked_softmax_cuda.so +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.cpp [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 63 +0: ninja: no work to do. +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda_kernel.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_hip_kernel.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 67 +0: [1/1] c++ layer_norm_cuda.o layer_norm_hip_kernel.cuda.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib -lamdhip64 -o fused_mix_prec_layer_norm_cuda.so +0: >>> done with compiling and loading fused kernels. Compilation time: 15.712 seconds +0: time to initialize megatron (seconds): 29.742 +0: [after megatron is initialized] datetime: 2022-11-29 16:54:21 +0: building GPT model ... +0: [2022-11-29 16:54:21,794] [INFO] [utils.py:827:see_memory_usage] Before Building Model +0: [2022-11-29 16:54:21,794] [INFO] [utils.py:828:see_memory_usage] MA 0.0 GB Max_MA 0.0 GB CA 0.0 GB Max_CA 0 GB +0: [2022-11-29 16:54:21,794] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 46.1 GB, percent = 9.2% +0: SEED_LAYERS=False BASE_SEED=1234 SEED_FN=None +0: Using topology: {ProcessCoord(pipe=0, data=0, model=0): 0, ProcessCoord(pipe=0, data=1, model=0): 1, ProcessCoord(pipe=0, data=2, model=0): 2, ProcessCoord(pipe=0, data=3, model=0): 3, ProcessCoord(pipe=0, data=4, model=0): 4, ProcessCoord(pipe=0, data=5, model=0): 5, ProcessCoord(pipe=0, data=6, model=0): 6, ProcessCoord(pipe=0, data=7, model=0): 7, ProcessCoord(pipe=0, data=8, model=0): 8, ProcessCoord(pipe=0, data=9, model=0): 9, ProcessCoord(pipe=0, data=10, model=0): 10, ProcessCoord(pipe=0, data=11, model=0): 11, ProcessCoord(pipe=0, data=12, model=0): 12, ProcessCoord(pipe=0, data=13, model=0): 13, ProcessCoord(pipe=0, data=14, model=0): 14, ProcessCoord(pipe=0, data=15, model=0): 15, ProcessCoord(pipe=0, data=16, model=0): 16, ProcessCoord(pipe=0, data=17, model=0): 17, ProcessCoord(pipe=0, data=18, model=0): 18, ProcessCoord(pipe=0, data=19, model=0): 19, ProcessCoord(pipe=0, data=20, model=0): 20, ProcessCoord(pipe=0, data=21, model=0): 21, ProcessCoord(pipe=0, data=22, model=0): 22, ProcessCoord(pi +0: pe=0, data=23, model=0): 23, ProcessCoord(pipe=0, data=24, model=0): 24, ProcessCoord(pipe=0, data=25, model=0): 25, ProcessCoord(pipe=0, data=26, model=0): 26, ProcessCoord(pipe=0, data=27, model=0): 27, ProcessCoord(pipe=0, data=28, model=0): 28, ProcessCoord(pipe=0, data=29, model=0): 29, ProcessCoord(pipe=0, data=30, model=0): 30, ProcessCoord(pipe=0, data=31, model=0): 31, ProcessCoord(pipe=0, data=32, model=0): 32, ProcessCoord(pipe=0, data=33, model=0): 33, ProcessCoord(pipe=0, data=34, model=0): 34, ProcessCoord(pipe=0, data=35, model=0): 35, ProcessCoord(pipe=0, data=36, model=0): 36, ProcessCoord(pipe=0, data=37, model=0): 37, ProcessCoord(pipe=0, data=38, model=0): 38, ProcessCoord(pipe=0, data=39, model=0): 39, ProcessCoord(pipe=0, data=40, model=0): 40, ProcessCoord(pipe=0, data=41, model=0): 41, ProcessCoord(pipe=0, data=42, model=0): 42, ProcessCoord(pipe=0, data=43, model=0): 43, ProcessCoord(pipe=0, data=44, model=0): 44, ProcessCoord(pipe=0, data=45, model=0): 45, ProcessCoord(pipe=0, data=4 +0: 6, model=0): 46, ProcessCoord(pipe=0, data=47, model=0): 47, ProcessCoord(pipe=0, data=48, model=0): 48, ProcessCoord(pipe=0, data=49, model=0): 49, ProcessCoord(pipe=0, data=50, model=0): 50, ProcessCoord(pipe=0, data=51, model=0): 51, ProcessCoord(pipe=0, data=52, model=0): 52, ProcessCoord(pipe=0, data=53, model=0): 53, ProcessCoord(pipe=0, data=54, model=0): 54, ProcessCoord(pipe=0, data=55, model=0): 55, ProcessCoord(pipe=0, data=56, model=0): 56, ProcessCoord(pipe=0, data=57, model=0): 57, ProcessCoord(pipe=0, data=58, model=0): 58, ProcessCoord(pipe=0, data=59, model=0): 59, ProcessCoord(pipe=0, data=60, model=0): 60, ProcessCoord(pipe=0, data=61, model=0): 61, ProcessCoord(pipe=0, data=62, model=0): 62, ProcessCoord(pipe=0, data=63, model=0): 63} +0: [2022-11-29 16:54:23,787] [INFO] [module.py:366:_partition_layers] Partitioning pipeline stages with method type:transformer +0: stage=0 layers=17 +0: 0: _to_float16 +0: 1: EmbeddingPipe +0: 2: +0: 3: ParallelTransformerLayerPipe +0: 4: ParallelTransformerLayerPipe +0: 5: ParallelTransformerLayerPipe +0: 6: ParallelTransformerLayerPipe +0: 7: ParallelTransformerLayerPipe +0: 8: ParallelTransformerLayerPipe +0: 9: ParallelTransformerLayerPipe +0: 10: ParallelTransformerLayerPipe +0: 11: ParallelTransformerLayerPipe +0: 12: ParallelTransformerLayerPipe +0: 13: undo +0: 14: MixedFusedLayerNorm +0: 15: EmbeddingPipe +0: 16: float16_to_fp32 +0: loss: CrossEntropy +0: [2022-11-29 16:54:23,899] [INFO] [utils.py:827:see_memory_usage] After Building Model +0: [2022-11-29 16:54:23,900] [INFO] [utils.py:828:see_memory_usage] MA 0.16 GB Max_MA 0.16 GB CA 0.17 GB Max_CA 0 GB +0: [2022-11-29 16:54:23,900] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 46.12 GB, percent = 9.2% +0: setting training iterations to 37905 +0: > learning rate decay style: cosine +0: DeepSpeed is enabled. +0: [2022-11-29 16:54:23,901] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed info: version=0.7.5, git-hash=unknown, git-branch=unknown +0: [2022-11-29 16:54:35,719] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False +0: [2022-11-29 16:54:35,720] [INFO] [logging.py:68:log_dist] [Rank 0] Removing param_group that has no 'params' in the client Optimizer +0: [2022-11-29 16:54:35,720] [INFO] [logging.py:68:log_dist] [Rank 0] Using client Optimizer as basic optimizer +0: [2022-11-29 16:54:35,722] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Basic Optimizer = FusedAdam +0: [2022-11-29 16:54:35,722] [INFO] [logging.py:68:log_dist] [Rank 0] Creating BF16 optimizer +0: [2022-11-29 16:54:35,764] [INFO] [utils.py:827:see_memory_usage] begin bf16_optimizer +0: [2022-11-29 16:54:35,764] [INFO] [utils.py:828:see_memory_usage] MA 0.16 GB Max_MA 0.16 GB CA 0.17 GB Max_CA 0 GB +0: [2022-11-29 16:54:35,765] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 46.79 GB, percent = 9.3% +4: ninja: no work to do. +4: Time to load utils op: 0.12447190284729004 seconds +3: Time to load utils op: 0.10919594764709473 seconds +0: ninja: no work to do. +0: Time to load utils op: 0.12016606330871582 seconds +7: Time to load utils op: 0.11201262474060059 secondsTime to load utils op: 0.11204266548156738 seconds +7: Time to load utils op: 0.11229109764099121 seconds +7: Time to load utils op: 0.11295723915100098 seconds +7: Time to load utils op: 0.1120154857635498 seconds +7: +5: Time to load utils op: 0.11215615272521973 secondsTime to load utils op: 0.11216402053833008 seconds +5: +5: Time to load utils op: 0.1121373176574707 seconds +7: Time to load utils op: 0.11206698417663574 secondsTime to load utils op: 0.11296200752258301 secondsTime to load utils op: 0.11203122138977051 seconds +7: +7: +5: Time to load utils op: 0.11218404769897461 secondsTime to load utils op: 0.11214423179626465 seconds +5: +5: Time to load utils op: 0.11217713356018066 seconds +5: Time to load utils op: 0.11218690872192383 seconds +5: Time to load utils op: 0.11216282844543457 seconds +6: Time to load utils op: 0.11204767227172852 seconds +6: Time to load utils op: 0.1120905876159668 seconds +6: Time to load utils op: 0.11205816268920898 secondsTime to load utils op: 0.1120607852935791 secondsTime to load utils op: 0.11208629608154297 seconds +6: +6: +6: Time to load utils op: 0.11207914352416992 secondsTime to load utils op: 0.11206984519958496 seconds +6: +6: Time to load utils op: 0.11210322380065918 seconds +4: Time to load utils op: 0.0006349086761474609 seconds +3: Time to load utils op: 0.00045490264892578125 seconds +0: Time to load utils op: 0.0005576610565185547 seconds +6: Time to load utils op: 0.000997304916381836 seconds +5: Time to load utils op: 0.0009779930114746094 seconds +6: Time to load utils op: 0.0011260509490966797 seconds +5: Time to load utils op: 0.0011720657348632812 seconds +5: Time to load utils op: 0.0013415813446044922 seconds +5: Time to load utils op: 0.0013546943664550781 seconds +5: Time to load utils op: 0.0014033317565917969 seconds +6: Time to load utils op: 0.001390218734741211 seconds +6: Time to load utils op: 0.0014297962188720703 secondsTime to load utils op: 0.0014035701751708984 seconds +6: +5: Time to load utils op: 0.0013546943664550781 seconds +5: Time to load utils op: 0.0013699531555175781 seconds +5: Time to load utils op: 0.001399993896484375 seconds +6: Time to load utils op: 0.001447439193725586 seconds +6: Time to load utils op: 0.0014159679412841797 seconds +6: Time to load utils op: 0.0014209747314453125 seconds +0: Time to load utils op: 0.2028365135192871 secondsTime to load utils op: 0.20281362533569336 secondsTime to load utils op: 0.20279407501220703 secondsTime to load utils op: 0.20282483100891113 seconds +0: +0: +0: +0: Time to load utils op: 0.20270943641662598 seconds +0: Time to load utils op: 0.2027437686920166 seconds +7: Time to load utils op: 0.0008487701416015625 seconds +7: Time to load utils op: 0.0010082721710205078 seconds +7: Time to load utils op: 0.0009305477142333984 seconds +7: Time to load utils op: 0.0011947154998779297 seconds +7: Time to load utils op: 0.0012211799621582031 secondsTime to load utils op: 0.001195669174194336 seconds +7: +7: Time to load utils op: 0.0011987686157226562 seconds +7: Time to load utils op: 0.0012812614440917969 seconds +3: Time to load utils op: 0.20499920845031738 seconds +3: Time to load utils op: 0.20446014404296875 seconds +3: Time to load utils op: 0.20484566688537598 seconds +4: Time to load utils op: 0.20381689071655273 seconds +4: Time to load utils op: 0.20337581634521484 secondsTime to load utils op: 0.2044386863708496 secondsTime to load utils op: 0.20359086990356445 secondsTime to load utils op: 0.20340728759765625 seconds +4: +4: +4: Time to load utils op: 0.2045276165008545 secondsTime to load utils op: 0.20442748069763184 seconds +4: +4: +3: Time to load utils op: 0.2047593593597412 secondsTime to load utils op: 0.20518279075622559 seconds +3: +3: Time to load utils op: 0.20499157905578613 secondsTime to load utils op: 0.20517325401306152 seconds +3: +0: Time to load utils op: 0.303847074508667 seconds +1: Time to load utils op: 0.21218538284301758 secondsTime to load utils op: 0.21218419075012207 seconds +1: +1: Time to load utils op: 0.2122507095336914 seconds +1: Time to load utils op: 0.21222710609436035 secondsTime to load utils op: 0.21222901344299316 seconds +1: +1: Time to load utils op: 0.21225190162658691 seconds +1: Time to load utils op: 0.21224522590637207 seconds +1: Time to load utils op: 0.21227169036865234 seconds +2: Time to load utils op: 0.21222925186157227 seconds +2: Time to load utils op: 0.21227455139160156 seconds +2: Time to load utils op: 0.2122664451599121 secondsTime to load utils op: 0.2122640609741211 seconds +2: +2: Time to load utils op: 0.21227049827575684 seconds +2: Time to load utils op: 0.21228694915771484 seconds +2: Time to load utils op: 0.2123262882232666 seconds +2: Time to load utils op: 0.21232819557189941 seconds +0: Time to load utils op: 0.0004353523254394531 seconds +0: Time to load utils op: 0.0004057884216308594 seconds +0: Time to load utils op: 0.0003902912139892578 seconds +0: Time to load utils op: 0.0003826618194580078 seconds +0: Time to load utils op: 0.00039005279541015625 seconds +0: Time to load utils op: 0.00038933753967285156 seconds +3: Time to load utils op: 0.00033164024353027344 seconds +3: Time to load utils op: 0.00032711029052734375 seconds +3: Time to load utils op: 0.00032830238342285156 seconds +3: Time to load utils op: 0.00033545494079589844 seconds +3: Time to load utils op: 0.0003254413604736328 seconds +4: Time to load utils op: 0.00031685829162597656 seconds +3: Time to load utils op: 0.0003325939178466797 secondsTime to load utils op: 0.0003285408020019531 seconds +3: +4: Time to load utils op: 0.0003809928894042969 seconds +4: Time to load utils op: 0.00033354759216308594 seconds +4: Time to load utils op: 0.00036716461181640625 seconds +4: Time to load utils op: 0.0003600120544433594 seconds +4: Time to load utils op: 0.00036144256591796875 seconds +4: Time to load utils op: 0.00038433074951171875 seconds +0: [2022-11-29 16:54:36,118] [INFO] [utils.py:827:see_memory_usage] before initializing group 0 +0: [2022-11-29 16:54:36,119] [INFO] [utils.py:828:see_memory_usage] MA 0.16 GB Max_MA 0.16 GB CA 0.17 GB Max_CA 0 GB +0: [2022-11-29 16:54:36,119] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 46.9 GB, percent = 9.3% +1: Time to load utils op: 0.0006353855133056641 seconds +2: Time to load utils op: 0.0009009838104248047 seconds +2: Time to load utils op: 0.0008242130279541016 seconds +1: Time to load utils op: 0.0010285377502441406 seconds +1: Time to load utils op: 0.001018524169921875 seconds +1: Time to load utils op: 0.0010061264038085938 seconds +2: Time to load utils op: 0.0011816024780273438 seconds +1: Time to load utils op: 0.0011649131774902344 seconds +1: Time to load utils op: 0.0011928081512451172 secondsTime to load utils op: 0.0011453628540039062 seconds +1: +1: Time to load utils op: 0.0011873245239257812 seconds +2: Time to load utils op: 0.0012767314910888672 seconds +2: Time to load utils op: 0.0012700557708740234 seconds +2: Time to load utils op: 0.0012278556823730469 secondsTime to load utils op: 0.0012784004211425781 seconds +2: +2: Time to load utils op: 0.0013127326965332031 seconds +0: [2022-11-29 16:54:36,170] [INFO] [utils.py:827:see_memory_usage] after initializing group 0 +0: [2022-11-29 16:54:36,170] [INFO] [utils.py:828:see_memory_usage] MA 0.37 GB Max_MA 0.37 GB CA 0.48 GB Max_CA 0 GB +0: [2022-11-29 16:54:36,170] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 46.94 GB, percent = 9.3% +0: [2022-11-29 16:54:36,206] [INFO] [utils.py:827:see_memory_usage] before initializing group 1 +0: [2022-11-29 16:54:36,206] [INFO] [utils.py:828:see_memory_usage] MA 0.37 GB Max_MA 0.37 GB CA 0.48 GB Max_CA 0 GB +0: [2022-11-29 16:54:36,207] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 46.94 GB, percent = 9.3% +0: [2022-11-29 16:54:36,240] [INFO] [utils.py:827:see_memory_usage] after initializing group 1 +0: [2022-11-29 16:54:36,241] [INFO] [utils.py:828:see_memory_usage] MA 0.47 GB Max_MA 0.47 GB CA 0.58 GB Max_CA 1 GB +0: [2022-11-29 16:54:36,241] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 46.94 GB, percent = 9.3% +0: [2022-11-29 16:54:36,273] [INFO] [utils.py:827:see_memory_usage] before initializing group 2 +0: [2022-11-29 16:54:36,274] [INFO] [utils.py:828:see_memory_usage] MA 0.47 GB Max_MA 0.47 GB CA 0.58 GB Max_CA 1 GB +0: [2022-11-29 16:54:36,274] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 46.94 GB, percent = 9.3% +0: [2022-11-29 16:54:36,307] [INFO] [utils.py:827:see_memory_usage] after initializing group 2 +0: [2022-11-29 16:54:36,308] [INFO] [utils.py:828:see_memory_usage] MA 0.47 GB Max_MA 0.47 GB CA 0.58 GB Max_CA 1 GB +0: [2022-11-29 16:54:36,308] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 46.94 GB, percent = 9.3% +0: [2022-11-29 16:54:36,342] [INFO] [utils.py:827:see_memory_usage] before initialize_optimizer +0: [2022-11-29 16:54:36,342] [INFO] [utils.py:828:see_memory_usage] MA 0.47 GB Max_MA 0.47 GB CA 0.58 GB Max_CA 1 GB +0: [2022-11-29 16:54:36,343] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 46.93 GB, percent = 9.3% +0: [2022-11-29 16:54:36,380] [INFO] [utils.py:827:see_memory_usage] end initialize_optimizer +0: [2022-11-29 16:54:36,380] [INFO] [utils.py:828:see_memory_usage] MA 0.48 GB Max_MA 0.48 GB CA 0.58 GB Max_CA 1 GB +0: [2022-11-29 16:54:36,381] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 46.93 GB, percent = 9.3% +0: [2022-11-29 16:54:36,412] [INFO] [utils.py:827:see_memory_usage] end bf16_optimizer +0: [2022-11-29 16:54:36,413] [INFO] [utils.py:828:see_memory_usage] MA 0.48 GB Max_MA 0.48 GB CA 0.58 GB Max_CA 1 GB +0: [2022-11-29 16:54:36,413] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 46.93 GB, percent = 9.3% +0: [2022-11-29 16:54:36,413] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Final Optimizer = FusedAdam +0: [2022-11-29 16:54:36,413] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed using client LR scheduler +0: [2022-11-29 16:54:36,413] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed LR Scheduler = +0: [2022-11-29 16:54:36,413] [INFO] [logging.py:68:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0, 0.0, 0.0], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +0: [2022-11-29 16:54:36,414] [INFO] [config.py:1007:print] DeepSpeedEngine configuration: +0: [2022-11-29 16:54:36,414] [INFO] [config.py:1011:print] activation_checkpointing_config { +0: "partition_activations": false, +0: "contiguous_memory_optimization": false, +0: "cpu_checkpointing": false, +0: "number_checkpoints": null, +0: "synchronize_checkpoint_boundary": false, +0: "profile": false +0: } +0: [2022-11-29 16:54:36,414] [INFO] [config.py:1011:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True} +0: [2022-11-29 16:54:36,414] [INFO] [config.py:1011:print] amp_enabled .................. False +0: [2022-11-29 16:54:36,414] [INFO] [config.py:1011:print] amp_params ................... False +0: [2022-11-29 16:54:36,414] [INFO] [config.py:1011:print] autotuning_config ............ { +0: "enabled": false, +0: "start_step": null, +0: "end_step": null, +0: "metric_path": null, +0: "arg_mappings": null, +0: "metric": "throughput", +0: "model_info": null, +0: "results_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_results", +0: "exps_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_exps", +0: "overwrite": true, +0: "fast": true, +0: "start_profile_step": 3, +0: "end_profile_step": 5, +0: "tuner_type": "gridsearch", +0: "tuner_early_stopping": 5, +0: "tuner_num_trials": 50, +0: "model_info_path": null, +0: "mp_size": 1, +0: "max_train_batch_size": null, +0: "min_train_batch_size": 1, +0: "max_train_micro_batch_size_per_gpu": 1.024000e+03, +0: "min_train_micro_batch_size_per_gpu": 1, +0: "num_tuning_micro_batch_sizes": 3 +0: } +0: [2022-11-29 16:54:36,414] [INFO] [config.py:1011:print] bfloat16_enabled ............. True +0: [2022-11-29 16:54:36,414] [INFO] [config.py:1011:print] checkpoint_parallel_write_pipeline False +0: [2022-11-29 16:54:36,414] [INFO] [config.py:1011:print] checkpoint_tag_validation_enabled True +0: [2022-11-29 16:54:36,414] [INFO] [config.py:1011:print] checkpoint_tag_validation_fail False +0: [2022-11-29 16:54:36,414] [INFO] [config.py:1011:print] comms_config ................. +0: [2022-11-29 16:54:36,414] [INFO] [config.py:1011:print] communication_data_type ...... None +0: [2022-11-29 16:54:36,414] [INFO] [config.py:1011:print] compression_config ........... {'weight_quantization': {'shared_parameters': {'enabled': False, 'quantizer_kernel': False, 'schedule_offset': 0, 'quantize_groups': 1, 'quantize_verbose': False, 'quantization_type': 'symmetric', 'quantize_weight_in_forward': False, 'rounding': 'nearest', 'fp16_mixed_quantize': False, 'quantize_change_ratio': 0.001}, 'different_groups': {}}, 'activation_quantization': {'shared_parameters': {'enabled': False, 'quantization_type': 'symmetric', 'range_calibration': 'dynamic', 'schedule_offset': 1000}, 'different_groups': {}}, 'sparse_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'row_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'head_pruning': {'shared_parameters': {'enabled': False, 'method': 'topk', 'schedule_offset': 1000}, 'different_groups': {}}, 'channel_pruning': {'shared_pa +0: rameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'layer_reduction': {'enabled': False}} +0: [2022-11-29 16:54:36,414] [INFO] [config.py:1011:print] curriculum_enabled ........... False +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] curriculum_params ............ False +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] dataloader_drop_last ......... False +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] disable_allgather ............ False +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] dump_state ................... False +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] dynamic_loss_scale_args ...... None +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] eigenvalue_enabled ........... False +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] eigenvalue_gas_boundary_resolution 1 +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] eigenvalue_layer_name ........ bert.encoder.layer +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] eigenvalue_layer_num ......... 0 +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] eigenvalue_max_iter .......... 100 +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] eigenvalue_stability ......... 1e-06 +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] eigenvalue_tol ............... 0.01 +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] eigenvalue_verbose ........... False +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] elasticity_enabled ........... False +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] flops_profiler_config ........ { +0: "enabled": false, +0: "profile_step": 1, +0: "module_depth": -1, +0: "top_modules": 1, +0: "detailed": true, +0: "output_file": null +0: } +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] fp16_auto_cast ............... None +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] fp16_enabled ................. False +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] fp16_master_weights_and_gradients False +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] global_rank .................. 0 +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] gradient_accumulation_steps .. 1 +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] gradient_clipping ............ 1.0 +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] gradient_predivide_factor .... 1.0 +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] initial_dynamic_scale ........ 1 +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] load_universal_checkpoint .... False +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] loss_scale ................... 1.0 +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] memory_breakdown ............. False +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] monitor_config ............... +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] nebula_config ................ { +0: "enabled": false, +0: "persistent_storage_path": null, +0: "persistent_time_interval": 100, +0: "num_of_version_in_retention": 2, +0: "enable_nebula_load": true, +0: "load_path": null +0: } +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] optimizer_legacy_fusion ...... False +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] optimizer_name ............... None +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] optimizer_params ............. None +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0} +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] pld_enabled .................. False +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] pld_params ................... False +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] prescale_gradients ........... False +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] scheduler_name ............... None +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] scheduler_params ............. None +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] sparse_attention ............. None +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] sparse_gradients_enabled ..... False +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] steps_per_print .............. 2000 +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] train_batch_size ............. 256 +0: [2022-11-29 16:54:36,415] [INFO] [config.py:1011:print] train_micro_batch_size_per_gpu 4 +0: [2022-11-29 16:54:36,416] [INFO] [config.py:1011:print] use_node_local_storage ....... False +0: [2022-11-29 16:54:36,416] [INFO] [config.py:1011:print] wall_clock_breakdown ......... False +0: [2022-11-29 16:54:36,416] [INFO] [config.py:1011:print] world_size ................... 64 +0: [2022-11-29 16:54:36,416] [INFO] [config.py:1011:print] zero_allow_untested_optimizer False +0: [2022-11-29 16:54:36,416] [INFO] [config.py:1011:print] zero_config .................. stage=0 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=500000000 allgather_partitions=True allgather_bucket_size=500000000 overlap_comm=False load_from_fp32_weights=True elastic_checkpoint=False offload_param=None offload_optimizer=None sub_group_size=1000000000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=50000000 param_persistence_threshold=100000 model_persistence_threshold=9223372036854775807 max_live_parameters=1000000000 max_reuse_distance=1000000000 gather_16bit_weights_on_model_save=False stage3_gather_fp16_weights_on_model_save=False ignore_unused_parameters=True legacy_stage1=False round_robin_gradients=False +0: [2022-11-29 16:54:36,416] [INFO] [config.py:1011:print] zero_enabled ................. False +0: [2022-11-29 16:54:36,416] [INFO] [config.py:1011:print] zero_optimization_stage ...... 0 +0: [2022-11-29 16:54:36,416] [INFO] [config.py:996:print_user_config] json = { +0: "train_micro_batch_size_per_gpu": 4, +0: "train_batch_size": 256, +0: "gradient_clipping": 1.0, +0: "zero_optimization": { +0: "stage": 0 +0: }, +0: "bf16": { +0: "enabled": true +0: }, +0: "steps_per_print": 2.000000e+03, +0: "wall_clock_breakdown": false +0: } +0: Time to load utils op: 0.0004036426544189453 seconds +0: [2022-11-29 16:54:36,416] [INFO] [engine.py:87:__init__] CONFIG: micro_batches=1 micro_batch_size=4 +0: [2022-11-29 16:54:36,437] [INFO] [engine.py:145:__init__] RANK=0 STAGE=0 LAYERS=17 [0, 17) STAGE_PARAMS=82741760 (82.742M) TOTAL_PARAMS=82741760 (82.742M) UNIQUE_PARAMS=82741760 (82.742M) +0: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: WARNING: could not find the metadata file checkpoints_83moscar +0: will not load any checkpoints and will start from random +0: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:54:36,443] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-29 16:54:36,444] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83moscar/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: time (ms) | load-checkpoint: 5.95 +0: estimated model parameters: 0.08274176 +0: estimated model parameters without embeddings: 0.04923648 +0: [after model, optimizer, and learning rate scheduler are built] datetime: 2022-11-29 16:54:36 +0: > building train, validation, and test datasets ... +0: > datasets target sizes (minimum size): +0: train: 9703701 +0: validation: 9728 +0: test: 256 +0: > building train, validation, and test datasets for GPT ... +0: > building dataset index ... +0: reading sizes... +0: reading pointers... +0: reading document index... +0: creating numpy buffer of mmap... +0: creating memory view of numpy buffer... +0: > finished creating indexed dataset in 0.033558 seconds +0: number of documents: 431992659 +0: > dataset split: +0: train: +0: document indices in [0, 409961033) total of 409961033 documents +0: validation: +0: document indices in [409961033, 431560666) total of 21599633 documents +0: test: +0: document indices in [431560666, 431992659) total of 431993 documents +0: > WARNING: could not find index map files, building the indices on rank 0 ... +0: > only one epoch required, setting separate_last_epoch to False +0: > elasped time to build and save doc-idx mapping (seconds): 31.251442 +0: using: +0: number of documents: 409961033 +0: number of epochs: 1 +0: sequence length: 2048 +0: total number of samples: 262636457 +0: > elasped time to build and save sample-idx mapping (seconds): 7.729889 +0: > building shuffle index with split [0, 262636457) and [262636457, 262636457) ... +0: > elasped time to build and save shuffle-idx mapping (seconds): 15.923986 +0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_9703701ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_9703701ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_train_indexmap_9703701ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 1.029 seconds +0: total number of samples: 262636458 +0: total number of epochs: 1 +0: > WARNING: could not find index map files, building the indices on rank 0 ... +0: > only one epoch required, setting separate_last_epoch to False +0: > elasped time to build and save doc-idx mapping (seconds): 1.230231 +0: using: +0: number of documents: 21599633 +0: number of epochs: 1 +0: sequence length: 2048 +0: total number of samples: 13852049 +0: > elasped time to build and save sample-idx mapping (seconds): 0.404845 +0: > building shuffle index with split [0, 13852049) and [13852049, 13852049) ... +0: > elasped time to build and save shuffle-idx mapping (seconds): 0.502119 +0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_9728ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_9728ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_valid_indexmap_9728ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.050 seconds +0: total number of samples: 13852050 +0: total number of epochs: 1 +0: > loading doc-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_256ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_256ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/oscar_megatron/gpt2tok_oscar_text_document_test_indexmap_256ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.035 seconds +0: total number of samples: 276852 +0: total number of epochs: 1 +0: > finished creating GPT datasets ... +0: [after dataloaders are built] datetime: 2022-11-29 16:56:03 +0: done with setup ... +0: training ... +0: Number of parameters: [tensor rank - pipeline rank] w/ and w/o embeddings: +7: time (ms) | model-and-optimizer-setup: 14888.58 | train/valid/test-data-iterators-setup: 86593.54 +0: [000-000] 0.0827B / 0.0492B +0: [before the start of training step] datetime: 2022-11-29 16:56:03 +0: [2022-11-29 16:56:03,830] [INFO] [checkpointing.py:553:forward] Activation Checkpointing Information +0: [2022-11-29 16:56:03,830] [INFO] [checkpointing.py:554:forward] ----Partition Activations False, CPU CHECKPOINTING False +0: [2022-11-29 16:56:03,830] [INFO] [checkpointing.py:557:forward] ----contiguous Memory Checkpointing False with None total layers +0: [2022-11-29 16:56:03,830] [INFO] [checkpointing.py:560:forward] ----Synchronization False +0: [2022-11-29 16:56:03,830] [INFO] [checkpointing.py:561:forward] ----Profiling time in checkpointing False +0: [Rank 0] (after 10 iterations) memory (MB) | allocated: 2225.85888671875 | max allocated: 4715.3271484375 | reserved: 5998.0 | max reserved: 5998.0 +7: iteration 10/ 37905 | consumed samples: 2560 | consumed tokens: 5242880 | elapsed time per iteration (s): 1.34 | learning rate: 5.276E-06 | global batch size: 256 | lm loss: 1.084941E+01 | grad norm: 6.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 190.947 | TFLOPs: 4.86 | +7: iteration 20/ 37905 | consumed samples: 5120 | consumed tokens: 10485760 | elapsed time per iteration (s): 0.23 | learning rate: 1.055E-05 | global batch size: 256 | lm loss: 1.022425E+01 | grad norm: 2.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.612 | TFLOPs: 28.11 | +7: iteration 30/ 37905 | consumed samples: 7680 | consumed tokens: 15728640 | elapsed time per iteration (s): 0.23 | learning rate: 1.583E-05 | global batch size: 256 | lm loss: 9.905324E+00 | grad norm: 1.860 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.802 | TFLOPs: 27.81 | +7: iteration 40/ 37905 | consumed samples: 10240 | consumed tokens: 20971520 | elapsed time per iteration (s): 0.24 | learning rate: 2.111E-05 | global batch size: 256 | lm loss: 9.726402E+00 | grad norm: 1.792 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1071.876 | TFLOPs: 27.31 | +7: iteration 50/ 37905 | consumed samples: 12800 | consumed tokens: 26214400 | elapsed time per iteration (s): 0.23 | learning rate: 2.638E-05 | global batch size: 256 | lm loss: 9.481022E+00 | grad norm: 1.777 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.608 | TFLOPs: 28.29 | +7: iteration 60/ 37905 | consumed samples: 15360 | consumed tokens: 31457280 | elapsed time per iteration (s): 0.23 | learning rate: 3.166E-05 | global batch size: 256 | lm loss: 9.180159E+00 | grad norm: 1.539 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.840 | TFLOPs: 27.92 | +7: iteration 70/ 37905 | consumed samples: 17920 | consumed tokens: 36700160 | elapsed time per iteration (s): 0.23 | learning rate: 3.693E-05 | global batch size: 256 | lm loss: 8.884698E+00 | grad norm: 1.412 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.092 | TFLOPs: 28.36 | +7: iteration 80/ 37905 | consumed samples: 20480 | consumed tokens: 41943040 | elapsed time per iteration (s): 0.23 | learning rate: 4.221E-05 | global batch size: 256 | lm loss: 8.602710E+00 | grad norm: 1.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.005 | TFLOPs: 28.15 | +7: iteration 90/ 37905 | consumed samples: 23040 | consumed tokens: 47185920 | elapsed time per iteration (s): 0.24 | learning rate: 4.749E-05 | global batch size: 256 | lm loss: 8.287189E+00 | grad norm: 1.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1076.171 | TFLOPs: 27.42 | +7: iteration 100/ 37905 | consumed samples: 25600 | consumed tokens: 52428800 | elapsed time per iteration (s): 0.24 | learning rate: 5.276E-05 | global batch size: 256 | lm loss: 8.016016E+00 | grad norm: 1.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1081.651 | TFLOPs: 27.56 | +7: iteration 110/ 37905 | consumed samples: 28160 | consumed tokens: 57671680 | elapsed time per iteration (s): 0.23 | learning rate: 5.804E-05 | global batch size: 256 | lm loss: 7.749650E+00 | grad norm: 1.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.484 | TFLOPs: 27.98 | +7: iteration 120/ 37905 | consumed samples: 30720 | consumed tokens: 62914560 | elapsed time per iteration (s): 0.23 | learning rate: 6.332E-05 | global batch size: 256 | lm loss: 7.546487E+00 | grad norm: 0.990 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.327 | TFLOPs: 28.57 | +7: iteration 130/ 37905 | consumed samples: 33280 | consumed tokens: 68157440 | elapsed time per iteration (s): 0.23 | learning rate: 6.859E-05 | global batch size: 256 | lm loss: 7.341124E+00 | grad norm: 0.840 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.829 | TFLOPs: 28.12 | +7: iteration 140/ 37905 | consumed samples: 35840 | consumed tokens: 73400320 | elapsed time per iteration (s): 0.24 | learning rate: 7.387E-05 | global batch size: 256 | lm loss: 7.225888E+00 | grad norm: 0.555 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1054.371 | TFLOPs: 26.86 | +7: iteration 150/ 37905 | consumed samples: 38400 | consumed tokens: 78643200 | elapsed time per iteration (s): 0.23 | learning rate: 7.915E-05 | global batch size: 256 | lm loss: 7.094825E+00 | grad norm: 1.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.709 | TFLOPs: 27.79 | +7: iteration 160/ 37905 | consumed samples: 40960 | consumed tokens: 83886080 | elapsed time per iteration (s): 0.26 | learning rate: 8.442E-05 | global batch size: 256 | lm loss: 7.016409E+00 | grad norm: 0.886 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1003.691 | TFLOPs: 25.57 | +7: iteration 170/ 37905 | consumed samples: 43520 | consumed tokens: 89128960 | elapsed time per iteration (s): 0.25 | learning rate: 8.970E-05 | global batch size: 256 | lm loss: 6.931753E+00 | grad norm: 1.442 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1034.880 | TFLOPs: 26.36 | +7: iteration 180/ 37905 | consumed samples: 46080 | consumed tokens: 94371840 | elapsed time per iteration (s): 0.23 | learning rate: 9.497E-05 | global batch size: 256 | lm loss: 6.842635E+00 | grad norm: 0.680 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.465 | TFLOPs: 27.88 | +7: iteration 190/ 37905 | consumed samples: 48640 | consumed tokens: 99614720 | elapsed time per iteration (s): 0.23 | learning rate: 1.003E-04 | global batch size: 256 | lm loss: 6.769339E+00 | grad norm: 0.960 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.711 | TFLOPs: 27.94 | +7: iteration 200/ 37905 | consumed samples: 51200 | consumed tokens: 104857600 | elapsed time per iteration (s): 0.24 | learning rate: 1.055E-04 | global batch size: 256 | lm loss: 6.727221E+00 | grad norm: 1.077 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.972 | TFLOPs: 27.69 | +7: iteration 210/ 37905 | consumed samples: 53760 | consumed tokens: 110100480 | elapsed time per iteration (s): 0.24 | learning rate: 1.108E-04 | global batch size: 256 | lm loss: 6.638607E+00 | grad norm: 0.441 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.451 | TFLOPs: 27.73 | +7: iteration 220/ 37905 | consumed samples: 56320 | consumed tokens: 115343360 | elapsed time per iteration (s): 0.24 | learning rate: 1.161E-04 | global batch size: 256 | lm loss: 6.596915E+00 | grad norm: 0.703 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1048.685 | TFLOPs: 26.72 | +7: iteration 230/ 37905 | consumed samples: 58880 | consumed tokens: 120586240 | elapsed time per iteration (s): 0.24 | learning rate: 1.214E-04 | global batch size: 256 | lm loss: 6.512364E+00 | grad norm: 0.940 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1080.885 | TFLOPs: 27.54 | +7: iteration 240/ 37905 | consumed samples: 61440 | consumed tokens: 125829120 | elapsed time per iteration (s): 0.24 | learning rate: 1.266E-04 | global batch size: 256 | lm loss: 6.444125E+00 | grad norm: 0.637 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1082.621 | TFLOPs: 27.58 | +7: iteration 250/ 37905 | consumed samples: 64000 | consumed tokens: 131072000 | elapsed time per iteration (s): 0.25 | learning rate: 1.319E-04 | global batch size: 256 | lm loss: 6.433690E+00 | grad norm: 1.001 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1029.733 | TFLOPs: 26.23 | +7: iteration 260/ 37905 | consumed samples: 66560 | consumed tokens: 136314880 | elapsed time per iteration (s): 0.24 | learning rate: 1.372E-04 | global batch size: 256 | lm loss: 6.384482E+00 | grad norm: 0.826 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1075.513 | TFLOPs: 27.40 | +7: iteration 270/ 37905 | consumed samples: 69120 | consumed tokens: 141557760 | elapsed time per iteration (s): 0.23 | learning rate: 1.425E-04 | global batch size: 256 | lm loss: 6.343816E+00 | grad norm: 1.060 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.225 | TFLOPs: 28.10 | +7: iteration 280/ 37905 | consumed samples: 71680 | consumed tokens: 146800640 | elapsed time per iteration (s): 0.23 | learning rate: 1.477E-04 | global batch size: 256 | lm loss: 6.321928E+00 | grad norm: 0.776 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.249 | TFLOPs: 28.08 | +7: iteration 290/ 37905 | consumed samples: 74240 | consumed tokens: 152043520 | elapsed time per iteration (s): 0.23 | learning rate: 1.530E-04 | global batch size: 256 | lm loss: 6.274311E+00 | grad norm: 0.888 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.198 | TFLOPs: 28.00 | +7: iteration 300/ 37905 | consumed samples: 76800 | consumed tokens: 157286400 | elapsed time per iteration (s): 0.23 | learning rate: 1.583E-04 | global batch size: 256 | lm loss: 6.226305E+00 | grad norm: 0.736 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.553 | TFLOPs: 28.19 | +7: iteration 310/ 37905 | consumed samples: 79360 | consumed tokens: 162529280 | elapsed time per iteration (s): 0.25 | learning rate: 1.636E-04 | global batch size: 256 | lm loss: 6.186801E+00 | grad norm: 0.894 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1017.709 | TFLOPs: 25.93 | +7: iteration 320/ 37905 | consumed samples: 81920 | consumed tokens: 167772160 | elapsed time per iteration (s): 0.23 | learning rate: 1.688E-04 | global batch size: 256 | lm loss: 6.153384E+00 | grad norm: 0.815 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.585 | TFLOPs: 28.06 | +7: iteration 330/ 37905 | consumed samples: 84480 | consumed tokens: 173015040 | elapsed time per iteration (s): 0.24 | learning rate: 1.741E-04 | global batch size: 256 | lm loss: 6.125492E+00 | grad norm: 0.794 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.335 | TFLOPs: 27.67 | +7: iteration 340/ 37905 | consumed samples: 87040 | consumed tokens: 178257920 | elapsed time per iteration (s): 0.24 | learning rate: 1.794E-04 | global batch size: 256 | lm loss: 6.094569E+00 | grad norm: 0.860 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1066.337 | TFLOPs: 27.17 | +7: iteration 350/ 37905 | consumed samples: 89600 | consumed tokens: 183500800 | elapsed time per iteration (s): 0.24 | learning rate: 1.847E-04 | global batch size: 256 | lm loss: 6.045417E+00 | grad norm: 0.732 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.932 | TFLOPs: 27.69 | +7: iteration 360/ 37905 | consumed samples: 92160 | consumed tokens: 188743680 | elapsed time per iteration (s): 0.24 | learning rate: 1.899E-04 | global batch size: 256 | lm loss: 6.025502E+00 | grad norm: 1.089 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1077.534 | TFLOPs: 27.45 | +7: iteration 370/ 37905 | consumed samples: 94720 | consumed tokens: 193986560 | elapsed time per iteration (s): 0.24 | learning rate: 1.952E-04 | global batch size: 256 | lm loss: 6.005598E+00 | grad norm: 0.936 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1083.803 | TFLOPs: 27.61 | +7: iteration 380/ 37905 | consumed samples: 97280 | consumed tokens: 199229440 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.933751E+00 | grad norm: 0.967 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1063.934 | TFLOPs: 27.10 | +7: iteration 390/ 37905 | consumed samples: 99840 | consumed tokens: 204472320 | elapsed time per iteration (s): 0.25 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.939144E+00 | grad norm: 0.995 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1034.926 | TFLOPs: 26.36 | +7: iteration 400/ 37905 | consumed samples: 102400 | consumed tokens: 209715200 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.885649E+00 | grad norm: 0.931 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.608 | TFLOPs: 27.99 | +7: iteration 410/ 37905 | consumed samples: 104960 | consumed tokens: 214958080 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.847894E+00 | grad norm: 0.917 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.482 | TFLOPs: 27.96 | +7: iteration 420/ 37905 | consumed samples: 107520 | consumed tokens: 220200960 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.842724E+00 | grad norm: 0.851 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1069.328 | TFLOPs: 27.24 | +7: iteration 430/ 37905 | consumed samples: 110080 | consumed tokens: 225443840 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.787041E+00 | grad norm: 1.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.197 | TFLOPs: 26.93 | +7: iteration 440/ 37905 | consumed samples: 112640 | consumed tokens: 230686720 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.769608E+00 | grad norm: 0.991 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1084.024 | TFLOPs: 27.62 | +7: iteration 450/ 37905 | consumed samples: 115200 | consumed tokens: 235929600 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.741891E+00 | grad norm: 0.928 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.728 | TFLOPs: 27.48 | +7: iteration 460/ 37905 | consumed samples: 117760 | consumed tokens: 241172480 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.734983E+00 | grad norm: 0.848 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.361 | TFLOPs: 27.27 | +7: iteration 470/ 37905 | consumed samples: 120320 | consumed tokens: 246415360 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.685920E+00 | grad norm: 0.919 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.045 | TFLOPs: 28.35 | +7: iteration 480/ 37905 | consumed samples: 122880 | consumed tokens: 251658240 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.695139E+00 | grad norm: 1.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1068.069 | TFLOPs: 27.21 | +7: iteration 490/ 37905 | consumed samples: 125440 | consumed tokens: 256901120 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.665565E+00 | grad norm: 0.997 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.970 | TFLOPs: 28.35 | +7: iteration 500/ 37905 | consumed samples: 128000 | consumed tokens: 262144000 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.644341E+00 | grad norm: 0.880 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1079.490 | TFLOPs: 27.50 | +7: iteration 510/ 37905 | consumed samples: 130560 | consumed tokens: 267386880 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.619301E+00 | grad norm: 0.832 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1060.040 | TFLOPs: 27.00 | +7: iteration 520/ 37905 | consumed samples: 133120 | consumed tokens: 272629760 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.584609E+00 | grad norm: 1.008 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.027 | TFLOPs: 27.97 | +7: iteration 530/ 37905 | consumed samples: 135680 | consumed tokens: 277872640 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.560263E+00 | grad norm: 1.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1083.783 | TFLOPs: 27.61 | +7: iteration 540/ 37905 | consumed samples: 138240 | consumed tokens: 283115520 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.559742E+00 | grad norm: 0.962 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1083.857 | TFLOPs: 27.61 | +7: iteration 550/ 37905 | consumed samples: 140800 | consumed tokens: 288358400 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.531761E+00 | grad norm: 0.859 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.549 | TFLOPs: 27.99 | +7: iteration 560/ 37905 | consumed samples: 143360 | consumed tokens: 293601280 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.508029E+00 | grad norm: 0.934 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1075.432 | TFLOPs: 27.40 | +7: iteration 570/ 37905 | consumed samples: 145920 | consumed tokens: 298844160 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.475528E+00 | grad norm: 1.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.387 | TFLOPs: 27.78 | +7: iteration 580/ 37905 | consumed samples: 148480 | consumed tokens: 304087040 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.458810E+00 | grad norm: 0.785 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.115 | TFLOPs: 27.90 | +7: iteration 590/ 37905 | consumed samples: 151040 | consumed tokens: 309329920 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.448166E+00 | grad norm: 0.958 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.852 | TFLOPs: 27.76 | +7: iteration 600/ 37905 | consumed samples: 153600 | consumed tokens: 314572800 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.414758E+00 | grad norm: 0.886 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1073.667 | TFLOPs: 27.35 | +7: iteration 610/ 37905 | consumed samples: 156160 | consumed tokens: 319815680 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.389635E+00 | grad norm: 0.987 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.407 | TFLOPs: 26.94 | +7: iteration 620/ 37905 | consumed samples: 158720 | consumed tokens: 325058560 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.377455E+00 | grad norm: 1.042 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.796 | TFLOPs: 27.69 | +7: iteration 630/ 37905 | consumed samples: 161280 | consumed tokens: 330301440 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.369039E+00 | grad norm: 1.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1074.903 | TFLOPs: 27.38 | +7: iteration 640/ 37905 | consumed samples: 163840 | consumed tokens: 335544320 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.353208E+00 | grad norm: 1.096 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1081.092 | TFLOPs: 27.54 | +7: iteration 650/ 37905 | consumed samples: 166400 | consumed tokens: 340787200 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.311553E+00 | grad norm: 0.991 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.049 | TFLOPs: 27.69 | +7: iteration 660/ 37905 | consumed samples: 168960 | consumed tokens: 346030080 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.316884E+00 | grad norm: 1.029 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1084.548 | TFLOPs: 27.63 | +7: iteration 670/ 37905 | consumed samples: 171520 | consumed tokens: 351272960 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.268806E+00 | grad norm: 0.717 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.657 | TFLOPs: 27.94 | +7: iteration 680/ 37905 | consumed samples: 174080 | consumed tokens: 356515840 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.250203E+00 | grad norm: 1.053 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.824 | TFLOPs: 27.84 | +7: iteration 690/ 37905 | consumed samples: 176640 | consumed tokens: 361758720 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.255927E+00 | grad norm: 0.952 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.240 | TFLOPs: 27.88 | +7: iteration 700/ 37905 | consumed samples: 179200 | consumed tokens: 367001600 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.237846E+00 | grad norm: 1.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1082.706 | TFLOPs: 27.58 | +7: iteration 710/ 37905 | consumed samples: 181760 | consumed tokens: 372244480 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.208771E+00 | grad norm: 1.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.117 | TFLOPs: 27.75 | +7: iteration 720/ 37905 | consumed samples: 184320 | consumed tokens: 377487360 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.205368E+00 | grad norm: 0.681 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.702 | TFLOPs: 28.07 | +7: iteration 730/ 37905 | consumed samples: 186880 | consumed tokens: 382730240 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.167897E+00 | grad norm: 0.743 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.476 | TFLOPs: 27.73 | +7: iteration 740/ 37905 | consumed samples: 189440 | consumed tokens: 387973120 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.156529E+00 | grad norm: 1.087 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.372 | TFLOPs: 28.29 | +7: iteration 750/ 37905 | consumed samples: 192000 | consumed tokens: 393216000 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.125928E+00 | grad norm: 0.934 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.195 | TFLOPs: 27.65 | +7: iteration 760/ 37905 | consumed samples: 194560 | consumed tokens: 398458880 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.114888E+00 | grad norm: 0.927 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.203 | TFLOPs: 27.26 | +7: iteration 770/ 37905 | consumed samples: 197120 | consumed tokens: 403701760 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.095713E+00 | grad norm: 0.850 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.740 | TFLOPs: 27.86 | +7: iteration 780/ 37905 | consumed samples: 199680 | consumed tokens: 408944640 | elapsed time per iteration (s): 0.23 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.094014E+00 | grad norm: 0.925 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.660 | TFLOPs: 28.19 | +7: iteration 790/ 37905 | consumed samples: 202240 | consumed tokens: 414187520 | elapsed time per iteration (s): 0.24 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.107090E+00 | grad norm: 1.080 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1079.571 | TFLOPs: 27.50 | +7: iteration 800/ 37905 | consumed samples: 204800 | consumed tokens: 419430400 | elapsed time per iteration (s): 0.23 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.117308E+00 | grad norm: 0.958 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.852 | TFLOPs: 27.76 | +7: iteration 810/ 37905 | consumed samples: 207360 | consumed tokens: 424673280 | elapsed time per iteration (s): 0.23 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.094771E+00 | grad norm: 0.988 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.718 | TFLOPs: 27.99 | +7: iteration 820/ 37905 | consumed samples: 209920 | consumed tokens: 429916160 | elapsed time per iteration (s): 0.23 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.040110E+00 | grad norm: 0.834 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.067 | TFLOPs: 27.90 | +7: iteration 830/ 37905 | consumed samples: 212480 | consumed tokens: 435159040 | elapsed time per iteration (s): 0.24 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.057529E+00 | grad norm: 0.819 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.172 | TFLOPs: 27.64 | +7: iteration 840/ 37905 | consumed samples: 215040 | consumed tokens: 440401920 | elapsed time per iteration (s): 0.24 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.024625E+00 | grad norm: 0.603 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1083.160 | TFLOPs: 27.59 | +7: iteration 850/ 37905 | consumed samples: 217600 | consumed tokens: 445644800 | elapsed time per iteration (s): 0.23 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.968198E+00 | grad norm: 0.745 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.117 | TFLOPs: 27.90 | +7: iteration 860/ 37905 | consumed samples: 220160 | consumed tokens: 450887680 | elapsed time per iteration (s): 0.24 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.952565E+00 | grad norm: 0.804 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.611 | TFLOPs: 27.66 | +7: iteration 870/ 37905 | consumed samples: 222720 | consumed tokens: 456130560 | elapsed time per iteration (s): 0.24 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.938953E+00 | grad norm: 0.834 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1065.492 | TFLOPs: 27.14 | +7: iteration 880/ 37905 | consumed samples: 225280 | consumed tokens: 461373440 | elapsed time per iteration (s): 0.23 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.893451E+00 | grad norm: 1.073 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.667 | TFLOPs: 28.12 | +7: iteration 890/ 37905 | consumed samples: 227840 | consumed tokens: 466616320 | elapsed time per iteration (s): 0.24 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.891588E+00 | grad norm: 0.787 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.208 | TFLOPs: 27.47 | +7: iteration 900/ 37905 | consumed samples: 230400 | consumed tokens: 471859200 | elapsed time per iteration (s): 0.24 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.901497E+00 | grad norm: 0.893 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1082.300 | TFLOPs: 27.57 | +7: iteration 910/ 37905 | consumed samples: 232960 | consumed tokens: 477102080 | elapsed time per iteration (s): 0.24 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.894187E+00 | grad norm: 1.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1055.257 | TFLOPs: 26.88 | +7: iteration 920/ 37905 | consumed samples: 235520 | consumed tokens: 482344960 | elapsed time per iteration (s): 0.24 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.823556E+00 | grad norm: 1.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1075.265 | TFLOPs: 27.39 | +7: iteration 930/ 37905 | consumed samples: 238080 | consumed tokens: 487587840 | elapsed time per iteration (s): 0.24 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.805666E+00 | grad norm: 0.953 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1056.584 | TFLOPs: 26.92 | +7: iteration 940/ 37905 | consumed samples: 240640 | consumed tokens: 492830720 | elapsed time per iteration (s): 0.25 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.767541E+00 | grad norm: 1.036 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1030.540 | TFLOPs: 26.25 | +7: iteration 950/ 37905 | consumed samples: 243200 | consumed tokens: 498073600 | elapsed time per iteration (s): 0.25 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.761861E+00 | grad norm: 0.868 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1015.504 | TFLOPs: 25.87 | +7: iteration 960/ 37905 | consumed samples: 245760 | consumed tokens: 503316480 | elapsed time per iteration (s): 0.24 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.736498E+00 | grad norm: 0.821 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1084.596 | TFLOPs: 27.63 | +7: iteration 970/ 37905 | consumed samples: 248320 | consumed tokens: 508559360 | elapsed time per iteration (s): 0.24 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.735132E+00 | grad norm: 1.034 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1066.439 | TFLOPs: 27.17 | +7: iteration 980/ 37905 | consumed samples: 250880 | consumed tokens: 513802240 | elapsed time per iteration (s): 0.23 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.713985E+00 | grad norm: 1.031 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.585 | TFLOPs: 27.96 | +7: iteration 990/ 37905 | consumed samples: 253440 | consumed tokens: 519045120 | elapsed time per iteration (s): 0.24 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.677246E+00 | grad norm: 0.977 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.113 | TFLOPs: 27.69 | +7: iteration 1000/ 37905 | consumed samples: 256000 | consumed tokens: 524288000 | elapsed time per iteration (s): 0.24 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.705824E+00 | grad norm: 0.951 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1060.651 | TFLOPs: 27.02 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 1000 | lm loss value: 4.416901E+00 | lm loss PPL: 8.283918E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 1000 to checkpoints_83moscar +0: [2022-11-29 17:00:11,455] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step1000 is begin to save! +0: [2022-11-29 17:00:11,481] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:00:11,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:00:11,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:00:11,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:00:11,571] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:00:11,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:00:11,582] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:00:11,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:00:11,594] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:00:11,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:00:11,605] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:00:11,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:00:11,616] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:00:11,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:00:11,627] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:00:11,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:00:11,639] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:00:11,650] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:00:11,650] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:00:11,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:00:11,662] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:00:11,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:00:11,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:00:11,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:00:11,675] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step1000/mp_rank_00_model_states.pt +0: [2022-11-29 17:00:11,675] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:00:11,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:00:11,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:00:11,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:00:11,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:00:11,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:00:11,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:00:11,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:00:11,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:00:11,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:00:11,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:00:11,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:00:11,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:00:11,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:00:11,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:00:11,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:00:11,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:00:11,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:00:11,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:00:11,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:00:11,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:00:11,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:00:11,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:00:11,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:00:11,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:00:11,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:00:11,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:00:11,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:00:11,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:00:11,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:00:11,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:00:11,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:00:11,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:00:11,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:00:11,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:00:11,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:00:11,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:00:11,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:00:11,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:00:11,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:00:11,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:00:11,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:00:11,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:00:11,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:00:11,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:00:11,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:00:11,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:00:11,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-29 17:00:11,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-29 17:00:11,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:00:11,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:00:11,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:00:11,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:00:11,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:00:11,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:00:11,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:00:11,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:00:11,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +2: [2022-11-29 17:00:11,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:00:11,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:00:11,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:00:11,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:00:11,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:00:11,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +2: [2022-11-29 17:00:11,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +7: [2022-11-29 17:00:11,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:00:11,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:00:11,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:00:11,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:00:11,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:00:11,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:00:11,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +4: [2022-11-29 17:00:11,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +6: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:00:11,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +6: [2022-11-29 17:00:11,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +7: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:00:11,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:00:11,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +4: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:00:11,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:00:11,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:00:11,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +7: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:00:11,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:00:11,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +4: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:00:11,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +7: [2022-11-29 17:00:11,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +4: [2022-11-29 17:00:11,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +6: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:00:11,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:00:11,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:00:11,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:00:11,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:00:11,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +6: [2022-11-29 17:00:11,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +2: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:00:11,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:00:11,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:00:11,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:00:11,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:00:11,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:00:11,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:00:11,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:00:11,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-29 17:00:11,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:00:11,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:00:11,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:00:11,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:00:11,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:00:11,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:00:11,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-29 17:00:11,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:00:11,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:00:11,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:00:11,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:00:11,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:00:11,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:00:11,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:00:11,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:00:11,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:00:11,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:00:11,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:00:11,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:00:11,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:00:11,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +3: [2022-11-29 17:00:11,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:00:11,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:00:11,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:00:11,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:00:11,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:00:11,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +1: [2022-11-29 17:00:11,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:00:11,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:00:11,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:00:11,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:00:11,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:00:11,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:00:11,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:00:11,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:00:11,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:00:11,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:00:11,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:00:11,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:00:11,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:00:11,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-29 17:00:11,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:00:11,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:00:11,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:00:11,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:00:11,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:00:11,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:00:11,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:00:11,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:00:11,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:00:11,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:00:11,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:00:11,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:00:11,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-29 17:00:11,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:00:11,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:00:11,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: successfully saved checkpoint at iteration 1000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 310.45 +7: iteration 1010/ 37905 | consumed samples: 258560 | consumed tokens: 529530880 | elapsed time per iteration (s): 0.28 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.653694E+00 | grad norm: 0.724 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 912.515 | TFLOPs: 23.25 | +7: iteration 1020/ 37905 | consumed samples: 261120 | consumed tokens: 534773760 | elapsed time per iteration (s): 0.24 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.653625E+00 | grad norm: 1.054 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.086 | TFLOPs: 27.67 | +7: iteration 1030/ 37905 | consumed samples: 263680 | consumed tokens: 540016640 | elapsed time per iteration (s): 0.24 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.631158E+00 | grad norm: 0.990 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1067.556 | TFLOPs: 27.20 | +7: iteration 1040/ 37905 | consumed samples: 266240 | consumed tokens: 545259520 | elapsed time per iteration (s): 0.24 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.597848E+00 | grad norm: 0.999 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.016 | TFLOPs: 27.64 | +7: iteration 1050/ 37905 | consumed samples: 268800 | consumed tokens: 550502400 | elapsed time per iteration (s): 0.23 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.607329E+00 | grad norm: 0.836 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.153 | TFLOPs: 28.26 | +7: iteration 1060/ 37905 | consumed samples: 271360 | consumed tokens: 555745280 | elapsed time per iteration (s): 0.23 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.601201E+00 | grad norm: 1.008 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.527 | TFLOPs: 27.76 | +7: iteration 1070/ 37905 | consumed samples: 273920 | consumed tokens: 560988160 | elapsed time per iteration (s): 0.24 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.571163E+00 | grad norm: 0.877 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.515 | TFLOPs: 27.27 | +7: iteration 1080/ 37905 | consumed samples: 276480 | consumed tokens: 566231040 | elapsed time per iteration (s): 0.24 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.558318E+00 | grad norm: 0.845 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1080.405 | TFLOPs: 27.52 | +7: iteration 1090/ 37905 | consumed samples: 279040 | consumed tokens: 571473920 | elapsed time per iteration (s): 0.24 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.567658E+00 | grad norm: 0.870 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.121 | TFLOPs: 27.67 | +7: iteration 1100/ 37905 | consumed samples: 281600 | consumed tokens: 576716800 | elapsed time per iteration (s): 0.23 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.530540E+00 | grad norm: 0.737 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.246 | TFLOPs: 27.98 | +7: iteration 1110/ 37905 | consumed samples: 284160 | consumed tokens: 581959680 | elapsed time per iteration (s): 0.24 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.496237E+00 | grad norm: 0.935 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1073.008 | TFLOPs: 27.34 | +7: iteration 1120/ 37905 | consumed samples: 286720 | consumed tokens: 587202560 | elapsed time per iteration (s): 0.23 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.512266E+00 | grad norm: 0.888 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.495 | TFLOPs: 28.24 | +7: iteration 1130/ 37905 | consumed samples: 289280 | consumed tokens: 592445440 | elapsed time per iteration (s): 0.24 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.493412E+00 | grad norm: 0.786 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1080.950 | TFLOPs: 27.54 | +7: iteration 1140/ 37905 | consumed samples: 291840 | consumed tokens: 597688320 | elapsed time per iteration (s): 0.24 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.507822E+00 | grad norm: 0.947 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1076.724 | TFLOPs: 27.43 | +7: iteration 1150/ 37905 | consumed samples: 294400 | consumed tokens: 602931200 | elapsed time per iteration (s): 0.24 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.474117E+00 | grad norm: 0.778 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1071.709 | TFLOPs: 27.30 | +7: iteration 1160/ 37905 | consumed samples: 296960 | consumed tokens: 608174080 | elapsed time per iteration (s): 0.24 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.493776E+00 | grad norm: 0.972 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.966 | TFLOPs: 27.72 | +7: iteration 1170/ 37905 | consumed samples: 299520 | consumed tokens: 613416960 | elapsed time per iteration (s): 0.24 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.476886E+00 | grad norm: 0.841 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1084.032 | TFLOPs: 27.62 | +7: iteration 1180/ 37905 | consumed samples: 302080 | consumed tokens: 618659840 | elapsed time per iteration (s): 0.23 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.451345E+00 | grad norm: 0.807 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.211 | TFLOPs: 27.80 | +7: iteration 1190/ 37905 | consumed samples: 304640 | consumed tokens: 623902720 | elapsed time per iteration (s): 0.23 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.494650E+00 | grad norm: 0.724 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.144 | TFLOPs: 28.15 | +7: iteration 1200/ 37905 | consumed samples: 307200 | consumed tokens: 629145600 | elapsed time per iteration (s): 0.23 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.443582E+00 | grad norm: 0.858 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.633 | TFLOPs: 28.32 | +7: iteration 1210/ 37905 | consumed samples: 309760 | consumed tokens: 634388480 | elapsed time per iteration (s): 0.23 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.437888E+00 | grad norm: 0.975 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.249 | TFLOPs: 28.26 | +7: iteration 1220/ 37905 | consumed samples: 312320 | consumed tokens: 639631360 | elapsed time per iteration (s): 0.23 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.429245E+00 | grad norm: 0.784 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.660 | TFLOPs: 27.76 | +7: iteration 1230/ 37905 | consumed samples: 314880 | consumed tokens: 644874240 | elapsed time per iteration (s): 0.23 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.418037E+00 | grad norm: 0.907 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.464 | TFLOPs: 28.11 | +7: iteration 1240/ 37905 | consumed samples: 317440 | consumed tokens: 650117120 | elapsed time per iteration (s): 0.23 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.445233E+00 | grad norm: 0.784 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.680 | TFLOPs: 28.50 | +7: iteration 1250/ 37905 | consumed samples: 320000 | consumed tokens: 655360000 | elapsed time per iteration (s): 0.23 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.412486E+00 | grad norm: 0.878 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.112 | TFLOPs: 28.00 | +7: iteration 1260/ 37905 | consumed samples: 322560 | consumed tokens: 660602880 | elapsed time per iteration (s): 0.23 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.413123E+00 | grad norm: 1.006 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.034 | TFLOPs: 28.48 | +7: iteration 1270/ 37905 | consumed samples: 325120 | consumed tokens: 665845760 | elapsed time per iteration (s): 0.23 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.401833E+00 | grad norm: 0.931 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.995 | TFLOPs: 28.23 | +7: iteration 1280/ 37905 | consumed samples: 327680 | consumed tokens: 671088640 | elapsed time per iteration (s): 0.23 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.392268E+00 | grad norm: 0.867 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.737 | TFLOPs: 27.97 | +7: iteration 1290/ 37905 | consumed samples: 330240 | consumed tokens: 676331520 | elapsed time per iteration (s): 0.24 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.369967E+00 | grad norm: 1.099 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1072.013 | TFLOPs: 27.31 | +7: iteration 1300/ 37905 | consumed samples: 332800 | consumed tokens: 681574400 | elapsed time per iteration (s): 0.23 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.390608E+00 | grad norm: 0.794 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.233 | TFLOPs: 28.18 | +7: iteration 1310/ 37905 | consumed samples: 335360 | consumed tokens: 686817280 | elapsed time per iteration (s): 0.23 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.372837E+00 | grad norm: 0.701 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.557 | TFLOPs: 28.57 | +7: iteration 1320/ 37905 | consumed samples: 337920 | consumed tokens: 692060160 | elapsed time per iteration (s): 0.23 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.359188E+00 | grad norm: 0.828 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.177 | TFLOPs: 28.33 | +7: iteration 1330/ 37905 | consumed samples: 340480 | consumed tokens: 697303040 | elapsed time per iteration (s): 0.23 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.344128E+00 | grad norm: 0.845 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.281 | TFLOPs: 28.26 | +7: iteration 1340/ 37905 | consumed samples: 343040 | consumed tokens: 702545920 | elapsed time per iteration (s): 0.24 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.333010E+00 | grad norm: 0.985 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1045.943 | TFLOPs: 26.65 | +7: iteration 1350/ 37905 | consumed samples: 345600 | consumed tokens: 707788800 | elapsed time per iteration (s): 0.24 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.335521E+00 | grad norm: 0.715 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1075.293 | TFLOPs: 27.39 | +7: iteration 1360/ 37905 | consumed samples: 348160 | consumed tokens: 713031680 | elapsed time per iteration (s): 0.24 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.328906E+00 | grad norm: 1.003 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.059 | TFLOPs: 27.67 | +7: iteration 1370/ 37905 | consumed samples: 350720 | consumed tokens: 718274560 | elapsed time per iteration (s): 0.24 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.312531E+00 | grad norm: 0.736 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1048.744 | TFLOPs: 26.72 | +7: iteration 1380/ 37905 | consumed samples: 353280 | consumed tokens: 723517440 | elapsed time per iteration (s): 0.23 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.304158E+00 | grad norm: 0.829 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.728 | TFLOPs: 28.12 | +7: iteration 1390/ 37905 | consumed samples: 355840 | consumed tokens: 728760320 | elapsed time per iteration (s): 0.23 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.296597E+00 | grad norm: 0.922 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.513 | TFLOPs: 28.01 | +7: iteration 1400/ 37905 | consumed samples: 358400 | consumed tokens: 734003200 | elapsed time per iteration (s): 0.23 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.319374E+00 | grad norm: 0.875 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.893 | TFLOPs: 28.55 | +7: iteration 1410/ 37905 | consumed samples: 360960 | consumed tokens: 739246080 | elapsed time per iteration (s): 0.23 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.298509E+00 | grad norm: 0.676 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.925 | TFLOPs: 28.66 | +7: iteration 1420/ 37905 | consumed samples: 363520 | consumed tokens: 744488960 | elapsed time per iteration (s): 0.24 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.270473E+00 | grad norm: 0.695 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1071.677 | TFLOPs: 27.30 | +7: iteration 1430/ 37905 | consumed samples: 366080 | consumed tokens: 749731840 | elapsed time per iteration (s): 0.24 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.311574E+00 | grad norm: 0.975 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1046.673 | TFLOPs: 26.66 | +7: iteration 1440/ 37905 | consumed samples: 368640 | consumed tokens: 754974720 | elapsed time per iteration (s): 0.23 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.270663E+00 | grad norm: 0.874 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.056 | TFLOPs: 28.28 | +7: iteration 1450/ 37905 | consumed samples: 371200 | consumed tokens: 760217600 | elapsed time per iteration (s): 0.23 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.291302E+00 | grad norm: 0.673 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.430 | TFLOPs: 28.59 | +7: iteration 1460/ 37905 | consumed samples: 373760 | consumed tokens: 765460480 | elapsed time per iteration (s): 0.23 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.272641E+00 | grad norm: 0.808 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.154 | TFLOPs: 28.43 | +7: iteration 1470/ 37905 | consumed samples: 376320 | consumed tokens: 770703360 | elapsed time per iteration (s): 0.23 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.290630E+00 | grad norm: 0.802 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.818 | TFLOPs: 28.04 | +7: iteration 1480/ 37905 | consumed samples: 378880 | consumed tokens: 775946240 | elapsed time per iteration (s): 0.23 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.291245E+00 | grad norm: 0.725 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.540 | TFLOPs: 28.14 | +7: iteration 1490/ 37905 | consumed samples: 381440 | consumed tokens: 781189120 | elapsed time per iteration (s): 0.23 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.236867E+00 | grad norm: 0.824 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.227 | TFLOPs: 28.03 | +7: iteration 1500/ 37905 | consumed samples: 384000 | consumed tokens: 786432000 | elapsed time per iteration (s): 0.23 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.256079E+00 | grad norm: 0.724 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.306 | TFLOPs: 28.72 | +7: iteration 1510/ 37905 | consumed samples: 386560 | consumed tokens: 791674880 | elapsed time per iteration (s): 0.24 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.268760E+00 | grad norm: 0.687 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1072.346 | TFLOPs: 27.32 | +7: iteration 1520/ 37905 | consumed samples: 389120 | consumed tokens: 796917760 | elapsed time per iteration (s): 0.24 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.245798E+00 | grad norm: 1.059 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.229 | TFLOPs: 27.70 | +7: iteration 1530/ 37905 | consumed samples: 391680 | consumed tokens: 802160640 | elapsed time per iteration (s): 0.23 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.232841E+00 | grad norm: 0.805 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.953 | TFLOPs: 28.61 | +7: iteration 1540/ 37905 | consumed samples: 394240 | consumed tokens: 807403520 | elapsed time per iteration (s): 0.23 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.255910E+00 | grad norm: 0.633 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.535 | TFLOPs: 28.09 | +7: iteration 1550/ 37905 | consumed samples: 396800 | consumed tokens: 812646400 | elapsed time per iteration (s): 0.23 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.213351E+00 | grad norm: 0.620 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.105 | TFLOPs: 28.51 | +7: iteration 1560/ 37905 | consumed samples: 399360 | consumed tokens: 817889280 | elapsed time per iteration (s): 0.23 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.214529E+00 | grad norm: 0.871 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.565 | TFLOPs: 28.04 | +7: iteration 1570/ 37905 | consumed samples: 401920 | consumed tokens: 823132160 | elapsed time per iteration (s): 0.23 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.206889E+00 | grad norm: 0.671 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.887 | TFLOPs: 28.12 | +7: iteration 1580/ 37905 | consumed samples: 404480 | consumed tokens: 828375040 | elapsed time per iteration (s): 0.23 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.186712E+00 | grad norm: 0.717 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.566 | TFLOPs: 28.32 | +7: iteration 1590/ 37905 | consumed samples: 407040 | consumed tokens: 833617920 | elapsed time per iteration (s): 0.24 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.193050E+00 | grad norm: 0.762 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1051.950 | TFLOPs: 26.80 | +7: iteration 1600/ 37905 | consumed samples: 409600 | consumed tokens: 838860800 | elapsed time per iteration (s): 0.23 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.226847E+00 | grad norm: 0.890 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.893 | TFLOPs: 28.10 | +7: iteration 1610/ 37905 | consumed samples: 412160 | consumed tokens: 844103680 | elapsed time per iteration (s): 0.24 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.191895E+00 | grad norm: 0.648 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1081.798 | TFLOPs: 27.56 | +7: iteration 1620/ 37905 | consumed samples: 414720 | consumed tokens: 849346560 | elapsed time per iteration (s): 0.23 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.210138E+00 | grad norm: 0.910 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.500 | TFLOPs: 28.32 | +7: iteration 1630/ 37905 | consumed samples: 417280 | consumed tokens: 854589440 | elapsed time per iteration (s): 0.23 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.204589E+00 | grad norm: 0.589 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.116 | TFLOPs: 28.46 | +7: iteration 1640/ 37905 | consumed samples: 419840 | consumed tokens: 859832320 | elapsed time per iteration (s): 0.23 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.194572E+00 | grad norm: 0.793 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.539 | TFLOPs: 28.62 | +7: iteration 1650/ 37905 | consumed samples: 422400 | consumed tokens: 865075200 | elapsed time per iteration (s): 0.23 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.199366E+00 | grad norm: 0.702 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.378 | TFLOPs: 28.31 | +7: iteration 1660/ 37905 | consumed samples: 424960 | consumed tokens: 870318080 | elapsed time per iteration (s): 0.23 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.193644E+00 | grad norm: 0.808 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.321 | TFLOPs: 27.85 | +7: iteration 1670/ 37905 | consumed samples: 427520 | consumed tokens: 875560960 | elapsed time per iteration (s): 0.23 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.184206E+00 | grad norm: 0.742 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.029 | TFLOPs: 28.71 | +7: iteration 1680/ 37905 | consumed samples: 430080 | consumed tokens: 880803840 | elapsed time per iteration (s): 0.25 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.168130E+00 | grad norm: 0.659 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1026.555 | TFLOPs: 26.15 | +7: iteration 1690/ 37905 | consumed samples: 432640 | consumed tokens: 886046720 | elapsed time per iteration (s): 0.23 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.188292E+00 | grad norm: 0.636 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.093 | TFLOPs: 28.36 | +7: iteration 1700/ 37905 | consumed samples: 435200 | consumed tokens: 891289600 | elapsed time per iteration (s): 0.23 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.157831E+00 | grad norm: 0.792 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.338 | TFLOPs: 28.18 | +7: iteration 1710/ 37905 | consumed samples: 437760 | consumed tokens: 896532480 | elapsed time per iteration (s): 0.23 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.147160E+00 | grad norm: 0.683 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.143 | TFLOPs: 28.10 | +7: iteration 1720/ 37905 | consumed samples: 440320 | consumed tokens: 901775360 | elapsed time per iteration (s): 0.23 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.177104E+00 | grad norm: 0.817 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.869 | TFLOPs: 27.82 | +7: iteration 1730/ 37905 | consumed samples: 442880 | consumed tokens: 907018240 | elapsed time per iteration (s): 0.23 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.154904E+00 | grad norm: 0.649 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.350 | TFLOPs: 28.01 | +7: iteration 1740/ 37905 | consumed samples: 445440 | consumed tokens: 912261120 | elapsed time per iteration (s): 0.23 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.162971E+00 | grad norm: 0.616 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.595 | TFLOPs: 27.96 | +7: iteration 1750/ 37905 | consumed samples: 448000 | consumed tokens: 917504000 | elapsed time per iteration (s): 0.23 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.173431E+00 | grad norm: 0.764 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.330 | TFLOPs: 28.52 | +7: iteration 1760/ 37905 | consumed samples: 450560 | consumed tokens: 922746880 | elapsed time per iteration (s): 0.23 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.126684E+00 | grad norm: 0.741 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.188 | TFLOPs: 28.72 | +7: iteration 1770/ 37905 | consumed samples: 453120 | consumed tokens: 927989760 | elapsed time per iteration (s): 0.23 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.154078E+00 | grad norm: 0.680 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.663 | TFLOPs: 28.45 | +7: iteration 1780/ 37905 | consumed samples: 455680 | consumed tokens: 933232640 | elapsed time per iteration (s): 0.25 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.137350E+00 | grad norm: 0.579 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1026.552 | TFLOPs: 26.15 | +7: iteration 1790/ 37905 | consumed samples: 458240 | consumed tokens: 938475520 | elapsed time per iteration (s): 0.23 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.138116E+00 | grad norm: 0.639 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.568 | TFLOPs: 28.50 | +7: iteration 1800/ 37905 | consumed samples: 460800 | consumed tokens: 943718400 | elapsed time per iteration (s): 0.23 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.151695E+00 | grad norm: 0.762 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.282 | TFLOPs: 28.31 | +7: iteration 1810/ 37905 | consumed samples: 463360 | consumed tokens: 948961280 | elapsed time per iteration (s): 0.23 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.145761E+00 | grad norm: 0.787 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.010 | TFLOPs: 28.23 | +7: iteration 1820/ 37905 | consumed samples: 465920 | consumed tokens: 954204160 | elapsed time per iteration (s): 0.23 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.121735E+00 | grad norm: 0.582 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.101 | TFLOPs: 28.51 | +7: iteration 1830/ 37905 | consumed samples: 468480 | consumed tokens: 959447040 | elapsed time per iteration (s): 0.23 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.166120E+00 | grad norm: 0.559 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.570 | TFLOPs: 28.42 | +7: iteration 1840/ 37905 | consumed samples: 471040 | consumed tokens: 964689920 | elapsed time per iteration (s): 0.23 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.133894E+00 | grad norm: 0.628 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.348 | TFLOPs: 28.21 | +7: iteration 1850/ 37905 | consumed samples: 473600 | consumed tokens: 969932800 | elapsed time per iteration (s): 0.24 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.128171E+00 | grad norm: 1.042 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.936 | TFLOPs: 27.74 | +7: iteration 1860/ 37905 | consumed samples: 476160 | consumed tokens: 975175680 | elapsed time per iteration (s): 0.23 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.121739E+00 | grad norm: 0.684 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.056 | TFLOPs: 28.15 | +7: iteration 1870/ 37905 | consumed samples: 478720 | consumed tokens: 980418560 | elapsed time per iteration (s): 0.23 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.084982E+00 | grad norm: 0.627 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.354 | TFLOPs: 28.31 | +7: iteration 1880/ 37905 | consumed samples: 481280 | consumed tokens: 985661440 | elapsed time per iteration (s): 0.23 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.100135E+00 | grad norm: 0.611 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.513 | TFLOPs: 28.57 | +7: iteration 1890/ 37905 | consumed samples: 483840 | consumed tokens: 990904320 | elapsed time per iteration (s): 0.23 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.118724E+00 | grad norm: 0.572 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.867 | TFLOPs: 28.30 | +7: iteration 1900/ 37905 | consumed samples: 486400 | consumed tokens: 996147200 | elapsed time per iteration (s): 0.23 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.115512E+00 | grad norm: 0.745 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.317 | TFLOPs: 27.88 | +7: iteration 1910/ 37905 | consumed samples: 488960 | consumed tokens: 1001390080 | elapsed time per iteration (s): 0.23 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.120526E+00 | grad norm: 0.762 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.305 | TFLOPs: 28.36 | +7: iteration 1920/ 37905 | consumed samples: 491520 | consumed tokens: 1006632960 | elapsed time per iteration (s): 0.23 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.083563E+00 | grad norm: 0.827 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.658 | TFLOPs: 28.55 | +7: iteration 1930/ 37905 | consumed samples: 494080 | consumed tokens: 1011875840 | elapsed time per iteration (s): 0.23 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.092413E+00 | grad norm: 0.872 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.128 | TFLOPs: 28.10 | +7: iteration 1940/ 37905 | consumed samples: 496640 | consumed tokens: 1017118720 | elapsed time per iteration (s): 0.23 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.109544E+00 | grad norm: 0.640 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.916 | TFLOPs: 28.17 | +7: iteration 1950/ 37905 | consumed samples: 499200 | consumed tokens: 1022361600 | elapsed time per iteration (s): 0.23 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.114706E+00 | grad norm: 0.758 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.848 | TFLOPs: 28.22 | +7: iteration 1960/ 37905 | consumed samples: 501760 | consumed tokens: 1027604480 | elapsed time per iteration (s): 0.23 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.115100E+00 | grad norm: 0.564 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.359 | TFLOPs: 28.39 | +7: iteration 1970/ 37905 | consumed samples: 504320 | consumed tokens: 1032847360 | elapsed time per iteration (s): 0.23 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.110106E+00 | grad norm: 0.572 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.804 | TFLOPs: 28.17 | +7: iteration 1980/ 37905 | consumed samples: 506880 | consumed tokens: 1038090240 | elapsed time per iteration (s): 0.23 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.088705E+00 | grad norm: 0.558 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.941 | TFLOPs: 28.17 | +7: iteration 1990/ 37905 | consumed samples: 509440 | consumed tokens: 1043333120 | elapsed time per iteration (s): 0.25 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.079786E+00 | grad norm: 0.669 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1029.384 | TFLOPs: 26.22 | +0: [2022-11-29 17:04:05,013] [INFO] [logging.py:68:log_dist] [Rank 0] step=2000, skipped=0, lr=[0.00019917259290531361, 0.00019917259290531361, 0.00019917259290531361], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 2000/ 37905 | consumed samples: 512000 | consumed tokens: 1048576000 | elapsed time per iteration (s): 0.23 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.091220E+00 | grad norm: 0.596 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.674 | TFLOPs: 28.50 | +0: steps: 2000 loss: 4.0752 iter time (s): 0.239 samples/sec: 1070.423 +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 2000 | lm loss value: 3.938342E+00 | lm loss PPL: 5.133344E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 2000 to checkpoints_83moscar +0: [2022-11-29 17:04:05,103] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step2000 is begin to save! +0: [2022-11-29 17:04:05,106] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:04:05,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:04:05,178] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:04:05,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:04:05,191] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:04:05,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:04:05,202] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:04:05,213] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:04:05,214] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:04:05,225] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:04:05,225] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:04:05,236] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:04:05,236] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:04:05,247] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:04:05,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:04:05,259] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:04:05,259] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:04:05,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:04:05,270] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:04:05,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:04:05,282] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:04:05,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:04:05,293] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:04:05,294] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:04:05,295] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step2000/mp_rank_00_model_states.pt +0: [2022-11-29 17:04:05,295] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:04:05,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:04:05,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:04:05,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:04:05,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:04:05,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:04:05,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:04:05,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +7: [2022-11-29 17:04:05,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:04:05,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:04:05,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:04:05,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:04:05,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:04:05,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +3: [2022-11-29 17:04:05,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:04:05,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:04:05,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +6: [2022-11-29 17:04:05,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:04:05,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:04:05,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:04:05,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:04:05,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:04:05,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:04:05,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:04:05,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:04:05,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:04:05,335] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:04:05,335] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:04:05,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:04:05,335] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:04:05,335] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:04:05,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:04:05,335] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:04:05,335] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:04:05,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:04:05,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:04:05,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:04:05,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:04:05,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:04:05,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +0: [2022-11-29 17:04:05,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3: [2022-11-29 17:04:05,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:04:05,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:04:05,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:04:05,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:04:05,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +2: [2022-11-29 17:04:05,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +1: [2022-11-29 17:04:05,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:04:05,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:04:05,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +6: [2022-11-29 17:04:05,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:04:05,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:04:05,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:04:05,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:04:05,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:04:05,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:04:05,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:04:05,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:04:05,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:04:05,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:04:05,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:04:05,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +3: [2022-11-29 17:04:05,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:04:05,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:04:05,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:04:05,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +5: [2022-11-29 17:04:05,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:04:05,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:04:05,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:04:05,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:04:05,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:04:05,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:04:05,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:04:05,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:04:05,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +6: [2022-11-29 17:04:05,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +1: [2022-11-29 17:04:05,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:04:05,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:04:05,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:04:05,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:04:05,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +6: [2022-11-29 17:04:05,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:04:05,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +0: [2022-11-29 17:04:05,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:04:05,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:04:05,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:04:05,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:04:05,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:04:05,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:04:05,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:04:05,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:04:05,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:04:05,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:04:05,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:04:05,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:04:05,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +5: [2022-11-29 17:04:05,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:04:05,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:04:05,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:04:05,339] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:04:05,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:04:05,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:04:05,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:04:05,339] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:04:05,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:04:05,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:04:05,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:04:05,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:04:05,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:04:05,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:04:05,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:04:05,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:04:05,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:04:05,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:04:05,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:04:05,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:04:05,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:04:05,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:04:05,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:04:05,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:04:05,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:04:05,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:04:05,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:04:05,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:04:05,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:04:05,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:04:05,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:04:05,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:04:05,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:04:05,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +4: [2022-11-29 17:04:05,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +0: [2022-11-29 17:04:05,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +2: [2022-11-29 17:04:05,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:04:05,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:04:05,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:04:05,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:04:05,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:04:05,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:04:05,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:04:05,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:04:05,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:04:05,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:04:05,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:04:05,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:04:05,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:04:05,342] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:04:05,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:04:05,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:04:05,342] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:04:05,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:04:05,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:04:05,342] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:04:05,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:04:05,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:04:05,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:04:05,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:04:05,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:04:05,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +4: [2022-11-29 17:04:05,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:04:05,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:04:05,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:04:05,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:04:05,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:04:05,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:04:05,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:04:05,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:04:05,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:04:05,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-29 17:04:05,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:04:05,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:04:05,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-29 17:04:05,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:04:05,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:04:05,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:04:05,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:04:05,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:04:05,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:04:05,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:04:05,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-29 17:04:05,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-29 17:04:05,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:04:05,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:04:05,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:04:05,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-29 17:04:05,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:04:05,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-29 17:04:05,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:04:05,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:04:05,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-29 17:04:05,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:04:05,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:04:05,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-29 17:04:05,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:04:05,345] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:04:05,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: successfully saved checkpoint at iteration 2000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 245.51 +7: iteration 2010/ 37905 | consumed samples: 514560 | consumed tokens: 1053818880 | elapsed time per iteration (s): 0.26 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.066650E+00 | grad norm: 0.581 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 977.976 | TFLOPs: 24.91 | +7: iteration 2020/ 37905 | consumed samples: 517120 | consumed tokens: 1059061760 | elapsed time per iteration (s): 0.23 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.070164E+00 | grad norm: 0.673 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.741 | TFLOPs: 28.68 | +7: iteration 2030/ 37905 | consumed samples: 519680 | consumed tokens: 1064304640 | elapsed time per iteration (s): 0.23 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 4.081255E+00 | grad norm: 0.602 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.609 | TFLOPs: 28.55 | +7: iteration 2040/ 37905 | consumed samples: 522240 | consumed tokens: 1069547520 | elapsed time per iteration (s): 0.23 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 4.055042E+00 | grad norm: 0.650 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.180 | TFLOPs: 28.51 | +7: iteration 2050/ 37905 | consumed samples: 524800 | consumed tokens: 1074790400 | elapsed time per iteration (s): 0.23 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 4.053129E+00 | grad norm: 0.661 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.834 | TFLOPs: 28.68 | +7: iteration 2060/ 37905 | consumed samples: 527360 | consumed tokens: 1080033280 | elapsed time per iteration (s): 0.23 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 4.063480E+00 | grad norm: 0.499 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.398 | TFLOPs: 27.98 | +7: iteration 2070/ 37905 | consumed samples: 529920 | consumed tokens: 1085276160 | elapsed time per iteration (s): 0.26 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 4.039795E+00 | grad norm: 0.561 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1000.370 | TFLOPs: 25.48 | +7: iteration 2080/ 37905 | consumed samples: 532480 | consumed tokens: 1090519040 | elapsed time per iteration (s): 0.23 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 4.048302E+00 | grad norm: 0.659 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.231 | TFLOPs: 28.33 | +7: iteration 2090/ 37905 | consumed samples: 535040 | consumed tokens: 1095761920 | elapsed time per iteration (s): 0.23 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 4.018704E+00 | grad norm: 0.557 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.749 | TFLOPs: 27.76 | +7: iteration 2100/ 37905 | consumed samples: 537600 | consumed tokens: 1101004800 | elapsed time per iteration (s): 0.23 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 4.053591E+00 | grad norm: 0.587 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.181 | TFLOPs: 28.64 | +7: iteration 2110/ 37905 | consumed samples: 540160 | consumed tokens: 1106247680 | elapsed time per iteration (s): 0.23 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 4.065705E+00 | grad norm: 0.653 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.209 | TFLOPs: 28.23 | +7: iteration 2120/ 37905 | consumed samples: 542720 | consumed tokens: 1111490560 | elapsed time per iteration (s): 0.23 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 4.036006E+00 | grad norm: 0.519 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.058 | TFLOPs: 28.23 | +7: iteration 2130/ 37905 | consumed samples: 545280 | consumed tokens: 1116733440 | elapsed time per iteration (s): 0.23 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 4.024969E+00 | grad norm: 0.659 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.566 | TFLOPs: 28.65 | +7: iteration 2140/ 37905 | consumed samples: 547840 | consumed tokens: 1121976320 | elapsed time per iteration (s): 0.23 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 4.048096E+00 | grad norm: 0.605 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.757 | TFLOPs: 27.84 | +7: iteration 2150/ 37905 | consumed samples: 550400 | consumed tokens: 1127219200 | elapsed time per iteration (s): 0.23 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 4.038911E+00 | grad norm: 0.624 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.203 | TFLOPs: 28.38 | +7: iteration 2160/ 37905 | consumed samples: 552960 | consumed tokens: 1132462080 | elapsed time per iteration (s): 0.23 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 4.062947E+00 | grad norm: 0.710 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.492 | TFLOPs: 28.14 | +7: iteration 2170/ 37905 | consumed samples: 555520 | consumed tokens: 1137704960 | elapsed time per iteration (s): 0.23 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 4.038583E+00 | grad norm: 0.574 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.249 | TFLOPs: 27.93 | +7: iteration 2180/ 37905 | consumed samples: 558080 | consumed tokens: 1142947840 | elapsed time per iteration (s): 0.23 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 4.042631E+00 | grad norm: 0.497 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.013 | TFLOPs: 28.66 | +7: iteration 2190/ 37905 | consumed samples: 560640 | consumed tokens: 1148190720 | elapsed time per iteration (s): 0.23 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 4.023553E+00 | grad norm: 0.609 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.059 | TFLOPs: 28.48 | +7: iteration 2200/ 37905 | consumed samples: 563200 | consumed tokens: 1153433600 | elapsed time per iteration (s): 0.23 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 4.022335E+00 | grad norm: 0.540 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.746 | TFLOPs: 28.35 | +7: iteration 2210/ 37905 | consumed samples: 565760 | consumed tokens: 1158676480 | elapsed time per iteration (s): 0.23 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 4.033907E+00 | grad norm: 0.555 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.942 | TFLOPs: 28.45 | +7: iteration 2220/ 37905 | consumed samples: 568320 | consumed tokens: 1163919360 | elapsed time per iteration (s): 0.23 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 4.028337E+00 | grad norm: 0.526 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.275 | TFLOPs: 28.41 | +7: iteration 2230/ 37905 | consumed samples: 570880 | consumed tokens: 1169162240 | elapsed time per iteration (s): 0.23 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 4.016743E+00 | grad norm: 0.609 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.973 | TFLOPs: 28.46 | +7: iteration 2240/ 37905 | consumed samples: 573440 | consumed tokens: 1174405120 | elapsed time per iteration (s): 0.23 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 4.031874E+00 | grad norm: 0.632 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.855 | TFLOPs: 28.02 | +7: iteration 2250/ 37905 | consumed samples: 576000 | consumed tokens: 1179648000 | elapsed time per iteration (s): 0.23 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 4.026750E+00 | grad norm: 0.590 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.468 | TFLOPs: 28.52 | +7: iteration 2260/ 37905 | consumed samples: 578560 | consumed tokens: 1184890880 | elapsed time per iteration (s): 0.23 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 4.008619E+00 | grad norm: 0.620 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.085 | TFLOPs: 28.71 | +7: iteration 2270/ 37905 | consumed samples: 581120 | consumed tokens: 1190133760 | elapsed time per iteration (s): 0.23 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 4.004513E+00 | grad norm: 0.627 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.201 | TFLOPs: 28.13 | +7: iteration 2280/ 37905 | consumed samples: 583680 | consumed tokens: 1195376640 | elapsed time per iteration (s): 0.23 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 4.017902E+00 | grad norm: 0.589 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.586 | TFLOPs: 28.67 | +7: iteration 2290/ 37905 | consumed samples: 586240 | consumed tokens: 1200619520 | elapsed time per iteration (s): 0.23 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 4.024744E+00 | grad norm: 0.550 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.826 | TFLOPs: 28.43 | +7: iteration 2300/ 37905 | consumed samples: 588800 | consumed tokens: 1205862400 | elapsed time per iteration (s): 0.23 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 3.996304E+00 | grad norm: 0.759 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.287 | TFLOPs: 28.18 | +7: iteration 2310/ 37905 | consumed samples: 591360 | consumed tokens: 1211105280 | elapsed time per iteration (s): 0.23 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 4.003929E+00 | grad norm: 0.484 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.622 | TFLOPs: 28.45 | +7: iteration 2320/ 37905 | consumed samples: 593920 | consumed tokens: 1216348160 | elapsed time per iteration (s): 0.23 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 3.994767E+00 | grad norm: 0.556 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.350 | TFLOPs: 28.49 | +7: iteration 2330/ 37905 | consumed samples: 596480 | consumed tokens: 1221591040 | elapsed time per iteration (s): 0.24 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 4.011921E+00 | grad norm: 0.512 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1051.428 | TFLOPs: 26.79 | +7: iteration 2340/ 37905 | consumed samples: 599040 | consumed tokens: 1226833920 | elapsed time per iteration (s): 0.23 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 4.007503E+00 | grad norm: 0.584 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.649 | TFLOPs: 28.22 | +7: iteration 2350/ 37905 | consumed samples: 601600 | consumed tokens: 1232076800 | elapsed time per iteration (s): 0.23 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 4.009705E+00 | grad norm: 0.557 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.737 | TFLOPs: 28.65 | +7: iteration 2360/ 37905 | consumed samples: 604160 | consumed tokens: 1237319680 | elapsed time per iteration (s): 0.23 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 3.974823E+00 | grad norm: 0.644 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.609 | TFLOPs: 28.65 | +7: iteration 2370/ 37905 | consumed samples: 606720 | consumed tokens: 1242562560 | elapsed time per iteration (s): 0.23 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 3.957733E+00 | grad norm: 0.629 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.536 | TFLOPs: 28.39 | +7: iteration 2380/ 37905 | consumed samples: 609280 | consumed tokens: 1247805440 | elapsed time per iteration (s): 0.23 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 3.966981E+00 | grad norm: 0.675 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.744 | TFLOPs: 28.17 | +7: iteration 2390/ 37905 | consumed samples: 611840 | consumed tokens: 1253048320 | elapsed time per iteration (s): 0.23 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 4.011612E+00 | grad norm: 0.598 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.013 | TFLOPs: 28.20 | +7: iteration 2400/ 37905 | consumed samples: 614400 | consumed tokens: 1258291200 | elapsed time per iteration (s): 0.23 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 3.963548E+00 | grad norm: 0.506 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.779 | TFLOPs: 28.53 | +7: iteration 2410/ 37905 | consumed samples: 616960 | consumed tokens: 1263534080 | elapsed time per iteration (s): 0.23 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 3.993968E+00 | grad norm: 0.757 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.040 | TFLOPs: 28.23 | +7: iteration 2420/ 37905 | consumed samples: 619520 | consumed tokens: 1268776960 | elapsed time per iteration (s): 0.23 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 3.969987E+00 | grad norm: 0.577 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.915 | TFLOPs: 28.50 | +7: iteration 2430/ 37905 | consumed samples: 622080 | consumed tokens: 1274019840 | elapsed time per iteration (s): 0.24 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 3.995169E+00 | grad norm: 0.581 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1073.721 | TFLOPs: 27.35 | +7: iteration 2440/ 37905 | consumed samples: 624640 | consumed tokens: 1279262720 | elapsed time per iteration (s): 0.23 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 3.984194E+00 | grad norm: 0.590 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.817 | TFLOPs: 28.60 | +7: iteration 2450/ 37905 | consumed samples: 627200 | consumed tokens: 1284505600 | elapsed time per iteration (s): 0.23 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 3.991614E+00 | grad norm: 0.521 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.568 | TFLOPs: 28.14 | +7: iteration 2460/ 37905 | consumed samples: 629760 | consumed tokens: 1289748480 | elapsed time per iteration (s): 0.24 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 3.955930E+00 | grad norm: 0.545 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1084.865 | TFLOPs: 27.64 | +7: iteration 2470/ 37905 | consumed samples: 632320 | consumed tokens: 1294991360 | elapsed time per iteration (s): 0.23 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 3.974558E+00 | grad norm: 0.560 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.579 | TFLOPs: 28.55 | +7: iteration 2480/ 37905 | consumed samples: 634880 | consumed tokens: 1300234240 | elapsed time per iteration (s): 0.23 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 3.985175E+00 | grad norm: 0.691 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.824 | TFLOPs: 28.60 | +7: iteration 2490/ 37905 | consumed samples: 637440 | consumed tokens: 1305477120 | elapsed time per iteration (s): 0.23 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 3.979830E+00 | grad norm: 0.568 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.031 | TFLOPs: 28.74 | +7: iteration 2500/ 37905 | consumed samples: 640000 | consumed tokens: 1310720000 | elapsed time per iteration (s): 0.23 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 3.998084E+00 | grad norm: 0.638 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.015 | TFLOPs: 27.87 | +7: iteration 2510/ 37905 | consumed samples: 642560 | consumed tokens: 1315962880 | elapsed time per iteration (s): 0.23 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 3.975998E+00 | grad norm: 0.561 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.829 | TFLOPs: 28.48 | +7: iteration 2520/ 37905 | consumed samples: 645120 | consumed tokens: 1321205760 | elapsed time per iteration (s): 0.23 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 3.969253E+00 | grad norm: 0.486 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1131.745 | TFLOPs: 28.83 | +7: iteration 2530/ 37905 | consumed samples: 647680 | consumed tokens: 1326448640 | elapsed time per iteration (s): 0.23 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 3.955466E+00 | grad norm: 0.543 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.420 | TFLOPs: 28.34 | +7: iteration 2540/ 37905 | consumed samples: 650240 | consumed tokens: 1331691520 | elapsed time per iteration (s): 0.23 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 3.957892E+00 | grad norm: 0.638 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.792 | TFLOPs: 28.37 | +7: iteration 2550/ 37905 | consumed samples: 652800 | consumed tokens: 1336934400 | elapsed time per iteration (s): 0.23 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 3.961476E+00 | grad norm: 0.566 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.739 | TFLOPs: 27.91 | +7: iteration 2560/ 37905 | consumed samples: 655360 | consumed tokens: 1342177280 | elapsed time per iteration (s): 0.23 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 3.951577E+00 | grad norm: 0.481 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.779 | TFLOPs: 28.50 | +7: iteration 2570/ 37905 | consumed samples: 657920 | consumed tokens: 1347420160 | elapsed time per iteration (s): 0.23 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 3.950914E+00 | grad norm: 0.581 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.014 | TFLOPs: 28.69 | +7: iteration 2580/ 37905 | consumed samples: 660480 | consumed tokens: 1352663040 | elapsed time per iteration (s): 0.23 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 3.956404E+00 | grad norm: 0.527 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.293 | TFLOPs: 28.31 | +7: iteration 2590/ 37905 | consumed samples: 663040 | consumed tokens: 1357905920 | elapsed time per iteration (s): 0.23 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 3.936757E+00 | grad norm: 0.532 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.168 | TFLOPs: 28.31 | +7: iteration 2600/ 37905 | consumed samples: 665600 | consumed tokens: 1363148800 | elapsed time per iteration (s): 0.23 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 3.933626E+00 | grad norm: 0.694 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.879 | TFLOPs: 28.63 | +7: iteration 2610/ 37905 | consumed samples: 668160 | consumed tokens: 1368391680 | elapsed time per iteration (s): 0.23 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 3.940955E+00 | grad norm: 0.490 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.082 | TFLOPs: 28.20 | +7: iteration 2620/ 37905 | consumed samples: 670720 | consumed tokens: 1373634560 | elapsed time per iteration (s): 0.23 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 3.930252E+00 | grad norm: 0.581 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.774 | TFLOPs: 28.45 | +7: iteration 2630/ 37905 | consumed samples: 673280 | consumed tokens: 1378877440 | elapsed time per iteration (s): 0.23 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 3.923481E+00 | grad norm: 0.574 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.843 | TFLOPs: 28.78 | +7: iteration 2640/ 37905 | consumed samples: 675840 | consumed tokens: 1384120320 | elapsed time per iteration (s): 0.24 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 3.957915E+00 | grad norm: 0.510 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1067.606 | TFLOPs: 27.20 | +7: iteration 2650/ 37905 | consumed samples: 678400 | consumed tokens: 1389363200 | elapsed time per iteration (s): 0.23 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 3.909699E+00 | grad norm: 0.543 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.174 | TFLOPs: 28.74 | +7: iteration 2660/ 37905 | consumed samples: 680960 | consumed tokens: 1394606080 | elapsed time per iteration (s): 0.24 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 3.984351E+00 | grad norm: 0.477 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1082.163 | TFLOPs: 27.57 | +7: iteration 2670/ 37905 | consumed samples: 683520 | consumed tokens: 1399848960 | elapsed time per iteration (s): 0.23 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 3.948639E+00 | grad norm: 0.521 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.422 | TFLOPs: 28.34 | +7: iteration 2680/ 37905 | consumed samples: 686080 | consumed tokens: 1405091840 | elapsed time per iteration (s): 0.23 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 3.936429E+00 | grad norm: 0.609 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.924 | TFLOPs: 28.73 | +7: iteration 2690/ 37905 | consumed samples: 688640 | consumed tokens: 1410334720 | elapsed time per iteration (s): 0.23 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 3.910407E+00 | grad norm: 0.539 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.573 | TFLOPs: 28.11 | +7: iteration 2700/ 37905 | consumed samples: 691200 | consumed tokens: 1415577600 | elapsed time per iteration (s): 0.23 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 3.937724E+00 | grad norm: 0.634 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.427 | TFLOPs: 28.24 | +7: iteration 2710/ 37905 | consumed samples: 693760 | consumed tokens: 1420820480 | elapsed time per iteration (s): 0.23 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 3.930606E+00 | grad norm: 0.494 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.593 | TFLOPs: 28.09 | +7: iteration 2720/ 37905 | consumed samples: 696320 | consumed tokens: 1426063360 | elapsed time per iteration (s): 0.24 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 3.921622E+00 | grad norm: 0.571 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1061.506 | TFLOPs: 27.04 | +7: iteration 2730/ 37905 | consumed samples: 698880 | consumed tokens: 1431306240 | elapsed time per iteration (s): 0.25 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 3.934104E+00 | grad norm: 0.563 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1020.513 | TFLOPs: 26.00 | +7: iteration 2740/ 37905 | consumed samples: 701440 | consumed tokens: 1436549120 | elapsed time per iteration (s): 0.23 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 3.908081E+00 | grad norm: 0.519 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.390 | TFLOPs: 28.39 | +7: iteration 2750/ 37905 | consumed samples: 704000 | consumed tokens: 1441792000 | elapsed time per iteration (s): 0.23 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 3.913601E+00 | grad norm: 0.587 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.543 | TFLOPs: 28.57 | +7: iteration 2760/ 37905 | consumed samples: 706560 | consumed tokens: 1447034880 | elapsed time per iteration (s): 0.23 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 3.944719E+00 | grad norm: 0.581 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.437 | TFLOPs: 28.16 | +7: iteration 2770/ 37905 | consumed samples: 709120 | consumed tokens: 1452277760 | elapsed time per iteration (s): 0.23 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 3.909301E+00 | grad norm: 0.496 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.277 | TFLOPs: 28.56 | +7: iteration 2780/ 37905 | consumed samples: 711680 | consumed tokens: 1457520640 | elapsed time per iteration (s): 0.23 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 3.904039E+00 | grad norm: 0.570 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.051 | TFLOPs: 28.13 | +7: iteration 2790/ 37905 | consumed samples: 714240 | consumed tokens: 1462763520 | elapsed time per iteration (s): 0.23 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 3.935281E+00 | grad norm: 0.475 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.669 | TFLOPs: 27.76 | +7: iteration 2800/ 37905 | consumed samples: 716800 | consumed tokens: 1468006400 | elapsed time per iteration (s): 0.23 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 3.889299E+00 | grad norm: 0.501 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.139 | TFLOPs: 28.23 | +7: iteration 2810/ 37905 | consumed samples: 719360 | consumed tokens: 1473249280 | elapsed time per iteration (s): 0.23 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 3.902533E+00 | grad norm: 0.480 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.570 | TFLOPs: 28.11 | +7: iteration 2820/ 37905 | consumed samples: 721920 | consumed tokens: 1478492160 | elapsed time per iteration (s): 0.23 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 3.910664E+00 | grad norm: 0.706 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.181 | TFLOPs: 28.38 | +7: iteration 2830/ 37905 | consumed samples: 724480 | consumed tokens: 1483735040 | elapsed time per iteration (s): 0.23 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 3.895118E+00 | grad norm: 0.613 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.329 | TFLOPs: 28.31 | +7: iteration 2840/ 37905 | consumed samples: 727040 | consumed tokens: 1488977920 | elapsed time per iteration (s): 0.23 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 3.908374E+00 | grad norm: 0.518 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.144 | TFLOPs: 28.00 | +7: iteration 2850/ 37905 | consumed samples: 729600 | consumed tokens: 1494220800 | elapsed time per iteration (s): 0.23 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 3.923541E+00 | grad norm: 0.597 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.175 | TFLOPs: 28.36 | +7: iteration 2860/ 37905 | consumed samples: 732160 | consumed tokens: 1499463680 | elapsed time per iteration (s): 0.23 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 3.914349E+00 | grad norm: 0.644 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.883 | TFLOPs: 28.27 | +7: iteration 2870/ 37905 | consumed samples: 734720 | consumed tokens: 1504706560 | elapsed time per iteration (s): 0.23 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 3.917092E+00 | grad norm: 0.546 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.644 | TFLOPs: 28.22 | +7: iteration 2880/ 37905 | consumed samples: 737280 | consumed tokens: 1509949440 | elapsed time per iteration (s): 0.23 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 3.882787E+00 | grad norm: 0.420 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.947 | TFLOPs: 28.28 | +7: iteration 2890/ 37905 | consumed samples: 739840 | consumed tokens: 1515192320 | elapsed time per iteration (s): 0.25 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 3.890372E+00 | grad norm: 0.583 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1035.353 | TFLOPs: 26.38 | +7: iteration 2900/ 37905 | consumed samples: 742400 | consumed tokens: 1520435200 | elapsed time per iteration (s): 0.23 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 3.907577E+00 | grad norm: 0.463 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.483 | TFLOPs: 28.44 | +7: iteration 2910/ 37905 | consumed samples: 744960 | consumed tokens: 1525678080 | elapsed time per iteration (s): 0.23 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 3.917200E+00 | grad norm: 0.500 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.565 | TFLOPs: 28.57 | +7: iteration 2920/ 37905 | consumed samples: 747520 | consumed tokens: 1530920960 | elapsed time per iteration (s): 0.23 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 3.888103E+00 | grad norm: 0.547 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.673 | TFLOPs: 28.32 | +7: iteration 2930/ 37905 | consumed samples: 750080 | consumed tokens: 1536163840 | elapsed time per iteration (s): 0.23 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 3.871029E+00 | grad norm: 0.747 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.671 | TFLOPs: 28.40 | +7: iteration 2940/ 37905 | consumed samples: 752640 | consumed tokens: 1541406720 | elapsed time per iteration (s): 0.23 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 3.926338E+00 | grad norm: 0.521 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.700 | TFLOPs: 28.35 | +7: iteration 2950/ 37905 | consumed samples: 755200 | consumed tokens: 1546649600 | elapsed time per iteration (s): 0.23 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 3.865277E+00 | grad norm: 0.627 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.356 | TFLOPs: 28.29 | +7: iteration 2960/ 37905 | consumed samples: 757760 | consumed tokens: 1551892480 | elapsed time per iteration (s): 0.23 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 3.865908E+00 | grad norm: 0.528 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.779 | TFLOPs: 28.76 | +7: iteration 2970/ 37905 | consumed samples: 760320 | consumed tokens: 1557135360 | elapsed time per iteration (s): 0.23 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 3.873624E+00 | grad norm: 0.460 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.462 | TFLOPs: 28.44 | +7: iteration 2980/ 37905 | consumed samples: 762880 | consumed tokens: 1562378240 | elapsed time per iteration (s): 0.24 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 3.922853E+00 | grad norm: 0.605 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1050.935 | TFLOPs: 26.77 | +7: iteration 2990/ 37905 | consumed samples: 765440 | consumed tokens: 1567621120 | elapsed time per iteration (s): 0.23 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 3.885519E+00 | grad norm: 0.516 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.632 | TFLOPs: 28.47 | +7: iteration 3000/ 37905 | consumed samples: 768000 | consumed tokens: 1572864000 | elapsed time per iteration (s): 0.24 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 3.869517E+00 | grad norm: 0.493 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1083.753 | TFLOPs: 27.61 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 3000 | lm loss value: 3.670186E+00 | lm loss PPL: 3.925921E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 3000 to checkpoints_83moscar +0: [2022-11-29 17:07:56,699] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step3000 is begin to save! +0: [2022-11-29 17:07:56,702] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:07:56,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:07:56,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:07:56,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:07:56,787] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:07:56,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:07:56,799] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:07:56,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:07:56,810] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:07:56,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:07:56,821] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:07:56,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:07:56,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:07:56,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:07:56,844] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:07:56,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:07:56,855] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:07:56,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:07:56,867] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:07:56,878] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:07:56,878] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:07:56,889] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:07:56,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:07:56,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:07:56,891] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step3000/mp_rank_00_model_states.pt +0: [2022-11-29 17:07:56,891] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:07:56,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:07:56,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:07:56,930] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:07:56,930] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:07:56,930] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:07:56,930] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:07:56,930] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:07:56,930] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:07:56,930] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:07:56,930] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:07:56,930] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:07:56,930] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +2: [2022-11-29 17:07:56,930] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +1: [2022-11-29 17:07:56,930] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:07:56,930] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:07:56,930] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:07:56,930] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:07:56,930] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:07:56,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:07:56,931] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:07:56,931] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:07:56,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:07:56,931] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:07:56,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:07:56,931] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:07:56,931] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:07:56,931] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:07:56,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:07:56,931] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:07:56,931] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:07:56,932] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:07:56,932] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:07:56,932] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:07:56,932] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:07:56,932] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:07:56,932] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:07:56,932] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:07:56,932] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:07:56,932] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +0: [2022-11-29 17:07:56,932] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +1: [2022-11-29 17:07:56,933] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:07:56,933] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:07:56,932] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:07:56,933] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:07:56,933] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:07:56,933] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:07:56,933] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +5: [2022-11-29 17:07:56,933] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:07:56,933] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:07:56,933] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:07:56,933] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:07:56,933] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:07:56,934] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:07:56,934] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:07:56,934] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:07:56,934] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:07:56,934] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:07:56,934] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:07:56,934] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:07:56,934] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:07:56,934] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:07:56,934] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:07:56,934] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:07:56,935] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:07:56,935] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:07:56,935] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:07:56,935] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:07:56,935] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:07:56,935] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:07:56,935] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:07:56,935] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:07:56,935] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:07:56,935] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:07:56,936] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:07:56,936] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:07:56,935] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:07:56,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:07:56,936] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +5: [2022-11-29 17:07:56,936] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +7: [2022-11-29 17:07:56,936] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:07:56,936] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:07:56,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:07:56,936] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:07:56,936] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:07:56,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:07:56,936] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:07:56,936] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:07:56,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:07:56,936] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:07:56,936] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:07:56,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:07:56,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:07:56,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:07:56,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:07:56,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:07:56,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:07:56,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:07:56,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:07:56,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:07:56,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:07:56,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:07:56,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:07:56,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:07:56,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:07:56,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:07:56,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:07:56,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:07:56,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:07:56,938] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +2: [2022-11-29 17:07:56,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +3: [2022-11-29 17:07:56,938] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:07:56,938] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:07:56,938] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:07:56,938] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:07:56,938] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:07:56,938] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:07:56,938] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:07:56,938] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:07:56,938] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +4: [2022-11-29 17:07:56,938] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:07:56,938] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:07:56,938] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:07:56,938] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:07:56,938] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:07:56,938] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:07:56,938] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:07:56,938] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:07:56,939] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:07:56,939] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:07:56,939] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:07:56,939] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:07:56,939] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:07:56,939] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:07:56,939] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:07:56,939] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-29 17:07:56,939] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:07:56,939] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +0: [2022-11-29 17:07:56,939] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:07:56,939] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:07:56,939] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:07:56,939] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:07:56,939] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:07:56,939] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:07:56,939] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:07:56,939] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:07:56,939] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:07:56,939] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:07:56,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:07:56,940] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:07:56,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:07:56,990] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +0: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:07:56,990] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +2: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:07:56,990] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +7: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:07:56,990] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +7: [2022-11-29 17:07:56,990] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +1: [2022-11-29 17:07:56,990] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +5: [2022-11-29 17:07:56,990] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:07:56,990] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:07:56,990] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +0: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:07:56,990] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +7: [2022-11-29 17:07:56,990] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +4: [2022-11-29 17:07:56,990] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +6: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:07:56,990] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +2: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-29 17:07:56,990] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:07:56,990] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-29 17:07:56,991] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:07:56,991] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: successfully saved checkpoint at iteration 3000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 296.20 +7: iteration 3010/ 37905 | consumed samples: 770560 | consumed tokens: 1578106880 | elapsed time per iteration (s): 0.27 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 3.877283E+00 | grad norm: 0.703 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 961.622 | TFLOPs: 24.50 | +7: iteration 3020/ 37905 | consumed samples: 773120 | consumed tokens: 1583349760 | elapsed time per iteration (s): 0.23 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 3.887723E+00 | grad norm: 0.527 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.716 | TFLOPs: 28.65 | +7: iteration 3030/ 37905 | consumed samples: 775680 | consumed tokens: 1588592640 | elapsed time per iteration (s): 0.23 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 3.870853E+00 | grad norm: 0.533 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.839 | TFLOPs: 28.40 | +7: iteration 3040/ 37905 | consumed samples: 778240 | consumed tokens: 1593835520 | elapsed time per iteration (s): 0.23 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 3.899823E+00 | grad norm: 0.605 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.647 | TFLOPs: 28.34 | +7: iteration 3050/ 37905 | consumed samples: 780800 | consumed tokens: 1599078400 | elapsed time per iteration (s): 0.23 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 3.885473E+00 | grad norm: 0.415 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.505 | TFLOPs: 28.67 | +7: iteration 3060/ 37905 | consumed samples: 783360 | consumed tokens: 1604321280 | elapsed time per iteration (s): 0.23 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 3.854519E+00 | grad norm: 0.436 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.587 | TFLOPs: 28.67 | +7: iteration 3070/ 37905 | consumed samples: 785920 | consumed tokens: 1609564160 | elapsed time per iteration (s): 0.23 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 3.897980E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.256 | TFLOPs: 28.33 | +7: iteration 3080/ 37905 | consumed samples: 788480 | consumed tokens: 1614807040 | elapsed time per iteration (s): 0.25 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 3.891021E+00 | grad norm: 0.423 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1033.318 | TFLOPs: 26.32 | +7: iteration 3090/ 37905 | consumed samples: 791040 | consumed tokens: 1620049920 | elapsed time per iteration (s): 0.23 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 3.888284E+00 | grad norm: 0.631 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.915 | TFLOPs: 28.63 | +7: iteration 3100/ 37905 | consumed samples: 793600 | consumed tokens: 1625292800 | elapsed time per iteration (s): 0.23 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 3.873396E+00 | grad norm: 0.412 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.063 | TFLOPs: 28.41 | +7: iteration 3110/ 37905 | consumed samples: 796160 | consumed tokens: 1630535680 | elapsed time per iteration (s): 0.23 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 3.876196E+00 | grad norm: 0.509 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.050 | TFLOPs: 28.33 | +7: iteration 3120/ 37905 | consumed samples: 798720 | consumed tokens: 1635778560 | elapsed time per iteration (s): 0.23 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 3.881693E+00 | grad norm: 0.563 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.459 | TFLOPs: 28.34 | +7: iteration 3130/ 37905 | consumed samples: 801280 | consumed tokens: 1641021440 | elapsed time per iteration (s): 0.23 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 3.884603E+00 | grad norm: 0.427 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.284 | TFLOPs: 28.69 | +7: iteration 3140/ 37905 | consumed samples: 803840 | consumed tokens: 1646264320 | elapsed time per iteration (s): 0.23 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 3.860628E+00 | grad norm: 0.526 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.053 | TFLOPs: 27.92 | +7: iteration 3150/ 37905 | consumed samples: 806400 | consumed tokens: 1651507200 | elapsed time per iteration (s): 0.23 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 3.849621E+00 | grad norm: 0.661 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.691 | TFLOPs: 28.32 | +7: iteration 3160/ 37905 | consumed samples: 808960 | consumed tokens: 1656750080 | elapsed time per iteration (s): 0.23 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 3.846111E+00 | grad norm: 0.649 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.189 | TFLOPs: 28.26 | +7: iteration 3170/ 37905 | consumed samples: 811520 | consumed tokens: 1661992960 | elapsed time per iteration (s): 0.23 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 3.854739E+00 | grad norm: 0.487 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.179 | TFLOPs: 28.49 | +7: iteration 3180/ 37905 | consumed samples: 814080 | consumed tokens: 1667235840 | elapsed time per iteration (s): 0.23 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 3.862492E+00 | grad norm: 0.452 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.087 | TFLOPs: 28.18 | +7: iteration 3190/ 37905 | consumed samples: 816640 | consumed tokens: 1672478720 | elapsed time per iteration (s): 0.23 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 3.842992E+00 | grad norm: 0.591 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.024 | TFLOPs: 28.33 | +7: iteration 3200/ 37905 | consumed samples: 819200 | consumed tokens: 1677721600 | elapsed time per iteration (s): 0.23 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 3.892496E+00 | grad norm: 0.465 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.181 | TFLOPs: 28.69 | +7: iteration 3210/ 37905 | consumed samples: 821760 | consumed tokens: 1682964480 | elapsed time per iteration (s): 0.23 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 3.856644E+00 | grad norm: 0.435 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.699 | TFLOPs: 28.75 | +7: iteration 3220/ 37905 | consumed samples: 824320 | consumed tokens: 1688207360 | elapsed time per iteration (s): 0.23 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 3.861115E+00 | grad norm: 0.404 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.218 | TFLOPs: 28.41 | +7: iteration 3230/ 37905 | consumed samples: 826880 | consumed tokens: 1693450240 | elapsed time per iteration (s): 0.23 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 3.841332E+00 | grad norm: 0.430 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.042 | TFLOPs: 28.66 | +7: iteration 3240/ 37905 | consumed samples: 829440 | consumed tokens: 1698693120 | elapsed time per iteration (s): 0.23 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 3.840074E+00 | grad norm: 0.564 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.088 | TFLOPs: 28.41 | +7: iteration 3250/ 37905 | consumed samples: 832000 | consumed tokens: 1703936000 | elapsed time per iteration (s): 0.23 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 3.831782E+00 | grad norm: 0.591 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.264 | TFLOPs: 28.49 | +7: iteration 3260/ 37905 | consumed samples: 834560 | consumed tokens: 1709178880 | elapsed time per iteration (s): 0.23 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 3.834635E+00 | grad norm: 0.583 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.897 | TFLOPs: 28.22 | +7: iteration 3270/ 37905 | consumed samples: 837120 | consumed tokens: 1714421760 | elapsed time per iteration (s): 0.23 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 3.863186E+00 | grad norm: 0.544 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.475 | TFLOPs: 28.57 | +7: iteration 3280/ 37905 | consumed samples: 839680 | consumed tokens: 1719664640 | elapsed time per iteration (s): 0.23 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 3.845674E+00 | grad norm: 0.456 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.004 | TFLOPs: 28.30 | +7: iteration 3290/ 37905 | consumed samples: 842240 | consumed tokens: 1724907520 | elapsed time per iteration (s): 0.24 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 3.830910E+00 | grad norm: 0.462 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1063.656 | TFLOPs: 27.10 | +7: iteration 3300/ 37905 | consumed samples: 844800 | consumed tokens: 1730150400 | elapsed time per iteration (s): 0.23 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 3.843543E+00 | grad norm: 0.423 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.950 | TFLOPs: 28.63 | +7: iteration 3310/ 37905 | consumed samples: 847360 | consumed tokens: 1735393280 | elapsed time per iteration (s): 0.23 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 3.845898E+00 | grad norm: 0.539 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.094 | TFLOPs: 28.59 | +7: iteration 3320/ 37905 | consumed samples: 849920 | consumed tokens: 1740636160 | elapsed time per iteration (s): 0.23 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 3.824924E+00 | grad norm: 0.462 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.593 | TFLOPs: 28.57 | +7: iteration 3330/ 37905 | consumed samples: 852480 | consumed tokens: 1745879040 | elapsed time per iteration (s): 0.23 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 3.850329E+00 | grad norm: 0.482 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.497 | TFLOPs: 28.44 | +7: iteration 3340/ 37905 | consumed samples: 855040 | consumed tokens: 1751121920 | elapsed time per iteration (s): 0.23 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 3.854673E+00 | grad norm: 0.589 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.674 | TFLOPs: 28.47 | +7: iteration 3350/ 37905 | consumed samples: 857600 | consumed tokens: 1756364800 | elapsed time per iteration (s): 0.23 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 3.832824E+00 | grad norm: 0.470 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.264 | TFLOPs: 28.44 | +7: iteration 3360/ 37905 | consumed samples: 860160 | consumed tokens: 1761607680 | elapsed time per iteration (s): 0.23 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 3.817403E+00 | grad norm: 0.486 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.635 | TFLOPs: 28.62 | +7: iteration 3370/ 37905 | consumed samples: 862720 | consumed tokens: 1766850560 | elapsed time per iteration (s): 0.23 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 3.843597E+00 | grad norm: 0.485 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.955 | TFLOPs: 27.77 | +7: iteration 3380/ 37905 | consumed samples: 865280 | consumed tokens: 1772093440 | elapsed time per iteration (s): 0.24 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 3.841506E+00 | grad norm: 0.466 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1052.712 | TFLOPs: 26.82 | +7: iteration 3390/ 37905 | consumed samples: 867840 | consumed tokens: 1777336320 | elapsed time per iteration (s): 0.23 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 3.840467E+00 | grad norm: 0.436 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.421 | TFLOPs: 28.52 | +7: iteration 3400/ 37905 | consumed samples: 870400 | consumed tokens: 1782579200 | elapsed time per iteration (s): 0.23 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 3.805684E+00 | grad norm: 0.517 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.173 | TFLOPs: 28.54 | +7: iteration 3410/ 37905 | consumed samples: 872960 | consumed tokens: 1787822080 | elapsed time per iteration (s): 0.23 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 3.833569E+00 | grad norm: 0.514 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.563 | TFLOPs: 28.01 | +7: iteration 3420/ 37905 | consumed samples: 875520 | consumed tokens: 1793064960 | elapsed time per iteration (s): 0.23 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 3.798684E+00 | grad norm: 0.481 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.527 | TFLOPs: 28.32 | +7: iteration 3430/ 37905 | consumed samples: 878080 | consumed tokens: 1798307840 | elapsed time per iteration (s): 0.23 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 3.840945E+00 | grad norm: 0.415 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.996 | TFLOPs: 28.25 | +7: iteration 3440/ 37905 | consumed samples: 880640 | consumed tokens: 1803550720 | elapsed time per iteration (s): 0.23 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 3.833053E+00 | grad norm: 0.512 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.227 | TFLOPs: 28.00 | +7: iteration 3450/ 37905 | consumed samples: 883200 | consumed tokens: 1808793600 | elapsed time per iteration (s): 0.23 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 3.858609E+00 | grad norm: 0.551 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.813 | TFLOPs: 28.32 | +7: iteration 3460/ 37905 | consumed samples: 885760 | consumed tokens: 1814036480 | elapsed time per iteration (s): 0.23 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 3.824007E+00 | grad norm: 0.535 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.968 | TFLOPs: 27.87 | +7: iteration 3470/ 37905 | consumed samples: 888320 | consumed tokens: 1819279360 | elapsed time per iteration (s): 0.23 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 3.822087E+00 | grad norm: 0.521 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.468 | TFLOPs: 28.47 | +7: iteration 3480/ 37905 | consumed samples: 890880 | consumed tokens: 1824522240 | elapsed time per iteration (s): 0.24 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 3.833585E+00 | grad norm: 0.437 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.495 | TFLOPs: 27.68 | +7: iteration 3490/ 37905 | consumed samples: 893440 | consumed tokens: 1829765120 | elapsed time per iteration (s): 0.23 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 3.795213E+00 | grad norm: 0.558 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.097 | TFLOPs: 28.15 | +7: iteration 3500/ 37905 | consumed samples: 896000 | consumed tokens: 1835008000 | elapsed time per iteration (s): 0.23 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 3.848930E+00 | grad norm: 0.491 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.299 | TFLOPs: 28.36 | +7: iteration 3510/ 37905 | consumed samples: 898560 | consumed tokens: 1840250880 | elapsed time per iteration (s): 0.23 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 3.789457E+00 | grad norm: 0.426 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.393 | TFLOPs: 28.64 | +7: iteration 3520/ 37905 | consumed samples: 901120 | consumed tokens: 1845493760 | elapsed time per iteration (s): 0.23 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 3.818383E+00 | grad norm: 0.455 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.585 | TFLOPs: 28.67 | +7: iteration 3530/ 37905 | consumed samples: 903680 | consumed tokens: 1850736640 | elapsed time per iteration (s): 0.23 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 3.809702E+00 | grad norm: 0.442 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.714 | TFLOPs: 28.07 | +7: iteration 3540/ 37905 | consumed samples: 906240 | consumed tokens: 1855979520 | elapsed time per iteration (s): 0.23 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 3.826395E+00 | grad norm: 0.414 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.389 | TFLOPs: 27.91 | +7: iteration 3550/ 37905 | consumed samples: 908800 | consumed tokens: 1861222400 | elapsed time per iteration (s): 0.23 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 3.823319E+00 | grad norm: 0.528 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.789 | TFLOPs: 28.58 | +7: iteration 3560/ 37905 | consumed samples: 911360 | consumed tokens: 1866465280 | elapsed time per iteration (s): 0.23 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 3.792324E+00 | grad norm: 0.459 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.364 | TFLOPs: 28.47 | +7: iteration 3570/ 37905 | consumed samples: 913920 | consumed tokens: 1871708160 | elapsed time per iteration (s): 0.23 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 3.835165E+00 | grad norm: 0.436 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.039 | TFLOPs: 27.90 | +7: iteration 3580/ 37905 | consumed samples: 916480 | consumed tokens: 1876951040 | elapsed time per iteration (s): 0.23 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 3.808037E+00 | grad norm: 0.557 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.057 | TFLOPs: 28.30 | +7: iteration 3590/ 37905 | consumed samples: 919040 | consumed tokens: 1882193920 | elapsed time per iteration (s): 0.23 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 3.806948E+00 | grad norm: 0.462 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.003 | TFLOPs: 28.63 | +7: iteration 3600/ 37905 | consumed samples: 921600 | consumed tokens: 1887436800 | elapsed time per iteration (s): 0.23 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 3.814557E+00 | grad norm: 0.480 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.207 | TFLOPs: 28.44 | +7: iteration 3610/ 37905 | consumed samples: 924160 | consumed tokens: 1892679680 | elapsed time per iteration (s): 0.23 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 3.802034E+00 | grad norm: 0.431 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.529 | TFLOPs: 28.01 | +7: iteration 3620/ 37905 | consumed samples: 926720 | consumed tokens: 1897922560 | elapsed time per iteration (s): 0.23 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 3.804056E+00 | grad norm: 0.557 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.939 | TFLOPs: 28.40 | +7: iteration 3630/ 37905 | consumed samples: 929280 | consumed tokens: 1903165440 | elapsed time per iteration (s): 0.23 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 3.820612E+00 | grad norm: 0.455 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.584 | TFLOPs: 27.99 | +7: iteration 3640/ 37905 | consumed samples: 931840 | consumed tokens: 1908408320 | elapsed time per iteration (s): 0.23 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 3.787552E+00 | grad norm: 0.468 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.534 | TFLOPs: 28.60 | +7: iteration 3650/ 37905 | consumed samples: 934400 | consumed tokens: 1913651200 | elapsed time per iteration (s): 0.23 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 3.781609E+00 | grad norm: 0.424 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.966 | TFLOPs: 28.56 | +7: iteration 3660/ 37905 | consumed samples: 936960 | consumed tokens: 1918894080 | elapsed time per iteration (s): 0.23 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 3.815807E+00 | grad norm: 0.454 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.021 | TFLOPs: 28.38 | +7: iteration 3670/ 37905 | consumed samples: 939520 | consumed tokens: 1924136960 | elapsed time per iteration (s): 0.23 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 3.812582E+00 | grad norm: 0.520 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.432 | TFLOPs: 28.21 | +7: iteration 3680/ 37905 | consumed samples: 942080 | consumed tokens: 1929379840 | elapsed time per iteration (s): 0.23 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 3.779866E+00 | grad norm: 0.464 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.323 | TFLOPs: 28.06 | +7: iteration 3690/ 37905 | consumed samples: 944640 | consumed tokens: 1934622720 | elapsed time per iteration (s): 0.23 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 3.793485E+00 | grad norm: 0.570 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.759 | TFLOPs: 28.14 | +7: iteration 3700/ 37905 | consumed samples: 947200 | consumed tokens: 1939865600 | elapsed time per iteration (s): 0.23 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 3.809052E+00 | grad norm: 0.555 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.518 | TFLOPs: 28.42 | +7: iteration 3710/ 37905 | consumed samples: 949760 | consumed tokens: 1945108480 | elapsed time per iteration (s): 0.23 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 3.813084E+00 | grad norm: 0.615 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.503 | TFLOPs: 28.49 | +7: iteration 3720/ 37905 | consumed samples: 952320 | consumed tokens: 1950351360 | elapsed time per iteration (s): 0.23 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 3.811708E+00 | grad norm: 0.533 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.128 | TFLOPs: 28.38 | +7: iteration 3730/ 37905 | consumed samples: 954880 | consumed tokens: 1955594240 | elapsed time per iteration (s): 0.24 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 3.815751E+00 | grad norm: 0.426 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1065.851 | TFLOPs: 27.15 | +7: iteration 3740/ 37905 | consumed samples: 957440 | consumed tokens: 1960837120 | elapsed time per iteration (s): 0.23 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 3.776617E+00 | grad norm: 0.459 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.586 | TFLOPs: 28.19 | +7: iteration 3750/ 37905 | consumed samples: 960000 | consumed tokens: 1966080000 | elapsed time per iteration (s): 0.23 | learning rate: 1.964E-04 | global batch size: 256 | lm loss: 3.781873E+00 | grad norm: 0.612 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.793 | TFLOPs: 28.73 | +7: iteration 3760/ 37905 | consumed samples: 962560 | consumed tokens: 1971322880 | elapsed time per iteration (s): 0.23 | learning rate: 1.964E-04 | global batch size: 256 | lm loss: 3.789621E+00 | grad norm: 0.470 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.574 | TFLOPs: 27.88 | +7: iteration 3770/ 37905 | consumed samples: 965120 | consumed tokens: 1976565760 | elapsed time per iteration (s): 0.23 | learning rate: 1.964E-04 | global batch size: 256 | lm loss: 3.805233E+00 | grad norm: 0.446 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.072 | TFLOPs: 28.56 | +7: iteration 3780/ 37905 | consumed samples: 967680 | consumed tokens: 1981808640 | elapsed time per iteration (s): 0.23 | learning rate: 1.964E-04 | global batch size: 256 | lm loss: 3.801377E+00 | grad norm: 0.453 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.478 | TFLOPs: 28.39 | +7: iteration 3790/ 37905 | consumed samples: 970240 | consumed tokens: 1987051520 | elapsed time per iteration (s): 0.23 | learning rate: 1.964E-04 | global batch size: 256 | lm loss: 3.769928E+00 | grad norm: 0.504 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.820 | TFLOPs: 27.92 | +7: iteration 3800/ 37905 | consumed samples: 972800 | consumed tokens: 1992294400 | elapsed time per iteration (s): 0.23 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 3.800621E+00 | grad norm: 0.500 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.580 | TFLOPs: 28.32 | +7: iteration 3810/ 37905 | consumed samples: 975360 | consumed tokens: 1997537280 | elapsed time per iteration (s): 0.23 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 3.792316E+00 | grad norm: 0.460 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.976 | TFLOPs: 28.20 | +7: iteration 3820/ 37905 | consumed samples: 977920 | consumed tokens: 2002780160 | elapsed time per iteration (s): 0.24 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 3.798325E+00 | grad norm: 0.465 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.804 | TFLOPs: 27.66 | +7: iteration 3830/ 37905 | consumed samples: 980480 | consumed tokens: 2008023040 | elapsed time per iteration (s): 0.23 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 3.793066E+00 | grad norm: 0.397 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.049 | TFLOPs: 28.30 | +7: iteration 3840/ 37905 | consumed samples: 983040 | consumed tokens: 2013265920 | elapsed time per iteration (s): 0.23 | learning rate: 1.962E-04 | global batch size: 256 | lm loss: 3.795450E+00 | grad norm: 0.475 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.854 | TFLOPs: 28.15 | +7: iteration 3850/ 37905 | consumed samples: 985600 | consumed tokens: 2018508800 | elapsed time per iteration (s): 0.23 | learning rate: 1.962E-04 | global batch size: 256 | lm loss: 3.809592E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.204 | TFLOPs: 28.72 | +7: iteration 3860/ 37905 | consumed samples: 988160 | consumed tokens: 2023751680 | elapsed time per iteration (s): 0.23 | learning rate: 1.962E-04 | global batch size: 256 | lm loss: 3.770853E+00 | grad norm: 0.576 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.072 | TFLOPs: 28.58 | +7: iteration 3870/ 37905 | consumed samples: 990720 | consumed tokens: 2028994560 | elapsed time per iteration (s): 0.23 | learning rate: 1.962E-04 | global batch size: 256 | lm loss: 3.782322E+00 | grad norm: 0.551 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.725 | TFLOPs: 28.45 | +7: iteration 3880/ 37905 | consumed samples: 993280 | consumed tokens: 2034237440 | elapsed time per iteration (s): 0.23 | learning rate: 1.962E-04 | global batch size: 256 | lm loss: 3.769190E+00 | grad norm: 0.441 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.109 | TFLOPs: 28.25 | +7: iteration 3890/ 37905 | consumed samples: 995840 | consumed tokens: 2039480320 | elapsed time per iteration (s): 0.23 | learning rate: 1.961E-04 | global batch size: 256 | lm loss: 3.774286E+00 | grad norm: 0.463 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.748 | TFLOPs: 28.12 | +7: iteration 3900/ 37905 | consumed samples: 998400 | consumed tokens: 2044723200 | elapsed time per iteration (s): 0.23 | learning rate: 1.961E-04 | global batch size: 256 | lm loss: 3.766430E+00 | grad norm: 0.471 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.763 | TFLOPs: 28.30 | +7: iteration 3910/ 37905 | consumed samples: 1000960 | consumed tokens: 2049966080 | elapsed time per iteration (s): 0.24 | learning rate: 1.961E-04 | global batch size: 256 | lm loss: 3.758365E+00 | grad norm: 0.496 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.815 | TFLOPs: 27.69 | +7: iteration 3920/ 37905 | consumed samples: 1003520 | consumed tokens: 2055208960 | elapsed time per iteration (s): 0.23 | learning rate: 1.961E-04 | global batch size: 256 | lm loss: 3.767736E+00 | grad norm: 0.476 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.803 | TFLOPs: 28.35 | +7: iteration 3930/ 37905 | consumed samples: 1006080 | consumed tokens: 2060451840 | elapsed time per iteration (s): 0.23 | learning rate: 1.961E-04 | global batch size: 256 | lm loss: 3.772729E+00 | grad norm: 0.411 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.702 | TFLOPs: 28.50 | +7: iteration 3940/ 37905 | consumed samples: 1008640 | consumed tokens: 2065694720 | elapsed time per iteration (s): 0.24 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 3.778680E+00 | grad norm: 0.559 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1071.669 | TFLOPs: 27.30 | +7: iteration 3950/ 37905 | consumed samples: 1011200 | consumed tokens: 2070937600 | elapsed time per iteration (s): 0.23 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 3.780263E+00 | grad norm: 0.522 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.209 | TFLOPs: 28.33 | +7: iteration 3960/ 37905 | consumed samples: 1013760 | consumed tokens: 2076180480 | elapsed time per iteration (s): 0.23 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 3.753223E+00 | grad norm: 0.483 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.232 | TFLOPs: 28.44 | +7: iteration 3970/ 37905 | consumed samples: 1016320 | consumed tokens: 2081423360 | elapsed time per iteration (s): 0.23 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 3.787041E+00 | grad norm: 0.594 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1131.088 | TFLOPs: 28.81 | +7: iteration 3980/ 37905 | consumed samples: 1018880 | consumed tokens: 2086666240 | elapsed time per iteration (s): 0.23 | learning rate: 1.959E-04 | global batch size: 256 | lm loss: 3.775772E+00 | grad norm: 0.413 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.622 | TFLOPs: 28.60 | +7: iteration 3990/ 37905 | consumed samples: 1021440 | consumed tokens: 2091909120 | elapsed time per iteration (s): 0.23 | learning rate: 1.959E-04 | global batch size: 256 | lm loss: 3.772100E+00 | grad norm: 0.428 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.870 | TFLOPs: 28.68 | +0: [2022-11-29 17:11:47,580] [INFO] [logging.py:68:log_dist] [Rank 0] step=4000, skipped=0, lr=[0.0001958964133300005, 0.0001958964133300005, 0.0001958964133300005], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 4000/ 37905 | consumed samples: 1024000 | consumed tokens: 2097152000 | elapsed time per iteration (s): 0.23 | learning rate: 1.959E-04 | global batch size: 256 | lm loss: 3.764545E+00 | grad norm: 0.441 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1131.393 | TFLOPs: 28.82 | +0: steps: 4000 loss: 3.7743 iter time (s): 0.230 samples/sec: 1115.238 +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 4000 | lm loss value: 3.594958E+00 | lm loss PPL: 3.641418E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 4000 to checkpoints_83moscar +0: [2022-11-29 17:11:47,677] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step4000 is begin to save! +0: [2022-11-29 17:11:47,681] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:11:47,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:11:47,753] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:11:47,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:11:47,766] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:11:47,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:11:47,777] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:11:47,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:11:47,789] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:11:47,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:11:47,800] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:11:47,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:11:47,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:11:47,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:11:47,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:11:47,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:11:47,834] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:11:47,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:11:47,846] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:11:47,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:11:47,857] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:11:47,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:11:47,868] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:11:47,869] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:11:47,870] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step4000/mp_rank_00_model_states.pt +0: [2022-11-29 17:11:47,870] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:11:47,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:11:47,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:11:47,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:11:47,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:11:47,907] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:11:47,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:11:47,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:11:47,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:11:47,908] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:11:47,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:11:47,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:11:47,908] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:11:47,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:11:47,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:11:47,908] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:11:47,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:11:47,908] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:11:47,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:11:47,909] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:11:47,909] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:11:47,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:11:47,909] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:11:47,909] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:11:47,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:11:47,909] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +1: [2022-11-29 17:11:47,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:11:47,909] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:11:47,909] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:11:47,909] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:11:47,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:11:47,910] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:11:47,910] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:11:47,910] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:11:47,910] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:11:47,910] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:11:47,910] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:11:47,910] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:11:47,910] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:11:47,910] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:11:47,910] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +6: [2022-11-29 17:11:47,910] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:11:47,910] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:11:47,910] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:11:47,910] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +0: [2022-11-29 17:11:47,910] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +6: [2022-11-29 17:11:47,910] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:11:47,910] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:11:47,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:11:47,911] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:11:47,911] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:11:47,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:11:47,911] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +4: [2022-11-29 17:11:47,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:11:47,911] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:11:47,911] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:11:47,911] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:11:47,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:11:47,911] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:11:47,911] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:11:47,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:11:47,911] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:11:47,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:11:47,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:11:47,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:11:47,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:11:47,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:11:47,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:11:47,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:11:47,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:11:47,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:11:47,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +5: [2022-11-29 17:11:47,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:11:47,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:11:47,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:11:47,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:11:47,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +3: [2022-11-29 17:11:47,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:11:47,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +5: [2022-11-29 17:11:47,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:11:47,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:11:47,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:11:47,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:11:47,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:11:47,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:11:47,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +1: [2022-11-29 17:11:47,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:11:47,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:11:47,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:11:47,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:11:47,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:11:47,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:11:47,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:11:47,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:11:47,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:11:47,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:11:47,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:11:47,914] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:11:47,914] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:11:47,914] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:11:47,914] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:11:47,914] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:11:47,914] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:11:47,914] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +6: [2022-11-29 17:11:47,914] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:11:47,914] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:11:47,914] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:11:47,914] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +4: [2022-11-29 17:11:47,914] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +6: [2022-11-29 17:11:47,914] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:11:47,914] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:11:47,914] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:11:47,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +6: [2022-11-29 17:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:11:47,915] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:11:47,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:11:47,915] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:11:47,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:11:47,915] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:11:47,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:11:47,915] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:11:47,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:11:47,915] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:11:47,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +1: [2022-11-29 17:11:47,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +5: [2022-11-29 17:11:47,915] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:11:47,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +2: [2022-11-29 17:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +0: [2022-11-29 17:11:47,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:11:47,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:11:47,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:11:47,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:11:47,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:11:47,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:11:47,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:11:47,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:11:47,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:11:47,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:11:47,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:11:47,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:11:47,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:11:47,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:11:47,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:11:47,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:11:47,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:11:47,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:11:47,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:11:47,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +7: [2022-11-29 17:11:47,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:11:47,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-29 17:11:47,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:11:47,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-29 17:11:47,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:11:47,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +5: [2022-11-29 17:11:47,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:11:47,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:11:47,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:11:47,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-29 17:11:47,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:11:47,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:11:47,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-29 17:11:47,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:11:47,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:11:47,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:11:47,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-29 17:11:47,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +4: [2022-11-29 17:11:47,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:11:47,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:11:47,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:11:47,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:11:47,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:11:47,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:11:47,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-29 17:11:47,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:11:47,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:11:47,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:11:47,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:11:47,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:11:47,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-29 17:11:47,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:11:47,919] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:11:47,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-29 17:11:47,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:11:47,920] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:11:47,920] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: successfully saved checkpoint at iteration 4000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 246.50 +7: iteration 4010/ 37905 | consumed samples: 1026560 | consumed tokens: 2102394880 | elapsed time per iteration (s): 0.26 | learning rate: 1.959E-04 | global batch size: 256 | lm loss: 3.771329E+00 | grad norm: 0.530 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 974.529 | TFLOPs: 24.83 | +7: iteration 4020/ 37905 | consumed samples: 1029120 | consumed tokens: 2107637760 | elapsed time per iteration (s): 0.25 | learning rate: 1.959E-04 | global batch size: 256 | lm loss: 3.786481E+00 | grad norm: 0.512 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1039.184 | TFLOPs: 26.47 | +7: iteration 4030/ 37905 | consumed samples: 1031680 | consumed tokens: 2112880640 | elapsed time per iteration (s): 0.25 | learning rate: 1.958E-04 | global batch size: 256 | lm loss: 3.776200E+00 | grad norm: 0.464 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1033.972 | TFLOPs: 26.34 | +7: iteration 4040/ 37905 | consumed samples: 1034240 | consumed tokens: 2118123520 | elapsed time per iteration (s): 0.23 | learning rate: 1.958E-04 | global batch size: 256 | lm loss: 3.780465E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.552 | TFLOPs: 28.70 | +7: iteration 4050/ 37905 | consumed samples: 1036800 | consumed tokens: 2123366400 | elapsed time per iteration (s): 0.23 | learning rate: 1.958E-04 | global batch size: 256 | lm loss: 3.771509E+00 | grad norm: 0.456 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.557 | TFLOPs: 28.62 | +7: iteration 4060/ 37905 | consumed samples: 1039360 | consumed tokens: 2128609280 | elapsed time per iteration (s): 0.23 | learning rate: 1.958E-04 | global batch size: 256 | lm loss: 3.764115E+00 | grad norm: 0.433 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.525 | TFLOPs: 28.52 | +7: iteration 4070/ 37905 | consumed samples: 1041920 | consumed tokens: 2133852160 | elapsed time per iteration (s): 0.23 | learning rate: 1.957E-04 | global batch size: 256 | lm loss: 3.754410E+00 | grad norm: 0.451 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.333 | TFLOPs: 28.64 | +7: iteration 4080/ 37905 | consumed samples: 1044480 | consumed tokens: 2139095040 | elapsed time per iteration (s): 0.23 | learning rate: 1.957E-04 | global batch size: 256 | lm loss: 3.773170E+00 | grad norm: 0.483 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.477 | TFLOPs: 28.44 | +7: iteration 4090/ 37905 | consumed samples: 1047040 | consumed tokens: 2144337920 | elapsed time per iteration (s): 0.23 | learning rate: 1.957E-04 | global batch size: 256 | lm loss: 3.787859E+00 | grad norm: 0.381 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.080 | TFLOPs: 28.25 | +7: iteration 4100/ 37905 | consumed samples: 1049600 | consumed tokens: 2149580800 | elapsed time per iteration (s): 0.23 | learning rate: 1.957E-04 | global batch size: 256 | lm loss: 3.759182E+00 | grad norm: 0.386 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.689 | TFLOPs: 28.17 | +7: iteration 4110/ 37905 | consumed samples: 1052160 | consumed tokens: 2154823680 | elapsed time per iteration (s): 0.23 | learning rate: 1.956E-04 | global batch size: 256 | lm loss: 3.761290E+00 | grad norm: 0.483 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.694 | TFLOPs: 28.50 | +7: iteration 4120/ 37905 | consumed samples: 1054720 | consumed tokens: 2160066560 | elapsed time per iteration (s): 0.23 | learning rate: 1.956E-04 | global batch size: 256 | lm loss: 3.740226E+00 | grad norm: 0.406 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.429 | TFLOPs: 28.57 | +7: iteration 4130/ 37905 | consumed samples: 1057280 | consumed tokens: 2165309440 | elapsed time per iteration (s): 0.23 | learning rate: 1.956E-04 | global batch size: 256 | lm loss: 3.769941E+00 | grad norm: 0.446 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.548 | TFLOPs: 27.99 | +7: iteration 4140/ 37905 | consumed samples: 1059840 | consumed tokens: 2170552320 | elapsed time per iteration (s): 0.23 | learning rate: 1.956E-04 | global batch size: 256 | lm loss: 3.748659E+00 | grad norm: 0.408 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.302 | TFLOPs: 28.46 | +7: iteration 4150/ 37905 | consumed samples: 1062400 | consumed tokens: 2175795200 | elapsed time per iteration (s): 0.23 | learning rate: 1.956E-04 | global batch size: 256 | lm loss: 3.765118E+00 | grad norm: 0.421 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.331 | TFLOPs: 28.59 | +7: iteration 4160/ 37905 | consumed samples: 1064960 | consumed tokens: 2181038080 | elapsed time per iteration (s): 0.23 | learning rate: 1.955E-04 | global batch size: 256 | lm loss: 3.757084E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.481 | TFLOPs: 28.54 | +7: iteration 4170/ 37905 | consumed samples: 1067520 | consumed tokens: 2186280960 | elapsed time per iteration (s): 0.23 | learning rate: 1.955E-04 | global batch size: 256 | lm loss: 3.733456E+00 | grad norm: 0.382 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1131.340 | TFLOPs: 28.82 | +7: iteration 4180/ 37905 | consumed samples: 1070080 | consumed tokens: 2191523840 | elapsed time per iteration (s): 0.23 | learning rate: 1.955E-04 | global batch size: 256 | lm loss: 3.736546E+00 | grad norm: 0.425 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1131.093 | TFLOPs: 28.81 | +7: iteration 4190/ 37905 | consumed samples: 1072640 | consumed tokens: 2196766720 | elapsed time per iteration (s): 0.24 | learning rate: 1.955E-04 | global batch size: 256 | lm loss: 3.746136E+00 | grad norm: 0.502 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1059.738 | TFLOPs: 27.00 | +7: iteration 4200/ 37905 | consumed samples: 1075200 | consumed tokens: 2202009600 | elapsed time per iteration (s): 0.23 | learning rate: 1.954E-04 | global batch size: 256 | lm loss: 3.750994E+00 | grad norm: 0.487 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.791 | TFLOPs: 28.71 | +7: iteration 4210/ 37905 | consumed samples: 1077760 | consumed tokens: 2207252480 | elapsed time per iteration (s): 0.23 | learning rate: 1.954E-04 | global batch size: 256 | lm loss: 3.767012E+00 | grad norm: 0.463 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.806 | TFLOPs: 28.37 | +7: iteration 4220/ 37905 | consumed samples: 1080320 | consumed tokens: 2212495360 | elapsed time per iteration (s): 0.23 | learning rate: 1.954E-04 | global batch size: 256 | lm loss: 3.765630E+00 | grad norm: 0.448 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.512 | TFLOPs: 28.52 | +7: iteration 4230/ 37905 | consumed samples: 1082880 | consumed tokens: 2217738240 | elapsed time per iteration (s): 0.23 | learning rate: 1.954E-04 | global batch size: 256 | lm loss: 3.741574E+00 | grad norm: 0.411 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.949 | TFLOPs: 28.17 | +7: iteration 4240/ 37905 | consumed samples: 1085440 | consumed tokens: 2222981120 | elapsed time per iteration (s): 0.23 | learning rate: 1.953E-04 | global batch size: 256 | lm loss: 3.782771E+00 | grad norm: 0.529 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.235 | TFLOPs: 28.61 | +7: iteration 4250/ 37905 | consumed samples: 1088000 | consumed tokens: 2228224000 | elapsed time per iteration (s): 0.23 | learning rate: 1.953E-04 | global batch size: 256 | lm loss: 3.716893E+00 | grad norm: 0.501 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.566 | TFLOPs: 28.62 | +7: iteration 4260/ 37905 | consumed samples: 1090560 | consumed tokens: 2233466880 | elapsed time per iteration (s): 0.23 | learning rate: 1.953E-04 | global batch size: 256 | lm loss: 3.789644E+00 | grad norm: 0.411 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.061 | TFLOPs: 28.69 | +7: iteration 4270/ 37905 | consumed samples: 1093120 | consumed tokens: 2238709760 | elapsed time per iteration (s): 0.23 | learning rate: 1.953E-04 | global batch size: 256 | lm loss: 3.760705E+00 | grad norm: 0.424 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.810 | TFLOPs: 28.35 | +7: iteration 4280/ 37905 | consumed samples: 1095680 | consumed tokens: 2243952640 | elapsed time per iteration (s): 0.24 | learning rate: 1.952E-04 | global batch size: 256 | lm loss: 3.755459E+00 | grad norm: 0.427 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1064.446 | TFLOPs: 27.12 | +7: iteration 4290/ 37905 | consumed samples: 1098240 | consumed tokens: 2249195520 | elapsed time per iteration (s): 0.23 | learning rate: 1.952E-04 | global batch size: 256 | lm loss: 3.750102E+00 | grad norm: 0.600 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.104 | TFLOPs: 28.48 | +7: iteration 4300/ 37905 | consumed samples: 1100800 | consumed tokens: 2254438400 | elapsed time per iteration (s): 0.23 | learning rate: 1.952E-04 | global batch size: 256 | lm loss: 3.711261E+00 | grad norm: 0.534 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.560 | TFLOPs: 28.57 | +7: iteration 4310/ 37905 | consumed samples: 1103360 | consumed tokens: 2259681280 | elapsed time per iteration (s): 0.23 | learning rate: 1.952E-04 | global batch size: 256 | lm loss: 3.741757E+00 | grad norm: 0.435 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.657 | TFLOPs: 28.55 | +7: iteration 4320/ 37905 | consumed samples: 1105920 | consumed tokens: 2264924160 | elapsed time per iteration (s): 0.23 | learning rate: 1.951E-04 | global batch size: 256 | lm loss: 3.718593E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.256 | TFLOPs: 28.54 | +7: iteration 4330/ 37905 | consumed samples: 1108480 | consumed tokens: 2270167040 | elapsed time per iteration (s): 0.23 | learning rate: 1.951E-04 | global batch size: 256 | lm loss: 3.738505E+00 | grad norm: 0.433 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.252 | TFLOPs: 28.36 | +7: iteration 4340/ 37905 | consumed samples: 1111040 | consumed tokens: 2275409920 | elapsed time per iteration (s): 0.23 | learning rate: 1.951E-04 | global batch size: 256 | lm loss: 3.777608E+00 | grad norm: 0.499 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.449 | TFLOPs: 28.31 | +7: iteration 4350/ 37905 | consumed samples: 1113600 | consumed tokens: 2280652800 | elapsed time per iteration (s): 0.23 | learning rate: 1.951E-04 | global batch size: 256 | lm loss: 3.711762E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.422 | TFLOPs: 28.24 | +7: iteration 4360/ 37905 | consumed samples: 1116160 | consumed tokens: 2285895680 | elapsed time per iteration (s): 0.23 | learning rate: 1.950E-04 | global batch size: 256 | lm loss: 3.721273E+00 | grad norm: 0.412 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.856 | TFLOPs: 28.73 | +7: iteration 4370/ 37905 | consumed samples: 1118720 | consumed tokens: 2291138560 | elapsed time per iteration (s): 0.23 | learning rate: 1.950E-04 | global batch size: 256 | lm loss: 3.749765E+00 | grad norm: 0.475 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.415 | TFLOPs: 28.72 | +7: iteration 4380/ 37905 | consumed samples: 1121280 | consumed tokens: 2296381440 | elapsed time per iteration (s): 0.25 | learning rate: 1.950E-04 | global batch size: 256 | lm loss: 3.735109E+00 | grad norm: 0.435 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1031.094 | TFLOPs: 26.27 | +7: iteration 4390/ 37905 | consumed samples: 1123840 | consumed tokens: 2301624320 | elapsed time per iteration (s): 0.23 | learning rate: 1.950E-04 | global batch size: 256 | lm loss: 3.731770E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.524 | TFLOPs: 28.04 | +7: iteration 4400/ 37905 | consumed samples: 1126400 | consumed tokens: 2306867200 | elapsed time per iteration (s): 0.23 | learning rate: 1.949E-04 | global batch size: 256 | lm loss: 3.740365E+00 | grad norm: 0.394 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.188 | TFLOPs: 28.31 | +7: iteration 4410/ 37905 | consumed samples: 1128960 | consumed tokens: 2312110080 | elapsed time per iteration (s): 0.23 | learning rate: 1.949E-04 | global batch size: 256 | lm loss: 3.724787E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.754 | TFLOPs: 28.60 | +7: iteration 4420/ 37905 | consumed samples: 1131520 | consumed tokens: 2317352960 | elapsed time per iteration (s): 0.23 | learning rate: 1.949E-04 | global batch size: 256 | lm loss: 3.737136E+00 | grad norm: 0.584 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.162 | TFLOPs: 28.59 | +7: iteration 4430/ 37905 | consumed samples: 1134080 | consumed tokens: 2322595840 | elapsed time per iteration (s): 0.23 | learning rate: 1.949E-04 | global batch size: 256 | lm loss: 3.738386E+00 | grad norm: 0.444 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.319 | TFLOPs: 28.46 | +7: iteration 4440/ 37905 | consumed samples: 1136640 | consumed tokens: 2327838720 | elapsed time per iteration (s): 0.23 | learning rate: 1.948E-04 | global batch size: 256 | lm loss: 3.712022E+00 | grad norm: 0.383 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.689 | TFLOPs: 28.60 | +7: iteration 4450/ 37905 | consumed samples: 1139200 | consumed tokens: 2333081600 | elapsed time per iteration (s): 0.23 | learning rate: 1.948E-04 | global batch size: 256 | lm loss: 3.729500E+00 | grad norm: 0.479 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.568 | TFLOPs: 28.29 | +7: iteration 4460/ 37905 | consumed samples: 1141760 | consumed tokens: 2338324480 | elapsed time per iteration (s): 0.23 | learning rate: 1.948E-04 | global batch size: 256 | lm loss: 3.729950E+00 | grad norm: 0.425 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.777 | TFLOPs: 28.14 | +7: iteration 4470/ 37905 | consumed samples: 1144320 | consumed tokens: 2343567360 | elapsed time per iteration (s): 0.23 | learning rate: 1.948E-04 | global batch size: 256 | lm loss: 3.712799E+00 | grad norm: 0.516 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.476 | TFLOPs: 28.42 | +7: iteration 4480/ 37905 | consumed samples: 1146880 | consumed tokens: 2348810240 | elapsed time per iteration (s): 0.23 | learning rate: 1.947E-04 | global batch size: 256 | lm loss: 3.743010E+00 | grad norm: 0.403 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.260 | TFLOPs: 28.08 | +7: iteration 4490/ 37905 | consumed samples: 1149440 | consumed tokens: 2354053120 | elapsed time per iteration (s): 0.23 | learning rate: 1.947E-04 | global batch size: 256 | lm loss: 3.733949E+00 | grad norm: 0.503 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.173 | TFLOPs: 28.61 | +7: iteration 4500/ 37905 | consumed samples: 1152000 | consumed tokens: 2359296000 | elapsed time per iteration (s): 0.23 | learning rate: 1.947E-04 | global batch size: 256 | lm loss: 3.717571E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.415 | TFLOPs: 28.59 | +7: iteration 4510/ 37905 | consumed samples: 1154560 | consumed tokens: 2364538880 | elapsed time per iteration (s): 0.23 | learning rate: 1.947E-04 | global batch size: 256 | lm loss: 3.743821E+00 | grad norm: 0.436 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.150 | TFLOPs: 28.69 | +7: iteration 4520/ 37905 | consumed samples: 1157120 | consumed tokens: 2369781760 | elapsed time per iteration (s): 0.23 | learning rate: 1.946E-04 | global batch size: 256 | lm loss: 3.724445E+00 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.056 | TFLOPs: 28.48 | +7: iteration 4530/ 37905 | consumed samples: 1159680 | consumed tokens: 2375024640 | elapsed time per iteration (s): 0.23 | learning rate: 1.946E-04 | global batch size: 256 | lm loss: 3.726280E+00 | grad norm: 0.426 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.086 | TFLOPs: 28.46 | +7: iteration 4540/ 37905 | consumed samples: 1162240 | consumed tokens: 2380267520 | elapsed time per iteration (s): 0.23 | learning rate: 1.946E-04 | global batch size: 256 | lm loss: 3.719298E+00 | grad norm: 0.426 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.123 | TFLOPs: 28.71 | +7: iteration 4550/ 37905 | consumed samples: 1164800 | consumed tokens: 2385510400 | elapsed time per iteration (s): 0.23 | learning rate: 1.946E-04 | global batch size: 256 | lm loss: 3.721608E+00 | grad norm: 0.452 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.727 | TFLOPs: 28.47 | +7: iteration 4560/ 37905 | consumed samples: 1167360 | consumed tokens: 2390753280 | elapsed time per iteration (s): 0.23 | learning rate: 1.945E-04 | global batch size: 256 | lm loss: 3.711018E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.652 | TFLOPs: 28.45 | +7: iteration 4570/ 37905 | consumed samples: 1169920 | consumed tokens: 2395996160 | elapsed time per iteration (s): 0.23 | learning rate: 1.945E-04 | global batch size: 256 | lm loss: 3.725508E+00 | grad norm: 0.399 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.659 | TFLOPs: 28.47 | +7: iteration 4580/ 37905 | consumed samples: 1172480 | consumed tokens: 2401239040 | elapsed time per iteration (s): 0.23 | learning rate: 1.945E-04 | global batch size: 256 | lm loss: 3.718334E+00 | grad norm: 0.495 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.317 | TFLOPs: 28.23 | +7: iteration 4590/ 37905 | consumed samples: 1175040 | consumed tokens: 2406481920 | elapsed time per iteration (s): 0.24 | learning rate: 1.945E-04 | global batch size: 256 | lm loss: 3.715667E+00 | grad norm: 0.409 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1045.490 | TFLOPs: 26.63 | +7: iteration 4600/ 37905 | consumed samples: 1177600 | consumed tokens: 2411724800 | elapsed time per iteration (s): 0.23 | learning rate: 1.944E-04 | global batch size: 256 | lm loss: 3.726079E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.472 | TFLOPs: 28.77 | +7: iteration 4610/ 37905 | consumed samples: 1180160 | consumed tokens: 2416967680 | elapsed time per iteration (s): 0.23 | learning rate: 1.944E-04 | global batch size: 256 | lm loss: 3.713123E+00 | grad norm: 0.436 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.989 | TFLOPs: 28.38 | +7: iteration 4620/ 37905 | consumed samples: 1182720 | consumed tokens: 2422210560 | elapsed time per iteration (s): 0.23 | learning rate: 1.944E-04 | global batch size: 256 | lm loss: 3.704851E+00 | grad norm: 0.482 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.987 | TFLOPs: 28.74 | +7: iteration 4630/ 37905 | consumed samples: 1185280 | consumed tokens: 2427453440 | elapsed time per iteration (s): 0.23 | learning rate: 1.944E-04 | global batch size: 256 | lm loss: 3.724205E+00 | grad norm: 0.408 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.079 | TFLOPs: 28.56 | +7: iteration 4640/ 37905 | consumed samples: 1187840 | consumed tokens: 2432696320 | elapsed time per iteration (s): 0.23 | learning rate: 1.943E-04 | global batch size: 256 | lm loss: 3.722931E+00 | grad norm: 0.423 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.164 | TFLOPs: 28.79 | +7: iteration 4650/ 37905 | consumed samples: 1190400 | consumed tokens: 2437939200 | elapsed time per iteration (s): 0.23 | learning rate: 1.943E-04 | global batch size: 256 | lm loss: 3.709436E+00 | grad norm: 0.445 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.732 | TFLOPs: 28.78 | +7: iteration 4660/ 37905 | consumed samples: 1192960 | consumed tokens: 2443182080 | elapsed time per iteration (s): 0.23 | learning rate: 1.943E-04 | global batch size: 256 | lm loss: 3.697980E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.870 | TFLOPs: 28.48 | +7: iteration 4670/ 37905 | consumed samples: 1195520 | consumed tokens: 2448424960 | elapsed time per iteration (s): 0.24 | learning rate: 1.943E-04 | global batch size: 256 | lm loss: 3.710830E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1069.605 | TFLOPs: 27.25 | +7: iteration 4680/ 37905 | consumed samples: 1198080 | consumed tokens: 2453667840 | elapsed time per iteration (s): 0.25 | learning rate: 1.942E-04 | global batch size: 256 | lm loss: 3.721954E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1036.696 | TFLOPs: 26.41 | +7: iteration 4690/ 37905 | consumed samples: 1200640 | consumed tokens: 2458910720 | elapsed time per iteration (s): 0.23 | learning rate: 1.942E-04 | global batch size: 256 | lm loss: 3.723824E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.017 | TFLOPs: 28.33 | +7: iteration 4700/ 37905 | consumed samples: 1203200 | consumed tokens: 2464153600 | elapsed time per iteration (s): 0.23 | learning rate: 1.942E-04 | global batch size: 256 | lm loss: 3.711977E+00 | grad norm: 0.450 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.032 | TFLOPs: 28.71 | +7: iteration 4710/ 37905 | consumed samples: 1205760 | consumed tokens: 2469396480 | elapsed time per iteration (s): 0.23 | learning rate: 1.941E-04 | global batch size: 256 | lm loss: 3.716970E+00 | grad norm: 0.495 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.995 | TFLOPs: 28.40 | +7: iteration 4720/ 37905 | consumed samples: 1208320 | consumed tokens: 2474639360 | elapsed time per iteration (s): 0.23 | learning rate: 1.941E-04 | global batch size: 256 | lm loss: 3.714938E+00 | grad norm: 0.435 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.258 | TFLOPs: 27.77 | +7: iteration 4730/ 37905 | consumed samples: 1210880 | consumed tokens: 2479882240 | elapsed time per iteration (s): 0.23 | learning rate: 1.941E-04 | global batch size: 256 | lm loss: 3.737712E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.031 | TFLOPs: 28.71 | +7: iteration 4740/ 37905 | consumed samples: 1213440 | consumed tokens: 2485125120 | elapsed time per iteration (s): 0.23 | learning rate: 1.941E-04 | global batch size: 256 | lm loss: 3.706171E+00 | grad norm: 0.373 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.075 | TFLOPs: 28.18 | +7: iteration 4750/ 37905 | consumed samples: 1216000 | consumed tokens: 2490368000 | elapsed time per iteration (s): 0.23 | learning rate: 1.940E-04 | global batch size: 256 | lm loss: 3.712543E+00 | grad norm: 0.413 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.805 | TFLOPs: 28.40 | +7: iteration 4760/ 37905 | consumed samples: 1218560 | consumed tokens: 2495610880 | elapsed time per iteration (s): 0.23 | learning rate: 1.940E-04 | global batch size: 256 | lm loss: 3.706589E+00 | grad norm: 0.419 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.711 | TFLOPs: 28.52 | +7: iteration 4770/ 37905 | consumed samples: 1221120 | consumed tokens: 2500853760 | elapsed time per iteration (s): 0.24 | learning rate: 1.940E-04 | global batch size: 256 | lm loss: 3.706440E+00 | grad norm: 0.410 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1058.459 | TFLOPs: 26.96 | +7: iteration 4780/ 37905 | consumed samples: 1223680 | consumed tokens: 2506096640 | elapsed time per iteration (s): 0.23 | learning rate: 1.940E-04 | global batch size: 256 | lm loss: 3.728204E+00 | grad norm: 0.534 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.571 | TFLOPs: 28.52 | +7: iteration 4790/ 37905 | consumed samples: 1226240 | consumed tokens: 2511339520 | elapsed time per iteration (s): 0.23 | learning rate: 1.939E-04 | global batch size: 256 | lm loss: 3.725258E+00 | grad norm: 0.442 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.988 | TFLOPs: 28.58 | +7: iteration 4800/ 37905 | consumed samples: 1228800 | consumed tokens: 2516582400 | elapsed time per iteration (s): 0.23 | learning rate: 1.939E-04 | global batch size: 256 | lm loss: 3.674019E+00 | grad norm: 0.404 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.271 | TFLOPs: 28.69 | +7: iteration 4810/ 37905 | consumed samples: 1231360 | consumed tokens: 2521825280 | elapsed time per iteration (s): 0.23 | learning rate: 1.939E-04 | global batch size: 256 | lm loss: 3.700956E+00 | grad norm: 0.421 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.767 | TFLOPs: 28.73 | +7: iteration 4820/ 37905 | consumed samples: 1233920 | consumed tokens: 2527068160 | elapsed time per iteration (s): 0.23 | learning rate: 1.939E-04 | global batch size: 256 | lm loss: 3.721699E+00 | grad norm: 0.473 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.514 | TFLOPs: 28.44 | +7: iteration 4830/ 37905 | consumed samples: 1236480 | consumed tokens: 2532311040 | elapsed time per iteration (s): 0.23 | learning rate: 1.938E-04 | global batch size: 256 | lm loss: 3.687552E+00 | grad norm: 0.388 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.729 | TFLOPs: 28.25 | +7: iteration 4840/ 37905 | consumed samples: 1239040 | consumed tokens: 2537553920 | elapsed time per iteration (s): 0.25 | learning rate: 1.938E-04 | global batch size: 256 | lm loss: 3.718913E+00 | grad norm: 0.390 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1039.670 | TFLOPs: 26.49 | +7: iteration 4850/ 37905 | consumed samples: 1241600 | consumed tokens: 2542796800 | elapsed time per iteration (s): 0.23 | learning rate: 1.938E-04 | global batch size: 256 | lm loss: 3.711369E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.184 | TFLOPs: 28.74 | +7: iteration 4860/ 37905 | consumed samples: 1244160 | consumed tokens: 2548039680 | elapsed time per iteration (s): 0.23 | learning rate: 1.937E-04 | global batch size: 256 | lm loss: 3.693707E+00 | grad norm: 0.415 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.621 | TFLOPs: 28.11 | +7: iteration 4870/ 37905 | consumed samples: 1246720 | consumed tokens: 2553282560 | elapsed time per iteration (s): 0.23 | learning rate: 1.937E-04 | global batch size: 256 | lm loss: 3.697030E+00 | grad norm: 0.407 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.354 | TFLOPs: 28.29 | +7: iteration 4880/ 37905 | consumed samples: 1249280 | consumed tokens: 2558525440 | elapsed time per iteration (s): 0.23 | learning rate: 1.937E-04 | global batch size: 256 | lm loss: 3.699771E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.205 | TFLOPs: 28.69 | +7: iteration 4890/ 37905 | consumed samples: 1251840 | consumed tokens: 2563768320 | elapsed time per iteration (s): 0.23 | learning rate: 1.937E-04 | global batch size: 256 | lm loss: 3.697682E+00 | grad norm: 0.390 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.695 | TFLOPs: 28.37 | +7: iteration 4900/ 37905 | consumed samples: 1254400 | consumed tokens: 2569011200 | elapsed time per iteration (s): 0.23 | learning rate: 1.936E-04 | global batch size: 256 | lm loss: 3.694956E+00 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.543 | TFLOPs: 28.72 | +7: iteration 4910/ 37905 | consumed samples: 1256960 | consumed tokens: 2574254080 | elapsed time per iteration (s): 0.23 | learning rate: 1.936E-04 | global batch size: 256 | lm loss: 3.689320E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.678 | TFLOPs: 28.50 | +7: iteration 4920/ 37905 | consumed samples: 1259520 | consumed tokens: 2579496960 | elapsed time per iteration (s): 0.23 | learning rate: 1.936E-04 | global batch size: 256 | lm loss: 3.709683E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.742 | TFLOPs: 28.60 | +7: iteration 4930/ 37905 | consumed samples: 1262080 | consumed tokens: 2584739840 | elapsed time per iteration (s): 0.24 | learning rate: 1.935E-04 | global batch size: 256 | lm loss: 3.685117E+00 | grad norm: 0.531 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1068.932 | TFLOPs: 27.23 | +7: iteration 4940/ 37905 | consumed samples: 1264640 | consumed tokens: 2589982720 | elapsed time per iteration (s): 0.23 | learning rate: 1.935E-04 | global batch size: 256 | lm loss: 3.715197E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.780 | TFLOPs: 28.45 | +7: iteration 4950/ 37905 | consumed samples: 1267200 | consumed tokens: 2595225600 | elapsed time per iteration (s): 0.23 | learning rate: 1.935E-04 | global batch size: 256 | lm loss: 3.701878E+00 | grad norm: 0.407 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.022 | TFLOPs: 28.76 | +7: iteration 4960/ 37905 | consumed samples: 1269760 | consumed tokens: 2600468480 | elapsed time per iteration (s): 0.23 | learning rate: 1.935E-04 | global batch size: 256 | lm loss: 3.714546E+00 | grad norm: 0.437 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.413 | TFLOPs: 28.42 | +7: iteration 4970/ 37905 | consumed samples: 1272320 | consumed tokens: 2605711360 | elapsed time per iteration (s): 0.23 | learning rate: 1.934E-04 | global batch size: 256 | lm loss: 3.710176E+00 | grad norm: 0.387 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.835 | TFLOPs: 28.55 | +7: iteration 4980/ 37905 | consumed samples: 1274880 | consumed tokens: 2610954240 | elapsed time per iteration (s): 0.23 | learning rate: 1.934E-04 | global batch size: 256 | lm loss: 3.681903E+00 | grad norm: 0.408 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.324 | TFLOPs: 27.85 | +7: iteration 4990/ 37905 | consumed samples: 1277440 | consumed tokens: 2616197120 | elapsed time per iteration (s): 0.23 | learning rate: 1.934E-04 | global batch size: 256 | lm loss: 3.709989E+00 | grad norm: 0.465 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.189 | TFLOPs: 28.46 | +7: iteration 5000/ 37905 | consumed samples: 1280000 | consumed tokens: 2621440000 | elapsed time per iteration (s): 0.23 | learning rate: 1.933E-04 | global batch size: 256 | lm loss: 3.682413E+00 | grad norm: 0.500 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.582 | TFLOPs: 28.32 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 5000 | lm loss value: 3.577270E+00 | lm loss PPL: 3.577575E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 5000 to checkpoints_83moscar +0: [2022-11-29 17:15:38,624] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step5000 is begin to save! +0: [2022-11-29 17:15:38,627] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:15:38,697] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:15:38,697] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:15:38,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:15:38,709] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:15:38,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:15:38,721] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:15:38,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:15:38,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:15:38,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:15:38,744] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:15:38,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:15:38,755] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:15:38,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:15:38,766] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:15:38,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:15:38,777] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:15:38,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:15:38,789] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:15:38,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:15:38,800] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:15:38,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:15:38,811] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:15:38,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:15:38,813] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step5000/mp_rank_00_model_states.pt +0: [2022-11-29 17:15:38,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:15:38,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:15:38,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:15:38,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:15:38,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:15:38,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:15:38,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:15:38,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:15:38,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:15:38,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:15:38,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:15:38,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:15:38,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:15:38,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:15:38,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:15:38,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:15:38,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:15:38,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +0: [2022-11-29 17:15:38,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:15:38,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:15:38,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:15:38,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:15:38,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:15:38,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:15:38,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:15:38,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:15:38,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:15:38,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:15:38,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:15:38,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +7: [2022-11-29 17:15:38,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:15:38,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +2: [2022-11-29 17:15:38,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:15:38,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +6: [2022-11-29 17:15:38,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:15:38,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:15:38,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:15:38,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +5: [2022-11-29 17:15:38,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:15:38,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:15:38,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:15:38,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:15:38,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:15:38,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +3: [2022-11-29 17:15:38,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:15:38,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:15:38,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:15:38,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:15:38,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:15:38,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:15:38,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:15:38,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:15:38,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:15:38,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:15:38,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:15:38,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:15:38,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:15:38,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:15:38,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:15:38,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:15:38,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +2: [2022-11-29 17:15:38,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +5: [2022-11-29 17:15:38,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:15:38,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +2: [2022-11-29 17:15:38,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:15:38,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:15:38,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:15:38,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:15:38,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:15:38,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:15:38,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:15:38,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:15:38,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:15:38,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:15:38,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:15:38,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:15:38,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:15:38,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:15:38,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +7: [2022-11-29 17:15:38,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +1: [2022-11-29 17:15:38,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:15:38,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:15:38,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:15:38,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +6: [2022-11-29 17:15:38,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:15:38,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +4: [2022-11-29 17:15:38,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:15:38,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +1: [2022-11-29 17:15:38,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:15:38,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:15:38,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:15:38,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:15:38,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:15:38,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:15:38,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:15:38,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:15:38,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:15:38,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:15:38,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:15:38,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:15:38,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:15:38,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:15:38,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:15:38,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:15:38,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:15:38,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:15:38,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:15:38,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:15:38,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:15:38,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:15:38,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:15:38,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:15:38,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:15:38,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:15:38,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:15:38,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:15:38,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +3: [2022-11-29 17:15:38,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +5: [2022-11-29 17:15:38,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:15:38,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:15:38,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:15:38,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:15:38,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:15:38,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:15:38,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:15:38,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:15:38,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:15:38,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:15:38,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:15:38,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:15:38,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:15:38,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:15:38,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:15:38,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:15:38,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:15:38,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:15:38,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:15:38,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:15:38,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:15:38,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:15:38,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:15:38,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:15:38,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:15:38,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:15:38,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:15:38,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:15:38,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +1: [2022-11-29 17:15:38,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +0: [2022-11-29 17:15:38,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:15:38,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-29 17:15:38,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:15:38,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:15:38,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:15:38,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:15:38,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:15:38,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +6: [2022-11-29 17:15:38,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +3: [2022-11-29 17:15:38,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:15:38,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:15:38,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:15:38,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:15:38,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +4: [2022-11-29 17:15:38,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:15:38,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +4: [2022-11-29 17:15:38,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +2: [2022-11-29 17:15:38,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:15:38,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:15:38,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:15:38,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:15:38,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:15:38,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-29 17:15:38,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:15:38,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:15:38,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +1: [2022-11-29 17:15:38,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +2: [2022-11-29 17:15:38,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:15:38,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-29 17:15:38,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:15:38,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:15:38,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-29 17:15:38,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:15:38,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:15:38,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +3: [2022-11-29 17:15:38,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +1: [2022-11-29 17:15:38,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-29 17:15:38,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-29 17:15:38,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:15:38,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +6: [2022-11-29 17:15:38,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:15:38,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-29 17:15:38,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:15:38,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-29 17:15:38,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:15:38,865] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:15:38,865] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: successfully saved checkpoint at iteration 5000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 244.73 +7: iteration 5010/ 37905 | consumed samples: 1282560 | consumed tokens: 2626682880 | elapsed time per iteration (s): 0.26 | learning rate: 1.933E-04 | global batch size: 256 | lm loss: 3.699659E+00 | grad norm: 0.458 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 992.180 | TFLOPs: 25.28 | +7: iteration 5020/ 37905 | consumed samples: 1285120 | consumed tokens: 2631925760 | elapsed time per iteration (s): 0.23 | learning rate: 1.933E-04 | global batch size: 256 | lm loss: 3.699009E+00 | grad norm: 0.488 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.185 | TFLOPs: 28.77 | +7: iteration 5030/ 37905 | consumed samples: 1287680 | consumed tokens: 2637168640 | elapsed time per iteration (s): 0.23 | learning rate: 1.933E-04 | global batch size: 256 | lm loss: 3.679039E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.919 | TFLOPs: 28.28 | +7: iteration 5040/ 37905 | consumed samples: 1290240 | consumed tokens: 2642411520 | elapsed time per iteration (s): 0.23 | learning rate: 1.932E-04 | global batch size: 256 | lm loss: 3.709240E+00 | grad norm: 0.457 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.627 | TFLOPs: 27.76 | +7: iteration 5050/ 37905 | consumed samples: 1292800 | consumed tokens: 2647654400 | elapsed time per iteration (s): 0.23 | learning rate: 1.932E-04 | global batch size: 256 | lm loss: 3.677147E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.308 | TFLOPs: 28.46 | +7: iteration 5060/ 37905 | consumed samples: 1295360 | consumed tokens: 2652897280 | elapsed time per iteration (s): 0.23 | learning rate: 1.932E-04 | global batch size: 256 | lm loss: 3.693395E+00 | grad norm: 0.558 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.643 | TFLOPs: 28.62 | +7: iteration 5070/ 37905 | consumed samples: 1297920 | consumed tokens: 2658140160 | elapsed time per iteration (s): 0.23 | learning rate: 1.931E-04 | global batch size: 256 | lm loss: 3.695757E+00 | grad norm: 0.484 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.682 | TFLOPs: 28.50 | +7: iteration 5080/ 37905 | consumed samples: 1300480 | consumed tokens: 2663383040 | elapsed time per iteration (s): 0.23 | learning rate: 1.931E-04 | global batch size: 256 | lm loss: 3.709293E+00 | grad norm: 0.441 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.692 | TFLOPs: 28.70 | +7: iteration 5090/ 37905 | consumed samples: 1303040 | consumed tokens: 2668625920 | elapsed time per iteration (s): 0.23 | learning rate: 1.931E-04 | global batch size: 256 | lm loss: 3.713515E+00 | grad norm: 0.387 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.220 | TFLOPs: 28.44 | +7: iteration 5100/ 37905 | consumed samples: 1305600 | consumed tokens: 2673868800 | elapsed time per iteration (s): 0.23 | learning rate: 1.931E-04 | global batch size: 256 | lm loss: 3.707148E+00 | grad norm: 0.388 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.648 | TFLOPs: 28.42 | +7: iteration 5110/ 37905 | consumed samples: 1308160 | consumed tokens: 2679111680 | elapsed time per iteration (s): 0.23 | learning rate: 1.930E-04 | global batch size: 256 | lm loss: 3.693228E+00 | grad norm: 0.383 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.643 | TFLOPs: 28.55 | +7: iteration 5120/ 37905 | consumed samples: 1310720 | consumed tokens: 2684354560 | elapsed time per iteration (s): 0.23 | learning rate: 1.930E-04 | global batch size: 256 | lm loss: 3.664970E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.044 | TFLOPs: 28.58 | +7: iteration 5130/ 37905 | consumed samples: 1313280 | consumed tokens: 2689597440 | elapsed time per iteration (s): 0.23 | learning rate: 1.930E-04 | global batch size: 256 | lm loss: 3.693811E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.777 | TFLOPs: 28.17 | +7: iteration 5140/ 37905 | consumed samples: 1315840 | consumed tokens: 2694840320 | elapsed time per iteration (s): 0.23 | learning rate: 1.929E-04 | global batch size: 256 | lm loss: 3.698471E+00 | grad norm: 0.436 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.738 | TFLOPs: 28.07 | +7: iteration 5150/ 37905 | consumed samples: 1318400 | consumed tokens: 2700083200 | elapsed time per iteration (s): 0.23 | learning rate: 1.929E-04 | global batch size: 256 | lm loss: 3.705743E+00 | grad norm: 0.465 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.263 | TFLOPs: 28.54 | +7: iteration 5160/ 37905 | consumed samples: 1320960 | consumed tokens: 2705326080 | elapsed time per iteration (s): 0.23 | learning rate: 1.929E-04 | global batch size: 256 | lm loss: 3.691589E+00 | grad norm: 0.411 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.968 | TFLOPs: 28.45 | +7: iteration 5170/ 37905 | consumed samples: 1323520 | consumed tokens: 2710568960 | elapsed time per iteration (s): 0.23 | learning rate: 1.929E-04 | global batch size: 256 | lm loss: 3.695402E+00 | grad norm: 0.459 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.674 | TFLOPs: 28.47 | +7: iteration 5180/ 37905 | consumed samples: 1326080 | consumed tokens: 2715811840 | elapsed time per iteration (s): 0.23 | learning rate: 1.928E-04 | global batch size: 256 | lm loss: 3.679947E+00 | grad norm: 0.409 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.963 | TFLOPs: 28.66 | +7: iteration 5190/ 37905 | consumed samples: 1328640 | consumed tokens: 2721054720 | elapsed time per iteration (s): 0.23 | learning rate: 1.928E-04 | global batch size: 256 | lm loss: 3.683361E+00 | grad norm: 0.396 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.586 | TFLOPs: 28.01 | +7: iteration 5200/ 37905 | consumed samples: 1331200 | consumed tokens: 2726297600 | elapsed time per iteration (s): 0.23 | learning rate: 1.928E-04 | global batch size: 256 | lm loss: 3.683036E+00 | grad norm: 0.409 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.304 | TFLOPs: 28.03 | +7: iteration 5210/ 37905 | consumed samples: 1333760 | consumed tokens: 2731540480 | elapsed time per iteration (s): 0.23 | learning rate: 1.927E-04 | global batch size: 256 | lm loss: 3.672707E+00 | grad norm: 0.389 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.518 | TFLOPs: 28.01 | +7: iteration 5220/ 37905 | consumed samples: 1336320 | consumed tokens: 2736783360 | elapsed time per iteration (s): 0.23 | learning rate: 1.927E-04 | global batch size: 256 | lm loss: 3.678289E+00 | grad norm: 0.415 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.208 | TFLOPs: 27.77 | +7: iteration 5230/ 37905 | consumed samples: 1338880 | consumed tokens: 2742026240 | elapsed time per iteration (s): 0.23 | learning rate: 1.927E-04 | global batch size: 256 | lm loss: 3.649273E+00 | grad norm: 0.574 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.182 | TFLOPs: 28.03 | +7: iteration 5240/ 37905 | consumed samples: 1341440 | consumed tokens: 2747269120 | elapsed time per iteration (s): 0.24 | learning rate: 1.926E-04 | global batch size: 256 | lm loss: 3.663102E+00 | grad norm: 0.416 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.081 | TFLOPs: 27.72 | +7: iteration 5250/ 37905 | consumed samples: 1344000 | consumed tokens: 2752512000 | elapsed time per iteration (s): 0.23 | learning rate: 1.926E-04 | global batch size: 256 | lm loss: 3.677839E+00 | grad norm: 0.437 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.230 | TFLOPs: 28.23 | +7: iteration 5260/ 37905 | consumed samples: 1346560 | consumed tokens: 2757754880 | elapsed time per iteration (s): 0.23 | learning rate: 1.926E-04 | global batch size: 256 | lm loss: 3.671714E+00 | grad norm: 0.424 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.316 | TFLOPs: 28.41 | +7: iteration 5270/ 37905 | consumed samples: 1349120 | consumed tokens: 2762997760 | elapsed time per iteration (s): 0.23 | learning rate: 1.926E-04 | global batch size: 256 | lm loss: 3.674565E+00 | grad norm: 0.502 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.438 | TFLOPs: 28.75 | +7: iteration 5280/ 37905 | consumed samples: 1351680 | consumed tokens: 2768240640 | elapsed time per iteration (s): 0.23 | learning rate: 1.925E-04 | global batch size: 256 | lm loss: 3.670794E+00 | grad norm: 0.441 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.501 | TFLOPs: 28.60 | +7: iteration 5290/ 37905 | consumed samples: 1354240 | consumed tokens: 2773483520 | elapsed time per iteration (s): 0.23 | learning rate: 1.925E-04 | global batch size: 256 | lm loss: 3.685275E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.042 | TFLOPs: 28.61 | +7: iteration 5300/ 37905 | consumed samples: 1356800 | consumed tokens: 2778726400 | elapsed time per iteration (s): 0.23 | learning rate: 1.925E-04 | global batch size: 256 | lm loss: 3.670407E+00 | grad norm: 0.457 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.009 | TFLOPs: 28.56 | +7: iteration 5310/ 37905 | consumed samples: 1359360 | consumed tokens: 2783969280 | elapsed time per iteration (s): 0.23 | learning rate: 1.924E-04 | global batch size: 256 | lm loss: 3.654729E+00 | grad norm: 0.373 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.513 | TFLOPs: 28.77 | +7: iteration 5320/ 37905 | consumed samples: 1361920 | consumed tokens: 2789212160 | elapsed time per iteration (s): 0.23 | learning rate: 1.924E-04 | global batch size: 256 | lm loss: 3.704704E+00 | grad norm: 0.404 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.721 | TFLOPs: 28.40 | +7: iteration 5330/ 37905 | consumed samples: 1364480 | consumed tokens: 2794455040 | elapsed time per iteration (s): 0.25 | learning rate: 1.924E-04 | global batch size: 256 | lm loss: 3.660257E+00 | grad norm: 0.439 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1032.744 | TFLOPs: 26.31 | +7: iteration 5340/ 37905 | consumed samples: 1367040 | consumed tokens: 2799697920 | elapsed time per iteration (s): 0.23 | learning rate: 1.923E-04 | global batch size: 256 | lm loss: 3.666140E+00 | grad norm: 0.470 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.512 | TFLOPs: 28.75 | +7: iteration 5350/ 37905 | consumed samples: 1369600 | consumed tokens: 2804940800 | elapsed time per iteration (s): 0.23 | learning rate: 1.923E-04 | global batch size: 256 | lm loss: 3.684081E+00 | grad norm: 0.412 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.963 | TFLOPs: 28.43 | +7: iteration 5360/ 37905 | consumed samples: 1372160 | consumed tokens: 2810183680 | elapsed time per iteration (s): 0.23 | learning rate: 1.923E-04 | global batch size: 256 | lm loss: 3.658354E+00 | grad norm: 0.486 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.587 | TFLOPs: 28.27 | +7: iteration 5370/ 37905 | consumed samples: 1374720 | consumed tokens: 2815426560 | elapsed time per iteration (s): 0.23 | learning rate: 1.923E-04 | global batch size: 256 | lm loss: 3.662455E+00 | grad norm: 0.483 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.440 | TFLOPs: 28.44 | +7: iteration 5380/ 37905 | consumed samples: 1377280 | consumed tokens: 2820669440 | elapsed time per iteration (s): 0.23 | learning rate: 1.922E-04 | global batch size: 256 | lm loss: 3.698862E+00 | grad norm: 0.367 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.597 | TFLOPs: 28.11 | +7: iteration 5390/ 37905 | consumed samples: 1379840 | consumed tokens: 2825912320 | elapsed time per iteration (s): 0.23 | learning rate: 1.922E-04 | global batch size: 256 | lm loss: 3.667289E+00 | grad norm: 0.411 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.689 | TFLOPs: 28.58 | +7: iteration 5400/ 37905 | consumed samples: 1382400 | consumed tokens: 2831155200 | elapsed time per iteration (s): 0.23 | learning rate: 1.922E-04 | global batch size: 256 | lm loss: 3.625074E+00 | grad norm: 0.428 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.050 | TFLOPs: 27.97 | +7: iteration 5410/ 37905 | consumed samples: 1384960 | consumed tokens: 2836398080 | elapsed time per iteration (s): 0.23 | learning rate: 1.921E-04 | global batch size: 256 | lm loss: 3.667464E+00 | grad norm: 0.448 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.554 | TFLOPs: 28.55 | +7: iteration 5420/ 37905 | consumed samples: 1387520 | consumed tokens: 2841640960 | elapsed time per iteration (s): 0.23 | learning rate: 1.921E-04 | global batch size: 256 | lm loss: 3.696485E+00 | grad norm: 0.389 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.596 | TFLOPs: 28.42 | +7: iteration 5430/ 37905 | consumed samples: 1390080 | consumed tokens: 2846883840 | elapsed time per iteration (s): 0.23 | learning rate: 1.921E-04 | global batch size: 256 | lm loss: 3.676997E+00 | grad norm: 0.383 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.532 | TFLOPs: 28.42 | +7: iteration 5440/ 37905 | consumed samples: 1392640 | consumed tokens: 2852126720 | elapsed time per iteration (s): 0.23 | learning rate: 1.920E-04 | global batch size: 256 | lm loss: 3.680098E+00 | grad norm: 0.394 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.010 | TFLOPs: 28.51 | +7: iteration 5450/ 37905 | consumed samples: 1395200 | consumed tokens: 2857369600 | elapsed time per iteration (s): 0.23 | learning rate: 1.920E-04 | global batch size: 256 | lm loss: 3.635740E+00 | grad norm: 0.427 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.355 | TFLOPs: 28.16 | +7: iteration 5460/ 37905 | consumed samples: 1397760 | consumed tokens: 2862612480 | elapsed time per iteration (s): 0.25 | learning rate: 1.920E-04 | global batch size: 256 | lm loss: 3.669881E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1039.991 | TFLOPs: 26.49 | +7: iteration 5470/ 37905 | consumed samples: 1400320 | consumed tokens: 2867855360 | elapsed time per iteration (s): 0.23 | learning rate: 1.919E-04 | global batch size: 256 | lm loss: 3.664152E+00 | grad norm: 0.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.847 | TFLOPs: 28.25 | +7: iteration 5480/ 37905 | consumed samples: 1402880 | consumed tokens: 2873098240 | elapsed time per iteration (s): 0.24 | learning rate: 1.919E-04 | global batch size: 256 | lm loss: 3.675283E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.058 | TFLOPs: 26.93 | +7: iteration 5490/ 37905 | consumed samples: 1405440 | consumed tokens: 2878341120 | elapsed time per iteration (s): 0.25 | learning rate: 1.919E-04 | global batch size: 256 | lm loss: 3.655694E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1042.155 | TFLOPs: 26.55 | +7: iteration 5500/ 37905 | consumed samples: 1408000 | consumed tokens: 2883584000 | elapsed time per iteration (s): 0.23 | learning rate: 1.919E-04 | global batch size: 256 | lm loss: 3.690833E+00 | grad norm: 0.417 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.341 | TFLOPs: 28.57 | +7: iteration 5510/ 37905 | consumed samples: 1410560 | consumed tokens: 2888826880 | elapsed time per iteration (s): 0.23 | learning rate: 1.918E-04 | global batch size: 256 | lm loss: 3.635592E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.929 | TFLOPs: 28.15 | +7: iteration 5520/ 37905 | consumed samples: 1413120 | consumed tokens: 2894069760 | elapsed time per iteration (s): 0.23 | learning rate: 1.918E-04 | global batch size: 256 | lm loss: 3.654089E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.122 | TFLOPs: 28.10 | +7: iteration 5530/ 37905 | consumed samples: 1415680 | consumed tokens: 2899312640 | elapsed time per iteration (s): 0.23 | learning rate: 1.918E-04 | global batch size: 256 | lm loss: 3.648915E+00 | grad norm: 0.472 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.143 | TFLOPs: 28.43 | +7: iteration 5540/ 37905 | consumed samples: 1418240 | consumed tokens: 2904555520 | elapsed time per iteration (s): 0.23 | learning rate: 1.917E-04 | global batch size: 256 | lm loss: 3.659303E+00 | grad norm: 0.428 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.746 | TFLOPs: 28.42 | +7: iteration 5550/ 37905 | consumed samples: 1420800 | consumed tokens: 2909798400 | elapsed time per iteration (s): 0.23 | learning rate: 1.917E-04 | global batch size: 256 | lm loss: 3.674485E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.625 | TFLOPs: 28.22 | +7: iteration 5560/ 37905 | consumed samples: 1423360 | consumed tokens: 2915041280 | elapsed time per iteration (s): 0.23 | learning rate: 1.917E-04 | global batch size: 256 | lm loss: 3.643174E+00 | grad norm: 0.473 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.845 | TFLOPs: 28.38 | +7: iteration 5570/ 37905 | consumed samples: 1425920 | consumed tokens: 2920284160 | elapsed time per iteration (s): 0.23 | learning rate: 1.916E-04 | global batch size: 256 | lm loss: 3.654641E+00 | grad norm: 0.380 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.094 | TFLOPs: 28.20 | +7: iteration 5580/ 37905 | consumed samples: 1428480 | consumed tokens: 2925527040 | elapsed time per iteration (s): 0.25 | learning rate: 1.916E-04 | global batch size: 256 | lm loss: 3.660714E+00 | grad norm: 0.385 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1029.828 | TFLOPs: 26.24 | +7: iteration 5590/ 37905 | consumed samples: 1431040 | consumed tokens: 2930769920 | elapsed time per iteration (s): 0.23 | learning rate: 1.916E-04 | global batch size: 256 | lm loss: 3.628533E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.372 | TFLOPs: 28.01 | +7: iteration 5600/ 37905 | consumed samples: 1433600 | consumed tokens: 2936012800 | elapsed time per iteration (s): 0.23 | learning rate: 1.915E-04 | global batch size: 256 | lm loss: 3.657505E+00 | grad norm: 0.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.823 | TFLOPs: 28.53 | +7: iteration 5610/ 37905 | consumed samples: 1436160 | consumed tokens: 2941255680 | elapsed time per iteration (s): 0.23 | learning rate: 1.915E-04 | global batch size: 256 | lm loss: 3.642457E+00 | grad norm: 0.404 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.404 | TFLOPs: 28.19 | +7: iteration 5620/ 37905 | consumed samples: 1438720 | consumed tokens: 2946498560 | elapsed time per iteration (s): 0.23 | learning rate: 1.915E-04 | global batch size: 256 | lm loss: 3.651572E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.550 | TFLOPs: 27.86 | +7: iteration 5630/ 37905 | consumed samples: 1441280 | consumed tokens: 2951741440 | elapsed time per iteration (s): 0.23 | learning rate: 1.914E-04 | global batch size: 256 | lm loss: 3.651526E+00 | grad norm: 0.390 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.256 | TFLOPs: 28.18 | +7: iteration 5640/ 37905 | consumed samples: 1443840 | consumed tokens: 2956984320 | elapsed time per iteration (s): 0.23 | learning rate: 1.914E-04 | global batch size: 256 | lm loss: 3.647044E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.404 | TFLOPs: 28.36 | +7: iteration 5650/ 37905 | consumed samples: 1446400 | consumed tokens: 2962227200 | elapsed time per iteration (s): 0.23 | learning rate: 1.914E-04 | global batch size: 256 | lm loss: 3.672866E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.148 | TFLOPs: 28.48 | +7: iteration 5660/ 37905 | consumed samples: 1448960 | consumed tokens: 2967470080 | elapsed time per iteration (s): 0.23 | learning rate: 1.913E-04 | global batch size: 256 | lm loss: 3.670351E+00 | grad norm: 0.459 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.508 | TFLOPs: 28.67 | +7: iteration 5670/ 37905 | consumed samples: 1451520 | consumed tokens: 2972712960 | elapsed time per iteration (s): 0.23 | learning rate: 1.913E-04 | global batch size: 256 | lm loss: 3.651663E+00 | grad norm: 0.443 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.981 | TFLOPs: 28.71 | +7: iteration 5680/ 37905 | consumed samples: 1454080 | consumed tokens: 2977955840 | elapsed time per iteration (s): 0.24 | learning rate: 1.913E-04 | global batch size: 256 | lm loss: 3.657278E+00 | grad norm: 0.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1062.705 | TFLOPs: 27.07 | +7: iteration 5690/ 37905 | consumed samples: 1456640 | consumed tokens: 2983198720 | elapsed time per iteration (s): 0.25 | learning rate: 1.912E-04 | global batch size: 256 | lm loss: 3.651068E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1044.244 | TFLOPs: 26.60 | +7: iteration 5700/ 37905 | consumed samples: 1459200 | consumed tokens: 2988441600 | elapsed time per iteration (s): 0.23 | learning rate: 1.912E-04 | global batch size: 256 | lm loss: 3.661382E+00 | grad norm: 0.418 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.106 | TFLOPs: 28.69 | +7: iteration 5710/ 37905 | consumed samples: 1461760 | consumed tokens: 2993684480 | elapsed time per iteration (s): 0.23 | learning rate: 1.912E-04 | global batch size: 256 | lm loss: 3.653524E+00 | grad norm: 0.422 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.742 | TFLOPs: 28.42 | +7: iteration 5720/ 37905 | consumed samples: 1464320 | consumed tokens: 2998927360 | elapsed time per iteration (s): 0.23 | learning rate: 1.912E-04 | global batch size: 256 | lm loss: 3.641549E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.440 | TFLOPs: 28.75 | +7: iteration 5730/ 37905 | consumed samples: 1466880 | consumed tokens: 3004170240 | elapsed time per iteration (s): 0.23 | learning rate: 1.911E-04 | global batch size: 256 | lm loss: 3.624776E+00 | grad norm: 0.475 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.349 | TFLOPs: 28.36 | +7: iteration 5740/ 37905 | consumed samples: 1469440 | consumed tokens: 3009413120 | elapsed time per iteration (s): 0.23 | learning rate: 1.911E-04 | global batch size: 256 | lm loss: 3.651925E+00 | grad norm: 0.424 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.399 | TFLOPs: 28.29 | +7: iteration 5750/ 37905 | consumed samples: 1472000 | consumed tokens: 3014656000 | elapsed time per iteration (s): 0.23 | learning rate: 1.911E-04 | global batch size: 256 | lm loss: 3.646092E+00 | grad norm: 0.448 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.623 | TFLOPs: 28.60 | +7: iteration 5760/ 37905 | consumed samples: 1474560 | consumed tokens: 3019898880 | elapsed time per iteration (s): 0.23 | learning rate: 1.910E-04 | global batch size: 256 | lm loss: 3.620794E+00 | grad norm: 0.386 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.999 | TFLOPs: 28.28 | +7: iteration 5770/ 37905 | consumed samples: 1477120 | consumed tokens: 3025141760 | elapsed time per iteration (s): 0.23 | learning rate: 1.910E-04 | global batch size: 256 | lm loss: 3.660412E+00 | grad norm: 0.418 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.911 | TFLOPs: 28.35 | +7: iteration 5780/ 37905 | consumed samples: 1479680 | consumed tokens: 3030384640 | elapsed time per iteration (s): 0.23 | learning rate: 1.910E-04 | global batch size: 256 | lm loss: 3.634518E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.310 | TFLOPs: 27.98 | +7: iteration 5790/ 37905 | consumed samples: 1482240 | consumed tokens: 3035627520 | elapsed time per iteration (s): 0.23 | learning rate: 1.909E-04 | global batch size: 256 | lm loss: 3.652385E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.796 | TFLOPs: 27.81 | +7: iteration 5800/ 37905 | consumed samples: 1484800 | consumed tokens: 3040870400 | elapsed time per iteration (s): 0.23 | learning rate: 1.909E-04 | global batch size: 256 | lm loss: 3.648978E+00 | grad norm: 0.391 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.598 | TFLOPs: 27.91 | +7: iteration 5810/ 37905 | consumed samples: 1487360 | consumed tokens: 3046113280 | elapsed time per iteration (s): 0.23 | learning rate: 1.909E-04 | global batch size: 256 | lm loss: 3.665164E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.376 | TFLOPs: 28.11 | +7: iteration 5820/ 37905 | consumed samples: 1489920 | consumed tokens: 3051356160 | elapsed time per iteration (s): 0.23 | learning rate: 1.908E-04 | global batch size: 256 | lm loss: 3.657172E+00 | grad norm: 0.409 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.699 | TFLOPs: 27.86 | +7: iteration 5830/ 37905 | consumed samples: 1492480 | consumed tokens: 3056599040 | elapsed time per iteration (s): 0.23 | learning rate: 1.908E-04 | global batch size: 256 | lm loss: 3.616917E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.240 | TFLOPs: 28.31 | +7: iteration 5840/ 37905 | consumed samples: 1495040 | consumed tokens: 3061841920 | elapsed time per iteration (s): 0.23 | learning rate: 1.908E-04 | global batch size: 256 | lm loss: 3.630701E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.797 | TFLOPs: 28.35 | +7: iteration 5850/ 37905 | consumed samples: 1497600 | consumed tokens: 3067084800 | elapsed time per iteration (s): 0.23 | learning rate: 1.907E-04 | global batch size: 256 | lm loss: 3.671229E+00 | grad norm: 0.460 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.725 | TFLOPs: 28.60 | +7: iteration 5860/ 37905 | consumed samples: 1500160 | consumed tokens: 3072327680 | elapsed time per iteration (s): 0.23 | learning rate: 1.907E-04 | global batch size: 256 | lm loss: 3.625891E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.941 | TFLOPs: 28.12 | +7: iteration 5870/ 37905 | consumed samples: 1502720 | consumed tokens: 3077570560 | elapsed time per iteration (s): 0.23 | learning rate: 1.907E-04 | global batch size: 256 | lm loss: 3.652815E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.330 | TFLOPs: 28.64 | +7: iteration 5880/ 37905 | consumed samples: 1505280 | consumed tokens: 3082813440 | elapsed time per iteration (s): 0.23 | learning rate: 1.906E-04 | global batch size: 256 | lm loss: 3.635437E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.179 | TFLOPs: 28.13 | +7: iteration 5890/ 37905 | consumed samples: 1507840 | consumed tokens: 3088056320 | elapsed time per iteration (s): 0.25 | learning rate: 1.906E-04 | global batch size: 256 | lm loss: 3.621841E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1033.103 | TFLOPs: 26.32 | +7: iteration 5900/ 37905 | consumed samples: 1510400 | consumed tokens: 3093299200 | elapsed time per iteration (s): 0.23 | learning rate: 1.906E-04 | global batch size: 256 | lm loss: 3.619831E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.198 | TFLOPs: 28.31 | +7: iteration 5910/ 37905 | consumed samples: 1512960 | consumed tokens: 3098542080 | elapsed time per iteration (s): 0.23 | learning rate: 1.905E-04 | global batch size: 256 | lm loss: 3.654085E+00 | grad norm: 0.388 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.808 | TFLOPs: 28.15 | +7: iteration 5920/ 37905 | consumed samples: 1515520 | consumed tokens: 3103784960 | elapsed time per iteration (s): 0.23 | learning rate: 1.905E-04 | global batch size: 256 | lm loss: 3.631548E+00 | grad norm: 0.373 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.886 | TFLOPs: 28.58 | +7: iteration 5930/ 37905 | consumed samples: 1518080 | consumed tokens: 3109027840 | elapsed time per iteration (s): 0.23 | learning rate: 1.905E-04 | global batch size: 256 | lm loss: 3.651060E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.968 | TFLOPs: 27.79 | +7: iteration 5940/ 37905 | consumed samples: 1520640 | consumed tokens: 3114270720 | elapsed time per iteration (s): 0.23 | learning rate: 1.904E-04 | global batch size: 256 | lm loss: 3.648917E+00 | grad norm: 0.447 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.323 | TFLOPs: 28.11 | +7: iteration 5950/ 37905 | consumed samples: 1523200 | consumed tokens: 3119513600 | elapsed time per iteration (s): 0.23 | learning rate: 1.904E-04 | global batch size: 256 | lm loss: 3.645583E+00 | grad norm: 0.440 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.528 | TFLOPs: 28.47 | +7: iteration 5960/ 37905 | consumed samples: 1525760 | consumed tokens: 3124756480 | elapsed time per iteration (s): 0.23 | learning rate: 1.904E-04 | global batch size: 256 | lm loss: 3.640550E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.230 | TFLOPs: 28.00 | +7: iteration 5970/ 37905 | consumed samples: 1528320 | consumed tokens: 3129999360 | elapsed time per iteration (s): 0.24 | learning rate: 1.903E-04 | global batch size: 256 | lm loss: 3.640204E+00 | grad norm: 0.426 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1073.155 | TFLOPs: 27.34 | +7: iteration 5980/ 37905 | consumed samples: 1530880 | consumed tokens: 3135242240 | elapsed time per iteration (s): 0.25 | learning rate: 1.903E-04 | global batch size: 256 | lm loss: 3.621389E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1042.384 | TFLOPs: 26.55 | +7: iteration 5990/ 37905 | consumed samples: 1533440 | consumed tokens: 3140485120 | elapsed time per iteration (s): 0.23 | learning rate: 1.903E-04 | global batch size: 256 | lm loss: 3.658350E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.484 | TFLOPs: 28.16 | +0: [2022-11-29 17:19:30,506] [INFO] [logging.py:68:log_dist] [Rank 0] step=6000, skipped=0, lr=[0.00019021778213052494, 0.00019021778213052494, 0.00019021778213052494], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 6000/ 37905 | consumed samples: 1536000 | consumed tokens: 3145728000 | elapsed time per iteration (s): 0.23 | learning rate: 1.902E-04 | global batch size: 256 | lm loss: 3.627463E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.131 | TFLOPs: 28.56 | +0: steps: 6000 loss: 3.5782 iter time (s): 0.230 samples/sec: 1114.351 +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 6000 | lm loss value: 3.499834E+00 | lm loss PPL: 3.310997E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 6000 to checkpoints_83moscar +0: [2022-11-29 17:19:30,595] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step6000 is begin to save! +0: [2022-11-29 17:19:30,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:19:30,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:19:30,672] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:19:30,684] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:19:30,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:19:30,695] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:19:30,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:19:30,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:19:30,707] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:19:30,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:19:30,719] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:19:30,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:19:30,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:19:30,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:19:30,742] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:19:30,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:19:30,754] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:19:30,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:19:30,765] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:19:30,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:19:30,777] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:19:30,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:19:30,789] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:19:30,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:19:30,791] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step6000/mp_rank_00_model_states.pt +0: [2022-11-29 17:19:30,791] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:19:30,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:19:30,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:19:30,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:19:30,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:19:30,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:19:30,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:19:30,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:19:30,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:19:30,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:19:30,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:19:30,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:19:30,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:19:30,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:19:30,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:19:30,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:19:30,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:19:30,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:19:30,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:19:30,832] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:19:30,832] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:19:30,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:19:30,832] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:19:30,832] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:19:30,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:19:30,832] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +1: [2022-11-29 17:19:30,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:19:30,833] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +2: [2022-11-29 17:19:30,833] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:19:30,833] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:19:30,833] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:19:30,833] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:19:30,833] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:19:30,833] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:19:30,833] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:19:30,833] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:19:30,833] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:19:30,833] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:19:30,833] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:19:30,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:19:30,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:19:30,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:19:30,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:19:30,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:19:30,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:19:30,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:19:30,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:19:30,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:19:30,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:19:30,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:19:30,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:19:30,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:19:30,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:19:30,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:19:30,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:19:30,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:19:30,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:19:30,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:19:30,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:19:30,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:19:30,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:19:30,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +3: [2022-11-29 17:19:30,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:19:30,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:19:30,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:19:30,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:19:30,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:19:30,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:19:30,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:19:30,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:19:30,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:19:30,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:19:30,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:19:30,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:19:30,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:19:30,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:19:30,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:19:30,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:19:30,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:19:30,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:19:30,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:19:30,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:19:30,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:19:30,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:19:30,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:19:30,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:19:30,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:19:30,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:19:30,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:19:30,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:19:30,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:19:30,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:19:30,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:19:30,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:19:30,840] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:19:30,840] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:19:30,840] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:19:30,840] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:19:30,840] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:19:30,840] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:19:30,840] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:19:30,840] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:19:30,841] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:19:30,841] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:19:30,841] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:19:30,841] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:19:30,841] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:19:30,841] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:19:30,841] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:19:30,841] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +4: [2022-11-29 17:19:30,841] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:19:30,841] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:19:30,841] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:19:30,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:19:30,841] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:19:30,842] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:19:30,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:19:30,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:19:30,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:19:30,842] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +3: [2022-11-29 17:19:30,842] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +5: [2022-11-29 17:19:30,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:19:30,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:19:30,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:19:30,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:19:30,842] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +2: [2022-11-29 17:19:30,842] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +0: [2022-11-29 17:19:30,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:19:30,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:19:30,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:19:30,842] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:19:30,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:19:30,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:19:30,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:19:30,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:19:30,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:19:30,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:19:30,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:19:30,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:19:30,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:19:30,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:19:30,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:19:30,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:19:30,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:19:30,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:19:30,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:19:30,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:19:30,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:19:30,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:19:30,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:19:30,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:19:30,844] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:19:30,844] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:19:30,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:19:30,844] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:19:30,844] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:19:30,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:19:30,844] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:19:30,844] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-29 17:19:30,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:19:30,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:19:30,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-29 17:19:30,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:19:30,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:19:30,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-29 17:19:30,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:19:30,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:19:30,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:19:30,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-29 17:19:30,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:19:30,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:19:30,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:19:30,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +7: [2022-11-29 17:19:30,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:19:30,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:19:30,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:19:30,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-29 17:19:30,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +4: [2022-11-29 17:19:30,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +6: [2022-11-29 17:19:30,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +4: [2022-11-29 17:19:30,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:19:30,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:19:30,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:19:30,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-29 17:19:30,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:19:30,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-29 17:19:30,846] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:19:30,846] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:19:30,846] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:19:30,846] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:19:30,846] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:19:30,846] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-29 17:19:30,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:19:30,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step6000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:19:30,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: successfully saved checkpoint at iteration 6000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 257.00 +7: iteration 6010/ 37905 | consumed samples: 1538560 | consumed tokens: 3150970880 | elapsed time per iteration (s): 0.27 | learning rate: 1.902E-04 | global batch size: 256 | lm loss: 3.641363E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 953.735 | TFLOPs: 24.30 | +7: iteration 6020/ 37905 | consumed samples: 1541120 | consumed tokens: 3156213760 | elapsed time per iteration (s): 0.23 | learning rate: 1.901E-04 | global batch size: 256 | lm loss: 3.648610E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.871 | TFLOPs: 28.27 | +7: iteration 6030/ 37905 | consumed samples: 1543680 | consumed tokens: 3161456640 | elapsed time per iteration (s): 0.23 | learning rate: 1.901E-04 | global batch size: 256 | lm loss: 3.654965E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.883 | TFLOPs: 28.33 | +7: iteration 6040/ 37905 | consumed samples: 1546240 | consumed tokens: 3166699520 | elapsed time per iteration (s): 0.23 | learning rate: 1.901E-04 | global batch size: 256 | lm loss: 3.619186E+00 | grad norm: 0.388 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.288 | TFLOPs: 28.00 | +7: iteration 6050/ 37905 | consumed samples: 1548800 | consumed tokens: 3171942400 | elapsed time per iteration (s): 0.23 | learning rate: 1.900E-04 | global batch size: 256 | lm loss: 3.608242E+00 | grad norm: 0.439 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.471 | TFLOPs: 28.26 | +7: iteration 6060/ 37905 | consumed samples: 1551360 | consumed tokens: 3177185280 | elapsed time per iteration (s): 0.23 | learning rate: 1.900E-04 | global batch size: 256 | lm loss: 3.621099E+00 | grad norm: 0.432 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.140 | TFLOPs: 28.66 | +7: iteration 6070/ 37905 | consumed samples: 1553920 | consumed tokens: 3182428160 | elapsed time per iteration (s): 0.23 | learning rate: 1.900E-04 | global batch size: 256 | lm loss: 3.654621E+00 | grad norm: 0.423 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.629 | TFLOPs: 28.65 | +7: iteration 6080/ 37905 | consumed samples: 1556480 | consumed tokens: 3187671040 | elapsed time per iteration (s): 0.23 | learning rate: 1.899E-04 | global batch size: 256 | lm loss: 3.606671E+00 | grad norm: 0.386 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.292 | TFLOPs: 28.49 | +7: iteration 6090/ 37905 | consumed samples: 1559040 | consumed tokens: 3192913920 | elapsed time per iteration (s): 0.23 | learning rate: 1.899E-04 | global batch size: 256 | lm loss: 3.670622E+00 | grad norm: 0.404 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.414 | TFLOPs: 28.54 | +7: iteration 6100/ 37905 | consumed samples: 1561600 | consumed tokens: 3198156800 | elapsed time per iteration (s): 0.23 | learning rate: 1.899E-04 | global batch size: 256 | lm loss: 3.629451E+00 | grad norm: 0.463 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.726 | TFLOPs: 28.50 | +7: iteration 6110/ 37905 | consumed samples: 1564160 | consumed tokens: 3203399680 | elapsed time per iteration (s): 0.23 | learning rate: 1.898E-04 | global batch size: 256 | lm loss: 3.649725E+00 | grad norm: 0.409 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.708 | TFLOPs: 28.50 | +7: iteration 6120/ 37905 | consumed samples: 1566720 | consumed tokens: 3208642560 | elapsed time per iteration (s): 0.23 | learning rate: 1.898E-04 | global batch size: 256 | lm loss: 3.637720E+00 | grad norm: 0.494 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.521 | TFLOPs: 27.86 | +7: iteration 6130/ 37905 | consumed samples: 1569280 | consumed tokens: 3213885440 | elapsed time per iteration (s): 0.23 | learning rate: 1.898E-04 | global batch size: 256 | lm loss: 3.619389E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.665 | TFLOPs: 28.40 | +7: iteration 6140/ 37905 | consumed samples: 1571840 | consumed tokens: 3219128320 | elapsed time per iteration (s): 0.24 | learning rate: 1.897E-04 | global batch size: 256 | lm loss: 3.598787E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1056.226 | TFLOPs: 26.91 | +7: iteration 6150/ 37905 | consumed samples: 1574400 | consumed tokens: 3224371200 | elapsed time per iteration (s): 0.23 | learning rate: 1.897E-04 | global batch size: 256 | lm loss: 3.627451E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.155 | TFLOPs: 28.43 | +7: iteration 6160/ 37905 | consumed samples: 1576960 | consumed tokens: 3229614080 | elapsed time per iteration (s): 0.23 | learning rate: 1.897E-04 | global batch size: 256 | lm loss: 3.624932E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.532 | TFLOPs: 28.09 | +7: iteration 6170/ 37905 | consumed samples: 1579520 | consumed tokens: 3234856960 | elapsed time per iteration (s): 0.23 | learning rate: 1.896E-04 | global batch size: 256 | lm loss: 3.628566E+00 | grad norm: 0.402 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.058 | TFLOPs: 28.43 | +7: iteration 6180/ 37905 | consumed samples: 1582080 | consumed tokens: 3240099840 | elapsed time per iteration (s): 0.24 | learning rate: 1.896E-04 | global batch size: 256 | lm loss: 3.626834E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.555 | TFLOPs: 27.68 | +7: iteration 6190/ 37905 | consumed samples: 1584640 | consumed tokens: 3245342720 | elapsed time per iteration (s): 0.23 | learning rate: 1.896E-04 | global batch size: 256 | lm loss: 3.619679E+00 | grad norm: 0.419 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.358 | TFLOPs: 28.41 | +7: iteration 6200/ 37905 | consumed samples: 1587200 | consumed tokens: 3250585600 | elapsed time per iteration (s): 0.23 | learning rate: 1.895E-04 | global batch size: 256 | lm loss: 3.623315E+00 | grad norm: 0.391 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.450 | TFLOPs: 28.14 | +7: iteration 6210/ 37905 | consumed samples: 1589760 | consumed tokens: 3255828480 | elapsed time per iteration (s): 0.23 | learning rate: 1.895E-04 | global batch size: 256 | lm loss: 3.592810E+00 | grad norm: 0.456 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.563 | TFLOPs: 28.47 | +7: iteration 6220/ 37905 | consumed samples: 1592320 | consumed tokens: 3261071360 | elapsed time per iteration (s): 0.23 | learning rate: 1.895E-04 | global batch size: 256 | lm loss: 3.635892E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.227 | TFLOPs: 28.46 | +7: iteration 6230/ 37905 | consumed samples: 1594880 | consumed tokens: 3266314240 | elapsed time per iteration (s): 0.24 | learning rate: 1.894E-04 | global batch size: 256 | lm loss: 3.620508E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1079.505 | TFLOPs: 27.50 | +7: iteration 6240/ 37905 | consumed samples: 1597440 | consumed tokens: 3271557120 | elapsed time per iteration (s): 0.23 | learning rate: 1.894E-04 | global batch size: 256 | lm loss: 3.622697E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.760 | TFLOPs: 28.45 | +7: iteration 6250/ 37905 | consumed samples: 1600000 | consumed tokens: 3276800000 | elapsed time per iteration (s): 0.23 | learning rate: 1.893E-04 | global batch size: 256 | lm loss: 3.617753E+00 | grad norm: 0.482 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.284 | TFLOPs: 28.56 | +7: iteration 6260/ 37905 | consumed samples: 1602560 | consumed tokens: 3282042880 | elapsed time per iteration (s): 0.23 | learning rate: 1.893E-04 | global batch size: 256 | lm loss: 3.641975E+00 | grad norm: 0.582 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.911 | TFLOPs: 28.45 | +7: iteration 6270/ 37905 | consumed samples: 1605120 | consumed tokens: 3287285760 | elapsed time per iteration (s): 0.23 | learning rate: 1.893E-04 | global batch size: 256 | lm loss: 3.652054E+00 | grad norm: 0.404 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.622 | TFLOPs: 28.55 | +7: iteration 6280/ 37905 | consumed samples: 1607680 | consumed tokens: 3292528640 | elapsed time per iteration (s): 0.23 | learning rate: 1.892E-04 | global batch size: 256 | lm loss: 3.614227E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.266 | TFLOPs: 28.54 | +7: iteration 6290/ 37905 | consumed samples: 1610240 | consumed tokens: 3297771520 | elapsed time per iteration (s): 0.23 | learning rate: 1.892E-04 | global batch size: 256 | lm loss: 3.622277E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.796 | TFLOPs: 28.76 | +7: iteration 6300/ 37905 | consumed samples: 1612800 | consumed tokens: 3303014400 | elapsed time per iteration (s): 0.23 | learning rate: 1.892E-04 | global batch size: 256 | lm loss: 3.630286E+00 | grad norm: 0.389 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.706 | TFLOPs: 28.35 | +7: iteration 6310/ 37905 | consumed samples: 1615360 | consumed tokens: 3308257280 | elapsed time per iteration (s): 0.23 | learning rate: 1.891E-04 | global batch size: 256 | lm loss: 3.606479E+00 | grad norm: 0.429 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.190 | TFLOPs: 28.56 | +7: iteration 6320/ 37905 | consumed samples: 1617920 | consumed tokens: 3313500160 | elapsed time per iteration (s): 0.23 | learning rate: 1.891E-04 | global batch size: 256 | lm loss: 3.617262E+00 | grad norm: 0.514 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.519 | TFLOPs: 28.37 | +7: iteration 6330/ 37905 | consumed samples: 1620480 | consumed tokens: 3318743040 | elapsed time per iteration (s): 0.25 | learning rate: 1.891E-04 | global batch size: 256 | lm loss: 3.626129E+00 | grad norm: 0.419 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1032.029 | TFLOPs: 26.29 | +7: iteration 6340/ 37905 | consumed samples: 1623040 | consumed tokens: 3323985920 | elapsed time per iteration (s): 0.23 | learning rate: 1.890E-04 | global batch size: 256 | lm loss: 3.628249E+00 | grad norm: 0.423 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.497 | TFLOPs: 28.47 | +7: iteration 6350/ 37905 | consumed samples: 1625600 | consumed tokens: 3329228800 | elapsed time per iteration (s): 0.23 | learning rate: 1.890E-04 | global batch size: 256 | lm loss: 3.644070E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.150 | TFLOPs: 28.49 | +7: iteration 6360/ 37905 | consumed samples: 1628160 | consumed tokens: 3334471680 | elapsed time per iteration (s): 0.23 | learning rate: 1.890E-04 | global batch size: 256 | lm loss: 3.608164E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.899 | TFLOPs: 28.20 | +7: iteration 6370/ 37905 | consumed samples: 1630720 | consumed tokens: 3339714560 | elapsed time per iteration (s): 0.23 | learning rate: 1.889E-04 | global batch size: 256 | lm loss: 3.622717E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.352 | TFLOPs: 28.80 | +7: iteration 6380/ 37905 | consumed samples: 1633280 | consumed tokens: 3344957440 | elapsed time per iteration (s): 0.23 | learning rate: 1.889E-04 | global batch size: 256 | lm loss: 3.618995E+00 | grad norm: 0.449 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.697 | TFLOPs: 28.63 | +7: iteration 6390/ 37905 | consumed samples: 1635840 | consumed tokens: 3350200320 | elapsed time per iteration (s): 0.23 | learning rate: 1.888E-04 | global batch size: 256 | lm loss: 3.625623E+00 | grad norm: 0.390 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.590 | TFLOPs: 28.50 | +7: iteration 6400/ 37905 | consumed samples: 1638400 | consumed tokens: 3355443200 | elapsed time per iteration (s): 0.23 | learning rate: 1.888E-04 | global batch size: 256 | lm loss: 3.641678E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.136 | TFLOPs: 28.64 | +7: iteration 6410/ 37905 | consumed samples: 1640960 | consumed tokens: 3360686080 | elapsed time per iteration (s): 0.23 | learning rate: 1.888E-04 | global batch size: 256 | lm loss: 3.613782E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.683 | TFLOPs: 28.45 | +7: iteration 6420/ 37905 | consumed samples: 1643520 | consumed tokens: 3365928960 | elapsed time per iteration (s): 0.23 | learning rate: 1.887E-04 | global batch size: 256 | lm loss: 3.633855E+00 | grad norm: 0.392 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.714 | TFLOPs: 28.45 | +7: iteration 6430/ 37905 | consumed samples: 1646080 | consumed tokens: 3371171840 | elapsed time per iteration (s): 0.23 | learning rate: 1.887E-04 | global batch size: 256 | lm loss: 3.629103E+00 | grad norm: 0.488 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.529 | TFLOPs: 28.77 | +7: iteration 6440/ 37905 | consumed samples: 1648640 | consumed tokens: 3376414720 | elapsed time per iteration (s): 0.23 | learning rate: 1.887E-04 | global batch size: 256 | lm loss: 3.628586E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.494 | TFLOPs: 28.77 | +7: iteration 6450/ 37905 | consumed samples: 1651200 | consumed tokens: 3381657600 | elapsed time per iteration (s): 0.23 | learning rate: 1.886E-04 | global batch size: 256 | lm loss: 3.634642E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.540 | TFLOPs: 28.75 | +7: iteration 6460/ 37905 | consumed samples: 1653760 | consumed tokens: 3386900480 | elapsed time per iteration (s): 0.23 | learning rate: 1.886E-04 | global batch size: 256 | lm loss: 3.617236E+00 | grad norm: 0.418 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.333 | TFLOPs: 28.57 | +7: iteration 6470/ 37905 | consumed samples: 1656320 | consumed tokens: 3392143360 | elapsed time per iteration (s): 0.23 | learning rate: 1.886E-04 | global batch size: 256 | lm loss: 3.647353E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1131.457 | TFLOPs: 28.82 | +7: iteration 6480/ 37905 | consumed samples: 1658880 | consumed tokens: 3397386240 | elapsed time per iteration (s): 0.23 | learning rate: 1.885E-04 | global batch size: 256 | lm loss: 3.617330E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.766 | TFLOPs: 28.81 | +7: iteration 6490/ 37905 | consumed samples: 1661440 | consumed tokens: 3402629120 | elapsed time per iteration (s): 0.23 | learning rate: 1.885E-04 | global batch size: 256 | lm loss: 3.611432E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.745 | TFLOPs: 28.32 | +7: iteration 6500/ 37905 | consumed samples: 1664000 | consumed tokens: 3407872000 | elapsed time per iteration (s): 0.23 | learning rate: 1.884E-04 | global batch size: 256 | lm loss: 3.615106E+00 | grad norm: 0.368 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.185 | TFLOPs: 28.21 | +7: iteration 6510/ 37905 | consumed samples: 1666560 | consumed tokens: 3413114880 | elapsed time per iteration (s): 0.23 | learning rate: 1.884E-04 | global batch size: 256 | lm loss: 3.599561E+00 | grad norm: 0.422 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.675 | TFLOPs: 28.55 | +7: iteration 6520/ 37905 | consumed samples: 1669120 | consumed tokens: 3418357760 | elapsed time per iteration (s): 0.23 | learning rate: 1.884E-04 | global batch size: 256 | lm loss: 3.605353E+00 | grad norm: 0.459 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.005 | TFLOPs: 28.69 | +7: iteration 6530/ 37905 | consumed samples: 1671680 | consumed tokens: 3423600640 | elapsed time per iteration (s): 0.23 | learning rate: 1.883E-04 | global batch size: 256 | lm loss: 3.583400E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.255 | TFLOPs: 28.56 | +7: iteration 6540/ 37905 | consumed samples: 1674240 | consumed tokens: 3428843520 | elapsed time per iteration (s): 0.24 | learning rate: 1.883E-04 | global batch size: 256 | lm loss: 3.611374E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1084.749 | TFLOPs: 27.63 | +7: iteration 6550/ 37905 | consumed samples: 1676800 | consumed tokens: 3434086400 | elapsed time per iteration (s): 0.23 | learning rate: 1.883E-04 | global batch size: 256 | lm loss: 3.608021E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.868 | TFLOPs: 28.76 | +7: iteration 6560/ 37905 | consumed samples: 1679360 | consumed tokens: 3439329280 | elapsed time per iteration (s): 0.23 | learning rate: 1.882E-04 | global batch size: 256 | lm loss: 3.603741E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.586 | TFLOPs: 28.60 | +7: iteration 6570/ 37905 | consumed samples: 1681920 | consumed tokens: 3444572160 | elapsed time per iteration (s): 0.23 | learning rate: 1.882E-04 | global batch size: 256 | lm loss: 3.604083E+00 | grad norm: 0.498 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.067 | TFLOPs: 28.51 | +7: iteration 6580/ 37905 | consumed samples: 1684480 | consumed tokens: 3449815040 | elapsed time per iteration (s): 0.23 | learning rate: 1.881E-04 | global batch size: 256 | lm loss: 3.630143E+00 | grad norm: 0.508 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.187 | TFLOPs: 28.69 | +7: iteration 6590/ 37905 | consumed samples: 1687040 | consumed tokens: 3455057920 | elapsed time per iteration (s): 0.23 | learning rate: 1.881E-04 | global batch size: 256 | lm loss: 3.610541E+00 | grad norm: 0.415 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.166 | TFLOPs: 28.38 | +7: iteration 6600/ 37905 | consumed samples: 1689600 | consumed tokens: 3460300800 | elapsed time per iteration (s): 0.23 | learning rate: 1.881E-04 | global batch size: 256 | lm loss: 3.640758E+00 | grad norm: 0.390 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.975 | TFLOPs: 28.40 | +7: iteration 6610/ 37905 | consumed samples: 1692160 | consumed tokens: 3465543680 | elapsed time per iteration (s): 0.23 | learning rate: 1.880E-04 | global batch size: 256 | lm loss: 3.625893E+00 | grad norm: 0.449 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.539 | TFLOPs: 28.62 | +7: iteration 6620/ 37905 | consumed samples: 1694720 | consumed tokens: 3470786560 | elapsed time per iteration (s): 0.23 | learning rate: 1.880E-04 | global batch size: 256 | lm loss: 3.595380E+00 | grad norm: 0.394 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.328 | TFLOPs: 28.52 | +7: iteration 6630/ 37905 | consumed samples: 1697280 | consumed tokens: 3476029440 | elapsed time per iteration (s): 0.26 | learning rate: 1.880E-04 | global batch size: 256 | lm loss: 3.616960E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 978.033 | TFLOPs: 24.92 | +7: iteration 6640/ 37905 | consumed samples: 1699840 | consumed tokens: 3481272320 | elapsed time per iteration (s): 0.23 | learning rate: 1.879E-04 | global batch size: 256 | lm loss: 3.589185E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.551 | TFLOPs: 28.47 | +7: iteration 6650/ 37905 | consumed samples: 1702400 | consumed tokens: 3486515200 | elapsed time per iteration (s): 0.23 | learning rate: 1.879E-04 | global batch size: 256 | lm loss: 3.611912E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.302 | TFLOPs: 28.26 | +7: iteration 6660/ 37905 | consumed samples: 1704960 | consumed tokens: 3491758080 | elapsed time per iteration (s): 0.24 | learning rate: 1.878E-04 | global batch size: 256 | lm loss: 3.622676E+00 | grad norm: 0.390 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1080.774 | TFLOPs: 27.53 | +7: iteration 6670/ 37905 | consumed samples: 1707520 | consumed tokens: 3497000960 | elapsed time per iteration (s): 0.24 | learning rate: 1.878E-04 | global batch size: 256 | lm loss: 3.605685E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1074.164 | TFLOPs: 27.36 | +7: iteration 6680/ 37905 | consumed samples: 1710080 | consumed tokens: 3502243840 | elapsed time per iteration (s): 0.23 | learning rate: 1.878E-04 | global batch size: 256 | lm loss: 3.612669E+00 | grad norm: 0.390 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.574 | TFLOPs: 28.01 | +7: iteration 6690/ 37905 | consumed samples: 1712640 | consumed tokens: 3507486720 | elapsed time per iteration (s): 0.23 | learning rate: 1.877E-04 | global batch size: 256 | lm loss: 3.615334E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.386 | TFLOPs: 28.06 | +7: iteration 6700/ 37905 | consumed samples: 1715200 | consumed tokens: 3512729600 | elapsed time per iteration (s): 0.23 | learning rate: 1.877E-04 | global batch size: 256 | lm loss: 3.581186E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.678 | TFLOPs: 28.37 | +7: iteration 6710/ 37905 | consumed samples: 1717760 | consumed tokens: 3517972480 | elapsed time per iteration (s): 0.23 | learning rate: 1.877E-04 | global batch size: 256 | lm loss: 3.620737E+00 | grad norm: 0.403 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.468 | TFLOPs: 28.06 | +7: iteration 6720/ 37905 | consumed samples: 1720320 | consumed tokens: 3523215360 | elapsed time per iteration (s): 0.24 | learning rate: 1.876E-04 | global batch size: 256 | lm loss: 3.588200E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.368 | TFLOPs: 27.70 | +7: iteration 6730/ 37905 | consumed samples: 1722880 | consumed tokens: 3528458240 | elapsed time per iteration (s): 0.23 | learning rate: 1.876E-04 | global batch size: 256 | lm loss: 3.608065E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.351 | TFLOPs: 28.06 | +7: iteration 6740/ 37905 | consumed samples: 1725440 | consumed tokens: 3533701120 | elapsed time per iteration (s): 0.23 | learning rate: 1.875E-04 | global batch size: 256 | lm loss: 3.622769E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.357 | TFLOPs: 28.52 | +7: iteration 6750/ 37905 | consumed samples: 1728000 | consumed tokens: 3538944000 | elapsed time per iteration (s): 0.23 | learning rate: 1.875E-04 | global batch size: 256 | lm loss: 3.610967E+00 | grad norm: 0.367 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.976 | TFLOPs: 28.63 | +7: iteration 6760/ 37905 | consumed samples: 1730560 | consumed tokens: 3544186880 | elapsed time per iteration (s): 0.23 | learning rate: 1.875E-04 | global batch size: 256 | lm loss: 3.604995E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.534 | TFLOPs: 28.70 | +7: iteration 6770/ 37905 | consumed samples: 1733120 | consumed tokens: 3549429760 | elapsed time per iteration (s): 0.23 | learning rate: 1.874E-04 | global batch size: 256 | lm loss: 3.623684E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.127 | TFLOPs: 28.74 | +7: iteration 6780/ 37905 | consumed samples: 1735680 | consumed tokens: 3554672640 | elapsed time per iteration (s): 0.23 | learning rate: 1.874E-04 | global batch size: 256 | lm loss: 3.583275E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.074 | TFLOPs: 28.69 | +7: iteration 6790/ 37905 | consumed samples: 1738240 | consumed tokens: 3559915520 | elapsed time per iteration (s): 0.25 | learning rate: 1.873E-04 | global batch size: 256 | lm loss: 3.595204E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1043.694 | TFLOPs: 26.59 | +7: iteration 6800/ 37905 | consumed samples: 1740800 | consumed tokens: 3565158400 | elapsed time per iteration (s): 0.23 | learning rate: 1.873E-04 | global batch size: 256 | lm loss: 3.646446E+00 | grad norm: 0.403 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.545 | TFLOPs: 28.67 | +7: iteration 6810/ 37905 | consumed samples: 1743360 | consumed tokens: 3570401280 | elapsed time per iteration (s): 0.23 | learning rate: 1.873E-04 | global batch size: 256 | lm loss: 3.583052E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.257 | TFLOPs: 28.62 | +7: iteration 6820/ 37905 | consumed samples: 1745920 | consumed tokens: 3575644160 | elapsed time per iteration (s): 0.23 | learning rate: 1.872E-04 | global batch size: 256 | lm loss: 3.609708E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.950 | TFLOPs: 27.89 | +7: iteration 6830/ 37905 | consumed samples: 1748480 | consumed tokens: 3580887040 | elapsed time per iteration (s): 0.23 | learning rate: 1.872E-04 | global batch size: 256 | lm loss: 3.604424E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.317 | TFLOPs: 28.46 | +7: iteration 6840/ 37905 | consumed samples: 1751040 | consumed tokens: 3586129920 | elapsed time per iteration (s): 0.23 | learning rate: 1.872E-04 | global batch size: 256 | lm loss: 3.609803E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.286 | TFLOPs: 28.41 | +7: iteration 6850/ 37905 | consumed samples: 1753600 | consumed tokens: 3591372800 | elapsed time per iteration (s): 0.23 | learning rate: 1.871E-04 | global batch size: 256 | lm loss: 3.590874E+00 | grad norm: 0.389 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.568 | TFLOPs: 28.11 | +7: iteration 6860/ 37905 | consumed samples: 1756160 | consumed tokens: 3596615680 | elapsed time per iteration (s): 0.24 | learning rate: 1.871E-04 | global batch size: 256 | lm loss: 3.570658E+00 | grad norm: 0.410 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1055.686 | TFLOPs: 26.89 | +7: iteration 6870/ 37905 | consumed samples: 1758720 | consumed tokens: 3601858560 | elapsed time per iteration (s): 0.23 | learning rate: 1.870E-04 | global batch size: 256 | lm loss: 3.571068E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.191 | TFLOPs: 28.41 | +7: iteration 6880/ 37905 | consumed samples: 1761280 | consumed tokens: 3607101440 | elapsed time per iteration (s): 0.41 | learning rate: 1.870E-04 | global batch size: 256 | lm loss: 3.578853E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 619.677 | TFLOPs: 15.79 | +7: iteration 6890/ 37905 | consumed samples: 1763840 | consumed tokens: 3612344320 | elapsed time per iteration (s): 0.25 | learning rate: 1.870E-04 | global batch size: 256 | lm loss: 3.600730E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1010.417 | TFLOPs: 25.74 | +7: iteration 6900/ 37905 | consumed samples: 1766400 | consumed tokens: 3617587200 | elapsed time per iteration (s): 0.24 | learning rate: 1.869E-04 | global batch size: 256 | lm loss: 3.603781E+00 | grad norm: 0.464 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.217 | TFLOPs: 27.65 | +7: iteration 6910/ 37905 | consumed samples: 1768960 | consumed tokens: 3622830080 | elapsed time per iteration (s): 0.23 | learning rate: 1.869E-04 | global batch size: 256 | lm loss: 3.588533E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.898 | TFLOPs: 28.38 | +7: iteration 6920/ 37905 | consumed samples: 1771520 | consumed tokens: 3628072960 | elapsed time per iteration (s): 0.25 | learning rate: 1.868E-04 | global batch size: 256 | lm loss: 3.602095E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1034.091 | TFLOPs: 26.34 | +7: iteration 6930/ 37905 | consumed samples: 1774080 | consumed tokens: 3633315840 | elapsed time per iteration (s): 0.23 | learning rate: 1.868E-04 | global batch size: 256 | lm loss: 3.593980E+00 | grad norm: 0.377 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.672 | TFLOPs: 28.60 | +7: iteration 6940/ 37905 | consumed samples: 1776640 | consumed tokens: 3638558720 | elapsed time per iteration (s): 0.23 | learning rate: 1.868E-04 | global batch size: 256 | lm loss: 3.585352E+00 | grad norm: 0.373 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.791 | TFLOPs: 28.65 | +7: iteration 6950/ 37905 | consumed samples: 1779200 | consumed tokens: 3643801600 | elapsed time per iteration (s): 0.23 | learning rate: 1.867E-04 | global batch size: 256 | lm loss: 3.600976E+00 | grad norm: 0.402 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.252 | TFLOPs: 28.72 | +7: iteration 6960/ 37905 | consumed samples: 1781760 | consumed tokens: 3649044480 | elapsed time per iteration (s): 0.23 | learning rate: 1.867E-04 | global batch size: 256 | lm loss: 3.575187E+00 | grad norm: 0.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.280 | TFLOPs: 28.28 | +7: iteration 6970/ 37905 | consumed samples: 1784320 | consumed tokens: 3654287360 | elapsed time per iteration (s): 0.23 | learning rate: 1.866E-04 | global batch size: 256 | lm loss: 3.590238E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.031 | TFLOPs: 28.61 | +7: iteration 6980/ 37905 | consumed samples: 1786880 | consumed tokens: 3659530240 | elapsed time per iteration (s): 0.24 | learning rate: 1.866E-04 | global batch size: 256 | lm loss: 3.563960E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1075.796 | TFLOPs: 27.41 | +7: iteration 6990/ 37905 | consumed samples: 1789440 | consumed tokens: 3664773120 | elapsed time per iteration (s): 0.23 | learning rate: 1.866E-04 | global batch size: 256 | lm loss: 3.581097E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.033 | TFLOPs: 28.23 | +7: iteration 7000/ 37905 | consumed samples: 1792000 | consumed tokens: 3670016000 | elapsed time per iteration (s): 0.23 | learning rate: 1.865E-04 | global batch size: 256 | lm loss: 3.597299E+00 | grad norm: 0.409 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.071 | TFLOPs: 28.51 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 7000 | lm loss value: 3.456590E+00 | lm loss PPL: 3.170866E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 7000 to checkpoints_83moscar +0: [2022-11-29 17:23:23,931] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step7000 is begin to save! +0: [2022-11-29 17:23:23,934] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:23:24,005] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:23:24,006] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:23:24,017] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:23:24,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:23:24,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:23:24,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:23:24,040] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:23:24,041] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:23:24,052] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:23:24,052] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:23:24,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:23:24,063] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:23:24,075] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:23:24,075] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:23:24,086] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:23:24,086] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:23:24,097] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:23:24,098] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:23:24,109] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:23:24,109] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:23:24,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:23:24,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:23:24,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:23:24,122] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step7000/mp_rank_00_model_states.pt +0: [2022-11-29 17:23:24,122] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:23:24,124] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:23:24,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:23:24,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:23:24,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:23:24,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:23:24,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 17:23:24,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:23:24,160] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +2: [2022-11-29 17:23:24,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:23:24,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:23:24,160] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:23:24,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 17:23:24,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:23:24,160] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:23:24,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:23:24,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:23:24,160] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +1: [2022-11-29 17:23:24,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:23:24,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 17:23:24,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:23:24,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 17:23:24,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:23:24,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +0: [2022-11-29 17:23:24,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +7: [2022-11-29 17:23:24,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:23:24,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:23:24,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:23:24,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +6: [2022-11-29 17:23:24,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:23:24,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:23:24,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:23:24,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:23:24,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:23:24,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:23:24,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:23:24,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:23:24,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:23:24,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:23:24,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:23:24,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:23:24,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 17:23:24,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:23:24,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:23:24,162] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +5: [2022-11-29 17:23:24,162] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +1: [2022-11-29 17:23:24,162] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:23:24,162] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:23:24,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:23:24,162] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:23:24,162] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:23:24,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:23:24,162] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:23:24,162] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:23:24,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:23:24,163] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:23:24,163] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:23:24,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:23:24,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:23:24,163] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +6: [2022-11-29 17:23:24,163] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +3: [2022-11-29 17:23:24,163] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 17:23:24,163] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 17:23:24,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:23:24,163] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:23:24,163] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:23:24,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:23:24,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:23:24,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:23:24,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:23:24,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +6: [2022-11-29 17:23:24,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:23:24,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:23:24,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +4: [2022-11-29 17:23:24,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 17:23:24,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +1: [2022-11-29 17:23:24,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:23:24,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 17:23:24,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 17:23:24,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +0: [2022-11-29 17:23:24,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:23:24,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +1: [2022-11-29 17:23:24,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:23:24,165] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:23:24,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:23:24,165] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:23:24,165] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:23:24,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:23:24,165] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:23:24,165] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 17:23:24,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:23:24,165] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:23:24,165] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:23:24,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:23:24,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:23:24,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +5: [2022-11-29 17:23:24,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +0: [2022-11-29 17:23:24,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:23:24,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:23:24,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:23:24,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:23:24,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:23:24,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:23:24,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:23:24,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +7: [2022-11-29 17:23:24,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:23:24,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:23:24,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:23:24,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:23:24,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:23:24,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:23:24,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:23:24,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:23:24,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +7: [2022-11-29 17:23:24,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +3: [2022-11-29 17:23:24,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:23:24,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:23:24,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:23:24,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:23:24,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:23:24,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:23:24,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +6: [2022-11-29 17:23:24,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:23:24,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 17:23:24,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:23:24,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 17:23:24,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:23:24,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:23:24,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:23:24,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:23:24,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:23:24,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 17:23:24,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:23:24,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:23:24,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:23:24,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 17:23:24,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:23:24,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 17:23:24,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:23:24,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:23:24,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +0: [2022-11-29 17:23:24,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +6: [2022-11-29 17:23:24,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:23:24,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:23:24,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:23:24,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:23:24,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:23:24,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:23:24,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:23:24,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:23:24,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:23:24,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:23:24,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-29 17:23:24,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:23:24,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:23:24,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:23:24,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:23:24,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:23:24,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-29 17:23:24,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:23:24,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:23:24,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-29 17:23:24,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:23:24,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:23:24,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:23:24,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:23:24,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:23:24,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:23:24,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:23:24,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:23:24,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +6: [2022-11-29 17:23:24,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +3: [2022-11-29 17:23:24,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:23:24,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:23:24,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:23:24,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-29 17:23:24,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +4: [2022-11-29 17:23:24,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:23:24,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:23:24,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:23:24,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-29 17:23:24,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:23:24,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-29 17:23:24,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:23:24,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:23:24,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 17:23:24,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:23:24,171] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:23:24,171] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-29 17:23:24,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:23:24,173] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:23:24,173] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-29 17:23:24,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:23:24,173] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step7000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:23:24,174] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: successfully saved checkpoint at iteration 7000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 246.13 +7: iteration 7010/ 37905 | consumed samples: 1794560 | consumed tokens: 3675258880 | elapsed time per iteration (s): 0.26 | learning rate: 1.865E-04 | global batch size: 256 | lm loss: 3.613521E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 984.930 | TFLOPs: 25.09 | +7: iteration 7020/ 37905 | consumed samples: 1797120 | consumed tokens: 3680501760 | elapsed time per iteration (s): 0.24 | learning rate: 1.864E-04 | global batch size: 256 | lm loss: 3.592219E+00 | grad norm: 0.454 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1084.413 | TFLOPs: 27.63 | +7: iteration 7030/ 37905 | consumed samples: 1799680 | consumed tokens: 3685744640 | elapsed time per iteration (s): 0.23 | learning rate: 1.864E-04 | global batch size: 256 | lm loss: 3.595504E+00 | grad norm: 0.437 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.067 | TFLOPs: 28.05 | +7: iteration 7040/ 37905 | consumed samples: 1802240 | consumed tokens: 3690987520 | elapsed time per iteration (s): 0.23 | learning rate: 1.864E-04 | global batch size: 256 | lm loss: 3.598822E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.420 | TFLOPs: 28.39 | +7: iteration 7050/ 37905 | consumed samples: 1804800 | consumed tokens: 3696230400 | elapsed time per iteration (s): 0.23 | learning rate: 1.863E-04 | global batch size: 256 | lm loss: 3.599555E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.419 | TFLOPs: 28.42 | +7: iteration 7060/ 37905 | consumed samples: 1807360 | consumed tokens: 3701473280 | elapsed time per iteration (s): 0.23 | learning rate: 1.863E-04 | global batch size: 256 | lm loss: 3.603368E+00 | grad norm: 0.396 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.257 | TFLOPs: 28.00 | +7: iteration 7070/ 37905 | consumed samples: 1809920 | consumed tokens: 3706716160 | elapsed time per iteration (s): 0.28 | learning rate: 1.862E-04 | global batch size: 256 | lm loss: 3.573381E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 915.135 | TFLOPs: 23.31 | +7: iteration 7080/ 37905 | consumed samples: 1812480 | consumed tokens: 3711959040 | elapsed time per iteration (s): 0.23 | learning rate: 1.862E-04 | global batch size: 256 | lm loss: 3.589729E+00 | grad norm: 0.410 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.735 | TFLOPs: 28.40 | +7: iteration 7090/ 37905 | consumed samples: 1815040 | consumed tokens: 3717201920 | elapsed time per iteration (s): 0.23 | learning rate: 1.862E-04 | global batch size: 256 | lm loss: 3.587608E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.315 | TFLOPs: 28.23 | +7: iteration 7100/ 37905 | consumed samples: 1817600 | consumed tokens: 3722444800 | elapsed time per iteration (s): 0.23 | learning rate: 1.861E-04 | global batch size: 256 | lm loss: 3.586287E+00 | grad norm: 0.405 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.238 | TFLOPs: 28.64 | +7: iteration 7110/ 37905 | consumed samples: 1820160 | consumed tokens: 3727687680 | elapsed time per iteration (s): 0.23 | learning rate: 1.861E-04 | global batch size: 256 | lm loss: 3.606772E+00 | grad norm: 0.445 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.454 | TFLOPs: 27.88 | +7: iteration 7120/ 37905 | consumed samples: 1822720 | consumed tokens: 3732930560 | elapsed time per iteration (s): 0.23 | learning rate: 1.860E-04 | global batch size: 256 | lm loss: 3.613672E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.332 | TFLOPs: 28.49 | +7: iteration 7130/ 37905 | consumed samples: 1825280 | consumed tokens: 3738173440 | elapsed time per iteration (s): 0.23 | learning rate: 1.860E-04 | global batch size: 256 | lm loss: 3.606180E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.723 | TFLOPs: 28.47 | +7: iteration 7140/ 37905 | consumed samples: 1827840 | consumed tokens: 3743416320 | elapsed time per iteration (s): 0.23 | learning rate: 1.860E-04 | global batch size: 256 | lm loss: 3.591251E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.289 | TFLOPs: 27.85 | +7: iteration 7150/ 37905 | consumed samples: 1830400 | consumed tokens: 3748659200 | elapsed time per iteration (s): 0.23 | learning rate: 1.859E-04 | global batch size: 256 | lm loss: 3.595513E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.731 | TFLOPs: 28.22 | +7: iteration 7160/ 37905 | consumed samples: 1832960 | consumed tokens: 3753902080 | elapsed time per iteration (s): 0.23 | learning rate: 1.859E-04 | global batch size: 256 | lm loss: 3.594078E+00 | grad norm: 0.403 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.960 | TFLOPs: 27.97 | +7: iteration 7170/ 37905 | consumed samples: 1835520 | consumed tokens: 3759144960 | elapsed time per iteration (s): 0.23 | learning rate: 1.858E-04 | global batch size: 256 | lm loss: 3.575453E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.040 | TFLOPs: 27.92 | +7: iteration 7180/ 37905 | consumed samples: 1838080 | consumed tokens: 3764387840 | elapsed time per iteration (s): 0.24 | learning rate: 1.858E-04 | global batch size: 256 | lm loss: 3.575661E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1060.750 | TFLOPs: 27.02 | +7: iteration 7190/ 37905 | consumed samples: 1840640 | consumed tokens: 3769630720 | elapsed time per iteration (s): 0.25 | learning rate: 1.858E-04 | global batch size: 256 | lm loss: 3.619476E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1031.418 | TFLOPs: 26.28 | +7: iteration 7200/ 37905 | consumed samples: 1843200 | consumed tokens: 3774873600 | elapsed time per iteration (s): 0.23 | learning rate: 1.857E-04 | global batch size: 256 | lm loss: 3.553868E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.649 | TFLOPs: 28.14 | +7: iteration 7210/ 37905 | consumed samples: 1845760 | consumed tokens: 3780116480 | elapsed time per iteration (s): 0.23 | learning rate: 1.857E-04 | global batch size: 256 | lm loss: 3.616721E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.115 | TFLOPs: 28.38 | +7: iteration 7220/ 37905 | consumed samples: 1848320 | consumed tokens: 3785359360 | elapsed time per iteration (s): 0.23 | learning rate: 1.856E-04 | global batch size: 256 | lm loss: 3.582661E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.932 | TFLOPs: 28.45 | +7: iteration 7230/ 37905 | consumed samples: 1850880 | consumed tokens: 3790602240 | elapsed time per iteration (s): 0.23 | learning rate: 1.856E-04 | global batch size: 256 | lm loss: 3.582299E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.029 | TFLOPs: 28.05 | +7: iteration 7240/ 37905 | consumed samples: 1853440 | consumed tokens: 3795845120 | elapsed time per iteration (s): 0.25 | learning rate: 1.856E-04 | global batch size: 256 | lm loss: 3.567140E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1017.620 | TFLOPs: 25.92 | +7: iteration 7250/ 37905 | consumed samples: 1856000 | consumed tokens: 3801088000 | elapsed time per iteration (s): 0.23 | learning rate: 1.855E-04 | global batch size: 256 | lm loss: 3.596221E+00 | grad norm: 0.414 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.620 | TFLOPs: 28.52 | +7: iteration 7260/ 37905 | consumed samples: 1858560 | consumed tokens: 3806330880 | elapsed time per iteration (s): 0.23 | learning rate: 1.855E-04 | global batch size: 256 | lm loss: 3.578122E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.323 | TFLOPs: 27.98 | +7: iteration 7270/ 37905 | consumed samples: 1861120 | consumed tokens: 3811573760 | elapsed time per iteration (s): 0.25 | learning rate: 1.854E-04 | global batch size: 256 | lm loss: 3.602182E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1007.607 | TFLOPs: 25.67 | +7: iteration 7280/ 37905 | consumed samples: 1863680 | consumed tokens: 3816816640 | elapsed time per iteration (s): 0.23 | learning rate: 1.854E-04 | global batch size: 256 | lm loss: 3.565316E+00 | grad norm: 0.388 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.593 | TFLOPs: 28.06 | +7: iteration 7290/ 37905 | consumed samples: 1866240 | consumed tokens: 3822059520 | elapsed time per iteration (s): 0.36 | learning rate: 1.854E-04 | global batch size: 256 | lm loss: 3.584487E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 707.579 | TFLOPs: 18.03 | +7: iteration 7300/ 37905 | consumed samples: 1868800 | consumed tokens: 3827302400 | elapsed time per iteration (s): 0.23 | learning rate: 1.853E-04 | global batch size: 256 | lm loss: 3.598069E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.014 | TFLOPs: 27.87 | +7: iteration 7310/ 37905 | consumed samples: 1871360 | consumed tokens: 3832545280 | elapsed time per iteration (s): 0.23 | learning rate: 1.853E-04 | global batch size: 256 | lm loss: 3.580624E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.779 | TFLOPs: 28.30 | +7: iteration 7320/ 37905 | consumed samples: 1873920 | consumed tokens: 3837788160 | elapsed time per iteration (s): 0.23 | learning rate: 1.852E-04 | global batch size: 256 | lm loss: 3.589371E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.345 | TFLOPs: 28.44 | +7: iteration 7330/ 37905 | consumed samples: 1876480 | consumed tokens: 3843031040 | elapsed time per iteration (s): 0.23 | learning rate: 1.852E-04 | global batch size: 256 | lm loss: 3.570049E+00 | grad norm: 0.388 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.318 | TFLOPs: 28.34 | +7: iteration 7340/ 37905 | consumed samples: 1879040 | consumed tokens: 3848273920 | elapsed time per iteration (s): 0.23 | learning rate: 1.851E-04 | global batch size: 256 | lm loss: 3.562664E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.844 | TFLOPs: 28.50 | +7: iteration 7350/ 37905 | consumed samples: 1881600 | consumed tokens: 3853516800 | elapsed time per iteration (s): 0.23 | learning rate: 1.851E-04 | global batch size: 256 | lm loss: 3.605208E+00 | grad norm: 0.377 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.767 | TFLOPs: 28.48 | +7: iteration 7360/ 37905 | consumed samples: 1884160 | consumed tokens: 3858759680 | elapsed time per iteration (s): 0.23 | learning rate: 1.851E-04 | global batch size: 256 | lm loss: 3.599152E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.411 | TFLOPs: 28.47 | +7: iteration 7370/ 37905 | consumed samples: 1886720 | consumed tokens: 3864002560 | elapsed time per iteration (s): 0.23 | learning rate: 1.850E-04 | global batch size: 256 | lm loss: 3.573008E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.395 | TFLOPs: 28.49 | +7: iteration 7380/ 37905 | consumed samples: 1889280 | consumed tokens: 3869245440 | elapsed time per iteration (s): 0.23 | learning rate: 1.850E-04 | global batch size: 256 | lm loss: 3.570974E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.713 | TFLOPs: 28.50 | +7: iteration 7390/ 37905 | consumed samples: 1891840 | consumed tokens: 3874488320 | elapsed time per iteration (s): 0.23 | learning rate: 1.849E-04 | global batch size: 256 | lm loss: 3.560999E+00 | grad norm: 0.382 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.425 | TFLOPs: 28.47 | +7: iteration 7400/ 37905 | consumed samples: 1894400 | consumed tokens: 3879731200 | elapsed time per iteration (s): 0.23 | learning rate: 1.849E-04 | global batch size: 256 | lm loss: 3.568955E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.133 | TFLOPs: 28.56 | +7: iteration 7410/ 37905 | consumed samples: 1896960 | consumed tokens: 3884974080 | elapsed time per iteration (s): 0.23 | learning rate: 1.849E-04 | global batch size: 256 | lm loss: 3.560953E+00 | grad norm: 0.423 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.339 | TFLOPs: 28.24 | +7: iteration 7420/ 37905 | consumed samples: 1899520 | consumed tokens: 3890216960 | elapsed time per iteration (s): 0.24 | learning rate: 1.848E-04 | global batch size: 256 | lm loss: 3.569912E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.316 | TFLOPs: 26.94 | +7: iteration 7430/ 37905 | consumed samples: 1902080 | consumed tokens: 3895459840 | elapsed time per iteration (s): 0.23 | learning rate: 1.848E-04 | global batch size: 256 | lm loss: 3.584498E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.707 | TFLOPs: 28.30 | +7: iteration 7440/ 37905 | consumed samples: 1904640 | consumed tokens: 3900702720 | elapsed time per iteration (s): 0.23 | learning rate: 1.847E-04 | global batch size: 256 | lm loss: 3.572142E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.739 | TFLOPs: 28.17 | +7: iteration 7450/ 37905 | consumed samples: 1907200 | consumed tokens: 3905945600 | elapsed time per iteration (s): 0.23 | learning rate: 1.847E-04 | global batch size: 256 | lm loss: 3.582510E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.883 | TFLOPs: 28.27 | +7: iteration 7460/ 37905 | consumed samples: 1909760 | consumed tokens: 3911188480 | elapsed time per iteration (s): 0.23 | learning rate: 1.846E-04 | global batch size: 256 | lm loss: 3.595969E+00 | grad norm: 0.421 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.418 | TFLOPs: 28.26 | +7: iteration 7470/ 37905 | consumed samples: 1912320 | consumed tokens: 3916431360 | elapsed time per iteration (s): 0.23 | learning rate: 1.846E-04 | global batch size: 256 | lm loss: 3.578648E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.747 | TFLOPs: 28.45 | +7: iteration 7480/ 37905 | consumed samples: 1914880 | consumed tokens: 3921674240 | elapsed time per iteration (s): 0.23 | learning rate: 1.846E-04 | global batch size: 256 | lm loss: 3.548315E+00 | grad norm: 0.394 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.536 | TFLOPs: 28.34 | +7: iteration 7490/ 37905 | consumed samples: 1917440 | consumed tokens: 3926917120 | elapsed time per iteration (s): 0.23 | learning rate: 1.845E-04 | global batch size: 256 | lm loss: 3.570515E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.237 | TFLOPs: 28.41 | +7: iteration 7500/ 37905 | consumed samples: 1920000 | consumed tokens: 3932160000 | elapsed time per iteration (s): 0.23 | learning rate: 1.845E-04 | global batch size: 256 | lm loss: 3.580798E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.193 | TFLOPs: 28.33 | +7: iteration 7510/ 37905 | consumed samples: 1922560 | consumed tokens: 3937402880 | elapsed time per iteration (s): 0.23 | learning rate: 1.844E-04 | global batch size: 256 | lm loss: 3.566772E+00 | grad norm: 0.409 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.855 | TFLOPs: 28.40 | +7: iteration 7520/ 37905 | consumed samples: 1925120 | consumed tokens: 3942645760 | elapsed time per iteration (s): 0.23 | learning rate: 1.844E-04 | global batch size: 256 | lm loss: 3.583820E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.446 | TFLOPs: 28.24 | +7: iteration 7530/ 37905 | consumed samples: 1927680 | consumed tokens: 3947888640 | elapsed time per iteration (s): 0.23 | learning rate: 1.843E-04 | global batch size: 256 | lm loss: 3.571982E+00 | grad norm: 0.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.969 | TFLOPs: 28.45 | +7: iteration 7540/ 37905 | consumed samples: 1930240 | consumed tokens: 3953131520 | elapsed time per iteration (s): 0.23 | learning rate: 1.843E-04 | global batch size: 256 | lm loss: 3.586969E+00 | grad norm: 0.447 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.146 | TFLOPs: 28.05 | +7: iteration 7550/ 37905 | consumed samples: 1932800 | consumed tokens: 3958374400 | elapsed time per iteration (s): 0.23 | learning rate: 1.843E-04 | global batch size: 256 | lm loss: 3.573920E+00 | grad norm: 0.422 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.980 | TFLOPs: 28.15 | +7: iteration 7560/ 37905 | consumed samples: 1935360 | consumed tokens: 3963617280 | elapsed time per iteration (s): 0.23 | learning rate: 1.842E-04 | global batch size: 256 | lm loss: 3.569246E+00 | grad norm: 0.380 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.214 | TFLOPs: 28.00 | +7: iteration 7570/ 37905 | consumed samples: 1937920 | consumed tokens: 3968860160 | elapsed time per iteration (s): 0.23 | learning rate: 1.842E-04 | global batch size: 256 | lm loss: 3.581779E+00 | grad norm: 0.437 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.967 | TFLOPs: 28.58 | +7: iteration 7580/ 37905 | consumed samples: 1940480 | consumed tokens: 3974103040 | elapsed time per iteration (s): 0.23 | learning rate: 1.841E-04 | global batch size: 256 | lm loss: 3.577839E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.757 | TFLOPs: 28.04 | +7: iteration 7590/ 37905 | consumed samples: 1943040 | consumed tokens: 3979345920 | elapsed time per iteration (s): 0.23 | learning rate: 1.841E-04 | global batch size: 256 | lm loss: 3.552192E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.548 | TFLOPs: 28.39 | +7: iteration 7600/ 37905 | consumed samples: 1945600 | consumed tokens: 3984588800 | elapsed time per iteration (s): 0.23 | learning rate: 1.840E-04 | global batch size: 256 | lm loss: 3.552536E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.678 | TFLOPs: 28.32 | +7: iteration 7610/ 37905 | consumed samples: 1948160 | consumed tokens: 3989831680 | elapsed time per iteration (s): 0.23 | learning rate: 1.840E-04 | global batch size: 256 | lm loss: 3.580613E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.359 | TFLOPs: 28.52 | +7: iteration 7620/ 37905 | consumed samples: 1950720 | consumed tokens: 3995074560 | elapsed time per iteration (s): 0.23 | learning rate: 1.840E-04 | global batch size: 256 | lm loss: 3.569881E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.965 | TFLOPs: 28.05 | +7: iteration 7630/ 37905 | consumed samples: 1953280 | consumed tokens: 4000317440 | elapsed time per iteration (s): 0.23 | learning rate: 1.839E-04 | global batch size: 256 | lm loss: 3.579908E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.354 | TFLOPs: 28.01 | +7: iteration 7640/ 37905 | consumed samples: 1955840 | consumed tokens: 4005560320 | elapsed time per iteration (s): 0.23 | learning rate: 1.839E-04 | global batch size: 256 | lm loss: 3.581117E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.231 | TFLOPs: 28.16 | +7: iteration 7650/ 37905 | consumed samples: 1958400 | consumed tokens: 4010803200 | elapsed time per iteration (s): 0.23 | learning rate: 1.838E-04 | global batch size: 256 | lm loss: 3.578916E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.722 | TFLOPs: 28.50 | +7: iteration 7660/ 37905 | consumed samples: 1960960 | consumed tokens: 4016046080 | elapsed time per iteration (s): 0.23 | learning rate: 1.838E-04 | global batch size: 256 | lm loss: 3.595059E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.685 | TFLOPs: 28.24 | +7: iteration 7670/ 37905 | consumed samples: 1963520 | consumed tokens: 4021288960 | elapsed time per iteration (s): 0.23 | learning rate: 1.837E-04 | global batch size: 256 | lm loss: 3.596660E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.262 | TFLOPs: 28.21 | +7: iteration 7680/ 37905 | consumed samples: 1966080 | consumed tokens: 4026531840 | elapsed time per iteration (s): 0.26 | learning rate: 1.837E-04 | global batch size: 256 | lm loss: 3.554920E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 984.974 | TFLOPs: 25.09 | +7: iteration 7690/ 37905 | consumed samples: 1968640 | consumed tokens: 4031774720 | elapsed time per iteration (s): 0.23 | learning rate: 1.837E-04 | global batch size: 256 | lm loss: 3.537382E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.986 | TFLOPs: 28.35 | +7: iteration 7700/ 37905 | consumed samples: 1971200 | consumed tokens: 4037017600 | elapsed time per iteration (s): 0.24 | learning rate: 1.836E-04 | global batch size: 256 | lm loss: 3.558212E+00 | grad norm: 0.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1050.341 | TFLOPs: 26.76 | +7: iteration 7710/ 37905 | consumed samples: 1973760 | consumed tokens: 4042260480 | elapsed time per iteration (s): 0.23 | learning rate: 1.836E-04 | global batch size: 256 | lm loss: 3.561846E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.727 | TFLOPs: 28.30 | +7: iteration 7720/ 37905 | consumed samples: 1976320 | consumed tokens: 4047503360 | elapsed time per iteration (s): 0.23 | learning rate: 1.835E-04 | global batch size: 256 | lm loss: 3.572259E+00 | grad norm: 0.410 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.569 | TFLOPs: 28.55 | +7: iteration 7730/ 37905 | consumed samples: 1978880 | consumed tokens: 4052746240 | elapsed time per iteration (s): 0.23 | learning rate: 1.835E-04 | global batch size: 256 | lm loss: 3.566031E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.691 | TFLOPs: 28.42 | +7: iteration 7740/ 37905 | consumed samples: 1981440 | consumed tokens: 4057989120 | elapsed time per iteration (s): 0.23 | learning rate: 1.834E-04 | global batch size: 256 | lm loss: 3.575291E+00 | grad norm: 0.387 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.371 | TFLOPs: 28.54 | +7: iteration 7750/ 37905 | consumed samples: 1984000 | consumed tokens: 4063232000 | elapsed time per iteration (s): 0.24 | learning rate: 1.834E-04 | global batch size: 256 | lm loss: 3.568693E+00 | grad norm: 0.391 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.136 | TFLOPs: 27.72 | +7: iteration 7760/ 37905 | consumed samples: 1986560 | consumed tokens: 4068474880 | elapsed time per iteration (s): 0.23 | learning rate: 1.834E-04 | global batch size: 256 | lm loss: 3.554316E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.740 | TFLOPs: 28.32 | +7: iteration 7770/ 37905 | consumed samples: 1989120 | consumed tokens: 4073717760 | elapsed time per iteration (s): 0.23 | learning rate: 1.833E-04 | global batch size: 256 | lm loss: 3.534522E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.356 | TFLOPs: 28.16 | +7: iteration 7780/ 37905 | consumed samples: 1991680 | consumed tokens: 4078960640 | elapsed time per iteration (s): 0.23 | learning rate: 1.833E-04 | global batch size: 256 | lm loss: 3.555010E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.285 | TFLOPs: 28.49 | +7: iteration 7790/ 37905 | consumed samples: 1994240 | consumed tokens: 4084203520 | elapsed time per iteration (s): 0.23 | learning rate: 1.832E-04 | global batch size: 256 | lm loss: 3.556757E+00 | grad norm: 0.417 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.769 | TFLOPs: 28.07 | +7: iteration 7800/ 37905 | consumed samples: 1996800 | consumed tokens: 4089446400 | elapsed time per iteration (s): 0.23 | learning rate: 1.832E-04 | global batch size: 256 | lm loss: 3.570616E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.957 | TFLOPs: 28.17 | +7: iteration 7810/ 37905 | consumed samples: 1999360 | consumed tokens: 4094689280 | elapsed time per iteration (s): 0.23 | learning rate: 1.831E-04 | global batch size: 256 | lm loss: 3.534567E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.783 | TFLOPs: 28.02 | +7: iteration 7820/ 37905 | consumed samples: 2001920 | consumed tokens: 4099932160 | elapsed time per iteration (s): 0.25 | learning rate: 1.831E-04 | global batch size: 256 | lm loss: 3.569779E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1015.823 | TFLOPs: 25.88 | +7: iteration 7830/ 37905 | consumed samples: 2004480 | consumed tokens: 4105175040 | elapsed time per iteration (s): 0.23 | learning rate: 1.831E-04 | global batch size: 256 | lm loss: 3.559810E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.314 | TFLOPs: 28.29 | +7: iteration 7840/ 37905 | consumed samples: 2007040 | consumed tokens: 4110417920 | elapsed time per iteration (s): 0.23 | learning rate: 1.830E-04 | global batch size: 256 | lm loss: 3.558672E+00 | grad norm: 0.390 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.210 | TFLOPs: 28.38 | +7: iteration 7850/ 37905 | consumed samples: 2009600 | consumed tokens: 4115660800 | elapsed time per iteration (s): 0.23 | learning rate: 1.830E-04 | global batch size: 256 | lm loss: 3.578905E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.806 | TFLOPs: 28.55 | +7: iteration 7860/ 37905 | consumed samples: 2012160 | consumed tokens: 4120903680 | elapsed time per iteration (s): 0.23 | learning rate: 1.829E-04 | global batch size: 256 | lm loss: 3.561438E+00 | grad norm: 0.382 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.101 | TFLOPs: 28.43 | +7: iteration 7870/ 37905 | consumed samples: 2014720 | consumed tokens: 4126146560 | elapsed time per iteration (s): 0.23 | learning rate: 1.829E-04 | global batch size: 256 | lm loss: 3.527328E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.078 | TFLOPs: 28.20 | +7: iteration 7880/ 37905 | consumed samples: 2017280 | consumed tokens: 4131389440 | elapsed time per iteration (s): 0.23 | learning rate: 1.828E-04 | global batch size: 256 | lm loss: 3.564472E+00 | grad norm: 0.390 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.476 | TFLOPs: 28.49 | +7: iteration 7890/ 37905 | consumed samples: 2019840 | consumed tokens: 4136632320 | elapsed time per iteration (s): 0.23 | learning rate: 1.828E-04 | global batch size: 256 | lm loss: 3.574997E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.582 | TFLOPs: 28.55 | +7: iteration 7900/ 37905 | consumed samples: 2022400 | consumed tokens: 4141875200 | elapsed time per iteration (s): 0.24 | learning rate: 1.827E-04 | global batch size: 256 | lm loss: 3.527586E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1062.315 | TFLOPs: 27.06 | +7: iteration 7910/ 37905 | consumed samples: 2024960 | consumed tokens: 4147118080 | elapsed time per iteration (s): 0.25 | learning rate: 1.827E-04 | global batch size: 256 | lm loss: 3.591197E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1041.713 | TFLOPs: 26.54 | +7: iteration 7920/ 37905 | consumed samples: 2027520 | consumed tokens: 4152360960 | elapsed time per iteration (s): 0.23 | learning rate: 1.827E-04 | global batch size: 256 | lm loss: 3.534150E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.809 | TFLOPs: 28.40 | +7: iteration 7930/ 37905 | consumed samples: 2030080 | consumed tokens: 4157603840 | elapsed time per iteration (s): 0.23 | learning rate: 1.826E-04 | global batch size: 256 | lm loss: 3.554475E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.752 | TFLOPs: 28.35 | +7: iteration 7940/ 37905 | consumed samples: 2032640 | consumed tokens: 4162846720 | elapsed time per iteration (s): 0.23 | learning rate: 1.826E-04 | global batch size: 256 | lm loss: 3.557473E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.211 | TFLOPs: 28.33 | +7: iteration 7950/ 37905 | consumed samples: 2035200 | consumed tokens: 4168089600 | elapsed time per iteration (s): 0.23 | learning rate: 1.825E-04 | global batch size: 256 | lm loss: 3.552943E+00 | grad norm: 0.473 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.049 | TFLOPs: 28.51 | +7: iteration 7960/ 37905 | consumed samples: 2037760 | consumed tokens: 4173332480 | elapsed time per iteration (s): 0.23 | learning rate: 1.825E-04 | global batch size: 256 | lm loss: 3.561744E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.101 | TFLOPs: 28.15 | +7: iteration 7970/ 37905 | consumed samples: 2040320 | consumed tokens: 4178575360 | elapsed time per iteration (s): 0.23 | learning rate: 1.824E-04 | global batch size: 256 | lm loss: 3.565755E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.174 | TFLOPs: 28.31 | +7: iteration 7980/ 37905 | consumed samples: 2042880 | consumed tokens: 4183818240 | elapsed time per iteration (s): 0.23 | learning rate: 1.824E-04 | global batch size: 256 | lm loss: 3.551253E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.131 | TFLOPs: 28.66 | +7: iteration 7990/ 37905 | consumed samples: 2045440 | consumed tokens: 4189061120 | elapsed time per iteration (s): 0.23 | learning rate: 1.823E-04 | global batch size: 256 | lm loss: 3.568783E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.277 | TFLOPs: 28.54 | +0: [2022-11-29 17:27:18,207] [INFO] [logging.py:68:log_dist] [Rank 0] step=8000, skipped=0, lr=[0.00018229552592396328, 0.00018229552592396328, 0.00018229552592396328], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 8000/ 37905 | consumed samples: 2048000 | consumed tokens: 4194304000 | elapsed time per iteration (s): 0.23 | learning rate: 1.823E-04 | global batch size: 256 | lm loss: 3.528852E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.461 | TFLOPs: 28.59 | +0: steps: 8000 loss: 3.5285 iter time (s): 0.232 samples/sec: 1102.608 +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 8000 | lm loss value: 3.539672E+00 | lm loss PPL: 3.445563E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 8000 to checkpoints_83moscar +0: [2022-11-29 17:27:18,296] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step8000 is begin to save! +0: [2022-11-29 17:27:18,300] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:27:18,371] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:27:18,372] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:27:18,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:27:18,384] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:27:18,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:27:18,395] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:27:18,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:27:18,406] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:27:18,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:27:18,418] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:27:18,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:27:18,429] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:27:18,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:27:18,441] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:27:18,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:27:18,452] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:27:18,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:27:18,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:27:18,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:27:18,475] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:27:18,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:27:18,486] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:27:18,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:27:18,488] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step8000/mp_rank_00_model_states.pt +0: [2022-11-29 17:27:18,488] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:27:18,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:27:18,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:27:18,526] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:27:18,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:27:18,527] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:27:18,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:27:18,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:27:18,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:27:18,527] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +2: [2022-11-29 17:27:18,527] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +7: [2022-11-29 17:27:18,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:27:18,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:27:18,528] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:27:18,528] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 17:27:18,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:27:18,528] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:27:18,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:27:18,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:27:18,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:27:18,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:27:18,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:27:18,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:27:18,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 17:27:18,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:27:18,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:27:18,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:27:18,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:27:18,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:27:18,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:27:18,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:27:18,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:27:18,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:27:18,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 17:27:18,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:27:18,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:27:18,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:27:18,530] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:27:18,530] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 17:27:18,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:27:18,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:27:18,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:27:18,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:27:18,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:27:18,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +4: [2022-11-29 17:27:18,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +7: [2022-11-29 17:27:18,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:27:18,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:27:18,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:27:18,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:27:18,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 17:27:18,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:27:18,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:27:18,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:27:18,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:27:18,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:27:18,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:27:18,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:27:18,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:27:18,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 17:27:18,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:27:18,532] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:27:18,532] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:27:18,532] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:27:18,532] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:27:18,532] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:27:18,532] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +0: [2022-11-29 17:27:18,532] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:27:18,532] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3: [2022-11-29 17:27:18,532] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:27:18,532] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:27:18,532] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:27:18,532] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:27:18,532] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:27:18,532] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:27:18,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:27:18,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:27:18,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 17:27:18,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:27:18,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:27:18,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 17:27:18,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:27:18,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:27:18,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 17:27:18,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:27:18,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:27:18,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:27:18,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:27:18,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:27:18,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 17:27:18,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:27:18,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +3: [2022-11-29 17:27:18,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:27:18,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:27:18,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +0: [2022-11-29 17:27:18,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:27:18,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:27:18,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +2: [2022-11-29 17:27:18,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:27:18,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:27:18,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:27:18,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:27:18,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:27:18,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:27:18,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 17:27:18,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:27:18,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:27:18,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:27:18,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:27:18,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:27:18,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +7: [2022-11-29 17:27:18,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +1: [2022-11-29 17:27:18,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:27:18,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:27:18,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +7: [2022-11-29 17:27:18,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:27:18,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:27:18,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:27:18,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:27:18,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:27:18,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:27:18,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:27:18,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:27:18,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:27:18,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:27:18,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +6: [2022-11-29 17:27:18,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:27:18,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:27:18,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:27:18,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:27:18,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:27:18,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 17:27:18,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:27:18,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:27:18,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +7: [2022-11-29 17:27:18,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +5: [2022-11-29 17:27:18,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 17:27:18,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:27:18,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:27:18,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +3: [2022-11-29 17:27:18,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:27:18,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:27:18,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:27:18,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 17:27:18,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:27:18,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:27:18,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 17:27:18,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:27:18,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:27:18,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +2: [2022-11-29 17:27:18,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +6: [2022-11-29 17:27:18,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:27:18,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 17:27:18,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:27:18,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:27:18,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 17:27:18,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:27:18,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:27:18,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:27:18,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:27:18,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:27:18,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +6: [2022-11-29 17:27:18,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +0: [2022-11-29 17:27:18,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +6: [2022-11-29 17:27:18,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +2: [2022-11-29 17:27:18,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:27:18,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +5: [2022-11-29 17:27:18,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:27:18,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:27:18,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +5: [2022-11-29 17:27:18,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +4: [2022-11-29 17:27:18,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +5: [2022-11-29 17:27:18,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:27:18,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:27:18,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:27:18,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +7: [2022-11-29 17:27:18,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:27:18,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +7: [2022-11-29 17:27:18,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +3: [2022-11-29 17:27:18,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:27:18,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:27:18,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:27:18,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: [2022-11-29 17:27:18,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:27:18,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:27:18,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +3: [2022-11-29 17:27:18,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:27:18,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:27:18,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +1: [2022-11-29 17:27:18,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:27:18,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:27:18,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +4: [2022-11-29 17:27:18,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:27:18,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step8000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:27:18,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +0: successfully saved checkpoint at iteration 8000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 246.50 +7: iteration 8010/ 37905 | consumed samples: 2050560 | consumed tokens: 4199546880 | elapsed time per iteration (s): 0.26 | learning rate: 1.823E-04 | global batch size: 256 | lm loss: 3.541624E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 982.154 | TFLOPs: 25.02 | +7: iteration 8020/ 37905 | consumed samples: 2053120 | consumed tokens: 4204789760 | elapsed time per iteration (s): 0.23 | learning rate: 1.822E-04 | global batch size: 256 | lm loss: 3.545364E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.450 | TFLOPs: 28.26 | +7: iteration 8030/ 37905 | consumed samples: 2055680 | consumed tokens: 4210032640 | elapsed time per iteration (s): 0.23 | learning rate: 1.822E-04 | global batch size: 256 | lm loss: 3.529528E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.615 | TFLOPs: 27.94 | +7: iteration 8040/ 37905 | consumed samples: 2058240 | consumed tokens: 4215275520 | elapsed time per iteration (s): 0.23 | learning rate: 1.821E-04 | global batch size: 256 | lm loss: 3.558131E+00 | grad norm: 0.400 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.651 | TFLOPs: 28.65 | +7: iteration 8050/ 37905 | consumed samples: 2060800 | consumed tokens: 4220518400 | elapsed time per iteration (s): 0.23 | learning rate: 1.821E-04 | global batch size: 256 | lm loss: 3.559217E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.125 | TFLOPs: 28.20 | +7: iteration 8060/ 37905 | consumed samples: 2063360 | consumed tokens: 4225761280 | elapsed time per iteration (s): 0.23 | learning rate: 1.820E-04 | global batch size: 256 | lm loss: 3.552178E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.197 | TFLOPs: 28.31 | +7: iteration 8070/ 37905 | consumed samples: 2065920 | consumed tokens: 4231004160 | elapsed time per iteration (s): 0.24 | learning rate: 1.820E-04 | global batch size: 256 | lm loss: 3.584159E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1076.201 | TFLOPs: 27.42 | +7: iteration 8080/ 37905 | consumed samples: 2068480 | consumed tokens: 4236247040 | elapsed time per iteration (s): 0.25 | learning rate: 1.819E-04 | global batch size: 256 | lm loss: 3.538844E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1006.890 | TFLOPs: 25.65 | +7: iteration 8090/ 37905 | consumed samples: 2071040 | consumed tokens: 4241489920 | elapsed time per iteration (s): 0.23 | learning rate: 1.819E-04 | global batch size: 256 | lm loss: 3.528774E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.809 | TFLOPs: 28.30 | +7: iteration 8100/ 37905 | consumed samples: 2073600 | consumed tokens: 4246732800 | elapsed time per iteration (s): 0.23 | learning rate: 1.818E-04 | global batch size: 256 | lm loss: 3.557287E+00 | grad norm: 0.382 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.008 | TFLOPs: 28.43 | +7: iteration 8110/ 37905 | consumed samples: 2076160 | consumed tokens: 4251975680 | elapsed time per iteration (s): 0.23 | learning rate: 1.818E-04 | global batch size: 256 | lm loss: 3.552046E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.981 | TFLOPs: 28.56 | +7: iteration 8120/ 37905 | consumed samples: 2078720 | consumed tokens: 4257218560 | elapsed time per iteration (s): 0.23 | learning rate: 1.818E-04 | global batch size: 256 | lm loss: 3.561615E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.133 | TFLOPs: 28.48 | +7: iteration 8130/ 37905 | consumed samples: 2081280 | consumed tokens: 4262461440 | elapsed time per iteration (s): 0.23 | learning rate: 1.817E-04 | global batch size: 256 | lm loss: 3.528389E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.328 | TFLOPs: 28.46 | +7: iteration 8140/ 37905 | consumed samples: 2083840 | consumed tokens: 4267704320 | elapsed time per iteration (s): 0.23 | learning rate: 1.817E-04 | global batch size: 256 | lm loss: 3.522822E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.573 | TFLOPs: 27.81 | +7: iteration 8150/ 37905 | consumed samples: 2086400 | consumed tokens: 4272947200 | elapsed time per iteration (s): 0.23 | learning rate: 1.816E-04 | global batch size: 256 | lm loss: 3.570524E+00 | grad norm: 0.433 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.792 | TFLOPs: 28.32 | +7: iteration 8160/ 37905 | consumed samples: 2088960 | consumed tokens: 4278190080 | elapsed time per iteration (s): 0.25 | learning rate: 1.816E-04 | global batch size: 256 | lm loss: 3.551907E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1013.040 | TFLOPs: 25.81 | +7: iteration 8170/ 37905 | consumed samples: 2091520 | consumed tokens: 4283432960 | elapsed time per iteration (s): 0.23 | learning rate: 1.815E-04 | global batch size: 256 | lm loss: 3.530395E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.062 | TFLOPs: 28.56 | +7: iteration 8180/ 37905 | consumed samples: 2094080 | consumed tokens: 4288675840 | elapsed time per iteration (s): 0.23 | learning rate: 1.815E-04 | global batch size: 256 | lm loss: 3.542808E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.672 | TFLOPs: 28.19 | +7: iteration 8190/ 37905 | consumed samples: 2096640 | consumed tokens: 4293918720 | elapsed time per iteration (s): 0.23 | learning rate: 1.814E-04 | global batch size: 256 | lm loss: 3.562180E+00 | grad norm: 0.454 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.320 | TFLOPs: 27.83 | +7: iteration 8200/ 37905 | consumed samples: 2099200 | consumed tokens: 4299161600 | elapsed time per iteration (s): 0.23 | learning rate: 1.814E-04 | global batch size: 256 | lm loss: 3.548974E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.196 | TFLOPs: 28.41 | +7: iteration 8210/ 37905 | consumed samples: 2101760 | consumed tokens: 4304404480 | elapsed time per iteration (s): 0.23 | learning rate: 1.813E-04 | global batch size: 256 | lm loss: 3.587934E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.388 | TFLOPs: 28.49 | +7: iteration 8220/ 37905 | consumed samples: 2104320 | consumed tokens: 4309647360 | elapsed time per iteration (s): 0.23 | learning rate: 1.813E-04 | global batch size: 256 | lm loss: 3.549440E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.715 | TFLOPs: 28.17 | +7: iteration 8230/ 37905 | consumed samples: 2106880 | consumed tokens: 4314890240 | elapsed time per iteration (s): 0.23 | learning rate: 1.813E-04 | global batch size: 256 | lm loss: 3.565420E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.249 | TFLOPs: 28.39 | +7: iteration 8240/ 37905 | consumed samples: 2109440 | consumed tokens: 4320133120 | elapsed time per iteration (s): 0.23 | learning rate: 1.812E-04 | global batch size: 256 | lm loss: 3.582427E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.373 | TFLOPs: 28.03 | +7: iteration 8250/ 37905 | consumed samples: 2112000 | consumed tokens: 4325376000 | elapsed time per iteration (s): 0.23 | learning rate: 1.812E-04 | global batch size: 256 | lm loss: 3.542271E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.081 | TFLOPs: 27.97 | +7: iteration 8260/ 37905 | consumed samples: 2114560 | consumed tokens: 4330618880 | elapsed time per iteration (s): 0.25 | learning rate: 1.811E-04 | global batch size: 256 | lm loss: 3.544129E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1020.546 | TFLOPs: 26.00 | +7: iteration 8270/ 37905 | consumed samples: 2117120 | consumed tokens: 4335861760 | elapsed time per iteration (s): 0.23 | learning rate: 1.811E-04 | global batch size: 256 | lm loss: 3.553485E+00 | grad norm: 0.381 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.235 | TFLOPs: 28.59 | +7: iteration 8280/ 37905 | consumed samples: 2119680 | consumed tokens: 4341104640 | elapsed time per iteration (s): 0.23 | learning rate: 1.810E-04 | global batch size: 256 | lm loss: 3.588797E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.836 | TFLOPs: 27.89 | +7: iteration 8290/ 37905 | consumed samples: 2122240 | consumed tokens: 4346347520 | elapsed time per iteration (s): 0.23 | learning rate: 1.810E-04 | global batch size: 256 | lm loss: 3.568460E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.087 | TFLOPs: 28.53 | +7: iteration 8300/ 37905 | consumed samples: 2124800 | consumed tokens: 4351590400 | elapsed time per iteration (s): 0.23 | learning rate: 1.809E-04 | global batch size: 256 | lm loss: 3.529497E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.386 | TFLOPs: 28.41 | +7: iteration 8310/ 37905 | consumed samples: 2127360 | consumed tokens: 4356833280 | elapsed time per iteration (s): 0.23 | learning rate: 1.809E-04 | global batch size: 256 | lm loss: 3.547771E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.983 | TFLOPs: 28.58 | +7: iteration 8320/ 37905 | consumed samples: 2129920 | consumed tokens: 4362076160 | elapsed time per iteration (s): 0.23 | learning rate: 1.808E-04 | global batch size: 256 | lm loss: 3.541449E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.503 | TFLOPs: 28.70 | +7: iteration 8330/ 37905 | consumed samples: 2132480 | consumed tokens: 4367319040 | elapsed time per iteration (s): 0.23 | learning rate: 1.808E-04 | global batch size: 256 | lm loss: 3.537271E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.801 | TFLOPs: 28.60 | +7: iteration 8340/ 37905 | consumed samples: 2135040 | consumed tokens: 4372561920 | elapsed time per iteration (s): 0.23 | learning rate: 1.807E-04 | global batch size: 256 | lm loss: 3.546148E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.874 | TFLOPs: 28.50 | +7: iteration 8350/ 37905 | consumed samples: 2137600 | consumed tokens: 4377804800 | elapsed time per iteration (s): 0.23 | learning rate: 1.807E-04 | global batch size: 256 | lm loss: 3.539075E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.106 | TFLOPs: 28.59 | +7: iteration 8360/ 37905 | consumed samples: 2140160 | consumed tokens: 4383047680 | elapsed time per iteration (s): 0.23 | learning rate: 1.806E-04 | global batch size: 256 | lm loss: 3.560423E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.007 | TFLOPs: 28.58 | +7: iteration 8370/ 37905 | consumed samples: 2142720 | consumed tokens: 4388290560 | elapsed time per iteration (s): 0.23 | learning rate: 1.806E-04 | global batch size: 256 | lm loss: 3.547451E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.621 | TFLOPs: 28.29 | +7: iteration 8380/ 37905 | consumed samples: 2145280 | consumed tokens: 4393533440 | elapsed time per iteration (s): 0.23 | learning rate: 1.806E-04 | global batch size: 256 | lm loss: 3.532803E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.098 | TFLOPs: 28.48 | +7: iteration 8390/ 37905 | consumed samples: 2147840 | consumed tokens: 4398776320 | elapsed time per iteration (s): 0.23 | learning rate: 1.805E-04 | global batch size: 256 | lm loss: 3.562739E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.112 | TFLOPs: 28.31 | +7: iteration 8400/ 37905 | consumed samples: 2150400 | consumed tokens: 4404019200 | elapsed time per iteration (s): 0.23 | learning rate: 1.805E-04 | global batch size: 256 | lm loss: 3.519962E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.114 | TFLOPs: 28.51 | +7: iteration 8410/ 37905 | consumed samples: 2152960 | consumed tokens: 4409262080 | elapsed time per iteration (s): 0.23 | learning rate: 1.804E-04 | global batch size: 256 | lm loss: 3.536444E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.450 | TFLOPs: 28.49 | +7: iteration 8420/ 37905 | consumed samples: 2155520 | consumed tokens: 4414504960 | elapsed time per iteration (s): 0.23 | learning rate: 1.804E-04 | global batch size: 256 | lm loss: 3.542662E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.155 | TFLOPs: 28.33 | +7: iteration 8430/ 37905 | consumed samples: 2158080 | consumed tokens: 4419747840 | elapsed time per iteration (s): 0.23 | learning rate: 1.803E-04 | global batch size: 256 | lm loss: 3.534044E+00 | grad norm: 0.400 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.499 | TFLOPs: 28.26 | +7: iteration 8440/ 37905 | consumed samples: 2160640 | consumed tokens: 4424990720 | elapsed time per iteration (s): 0.23 | learning rate: 1.803E-04 | global batch size: 256 | lm loss: 3.542947E+00 | grad norm: 0.381 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.618 | TFLOPs: 28.57 | +7: iteration 8450/ 37905 | consumed samples: 2163200 | consumed tokens: 4430233600 | elapsed time per iteration (s): 0.23 | learning rate: 1.802E-04 | global batch size: 256 | lm loss: 3.537387E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.258 | TFLOPs: 28.33 | +7: iteration 8460/ 37905 | consumed samples: 2165760 | consumed tokens: 4435476480 | elapsed time per iteration (s): 0.23 | learning rate: 1.802E-04 | global batch size: 256 | lm loss: 3.553857E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.790 | TFLOPs: 28.53 | +7: iteration 8470/ 37905 | consumed samples: 2168320 | consumed tokens: 4440719360 | elapsed time per iteration (s): 0.24 | learning rate: 1.801E-04 | global batch size: 256 | lm loss: 3.547269E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.227 | TFLOPs: 27.70 | +7: iteration 8480/ 37905 | consumed samples: 2170880 | consumed tokens: 4445962240 | elapsed time per iteration (s): 0.23 | learning rate: 1.801E-04 | global batch size: 256 | lm loss: 3.538359E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.516 | TFLOPs: 28.29 | +7: iteration 8490/ 37905 | consumed samples: 2173440 | consumed tokens: 4451205120 | elapsed time per iteration (s): 0.23 | learning rate: 1.800E-04 | global batch size: 256 | lm loss: 3.556536E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.752 | TFLOPs: 28.12 | +7: iteration 8500/ 37905 | consumed samples: 2176000 | consumed tokens: 4456448000 | elapsed time per iteration (s): 0.23 | learning rate: 1.800E-04 | global batch size: 256 | lm loss: 3.579593E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.245 | TFLOPs: 28.28 | +7: iteration 8510/ 37905 | consumed samples: 2178560 | consumed tokens: 4461690880 | elapsed time per iteration (s): 0.23 | learning rate: 1.799E-04 | global batch size: 256 | lm loss: 3.543381E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.208 | TFLOPs: 28.26 | +7: iteration 8520/ 37905 | consumed samples: 2181120 | consumed tokens: 4466933760 | elapsed time per iteration (s): 0.23 | learning rate: 1.799E-04 | global batch size: 256 | lm loss: 3.544712E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.048 | TFLOPs: 28.30 | +7: iteration 8530/ 37905 | consumed samples: 2183680 | consumed tokens: 4472176640 | elapsed time per iteration (s): 0.23 | learning rate: 1.798E-04 | global batch size: 256 | lm loss: 3.559209E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.447 | TFLOPs: 28.59 | +7: iteration 8540/ 37905 | consumed samples: 2186240 | consumed tokens: 4477419520 | elapsed time per iteration (s): 0.23 | learning rate: 1.798E-04 | global batch size: 256 | lm loss: 3.540688E+00 | grad norm: 0.397 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.771 | TFLOPs: 27.99 | +7: iteration 8550/ 37905 | consumed samples: 2188800 | consumed tokens: 4482662400 | elapsed time per iteration (s): 0.23 | learning rate: 1.798E-04 | global batch size: 256 | lm loss: 3.546732E+00 | grad norm: 0.410 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.982 | TFLOPs: 28.02 | +7: iteration 8560/ 37905 | consumed samples: 2191360 | consumed tokens: 4487905280 | elapsed time per iteration (s): 0.25 | learning rate: 1.797E-04 | global batch size: 256 | lm loss: 3.522192E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1018.378 | TFLOPs: 25.94 | +7: iteration 8570/ 37905 | consumed samples: 2193920 | consumed tokens: 4493148160 | elapsed time per iteration (s): 0.23 | learning rate: 1.797E-04 | global batch size: 256 | lm loss: 3.555399E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.320 | TFLOPs: 28.23 | +7: iteration 8580/ 37905 | consumed samples: 2196480 | consumed tokens: 4498391040 | elapsed time per iteration (s): 0.23 | learning rate: 1.796E-04 | global batch size: 256 | lm loss: 3.516582E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.708 | TFLOPs: 28.14 | +7: iteration 8590/ 37905 | consumed samples: 2199040 | consumed tokens: 4503633920 | elapsed time per iteration (s): 0.23 | learning rate: 1.796E-04 | global batch size: 256 | lm loss: 3.556765E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.284 | TFLOPs: 28.56 | +7: iteration 8600/ 37905 | consumed samples: 2201600 | consumed tokens: 4508876800 | elapsed time per iteration (s): 0.23 | learning rate: 1.795E-04 | global batch size: 256 | lm loss: 3.521911E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.679 | TFLOPs: 28.47 | +7: iteration 8610/ 37905 | consumed samples: 2204160 | consumed tokens: 4514119680 | elapsed time per iteration (s): 0.23 | learning rate: 1.795E-04 | global batch size: 256 | lm loss: 3.531574E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.079 | TFLOPs: 28.20 | +7: iteration 8620/ 37905 | consumed samples: 2206720 | consumed tokens: 4519362560 | elapsed time per iteration (s): 0.23 | learning rate: 1.794E-04 | global batch size: 256 | lm loss: 3.518230E+00 | grad norm: 0.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.589 | TFLOPs: 28.65 | +7: iteration 8630/ 37905 | consumed samples: 2209280 | consumed tokens: 4524605440 | elapsed time per iteration (s): 0.23 | learning rate: 1.794E-04 | global batch size: 256 | lm loss: 3.576720E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.403 | TFLOPs: 28.54 | +7: iteration 8640/ 37905 | consumed samples: 2211840 | consumed tokens: 4529848320 | elapsed time per iteration (s): 0.23 | learning rate: 1.793E-04 | global batch size: 256 | lm loss: 3.576920E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.571 | TFLOPs: 28.32 | +7: iteration 8650/ 37905 | consumed samples: 2214400 | consumed tokens: 4535091200 | elapsed time per iteration (s): 0.23 | learning rate: 1.793E-04 | global batch size: 256 | lm loss: 3.521160E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.140 | TFLOPs: 28.46 | +7: iteration 8660/ 37905 | consumed samples: 2216960 | consumed tokens: 4540334080 | elapsed time per iteration (s): 0.23 | learning rate: 1.792E-04 | global batch size: 256 | lm loss: 3.529855E+00 | grad norm: 0.373 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.878 | TFLOPs: 28.45 | +7: iteration 8670/ 37905 | consumed samples: 2219520 | consumed tokens: 4545576960 | elapsed time per iteration (s): 0.23 | learning rate: 1.792E-04 | global batch size: 256 | lm loss: 3.540885E+00 | grad norm: 0.367 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.507 | TFLOPs: 28.19 | +7: iteration 8680/ 37905 | consumed samples: 2222080 | consumed tokens: 4550819840 | elapsed time per iteration (s): 0.23 | learning rate: 1.791E-04 | global batch size: 256 | lm loss: 3.516658E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.101 | TFLOPs: 28.28 | +7: iteration 8690/ 37905 | consumed samples: 2224640 | consumed tokens: 4556062720 | elapsed time per iteration (s): 0.23 | learning rate: 1.791E-04 | global batch size: 256 | lm loss: 3.507561E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.213 | TFLOPs: 28.54 | +7: iteration 8700/ 37905 | consumed samples: 2227200 | consumed tokens: 4561305600 | elapsed time per iteration (s): 0.23 | learning rate: 1.790E-04 | global batch size: 256 | lm loss: 3.551984E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.533 | TFLOPs: 28.29 | +7: iteration 8710/ 37905 | consumed samples: 2229760 | consumed tokens: 4566548480 | elapsed time per iteration (s): 0.23 | learning rate: 1.790E-04 | global batch size: 256 | lm loss: 3.545298E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.034 | TFLOPs: 28.00 | +7: iteration 8720/ 37905 | consumed samples: 2232320 | consumed tokens: 4571791360 | elapsed time per iteration (s): 0.24 | learning rate: 1.789E-04 | global batch size: 256 | lm loss: 3.534991E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1052.020 | TFLOPs: 26.80 | +7: iteration 8730/ 37905 | consumed samples: 2234880 | consumed tokens: 4577034240 | elapsed time per iteration (s): 0.23 | learning rate: 1.789E-04 | global batch size: 256 | lm loss: 3.545301E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.410 | TFLOPs: 28.62 | +7: iteration 8740/ 37905 | consumed samples: 2237440 | consumed tokens: 4582277120 | elapsed time per iteration (s): 0.23 | learning rate: 1.788E-04 | global batch size: 256 | lm loss: 3.539627E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.464 | TFLOPs: 28.62 | +7: iteration 8750/ 37905 | consumed samples: 2240000 | consumed tokens: 4587520000 | elapsed time per iteration (s): 0.23 | learning rate: 1.788E-04 | global batch size: 256 | lm loss: 3.523466E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.014 | TFLOPs: 28.38 | +7: iteration 8760/ 37905 | consumed samples: 2242560 | consumed tokens: 4592762880 | elapsed time per iteration (s): 0.24 | learning rate: 1.787E-04 | global batch size: 256 | lm loss: 3.521714E+00 | grad norm: 0.381 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.350 | TFLOPs: 27.70 | +7: iteration 8770/ 37905 | consumed samples: 2245120 | consumed tokens: 4598005760 | elapsed time per iteration (s): 0.23 | learning rate: 1.787E-04 | global batch size: 256 | lm loss: 3.540296E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.565 | TFLOPs: 28.04 | +7: iteration 8780/ 37905 | consumed samples: 2247680 | consumed tokens: 4603248640 | elapsed time per iteration (s): 0.23 | learning rate: 1.786E-04 | global batch size: 256 | lm loss: 3.545555E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.500 | TFLOPs: 27.76 | +7: iteration 8790/ 37905 | consumed samples: 2250240 | consumed tokens: 4608491520 | elapsed time per iteration (s): 0.23 | learning rate: 1.786E-04 | global batch size: 256 | lm loss: 3.551511E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.018 | TFLOPs: 27.82 | +7: iteration 8800/ 37905 | consumed samples: 2252800 | consumed tokens: 4613734400 | elapsed time per iteration (s): 0.23 | learning rate: 1.785E-04 | global batch size: 256 | lm loss: 3.535878E+00 | grad norm: 0.422 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.756 | TFLOPs: 28.04 | +7: iteration 8810/ 37905 | consumed samples: 2255360 | consumed tokens: 4618977280 | elapsed time per iteration (s): 0.26 | learning rate: 1.785E-04 | global batch size: 256 | lm loss: 3.532200E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 986.342 | TFLOPs: 25.13 | +7: iteration 8820/ 37905 | consumed samples: 2257920 | consumed tokens: 4624220160 | elapsed time per iteration (s): 0.23 | learning rate: 1.784E-04 | global batch size: 256 | lm loss: 3.525055E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.689 | TFLOPs: 28.52 | +7: iteration 8830/ 37905 | consumed samples: 2260480 | consumed tokens: 4629463040 | elapsed time per iteration (s): 0.23 | learning rate: 1.784E-04 | global batch size: 256 | lm loss: 3.539093E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.802 | TFLOPs: 28.04 | +7: iteration 8840/ 37905 | consumed samples: 2263040 | consumed tokens: 4634705920 | elapsed time per iteration (s): 0.23 | learning rate: 1.784E-04 | global batch size: 256 | lm loss: 3.525048E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.388 | TFLOPs: 28.52 | +7: iteration 8850/ 37905 | consumed samples: 2265600 | consumed tokens: 4639948800 | elapsed time per iteration (s): 0.23 | learning rate: 1.783E-04 | global batch size: 256 | lm loss: 3.551222E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.064 | TFLOPs: 28.38 | +7: iteration 8860/ 37905 | consumed samples: 2268160 | consumed tokens: 4645191680 | elapsed time per iteration (s): 0.23 | learning rate: 1.783E-04 | global batch size: 256 | lm loss: 3.529900E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.271 | TFLOPs: 28.59 | +7: iteration 8870/ 37905 | consumed samples: 2270720 | consumed tokens: 4650434560 | elapsed time per iteration (s): 0.23 | learning rate: 1.782E-04 | global batch size: 256 | lm loss: 3.539250E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.935 | TFLOPs: 28.56 | +7: iteration 8880/ 37905 | consumed samples: 2273280 | consumed tokens: 4655677440 | elapsed time per iteration (s): 0.23 | learning rate: 1.782E-04 | global batch size: 256 | lm loss: 3.530031E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.458 | TFLOPs: 28.31 | +7: iteration 8890/ 37905 | consumed samples: 2275840 | consumed tokens: 4660920320 | elapsed time per iteration (s): 0.23 | learning rate: 1.781E-04 | global batch size: 256 | lm loss: 3.538338E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.330 | TFLOPs: 28.36 | +7: iteration 8900/ 37905 | consumed samples: 2278400 | consumed tokens: 4666163200 | elapsed time per iteration (s): 0.23 | learning rate: 1.781E-04 | global batch size: 256 | lm loss: 3.531480E+00 | grad norm: 0.423 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.488 | TFLOPs: 28.57 | +7: iteration 8910/ 37905 | consumed samples: 2280960 | consumed tokens: 4671406080 | elapsed time per iteration (s): 0.24 | learning rate: 1.780E-04 | global batch size: 256 | lm loss: 3.567481E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1063.302 | TFLOPs: 27.09 | +7: iteration 8920/ 37905 | consumed samples: 2283520 | consumed tokens: 4676648960 | elapsed time per iteration (s): 0.26 | learning rate: 1.780E-04 | global batch size: 256 | lm loss: 3.534082E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 973.868 | TFLOPs: 24.81 | +7: iteration 8930/ 37905 | consumed samples: 2286080 | consumed tokens: 4681891840 | elapsed time per iteration (s): 0.23 | learning rate: 1.779E-04 | global batch size: 256 | lm loss: 3.537111E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.126 | TFLOPs: 28.31 | +7: iteration 8940/ 37905 | consumed samples: 2288640 | consumed tokens: 4687134720 | elapsed time per iteration (s): 0.23 | learning rate: 1.779E-04 | global batch size: 256 | lm loss: 3.537026E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.752 | TFLOPs: 28.12 | +7: iteration 8950/ 37905 | consumed samples: 2291200 | consumed tokens: 4692377600 | elapsed time per iteration (s): 0.23 | learning rate: 1.778E-04 | global batch size: 256 | lm loss: 3.522964E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.919 | TFLOPs: 27.79 | +7: iteration 8960/ 37905 | consumed samples: 2293760 | consumed tokens: 4697620480 | elapsed time per iteration (s): 0.25 | learning rate: 1.778E-04 | global batch size: 256 | lm loss: 3.537291E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1040.497 | TFLOPs: 26.51 | +7: iteration 8970/ 37905 | consumed samples: 2296320 | consumed tokens: 4702863360 | elapsed time per iteration (s): 0.24 | learning rate: 1.777E-04 | global batch size: 256 | lm loss: 3.538840E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.160 | TFLOPs: 27.64 | +7: iteration 8980/ 37905 | consumed samples: 2298880 | consumed tokens: 4708106240 | elapsed time per iteration (s): 0.23 | learning rate: 1.777E-04 | global batch size: 256 | lm loss: 3.500746E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.794 | TFLOPs: 27.94 | +7: iteration 8990/ 37905 | consumed samples: 2301440 | consumed tokens: 4713349120 | elapsed time per iteration (s): 0.25 | learning rate: 1.776E-04 | global batch size: 256 | lm loss: 3.539670E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1016.494 | TFLOPs: 25.90 | +7: iteration 9000/ 37905 | consumed samples: 2304000 | consumed tokens: 4718592000 | elapsed time per iteration (s): 0.24 | learning rate: 1.776E-04 | global batch size: 256 | lm loss: 3.548034E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1064.054 | TFLOPs: 27.11 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 9000 | lm loss value: 3.324680E+00 | lm loss PPL: 2.779009E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 9000 to checkpoints_83moscar +0: [2022-11-29 17:31:11,304] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step9000 is begin to save! +0: [2022-11-29 17:31:11,311] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:31:11,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:31:11,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:31:11,394] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:31:11,395] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:31:11,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:31:11,406] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:31:11,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:31:11,418] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:31:11,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:31:11,430] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:31:11,441] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:31:11,441] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:31:11,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:31:11,453] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:31:11,464] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:31:11,464] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:31:11,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:31:11,475] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:31:11,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:31:11,487] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:31:11,498] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:31:11,498] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:31:11,499] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:31:11,499] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step9000/mp_rank_00_model_states.pt +0: [2022-11-29 17:31:11,499] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:31:11,501] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:31:11,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:31:11,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:31:11,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:31:11,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 17:31:11,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:31:11,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:31:11,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 17:31:11,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:31:11,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:31:11,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 17:31:11,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:31:11,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:31:11,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:31:11,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 17:31:11,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:31:11,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 17:31:11,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:31:11,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:31:11,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 17:31:11,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:31:11,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:31:11,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 17:31:11,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:31:11,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:31:11,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 17:31:11,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:31:11,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:31:11,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 17:31:11,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:31:11,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:31:11,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 17:31:11,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:31:11,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:31:11,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 17:31:11,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:31:11,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:31:11,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 17:31:11,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:31:11,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:31:11,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 17:31:11,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:31:11,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:31:11,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +1: [2022-11-29 17:31:11,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +2: [2022-11-29 17:31:11,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 17:31:11,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:31:11,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 17:31:11,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:31:11,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +5: [2022-11-29 17:31:11,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:31:11,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +7: [2022-11-29 17:31:11,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 17:31:11,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:31:11,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 17:31:11,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 17:31:11,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:31:11,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:31:11,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 17:31:11,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:31:11,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:31:11,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 17:31:11,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:31:11,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:31:11,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 17:31:11,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:31:11,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:31:11,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 17:31:11,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:31:11,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:31:11,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 17:31:11,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:31:11,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:31:11,547] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:31:11,547] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 17:31:11,547] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:31:11,547] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 17:31:11,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:31:11,547] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:31:11,547] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 17:31:11,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:31:11,547] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:31:11,547] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 17:31:11,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:31:11,547] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:31:11,547] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 17:31:11,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:31:11,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:31:11,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 17:31:11,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:31:11,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:31:11,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 17:31:11,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:31:11,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +2: [2022-11-29 17:31:11,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:31:11,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 17:31:11,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:31:11,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 17:31:11,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:31:11,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:31:11,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +1: [2022-11-29 17:31:11,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +7: [2022-11-29 17:31:11,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 17:31:11,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 17:31:11,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:31:11,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:31:11,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 17:31:11,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:31:11,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:31:11,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 17:31:11,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:31:11,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:31:11,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 17:31:11,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:31:11,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:31:11,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 17:31:11,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:31:11,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +2: [2022-11-29 17:31:11,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:31:11,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 17:31:11,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:31:11,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 17:31:11,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:31:11,550] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:31:11,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 17:31:11,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:31:11,550] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:31:11,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 17:31:11,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:31:11,550] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:31:11,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 17:31:11,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:31:11,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:31:11,550] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +1: [2022-11-29 17:31:11,550] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +7: [2022-11-29 17:31:11,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 17:31:11,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 17:31:11,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:31:11,551] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:31:11,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 17:31:11,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:31:11,551] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:31:11,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 17:31:11,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:31:11,551] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:31:11,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 17:31:11,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:31:11,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:31:11,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 17:31:11,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:31:11,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:31:11,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 17:31:11,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:31:11,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +7: [2022-11-29 17:31:11,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:31:11,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 17:31:11,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:31:11,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +5: [2022-11-29 17:31:11,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:31:11,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:31:11,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +2: [2022-11-29 17:31:11,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:31:11,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:31:11,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 17:31:11,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:31:11,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:31:11,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:31:11,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +6: [2022-11-29 17:31:11,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +7: [2022-11-29 17:31:11,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +1: [2022-11-29 17:31:11,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +6: [2022-11-29 17:31:11,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +7: [2022-11-29 17:31:11,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 17:31:11,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:31:11,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:31:11,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +1: [2022-11-29 17:31:11,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:31:11,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:31:11,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 17:31:11,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:31:11,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:31:11,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3: [2022-11-29 17:31:11,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +0: [2022-11-29 17:31:11,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +3: [2022-11-29 17:31:11,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 17:31:11,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:31:11,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:31:11,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +4: [2022-11-29 17:31:11,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:31:11,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:31:11,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: [2022-11-29 17:31:11,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:31:11,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step9000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:31:11,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +0: successfully saved checkpoint at iteration 9000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 255.64 +7: iteration 9010/ 37905 | consumed samples: 2306560 | consumed tokens: 4723834880 | elapsed time per iteration (s): 0.33 | learning rate: 1.775E-04 | global batch size: 256 | lm loss: 3.523892E+00 | grad norm: 0.386 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 769.081 | TFLOPs: 19.59 | +7: iteration 9020/ 37905 | consumed samples: 2309120 | consumed tokens: 4729077760 | elapsed time per iteration (s): 0.23 | learning rate: 1.775E-04 | global batch size: 256 | lm loss: 3.525786E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.529 | TFLOPs: 27.93 | +7: iteration 9030/ 37905 | consumed samples: 2311680 | consumed tokens: 4734320640 | elapsed time per iteration (s): 0.25 | learning rate: 1.774E-04 | global batch size: 256 | lm loss: 3.525411E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1035.817 | TFLOPs: 26.39 | +7: iteration 9040/ 37905 | consumed samples: 2314240 | consumed tokens: 4739563520 | elapsed time per iteration (s): 0.23 | learning rate: 1.774E-04 | global batch size: 256 | lm loss: 3.505459E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.163 | TFLOPs: 27.95 | +7: iteration 9050/ 37905 | consumed samples: 2316800 | consumed tokens: 4744806400 | elapsed time per iteration (s): 0.23 | learning rate: 1.773E-04 | global batch size: 256 | lm loss: 3.512690E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.013 | TFLOPs: 28.20 | +7: iteration 9060/ 37905 | consumed samples: 2319360 | consumed tokens: 4750049280 | elapsed time per iteration (s): 0.23 | learning rate: 1.773E-04 | global batch size: 256 | lm loss: 3.502229E+00 | grad norm: 0.380 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.503 | TFLOPs: 28.60 | +7: iteration 9070/ 37905 | consumed samples: 2321920 | consumed tokens: 4755292160 | elapsed time per iteration (s): 0.23 | learning rate: 1.772E-04 | global batch size: 256 | lm loss: 3.527951E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.081 | TFLOPs: 28.15 | +7: iteration 9080/ 37905 | consumed samples: 2324480 | consumed tokens: 4760535040 | elapsed time per iteration (s): 0.23 | learning rate: 1.772E-04 | global batch size: 256 | lm loss: 3.546107E+00 | grad norm: 0.390 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.168 | TFLOPs: 28.26 | +7: iteration 9090/ 37905 | consumed samples: 2327040 | consumed tokens: 4765777920 | elapsed time per iteration (s): 0.23 | learning rate: 1.771E-04 | global batch size: 256 | lm loss: 3.550522E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.099 | TFLOPs: 28.53 | +7: iteration 9100/ 37905 | consumed samples: 2329600 | consumed tokens: 4771020800 | elapsed time per iteration (s): 0.23 | learning rate: 1.771E-04 | global batch size: 256 | lm loss: 3.505145E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.772 | TFLOPs: 28.32 | +7: iteration 9110/ 37905 | consumed samples: 2332160 | consumed tokens: 4776263680 | elapsed time per iteration (s): 0.25 | learning rate: 1.770E-04 | global batch size: 256 | lm loss: 3.524605E+00 | grad norm: 0.373 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1040.619 | TFLOPs: 26.51 | +7: iteration 9120/ 37905 | consumed samples: 2334720 | consumed tokens: 4781506560 | elapsed time per iteration (s): 0.23 | learning rate: 1.770E-04 | global batch size: 256 | lm loss: 3.511637E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.046 | TFLOPs: 27.90 | +7: iteration 9130/ 37905 | consumed samples: 2337280 | consumed tokens: 4786749440 | elapsed time per iteration (s): 0.23 | learning rate: 1.769E-04 | global batch size: 256 | lm loss: 3.524271E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.831 | TFLOPs: 28.20 | +7: iteration 9140/ 37905 | consumed samples: 2339840 | consumed tokens: 4791992320 | elapsed time per iteration (s): 0.23 | learning rate: 1.769E-04 | global batch size: 256 | lm loss: 3.527608E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.075 | TFLOPs: 28.30 | +7: iteration 9150/ 37905 | consumed samples: 2342400 | consumed tokens: 4797235200 | elapsed time per iteration (s): 0.23 | learning rate: 1.768E-04 | global batch size: 256 | lm loss: 3.490535E+00 | grad norm: 0.368 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.475 | TFLOPs: 28.03 | +7: iteration 9160/ 37905 | consumed samples: 2344960 | consumed tokens: 4802478080 | elapsed time per iteration (s): 0.23 | learning rate: 1.768E-04 | global batch size: 256 | lm loss: 3.515359E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.156 | TFLOPs: 28.13 | +7: iteration 9170/ 37905 | consumed samples: 2347520 | consumed tokens: 4807720960 | elapsed time per iteration (s): 0.24 | learning rate: 1.767E-04 | global batch size: 256 | lm loss: 3.512858E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1082.970 | TFLOPs: 27.59 | +7: iteration 9180/ 37905 | consumed samples: 2350080 | consumed tokens: 4812963840 | elapsed time per iteration (s): 0.23 | learning rate: 1.767E-04 | global batch size: 256 | lm loss: 3.528008E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.661 | TFLOPs: 28.22 | +7: iteration 9190/ 37905 | consumed samples: 2352640 | consumed tokens: 4818206720 | elapsed time per iteration (s): 0.25 | learning rate: 1.766E-04 | global batch size: 256 | lm loss: 3.516322E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1041.261 | TFLOPs: 26.53 | +7: iteration 9200/ 37905 | consumed samples: 2355200 | consumed tokens: 4823449600 | elapsed time per iteration (s): 0.24 | learning rate: 1.766E-04 | global batch size: 256 | lm loss: 3.552250E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1050.539 | TFLOPs: 26.76 | +7: iteration 9210/ 37905 | consumed samples: 2357760 | consumed tokens: 4828692480 | elapsed time per iteration (s): 0.25 | learning rate: 1.765E-04 | global batch size: 256 | lm loss: 3.536626E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1012.849 | TFLOPs: 25.80 | +7: iteration 9220/ 37905 | consumed samples: 2360320 | consumed tokens: 4833935360 | elapsed time per iteration (s): 0.23 | learning rate: 1.765E-04 | global batch size: 256 | lm loss: 3.540602E+00 | grad norm: 0.385 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.053 | TFLOPs: 28.02 | +7: iteration 9230/ 37905 | consumed samples: 2362880 | consumed tokens: 4839178240 | elapsed time per iteration (s): 0.23 | learning rate: 1.764E-04 | global batch size: 256 | lm loss: 3.531083E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.713 | TFLOPs: 28.09 | +7: iteration 9240/ 37905 | consumed samples: 2365440 | consumed tokens: 4844421120 | elapsed time per iteration (s): 0.23 | learning rate: 1.764E-04 | global batch size: 256 | lm loss: 3.552122E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.945 | TFLOPs: 27.87 | +7: iteration 9250/ 37905 | consumed samples: 2368000 | consumed tokens: 4849664000 | elapsed time per iteration (s): 0.23 | learning rate: 1.763E-04 | global batch size: 256 | lm loss: 3.546910E+00 | grad norm: 0.420 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.658 | TFLOPs: 28.57 | +7: iteration 9260/ 37905 | consumed samples: 2370560 | consumed tokens: 4854906880 | elapsed time per iteration (s): 0.23 | learning rate: 1.762E-04 | global batch size: 256 | lm loss: 3.504171E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.572 | TFLOPs: 28.24 | +7: iteration 9270/ 37905 | consumed samples: 2373120 | consumed tokens: 4860149760 | elapsed time per iteration (s): 0.23 | learning rate: 1.762E-04 | global batch size: 256 | lm loss: 3.496696E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.208 | TFLOPs: 28.26 | +7: iteration 9280/ 37905 | consumed samples: 2375680 | consumed tokens: 4865392640 | elapsed time per iteration (s): 0.23 | learning rate: 1.761E-04 | global batch size: 256 | lm loss: 3.536147E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.842 | TFLOPs: 28.63 | +7: iteration 9290/ 37905 | consumed samples: 2378240 | consumed tokens: 4870635520 | elapsed time per iteration (s): 0.23 | learning rate: 1.761E-04 | global batch size: 256 | lm loss: 3.517687E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.963 | TFLOPs: 28.38 | +7: iteration 9300/ 37905 | consumed samples: 2380800 | consumed tokens: 4875878400 | elapsed time per iteration (s): 0.23 | learning rate: 1.760E-04 | global batch size: 256 | lm loss: 3.503256E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.512 | TFLOPs: 28.24 | +7: iteration 9310/ 37905 | consumed samples: 2383360 | consumed tokens: 4881121280 | elapsed time per iteration (s): 0.23 | learning rate: 1.760E-04 | global batch size: 256 | lm loss: 3.518145E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.257 | TFLOPs: 28.31 | +7: iteration 9320/ 37905 | consumed samples: 2385920 | consumed tokens: 4886364160 | elapsed time per iteration (s): 0.23 | learning rate: 1.759E-04 | global batch size: 256 | lm loss: 3.499067E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.569 | TFLOPs: 28.47 | +7: iteration 9330/ 37905 | consumed samples: 2388480 | consumed tokens: 4891607040 | elapsed time per iteration (s): 0.23 | learning rate: 1.759E-04 | global batch size: 256 | lm loss: 3.506617E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.198 | TFLOPs: 28.46 | +7: iteration 9340/ 37905 | consumed samples: 2391040 | consumed tokens: 4896849920 | elapsed time per iteration (s): 0.23 | learning rate: 1.758E-04 | global batch size: 256 | lm loss: 3.515556E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.350 | TFLOPs: 28.11 | +7: iteration 9350/ 37905 | consumed samples: 2393600 | consumed tokens: 4902092800 | elapsed time per iteration (s): 0.23 | learning rate: 1.758E-04 | global batch size: 256 | lm loss: 3.536916E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.960 | TFLOPs: 28.02 | +7: iteration 9360/ 37905 | consumed samples: 2396160 | consumed tokens: 4907335680 | elapsed time per iteration (s): 0.24 | learning rate: 1.757E-04 | global batch size: 256 | lm loss: 3.512122E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1066.378 | TFLOPs: 27.17 | +7: iteration 9370/ 37905 | consumed samples: 2398720 | consumed tokens: 4912578560 | elapsed time per iteration (s): 0.23 | learning rate: 1.757E-04 | global batch size: 256 | lm loss: 3.512033E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.752 | TFLOPs: 28.14 | +7: iteration 9380/ 37905 | consumed samples: 2401280 | consumed tokens: 4917821440 | elapsed time per iteration (s): 0.24 | learning rate: 1.756E-04 | global batch size: 256 | lm loss: 3.519176E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.054 | TFLOPs: 27.67 | +7: iteration 9390/ 37905 | consumed samples: 2403840 | consumed tokens: 4923064320 | elapsed time per iteration (s): 0.24 | learning rate: 1.756E-04 | global batch size: 256 | lm loss: 3.513902E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.801 | TFLOPs: 27.74 | +7: iteration 9400/ 37905 | consumed samples: 2406400 | consumed tokens: 4928307200 | elapsed time per iteration (s): 0.23 | learning rate: 1.755E-04 | global batch size: 256 | lm loss: 3.511081E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.102 | TFLOPs: 28.28 | +7: iteration 9410/ 37905 | consumed samples: 2408960 | consumed tokens: 4933550080 | elapsed time per iteration (s): 0.23 | learning rate: 1.755E-04 | global batch size: 256 | lm loss: 3.527905E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.790 | TFLOPs: 28.25 | +7: iteration 9420/ 37905 | consumed samples: 2411520 | consumed tokens: 4938792960 | elapsed time per iteration (s): 0.29 | learning rate: 1.754E-04 | global batch size: 256 | lm loss: 3.520803E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 893.301 | TFLOPs: 22.76 | +7: iteration 9430/ 37905 | consumed samples: 2414080 | consumed tokens: 4944035840 | elapsed time per iteration (s): 0.23 | learning rate: 1.754E-04 | global batch size: 256 | lm loss: 3.538419E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.497 | TFLOPs: 28.16 | +7: iteration 9440/ 37905 | consumed samples: 2416640 | consumed tokens: 4949278720 | elapsed time per iteration (s): 0.23 | learning rate: 1.753E-04 | global batch size: 256 | lm loss: 3.547800E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.259 | TFLOPs: 28.26 | +7: iteration 9450/ 37905 | consumed samples: 2419200 | consumed tokens: 4954521600 | elapsed time per iteration (s): 0.25 | learning rate: 1.753E-04 | global batch size: 256 | lm loss: 3.490954E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1029.243 | TFLOPs: 26.22 | +7: iteration 9460/ 37905 | consumed samples: 2421760 | consumed tokens: 4959764480 | elapsed time per iteration (s): 0.23 | learning rate: 1.752E-04 | global batch size: 256 | lm loss: 3.518048E+00 | grad norm: 0.367 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.126 | TFLOPs: 28.26 | +7: iteration 9470/ 37905 | consumed samples: 2424320 | consumed tokens: 4965007360 | elapsed time per iteration (s): 0.23 | learning rate: 1.752E-04 | global batch size: 256 | lm loss: 3.531611E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.386 | TFLOPs: 28.21 | +7: iteration 9480/ 37905 | consumed samples: 2426880 | consumed tokens: 4970250240 | elapsed time per iteration (s): 0.23 | learning rate: 1.751E-04 | global batch size: 256 | lm loss: 3.500092E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.921 | TFLOPs: 28.28 | +7: iteration 9490/ 37905 | consumed samples: 2429440 | consumed tokens: 4975493120 | elapsed time per iteration (s): 0.23 | learning rate: 1.751E-04 | global batch size: 256 | lm loss: 3.476546E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.274 | TFLOPs: 28.36 | +7: iteration 9500/ 37905 | consumed samples: 2432000 | consumed tokens: 4980736000 | elapsed time per iteration (s): 0.23 | learning rate: 1.750E-04 | global batch size: 256 | lm loss: 3.516813E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.856 | TFLOPs: 28.07 | +7: iteration 9510/ 37905 | consumed samples: 2434560 | consumed tokens: 4985978880 | elapsed time per iteration (s): 0.23 | learning rate: 1.750E-04 | global batch size: 256 | lm loss: 3.532534E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.558 | TFLOPs: 27.83 | +7: iteration 9520/ 37905 | consumed samples: 2437120 | consumed tokens: 4991221760 | elapsed time per iteration (s): 0.23 | learning rate: 1.749E-04 | global batch size: 256 | lm loss: 3.538594E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.460 | TFLOPs: 28.14 | +7: iteration 9530/ 37905 | consumed samples: 2439680 | consumed tokens: 4996464640 | elapsed time per iteration (s): 0.24 | learning rate: 1.749E-04 | global batch size: 256 | lm loss: 3.510752E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1084.870 | TFLOPs: 27.64 | +7: iteration 9540/ 37905 | consumed samples: 2442240 | consumed tokens: 5001707520 | elapsed time per iteration (s): 0.23 | learning rate: 1.748E-04 | global batch size: 256 | lm loss: 3.523549E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.647 | TFLOPs: 27.94 | +7: iteration 9550/ 37905 | consumed samples: 2444800 | consumed tokens: 5006950400 | elapsed time per iteration (s): 0.24 | learning rate: 1.748E-04 | global batch size: 256 | lm loss: 3.521322E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.698 | TFLOPs: 27.48 | +7: iteration 9560/ 37905 | consumed samples: 2447360 | consumed tokens: 5012193280 | elapsed time per iteration (s): 0.24 | learning rate: 1.747E-04 | global batch size: 256 | lm loss: 3.505148E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1077.005 | TFLOPs: 27.44 | +7: iteration 9570/ 37905 | consumed samples: 2449920 | consumed tokens: 5017436160 | elapsed time per iteration (s): 0.23 | learning rate: 1.746E-04 | global batch size: 256 | lm loss: 3.491534E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.531 | TFLOPs: 27.86 | +7: iteration 9580/ 37905 | consumed samples: 2452480 | consumed tokens: 5022679040 | elapsed time per iteration (s): 0.23 | learning rate: 1.746E-04 | global batch size: 256 | lm loss: 3.514790E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.536 | TFLOPs: 27.99 | +7: iteration 9590/ 37905 | consumed samples: 2455040 | consumed tokens: 5027921920 | elapsed time per iteration (s): 0.25 | learning rate: 1.745E-04 | global batch size: 256 | lm loss: 3.523473E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1015.171 | TFLOPs: 25.86 | +7: iteration 9600/ 37905 | consumed samples: 2457600 | consumed tokens: 5033164800 | elapsed time per iteration (s): 0.23 | learning rate: 1.745E-04 | global batch size: 256 | lm loss: 3.503482E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.597 | TFLOPs: 27.99 | +7: iteration 9610/ 37905 | consumed samples: 2460160 | consumed tokens: 5038407680 | elapsed time per iteration (s): 0.23 | learning rate: 1.744E-04 | global batch size: 256 | lm loss: 3.485991E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.325 | TFLOPs: 28.01 | +7: iteration 9620/ 37905 | consumed samples: 2462720 | consumed tokens: 5043650560 | elapsed time per iteration (s): 0.24 | learning rate: 1.744E-04 | global batch size: 256 | lm loss: 3.521035E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.817 | TFLOPs: 27.74 | +7: iteration 9630/ 37905 | consumed samples: 2465280 | consumed tokens: 5048893440 | elapsed time per iteration (s): 0.23 | learning rate: 1.743E-04 | global batch size: 256 | lm loss: 3.521003E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.115 | TFLOPs: 28.36 | +7: iteration 9640/ 37905 | consumed samples: 2467840 | consumed tokens: 5054136320 | elapsed time per iteration (s): 0.23 | learning rate: 1.743E-04 | global batch size: 256 | lm loss: 3.514847E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.271 | TFLOPs: 28.26 | +7: iteration 9650/ 37905 | consumed samples: 2470400 | consumed tokens: 5059379200 | elapsed time per iteration (s): 0.23 | learning rate: 1.742E-04 | global batch size: 256 | lm loss: 3.516788E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.372 | TFLOPs: 28.08 | +7: iteration 9660/ 37905 | consumed samples: 2472960 | consumed tokens: 5064622080 | elapsed time per iteration (s): 0.23 | learning rate: 1.742E-04 | global batch size: 256 | lm loss: 3.496463E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.716 | TFLOPs: 28.50 | +7: iteration 9670/ 37905 | consumed samples: 2475520 | consumed tokens: 5069864960 | elapsed time per iteration (s): 0.23 | learning rate: 1.741E-04 | global batch size: 256 | lm loss: 3.509975E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.299 | TFLOPs: 28.46 | +7: iteration 9680/ 37905 | consumed samples: 2478080 | consumed tokens: 5075107840 | elapsed time per iteration (s): 0.23 | learning rate: 1.741E-04 | global batch size: 256 | lm loss: 3.476524E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.915 | TFLOPs: 28.45 | +7: iteration 9690/ 37905 | consumed samples: 2480640 | consumed tokens: 5080350720 | elapsed time per iteration (s): 0.23 | learning rate: 1.740E-04 | global batch size: 256 | lm loss: 3.516664E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.189 | TFLOPs: 28.18 | +7: iteration 9700/ 37905 | consumed samples: 2483200 | consumed tokens: 5085593600 | elapsed time per iteration (s): 0.23 | learning rate: 1.740E-04 | global batch size: 256 | lm loss: 3.494567E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.145 | TFLOPs: 28.03 | +7: iteration 9710/ 37905 | consumed samples: 2485760 | consumed tokens: 5090836480 | elapsed time per iteration (s): 0.23 | learning rate: 1.739E-04 | global batch size: 256 | lm loss: 3.526507E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.068 | TFLOPs: 28.10 | +7: iteration 9720/ 37905 | consumed samples: 2488320 | consumed tokens: 5096079360 | elapsed time per iteration (s): 0.23 | learning rate: 1.739E-04 | global batch size: 256 | lm loss: 3.492676E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.656 | TFLOPs: 28.29 | +7: iteration 9730/ 37905 | consumed samples: 2490880 | consumed tokens: 5101322240 | elapsed time per iteration (s): 0.23 | learning rate: 1.738E-04 | global batch size: 256 | lm loss: 3.514509E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.307 | TFLOPs: 28.18 | +7: iteration 9740/ 37905 | consumed samples: 2493440 | consumed tokens: 5106565120 | elapsed time per iteration (s): 0.23 | learning rate: 1.737E-04 | global batch size: 256 | lm loss: 3.471817E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.287 | TFLOPs: 28.39 | +7: iteration 9750/ 37905 | consumed samples: 2496000 | consumed tokens: 5111808000 | elapsed time per iteration (s): 0.23 | learning rate: 1.737E-04 | global batch size: 256 | lm loss: 3.521716E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.375 | TFLOPs: 28.06 | +7: iteration 9760/ 37905 | consumed samples: 2498560 | consumed tokens: 5117050880 | elapsed time per iteration (s): 0.23 | learning rate: 1.736E-04 | global batch size: 256 | lm loss: 3.523599E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.972 | TFLOPs: 28.07 | +7: iteration 9770/ 37905 | consumed samples: 2501120 | consumed tokens: 5122293760 | elapsed time per iteration (s): 0.24 | learning rate: 1.736E-04 | global batch size: 256 | lm loss: 3.509800E+00 | grad norm: 0.377 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1079.309 | TFLOPs: 27.50 | +7: iteration 9780/ 37905 | consumed samples: 2503680 | consumed tokens: 5127536640 | elapsed time per iteration (s): 0.23 | learning rate: 1.735E-04 | global batch size: 256 | lm loss: 3.487930E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.864 | TFLOPs: 28.30 | +7: iteration 9790/ 37905 | consumed samples: 2506240 | consumed tokens: 5132779520 | elapsed time per iteration (s): 0.24 | learning rate: 1.735E-04 | global batch size: 256 | lm loss: 3.506251E+00 | grad norm: 0.406 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1054.641 | TFLOPs: 26.87 | +7: iteration 9800/ 37905 | consumed samples: 2508800 | consumed tokens: 5138022400 | elapsed time per iteration (s): 0.24 | learning rate: 1.734E-04 | global batch size: 256 | lm loss: 3.528482E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.288 | TFLOPs: 27.70 | +7: iteration 9810/ 37905 | consumed samples: 2511360 | consumed tokens: 5143265280 | elapsed time per iteration (s): 0.23 | learning rate: 1.734E-04 | global batch size: 256 | lm loss: 3.504802E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.395 | TFLOPs: 28.21 | +7: iteration 9820/ 37905 | consumed samples: 2513920 | consumed tokens: 5148508160 | elapsed time per iteration (s): 0.23 | learning rate: 1.733E-04 | global batch size: 256 | lm loss: 3.494572E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.445 | TFLOPs: 28.21 | +7: iteration 9830/ 37905 | consumed samples: 2516480 | consumed tokens: 5153751040 | elapsed time per iteration (s): 0.23 | learning rate: 1.733E-04 | global batch size: 256 | lm loss: 3.501683E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.157 | TFLOPs: 28.18 | +7: iteration 9840/ 37905 | consumed samples: 2519040 | consumed tokens: 5158993920 | elapsed time per iteration (s): 0.24 | learning rate: 1.732E-04 | global batch size: 256 | lm loss: 3.524142E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1054.153 | TFLOPs: 26.85 | +7: iteration 9850/ 37905 | consumed samples: 2521600 | consumed tokens: 5164236800 | elapsed time per iteration (s): 0.23 | learning rate: 1.732E-04 | global batch size: 256 | lm loss: 3.491145E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.234 | TFLOPs: 27.95 | +7: iteration 9860/ 37905 | consumed samples: 2524160 | consumed tokens: 5169479680 | elapsed time per iteration (s): 0.23 | learning rate: 1.731E-04 | global batch size: 256 | lm loss: 3.471498E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.197 | TFLOPs: 27.93 | +7: iteration 9870/ 37905 | consumed samples: 2526720 | consumed tokens: 5174722560 | elapsed time per iteration (s): 0.24 | learning rate: 1.731E-04 | global batch size: 256 | lm loss: 3.499860E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1081.813 | TFLOPs: 27.56 | +7: iteration 9880/ 37905 | consumed samples: 2529280 | consumed tokens: 5179965440 | elapsed time per iteration (s): 0.23 | learning rate: 1.730E-04 | global batch size: 256 | lm loss: 3.518334E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.346 | TFLOPs: 28.13 | +7: iteration 9890/ 37905 | consumed samples: 2531840 | consumed tokens: 5185208320 | elapsed time per iteration (s): 0.23 | learning rate: 1.729E-04 | global batch size: 256 | lm loss: 3.513569E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.541 | TFLOPs: 28.37 | +7: iteration 9900/ 37905 | consumed samples: 2534400 | consumed tokens: 5190451200 | elapsed time per iteration (s): 0.24 | learning rate: 1.729E-04 | global batch size: 256 | lm loss: 3.523259E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.643 | TFLOPs: 27.73 | +7: iteration 9910/ 37905 | consumed samples: 2536960 | consumed tokens: 5195694080 | elapsed time per iteration (s): 0.23 | learning rate: 1.728E-04 | global batch size: 256 | lm loss: 3.530082E+00 | grad norm: 0.377 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.622 | TFLOPs: 27.89 | +7: iteration 9920/ 37905 | consumed samples: 2539520 | consumed tokens: 5200936960 | elapsed time per iteration (s): 0.24 | learning rate: 1.728E-04 | global batch size: 256 | lm loss: 3.500827E+00 | grad norm: 0.435 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1084.292 | TFLOPs: 27.62 | +7: iteration 9930/ 37905 | consumed samples: 2542080 | consumed tokens: 5206179840 | elapsed time per iteration (s): 0.23 | learning rate: 1.727E-04 | global batch size: 256 | lm loss: 3.503950E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.950 | TFLOPs: 28.28 | +7: iteration 9940/ 37905 | consumed samples: 2544640 | consumed tokens: 5211422720 | elapsed time per iteration (s): 0.23 | learning rate: 1.727E-04 | global batch size: 256 | lm loss: 3.515852E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.276 | TFLOPs: 27.90 | +7: iteration 9950/ 37905 | consumed samples: 2547200 | consumed tokens: 5216665600 | elapsed time per iteration (s): 0.23 | learning rate: 1.726E-04 | global batch size: 256 | lm loss: 3.517183E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.011 | TFLOPs: 28.23 | +7: iteration 9960/ 37905 | consumed samples: 2549760 | consumed tokens: 5221908480 | elapsed time per iteration (s): 0.23 | learning rate: 1.726E-04 | global batch size: 256 | lm loss: 3.515994E+00 | grad norm: 0.387 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.818 | TFLOPs: 28.07 | +7: iteration 9970/ 37905 | consumed samples: 2552320 | consumed tokens: 5227151360 | elapsed time per iteration (s): 0.23 | learning rate: 1.725E-04 | global batch size: 256 | lm loss: 3.498879E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.873 | TFLOPs: 28.40 | +7: iteration 9980/ 37905 | consumed samples: 2554880 | consumed tokens: 5232394240 | elapsed time per iteration (s): 0.23 | learning rate: 1.725E-04 | global batch size: 256 | lm loss: 3.482792E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.472 | TFLOPs: 28.21 | +7: iteration 9990/ 37905 | consumed samples: 2557440 | consumed tokens: 5237637120 | elapsed time per iteration (s): 0.23 | learning rate: 1.724E-04 | global batch size: 256 | lm loss: 3.510801E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.968 | TFLOPs: 27.97 | +0: [2022-11-29 17:35:06,230] [INFO] [logging.py:68:log_dist] [Rank 0] step=10000, skipped=0, lr=[0.00017235122366283088, 0.00017235122366283088, 0.00017235122366283088], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 10000/ 37905 | consumed samples: 2560000 | consumed tokens: 5242880000 | elapsed time per iteration (s): 0.23 | learning rate: 1.724E-04 | global batch size: 256 | lm loss: 3.512525E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.627 | TFLOPs: 28.01 | +0: steps: 10000 loss: 3.4989 iter time (s): 0.233 samples/sec: 1100.576 +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 10000 | lm loss value: 3.346467E+00 | lm loss PPL: 2.840223E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 10000 to checkpoints_83moscar +0: [2022-11-29 17:35:06,320] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step10000 is begin to save! +0: [2022-11-29 17:35:06,323] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:35:06,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:35:06,397] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:35:06,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:35:06,410] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:35:06,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:35:06,421] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:35:06,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:35:06,433] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:35:06,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:35:06,444] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:35:06,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:35:06,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:35:06,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:35:06,467] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:35:06,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:35:06,478] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:35:06,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:35:06,490] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:35:06,501] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:35:06,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:35:06,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:35:06,512] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:35:06,513] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:35:06,514] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step10000/mp_rank_00_model_states.pt +0: [2022-11-29 17:35:06,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:35:06,516] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:35:06,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:35:06,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:35:06,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:35:06,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 17:35:06,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:35:06,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:35:06,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 17:35:06,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:35:06,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:35:06,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 17:35:06,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:35:06,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:35:06,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 17:35:06,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:35:06,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:35:06,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:35:06,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 17:35:06,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:35:06,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:35:06,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 17:35:06,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:35:06,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:35:06,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 17:35:06,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:35:06,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:35:06,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 17:35:06,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:35:06,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:35:06,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 17:35:06,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:35:06,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 17:35:06,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:35:06,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:35:06,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3: [2022-11-29 17:35:06,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:35:06,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 17:35:06,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 17:35:06,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:35:06,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:35:06,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 17:35:06,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:35:06,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:35:06,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 17:35:06,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:35:06,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:35:06,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:35:06,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 17:35:06,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:35:06,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 17:35:06,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:35:06,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:35:06,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 17:35:06,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:35:06,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:35:06,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 17:35:06,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:35:06,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:35:06,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:35:06,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:35:06,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:35:06,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 17:35:06,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 17:35:06,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:35:06,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 17:35:06,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:35:06,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:35:06,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 17:35:06,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:35:06,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:35:06,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 17:35:06,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:35:06,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:35:06,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 17:35:06,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:35:06,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:35:06,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +4: [2022-11-29 17:35:06,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +1: [2022-11-29 17:35:06,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 17:35:06,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 17:35:06,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:35:06,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +0: [2022-11-29 17:35:06,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:35:06,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 17:35:06,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:35:06,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 17:35:06,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:35:06,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:35:06,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 17:35:06,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:35:06,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:35:06,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 17:35:06,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:35:06,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:35:06,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 17:35:06,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:35:06,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:35:06,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 17:35:06,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:35:06,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:35:06,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 17:35:06,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:35:06,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:35:06,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 17:35:06,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:35:06,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:35:06,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 17:35:06,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:35:06,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:35:06,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 17:35:06,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:35:06,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:35:06,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 17:35:06,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:35:06,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:35:06,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 17:35:06,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:35:06,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:35:06,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 17:35:06,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:35:06,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:35:06,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 17:35:06,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:35:06,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:35:06,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +4: [2022-11-29 17:35:06,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +1: [2022-11-29 17:35:06,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 17:35:06,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 17:35:06,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:35:06,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:35:06,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:35:06,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:35:06,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 17:35:06,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 17:35:06,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:35:06,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:35:06,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 17:35:06,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:35:06,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:35:06,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 17:35:06,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:35:06,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:35:06,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 17:35:06,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:35:06,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:35:06,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 17:35:06,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:35:06,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:35:06,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 17:35:06,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:35:06,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:35:06,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:35:06,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 17:35:06,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:35:06,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 17:35:06,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:35:06,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:35:06,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 17:35:06,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:35:06,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:35:06,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 17:35:06,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:35:06,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:35:06,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +7: [2022-11-29 17:35:06,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:35:06,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:35:06,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +5: [2022-11-29 17:35:06,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:35:06,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:35:06,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 17:35:06,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:35:06,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:35:06,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +4: [2022-11-29 17:35:06,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:35:06,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:35:06,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +0: [2022-11-29 17:35:06,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +4: [2022-11-29 17:35:06,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: [2022-11-29 17:35:06,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +6: [2022-11-29 17:35:06,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:35:06,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:35:06,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +2: [2022-11-29 17:35:06,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +6: [2022-11-29 17:35:06,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 17:35:06,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +2: [2022-11-29 17:35:06,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:35:06,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:35:06,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +1: [2022-11-29 17:35:06,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:35:06,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:35:06,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +3: [2022-11-29 17:35:06,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:35:06,571] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step10000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:35:06,571] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +0: successfully saved checkpoint at iteration 10000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 255.73 +7: iteration 10010/ 37905 | consumed samples: 2562560 | consumed tokens: 5248122880 | elapsed time per iteration (s): 0.27 | learning rate: 1.723E-04 | global batch size: 256 | lm loss: 3.524781E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 963.157 | TFLOPs: 24.54 | +7: iteration 10020/ 37905 | consumed samples: 2565120 | consumed tokens: 5253365760 | elapsed time per iteration (s): 0.23 | learning rate: 1.722E-04 | global batch size: 256 | lm loss: 3.479338E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.476 | TFLOPs: 28.34 | +7: iteration 10030/ 37905 | consumed samples: 2567680 | consumed tokens: 5258608640 | elapsed time per iteration (s): 0.23 | learning rate: 1.722E-04 | global batch size: 256 | lm loss: 3.513310E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.369 | TFLOPs: 28.01 | +7: iteration 10040/ 37905 | consumed samples: 2570240 | consumed tokens: 5263851520 | elapsed time per iteration (s): 0.26 | learning rate: 1.721E-04 | global batch size: 256 | lm loss: 3.521532E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 994.358 | TFLOPs: 25.33 | +7: iteration 10050/ 37905 | consumed samples: 2572800 | consumed tokens: 5269094400 | elapsed time per iteration (s): 0.23 | learning rate: 1.721E-04 | global batch size: 256 | lm loss: 3.487642E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.416 | TFLOPs: 28.16 | +7: iteration 10060/ 37905 | consumed samples: 2575360 | consumed tokens: 5274337280 | elapsed time per iteration (s): 0.23 | learning rate: 1.720E-04 | global batch size: 256 | lm loss: 3.519468E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.569 | TFLOPs: 28.19 | +7: iteration 10070/ 37905 | consumed samples: 2577920 | consumed tokens: 5279580160 | elapsed time per iteration (s): 0.23 | learning rate: 1.720E-04 | global batch size: 256 | lm loss: 3.509142E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.064 | TFLOPs: 28.28 | +7: iteration 10080/ 37905 | consumed samples: 2580480 | consumed tokens: 5284823040 | elapsed time per iteration (s): 0.23 | learning rate: 1.719E-04 | global batch size: 256 | lm loss: 3.497851E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.862 | TFLOPs: 28.22 | +7: iteration 10090/ 37905 | consumed samples: 2583040 | consumed tokens: 5290065920 | elapsed time per iteration (s): 0.25 | learning rate: 1.719E-04 | global batch size: 256 | lm loss: 3.490299E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1033.300 | TFLOPs: 26.32 | +7: iteration 10100/ 37905 | consumed samples: 2585600 | consumed tokens: 5295308800 | elapsed time per iteration (s): 0.24 | learning rate: 1.718E-04 | global batch size: 256 | lm loss: 3.473644E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1082.379 | TFLOPs: 27.57 | +7: iteration 10110/ 37905 | consumed samples: 2588160 | consumed tokens: 5300551680 | elapsed time per iteration (s): 0.23 | learning rate: 1.718E-04 | global batch size: 256 | lm loss: 3.508858E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.086 | TFLOPs: 28.38 | +7: iteration 10120/ 37905 | consumed samples: 2590720 | consumed tokens: 5305794560 | elapsed time per iteration (s): 0.23 | learning rate: 1.717E-04 | global batch size: 256 | lm loss: 3.495399E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.348 | TFLOPs: 27.93 | +7: iteration 10130/ 37905 | consumed samples: 2593280 | consumed tokens: 5311037440 | elapsed time per iteration (s): 0.23 | learning rate: 1.716E-04 | global batch size: 256 | lm loss: 3.500290E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.462 | TFLOPs: 27.75 | +7: iteration 10140/ 37905 | consumed samples: 2595840 | consumed tokens: 5316280320 | elapsed time per iteration (s): 0.23 | learning rate: 1.716E-04 | global batch size: 256 | lm loss: 3.497154E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.917 | TFLOPs: 28.17 | +7: iteration 10150/ 37905 | consumed samples: 2598400 | consumed tokens: 5321523200 | elapsed time per iteration (s): 0.23 | learning rate: 1.715E-04 | global batch size: 256 | lm loss: 3.514713E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.957 | TFLOPs: 28.45 | +7: iteration 10160/ 37905 | consumed samples: 2600960 | consumed tokens: 5326766080 | elapsed time per iteration (s): 0.24 | learning rate: 1.715E-04 | global batch size: 256 | lm loss: 3.533868E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1077.039 | TFLOPs: 27.44 | +7: iteration 10170/ 37905 | consumed samples: 2603520 | consumed tokens: 5332008960 | elapsed time per iteration (s): 0.23 | learning rate: 1.714E-04 | global batch size: 256 | lm loss: 3.524423E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.599 | TFLOPs: 28.27 | +7: iteration 10180/ 37905 | consumed samples: 2606080 | consumed tokens: 5337251840 | elapsed time per iteration (s): 0.27 | learning rate: 1.714E-04 | global batch size: 256 | lm loss: 3.498156E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 952.253 | TFLOPs: 24.26 | +7: iteration 10190/ 37905 | consumed samples: 2608640 | consumed tokens: 5342494720 | elapsed time per iteration (s): 0.24 | learning rate: 1.713E-04 | global batch size: 256 | lm loss: 3.506814E+00 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1052.369 | TFLOPs: 26.81 | +7: iteration 10200/ 37905 | consumed samples: 2611200 | consumed tokens: 5347737600 | elapsed time per iteration (s): 0.23 | learning rate: 1.713E-04 | global batch size: 256 | lm loss: 3.507251E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.389 | TFLOPs: 27.96 | +7: iteration 10210/ 37905 | consumed samples: 2613760 | consumed tokens: 5352980480 | elapsed time per iteration (s): 0.23 | learning rate: 1.712E-04 | global batch size: 256 | lm loss: 3.489032E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.606 | TFLOPs: 27.99 | +7: iteration 10220/ 37905 | consumed samples: 2616320 | consumed tokens: 5358223360 | elapsed time per iteration (s): 0.23 | learning rate: 1.711E-04 | global batch size: 256 | lm loss: 3.499382E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.455 | TFLOPs: 28.11 | +7: iteration 10230/ 37905 | consumed samples: 2618880 | consumed tokens: 5363466240 | elapsed time per iteration (s): 0.24 | learning rate: 1.711E-04 | global batch size: 256 | lm loss: 3.512606E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.071 | TFLOPs: 27.64 | +7: iteration 10240/ 37905 | consumed samples: 2621440 | consumed tokens: 5368709120 | elapsed time per iteration (s): 0.23 | learning rate: 1.710E-04 | global batch size: 256 | lm loss: 3.501194E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.762 | TFLOPs: 28.17 | +7: iteration 10250/ 37905 | consumed samples: 2624000 | consumed tokens: 5373952000 | elapsed time per iteration (s): 0.23 | learning rate: 1.710E-04 | global batch size: 256 | lm loss: 3.501122E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.717 | TFLOPs: 28.22 | +7: iteration 10260/ 37905 | consumed samples: 2626560 | consumed tokens: 5379194880 | elapsed time per iteration (s): 0.24 | learning rate: 1.709E-04 | global batch size: 256 | lm loss: 3.483699E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.312 | TFLOPs: 27.70 | +7: iteration 10270/ 37905 | consumed samples: 2629120 | consumed tokens: 5384437760 | elapsed time per iteration (s): 0.23 | learning rate: 1.709E-04 | global batch size: 256 | lm loss: 3.492764E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.963 | TFLOPs: 27.84 | +7: iteration 10280/ 37905 | consumed samples: 2631680 | consumed tokens: 5389680640 | elapsed time per iteration (s): 0.23 | learning rate: 1.708E-04 | global batch size: 256 | lm loss: 3.465294E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.371 | TFLOPs: 28.39 | +7: iteration 10290/ 37905 | consumed samples: 2634240 | consumed tokens: 5394923520 | elapsed time per iteration (s): 0.23 | learning rate: 1.708E-04 | global batch size: 256 | lm loss: 3.481764E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.786 | TFLOPs: 28.20 | +7: iteration 10300/ 37905 | consumed samples: 2636800 | consumed tokens: 5400166400 | elapsed time per iteration (s): 0.23 | learning rate: 1.707E-04 | global batch size: 256 | lm loss: 3.488001E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.315 | TFLOPs: 27.85 | +7: iteration 10310/ 37905 | consumed samples: 2639360 | consumed tokens: 5405409280 | elapsed time per iteration (s): 0.23 | learning rate: 1.706E-04 | global batch size: 256 | lm loss: 3.504799E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.590 | TFLOPs: 28.42 | +7: iteration 10320/ 37905 | consumed samples: 2641920 | consumed tokens: 5410652160 | elapsed time per iteration (s): 0.23 | learning rate: 1.706E-04 | global batch size: 256 | lm loss: 3.530383E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.256 | TFLOPs: 27.93 | +7: iteration 10330/ 37905 | consumed samples: 2644480 | consumed tokens: 5415895040 | elapsed time per iteration (s): 0.23 | learning rate: 1.705E-04 | global batch size: 256 | lm loss: 3.507862E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.365 | TFLOPs: 28.31 | +7: iteration 10340/ 37905 | consumed samples: 2647040 | consumed tokens: 5421137920 | elapsed time per iteration (s): 0.23 | learning rate: 1.705E-04 | global batch size: 256 | lm loss: 3.505400E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.952 | TFLOPs: 28.12 | +7: iteration 10350/ 37905 | consumed samples: 2649600 | consumed tokens: 5426380800 | elapsed time per iteration (s): 0.23 | learning rate: 1.704E-04 | global batch size: 256 | lm loss: 3.530738E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.937 | TFLOPs: 28.30 | +7: iteration 10360/ 37905 | consumed samples: 2652160 | consumed tokens: 5431623680 | elapsed time per iteration (s): 0.23 | learning rate: 1.704E-04 | global batch size: 256 | lm loss: 3.517331E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.056 | TFLOPs: 28.05 | +7: iteration 10370/ 37905 | consumed samples: 2654720 | consumed tokens: 5436866560 | elapsed time per iteration (s): 0.23 | learning rate: 1.703E-04 | global batch size: 256 | lm loss: 3.503270E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.135 | TFLOPs: 28.15 | +7: iteration 10380/ 37905 | consumed samples: 2657280 | consumed tokens: 5442109440 | elapsed time per iteration (s): 0.23 | learning rate: 1.703E-04 | global batch size: 256 | lm loss: 3.486724E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.083 | TFLOPs: 28.02 | +7: iteration 10390/ 37905 | consumed samples: 2659840 | consumed tokens: 5447352320 | elapsed time per iteration (s): 0.24 | learning rate: 1.702E-04 | global batch size: 256 | lm loss: 3.522780E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.833 | TFLOPs: 26.95 | +7: iteration 10400/ 37905 | consumed samples: 2662400 | consumed tokens: 5452595200 | elapsed time per iteration (s): 0.23 | learning rate: 1.701E-04 | global batch size: 256 | lm loss: 3.506735E+00 | grad norm: 0.382 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.606 | TFLOPs: 28.17 | +7: iteration 10410/ 37905 | consumed samples: 2664960 | consumed tokens: 5457838080 | elapsed time per iteration (s): 0.23 | learning rate: 1.701E-04 | global batch size: 256 | lm loss: 3.515595E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.295 | TFLOPs: 28.21 | +7: iteration 10420/ 37905 | consumed samples: 2667520 | consumed tokens: 5463080960 | elapsed time per iteration (s): 0.23 | learning rate: 1.700E-04 | global batch size: 256 | lm loss: 3.497449E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.010 | TFLOPs: 28.20 | +7: iteration 10430/ 37905 | consumed samples: 2670080 | consumed tokens: 5468323840 | elapsed time per iteration (s): 0.23 | learning rate: 1.700E-04 | global batch size: 256 | lm loss: 3.485680E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.554 | TFLOPs: 28.44 | +7: iteration 10440/ 37905 | consumed samples: 2672640 | consumed tokens: 5473566720 | elapsed time per iteration (s): 0.24 | learning rate: 1.699E-04 | global batch size: 256 | lm loss: 3.512108E+00 | grad norm: 0.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1061.435 | TFLOPs: 27.04 | +7: iteration 10450/ 37905 | consumed samples: 2675200 | consumed tokens: 5478809600 | elapsed time per iteration (s): 0.23 | learning rate: 1.699E-04 | global batch size: 256 | lm loss: 3.473483E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.223 | TFLOPs: 28.23 | +7: iteration 10460/ 37905 | consumed samples: 2677760 | consumed tokens: 5484052480 | elapsed time per iteration (s): 0.23 | learning rate: 1.698E-04 | global batch size: 256 | lm loss: 3.505029E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.121 | TFLOPs: 28.31 | +7: iteration 10470/ 37905 | consumed samples: 2680320 | consumed tokens: 5489295360 | elapsed time per iteration (s): 0.23 | learning rate: 1.697E-04 | global batch size: 256 | lm loss: 3.474202E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.636 | TFLOPs: 28.34 | +7: iteration 10480/ 37905 | consumed samples: 2682880 | consumed tokens: 5494538240 | elapsed time per iteration (s): 0.26 | learning rate: 1.697E-04 | global batch size: 256 | lm loss: 3.469097E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 979.749 | TFLOPs: 24.96 | +7: iteration 10490/ 37905 | consumed samples: 2685440 | consumed tokens: 5499781120 | elapsed time per iteration (s): 0.23 | learning rate: 1.696E-04 | global batch size: 256 | lm loss: 3.513731E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.337 | TFLOPs: 28.39 | +7: iteration 10500/ 37905 | consumed samples: 2688000 | consumed tokens: 5505024000 | elapsed time per iteration (s): 0.23 | learning rate: 1.696E-04 | global batch size: 256 | lm loss: 3.497853E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.103 | TFLOPs: 28.20 | +7: iteration 10510/ 37905 | consumed samples: 2690560 | consumed tokens: 5510266880 | elapsed time per iteration (s): 0.23 | learning rate: 1.695E-04 | global batch size: 256 | lm loss: 3.499099E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.074 | TFLOPs: 28.30 | +7: iteration 10520/ 37905 | consumed samples: 2693120 | consumed tokens: 5515509760 | elapsed time per iteration (s): 0.23 | learning rate: 1.695E-04 | global batch size: 256 | lm loss: 3.494335E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.483 | TFLOPs: 28.34 | +7: iteration 10530/ 37905 | consumed samples: 2695680 | consumed tokens: 5520752640 | elapsed time per iteration (s): 0.23 | learning rate: 1.694E-04 | global batch size: 256 | lm loss: 3.476617E+00 | grad norm: 0.383 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.763 | TFLOPs: 28.25 | +7: iteration 10540/ 37905 | consumed samples: 2698240 | consumed tokens: 5525995520 | elapsed time per iteration (s): 0.23 | learning rate: 1.694E-04 | global batch size: 256 | lm loss: 3.454372E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.641 | TFLOPs: 28.24 | +7: iteration 10550/ 37905 | consumed samples: 2700800 | consumed tokens: 5531238400 | elapsed time per iteration (s): 0.23 | learning rate: 1.693E-04 | global batch size: 256 | lm loss: 3.495369E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.990 | TFLOPs: 27.79 | +7: iteration 10560/ 37905 | consumed samples: 2703360 | consumed tokens: 5536481280 | elapsed time per iteration (s): 0.23 | learning rate: 1.692E-04 | global batch size: 256 | lm loss: 3.444204E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.441 | TFLOPs: 27.78 | +7: iteration 10570/ 37905 | consumed samples: 2705920 | consumed tokens: 5541724160 | elapsed time per iteration (s): 0.23 | learning rate: 1.692E-04 | global batch size: 256 | lm loss: 3.507990E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.508 | TFLOPs: 28.24 | +7: iteration 10580/ 37905 | consumed samples: 2708480 | consumed tokens: 5546967040 | elapsed time per iteration (s): 0.23 | learning rate: 1.691E-04 | global batch size: 256 | lm loss: 3.518302E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.359 | TFLOPs: 28.34 | +7: iteration 10590/ 37905 | consumed samples: 2711040 | consumed tokens: 5552209920 | elapsed time per iteration (s): 0.23 | learning rate: 1.691E-04 | global batch size: 256 | lm loss: 3.478109E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.077 | TFLOPs: 27.85 | +7: iteration 10600/ 37905 | consumed samples: 2713600 | consumed tokens: 5557452800 | elapsed time per iteration (s): 0.23 | learning rate: 1.690E-04 | global batch size: 256 | lm loss: 3.527125E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.259 | TFLOPs: 28.23 | +7: iteration 10610/ 37905 | consumed samples: 2716160 | consumed tokens: 5562695680 | elapsed time per iteration (s): 0.23 | learning rate: 1.690E-04 | global batch size: 256 | lm loss: 3.500926E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.606 | TFLOPs: 27.96 | +7: iteration 10620/ 37905 | consumed samples: 2718720 | consumed tokens: 5567938560 | elapsed time per iteration (s): 0.23 | learning rate: 1.689E-04 | global batch size: 256 | lm loss: 3.470415E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.239 | TFLOPs: 28.28 | +7: iteration 10630/ 37905 | consumed samples: 2721280 | consumed tokens: 5573181440 | elapsed time per iteration (s): 0.24 | learning rate: 1.688E-04 | global batch size: 256 | lm loss: 3.468952E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1083.246 | TFLOPs: 27.60 | +7: iteration 10640/ 37905 | consumed samples: 2723840 | consumed tokens: 5578424320 | elapsed time per iteration (s): 0.25 | learning rate: 1.688E-04 | global batch size: 256 | lm loss: 3.475131E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1039.431 | TFLOPs: 26.48 | +7: iteration 10650/ 37905 | consumed samples: 2726400 | consumed tokens: 5583667200 | elapsed time per iteration (s): 0.23 | learning rate: 1.687E-04 | global batch size: 256 | lm loss: 3.481490E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.330 | TFLOPs: 28.52 | +7: iteration 10660/ 37905 | consumed samples: 2728960 | consumed tokens: 5588910080 | elapsed time per iteration (s): 0.24 | learning rate: 1.687E-04 | global batch size: 256 | lm loss: 3.501943E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1076.379 | TFLOPs: 27.42 | +7: iteration 10670/ 37905 | consumed samples: 2731520 | consumed tokens: 5594152960 | elapsed time per iteration (s): 0.23 | learning rate: 1.686E-04 | global batch size: 256 | lm loss: 3.470274E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.434 | TFLOPs: 28.29 | +7: iteration 10680/ 37905 | consumed samples: 2734080 | consumed tokens: 5599395840 | elapsed time per iteration (s): 0.23 | learning rate: 1.686E-04 | global batch size: 256 | lm loss: 3.491573E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.408 | TFLOPs: 28.36 | +7: iteration 10690/ 37905 | consumed samples: 2736640 | consumed tokens: 5604638720 | elapsed time per iteration (s): 0.23 | learning rate: 1.685E-04 | global batch size: 256 | lm loss: 3.468539E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.402 | TFLOPs: 28.03 | +7: iteration 10700/ 37905 | consumed samples: 2739200 | consumed tokens: 5609881600 | elapsed time per iteration (s): 0.24 | learning rate: 1.684E-04 | global batch size: 256 | lm loss: 3.508955E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1081.812 | TFLOPs: 27.56 | +7: iteration 10710/ 37905 | consumed samples: 2741760 | consumed tokens: 5615124480 | elapsed time per iteration (s): 0.23 | learning rate: 1.684E-04 | global batch size: 256 | lm loss: 3.494558E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.939 | TFLOPs: 28.05 | +7: iteration 10720/ 37905 | consumed samples: 2744320 | consumed tokens: 5620367360 | elapsed time per iteration (s): 0.23 | learning rate: 1.683E-04 | global batch size: 256 | lm loss: 3.532787E+00 | grad norm: 0.377 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.470 | TFLOPs: 27.96 | +7: iteration 10730/ 37905 | consumed samples: 2746880 | consumed tokens: 5625610240 | elapsed time per iteration (s): 0.25 | learning rate: 1.683E-04 | global batch size: 256 | lm loss: 3.498305E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1029.042 | TFLOPs: 26.22 | +7: iteration 10740/ 37905 | consumed samples: 2749440 | consumed tokens: 5630853120 | elapsed time per iteration (s): 0.23 | learning rate: 1.682E-04 | global batch size: 256 | lm loss: 3.463179E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.286 | TFLOPs: 28.49 | +7: iteration 10750/ 37905 | consumed samples: 2752000 | consumed tokens: 5636096000 | elapsed time per iteration (s): 0.23 | learning rate: 1.682E-04 | global batch size: 256 | lm loss: 3.497192E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.113 | TFLOPs: 28.18 | +7: iteration 10760/ 37905 | consumed samples: 2754560 | consumed tokens: 5641338880 | elapsed time per iteration (s): 0.23 | learning rate: 1.681E-04 | global batch size: 256 | lm loss: 3.476042E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.117 | TFLOPs: 28.23 | +7: iteration 10770/ 37905 | consumed samples: 2757120 | consumed tokens: 5646581760 | elapsed time per iteration (s): 0.23 | learning rate: 1.680E-04 | global batch size: 256 | lm loss: 3.478444E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.865 | TFLOPs: 27.79 | +7: iteration 10780/ 37905 | consumed samples: 2759680 | consumed tokens: 5651824640 | elapsed time per iteration (s): 0.23 | learning rate: 1.680E-04 | global batch size: 256 | lm loss: 3.509529E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.148 | TFLOPs: 28.15 | +7: iteration 10790/ 37905 | consumed samples: 2762240 | consumed tokens: 5657067520 | elapsed time per iteration (s): 0.23 | learning rate: 1.679E-04 | global batch size: 256 | lm loss: 3.467646E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.949 | TFLOPs: 28.17 | +7: iteration 10800/ 37905 | consumed samples: 2764800 | consumed tokens: 5662310400 | elapsed time per iteration (s): 0.23 | learning rate: 1.679E-04 | global batch size: 256 | lm loss: 3.516511E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.727 | TFLOPs: 28.19 | +7: iteration 10810/ 37905 | consumed samples: 2767360 | consumed tokens: 5667553280 | elapsed time per iteration (s): 0.23 | learning rate: 1.678E-04 | global batch size: 256 | lm loss: 3.470139E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.862 | TFLOPs: 28.32 | +7: iteration 10820/ 37905 | consumed samples: 2769920 | consumed tokens: 5672796160 | elapsed time per iteration (s): 0.23 | learning rate: 1.678E-04 | global batch size: 256 | lm loss: 3.489302E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.491 | TFLOPs: 28.34 | +7: iteration 10830/ 37905 | consumed samples: 2772480 | consumed tokens: 5678039040 | elapsed time per iteration (s): 0.23 | learning rate: 1.677E-04 | global batch size: 256 | lm loss: 3.490616E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.283 | TFLOPs: 28.41 | +7: iteration 10840/ 37905 | consumed samples: 2775040 | consumed tokens: 5683281920 | elapsed time per iteration (s): 0.23 | learning rate: 1.676E-04 | global batch size: 256 | lm loss: 3.472548E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.760 | TFLOPs: 27.99 | +7: iteration 10850/ 37905 | consumed samples: 2777600 | consumed tokens: 5688524800 | elapsed time per iteration (s): 0.23 | learning rate: 1.676E-04 | global batch size: 256 | lm loss: 3.515510E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.439 | TFLOPs: 28.11 | +7: iteration 10860/ 37905 | consumed samples: 2780160 | consumed tokens: 5693767680 | elapsed time per iteration (s): 0.23 | learning rate: 1.675E-04 | global batch size: 256 | lm loss: 3.516805E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.818 | TFLOPs: 27.94 | +7: iteration 10870/ 37905 | consumed samples: 2782720 | consumed tokens: 5699010560 | elapsed time per iteration (s): 0.23 | learning rate: 1.675E-04 | global batch size: 256 | lm loss: 3.522964E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.047 | TFLOPs: 28.10 | +7: iteration 10880/ 37905 | consumed samples: 2785280 | consumed tokens: 5704253440 | elapsed time per iteration (s): 0.23 | learning rate: 1.674E-04 | global batch size: 256 | lm loss: 3.462881E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.970 | TFLOPs: 28.38 | +7: iteration 10890/ 37905 | consumed samples: 2787840 | consumed tokens: 5709496320 | elapsed time per iteration (s): 0.23 | learning rate: 1.673E-04 | global batch size: 256 | lm loss: 3.461652E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.395 | TFLOPs: 27.91 | +7: iteration 10900/ 37905 | consumed samples: 2790400 | consumed tokens: 5714739200 | elapsed time per iteration (s): 0.23 | learning rate: 1.673E-04 | global batch size: 256 | lm loss: 3.483109E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.286 | TFLOPs: 28.36 | +7: iteration 10910/ 37905 | consumed samples: 2792960 | consumed tokens: 5719982080 | elapsed time per iteration (s): 0.23 | learning rate: 1.672E-04 | global batch size: 256 | lm loss: 3.476289E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.047 | TFLOPs: 28.51 | +7: iteration 10920/ 37905 | consumed samples: 2795520 | consumed tokens: 5725224960 | elapsed time per iteration (s): 0.24 | learning rate: 1.672E-04 | global batch size: 256 | lm loss: 3.485548E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.017 | TFLOPs: 27.46 | +7: iteration 10930/ 37905 | consumed samples: 2798080 | consumed tokens: 5730467840 | elapsed time per iteration (s): 0.23 | learning rate: 1.671E-04 | global batch size: 256 | lm loss: 3.500387E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.363 | TFLOPs: 28.31 | +7: iteration 10940/ 37905 | consumed samples: 2800640 | consumed tokens: 5735710720 | elapsed time per iteration (s): 0.23 | learning rate: 1.671E-04 | global batch size: 256 | lm loss: 3.459914E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.783 | TFLOPs: 27.86 | +7: iteration 10950/ 37905 | consumed samples: 2803200 | consumed tokens: 5740953600 | elapsed time per iteration (s): 0.23 | learning rate: 1.670E-04 | global batch size: 256 | lm loss: 3.494139E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.525 | TFLOPs: 28.37 | +7: iteration 10960/ 37905 | consumed samples: 2805760 | consumed tokens: 5746196480 | elapsed time per iteration (s): 0.23 | learning rate: 1.669E-04 | global batch size: 256 | lm loss: 3.480290E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.968 | TFLOPs: 28.35 | +7: iteration 10970/ 37905 | consumed samples: 2808320 | consumed tokens: 5751439360 | elapsed time per iteration (s): 0.23 | learning rate: 1.669E-04 | global batch size: 256 | lm loss: 3.495491E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.939 | TFLOPs: 28.20 | +7: iteration 10980/ 37905 | consumed samples: 2810880 | consumed tokens: 5756682240 | elapsed time per iteration (s): 0.23 | learning rate: 1.668E-04 | global batch size: 256 | lm loss: 3.494172E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.713 | TFLOPs: 28.27 | +7: iteration 10990/ 37905 | consumed samples: 2813440 | consumed tokens: 5761925120 | elapsed time per iteration (s): 0.23 | learning rate: 1.668E-04 | global batch size: 256 | lm loss: 3.479125E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.951 | TFLOPs: 28.33 | +7: iteration 11000/ 37905 | consumed samples: 2816000 | consumed tokens: 5767168000 | elapsed time per iteration (s): 0.23 | learning rate: 1.667E-04 | global batch size: 256 | lm loss: 3.473878E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.467 | TFLOPs: 28.29 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 11000 | lm loss value: 3.406918E+00 | lm loss PPL: 3.017211E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 11000 to checkpoints_83moscar +0: [2022-11-29 17:39:00,240] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step11000 is begin to save! +0: [2022-11-29 17:39:00,243] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:39:00,314] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:39:00,315] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:39:00,327] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:39:00,327] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:39:00,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:39:00,341] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:39:00,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:39:00,353] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:39:00,364] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:39:00,364] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:39:00,375] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:39:00,375] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:39:00,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:39:00,387] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:39:00,398] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:39:00,398] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:39:00,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:39:00,410] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:39:00,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:39:00,421] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:39:00,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:39:00,433] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:39:00,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:39:00,434] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step11000/mp_rank_00_model_states.pt +0: [2022-11-29 17:39:00,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:39:00,436] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:39:00,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:39:00,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:39:00,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:39:00,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 17:39:00,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:39:00,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:39:00,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:39:00,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 17:39:00,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:39:00,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:39:00,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 17:39:00,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +2: [2022-11-29 17:39:00,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:39:00,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 17:39:00,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:39:00,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 17:39:00,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:39:00,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:39:00,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 17:39:00,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:39:00,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:39:00,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 17:39:00,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:39:00,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:39:00,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 17:39:00,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:39:00,477] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +7: [2022-11-29 17:39:00,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:39:00,477] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 17:39:00,477] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:39:00,477] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 17:39:00,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:39:00,477] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:39:00,477] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 17:39:00,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:39:00,477] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:39:00,477] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 17:39:00,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:39:00,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:39:00,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:39:00,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 17:39:00,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:39:00,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 17:39:00,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:39:00,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:39:00,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 17:39:00,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:39:00,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:39:00,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 17:39:00,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:39:00,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:39:00,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:39:00,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 17:39:00,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:39:00,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 17:39:00,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:39:00,479] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:39:00,479] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 17:39:00,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:39:00,479] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:39:00,479] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 17:39:00,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:39:00,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:39:00,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 17:39:00,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:39:00,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:39:00,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 17:39:00,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:39:00,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:39:00,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 17:39:00,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:39:00,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:39:00,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 17:39:00,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:39:00,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +6: [2022-11-29 17:39:00,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:39:00,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 17:39:00,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:39:00,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 17:39:00,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:39:00,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:39:00,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 17:39:00,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:39:00,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:39:00,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 17:39:00,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:39:00,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +4: [2022-11-29 17:39:00,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:39:00,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 17:39:00,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +5: [2022-11-29 17:39:00,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:39:00,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 17:39:00,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:39:00,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 17:39:00,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:39:00,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:39:00,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 17:39:00,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:39:00,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:39:00,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 17:39:00,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:39:00,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:39:00,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 17:39:00,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:39:00,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:39:00,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:39:00,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 17:39:00,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:39:00,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 17:39:00,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:39:00,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:39:00,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 17:39:00,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:39:00,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:39:00,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 17:39:00,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:39:00,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:39:00,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 17:39:00,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:39:00,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:39:00,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 17:39:00,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:39:00,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:39:00,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:39:00,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 17:39:00,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +2: [2022-11-29 17:39:00,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:39:00,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 17:39:00,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:39:00,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 17:39:00,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:39:00,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:39:00,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +1: [2022-11-29 17:39:00,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +3: [2022-11-29 17:39:00,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 17:39:00,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 17:39:00,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:39:00,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:39:00,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +2: [2022-11-29 17:39:00,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:39:00,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:39:00,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 17:39:00,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:39:00,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +0: [2022-11-29 17:39:00,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:39:00,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 17:39:00,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:39:00,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 17:39:00,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:39:00,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:39:00,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +7: [2022-11-29 17:39:00,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +3: [2022-11-29 17:39:00,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 17:39:00,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:39:00,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 17:39:00,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:39:00,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +5: [2022-11-29 17:39:00,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:39:00,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 17:39:00,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +6: [2022-11-29 17:39:00,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:39:00,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +5: [2022-11-29 17:39:00,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:39:00,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +5: [2022-11-29 17:39:00,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +7: [2022-11-29 17:39:00,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:39:00,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +7: [2022-11-29 17:39:00,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:39:00,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: [2022-11-29 17:39:00,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:39:00,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:39:00,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 17:39:00,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:39:00,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:39:00,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +1: [2022-11-29 17:39:00,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:39:00,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:39:00,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 17:39:00,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:39:00,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:39:00,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 17:39:00,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:39:00,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:39:00,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +4: [2022-11-29 17:39:00,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:39:00,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:39:00,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 17:39:00,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:39:00,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:39:00,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +3: [2022-11-29 17:39:00,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:39:00,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step11000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:39:00,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +0: successfully saved checkpoint at iteration 11000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 252.09 +7: iteration 11010/ 37905 | consumed samples: 2818560 | consumed tokens: 5772410880 | elapsed time per iteration (s): 0.26 | learning rate: 1.666E-04 | global batch size: 256 | lm loss: 3.469641E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 975.631 | TFLOPs: 24.85 | +7: iteration 11020/ 37905 | consumed samples: 2821120 | consumed tokens: 5777653760 | elapsed time per iteration (s): 0.30 | learning rate: 1.666E-04 | global batch size: 256 | lm loss: 3.464770E+00 | grad norm: 0.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 850.593 | TFLOPs: 21.67 | +7: iteration 11030/ 37905 | consumed samples: 2823680 | consumed tokens: 5782896640 | elapsed time per iteration (s): 0.23 | learning rate: 1.665E-04 | global batch size: 256 | lm loss: 3.489274E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.335 | TFLOPs: 28.03 | +7: iteration 11040/ 37905 | consumed samples: 2826240 | consumed tokens: 5788139520 | elapsed time per iteration (s): 0.24 | learning rate: 1.665E-04 | global batch size: 256 | lm loss: 3.498148E+00 | grad norm: 0.373 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1054.772 | TFLOPs: 26.87 | +7: iteration 11050/ 37905 | consumed samples: 2828800 | consumed tokens: 5793382400 | elapsed time per iteration (s): 0.23 | learning rate: 1.664E-04 | global batch size: 256 | lm loss: 3.480325E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.908 | TFLOPs: 28.40 | +7: iteration 11060/ 37905 | consumed samples: 2831360 | consumed tokens: 5798625280 | elapsed time per iteration (s): 0.23 | learning rate: 1.664E-04 | global batch size: 256 | lm loss: 3.501421E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.053 | TFLOPs: 28.41 | +7: iteration 11070/ 37905 | consumed samples: 2833920 | consumed tokens: 5803868160 | elapsed time per iteration (s): 0.23 | learning rate: 1.663E-04 | global batch size: 256 | lm loss: 3.502522E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.641 | TFLOPs: 28.24 | +7: iteration 11080/ 37905 | consumed samples: 2836480 | consumed tokens: 5809111040 | elapsed time per iteration (s): 0.24 | learning rate: 1.662E-04 | global batch size: 256 | lm loss: 3.448005E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.981 | TFLOPs: 27.49 | +7: iteration 11090/ 37905 | consumed samples: 2839040 | consumed tokens: 5814353920 | elapsed time per iteration (s): 0.23 | learning rate: 1.662E-04 | global batch size: 256 | lm loss: 3.474466E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.310 | TFLOPs: 28.13 | +7: iteration 11100/ 37905 | consumed samples: 2841600 | consumed tokens: 5819596800 | elapsed time per iteration (s): 0.23 | learning rate: 1.661E-04 | global batch size: 256 | lm loss: 3.468385E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.004 | TFLOPs: 28.07 | +7: iteration 11110/ 37905 | consumed samples: 2844160 | consumed tokens: 5824839680 | elapsed time per iteration (s): 0.23 | learning rate: 1.661E-04 | global batch size: 256 | lm loss: 3.482961E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.334 | TFLOPs: 27.85 | +7: iteration 11120/ 37905 | consumed samples: 2846720 | consumed tokens: 5830082560 | elapsed time per iteration (s): 0.26 | learning rate: 1.660E-04 | global batch size: 256 | lm loss: 3.490040E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 987.847 | TFLOPs: 25.17 | +7: iteration 11130/ 37905 | consumed samples: 2849280 | consumed tokens: 5835325440 | elapsed time per iteration (s): 0.23 | learning rate: 1.659E-04 | global batch size: 256 | lm loss: 3.498719E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.285 | TFLOPs: 28.16 | +7: iteration 11140/ 37905 | consumed samples: 2851840 | consumed tokens: 5840568320 | elapsed time per iteration (s): 0.23 | learning rate: 1.659E-04 | global batch size: 256 | lm loss: 3.470770E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.674 | TFLOPs: 27.96 | +7: iteration 11150/ 37905 | consumed samples: 2854400 | consumed tokens: 5845811200 | elapsed time per iteration (s): 0.24 | learning rate: 1.658E-04 | global batch size: 256 | lm loss: 3.500203E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1075.728 | TFLOPs: 27.40 | +7: iteration 11160/ 37905 | consumed samples: 2856960 | consumed tokens: 5851054080 | elapsed time per iteration (s): 0.23 | learning rate: 1.658E-04 | global batch size: 256 | lm loss: 3.470022E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.180 | TFLOPs: 28.05 | +7: iteration 11170/ 37905 | consumed samples: 2859520 | consumed tokens: 5856296960 | elapsed time per iteration (s): 0.23 | learning rate: 1.657E-04 | global batch size: 256 | lm loss: 3.474988E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.100 | TFLOPs: 28.25 | +7: iteration 11180/ 37905 | consumed samples: 2862080 | consumed tokens: 5861539840 | elapsed time per iteration (s): 0.23 | learning rate: 1.656E-04 | global batch size: 256 | lm loss: 3.480975E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.803 | TFLOPs: 27.89 | +7: iteration 11190/ 37905 | consumed samples: 2864640 | consumed tokens: 5866782720 | elapsed time per iteration (s): 0.23 | learning rate: 1.656E-04 | global batch size: 256 | lm loss: 3.468810E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.636 | TFLOPs: 28.27 | +7: iteration 11200/ 37905 | consumed samples: 2867200 | consumed tokens: 5872025600 | elapsed time per iteration (s): 0.26 | learning rate: 1.655E-04 | global batch size: 256 | lm loss: 3.500249E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 986.037 | TFLOPs: 25.12 | +7: iteration 11210/ 37905 | consumed samples: 2869760 | consumed tokens: 5877268480 | elapsed time per iteration (s): 0.25 | learning rate: 1.655E-04 | global batch size: 256 | lm loss: 3.482790E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1009.354 | TFLOPs: 25.71 | +7: iteration 11220/ 37905 | consumed samples: 2872320 | consumed tokens: 5882511360 | elapsed time per iteration (s): 0.23 | learning rate: 1.654E-04 | global batch size: 256 | lm loss: 3.464438E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.399 | TFLOPs: 28.21 | +7: iteration 11230/ 37905 | consumed samples: 2874880 | consumed tokens: 5887754240 | elapsed time per iteration (s): 0.23 | learning rate: 1.653E-04 | global batch size: 256 | lm loss: 3.494260E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.674 | TFLOPs: 28.01 | +7: iteration 11240/ 37905 | consumed samples: 2877440 | consumed tokens: 5892997120 | elapsed time per iteration (s): 0.23 | learning rate: 1.653E-04 | global batch size: 256 | lm loss: 3.490485E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.902 | TFLOPs: 28.07 | +7: iteration 11250/ 37905 | consumed samples: 2880000 | consumed tokens: 5898240000 | elapsed time per iteration (s): 0.23 | learning rate: 1.652E-04 | global batch size: 256 | lm loss: 3.464397E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.249 | TFLOPs: 27.77 | +7: iteration 11260/ 37905 | consumed samples: 2882560 | consumed tokens: 5903482880 | elapsed time per iteration (s): 0.23 | learning rate: 1.652E-04 | global batch size: 256 | lm loss: 3.466656E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.758 | TFLOPs: 28.22 | +7: iteration 11270/ 37905 | consumed samples: 2885120 | consumed tokens: 5908725760 | elapsed time per iteration (s): 0.23 | learning rate: 1.651E-04 | global batch size: 256 | lm loss: 3.485442E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.459 | TFLOPs: 28.42 | +7: iteration 11280/ 37905 | consumed samples: 2887680 | consumed tokens: 5913968640 | elapsed time per iteration (s): 0.24 | learning rate: 1.651E-04 | global batch size: 256 | lm loss: 3.480916E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1072.292 | TFLOPs: 27.32 | +7: iteration 11290/ 37905 | consumed samples: 2890240 | consumed tokens: 5919211520 | elapsed time per iteration (s): 0.23 | learning rate: 1.650E-04 | global batch size: 256 | lm loss: 3.475894E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.816 | TFLOPs: 28.37 | +7: iteration 11300/ 37905 | consumed samples: 2892800 | consumed tokens: 5924454400 | elapsed time per iteration (s): 0.23 | learning rate: 1.649E-04 | global batch size: 256 | lm loss: 3.487606E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.585 | TFLOPs: 28.47 | +7: iteration 11310/ 37905 | consumed samples: 2895360 | consumed tokens: 5929697280 | elapsed time per iteration (s): 0.23 | learning rate: 1.649E-04 | global batch size: 256 | lm loss: 3.488937E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.250 | TFLOPs: 28.36 | +7: iteration 11320/ 37905 | consumed samples: 2897920 | consumed tokens: 5934940160 | elapsed time per iteration (s): 0.23 | learning rate: 1.648E-04 | global batch size: 256 | lm loss: 3.464544E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.719 | TFLOPs: 27.79 | +7: iteration 11330/ 37905 | consumed samples: 2900480 | consumed tokens: 5940183040 | elapsed time per iteration (s): 0.23 | learning rate: 1.648E-04 | global batch size: 256 | lm loss: 3.468395E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.012 | TFLOPs: 28.05 | +7: iteration 11340/ 37905 | consumed samples: 2903040 | consumed tokens: 5945425920 | elapsed time per iteration (s): 0.23 | learning rate: 1.647E-04 | global batch size: 256 | lm loss: 3.497596E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.036 | TFLOPs: 28.25 | +7: iteration 11350/ 37905 | consumed samples: 2905600 | consumed tokens: 5950668800 | elapsed time per iteration (s): 0.23 | learning rate: 1.646E-04 | global batch size: 256 | lm loss: 3.480850E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.572 | TFLOPs: 28.32 | +7: iteration 11360/ 37905 | consumed samples: 2908160 | consumed tokens: 5955911680 | elapsed time per iteration (s): 0.23 | learning rate: 1.646E-04 | global batch size: 256 | lm loss: 3.495924E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.859 | TFLOPs: 27.99 | +7: iteration 11370/ 37905 | consumed samples: 2910720 | consumed tokens: 5961154560 | elapsed time per iteration (s): 0.24 | learning rate: 1.645E-04 | global batch size: 256 | lm loss: 3.485963E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.472 | TFLOPs: 27.47 | +7: iteration 11380/ 37905 | consumed samples: 2913280 | consumed tokens: 5966397440 | elapsed time per iteration (s): 0.23 | learning rate: 1.645E-04 | global batch size: 256 | lm loss: 3.448591E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.478 | TFLOPs: 28.29 | +7: iteration 11390/ 37905 | consumed samples: 2915840 | consumed tokens: 5971640320 | elapsed time per iteration (s): 0.23 | learning rate: 1.644E-04 | global batch size: 256 | lm loss: 3.474684E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.542 | TFLOPs: 28.29 | +7: iteration 11400/ 37905 | consumed samples: 2918400 | consumed tokens: 5976883200 | elapsed time per iteration (s): 0.23 | learning rate: 1.643E-04 | global batch size: 256 | lm loss: 3.477814E+00 | grad norm: 0.412 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.016 | TFLOPs: 28.02 | +7: iteration 11410/ 37905 | consumed samples: 2920960 | consumed tokens: 5982126080 | elapsed time per iteration (s): 0.23 | learning rate: 1.643E-04 | global batch size: 256 | lm loss: 3.479950E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.120 | TFLOPs: 28.08 | +7: iteration 11420/ 37905 | consumed samples: 2923520 | consumed tokens: 5987368960 | elapsed time per iteration (s): 0.23 | learning rate: 1.642E-04 | global batch size: 256 | lm loss: 3.483917E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.619 | TFLOPs: 28.09 | +7: iteration 11430/ 37905 | consumed samples: 2926080 | consumed tokens: 5992611840 | elapsed time per iteration (s): 0.23 | learning rate: 1.642E-04 | global batch size: 256 | lm loss: 3.466015E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.171 | TFLOPs: 27.98 | +7: iteration 11440/ 37905 | consumed samples: 2928640 | consumed tokens: 5997854720 | elapsed time per iteration (s): 0.23 | learning rate: 1.641E-04 | global batch size: 256 | lm loss: 3.521836E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.081 | TFLOPs: 28.36 | +7: iteration 11450/ 37905 | consumed samples: 2931200 | consumed tokens: 6003097600 | elapsed time per iteration (s): 0.24 | learning rate: 1.640E-04 | global batch size: 256 | lm loss: 3.454934E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1065.934 | TFLOPs: 27.15 | +7: iteration 11460/ 37905 | consumed samples: 2933760 | consumed tokens: 6008340480 | elapsed time per iteration (s): 0.23 | learning rate: 1.640E-04 | global batch size: 256 | lm loss: 3.460426E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.091 | TFLOPs: 28.25 | +7: iteration 11470/ 37905 | consumed samples: 2936320 | consumed tokens: 6013583360 | elapsed time per iteration (s): 0.23 | learning rate: 1.639E-04 | global batch size: 256 | lm loss: 3.456804E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.727 | TFLOPs: 28.09 | +7: iteration 11480/ 37905 | consumed samples: 2938880 | consumed tokens: 6018826240 | elapsed time per iteration (s): 0.24 | learning rate: 1.639E-04 | global batch size: 256 | lm loss: 3.497810E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.999 | TFLOPs: 27.69 | +7: iteration 11490/ 37905 | consumed samples: 2941440 | consumed tokens: 6024069120 | elapsed time per iteration (s): 0.23 | learning rate: 1.638E-04 | global batch size: 256 | lm loss: 3.500320E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.030 | TFLOPs: 28.28 | +7: iteration 11500/ 37905 | consumed samples: 2944000 | consumed tokens: 6029312000 | elapsed time per iteration (s): 0.23 | learning rate: 1.637E-04 | global batch size: 256 | lm loss: 3.453913E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.611 | TFLOPs: 28.39 | +7: iteration 11510/ 37905 | consumed samples: 2946560 | consumed tokens: 6034554880 | elapsed time per iteration (s): 0.23 | learning rate: 1.637E-04 | global batch size: 256 | lm loss: 3.500329E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.126 | TFLOPs: 28.28 | +7: iteration 11520/ 37905 | consumed samples: 2949120 | consumed tokens: 6039797760 | elapsed time per iteration (s): 0.23 | learning rate: 1.636E-04 | global batch size: 256 | lm loss: 3.487218E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.580 | TFLOPs: 27.94 | +7: iteration 11530/ 37905 | consumed samples: 2951680 | consumed tokens: 6045040640 | elapsed time per iteration (s): 0.23 | learning rate: 1.635E-04 | global batch size: 256 | lm loss: 3.460088E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.816 | TFLOPs: 28.12 | +7: iteration 11540/ 37905 | consumed samples: 2954240 | consumed tokens: 6050283520 | elapsed time per iteration (s): 0.24 | learning rate: 1.635E-04 | global batch size: 256 | lm loss: 3.473152E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1084.601 | TFLOPs: 27.63 | +7: iteration 11550/ 37905 | consumed samples: 2956800 | consumed tokens: 6055526400 | elapsed time per iteration (s): 0.23 | learning rate: 1.634E-04 | global batch size: 256 | lm loss: 3.473601E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.115 | TFLOPs: 28.23 | +7: iteration 11560/ 37905 | consumed samples: 2959360 | consumed tokens: 6060769280 | elapsed time per iteration (s): 0.23 | learning rate: 1.634E-04 | global batch size: 256 | lm loss: 3.507468E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.560 | TFLOPs: 28.22 | +7: iteration 11570/ 37905 | consumed samples: 2961920 | consumed tokens: 6066012160 | elapsed time per iteration (s): 0.23 | learning rate: 1.633E-04 | global batch size: 256 | lm loss: 3.484216E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.201 | TFLOPs: 28.21 | +7: iteration 11580/ 37905 | consumed samples: 2964480 | consumed tokens: 6071255040 | elapsed time per iteration (s): 0.23 | learning rate: 1.632E-04 | global batch size: 256 | lm loss: 3.498988E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.584 | TFLOPs: 27.81 | +7: iteration 11590/ 37905 | consumed samples: 2967040 | consumed tokens: 6076497920 | elapsed time per iteration (s): 0.23 | learning rate: 1.632E-04 | global batch size: 256 | lm loss: 3.462951E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.498 | TFLOPs: 27.81 | +7: iteration 11600/ 37905 | consumed samples: 2969600 | consumed tokens: 6081740800 | elapsed time per iteration (s): 0.23 | learning rate: 1.631E-04 | global batch size: 256 | lm loss: 3.453749E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.919 | TFLOPs: 28.25 | +7: iteration 11610/ 37905 | consumed samples: 2972160 | consumed tokens: 6086983680 | elapsed time per iteration (s): 0.23 | learning rate: 1.631E-04 | global batch size: 256 | lm loss: 3.490124E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.958 | TFLOPs: 28.33 | +7: iteration 11620/ 37905 | consumed samples: 2974720 | consumed tokens: 6092226560 | elapsed time per iteration (s): 0.23 | learning rate: 1.630E-04 | global batch size: 256 | lm loss: 3.495544E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.269 | TFLOPs: 28.28 | +7: iteration 11630/ 37905 | consumed samples: 2977280 | consumed tokens: 6097469440 | elapsed time per iteration (s): 0.28 | learning rate: 1.629E-04 | global batch size: 256 | lm loss: 3.468155E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 912.546 | TFLOPs: 23.25 | +7: iteration 11640/ 37905 | consumed samples: 2979840 | consumed tokens: 6102712320 | elapsed time per iteration (s): 0.24 | learning rate: 1.629E-04 | global batch size: 256 | lm loss: 3.454127E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1080.898 | TFLOPs: 27.54 | +7: iteration 11650/ 37905 | consumed samples: 2982400 | consumed tokens: 6107955200 | elapsed time per iteration (s): 0.23 | learning rate: 1.628E-04 | global batch size: 256 | lm loss: 3.456507E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.212 | TFLOPs: 28.13 | +7: iteration 11660/ 37905 | consumed samples: 2984960 | consumed tokens: 6113198080 | elapsed time per iteration (s): 0.23 | learning rate: 1.628E-04 | global batch size: 256 | lm loss: 3.484793E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.925 | TFLOPs: 27.94 | +7: iteration 11670/ 37905 | consumed samples: 2987520 | consumed tokens: 6118440960 | elapsed time per iteration (s): 0.23 | learning rate: 1.627E-04 | global batch size: 256 | lm loss: 3.452205E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.724 | TFLOPs: 28.40 | +7: iteration 11680/ 37905 | consumed samples: 2990080 | consumed tokens: 6123683840 | elapsed time per iteration (s): 0.25 | learning rate: 1.626E-04 | global batch size: 256 | lm loss: 3.465285E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1040.529 | TFLOPs: 26.51 | +7: iteration 11690/ 37905 | consumed samples: 2992640 | consumed tokens: 6128926720 | elapsed time per iteration (s): 0.23 | learning rate: 1.626E-04 | global batch size: 256 | lm loss: 3.484856E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.044 | TFLOPs: 28.02 | +7: iteration 11700/ 37905 | consumed samples: 2995200 | consumed tokens: 6134169600 | elapsed time per iteration (s): 0.23 | learning rate: 1.625E-04 | global batch size: 256 | lm loss: 3.481452E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.568 | TFLOPs: 28.37 | +7: iteration 11710/ 37905 | consumed samples: 2997760 | consumed tokens: 6139412480 | elapsed time per iteration (s): 0.23 | learning rate: 1.625E-04 | global batch size: 256 | lm loss: 3.476032E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.231 | TFLOPs: 28.41 | +7: iteration 11720/ 37905 | consumed samples: 3000320 | consumed tokens: 6144655360 | elapsed time per iteration (s): 0.23 | learning rate: 1.624E-04 | global batch size: 256 | lm loss: 3.449640E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.478 | TFLOPs: 28.19 | +7: iteration 11730/ 37905 | consumed samples: 3002880 | consumed tokens: 6149898240 | elapsed time per iteration (s): 0.23 | learning rate: 1.623E-04 | global batch size: 256 | lm loss: 3.457085E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.049 | TFLOPs: 28.38 | +7: iteration 11740/ 37905 | consumed samples: 3005440 | consumed tokens: 6155141120 | elapsed time per iteration (s): 0.23 | learning rate: 1.623E-04 | global batch size: 256 | lm loss: 3.439306E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.438 | TFLOPs: 27.98 | +7: iteration 11750/ 37905 | consumed samples: 3008000 | consumed tokens: 6160384000 | elapsed time per iteration (s): 0.24 | learning rate: 1.622E-04 | global batch size: 256 | lm loss: 3.474752E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1049.157 | TFLOPs: 26.73 | +7: iteration 11760/ 37905 | consumed samples: 3010560 | consumed tokens: 6165626880 | elapsed time per iteration (s): 0.24 | learning rate: 1.621E-04 | global batch size: 256 | lm loss: 3.488907E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1061.571 | TFLOPs: 27.04 | +7: iteration 11770/ 37905 | consumed samples: 3013120 | consumed tokens: 6170869760 | elapsed time per iteration (s): 0.24 | learning rate: 1.621E-04 | global batch size: 256 | lm loss: 3.457165E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.063 | TFLOPs: 27.26 | +7: iteration 11780/ 37905 | consumed samples: 3015680 | consumed tokens: 6176112640 | elapsed time per iteration (s): 0.25 | learning rate: 1.620E-04 | global batch size: 256 | lm loss: 3.471564E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1038.824 | TFLOPs: 26.46 | +7: iteration 11790/ 37905 | consumed samples: 3018240 | consumed tokens: 6181355520 | elapsed time per iteration (s): 0.23 | learning rate: 1.620E-04 | global batch size: 256 | lm loss: 3.455512E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.172 | TFLOPs: 28.28 | +7: iteration 11800/ 37905 | consumed samples: 3020800 | consumed tokens: 6186598400 | elapsed time per iteration (s): 0.24 | learning rate: 1.619E-04 | global batch size: 256 | lm loss: 3.465959E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.479 | TFLOPs: 27.73 | +7: iteration 11810/ 37905 | consumed samples: 3023360 | consumed tokens: 6191841280 | elapsed time per iteration (s): 0.23 | learning rate: 1.618E-04 | global batch size: 256 | lm loss: 3.480493E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.019 | TFLOPs: 28.20 | +7: iteration 11820/ 37905 | consumed samples: 3025920 | consumed tokens: 6197084160 | elapsed time per iteration (s): 0.23 | learning rate: 1.618E-04 | global batch size: 256 | lm loss: 3.472472E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.677 | TFLOPs: 27.96 | +7: iteration 11830/ 37905 | consumed samples: 3028480 | consumed tokens: 6202327040 | elapsed time per iteration (s): 0.23 | learning rate: 1.617E-04 | global batch size: 256 | lm loss: 3.480777E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.486 | TFLOPs: 27.91 | +7: iteration 11840/ 37905 | consumed samples: 3031040 | consumed tokens: 6207569920 | elapsed time per iteration (s): 0.23 | learning rate: 1.617E-04 | global batch size: 256 | lm loss: 3.466329E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.254 | TFLOPs: 28.18 | +7: iteration 11850/ 37905 | consumed samples: 3033600 | consumed tokens: 6212812800 | elapsed time per iteration (s): 0.23 | learning rate: 1.616E-04 | global batch size: 256 | lm loss: 3.477826E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.387 | TFLOPs: 27.80 | +7: iteration 11860/ 37905 | consumed samples: 3036160 | consumed tokens: 6218055680 | elapsed time per iteration (s): 0.24 | learning rate: 1.615E-04 | global batch size: 256 | lm loss: 3.486660E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1055.484 | TFLOPs: 26.89 | +7: iteration 11870/ 37905 | consumed samples: 3038720 | consumed tokens: 6223298560 | elapsed time per iteration (s): 0.23 | learning rate: 1.615E-04 | global batch size: 256 | lm loss: 3.495420E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.847 | TFLOPs: 28.22 | +7: iteration 11880/ 37905 | consumed samples: 3041280 | consumed tokens: 6228541440 | elapsed time per iteration (s): 0.23 | learning rate: 1.614E-04 | global batch size: 256 | lm loss: 3.429360E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.313 | TFLOPs: 27.88 | +7: iteration 11890/ 37905 | consumed samples: 3043840 | consumed tokens: 6233784320 | elapsed time per iteration (s): 0.23 | learning rate: 1.613E-04 | global batch size: 256 | lm loss: 3.444278E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.746 | TFLOPs: 27.81 | +7: iteration 11900/ 37905 | consumed samples: 3046400 | consumed tokens: 6239027200 | elapsed time per iteration (s): 0.23 | learning rate: 1.613E-04 | global batch size: 256 | lm loss: 3.458110E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.976 | TFLOPs: 27.84 | +7: iteration 11910/ 37905 | consumed samples: 3048960 | consumed tokens: 6244270080 | elapsed time per iteration (s): 0.23 | learning rate: 1.612E-04 | global batch size: 256 | lm loss: 3.459201E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.629 | TFLOPs: 27.96 | +7: iteration 11920/ 37905 | consumed samples: 3051520 | consumed tokens: 6249512960 | elapsed time per iteration (s): 0.23 | learning rate: 1.612E-04 | global batch size: 256 | lm loss: 3.455926E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.152 | TFLOPs: 27.98 | +7: iteration 11930/ 37905 | consumed samples: 3054080 | consumed tokens: 6254755840 | elapsed time per iteration (s): 0.24 | learning rate: 1.611E-04 | global batch size: 256 | lm loss: 3.470631E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1072.199 | TFLOPs: 27.31 | +7: iteration 11940/ 37905 | consumed samples: 3056640 | consumed tokens: 6259998720 | elapsed time per iteration (s): 0.23 | learning rate: 1.610E-04 | global batch size: 256 | lm loss: 3.446332E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.852 | TFLOPs: 28.07 | +7: iteration 11950/ 37905 | consumed samples: 3059200 | consumed tokens: 6265241600 | elapsed time per iteration (s): 0.23 | learning rate: 1.610E-04 | global batch size: 256 | lm loss: 3.463817E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.884 | TFLOPs: 27.84 | +7: iteration 11960/ 37905 | consumed samples: 3061760 | consumed tokens: 6270484480 | elapsed time per iteration (s): 0.23 | learning rate: 1.609E-04 | global batch size: 256 | lm loss: 3.474153E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.398 | TFLOPs: 28.11 | +7: iteration 11970/ 37905 | consumed samples: 3064320 | consumed tokens: 6275727360 | elapsed time per iteration (s): 0.23 | learning rate: 1.608E-04 | global batch size: 256 | lm loss: 3.467499E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.642 | TFLOPs: 28.22 | +7: iteration 11980/ 37905 | consumed samples: 3066880 | consumed tokens: 6280970240 | elapsed time per iteration (s): 0.23 | learning rate: 1.608E-04 | global batch size: 256 | lm loss: 3.460593E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.913 | TFLOPs: 28.12 | +7: iteration 11990/ 37905 | consumed samples: 3069440 | consumed tokens: 6286213120 | elapsed time per iteration (s): 0.23 | learning rate: 1.607E-04 | global batch size: 256 | lm loss: 3.433541E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.665 | TFLOPs: 27.78 | +0: [2022-11-29 17:42:55,627] [INFO] [logging.py:68:log_dist] [Rank 0] step=12000, skipped=0, lr=[0.00016066300925507844, 0.00016066300925507844, 0.00016066300925507844], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +0: steps: 12000 loss: 3.4174 iter time (s): 0.233 samples/sec: 1097.533 +7: iteration 12000/ 37905 | consumed samples: 3072000 | consumed tokens: 6291456000 | elapsed time per iteration (s): 0.23 | learning rate: 1.607E-04 | global batch size: 256 | lm loss: 3.438174E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.621 | TFLOPs: 28.01 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 12000 | lm loss value: 3.272535E+00 | lm loss PPL: 2.637812E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 12000 to checkpoints_83moscar +0: [2022-11-29 17:42:55,721] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step12000 is begin to save! +0: [2022-11-29 17:42:55,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:42:55,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:42:55,798] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:42:55,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:42:55,810] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:42:55,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:42:55,821] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:42:55,833] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:42:55,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:42:55,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:42:55,844] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:42:55,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:42:55,856] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:42:55,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:42:55,867] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:42:55,879] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:42:55,880] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:42:55,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:42:55,891] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:42:55,902] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:42:55,902] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:42:55,914] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:42:55,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:42:55,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:42:55,915] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step12000/mp_rank_00_model_states.pt +0: [2022-11-29 17:42:55,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:42:55,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:42:55,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:42:55,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:42:55,972] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:42:55,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +5: [2022-11-29 17:42:55,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:42:55,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:42:55,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:42:55,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 17:42:55,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:42:55,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 17:42:55,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:42:55,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:42:55,974] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:42:55,974] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 17:42:55,974] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:42:55,974] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:42:55,974] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +5: [2022-11-29 17:42:55,974] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:42:55,974] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:42:55,974] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 17:42:55,974] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:42:55,974] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:42:55,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +2: [2022-11-29 17:42:55,974] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:42:55,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +0: [2022-11-29 17:42:55,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:42:55,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 17:42:55,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:42:55,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 17:42:55,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:42:55,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +4: [2022-11-29 17:42:55,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:42:55,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 17:42:55,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:42:55,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 17:42:55,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:42:55,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +7: [2022-11-29 17:42:55,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:42:55,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:42:55,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +1: [2022-11-29 17:42:55,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:42:55,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:42:55,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +5: [2022-11-29 17:42:55,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:42:55,976] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:42:55,976] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +2: [2022-11-29 17:42:55,976] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:42:55,976] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:42:55,976] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +1: [2022-11-29 17:42:55,976] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:42:55,976] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:42:55,976] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 17:42:55,976] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:42:55,976] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +0: [2022-11-29 17:42:55,976] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:42:55,976] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 17:42:55,976] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:42:55,976] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 17:42:55,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:42:55,977] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:42:55,977] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +1: [2022-11-29 17:42:55,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:42:55,977] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:42:55,977] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +5: [2022-11-29 17:42:55,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:42:55,977] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:42:55,977] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 17:42:55,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:42:55,977] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +7: [2022-11-29 17:42:55,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:42:55,978] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +7: [2022-11-29 17:42:55,978] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:42:55,978] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +2: [2022-11-29 17:42:55,978] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:42:55,978] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:42:55,978] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 17:42:55,978] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:42:55,978] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:42:55,978] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +4: [2022-11-29 17:42:55,978] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +6: [2022-11-29 17:42:55,978] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 17:42:55,978] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 17:42:55,979] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:42:55,979] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:42:55,979] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 17:42:55,979] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:42:55,979] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:42:55,979] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 17:42:55,979] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:42:55,979] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:42:55,979] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:42:55,980] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +7: [2022-11-29 17:42:55,980] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +2: [2022-11-29 17:42:55,980] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +0: [2022-11-29 17:42:55,980] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +2: [2022-11-29 17:42:55,980] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +7: [2022-11-29 17:42:55,980] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +1: [2022-11-29 17:42:55,980] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:42:55,980] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:42:55,980] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 17:42:55,980] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:42:55,980] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:42:55,980] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +2: [2022-11-29 17:42:55,980] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:42:55,981] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:42:55,981] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +5: [2022-11-29 17:42:55,981] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:42:55,981] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:42:55,981] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +6: [2022-11-29 17:42:55,981] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +5: [2022-11-29 17:42:55,981] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 17:42:55,981] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +7: [2022-11-29 17:42:55,981] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:42:55,981] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +5: [2022-11-29 17:42:55,981] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:42:55,981] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +5: [2022-11-29 17:42:55,981] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +3: [2022-11-29 17:42:55,981] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:42:55,981] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +5: [2022-11-29 17:42:55,981] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 17:42:55,981] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +1: [2022-11-29 17:42:55,981] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:42:55,981] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:42:55,981] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 17:42:55,981] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:42:55,982] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:42:55,982] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 17:42:55,982] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:42:55,982] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:42:55,982] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +1: [2022-11-29 17:42:55,982] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:42:55,982] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:42:55,982] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +2: [2022-11-29 17:42:55,983] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:42:55,983] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:42:55,983] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +3: [2022-11-29 17:42:55,983] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +2: [2022-11-29 17:42:55,983] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 17:42:55,983] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 17:42:55,983] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:42:55,983] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:42:55,983] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +2: [2022-11-29 17:42:55,983] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:42:55,983] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:42:55,983] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +4: [2022-11-29 17:42:55,983] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +2: [2022-11-29 17:42:55,983] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 17:42:55,983] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +7: [2022-11-29 17:42:55,984] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:42:55,984] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:42:55,984] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:42:55,984] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:42:55,984] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +7: [2022-11-29 17:42:55,984] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 17:42:55,984] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:42:55,984] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:42:55,984] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +2: [2022-11-29 17:42:55,984] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:42:55,984] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:42:55,984] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +3: [2022-11-29 17:42:55,984] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +5: [2022-11-29 17:42:55,984] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +1: [2022-11-29 17:42:55,984] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +2: [2022-11-29 17:42:55,984] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +1: [2022-11-29 17:42:55,984] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +2: [2022-11-29 17:42:55,984] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +5: [2022-11-29 17:42:55,984] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:42:55,984] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:42:55,984] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:42:55,984] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +3: [2022-11-29 17:42:55,984] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +6: [2022-11-29 17:42:55,984] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:42:55,984] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:42:55,984] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 17:42:55,984] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:42:55,984] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:42:55,984] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 17:42:55,984] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 17:42:55,984] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:42:55,985] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:42:55,985] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +6: [2022-11-29 17:42:55,985] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:42:55,985] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +0: [2022-11-29 17:42:55,985] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:42:55,985] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:42:55,985] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: [2022-11-29 17:42:55,985] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +7: [2022-11-29 17:42:55,985] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +0: [2022-11-29 17:42:55,985] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +7: [2022-11-29 17:42:55,985] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +4: [2022-11-29 17:42:55,986] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:42:55,986] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step12000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:42:55,986] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +0: successfully saved checkpoint at iteration 12000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 268.12 +7: iteration 12010/ 37905 | consumed samples: 3074560 | consumed tokens: 6296698880 | elapsed time per iteration (s): 0.27 | learning rate: 1.606E-04 | global batch size: 256 | lm loss: 3.460901E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 956.627 | TFLOPs: 24.37 | +7: iteration 12020/ 37905 | consumed samples: 3077120 | consumed tokens: 6301941760 | elapsed time per iteration (s): 0.23 | learning rate: 1.605E-04 | global batch size: 256 | lm loss: 3.489214E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.926 | TFLOPs: 28.17 | +7: iteration 12030/ 37905 | consumed samples: 3079680 | consumed tokens: 6307184640 | elapsed time per iteration (s): 0.23 | learning rate: 1.605E-04 | global batch size: 256 | lm loss: 3.460074E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.743 | TFLOPs: 28.04 | +7: iteration 12040/ 37905 | consumed samples: 3082240 | consumed tokens: 6312427520 | elapsed time per iteration (s): 0.24 | learning rate: 1.604E-04 | global batch size: 256 | lm loss: 3.452015E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.383 | TFLOPs: 27.65 | +7: iteration 12050/ 37905 | consumed samples: 3084800 | consumed tokens: 6317670400 | elapsed time per iteration (s): 0.24 | learning rate: 1.604E-04 | global batch size: 256 | lm loss: 3.431185E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1069.904 | TFLOPs: 27.26 | +7: iteration 12060/ 37905 | consumed samples: 3087360 | consumed tokens: 6322913280 | elapsed time per iteration (s): 0.24 | learning rate: 1.603E-04 | global batch size: 256 | lm loss: 3.486309E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1080.402 | TFLOPs: 27.52 | +7: iteration 12070/ 37905 | consumed samples: 3089920 | consumed tokens: 6328156160 | elapsed time per iteration (s): 0.23 | learning rate: 1.602E-04 | global batch size: 256 | lm loss: 3.488496E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.777 | TFLOPs: 28.27 | +7: iteration 12080/ 37905 | consumed samples: 3092480 | consumed tokens: 6333399040 | elapsed time per iteration (s): 0.25 | learning rate: 1.602E-04 | global batch size: 256 | lm loss: 3.456968E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1015.150 | TFLOPs: 25.86 | +7: iteration 12090/ 37905 | consumed samples: 3095040 | consumed tokens: 6338641920 | elapsed time per iteration (s): 0.27 | learning rate: 1.601E-04 | global batch size: 256 | lm loss: 3.490490E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 936.015 | TFLOPs: 23.85 | +7: iteration 12100/ 37905 | consumed samples: 3097600 | consumed tokens: 6343884800 | elapsed time per iteration (s): 0.24 | learning rate: 1.600E-04 | global batch size: 256 | lm loss: 3.454005E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1077.641 | TFLOPs: 27.45 | +7: iteration 12110/ 37905 | consumed samples: 3100160 | consumed tokens: 6349127680 | elapsed time per iteration (s): 0.23 | learning rate: 1.600E-04 | global batch size: 256 | lm loss: 3.463695E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.698 | TFLOPs: 28.09 | +7: iteration 12120/ 37905 | consumed samples: 3102720 | consumed tokens: 6354370560 | elapsed time per iteration (s): 0.23 | learning rate: 1.599E-04 | global batch size: 256 | lm loss: 3.484742E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.232 | TFLOPs: 28.23 | +7: iteration 12130/ 37905 | consumed samples: 3105280 | consumed tokens: 6359613440 | elapsed time per iteration (s): 0.25 | learning rate: 1.599E-04 | global batch size: 256 | lm loss: 3.449158E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1028.581 | TFLOPs: 26.20 | +7: iteration 12140/ 37905 | consumed samples: 3107840 | consumed tokens: 6364856320 | elapsed time per iteration (s): 0.24 | learning rate: 1.598E-04 | global batch size: 256 | lm loss: 3.451075E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.151 | TFLOPs: 26.93 | +7: iteration 12150/ 37905 | consumed samples: 3110400 | consumed tokens: 6370099200 | elapsed time per iteration (s): 0.23 | learning rate: 1.597E-04 | global batch size: 256 | lm loss: 3.474423E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.170 | TFLOPs: 28.41 | +7: iteration 12160/ 37905 | consumed samples: 3112960 | consumed tokens: 6375342080 | elapsed time per iteration (s): 0.29 | learning rate: 1.597E-04 | global batch size: 256 | lm loss: 3.467289E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 886.354 | TFLOPs: 22.58 | +7: iteration 12170/ 37905 | consumed samples: 3115520 | consumed tokens: 6380584960 | elapsed time per iteration (s): 0.23 | learning rate: 1.596E-04 | global batch size: 256 | lm loss: 3.467150E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.497 | TFLOPs: 28.19 | +7: iteration 12180/ 37905 | consumed samples: 3118080 | consumed tokens: 6385827840 | elapsed time per iteration (s): 0.23 | learning rate: 1.595E-04 | global batch size: 256 | lm loss: 3.433068E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.364 | TFLOPs: 28.29 | +7: iteration 12190/ 37905 | consumed samples: 3120640 | consumed tokens: 6391070720 | elapsed time per iteration (s): 0.23 | learning rate: 1.595E-04 | global batch size: 256 | lm loss: 3.446287E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.684 | TFLOPs: 28.17 | +7: iteration 12200/ 37905 | consumed samples: 3123200 | consumed tokens: 6396313600 | elapsed time per iteration (s): 0.23 | learning rate: 1.594E-04 | global batch size: 256 | lm loss: 3.478692E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.924 | TFLOPs: 27.97 | +7: iteration 12210/ 37905 | consumed samples: 3125760 | consumed tokens: 6401556480 | elapsed time per iteration (s): 0.23 | learning rate: 1.593E-04 | global batch size: 256 | lm loss: 3.455878E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.912 | TFLOPs: 28.25 | +7: iteration 12220/ 37905 | consumed samples: 3128320 | consumed tokens: 6406799360 | elapsed time per iteration (s): 0.23 | learning rate: 1.593E-04 | global batch size: 256 | lm loss: 3.468731E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.756 | TFLOPs: 27.94 | +7: iteration 12230/ 37905 | consumed samples: 3130880 | consumed tokens: 6412042240 | elapsed time per iteration (s): 0.23 | learning rate: 1.592E-04 | global batch size: 256 | lm loss: 3.460491E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.015 | TFLOPs: 28.18 | +7: iteration 12240/ 37905 | consumed samples: 3133440 | consumed tokens: 6417285120 | elapsed time per iteration (s): 0.23 | learning rate: 1.592E-04 | global batch size: 256 | lm loss: 3.472733E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.784 | TFLOPs: 28.22 | +7: iteration 12250/ 37905 | consumed samples: 3136000 | consumed tokens: 6422528000 | elapsed time per iteration (s): 0.24 | learning rate: 1.591E-04 | global batch size: 256 | lm loss: 3.468855E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.990 | TFLOPs: 27.49 | +7: iteration 12260/ 37905 | consumed samples: 3138560 | consumed tokens: 6427770880 | elapsed time per iteration (s): 0.24 | learning rate: 1.590E-04 | global batch size: 256 | lm loss: 3.458582E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1077.539 | TFLOPs: 27.45 | +7: iteration 12270/ 37905 | consumed samples: 3141120 | consumed tokens: 6433013760 | elapsed time per iteration (s): 0.23 | learning rate: 1.590E-04 | global batch size: 256 | lm loss: 3.488087E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.841 | TFLOPs: 28.15 | +7: iteration 12280/ 37905 | consumed samples: 3143680 | consumed tokens: 6438256640 | elapsed time per iteration (s): 0.23 | learning rate: 1.589E-04 | global batch size: 256 | lm loss: 3.463380E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.058 | TFLOPs: 28.00 | +7: iteration 12290/ 37905 | consumed samples: 3146240 | consumed tokens: 6443499520 | elapsed time per iteration (s): 0.23 | learning rate: 1.588E-04 | global batch size: 256 | lm loss: 3.463121E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.256 | TFLOPs: 28.08 | +7: iteration 12300/ 37905 | consumed samples: 3148800 | consumed tokens: 6448742400 | elapsed time per iteration (s): 0.23 | learning rate: 1.588E-04 | global batch size: 256 | lm loss: 3.453017E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.038 | TFLOPs: 28.13 | +7: iteration 12310/ 37905 | consumed samples: 3151360 | consumed tokens: 6453985280 | elapsed time per iteration (s): 0.25 | learning rate: 1.587E-04 | global batch size: 256 | lm loss: 3.461512E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1023.530 | TFLOPs: 26.07 | +7: iteration 12320/ 37905 | consumed samples: 3153920 | consumed tokens: 6459228160 | elapsed time per iteration (s): 0.24 | learning rate: 1.587E-04 | global batch size: 256 | lm loss: 3.472158E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1059.640 | TFLOPs: 26.99 | +7: iteration 12330/ 37905 | consumed samples: 3156480 | consumed tokens: 6464471040 | elapsed time per iteration (s): 0.24 | learning rate: 1.586E-04 | global batch size: 256 | lm loss: 3.455373E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.446 | TFLOPs: 27.68 | +7: iteration 12340/ 37905 | consumed samples: 3159040 | consumed tokens: 6469713920 | elapsed time per iteration (s): 0.23 | learning rate: 1.585E-04 | global batch size: 256 | lm loss: 3.445973E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.507 | TFLOPs: 28.29 | +7: iteration 12350/ 37905 | consumed samples: 3161600 | consumed tokens: 6474956800 | elapsed time per iteration (s): 0.24 | learning rate: 1.585E-04 | global batch size: 256 | lm loss: 3.466327E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1079.950 | TFLOPs: 27.51 | +7: iteration 12360/ 37905 | consumed samples: 3164160 | consumed tokens: 6480199680 | elapsed time per iteration (s): 0.24 | learning rate: 1.584E-04 | global batch size: 256 | lm loss: 3.461047E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.836 | TFLOPs: 27.66 | +7: iteration 12370/ 37905 | consumed samples: 3166720 | consumed tokens: 6485442560 | elapsed time per iteration (s): 0.23 | learning rate: 1.583E-04 | global batch size: 256 | lm loss: 3.465365E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.268 | TFLOPs: 27.80 | +7: iteration 12380/ 37905 | consumed samples: 3169280 | consumed tokens: 6490685440 | elapsed time per iteration (s): 0.23 | learning rate: 1.583E-04 | global batch size: 256 | lm loss: 3.443349E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.480 | TFLOPs: 28.37 | +7: iteration 12390/ 37905 | consumed samples: 3171840 | consumed tokens: 6495928320 | elapsed time per iteration (s): 0.25 | learning rate: 1.582E-04 | global batch size: 256 | lm loss: 3.431251E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1011.234 | TFLOPs: 25.76 | +7: iteration 12400/ 37905 | consumed samples: 3174400 | consumed tokens: 6501171200 | elapsed time per iteration (s): 0.24 | learning rate: 1.581E-04 | global batch size: 256 | lm loss: 3.481196E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1067.040 | TFLOPs: 27.18 | +7: iteration 12410/ 37905 | consumed samples: 3176960 | consumed tokens: 6506414080 | elapsed time per iteration (s): 0.23 | learning rate: 1.581E-04 | global batch size: 256 | lm loss: 3.471143E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.585 | TFLOPs: 27.96 | +7: iteration 12420/ 37905 | consumed samples: 3179520 | consumed tokens: 6511656960 | elapsed time per iteration (s): 0.23 | learning rate: 1.580E-04 | global batch size: 256 | lm loss: 3.454685E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.339 | TFLOPs: 28.11 | +7: iteration 12430/ 37905 | consumed samples: 3182080 | consumed tokens: 6516899840 | elapsed time per iteration (s): 0.24 | learning rate: 1.580E-04 | global batch size: 256 | lm loss: 3.467415E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1072.011 | TFLOPs: 27.31 | +7: iteration 12440/ 37905 | consumed samples: 3184640 | consumed tokens: 6522142720 | elapsed time per iteration (s): 0.23 | learning rate: 1.579E-04 | global batch size: 256 | lm loss: 3.459389E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.884 | TFLOPs: 28.17 | +7: iteration 12450/ 37905 | consumed samples: 3187200 | consumed tokens: 6527385600 | elapsed time per iteration (s): 0.23 | learning rate: 1.578E-04 | global batch size: 256 | lm loss: 3.461346E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.057 | TFLOPs: 28.13 | +7: iteration 12460/ 37905 | consumed samples: 3189760 | consumed tokens: 6532628480 | elapsed time per iteration (s): 0.23 | learning rate: 1.578E-04 | global batch size: 256 | lm loss: 3.467914E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.238 | TFLOPs: 28.28 | +7: iteration 12470/ 37905 | consumed samples: 3192320 | consumed tokens: 6537871360 | elapsed time per iteration (s): 0.25 | learning rate: 1.577E-04 | global batch size: 256 | lm loss: 3.460441E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1010.416 | TFLOPs: 25.74 | +7: iteration 12480/ 37905 | consumed samples: 3194880 | consumed tokens: 6543114240 | elapsed time per iteration (s): 0.23 | learning rate: 1.576E-04 | global batch size: 256 | lm loss: 3.463934E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.174 | TFLOPs: 28.21 | +7: iteration 12490/ 37905 | consumed samples: 3197440 | consumed tokens: 6548357120 | elapsed time per iteration (s): 0.36 | learning rate: 1.576E-04 | global batch size: 256 | lm loss: 3.446742E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 706.588 | TFLOPs: 18.00 | +7: iteration 12500/ 37905 | consumed samples: 3200000 | consumed tokens: 6553600000 | elapsed time per iteration (s): 0.23 | learning rate: 1.575E-04 | global batch size: 256 | lm loss: 3.448333E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.315 | TFLOPs: 28.46 | +7: iteration 12510/ 37905 | consumed samples: 3202560 | consumed tokens: 6558842880 | elapsed time per iteration (s): 0.23 | learning rate: 1.574E-04 | global batch size: 256 | lm loss: 3.451768E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.765 | TFLOPs: 27.97 | +7: iteration 12520/ 37905 | consumed samples: 3205120 | consumed tokens: 6564085760 | elapsed time per iteration (s): 0.24 | learning rate: 1.574E-04 | global batch size: 256 | lm loss: 3.463986E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.890 | TFLOPs: 27.66 | +7: iteration 12530/ 37905 | consumed samples: 3207680 | consumed tokens: 6569328640 | elapsed time per iteration (s): 0.23 | learning rate: 1.573E-04 | global batch size: 256 | lm loss: 3.456274E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.134 | TFLOPs: 27.92 | +7: iteration 12540/ 37905 | consumed samples: 3210240 | consumed tokens: 6574571520 | elapsed time per iteration (s): 0.24 | learning rate: 1.572E-04 | global batch size: 256 | lm loss: 3.443867E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1074.978 | TFLOPs: 27.39 | +7: iteration 12550/ 37905 | consumed samples: 3212800 | consumed tokens: 6579814400 | elapsed time per iteration (s): 0.29 | learning rate: 1.572E-04 | global batch size: 256 | lm loss: 3.440369E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 870.880 | TFLOPs: 22.19 | +7: iteration 12560/ 37905 | consumed samples: 3215360 | consumed tokens: 6585057280 | elapsed time per iteration (s): 0.23 | learning rate: 1.571E-04 | global batch size: 256 | lm loss: 3.469196E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.701 | TFLOPs: 28.32 | +7: iteration 12570/ 37905 | consumed samples: 3217920 | consumed tokens: 6590300160 | elapsed time per iteration (s): 0.24 | learning rate: 1.571E-04 | global batch size: 256 | lm loss: 3.468131E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.531 | TFLOPs: 27.48 | +7: iteration 12580/ 37905 | consumed samples: 3220480 | consumed tokens: 6595543040 | elapsed time per iteration (s): 0.23 | learning rate: 1.570E-04 | global batch size: 256 | lm loss: 3.458823E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.589 | TFLOPs: 28.42 | +7: iteration 12590/ 37905 | consumed samples: 3223040 | consumed tokens: 6600785920 | elapsed time per iteration (s): 0.23 | learning rate: 1.569E-04 | global batch size: 256 | lm loss: 3.473619E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.914 | TFLOPs: 28.38 | +7: iteration 12600/ 37905 | consumed samples: 3225600 | consumed tokens: 6606028800 | elapsed time per iteration (s): 0.23 | learning rate: 1.569E-04 | global batch size: 256 | lm loss: 3.447204E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.903 | TFLOPs: 28.40 | +7: iteration 12610/ 37905 | consumed samples: 3228160 | consumed tokens: 6611271680 | elapsed time per iteration (s): 0.23 | learning rate: 1.568E-04 | global batch size: 256 | lm loss: 3.445061E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.545 | TFLOPs: 28.34 | +7: iteration 12620/ 37905 | consumed samples: 3230720 | consumed tokens: 6616514560 | elapsed time per iteration (s): 0.25 | learning rate: 1.567E-04 | global batch size: 256 | lm loss: 3.427106E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1032.437 | TFLOPs: 26.30 | +7: iteration 12630/ 37905 | consumed samples: 3233280 | consumed tokens: 6621757440 | elapsed time per iteration (s): 0.23 | learning rate: 1.567E-04 | global batch size: 256 | lm loss: 3.445223E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.745 | TFLOPs: 28.09 | +7: iteration 12640/ 37905 | consumed samples: 3235840 | consumed tokens: 6627000320 | elapsed time per iteration (s): 0.24 | learning rate: 1.566E-04 | global batch size: 256 | lm loss: 3.460326E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1063.480 | TFLOPs: 27.09 | +7: iteration 12650/ 37905 | consumed samples: 3238400 | consumed tokens: 6632243200 | elapsed time per iteration (s): 0.23 | learning rate: 1.565E-04 | global batch size: 256 | lm loss: 3.433293E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.697 | TFLOPs: 28.55 | +7: iteration 12660/ 37905 | consumed samples: 3240960 | consumed tokens: 6637486080 | elapsed time per iteration (s): 0.23 | learning rate: 1.565E-04 | global batch size: 256 | lm loss: 3.441652E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.535 | TFLOPs: 28.24 | +7: iteration 12670/ 37905 | consumed samples: 3243520 | consumed tokens: 6642728960 | elapsed time per iteration (s): 0.23 | learning rate: 1.564E-04 | global batch size: 256 | lm loss: 3.441093E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.525 | TFLOPs: 27.76 | +7: iteration 12680/ 37905 | consumed samples: 3246080 | consumed tokens: 6647971840 | elapsed time per iteration (s): 0.23 | learning rate: 1.563E-04 | global batch size: 256 | lm loss: 3.441626E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.763 | TFLOPs: 28.04 | +7: iteration 12690/ 37905 | consumed samples: 3248640 | consumed tokens: 6653214720 | elapsed time per iteration (s): 0.23 | learning rate: 1.563E-04 | global batch size: 256 | lm loss: 3.447858E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.382 | TFLOPs: 28.36 | +7: iteration 12700/ 37905 | consumed samples: 3251200 | consumed tokens: 6658457600 | elapsed time per iteration (s): 0.23 | learning rate: 1.562E-04 | global batch size: 256 | lm loss: 3.430708E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.912 | TFLOPs: 27.84 | +7: iteration 12710/ 37905 | consumed samples: 3253760 | consumed tokens: 6663700480 | elapsed time per iteration (s): 0.23 | learning rate: 1.562E-04 | global batch size: 256 | lm loss: 3.443836E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.324 | TFLOPs: 28.11 | +7: iteration 12720/ 37905 | consumed samples: 3256320 | consumed tokens: 6668943360 | elapsed time per iteration (s): 0.23 | learning rate: 1.561E-04 | global batch size: 256 | lm loss: 3.443641E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.940 | TFLOPs: 27.77 | +7: iteration 12730/ 37905 | consumed samples: 3258880 | consumed tokens: 6674186240 | elapsed time per iteration (s): 0.23 | learning rate: 1.560E-04 | global batch size: 256 | lm loss: 3.452750E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.616 | TFLOPs: 27.86 | +7: iteration 12740/ 37905 | consumed samples: 3261440 | consumed tokens: 6679429120 | elapsed time per iteration (s): 0.24 | learning rate: 1.560E-04 | global batch size: 256 | lm loss: 3.465956E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1072.596 | TFLOPs: 27.32 | +7: iteration 12750/ 37905 | consumed samples: 3264000 | consumed tokens: 6684672000 | elapsed time per iteration (s): 0.23 | learning rate: 1.559E-04 | global batch size: 256 | lm loss: 3.461659E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.340 | TFLOPs: 27.93 | +7: iteration 12760/ 37905 | consumed samples: 3266560 | consumed tokens: 6689914880 | elapsed time per iteration (s): 0.23 | learning rate: 1.558E-04 | global batch size: 256 | lm loss: 3.435119E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.054 | TFLOPs: 28.30 | +7: iteration 12770/ 37905 | consumed samples: 3269120 | consumed tokens: 6695157760 | elapsed time per iteration (s): 0.24 | learning rate: 1.558E-04 | global batch size: 256 | lm loss: 3.441024E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.303 | TFLOPs: 27.75 | +7: iteration 12780/ 37905 | consumed samples: 3271680 | consumed tokens: 6700400640 | elapsed time per iteration (s): 0.23 | learning rate: 1.557E-04 | global batch size: 256 | lm loss: 3.450940E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.922 | TFLOPs: 28.00 | +7: iteration 12790/ 37905 | consumed samples: 3274240 | consumed tokens: 6705643520 | elapsed time per iteration (s): 0.23 | learning rate: 1.556E-04 | global batch size: 256 | lm loss: 3.485881E+00 | grad norm: 0.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.964 | TFLOPs: 27.97 | +7: iteration 12800/ 37905 | consumed samples: 3276800 | consumed tokens: 6710886400 | elapsed time per iteration (s): 0.23 | learning rate: 1.556E-04 | global batch size: 256 | lm loss: 3.442772E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.555 | TFLOPs: 28.39 | +7: iteration 12810/ 37905 | consumed samples: 3279360 | consumed tokens: 6716129280 | elapsed time per iteration (s): 0.23 | learning rate: 1.555E-04 | global batch size: 256 | lm loss: 3.437154E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.242 | TFLOPs: 28.21 | +7: iteration 12820/ 37905 | consumed samples: 3281920 | consumed tokens: 6721372160 | elapsed time per iteration (s): 0.23 | learning rate: 1.554E-04 | global batch size: 256 | lm loss: 3.427290E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.913 | TFLOPs: 28.30 | +7: iteration 12830/ 37905 | consumed samples: 3284480 | consumed tokens: 6726615040 | elapsed time per iteration (s): 0.23 | learning rate: 1.554E-04 | global batch size: 256 | lm loss: 3.417192E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.293 | TFLOPs: 28.23 | +7: iteration 12840/ 37905 | consumed samples: 3287040 | consumed tokens: 6731857920 | elapsed time per iteration (s): 0.23 | learning rate: 1.553E-04 | global batch size: 256 | lm loss: 3.450649E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.631 | TFLOPs: 28.12 | +7: iteration 12850/ 37905 | consumed samples: 3289600 | consumed tokens: 6737100800 | elapsed time per iteration (s): 0.23 | learning rate: 1.552E-04 | global batch size: 256 | lm loss: 3.448598E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.567 | TFLOPs: 28.27 | +7: iteration 12860/ 37905 | consumed samples: 3292160 | consumed tokens: 6742343680 | elapsed time per iteration (s): 0.23 | learning rate: 1.552E-04 | global batch size: 256 | lm loss: 3.428752E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.644 | TFLOPs: 28.04 | +7: iteration 12870/ 37905 | consumed samples: 3294720 | consumed tokens: 6747586560 | elapsed time per iteration (s): 0.23 | learning rate: 1.551E-04 | global batch size: 256 | lm loss: 3.449257E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.409 | TFLOPs: 28.26 | +7: iteration 12880/ 37905 | consumed samples: 3297280 | consumed tokens: 6752829440 | elapsed time per iteration (s): 0.23 | learning rate: 1.551E-04 | global batch size: 256 | lm loss: 3.449835E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.004 | TFLOPs: 28.10 | +7: iteration 12890/ 37905 | consumed samples: 3299840 | consumed tokens: 6758072320 | elapsed time per iteration (s): 0.23 | learning rate: 1.550E-04 | global batch size: 256 | lm loss: 3.417669E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.561 | TFLOPs: 28.06 | +7: iteration 12900/ 37905 | consumed samples: 3302400 | consumed tokens: 6763315200 | elapsed time per iteration (s): 0.23 | learning rate: 1.549E-04 | global batch size: 256 | lm loss: 3.459901E+00 | grad norm: 0.381 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.392 | TFLOPs: 28.03 | +7: iteration 12910/ 37905 | consumed samples: 3304960 | consumed tokens: 6768558080 | elapsed time per iteration (s): 0.23 | learning rate: 1.549E-04 | global batch size: 256 | lm loss: 3.439383E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.706 | TFLOPs: 28.42 | +7: iteration 12920/ 37905 | consumed samples: 3307520 | consumed tokens: 6773800960 | elapsed time per iteration (s): 0.23 | learning rate: 1.548E-04 | global batch size: 256 | lm loss: 3.445287E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.187 | TFLOPs: 28.03 | +7: iteration 12930/ 37905 | consumed samples: 3310080 | consumed tokens: 6779043840 | elapsed time per iteration (s): 0.30 | learning rate: 1.547E-04 | global batch size: 256 | lm loss: 3.431073E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 867.722 | TFLOPs: 22.11 | +7: iteration 12940/ 37905 | consumed samples: 3312640 | consumed tokens: 6784286720 | elapsed time per iteration (s): 0.25 | learning rate: 1.547E-04 | global batch size: 256 | lm loss: 3.465136E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1030.003 | TFLOPs: 26.24 | +7: iteration 12950/ 37905 | consumed samples: 3315200 | consumed tokens: 6789529600 | elapsed time per iteration (s): 0.24 | learning rate: 1.546E-04 | global batch size: 256 | lm loss: 3.444550E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1077.001 | TFLOPs: 27.44 | +7: iteration 12960/ 37905 | consumed samples: 3317760 | consumed tokens: 6794772480 | elapsed time per iteration (s): 0.32 | learning rate: 1.545E-04 | global batch size: 256 | lm loss: 3.462734E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 806.997 | TFLOPs: 20.56 | +7: iteration 12970/ 37905 | consumed samples: 3320320 | consumed tokens: 6800015360 | elapsed time per iteration (s): 0.23 | learning rate: 1.545E-04 | global batch size: 256 | lm loss: 3.460775E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.151 | TFLOPs: 28.20 | +7: iteration 12980/ 37905 | consumed samples: 3322880 | consumed tokens: 6805258240 | elapsed time per iteration (s): 0.28 | learning rate: 1.544E-04 | global batch size: 256 | lm loss: 3.455700E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 911.699 | TFLOPs: 23.23 | +7: iteration 12990/ 37905 | consumed samples: 3325440 | consumed tokens: 6810501120 | elapsed time per iteration (s): 0.23 | learning rate: 1.543E-04 | global batch size: 256 | lm loss: 3.424260E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.061 | TFLOPs: 28.36 | +7: iteration 13000/ 37905 | consumed samples: 3328000 | consumed tokens: 6815744000 | elapsed time per iteration (s): 0.23 | learning rate: 1.543E-04 | global batch size: 256 | lm loss: 3.440621E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.904 | TFLOPs: 28.43 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 13000 | lm loss value: 3.337577E+00 | lm loss PPL: 2.815084E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 13000 to checkpoints_83moscar +0: [2022-11-29 17:46:55,175] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step13000 is begin to save! +0: [2022-11-29 17:46:55,179] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:46:55,250] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:46:55,250] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:46:55,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:46:55,263] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:46:55,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:46:55,274] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:46:55,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:46:55,286] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:46:55,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:46:55,297] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:46:55,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:46:55,308] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:46:55,319] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:46:55,319] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:46:55,330] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:46:55,331] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:46:55,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:46:55,342] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:46:55,353] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:46:55,353] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:46:55,364] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:46:55,364] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:46:55,365] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:46:55,366] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step13000/mp_rank_00_model_states.pt +0: [2022-11-29 17:46:55,366] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:46:55,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:46:55,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:46:55,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:46:55,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:46:55,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:46:55,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 17:46:55,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:46:55,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:46:55,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 17:46:55,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:46:55,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:46:55,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:46:55,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +6: [2022-11-29 17:46:55,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:46:55,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 17:46:55,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:46:55,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:46:55,408] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: [2022-11-29 17:46:55,408] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:46:55,408] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:46:55,408] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: [2022-11-29 17:46:55,408] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:46:55,408] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 17:46:55,408] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:46:55,408] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:46:55,408] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +6: [2022-11-29 17:46:55,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:46:55,409] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:46:55,409] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 17:46:55,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:46:55,409] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:46:55,409] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 17:46:55,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:46:55,409] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:46:55,409] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 17:46:55,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:46:55,409] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:46:55,409] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +3: [2022-11-29 17:46:55,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:46:55,410] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:46:55,410] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 17:46:55,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:46:55,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:46:55,410] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +5: [2022-11-29 17:46:55,410] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +2: [2022-11-29 17:46:55,410] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 17:46:55,410] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: [2022-11-29 17:46:55,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:46:55,410] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:46:55,410] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +3: [2022-11-29 17:46:55,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:46:55,410] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:46:55,410] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 17:46:55,411] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:46:55,411] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:46:55,411] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 17:46:55,411] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:46:55,411] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:46:55,411] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 17:46:55,411] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:46:55,411] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:46:55,411] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 17:46:55,411] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:46:55,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:46:55,412] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: [2022-11-29 17:46:55,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:46:55,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:46:55,412] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 17:46:55,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:46:55,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:46:55,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:46:55,412] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 17:46:55,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +6: [2022-11-29 17:46:55,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:46:55,412] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +6: [2022-11-29 17:46:55,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:46:55,412] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +3: [2022-11-29 17:46:55,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:46:55,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:46:55,412] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 17:46:55,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:46:55,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +6: [2022-11-29 17:46:55,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:46:55,412] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +6: [2022-11-29 17:46:55,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:46:55,412] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 17:46:55,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:46:55,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:46:55,412] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: [2022-11-29 17:46:55,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:46:55,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:46:55,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +7: [2022-11-29 17:46:55,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +0: [2022-11-29 17:46:55,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 17:46:55,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +3: [2022-11-29 17:46:55,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:46:55,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:46:55,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 17:46:55,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:46:55,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:46:55,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +5: [2022-11-29 17:46:55,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +2: [2022-11-29 17:46:55,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 17:46:55,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 17:46:55,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:46:55,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:46:55,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +6: [2022-11-29 17:46:55,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:46:55,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:46:55,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 17:46:55,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:46:55,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:46:55,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +5: [2022-11-29 17:46:55,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +7: [2022-11-29 17:46:55,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 17:46:55,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: [2022-11-29 17:46:55,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:46:55,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:46:55,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 17:46:55,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:46:55,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:46:55,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 17:46:55,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:46:55,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:46:55,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 17:46:55,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:46:55,416] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:46:55,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +6: [2022-11-29 17:46:55,416] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:46:55,416] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:46:55,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: [2022-11-29 17:46:55,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:46:55,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:46:55,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:46:55,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:46:55,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +2: [2022-11-29 17:46:55,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:46:55,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +4: [2022-11-29 17:46:55,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +0: [2022-11-29 17:46:55,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 17:46:55,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 17:46:55,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:46:55,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 17:46:55,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +5: [2022-11-29 17:46:55,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +2: [2022-11-29 17:46:55,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 17:46:55,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 17:46:55,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:46:55,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +3: [2022-11-29 17:46:55,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:46:55,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:46:55,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:46:55,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 17:46:55,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:46:55,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:46:55,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 17:46:55,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:46:55,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 17:46:55,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:46:55,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:46:55,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +2: [2022-11-29 17:46:55,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:46:55,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:46:55,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +1: [2022-11-29 17:46:55,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +2: [2022-11-29 17:46:55,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +1: [2022-11-29 17:46:55,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: [2022-11-29 17:46:55,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:46:55,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:46:55,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 17:46:55,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:46:55,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:46:55,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +6: [2022-11-29 17:46:55,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +4: [2022-11-29 17:46:55,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:46:55,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 17:46:55,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +6: [2022-11-29 17:46:55,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +4: [2022-11-29 17:46:55,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +6: [2022-11-29 17:46:55,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:46:55,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:46:55,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +3: [2022-11-29 17:46:55,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:46:55,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:46:55,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +7: [2022-11-29 17:46:55,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +3: [2022-11-29 17:46:55,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 17:46:55,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +5: [2022-11-29 17:46:55,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:46:55,420] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:46:55,420] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +7: [2022-11-29 17:46:55,420] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:46:55,420] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step13000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:46:55,420] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +0: successfully saved checkpoint at iteration 13000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 249.51 +7: iteration 13010/ 37905 | consumed samples: 3330560 | consumed tokens: 6820986880 | elapsed time per iteration (s): 0.26 | learning rate: 1.542E-04 | global batch size: 256 | lm loss: 3.446931E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 979.938 | TFLOPs: 24.96 | +7: iteration 13020/ 37905 | consumed samples: 3333120 | consumed tokens: 6826229760 | elapsed time per iteration (s): 0.24 | learning rate: 1.541E-04 | global batch size: 256 | lm loss: 3.454766E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.122 | TFLOPs: 27.72 | +7: iteration 13030/ 37905 | consumed samples: 3335680 | consumed tokens: 6831472640 | elapsed time per iteration (s): 0.24 | learning rate: 1.541E-04 | global batch size: 256 | lm loss: 3.453984E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1077.798 | TFLOPs: 27.46 | +7: iteration 13040/ 37905 | consumed samples: 3338240 | consumed tokens: 6836715520 | elapsed time per iteration (s): 0.23 | learning rate: 1.540E-04 | global batch size: 256 | lm loss: 3.447050E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.400 | TFLOPs: 27.98 | +7: iteration 13050/ 37905 | consumed samples: 3340800 | consumed tokens: 6841958400 | elapsed time per iteration (s): 0.23 | learning rate: 1.539E-04 | global batch size: 256 | lm loss: 3.425066E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.083 | TFLOPs: 28.25 | +7: iteration 13060/ 37905 | consumed samples: 3343360 | consumed tokens: 6847201280 | elapsed time per iteration (s): 0.23 | learning rate: 1.539E-04 | global batch size: 256 | lm loss: 3.460469E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.160 | TFLOPs: 27.82 | +7: iteration 13070/ 37905 | consumed samples: 3345920 | consumed tokens: 6852444160 | elapsed time per iteration (s): 0.23 | learning rate: 1.538E-04 | global batch size: 256 | lm loss: 3.417706E+00 | grad norm: 0.377 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.778 | TFLOPs: 28.37 | +7: iteration 13080/ 37905 | consumed samples: 3348480 | consumed tokens: 6857687040 | elapsed time per iteration (s): 0.23 | learning rate: 1.537E-04 | global batch size: 256 | lm loss: 3.455433E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.479 | TFLOPs: 28.16 | +7: iteration 13090/ 37905 | consumed samples: 3351040 | consumed tokens: 6862929920 | elapsed time per iteration (s): 0.23 | learning rate: 1.537E-04 | global batch size: 256 | lm loss: 3.464283E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.278 | TFLOPs: 28.16 | +7: iteration 13100/ 37905 | consumed samples: 3353600 | consumed tokens: 6868172800 | elapsed time per iteration (s): 0.23 | learning rate: 1.536E-04 | global batch size: 256 | lm loss: 3.471363E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.461 | TFLOPs: 27.96 | +7: iteration 13110/ 37905 | consumed samples: 3356160 | consumed tokens: 6873415680 | elapsed time per iteration (s): 0.23 | learning rate: 1.535E-04 | global batch size: 256 | lm loss: 3.427915E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.998 | TFLOPs: 28.30 | +7: iteration 13120/ 37905 | consumed samples: 3358720 | consumed tokens: 6878658560 | elapsed time per iteration (s): 0.23 | learning rate: 1.535E-04 | global batch size: 256 | lm loss: 3.435949E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.800 | TFLOPs: 28.22 | +7: iteration 13130/ 37905 | consumed samples: 3361280 | consumed tokens: 6883901440 | elapsed time per iteration (s): 0.24 | learning rate: 1.534E-04 | global batch size: 256 | lm loss: 3.440442E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1077.800 | TFLOPs: 27.46 | +7: iteration 13140/ 37905 | consumed samples: 3363840 | consumed tokens: 6889144320 | elapsed time per iteration (s): 0.23 | learning rate: 1.533E-04 | global batch size: 256 | lm loss: 3.448709E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.550 | TFLOPs: 28.14 | +7: iteration 13150/ 37905 | consumed samples: 3366400 | consumed tokens: 6894387200 | elapsed time per iteration (s): 0.24 | learning rate: 1.533E-04 | global batch size: 256 | lm loss: 3.452482E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1060.843 | TFLOPs: 27.03 | +7: iteration 13160/ 37905 | consumed samples: 3368960 | consumed tokens: 6899630080 | elapsed time per iteration (s): 0.23 | learning rate: 1.532E-04 | global batch size: 256 | lm loss: 3.449846E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.486 | TFLOPs: 28.09 | +7: iteration 13170/ 37905 | consumed samples: 3371520 | consumed tokens: 6904872960 | elapsed time per iteration (s): 0.23 | learning rate: 1.531E-04 | global batch size: 256 | lm loss: 3.451771E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.293 | TFLOPs: 28.13 | +7: iteration 13180/ 37905 | consumed samples: 3374080 | consumed tokens: 6910115840 | elapsed time per iteration (s): 0.24 | learning rate: 1.531E-04 | global batch size: 256 | lm loss: 3.443758E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1077.111 | TFLOPs: 27.44 | +7: iteration 13190/ 37905 | consumed samples: 3376640 | consumed tokens: 6915358720 | elapsed time per iteration (s): 0.24 | learning rate: 1.530E-04 | global batch size: 256 | lm loss: 3.436526E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.172 | TFLOPs: 27.70 | +7: iteration 13200/ 37905 | consumed samples: 3379200 | consumed tokens: 6920601600 | elapsed time per iteration (s): 0.23 | learning rate: 1.529E-04 | global batch size: 256 | lm loss: 3.449775E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.705 | TFLOPs: 28.32 | +7: iteration 13210/ 37905 | consumed samples: 3381760 | consumed tokens: 6925844480 | elapsed time per iteration (s): 0.23 | learning rate: 1.529E-04 | global batch size: 256 | lm loss: 3.445014E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.404 | TFLOPs: 27.96 | +7: iteration 13220/ 37905 | consumed samples: 3384320 | consumed tokens: 6931087360 | elapsed time per iteration (s): 0.23 | learning rate: 1.528E-04 | global batch size: 256 | lm loss: 3.433392E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.428 | TFLOPs: 28.24 | +7: iteration 13230/ 37905 | consumed samples: 3386880 | consumed tokens: 6936330240 | elapsed time per iteration (s): 0.23 | learning rate: 1.527E-04 | global batch size: 256 | lm loss: 3.420473E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.311 | TFLOPs: 28.11 | +7: iteration 13240/ 37905 | consumed samples: 3389440 | consumed tokens: 6941573120 | elapsed time per iteration (s): 0.23 | learning rate: 1.527E-04 | global batch size: 256 | lm loss: 3.436207E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.997 | TFLOPs: 28.28 | +7: iteration 13250/ 37905 | consumed samples: 3392000 | consumed tokens: 6946816000 | elapsed time per iteration (s): 0.23 | learning rate: 1.526E-04 | global batch size: 256 | lm loss: 3.461559E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.512 | TFLOPs: 28.37 | +7: iteration 13260/ 37905 | consumed samples: 3394560 | consumed tokens: 6952058880 | elapsed time per iteration (s): 0.23 | learning rate: 1.525E-04 | global batch size: 256 | lm loss: 3.432215E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.538 | TFLOPs: 27.91 | +7: iteration 13270/ 37905 | consumed samples: 3397120 | consumed tokens: 6957301760 | elapsed time per iteration (s): 0.23 | learning rate: 1.525E-04 | global batch size: 256 | lm loss: 3.454319E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.105 | TFLOPs: 28.36 | +7: iteration 13280/ 37905 | consumed samples: 3399680 | consumed tokens: 6962544640 | elapsed time per iteration (s): 0.23 | learning rate: 1.524E-04 | global batch size: 256 | lm loss: 3.442105E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.989 | TFLOPs: 28.20 | +7: iteration 13290/ 37905 | consumed samples: 3402240 | consumed tokens: 6967787520 | elapsed time per iteration (s): 0.25 | learning rate: 1.524E-04 | global batch size: 256 | lm loss: 3.444838E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1030.879 | TFLOPs: 26.26 | +7: iteration 13300/ 37905 | consumed samples: 3404800 | consumed tokens: 6973030400 | elapsed time per iteration (s): 0.23 | learning rate: 1.523E-04 | global batch size: 256 | lm loss: 3.430831E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.616 | TFLOPs: 28.27 | +7: iteration 13310/ 37905 | consumed samples: 3407360 | consumed tokens: 6978273280 | elapsed time per iteration (s): 0.23 | learning rate: 1.522E-04 | global batch size: 256 | lm loss: 3.419401E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.050 | TFLOPs: 28.30 | +7: iteration 13320/ 37905 | consumed samples: 3409920 | consumed tokens: 6983516160 | elapsed time per iteration (s): 0.23 | learning rate: 1.522E-04 | global batch size: 256 | lm loss: 3.422123E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.444 | TFLOPs: 28.11 | +7: iteration 13330/ 37905 | consumed samples: 3412480 | consumed tokens: 6988759040 | elapsed time per iteration (s): 0.24 | learning rate: 1.521E-04 | global batch size: 256 | lm loss: 3.464122E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.769 | TFLOPs: 26.95 | +7: iteration 13340/ 37905 | consumed samples: 3415040 | consumed tokens: 6994001920 | elapsed time per iteration (s): 0.23 | learning rate: 1.520E-04 | global batch size: 256 | lm loss: 3.459091E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.849 | TFLOPs: 28.15 | +7: iteration 13350/ 37905 | consumed samples: 3417600 | consumed tokens: 6999244800 | elapsed time per iteration (s): 0.26 | learning rate: 1.520E-04 | global batch size: 256 | lm loss: 3.458234E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 992.826 | TFLOPs: 25.29 | +7: iteration 13360/ 37905 | consumed samples: 3420160 | consumed tokens: 7004487680 | elapsed time per iteration (s): 0.26 | learning rate: 1.519E-04 | global batch size: 256 | lm loss: 3.468095E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1003.514 | TFLOPs: 25.56 | +7: iteration 13370/ 37905 | consumed samples: 3422720 | consumed tokens: 7009730560 | elapsed time per iteration (s): 0.31 | learning rate: 1.518E-04 | global batch size: 256 | lm loss: 3.474482E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 823.017 | TFLOPs: 20.97 | +7: iteration 13380/ 37905 | consumed samples: 3425280 | consumed tokens: 7014973440 | elapsed time per iteration (s): 0.28 | learning rate: 1.518E-04 | global batch size: 256 | lm loss: 3.456950E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 918.442 | TFLOPs: 23.40 | +7: iteration 13390/ 37905 | consumed samples: 3427840 | consumed tokens: 7020216320 | elapsed time per iteration (s): 0.30 | learning rate: 1.517E-04 | global batch size: 256 | lm loss: 3.443611E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 841.092 | TFLOPs: 21.43 | +7: iteration 13400/ 37905 | consumed samples: 3430400 | consumed tokens: 7025459200 | elapsed time per iteration (s): 0.23 | learning rate: 1.516E-04 | global batch size: 256 | lm loss: 3.420741E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.509 | TFLOPs: 28.49 | +7: iteration 13410/ 37905 | consumed samples: 3432960 | consumed tokens: 7030702080 | elapsed time per iteration (s): 0.23 | learning rate: 1.516E-04 | global batch size: 256 | lm loss: 3.434753E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.713 | TFLOPs: 28.19 | +7: iteration 13420/ 37905 | consumed samples: 3435520 | consumed tokens: 7035944960 | elapsed time per iteration (s): 0.23 | learning rate: 1.515E-04 | global batch size: 256 | lm loss: 3.428609E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.214 | TFLOPs: 27.98 | +7: iteration 13430/ 37905 | consumed samples: 3438080 | consumed tokens: 7041187840 | elapsed time per iteration (s): 0.23 | learning rate: 1.514E-04 | global batch size: 256 | lm loss: 3.447880E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.790 | TFLOPs: 28.12 | +7: iteration 13440/ 37905 | consumed samples: 3440640 | consumed tokens: 7046430720 | elapsed time per iteration (s): 0.23 | learning rate: 1.513E-04 | global batch size: 256 | lm loss: 3.436838E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.319 | TFLOPs: 28.26 | +7: iteration 13450/ 37905 | consumed samples: 3443200 | consumed tokens: 7051673600 | elapsed time per iteration (s): 0.23 | learning rate: 1.513E-04 | global batch size: 256 | lm loss: 3.447349E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.977 | TFLOPs: 28.10 | +7: iteration 13460/ 37905 | consumed samples: 3445760 | consumed tokens: 7056916480 | elapsed time per iteration (s): 0.23 | learning rate: 1.512E-04 | global batch size: 256 | lm loss: 3.455896E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.888 | TFLOPs: 28.17 | +7: iteration 13470/ 37905 | consumed samples: 3448320 | consumed tokens: 7062159360 | elapsed time per iteration (s): 0.23 | learning rate: 1.511E-04 | global batch size: 256 | lm loss: 3.429088E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.834 | TFLOPs: 28.17 | +7: iteration 13480/ 37905 | consumed samples: 3450880 | consumed tokens: 7067402240 | elapsed time per iteration (s): 0.23 | learning rate: 1.511E-04 | global batch size: 256 | lm loss: 3.441544E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.838 | TFLOPs: 27.99 | +7: iteration 13490/ 37905 | consumed samples: 3453440 | consumed tokens: 7072645120 | elapsed time per iteration (s): 0.23 | learning rate: 1.510E-04 | global batch size: 256 | lm loss: 3.459244E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.929 | TFLOPs: 27.94 | +7: iteration 13500/ 37905 | consumed samples: 3456000 | consumed tokens: 7077888000 | elapsed time per iteration (s): 0.24 | learning rate: 1.509E-04 | global batch size: 256 | lm loss: 3.441833E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.852 | TFLOPs: 27.69 | +7: iteration 13510/ 37905 | consumed samples: 3458560 | consumed tokens: 7083130880 | elapsed time per iteration (s): 0.23 | learning rate: 1.509E-04 | global batch size: 256 | lm loss: 3.456543E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.774 | TFLOPs: 28.12 | +7: iteration 13520/ 37905 | consumed samples: 3461120 | consumed tokens: 7088373760 | elapsed time per iteration (s): 0.23 | learning rate: 1.508E-04 | global batch size: 256 | lm loss: 3.436963E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.568 | TFLOPs: 28.16 | +7: iteration 13530/ 37905 | consumed samples: 3463680 | consumed tokens: 7093616640 | elapsed time per iteration (s): 0.23 | learning rate: 1.507E-04 | global batch size: 256 | lm loss: 3.422559E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.157 | TFLOPs: 28.31 | +7: iteration 13540/ 37905 | consumed samples: 3466240 | consumed tokens: 7098859520 | elapsed time per iteration (s): 0.23 | learning rate: 1.507E-04 | global batch size: 256 | lm loss: 3.413483E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.829 | TFLOPs: 28.09 | +7: iteration 13550/ 37905 | consumed samples: 3468800 | consumed tokens: 7104102400 | elapsed time per iteration (s): 0.23 | learning rate: 1.506E-04 | global batch size: 256 | lm loss: 3.420823E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.344 | TFLOPs: 28.31 | +7: iteration 13560/ 37905 | consumed samples: 3471360 | consumed tokens: 7109345280 | elapsed time per iteration (s): 0.23 | learning rate: 1.505E-04 | global batch size: 256 | lm loss: 3.437616E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.647 | TFLOPs: 27.78 | +7: iteration 13570/ 37905 | consumed samples: 3473920 | consumed tokens: 7114588160 | elapsed time per iteration (s): 0.23 | learning rate: 1.505E-04 | global batch size: 256 | lm loss: 3.450340E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.435 | TFLOPs: 28.29 | +7: iteration 13580/ 37905 | consumed samples: 3476480 | consumed tokens: 7119831040 | elapsed time per iteration (s): 0.25 | learning rate: 1.504E-04 | global batch size: 256 | lm loss: 3.442400E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1018.779 | TFLOPs: 25.95 | +7: iteration 13590/ 37905 | consumed samples: 3479040 | consumed tokens: 7125073920 | elapsed time per iteration (s): 0.23 | learning rate: 1.503E-04 | global batch size: 256 | lm loss: 3.473808E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.806 | TFLOPs: 28.20 | +7: iteration 13600/ 37905 | consumed samples: 3481600 | consumed tokens: 7130316800 | elapsed time per iteration (s): 0.23 | learning rate: 1.503E-04 | global batch size: 256 | lm loss: 3.447095E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.701 | TFLOPs: 28.32 | +7: iteration 13610/ 37905 | consumed samples: 3484160 | consumed tokens: 7135559680 | elapsed time per iteration (s): 0.23 | learning rate: 1.502E-04 | global batch size: 256 | lm loss: 3.445744E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.479 | TFLOPs: 28.09 | +7: iteration 13620/ 37905 | consumed samples: 3486720 | consumed tokens: 7140802560 | elapsed time per iteration (s): 0.24 | learning rate: 1.501E-04 | global batch size: 256 | lm loss: 3.410829E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.066 | TFLOPs: 27.64 | +7: iteration 13630/ 37905 | consumed samples: 3489280 | consumed tokens: 7146045440 | elapsed time per iteration (s): 0.23 | learning rate: 1.501E-04 | global batch size: 256 | lm loss: 3.472184E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.753 | TFLOPs: 27.89 | +7: iteration 13640/ 37905 | consumed samples: 3491840 | consumed tokens: 7151288320 | elapsed time per iteration (s): 0.23 | learning rate: 1.500E-04 | global batch size: 256 | lm loss: 3.459690E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.781 | TFLOPs: 28.25 | +7: iteration 13650/ 37905 | consumed samples: 3494400 | consumed tokens: 7156531200 | elapsed time per iteration (s): 0.24 | learning rate: 1.499E-04 | global batch size: 256 | lm loss: 3.450379E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1073.949 | TFLOPs: 27.36 | +7: iteration 13660/ 37905 | consumed samples: 3496960 | consumed tokens: 7161774080 | elapsed time per iteration (s): 0.24 | learning rate: 1.499E-04 | global batch size: 256 | lm loss: 3.459933E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1049.219 | TFLOPs: 26.73 | +7: iteration 13670/ 37905 | consumed samples: 3499520 | consumed tokens: 7167016960 | elapsed time per iteration (s): 0.24 | learning rate: 1.498E-04 | global batch size: 256 | lm loss: 3.432165E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1081.586 | TFLOPs: 27.55 | +7: iteration 13680/ 37905 | consumed samples: 3502080 | consumed tokens: 7172259840 | elapsed time per iteration (s): 0.24 | learning rate: 1.497E-04 | global batch size: 256 | lm loss: 3.438873E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.485 | TFLOPs: 27.65 | +7: iteration 13690/ 37905 | consumed samples: 3504640 | consumed tokens: 7177502720 | elapsed time per iteration (s): 0.23 | learning rate: 1.497E-04 | global batch size: 256 | lm loss: 3.409036E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.383 | TFLOPs: 28.54 | +7: iteration 13700/ 37905 | consumed samples: 3507200 | consumed tokens: 7182745600 | elapsed time per iteration (s): 0.23 | learning rate: 1.496E-04 | global batch size: 256 | lm loss: 3.430365E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.962 | TFLOPs: 28.38 | +7: iteration 13710/ 37905 | consumed samples: 3509760 | consumed tokens: 7187988480 | elapsed time per iteration (s): 0.23 | learning rate: 1.495E-04 | global batch size: 256 | lm loss: 3.467722E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.529 | TFLOPs: 28.42 | +7: iteration 13720/ 37905 | consumed samples: 3512320 | consumed tokens: 7193231360 | elapsed time per iteration (s): 0.23 | learning rate: 1.495E-04 | global batch size: 256 | lm loss: 3.423328E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.551 | TFLOPs: 28.52 | +7: iteration 13730/ 37905 | consumed samples: 3514880 | consumed tokens: 7198474240 | elapsed time per iteration (s): 0.23 | learning rate: 1.494E-04 | global batch size: 256 | lm loss: 3.454818E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.656 | TFLOPs: 28.37 | +7: iteration 13740/ 37905 | consumed samples: 3517440 | consumed tokens: 7203717120 | elapsed time per iteration (s): 0.23 | learning rate: 1.493E-04 | global batch size: 256 | lm loss: 3.420602E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.282 | TFLOPs: 27.95 | +7: iteration 13750/ 37905 | consumed samples: 3520000 | consumed tokens: 7208960000 | elapsed time per iteration (s): 0.23 | learning rate: 1.493E-04 | global batch size: 256 | lm loss: 3.448814E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.126 | TFLOPs: 28.33 | +7: iteration 13760/ 37905 | consumed samples: 3522560 | consumed tokens: 7214202880 | elapsed time per iteration (s): 0.23 | learning rate: 1.492E-04 | global batch size: 256 | lm loss: 3.426511E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.295 | TFLOPs: 28.18 | +7: iteration 13770/ 37905 | consumed samples: 3525120 | consumed tokens: 7219445760 | elapsed time per iteration (s): 0.23 | learning rate: 1.491E-04 | global batch size: 256 | lm loss: 3.448302E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.739 | TFLOPs: 27.99 | +7: iteration 13780/ 37905 | consumed samples: 3527680 | consumed tokens: 7224688640 | elapsed time per iteration (s): 0.24 | learning rate: 1.491E-04 | global batch size: 256 | lm loss: 3.414801E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.369 | TFLOPs: 27.68 | +7: iteration 13790/ 37905 | consumed samples: 3530240 | consumed tokens: 7229931520 | elapsed time per iteration (s): 0.30 | learning rate: 1.490E-04 | global batch size: 256 | lm loss: 3.444727E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 863.154 | TFLOPs: 21.99 | +7: iteration 13800/ 37905 | consumed samples: 3532800 | consumed tokens: 7235174400 | elapsed time per iteration (s): 0.23 | learning rate: 1.489E-04 | global batch size: 256 | lm loss: 3.426896E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.135 | TFLOPs: 28.05 | +7: iteration 13810/ 37905 | consumed samples: 3535360 | consumed tokens: 7240417280 | elapsed time per iteration (s): 0.31 | learning rate: 1.489E-04 | global batch size: 256 | lm loss: 3.454379E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.772 | TFLOPs: 20.71 | +7: iteration 13820/ 37905 | consumed samples: 3537920 | consumed tokens: 7245660160 | elapsed time per iteration (s): 0.25 | learning rate: 1.488E-04 | global batch size: 256 | lm loss: 3.437664E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1023.878 | TFLOPs: 26.08 | +7: iteration 13830/ 37905 | consumed samples: 3540480 | consumed tokens: 7250903040 | elapsed time per iteration (s): 0.26 | learning rate: 1.487E-04 | global batch size: 256 | lm loss: 3.441518E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 989.159 | TFLOPs: 25.20 | +7: iteration 13840/ 37905 | consumed samples: 3543040 | consumed tokens: 7256145920 | elapsed time per iteration (s): 0.23 | learning rate: 1.486E-04 | global batch size: 256 | lm loss: 3.426784E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.163 | TFLOPs: 28.28 | +7: iteration 13850/ 37905 | consumed samples: 3545600 | consumed tokens: 7261388800 | elapsed time per iteration (s): 0.23 | learning rate: 1.486E-04 | global batch size: 256 | lm loss: 3.411814E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.048 | TFLOPs: 28.30 | +7: iteration 13860/ 37905 | consumed samples: 3548160 | consumed tokens: 7266631680 | elapsed time per iteration (s): 0.23 | learning rate: 1.485E-04 | global batch size: 256 | lm loss: 3.431987E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.869 | TFLOPs: 28.12 | +7: iteration 13870/ 37905 | consumed samples: 3550720 | consumed tokens: 7271874560 | elapsed time per iteration (s): 0.23 | learning rate: 1.484E-04 | global batch size: 256 | lm loss: 3.430897E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.192 | TFLOPs: 28.23 | +7: iteration 13880/ 37905 | consumed samples: 3553280 | consumed tokens: 7277117440 | elapsed time per iteration (s): 0.23 | learning rate: 1.484E-04 | global batch size: 256 | lm loss: 3.417896E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.746 | TFLOPs: 28.25 | +7: iteration 13890/ 37905 | consumed samples: 3555840 | consumed tokens: 7282360320 | elapsed time per iteration (s): 0.23 | learning rate: 1.483E-04 | global batch size: 256 | lm loss: 3.440911E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.385 | TFLOPs: 28.03 | +7: iteration 13900/ 37905 | consumed samples: 3558400 | consumed tokens: 7287603200 | elapsed time per iteration (s): 0.24 | learning rate: 1.482E-04 | global batch size: 256 | lm loss: 3.437720E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.235 | TFLOPs: 27.72 | +7: iteration 13910/ 37905 | consumed samples: 3560960 | consumed tokens: 7292846080 | elapsed time per iteration (s): 0.26 | learning rate: 1.482E-04 | global batch size: 256 | lm loss: 3.418006E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1001.480 | TFLOPs: 25.51 | +7: iteration 13920/ 37905 | consumed samples: 3563520 | consumed tokens: 7298088960 | elapsed time per iteration (s): 0.23 | learning rate: 1.481E-04 | global batch size: 256 | lm loss: 3.431197E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.239 | TFLOPs: 28.41 | +7: iteration 13930/ 37905 | consumed samples: 3566080 | consumed tokens: 7303331840 | elapsed time per iteration (s): 0.23 | learning rate: 1.480E-04 | global batch size: 256 | lm loss: 3.434415E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.335 | TFLOPs: 28.06 | +7: iteration 13940/ 37905 | consumed samples: 3568640 | consumed tokens: 7308574720 | elapsed time per iteration (s): 0.23 | learning rate: 1.480E-04 | global batch size: 256 | lm loss: 3.423090E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.682 | TFLOPs: 28.27 | +7: iteration 13950/ 37905 | consumed samples: 3571200 | consumed tokens: 7313817600 | elapsed time per iteration (s): 0.23 | learning rate: 1.479E-04 | global batch size: 256 | lm loss: 3.453659E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.320 | TFLOPs: 28.18 | +7: iteration 13960/ 37905 | consumed samples: 3573760 | consumed tokens: 7319060480 | elapsed time per iteration (s): 0.23 | learning rate: 1.478E-04 | global batch size: 256 | lm loss: 3.412305E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.872 | TFLOPs: 28.25 | +7: iteration 13970/ 37905 | consumed samples: 3576320 | consumed tokens: 7324303360 | elapsed time per iteration (s): 0.23 | learning rate: 1.478E-04 | global batch size: 256 | lm loss: 3.445418E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.664 | TFLOPs: 27.89 | +7: iteration 13980/ 37905 | consumed samples: 3578880 | consumed tokens: 7329546240 | elapsed time per iteration (s): 0.24 | learning rate: 1.477E-04 | global batch size: 256 | lm loss: 3.445985E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1054.519 | TFLOPs: 26.86 | +7: iteration 13990/ 37905 | consumed samples: 3581440 | consumed tokens: 7334789120 | elapsed time per iteration (s): 0.23 | learning rate: 1.476E-04 | global batch size: 256 | lm loss: 3.431652E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.084 | TFLOPs: 28.05 | +0: [2022-11-29 17:50:52,931] [INFO] [logging.py:68:log_dist] [Rank 0] step=14000, skipped=0, lr=[0.00014755779238876917, 0.00014755779238876917, 0.00014755779238876917], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 14000/ 37905 | consumed samples: 3584000 | consumed tokens: 7340032000 | elapsed time per iteration (s): 0.23 | learning rate: 1.476E-04 | global batch size: 256 | lm loss: 3.401881E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.916 | TFLOPs: 28.07 | +0: steps: 14000 loss: 3.4374 iter time (s): 0.237 samples/sec: 1079.474 +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 14000 | lm loss value: 3.414446E+00 | lm loss PPL: 3.040010E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 14000 to checkpoints_83moscar +0: [2022-11-29 17:50:53,022] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step14000 is begin to save! +0: [2022-11-29 17:50:53,025] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:50:53,096] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:50:53,096] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:50:53,108] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:50:53,109] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:50:53,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:50:53,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:50:53,131] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:50:53,131] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:50:53,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:50:53,142] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:50:53,153] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:50:53,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:50:53,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:50:53,165] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:50:53,176] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:50:53,176] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:50:53,187] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:50:53,187] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:50:53,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:50:53,198] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:50:53,209] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:50:53,210] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:50:53,211] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:50:53,211] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step14000/mp_rank_00_model_states.pt +0: [2022-11-29 17:50:53,211] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:50:53,213] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:50:53,232] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:50:53,248] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:50:53,248] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:50:53,249] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:50:53,249] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +4: [2022-11-29 17:50:53,249] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:50:53,249] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +6: [2022-11-29 17:50:53,249] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:50:53,249] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:50:53,249] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 17:50:53,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:50:53,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:50:53,311] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:50:53,311] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 17:50:53,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:50:53,311] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:50:53,311] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 17:50:53,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:50:53,311] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:50:53,311] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +5: [2022-11-29 17:50:53,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:50:53,312] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:50:53,312] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 17:50:53,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:50:53,312] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:50:53,312] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 17:50:53,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:50:53,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:50:53,312] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +0: [2022-11-29 17:50:53,312] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3: [2022-11-29 17:50:53,312] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 17:50:53,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:50:53,312] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +0: [2022-11-29 17:50:53,312] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 17:50:53,312] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +4: [2022-11-29 17:50:53,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:50:53,312] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:50:53,312] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +4: [2022-11-29 17:50:53,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:50:53,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:50:53,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 17:50:53,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:50:53,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 17:50:53,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +6: [2022-11-29 17:50:53,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:50:53,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:50:53,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +5: [2022-11-29 17:50:53,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:50:53,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +7: [2022-11-29 17:50:53,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:50:53,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +7: [2022-11-29 17:50:53,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:50:53,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 17:50:53,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:50:53,314] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:50:53,314] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +7: [2022-11-29 17:50:53,314] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:50:53,314] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:50:53,314] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +6: [2022-11-29 17:50:53,314] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:50:53,314] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:50:53,314] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +5: [2022-11-29 17:50:53,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:50:53,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:50:53,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:50:53,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +4: [2022-11-29 17:50:53,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +5: [2022-11-29 17:50:53,315] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 17:50:53,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +4: [2022-11-29 17:50:53,315] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 17:50:53,315] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 17:50:53,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:50:53,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:50:53,315] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 17:50:53,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:50:53,316] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:50:53,316] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 17:50:53,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:50:53,316] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:50:53,316] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +6: [2022-11-29 17:50:53,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:50:53,316] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:50:53,316] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +7: [2022-11-29 17:50:53,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:50:53,316] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:50:53,316] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 17:50:53,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:50:53,317] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:50:53,317] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +4: [2022-11-29 17:50:53,317] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:50:53,317] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:50:53,317] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +1: [2022-11-29 17:50:53,317] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +4: [2022-11-29 17:50:53,317] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 17:50:53,317] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +5: [2022-11-29 17:50:53,317] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:50:53,317] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:50:53,317] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:50:53,317] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:50:53,317] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +5: [2022-11-29 17:50:53,317] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 17:50:53,317] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:50:53,318] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:50:53,318] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 17:50:53,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:50:53,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +7: [2022-11-29 17:50:53,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:50:53,350] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:50:53,350] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 17:50:53,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:50:53,350] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:50:53,350] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 17:50:53,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:50:53,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:50:53,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 17:50:53,354] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:50:53,354] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 17:50:53,354] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 17:50:53,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:50:53,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:50:53,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +6: [2022-11-29 17:50:53,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:50:53,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:50:53,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +4: [2022-11-29 17:50:53,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:50:53,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:50:53,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +7: [2022-11-29 17:50:53,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:50:53,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:50:53,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 17:50:53,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:50:53,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:50:53,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 17:50:53,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:50:53,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:50:53,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 17:50:53,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:50:53,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 17:50:53,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 17:50:53,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:50:53,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:50:53,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +5: [2022-11-29 17:50:53,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:50:53,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +0: [2022-11-29 17:50:53,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +5: [2022-11-29 17:50:53,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +6: [2022-11-29 17:50:53,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +5: [2022-11-29 17:50:53,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +4: [2022-11-29 17:50:53,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:50:53,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:50:53,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 17:50:53,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:50:53,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:50:53,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 17:50:53,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:50:53,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:50:53,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +1: [2022-11-29 17:50:53,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:50:53,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +7: [2022-11-29 17:50:53,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: [2022-11-29 17:50:53,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:50:53,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +2: [2022-11-29 17:50:53,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:50:53,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +0: [2022-11-29 17:50:53,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 17:50:53,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +6: [2022-11-29 17:50:53,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:50:53,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:50:53,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +1: [2022-11-29 17:50:53,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:50:53,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +4: [2022-11-29 17:50:53,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:50:53,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +4: [2022-11-29 17:50:53,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +5: [2022-11-29 17:50:53,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:50:53,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 17:50:53,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:50:53,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:50:53,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 17:50:53,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:50:53,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +2: [2022-11-29 17:50:53,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:50:53,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:50:53,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:50:53,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +5: [2022-11-29 17:50:53,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:50:53,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +7: [2022-11-29 17:50:53,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:50:53,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:50:53,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +3: [2022-11-29 17:50:53,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:50:53,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step14000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:50:53,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +0: successfully saved checkpoint at iteration 14000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 552.56 +7: iteration 14010/ 37905 | consumed samples: 3586560 | consumed tokens: 7345274880 | elapsed time per iteration (s): 0.30 | learning rate: 1.475E-04 | global batch size: 256 | lm loss: 3.444707E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 866.458 | TFLOPs: 22.07 | +7: iteration 14020/ 37905 | consumed samples: 3589120 | consumed tokens: 7350517760 | elapsed time per iteration (s): 0.26 | learning rate: 1.474E-04 | global batch size: 256 | lm loss: 3.394437E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 974.716 | TFLOPs: 24.83 | +7: iteration 14030/ 37905 | consumed samples: 3591680 | consumed tokens: 7355760640 | elapsed time per iteration (s): 0.23 | learning rate: 1.474E-04 | global batch size: 256 | lm loss: 3.419536E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.018 | TFLOPs: 27.82 | +7: iteration 14040/ 37905 | consumed samples: 3594240 | consumed tokens: 7361003520 | elapsed time per iteration (s): 0.24 | learning rate: 1.473E-04 | global batch size: 256 | lm loss: 3.411861E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.828 | TFLOPs: 27.71 | +7: iteration 14050/ 37905 | consumed samples: 3596800 | consumed tokens: 7366246400 | elapsed time per iteration (s): 0.23 | learning rate: 1.472E-04 | global batch size: 256 | lm loss: 3.430313E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.173 | TFLOPs: 28.10 | +7: iteration 14060/ 37905 | consumed samples: 3599360 | consumed tokens: 7371489280 | elapsed time per iteration (s): 0.23 | learning rate: 1.471E-04 | global batch size: 256 | lm loss: 3.437568E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.454 | TFLOPs: 28.16 | +7: iteration 14070/ 37905 | consumed samples: 3601920 | consumed tokens: 7376732160 | elapsed time per iteration (s): 0.23 | learning rate: 1.471E-04 | global batch size: 256 | lm loss: 3.420105E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.126 | TFLOPs: 28.13 | +7: iteration 14080/ 37905 | consumed samples: 3604480 | consumed tokens: 7381975040 | elapsed time per iteration (s): 0.23 | learning rate: 1.470E-04 | global batch size: 256 | lm loss: 3.445929E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.255 | TFLOPs: 28.11 | +7: iteration 14090/ 37905 | consumed samples: 3607040 | consumed tokens: 7387217920 | elapsed time per iteration (s): 0.23 | learning rate: 1.469E-04 | global batch size: 256 | lm loss: 3.438849E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.662 | TFLOPs: 28.47 | +7: iteration 14100/ 37905 | consumed samples: 3609600 | consumed tokens: 7392460800 | elapsed time per iteration (s): 0.23 | learning rate: 1.469E-04 | global batch size: 256 | lm loss: 3.416951E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.778 | TFLOPs: 28.37 | +7: iteration 14110/ 37905 | consumed samples: 3612160 | consumed tokens: 7397703680 | elapsed time per iteration (s): 0.23 | learning rate: 1.468E-04 | global batch size: 256 | lm loss: 3.433477E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.014 | TFLOPs: 28.38 | +7: iteration 14120/ 37905 | consumed samples: 3614720 | consumed tokens: 7402946560 | elapsed time per iteration (s): 0.23 | learning rate: 1.467E-04 | global batch size: 256 | lm loss: 3.451149E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.446 | TFLOPs: 28.14 | +7: iteration 14130/ 37905 | consumed samples: 3617280 | consumed tokens: 7408189440 | elapsed time per iteration (s): 0.23 | learning rate: 1.467E-04 | global batch size: 256 | lm loss: 3.434504E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.931 | TFLOPs: 28.45 | +7: iteration 14140/ 37905 | consumed samples: 3619840 | consumed tokens: 7413432320 | elapsed time per iteration (s): 0.23 | learning rate: 1.466E-04 | global batch size: 256 | lm loss: 3.405375E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.768 | TFLOPs: 28.17 | +7: iteration 14150/ 37905 | consumed samples: 3622400 | consumed tokens: 7418675200 | elapsed time per iteration (s): 0.23 | learning rate: 1.465E-04 | global batch size: 256 | lm loss: 3.411197E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.205 | TFLOPs: 28.18 | +7: iteration 14160/ 37905 | consumed samples: 3624960 | consumed tokens: 7423918080 | elapsed time per iteration (s): 0.23 | learning rate: 1.465E-04 | global batch size: 256 | lm loss: 3.455040E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.496 | TFLOPs: 28.21 | +7: iteration 14170/ 37905 | consumed samples: 3627520 | consumed tokens: 7429160960 | elapsed time per iteration (s): 0.23 | learning rate: 1.464E-04 | global batch size: 256 | lm loss: 3.424788E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.204 | TFLOPs: 28.36 | +7: iteration 14180/ 37905 | consumed samples: 3630080 | consumed tokens: 7434403840 | elapsed time per iteration (s): 0.23 | learning rate: 1.463E-04 | global batch size: 256 | lm loss: 3.437731E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.866 | TFLOPs: 28.20 | +7: iteration 14190/ 37905 | consumed samples: 3632640 | consumed tokens: 7439646720 | elapsed time per iteration (s): 0.23 | learning rate: 1.463E-04 | global batch size: 256 | lm loss: 3.437027E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.406 | TFLOPs: 28.11 | +7: iteration 14200/ 37905 | consumed samples: 3635200 | consumed tokens: 7444889600 | elapsed time per iteration (s): 0.25 | learning rate: 1.462E-04 | global batch size: 256 | lm loss: 3.437983E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1022.550 | TFLOPs: 26.05 | +7: iteration 14210/ 37905 | consumed samples: 3637760 | consumed tokens: 7450132480 | elapsed time per iteration (s): 0.24 | learning rate: 1.461E-04 | global batch size: 256 | lm loss: 3.413110E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1061.014 | TFLOPs: 27.03 | +7: iteration 14220/ 37905 | consumed samples: 3640320 | consumed tokens: 7455375360 | elapsed time per iteration (s): 0.25 | learning rate: 1.460E-04 | global batch size: 256 | lm loss: 3.409340E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1021.931 | TFLOPs: 26.03 | +7: iteration 14230/ 37905 | consumed samples: 3642880 | consumed tokens: 7460618240 | elapsed time per iteration (s): 0.23 | learning rate: 1.460E-04 | global batch size: 256 | lm loss: 3.443670E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.461 | TFLOPs: 28.01 | +7: iteration 14240/ 37905 | consumed samples: 3645440 | consumed tokens: 7465861120 | elapsed time per iteration (s): 0.27 | learning rate: 1.459E-04 | global batch size: 256 | lm loss: 3.419030E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 950.633 | TFLOPs: 24.22 | +7: iteration 14250/ 37905 | consumed samples: 3648000 | consumed tokens: 7471104000 | elapsed time per iteration (s): 0.23 | learning rate: 1.458E-04 | global batch size: 256 | lm loss: 3.417915E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.446 | TFLOPs: 28.06 | +7: iteration 14260/ 37905 | consumed samples: 3650560 | consumed tokens: 7476346880 | elapsed time per iteration (s): 0.24 | learning rate: 1.458E-04 | global batch size: 256 | lm loss: 3.424836E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1074.829 | TFLOPs: 27.38 | +7: iteration 14270/ 37905 | consumed samples: 3653120 | consumed tokens: 7481589760 | elapsed time per iteration (s): 0.23 | learning rate: 1.457E-04 | global batch size: 256 | lm loss: 3.425248E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.965 | TFLOPs: 27.92 | +7: iteration 14280/ 37905 | consumed samples: 3655680 | consumed tokens: 7486832640 | elapsed time per iteration (s): 0.24 | learning rate: 1.456E-04 | global batch size: 256 | lm loss: 3.444197E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1048.373 | TFLOPs: 26.71 | +7: iteration 14290/ 37905 | consumed samples: 3658240 | consumed tokens: 7492075520 | elapsed time per iteration (s): 0.24 | learning rate: 1.456E-04 | global batch size: 256 | lm loss: 3.433095E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.202 | TFLOPs: 27.47 | +7: iteration 14300/ 37905 | consumed samples: 3660800 | consumed tokens: 7497318400 | elapsed time per iteration (s): 0.26 | learning rate: 1.455E-04 | global batch size: 256 | lm loss: 3.431509E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 980.525 | TFLOPs: 24.98 | +7: iteration 14310/ 37905 | consumed samples: 3663360 | consumed tokens: 7502561280 | elapsed time per iteration (s): 0.23 | learning rate: 1.454E-04 | global batch size: 256 | lm loss: 3.396077E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.527 | TFLOPs: 28.04 | +7: iteration 14320/ 37905 | consumed samples: 3665920 | consumed tokens: 7507804160 | elapsed time per iteration (s): 0.23 | learning rate: 1.454E-04 | global batch size: 256 | lm loss: 3.434837E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.621 | TFLOPs: 27.99 | +7: iteration 14330/ 37905 | consumed samples: 3668480 | consumed tokens: 7513047040 | elapsed time per iteration (s): 0.24 | learning rate: 1.453E-04 | global batch size: 256 | lm loss: 3.422589E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1073.618 | TFLOPs: 27.35 | +7: iteration 14340/ 37905 | consumed samples: 3671040 | consumed tokens: 7518289920 | elapsed time per iteration (s): 0.23 | learning rate: 1.452E-04 | global batch size: 256 | lm loss: 3.413097E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.611 | TFLOPs: 28.17 | +7: iteration 14350/ 37905 | consumed samples: 3673600 | consumed tokens: 7523532800 | elapsed time per iteration (s): 0.23 | learning rate: 1.451E-04 | global batch size: 256 | lm loss: 3.450163E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.523 | TFLOPs: 28.14 | +7: iteration 14360/ 37905 | consumed samples: 3676160 | consumed tokens: 7528775680 | elapsed time per iteration (s): 0.23 | learning rate: 1.451E-04 | global batch size: 256 | lm loss: 3.435391E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.691 | TFLOPs: 27.99 | +7: iteration 14370/ 37905 | consumed samples: 3678720 | consumed tokens: 7534018560 | elapsed time per iteration (s): 0.23 | learning rate: 1.450E-04 | global batch size: 256 | lm loss: 3.414608E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.977 | TFLOPs: 28.10 | +7: iteration 14380/ 37905 | consumed samples: 3681280 | consumed tokens: 7539261440 | elapsed time per iteration (s): 0.24 | learning rate: 1.449E-04 | global batch size: 256 | lm loss: 3.422423E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1077.349 | TFLOPs: 27.45 | +7: iteration 14390/ 37905 | consumed samples: 3683840 | consumed tokens: 7544504320 | elapsed time per iteration (s): 0.25 | learning rate: 1.449E-04 | global batch size: 256 | lm loss: 3.435191E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1027.254 | TFLOPs: 26.17 | +7: iteration 14400/ 37905 | consumed samples: 3686400 | consumed tokens: 7549747200 | elapsed time per iteration (s): 0.23 | learning rate: 1.448E-04 | global batch size: 256 | lm loss: 3.436333E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.591 | TFLOPs: 28.09 | +7: iteration 14410/ 37905 | consumed samples: 3688960 | consumed tokens: 7554990080 | elapsed time per iteration (s): 0.23 | learning rate: 1.447E-04 | global batch size: 256 | lm loss: 3.441431E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.629 | TFLOPs: 28.04 | +7: iteration 14420/ 37905 | consumed samples: 3691520 | consumed tokens: 7560232960 | elapsed time per iteration (s): 0.24 | learning rate: 1.447E-04 | global batch size: 256 | lm loss: 3.398304E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1081.720 | TFLOPs: 27.56 | +7: iteration 14430/ 37905 | consumed samples: 3694080 | consumed tokens: 7565475840 | elapsed time per iteration (s): 0.23 | learning rate: 1.446E-04 | global batch size: 256 | lm loss: 3.428289E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.637 | TFLOPs: 27.86 | +7: iteration 14440/ 37905 | consumed samples: 3696640 | consumed tokens: 7570718720 | elapsed time per iteration (s): 0.23 | learning rate: 1.445E-04 | global batch size: 256 | lm loss: 3.411936E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.561 | TFLOPs: 28.01 | +7: iteration 14450/ 37905 | consumed samples: 3699200 | consumed tokens: 7575961600 | elapsed time per iteration (s): 0.28 | learning rate: 1.445E-04 | global batch size: 256 | lm loss: 3.442924E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 926.916 | TFLOPs: 23.61 | +7: iteration 14460/ 37905 | consumed samples: 3701760 | consumed tokens: 7581204480 | elapsed time per iteration (s): 0.23 | learning rate: 1.444E-04 | global batch size: 256 | lm loss: 3.436709E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.118 | TFLOPs: 28.38 | +7: iteration 14470/ 37905 | consumed samples: 3704320 | consumed tokens: 7586447360 | elapsed time per iteration (s): 0.23 | learning rate: 1.443E-04 | global batch size: 256 | lm loss: 3.431903E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.157 | TFLOPs: 28.31 | +7: iteration 14480/ 37905 | consumed samples: 3706880 | consumed tokens: 7591690240 | elapsed time per iteration (s): 0.23 | learning rate: 1.442E-04 | global batch size: 256 | lm loss: 3.418166E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.153 | TFLOPs: 28.41 | +7: iteration 14490/ 37905 | consumed samples: 3709440 | consumed tokens: 7596933120 | elapsed time per iteration (s): 0.23 | learning rate: 1.442E-04 | global batch size: 256 | lm loss: 3.430780E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.335 | TFLOPs: 28.49 | +7: iteration 14500/ 37905 | consumed samples: 3712000 | consumed tokens: 7602176000 | elapsed time per iteration (s): 0.23 | learning rate: 1.441E-04 | global batch size: 256 | lm loss: 3.418463E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.606 | TFLOPs: 28.14 | +7: iteration 14510/ 37905 | consumed samples: 3714560 | consumed tokens: 7607418880 | elapsed time per iteration (s): 0.28 | learning rate: 1.440E-04 | global batch size: 256 | lm loss: 3.416560E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 914.517 | TFLOPs: 23.30 | +7: iteration 14520/ 37905 | consumed samples: 3717120 | consumed tokens: 7612661760 | elapsed time per iteration (s): 0.23 | learning rate: 1.440E-04 | global batch size: 256 | lm loss: 3.415426E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.326 | TFLOPs: 28.41 | +7: iteration 14530/ 37905 | consumed samples: 3719680 | consumed tokens: 7617904640 | elapsed time per iteration (s): 0.23 | learning rate: 1.439E-04 | global batch size: 256 | lm loss: 3.415077E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.934 | TFLOPs: 28.25 | +7: iteration 14540/ 37905 | consumed samples: 3722240 | consumed tokens: 7623147520 | elapsed time per iteration (s): 0.25 | learning rate: 1.438E-04 | global batch size: 256 | lm loss: 3.398732E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1018.425 | TFLOPs: 25.94 | +7: iteration 14550/ 37905 | consumed samples: 3724800 | consumed tokens: 7628390400 | elapsed time per iteration (s): 0.23 | learning rate: 1.438E-04 | global batch size: 256 | lm loss: 3.429548E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.239 | TFLOPs: 28.36 | +7: iteration 14560/ 37905 | consumed samples: 3727360 | consumed tokens: 7633633280 | elapsed time per iteration (s): 0.23 | learning rate: 1.437E-04 | global batch size: 256 | lm loss: 3.398368E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.635 | TFLOPs: 28.40 | +7: iteration 14570/ 37905 | consumed samples: 3729920 | consumed tokens: 7638876160 | elapsed time per iteration (s): 0.24 | learning rate: 1.436E-04 | global batch size: 256 | lm loss: 3.399627E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.885 | TFLOPs: 26.95 | +7: iteration 14580/ 37905 | consumed samples: 3732480 | consumed tokens: 7644119040 | elapsed time per iteration (s): 0.32 | learning rate: 1.435E-04 | global batch size: 256 | lm loss: 3.400192E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 805.742 | TFLOPs: 20.53 | +7: iteration 14590/ 37905 | consumed samples: 3735040 | consumed tokens: 7649361920 | elapsed time per iteration (s): 0.23 | learning rate: 1.435E-04 | global batch size: 256 | lm loss: 3.416155E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.168 | TFLOPs: 28.46 | +7: iteration 14600/ 37905 | consumed samples: 3737600 | consumed tokens: 7654604800 | elapsed time per iteration (s): 0.28 | learning rate: 1.434E-04 | global batch size: 256 | lm loss: 3.425771E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 929.612 | TFLOPs: 23.68 | +7: iteration 14610/ 37905 | consumed samples: 3740160 | consumed tokens: 7659847680 | elapsed time per iteration (s): 0.24 | learning rate: 1.433E-04 | global batch size: 256 | lm loss: 3.410968E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.075 | TFLOPs: 27.74 | +7: iteration 14620/ 37905 | consumed samples: 3742720 | consumed tokens: 7665090560 | elapsed time per iteration (s): 0.30 | learning rate: 1.433E-04 | global batch size: 256 | lm loss: 3.446021E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 854.186 | TFLOPs: 21.76 | +7: iteration 14630/ 37905 | consumed samples: 3745280 | consumed tokens: 7670333440 | elapsed time per iteration (s): 0.23 | learning rate: 1.432E-04 | global batch size: 256 | lm loss: 3.397921E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.156 | TFLOPs: 27.80 | +7: iteration 14640/ 37905 | consumed samples: 3747840 | consumed tokens: 7675576320 | elapsed time per iteration (s): 0.24 | learning rate: 1.431E-04 | global batch size: 256 | lm loss: 3.457367E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1054.334 | TFLOPs: 26.86 | +7: iteration 14650/ 37905 | consumed samples: 3750400 | consumed tokens: 7680819200 | elapsed time per iteration (s): 0.23 | learning rate: 1.431E-04 | global batch size: 256 | lm loss: 3.414890E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.008 | TFLOPs: 27.92 | +7: iteration 14660/ 37905 | consumed samples: 3752960 | consumed tokens: 7686062080 | elapsed time per iteration (s): 0.25 | learning rate: 1.430E-04 | global batch size: 256 | lm loss: 3.426942E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1031.419 | TFLOPs: 26.28 | +7: iteration 14670/ 37905 | consumed samples: 3755520 | consumed tokens: 7691304960 | elapsed time per iteration (s): 0.28 | learning rate: 1.429E-04 | global batch size: 256 | lm loss: 3.422346E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 909.323 | TFLOPs: 23.17 | +7: iteration 14680/ 37905 | consumed samples: 3758080 | consumed tokens: 7696547840 | elapsed time per iteration (s): 0.26 | learning rate: 1.428E-04 | global batch size: 256 | lm loss: 3.404445E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 985.629 | TFLOPs: 25.11 | +7: iteration 14690/ 37905 | consumed samples: 3760640 | consumed tokens: 7701790720 | elapsed time per iteration (s): 0.25 | learning rate: 1.428E-04 | global batch size: 256 | lm loss: 3.427022E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1028.348 | TFLOPs: 26.20 | +7: iteration 14700/ 37905 | consumed samples: 3763200 | consumed tokens: 7707033600 | elapsed time per iteration (s): 0.24 | learning rate: 1.427E-04 | global batch size: 256 | lm loss: 3.401699E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1081.432 | TFLOPs: 27.55 | +7: iteration 14710/ 37905 | consumed samples: 3765760 | consumed tokens: 7712276480 | elapsed time per iteration (s): 0.23 | learning rate: 1.426E-04 | global batch size: 256 | lm loss: 3.411481E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.579 | TFLOPs: 28.24 | +7: iteration 14720/ 37905 | consumed samples: 3768320 | consumed tokens: 7717519360 | elapsed time per iteration (s): 0.23 | learning rate: 1.426E-04 | global batch size: 256 | lm loss: 3.415903E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.525 | TFLOPs: 27.88 | +7: iteration 14730/ 37905 | consumed samples: 3770880 | consumed tokens: 7722762240 | elapsed time per iteration (s): 0.23 | learning rate: 1.425E-04 | global batch size: 256 | lm loss: 3.411482E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.641 | TFLOPs: 28.01 | +7: iteration 14740/ 37905 | consumed samples: 3773440 | consumed tokens: 7728005120 | elapsed time per iteration (s): 0.23 | learning rate: 1.424E-04 | global batch size: 256 | lm loss: 3.449978E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.743 | TFLOPs: 28.09 | +7: iteration 14750/ 37905 | consumed samples: 3776000 | consumed tokens: 7733248000 | elapsed time per iteration (s): 0.23 | learning rate: 1.424E-04 | global batch size: 256 | lm loss: 3.431340E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.045 | TFLOPs: 28.35 | +7: iteration 14760/ 37905 | consumed samples: 3778560 | consumed tokens: 7738490880 | elapsed time per iteration (s): 0.23 | learning rate: 1.423E-04 | global batch size: 256 | lm loss: 3.408019E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.770 | TFLOPs: 28.07 | +7: iteration 14770/ 37905 | consumed samples: 3781120 | consumed tokens: 7743733760 | elapsed time per iteration (s): 0.23 | learning rate: 1.422E-04 | global batch size: 256 | lm loss: 3.414151E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.911 | TFLOPs: 28.28 | +7: iteration 14780/ 37905 | consumed samples: 3783680 | consumed tokens: 7748976640 | elapsed time per iteration (s): 0.23 | learning rate: 1.421E-04 | global batch size: 256 | lm loss: 3.408978E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.967 | TFLOPs: 27.95 | +7: iteration 14790/ 37905 | consumed samples: 3786240 | consumed tokens: 7754219520 | elapsed time per iteration (s): 0.24 | learning rate: 1.421E-04 | global batch size: 256 | lm loss: 3.431356E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1080.463 | TFLOPs: 27.52 | +7: iteration 14800/ 37905 | consumed samples: 3788800 | consumed tokens: 7759462400 | elapsed time per iteration (s): 0.23 | learning rate: 1.420E-04 | global batch size: 256 | lm loss: 3.458704E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.316 | TFLOPs: 28.39 | +7: iteration 14810/ 37905 | consumed samples: 3791360 | consumed tokens: 7764705280 | elapsed time per iteration (s): 0.24 | learning rate: 1.419E-04 | global batch size: 256 | lm loss: 3.412841E+00 | grad norm: 0.381 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1073.293 | TFLOPs: 27.34 | +7: iteration 14820/ 37905 | consumed samples: 3793920 | consumed tokens: 7769948160 | elapsed time per iteration (s): 0.23 | learning rate: 1.419E-04 | global batch size: 256 | lm loss: 3.406655E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.056 | TFLOPs: 28.10 | +7: iteration 14830/ 37905 | consumed samples: 3796480 | consumed tokens: 7775191040 | elapsed time per iteration (s): 0.24 | learning rate: 1.418E-04 | global batch size: 256 | lm loss: 3.419891E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1079.839 | TFLOPs: 27.51 | +7: iteration 14840/ 37905 | consumed samples: 3799040 | consumed tokens: 7780433920 | elapsed time per iteration (s): 0.23 | learning rate: 1.417E-04 | global batch size: 256 | lm loss: 3.401604E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.517 | TFLOPs: 27.93 | +7: iteration 14850/ 37905 | consumed samples: 3801600 | consumed tokens: 7785676800 | elapsed time per iteration (s): 0.23 | learning rate: 1.416E-04 | global batch size: 256 | lm loss: 3.455457E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.771 | TFLOPs: 28.17 | +7: iteration 14860/ 37905 | consumed samples: 3804160 | consumed tokens: 7790919680 | elapsed time per iteration (s): 0.23 | learning rate: 1.416E-04 | global batch size: 256 | lm loss: 3.443401E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.456 | TFLOPs: 27.88 | +7: iteration 14870/ 37905 | consumed samples: 3806720 | consumed tokens: 7796162560 | elapsed time per iteration (s): 0.23 | learning rate: 1.415E-04 | global batch size: 256 | lm loss: 3.402812E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.239 | TFLOPs: 28.39 | +7: iteration 14880/ 37905 | consumed samples: 3809280 | consumed tokens: 7801405440 | elapsed time per iteration (s): 0.25 | learning rate: 1.414E-04 | global batch size: 256 | lm loss: 3.418557E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1027.985 | TFLOPs: 26.19 | +7: iteration 14890/ 37905 | consumed samples: 3811840 | consumed tokens: 7806648320 | elapsed time per iteration (s): 0.24 | learning rate: 1.414E-04 | global batch size: 256 | lm loss: 3.400509E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1077.244 | TFLOPs: 27.44 | +7: iteration 14900/ 37905 | consumed samples: 3814400 | consumed tokens: 7811891200 | elapsed time per iteration (s): 0.23 | learning rate: 1.413E-04 | global batch size: 256 | lm loss: 3.433358E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.570 | TFLOPs: 28.42 | +7: iteration 14910/ 37905 | consumed samples: 3816960 | consumed tokens: 7817134080 | elapsed time per iteration (s): 0.24 | learning rate: 1.412E-04 | global batch size: 256 | lm loss: 3.422243E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1048.975 | TFLOPs: 26.72 | +7: iteration 14920/ 37905 | consumed samples: 3819520 | consumed tokens: 7822376960 | elapsed time per iteration (s): 0.24 | learning rate: 1.412E-04 | global batch size: 256 | lm loss: 3.396747E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1066.840 | TFLOPs: 27.18 | +7: iteration 14930/ 37905 | consumed samples: 3822080 | consumed tokens: 7827619840 | elapsed time per iteration (s): 0.24 | learning rate: 1.411E-04 | global batch size: 256 | lm loss: 3.417171E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1072.873 | TFLOPs: 27.33 | +7: iteration 14940/ 37905 | consumed samples: 3824640 | consumed tokens: 7832862720 | elapsed time per iteration (s): 0.23 | learning rate: 1.410E-04 | global batch size: 256 | lm loss: 3.413306E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.060 | TFLOPs: 28.20 | +7: iteration 14950/ 37905 | consumed samples: 3827200 | consumed tokens: 7838105600 | elapsed time per iteration (s): 0.23 | learning rate: 1.409E-04 | global batch size: 256 | lm loss: 3.438831E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.487 | TFLOPs: 28.32 | +7: iteration 14960/ 37905 | consumed samples: 3829760 | consumed tokens: 7843348480 | elapsed time per iteration (s): 0.23 | learning rate: 1.409E-04 | global batch size: 256 | lm loss: 3.421383E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.205 | TFLOPs: 27.93 | +7: iteration 14970/ 37905 | consumed samples: 3832320 | consumed tokens: 7848591360 | elapsed time per iteration (s): 0.23 | learning rate: 1.408E-04 | global batch size: 256 | lm loss: 3.422680E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.763 | TFLOPs: 28.45 | +7: iteration 14980/ 37905 | consumed samples: 3834880 | consumed tokens: 7853834240 | elapsed time per iteration (s): 0.23 | learning rate: 1.407E-04 | global batch size: 256 | lm loss: 3.395404E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.706 | TFLOPs: 28.47 | +7: iteration 14990/ 37905 | consumed samples: 3837440 | consumed tokens: 7859077120 | elapsed time per iteration (s): 0.23 | learning rate: 1.407E-04 | global batch size: 256 | lm loss: 3.431137E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.139 | TFLOPs: 28.26 | +7: iteration 15000/ 37905 | consumed samples: 3840000 | consumed tokens: 7864320000 | elapsed time per iteration (s): 0.23 | learning rate: 1.406E-04 | global batch size: 256 | lm loss: 3.416246E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.212 | TFLOPs: 27.98 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 15000 | lm loss value: 3.327152E+00 | lm loss PPL: 2.785890E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 15000 to checkpoints_83moscar +0: [2022-11-29 17:54:52,674] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step15000 is begin to save! +0: [2022-11-29 17:54:52,679] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:54:52,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:54:52,752] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:54:52,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:54:52,765] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:54:52,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:54:52,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:54:52,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:54:52,789] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:54:52,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:54:52,800] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:54:52,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:54:52,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:54:52,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:54:52,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:54:52,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:54:52,835] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:54:52,846] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:54:52,846] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:54:52,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:54:52,857] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:54:52,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:54:52,869] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:54:52,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:54:52,870] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step15000/mp_rank_00_model_states.pt +0: [2022-11-29 17:54:52,870] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:54:52,872] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:54:52,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:54:52,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:54:52,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 17:54:52,908] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +1: [2022-11-29 17:54:52,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:54:52,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:54:52,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +6: [2022-11-29 17:54:52,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +1: [2022-11-29 17:54:52,908] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +6: [2022-11-29 17:54:52,908] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +4: [2022-11-29 17:54:52,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:54:52,909] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:54:52,909] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +2: [2022-11-29 17:54:52,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:54:52,909] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:54:52,909] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +3: [2022-11-29 17:54:52,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:54:52,909] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:54:52,909] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +2: [2022-11-29 17:54:52,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:54:52,910] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:54:52,910] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +7: [2022-11-29 17:54:52,910] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:54:52,910] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:54:52,910] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 17:54:52,910] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +5: [2022-11-29 17:54:52,910] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:54:52,910] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:54:52,910] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +5: [2022-11-29 17:54:52,910] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:54:52,910] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +3: [2022-11-29 17:54:52,910] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +5: [2022-11-29 17:54:52,910] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +5: [2022-11-29 17:54:52,910] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +0: [2022-11-29 17:54:52,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:54:52,911] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:54:52,911] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +2: [2022-11-29 17:54:52,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:54:52,911] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:54:52,911] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +7: [2022-11-29 17:54:52,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:54:52,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:54:52,911] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +6: [2022-11-29 17:54:52,911] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:54:52,911] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +7: [2022-11-29 17:54:52,911] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +4: [2022-11-29 17:54:52,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:54:52,911] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:54:52,911] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +0: [2022-11-29 17:54:52,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:54:52,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:54:52,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 17:54:52,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +3: [2022-11-29 17:54:52,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:54:52,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:54:52,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +4: [2022-11-29 17:54:52,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:54:52,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:54:52,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +0: [2022-11-29 17:54:52,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:54:52,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:54:52,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +2: [2022-11-29 17:54:52,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:54:52,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 17:54:52,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +6: [2022-11-29 17:54:52,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:54:52,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:54:52,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:54:52,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +5: [2022-11-29 17:54:52,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:54:52,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +0: [2022-11-29 17:54:52,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 17:54:52,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +1: [2022-11-29 17:54:52,914] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:54:52,914] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +4: [2022-11-29 17:54:52,914] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:54:52,914] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +4: [2022-11-29 17:54:52,914] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:54:52,914] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +7: [2022-11-29 17:54:52,914] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:54:52,914] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 17:54:52,914] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +2: [2022-11-29 17:54:52,914] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:54:52,914] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +0: [2022-11-29 17:54:52,914] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:54:52,914] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +0: [2022-11-29 17:54:52,914] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 17:54:52,914] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +5: [2022-11-29 17:54:52,914] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:54:52,914] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:54:52,914] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +3: [2022-11-29 17:54:52,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:54:52,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +1: [2022-11-29 17:54:52,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:54:52,915] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +1: [2022-11-29 17:54:52,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:54:52,915] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +6: [2022-11-29 17:54:52,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:54:52,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:54:52,915] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +7: [2022-11-29 17:54:52,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:54:52,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 17:54:52,915] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +0: [2022-11-29 17:54:52,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:54:52,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:54:52,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +4: [2022-11-29 17:54:52,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:54:52,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:54:52,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +3: [2022-11-29 17:54:52,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:54:52,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:54:52,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +5: [2022-11-29 17:54:52,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:54:52,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:54:52,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +2: [2022-11-29 17:54:52,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:54:52,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:54:52,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +7: [2022-11-29 17:54:52,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:54:52,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:54:52,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +1: [2022-11-29 17:54:52,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +7: [2022-11-29 17:54:52,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +1: [2022-11-29 17:54:52,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +6: [2022-11-29 17:54:52,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:54:52,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:54:52,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +3: [2022-11-29 17:54:52,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:54:52,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:54:52,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +0: [2022-11-29 17:54:52,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:54:52,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 17:54:52,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +4: [2022-11-29 17:54:52,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:54:52,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:54:52,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +2: [2022-11-29 17:54:52,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:54:52,919] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 17:54:52,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +7: [2022-11-29 17:54:52,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:54:52,919] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 17:54:52,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +1: [2022-11-29 17:54:52,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:54:52,919] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 17:54:52,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +6: [2022-11-29 17:54:52,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:54:52,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:54:52,920] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +5: [2022-11-29 17:54:52,920] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 17:54:52,920] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +6: [2022-11-29 17:54:52,920] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +3: [2022-11-29 17:54:52,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:54:52,920] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:54:52,920] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +1: [2022-11-29 17:54:52,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:54:52,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:54:52,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:54:52,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +2: [2022-11-29 17:54:52,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:54:52,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +4: [2022-11-29 17:54:52,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:54:52,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:54:52,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +4: [2022-11-29 17:54:52,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:54:52,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:54:52,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +7: [2022-11-29 17:54:52,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:54:52,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +6: [2022-11-29 17:54:52,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:54:52,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +6: [2022-11-29 17:54:52,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:54:52,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +1: [2022-11-29 17:54:52,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:54:52,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 17:54:52,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +6: [2022-11-29 17:54:52,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:54:52,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:54:52,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +0: [2022-11-29 17:54:52,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:54:52,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:54:52,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3: [2022-11-29 17:54:52,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +0: [2022-11-29 17:54:52,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +3: [2022-11-29 17:54:52,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +5: [2022-11-29 17:54:52,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:54:52,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:54:52,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +0: [2022-11-29 17:54:52,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +5: [2022-11-29 17:54:52,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +5: [2022-11-29 17:54:52,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:54:52,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +5: [2022-11-29 17:54:52,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step15000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:54:52,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +0: successfully saved checkpoint at iteration 15000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 406.85 +7: iteration 15010/ 37905 | consumed samples: 3842560 | consumed tokens: 7869562880 | elapsed time per iteration (s): 0.28 | learning rate: 1.405E-04 | global batch size: 256 | lm loss: 3.411917E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 926.494 | TFLOPs: 23.60 | +7: iteration 15020/ 37905 | consumed samples: 3845120 | consumed tokens: 7874805760 | elapsed time per iteration (s): 0.23 | learning rate: 1.404E-04 | global batch size: 256 | lm loss: 3.399994E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.111 | TFLOPs: 28.36 | +7: iteration 15030/ 37905 | consumed samples: 3847680 | consumed tokens: 7880048640 | elapsed time per iteration (s): 0.23 | learning rate: 1.404E-04 | global batch size: 256 | lm loss: 3.453541E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.894 | TFLOPs: 28.40 | +7: iteration 15040/ 37905 | consumed samples: 3850240 | consumed tokens: 7885291520 | elapsed time per iteration (s): 0.24 | learning rate: 1.403E-04 | global batch size: 256 | lm loss: 3.410839E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1054.349 | TFLOPs: 26.86 | +7: iteration 15050/ 37905 | consumed samples: 3852800 | consumed tokens: 7890534400 | elapsed time per iteration (s): 0.25 | learning rate: 1.402E-04 | global batch size: 256 | lm loss: 3.433678E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1037.024 | TFLOPs: 26.42 | +7: iteration 15060/ 37905 | consumed samples: 3855360 | consumed tokens: 7895777280 | elapsed time per iteration (s): 0.25 | learning rate: 1.402E-04 | global batch size: 256 | lm loss: 3.436475E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1037.832 | TFLOPs: 26.44 | +7: iteration 15070/ 37905 | consumed samples: 3857920 | consumed tokens: 7901020160 | elapsed time per iteration (s): 0.24 | learning rate: 1.401E-04 | global batch size: 256 | lm loss: 3.432762E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1065.045 | TFLOPs: 27.13 | +7: iteration 15080/ 37905 | consumed samples: 3860480 | consumed tokens: 7906263040 | elapsed time per iteration (s): 0.27 | learning rate: 1.400E-04 | global batch size: 256 | lm loss: 3.402385E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 955.703 | TFLOPs: 24.35 | +7: iteration 15090/ 37905 | consumed samples: 3863040 | consumed tokens: 7911505920 | elapsed time per iteration (s): 0.24 | learning rate: 1.399E-04 | global batch size: 256 | lm loss: 3.413219E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1068.700 | TFLOPs: 27.23 | +7: iteration 15100/ 37905 | consumed samples: 3865600 | consumed tokens: 7916748800 | elapsed time per iteration (s): 0.24 | learning rate: 1.399E-04 | global batch size: 256 | lm loss: 3.405341E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1058.091 | TFLOPs: 26.96 | +7: iteration 15110/ 37905 | consumed samples: 3868160 | consumed tokens: 7921991680 | elapsed time per iteration (s): 0.23 | learning rate: 1.398E-04 | global batch size: 256 | lm loss: 3.429905E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.569 | TFLOPs: 27.91 | +7: iteration 15120/ 37905 | consumed samples: 3870720 | consumed tokens: 7927234560 | elapsed time per iteration (s): 0.25 | learning rate: 1.397E-04 | global batch size: 256 | lm loss: 3.426398E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1018.611 | TFLOPs: 25.95 | +7: iteration 15130/ 37905 | consumed samples: 3873280 | consumed tokens: 7932477440 | elapsed time per iteration (s): 0.28 | learning rate: 1.397E-04 | global batch size: 256 | lm loss: 3.474191E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 921.347 | TFLOPs: 23.47 | +7: iteration 15140/ 37905 | consumed samples: 3875840 | consumed tokens: 7937720320 | elapsed time per iteration (s): 0.28 | learning rate: 1.396E-04 | global batch size: 256 | lm loss: 3.397758E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 906.609 | TFLOPs: 23.10 | +7: iteration 15150/ 37905 | consumed samples: 3878400 | consumed tokens: 7942963200 | elapsed time per iteration (s): 0.23 | learning rate: 1.395E-04 | global batch size: 256 | lm loss: 3.421399E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.925 | TFLOPs: 28.22 | +7: iteration 15160/ 37905 | consumed samples: 3880960 | consumed tokens: 7948206080 | elapsed time per iteration (s): 0.26 | learning rate: 1.395E-04 | global batch size: 256 | lm loss: 3.396216E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 970.680 | TFLOPs: 24.73 | +7: iteration 15170/ 37905 | consumed samples: 3883520 | consumed tokens: 7953448960 | elapsed time per iteration (s): 0.23 | learning rate: 1.394E-04 | global batch size: 256 | lm loss: 3.396340E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.357 | TFLOPs: 27.93 | +7: iteration 15180/ 37905 | consumed samples: 3886080 | consumed tokens: 7958691840 | elapsed time per iteration (s): 0.24 | learning rate: 1.393E-04 | global batch size: 256 | lm loss: 3.415826E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.967 | TFLOPs: 27.72 | +7: iteration 15190/ 37905 | consumed samples: 3888640 | consumed tokens: 7963934720 | elapsed time per iteration (s): 0.24 | learning rate: 1.392E-04 | global batch size: 256 | lm loss: 3.422099E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.226 | TFLOPs: 27.47 | +7: iteration 15200/ 37905 | consumed samples: 3891200 | consumed tokens: 7969177600 | elapsed time per iteration (s): 0.23 | learning rate: 1.392E-04 | global batch size: 256 | lm loss: 3.418526E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.352 | TFLOPs: 28.01 | +7: iteration 15210/ 37905 | consumed samples: 3893760 | consumed tokens: 7974420480 | elapsed time per iteration (s): 0.23 | learning rate: 1.391E-04 | global batch size: 256 | lm loss: 3.395026E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.841 | TFLOPs: 28.32 | +7: iteration 15220/ 37905 | consumed samples: 3896320 | consumed tokens: 7979663360 | elapsed time per iteration (s): 0.23 | learning rate: 1.390E-04 | global batch size: 256 | lm loss: 3.405018E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.571 | TFLOPs: 28.24 | +7: iteration 15230/ 37905 | consumed samples: 3898880 | consumed tokens: 7984906240 | elapsed time per iteration (s): 0.23 | learning rate: 1.390E-04 | global batch size: 256 | lm loss: 3.403395E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.839 | TFLOPs: 28.17 | +7: iteration 15240/ 37905 | consumed samples: 3901440 | consumed tokens: 7990149120 | elapsed time per iteration (s): 0.23 | learning rate: 1.389E-04 | global batch size: 256 | lm loss: 3.424525E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.243 | TFLOPs: 28.33 | +7: iteration 15250/ 37905 | consumed samples: 3904000 | consumed tokens: 7995392000 | elapsed time per iteration (s): 0.23 | learning rate: 1.388E-04 | global batch size: 256 | lm loss: 3.427438E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.496 | TFLOPs: 28.11 | +7: iteration 15260/ 37905 | consumed samples: 3906560 | consumed tokens: 8000634880 | elapsed time per iteration (s): 0.24 | learning rate: 1.387E-04 | global batch size: 256 | lm loss: 3.404588E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.169 | TFLOPs: 27.26 | +7: iteration 15270/ 37905 | consumed samples: 3909120 | consumed tokens: 8005877760 | elapsed time per iteration (s): 0.23 | learning rate: 1.387E-04 | global batch size: 256 | lm loss: 3.436715E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.278 | TFLOPs: 27.95 | +7: iteration 15280/ 37905 | consumed samples: 3911680 | consumed tokens: 8011120640 | elapsed time per iteration (s): 0.23 | learning rate: 1.386E-04 | global batch size: 256 | lm loss: 3.400899E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.045 | TFLOPs: 28.18 | +7: iteration 15290/ 37905 | consumed samples: 3914240 | consumed tokens: 8016363520 | elapsed time per iteration (s): 0.23 | learning rate: 1.385E-04 | global batch size: 256 | lm loss: 3.421606E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.066 | TFLOPs: 28.25 | +7: iteration 15300/ 37905 | consumed samples: 3916800 | consumed tokens: 8021606400 | elapsed time per iteration (s): 0.23 | learning rate: 1.385E-04 | global batch size: 256 | lm loss: 3.435766E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.535 | TFLOPs: 28.01 | +7: iteration 15310/ 37905 | consumed samples: 3919360 | consumed tokens: 8026849280 | elapsed time per iteration (s): 0.23 | learning rate: 1.384E-04 | global batch size: 256 | lm loss: 3.410783E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.972 | TFLOPs: 28.07 | +7: iteration 15320/ 37905 | consumed samples: 3921920 | consumed tokens: 8032092160 | elapsed time per iteration (s): 0.24 | learning rate: 1.383E-04 | global batch size: 256 | lm loss: 3.419519E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1075.815 | TFLOPs: 27.41 | +7: iteration 15330/ 37905 | consumed samples: 3924480 | consumed tokens: 8037335040 | elapsed time per iteration (s): 0.25 | learning rate: 1.382E-04 | global batch size: 256 | lm loss: 3.402291E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1009.805 | TFLOPs: 25.72 | +7: iteration 15340/ 37905 | consumed samples: 3927040 | consumed tokens: 8042577920 | elapsed time per iteration (s): 0.30 | learning rate: 1.382E-04 | global batch size: 256 | lm loss: 3.422645E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 846.974 | TFLOPs: 21.58 | +7: iteration 15350/ 37905 | consumed samples: 3929600 | consumed tokens: 8047820800 | elapsed time per iteration (s): 0.23 | learning rate: 1.381E-04 | global batch size: 256 | lm loss: 3.431066E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.078 | TFLOPs: 27.85 | +7: iteration 15360/ 37905 | consumed samples: 3932160 | consumed tokens: 8053063680 | elapsed time per iteration (s): 0.23 | learning rate: 1.380E-04 | global batch size: 256 | lm loss: 3.400640E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.782 | TFLOPs: 28.48 | +7: iteration 15370/ 37905 | consumed samples: 3934720 | consumed tokens: 8058306560 | elapsed time per iteration (s): 0.23 | learning rate: 1.380E-04 | global batch size: 256 | lm loss: 3.423622E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.295 | TFLOPs: 28.28 | +7: iteration 15380/ 37905 | consumed samples: 3937280 | consumed tokens: 8063549440 | elapsed time per iteration (s): 0.23 | learning rate: 1.379E-04 | global batch size: 256 | lm loss: 3.396944E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.412 | TFLOPs: 28.19 | +7: iteration 15390/ 37905 | consumed samples: 3939840 | consumed tokens: 8068792320 | elapsed time per iteration (s): 0.23 | learning rate: 1.378E-04 | global batch size: 256 | lm loss: 3.452543E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.298 | TFLOPs: 27.88 | +7: iteration 15400/ 37905 | consumed samples: 3942400 | consumed tokens: 8074035200 | elapsed time per iteration (s): 0.23 | learning rate: 1.377E-04 | global batch size: 256 | lm loss: 3.431462E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.788 | TFLOPs: 28.42 | +7: iteration 15410/ 37905 | consumed samples: 3944960 | consumed tokens: 8079278080 | elapsed time per iteration (s): 0.23 | learning rate: 1.377E-04 | global batch size: 256 | lm loss: 3.426557E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.168 | TFLOPs: 28.51 | +7: iteration 15420/ 37905 | consumed samples: 3947520 | consumed tokens: 8084520960 | elapsed time per iteration (s): 0.23 | learning rate: 1.376E-04 | global batch size: 256 | lm loss: 3.412383E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.679 | TFLOPs: 28.17 | +7: iteration 15430/ 37905 | consumed samples: 3950080 | consumed tokens: 8089763840 | elapsed time per iteration (s): 0.26 | learning rate: 1.375E-04 | global batch size: 256 | lm loss: 3.413176E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 967.943 | TFLOPs: 24.66 | +7: iteration 15440/ 37905 | consumed samples: 3952640 | consumed tokens: 8095006720 | elapsed time per iteration (s): 0.23 | learning rate: 1.374E-04 | global batch size: 256 | lm loss: 3.418155E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.383 | TFLOPs: 27.91 | +7: iteration 15450/ 37905 | consumed samples: 3955200 | consumed tokens: 8100249600 | elapsed time per iteration (s): 0.24 | learning rate: 1.374E-04 | global batch size: 256 | lm loss: 3.402654E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1080.976 | TFLOPs: 27.54 | +7: iteration 15460/ 37905 | consumed samples: 3957760 | consumed tokens: 8105492480 | elapsed time per iteration (s): 0.25 | learning rate: 1.373E-04 | global batch size: 256 | lm loss: 3.413241E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1014.346 | TFLOPs: 25.84 | +7: iteration 15470/ 37905 | consumed samples: 3960320 | consumed tokens: 8110735360 | elapsed time per iteration (s): 0.24 | learning rate: 1.372E-04 | global batch size: 256 | lm loss: 3.389999E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.177 | TFLOPs: 26.93 | +7: iteration 15480/ 37905 | consumed samples: 3962880 | consumed tokens: 8115978240 | elapsed time per iteration (s): 0.23 | learning rate: 1.372E-04 | global batch size: 256 | lm loss: 3.402230E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.723 | TFLOPs: 28.12 | +7: iteration 15490/ 37905 | consumed samples: 3965440 | consumed tokens: 8121221120 | elapsed time per iteration (s): 0.23 | learning rate: 1.371E-04 | global batch size: 256 | lm loss: 3.411206E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.975 | TFLOPs: 28.23 | +7: iteration 15500/ 37905 | consumed samples: 3968000 | consumed tokens: 8126464000 | elapsed time per iteration (s): 0.23 | learning rate: 1.370E-04 | global batch size: 256 | lm loss: 3.412622E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.755 | TFLOPs: 28.09 | +7: iteration 15510/ 37905 | consumed samples: 3970560 | consumed tokens: 8131706880 | elapsed time per iteration (s): 0.23 | learning rate: 1.369E-04 | global batch size: 256 | lm loss: 3.427325E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.135 | TFLOPs: 28.26 | +7: iteration 15520/ 37905 | consumed samples: 3973120 | consumed tokens: 8136949760 | elapsed time per iteration (s): 0.23 | learning rate: 1.369E-04 | global batch size: 256 | lm loss: 3.406012E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.835 | TFLOPs: 28.12 | +7: iteration 15530/ 37905 | consumed samples: 3975680 | consumed tokens: 8142192640 | elapsed time per iteration (s): 0.24 | learning rate: 1.368E-04 | global batch size: 256 | lm loss: 3.417846E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1063.884 | TFLOPs: 27.10 | +7: iteration 15540/ 37905 | consumed samples: 3978240 | consumed tokens: 8147435520 | elapsed time per iteration (s): 0.24 | learning rate: 1.367E-04 | global batch size: 256 | lm loss: 3.414899E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1055.538 | TFLOPs: 26.89 | +7: iteration 15550/ 37905 | consumed samples: 3980800 | consumed tokens: 8152678400 | elapsed time per iteration (s): 0.26 | learning rate: 1.367E-04 | global batch size: 256 | lm loss: 3.420456E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 993.306 | TFLOPs: 25.30 | +7: iteration 15560/ 37905 | consumed samples: 3983360 | consumed tokens: 8157921280 | elapsed time per iteration (s): 0.29 | learning rate: 1.366E-04 | global batch size: 256 | lm loss: 3.441283E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 884.798 | TFLOPs: 22.54 | +7: iteration 15570/ 37905 | consumed samples: 3985920 | consumed tokens: 8163164160 | elapsed time per iteration (s): 0.23 | learning rate: 1.365E-04 | global batch size: 256 | lm loss: 3.411951E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.490 | TFLOPs: 28.04 | +7: iteration 15580/ 37905 | consumed samples: 3988480 | consumed tokens: 8168407040 | elapsed time per iteration (s): 0.25 | learning rate: 1.364E-04 | global batch size: 256 | lm loss: 3.403432E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1040.248 | TFLOPs: 26.50 | +7: iteration 15590/ 37905 | consumed samples: 3991040 | consumed tokens: 8173649920 | elapsed time per iteration (s): 0.24 | learning rate: 1.364E-04 | global batch size: 256 | lm loss: 3.455992E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.686 | TFLOPs: 27.66 | +7: iteration 15600/ 37905 | consumed samples: 3993600 | consumed tokens: 8178892800 | elapsed time per iteration (s): 0.23 | learning rate: 1.363E-04 | global batch size: 256 | lm loss: 3.396156E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.647 | TFLOPs: 28.24 | +7: iteration 15610/ 37905 | consumed samples: 3996160 | consumed tokens: 8184135680 | elapsed time per iteration (s): 0.23 | learning rate: 1.362E-04 | global batch size: 256 | lm loss: 3.397644E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.742 | TFLOPs: 27.86 | +7: iteration 15620/ 37905 | consumed samples: 3998720 | consumed tokens: 8189378560 | elapsed time per iteration (s): 0.23 | learning rate: 1.362E-04 | global batch size: 256 | lm loss: 3.428821E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.983 | TFLOPs: 28.05 | +7: iteration 15630/ 37905 | consumed samples: 4001280 | consumed tokens: 8194621440 | elapsed time per iteration (s): 0.25 | learning rate: 1.361E-04 | global batch size: 256 | lm loss: 3.419477E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1039.258 | TFLOPs: 26.48 | +7: iteration 15640/ 37905 | consumed samples: 4003840 | consumed tokens: 8199864320 | elapsed time per iteration (s): 0.25 | learning rate: 1.360E-04 | global batch size: 256 | lm loss: 3.418646E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1032.918 | TFLOPs: 26.31 | +7: iteration 15650/ 37905 | consumed samples: 4006400 | consumed tokens: 8205107200 | elapsed time per iteration (s): 0.23 | learning rate: 1.359E-04 | global batch size: 256 | lm loss: 3.411129E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.360 | TFLOPs: 28.18 | +7: iteration 15660/ 37905 | consumed samples: 4008960 | consumed tokens: 8210350080 | elapsed time per iteration (s): 0.23 | learning rate: 1.359E-04 | global batch size: 256 | lm loss: 3.404762E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.356 | TFLOPs: 28.36 | +7: iteration 15670/ 37905 | consumed samples: 4011520 | consumed tokens: 8215592960 | elapsed time per iteration (s): 0.23 | learning rate: 1.358E-04 | global batch size: 256 | lm loss: 3.417647E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.419 | TFLOPs: 28.08 | +7: iteration 15680/ 37905 | consumed samples: 4014080 | consumed tokens: 8220835840 | elapsed time per iteration (s): 0.23 | learning rate: 1.357E-04 | global batch size: 256 | lm loss: 3.408613E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.853 | TFLOPs: 28.45 | +7: iteration 15690/ 37905 | consumed samples: 4016640 | consumed tokens: 8226078720 | elapsed time per iteration (s): 0.23 | learning rate: 1.356E-04 | global batch size: 256 | lm loss: 3.416613E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.559 | TFLOPs: 28.42 | +7: iteration 15700/ 37905 | consumed samples: 4019200 | consumed tokens: 8231321600 | elapsed time per iteration (s): 0.25 | learning rate: 1.356E-04 | global batch size: 256 | lm loss: 3.417297E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1019.043 | TFLOPs: 25.96 | +7: iteration 15710/ 37905 | consumed samples: 4021760 | consumed tokens: 8236564480 | elapsed time per iteration (s): 0.23 | learning rate: 1.355E-04 | global batch size: 256 | lm loss: 3.415776E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.876 | TFLOPs: 28.25 | +7: iteration 15720/ 37905 | consumed samples: 4024320 | consumed tokens: 8241807360 | elapsed time per iteration (s): 0.23 | learning rate: 1.354E-04 | global batch size: 256 | lm loss: 3.408831E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.344 | TFLOPs: 28.34 | +7: iteration 15730/ 37905 | consumed samples: 4026880 | consumed tokens: 8247050240 | elapsed time per iteration (s): 0.23 | learning rate: 1.354E-04 | global batch size: 256 | lm loss: 3.424857E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.125 | TFLOPs: 27.95 | +7: iteration 15740/ 37905 | consumed samples: 4029440 | consumed tokens: 8252293120 | elapsed time per iteration (s): 0.23 | learning rate: 1.353E-04 | global batch size: 256 | lm loss: 3.448978E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.654 | TFLOPs: 28.24 | +7: iteration 15750/ 37905 | consumed samples: 4032000 | consumed tokens: 8257536000 | elapsed time per iteration (s): 0.23 | learning rate: 1.352E-04 | global batch size: 256 | lm loss: 3.424479E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.115 | TFLOPs: 28.20 | +7: iteration 15760/ 37905 | consumed samples: 4034560 | consumed tokens: 8262778880 | elapsed time per iteration (s): 0.23 | learning rate: 1.351E-04 | global batch size: 256 | lm loss: 3.426553E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.934 | TFLOPs: 28.30 | +7: iteration 15770/ 37905 | consumed samples: 4037120 | consumed tokens: 8268021760 | elapsed time per iteration (s): 0.24 | learning rate: 1.351E-04 | global batch size: 256 | lm loss: 3.403197E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.527 | TFLOPs: 27.65 | +7: iteration 15780/ 37905 | consumed samples: 4039680 | consumed tokens: 8273264640 | elapsed time per iteration (s): 0.24 | learning rate: 1.350E-04 | global batch size: 256 | lm loss: 3.408185E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1081.565 | TFLOPs: 27.55 | +7: iteration 15790/ 37905 | consumed samples: 4042240 | consumed tokens: 8278507520 | elapsed time per iteration (s): 0.28 | learning rate: 1.349E-04 | global batch size: 256 | lm loss: 3.394512E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 912.832 | TFLOPs: 23.25 | +7: iteration 15800/ 37905 | consumed samples: 4044800 | consumed tokens: 8283750400 | elapsed time per iteration (s): 0.23 | learning rate: 1.349E-04 | global batch size: 256 | lm loss: 3.407641E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.819 | TFLOPs: 28.35 | +7: iteration 15810/ 37905 | consumed samples: 4047360 | consumed tokens: 8288993280 | elapsed time per iteration (s): 0.23 | learning rate: 1.348E-04 | global batch size: 256 | lm loss: 3.396859E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.033 | TFLOPs: 28.28 | +7: iteration 15820/ 37905 | consumed samples: 4049920 | consumed tokens: 8294236160 | elapsed time per iteration (s): 0.23 | learning rate: 1.347E-04 | global batch size: 256 | lm loss: 3.405900E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.397 | TFLOPs: 28.08 | +7: iteration 15830/ 37905 | consumed samples: 4052480 | consumed tokens: 8299479040 | elapsed time per iteration (s): 0.23 | learning rate: 1.346E-04 | global batch size: 256 | lm loss: 3.424715E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.219 | TFLOPs: 28.41 | +7: iteration 15840/ 37905 | consumed samples: 4055040 | consumed tokens: 8304721920 | elapsed time per iteration (s): 0.23 | learning rate: 1.346E-04 | global batch size: 256 | lm loss: 3.418829E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.286 | TFLOPs: 27.83 | +7: iteration 15850/ 37905 | consumed samples: 4057600 | consumed tokens: 8309964800 | elapsed time per iteration (s): 0.23 | learning rate: 1.345E-04 | global batch size: 256 | lm loss: 3.420877E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.511 | TFLOPs: 28.26 | +7: iteration 15860/ 37905 | consumed samples: 4060160 | consumed tokens: 8315207680 | elapsed time per iteration (s): 0.23 | learning rate: 1.344E-04 | global batch size: 256 | lm loss: 3.421271E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.826 | TFLOPs: 27.79 | +7: iteration 15870/ 37905 | consumed samples: 4062720 | consumed tokens: 8320450560 | elapsed time per iteration (s): 0.23 | learning rate: 1.343E-04 | global batch size: 256 | lm loss: 3.405474E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.347 | TFLOPs: 28.03 | +7: iteration 15880/ 37905 | consumed samples: 4065280 | consumed tokens: 8325693440 | elapsed time per iteration (s): 0.23 | learning rate: 1.343E-04 | global batch size: 256 | lm loss: 3.435862E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.500 | TFLOPs: 28.06 | +7: iteration 15890/ 37905 | consumed samples: 4067840 | consumed tokens: 8330936320 | elapsed time per iteration (s): 0.25 | learning rate: 1.342E-04 | global batch size: 256 | lm loss: 3.426520E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1020.211 | TFLOPs: 25.99 | +7: iteration 15900/ 37905 | consumed samples: 4070400 | consumed tokens: 8336179200 | elapsed time per iteration (s): 0.23 | learning rate: 1.341E-04 | global batch size: 256 | lm loss: 3.414879E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.391 | TFLOPs: 28.21 | +7: iteration 15910/ 37905 | consumed samples: 4072960 | consumed tokens: 8341422080 | elapsed time per iteration (s): 0.23 | learning rate: 1.341E-04 | global batch size: 256 | lm loss: 3.432857E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.856 | TFLOPs: 27.99 | +7: iteration 15920/ 37905 | consumed samples: 4075520 | consumed tokens: 8346664960 | elapsed time per iteration (s): 0.24 | learning rate: 1.340E-04 | global batch size: 256 | lm loss: 3.426696E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1061.260 | TFLOPs: 27.04 | +7: iteration 15930/ 37905 | consumed samples: 4078080 | consumed tokens: 8351907840 | elapsed time per iteration (s): 0.23 | learning rate: 1.339E-04 | global batch size: 256 | lm loss: 3.402703E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.094 | TFLOPs: 28.41 | +7: iteration 15940/ 37905 | consumed samples: 4080640 | consumed tokens: 8357150720 | elapsed time per iteration (s): 0.27 | learning rate: 1.338E-04 | global batch size: 256 | lm loss: 3.448230E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 949.363 | TFLOPs: 24.19 | +7: iteration 15950/ 37905 | consumed samples: 4083200 | consumed tokens: 8362393600 | elapsed time per iteration (s): 0.26 | learning rate: 1.338E-04 | global batch size: 256 | lm loss: 3.399756E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 995.715 | TFLOPs: 25.37 | +7: iteration 15960/ 37905 | consumed samples: 4085760 | consumed tokens: 8367636480 | elapsed time per iteration (s): 0.27 | learning rate: 1.337E-04 | global batch size: 256 | lm loss: 3.430101E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 958.611 | TFLOPs: 24.42 | +7: iteration 15970/ 37905 | consumed samples: 4088320 | consumed tokens: 8372879360 | elapsed time per iteration (s): 0.24 | learning rate: 1.336E-04 | global batch size: 256 | lm loss: 3.415489E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1082.121 | TFLOPs: 27.57 | +7: iteration 15980/ 37905 | consumed samples: 4090880 | consumed tokens: 8378122240 | elapsed time per iteration (s): 0.29 | learning rate: 1.335E-04 | global batch size: 256 | lm loss: 3.386082E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 884.873 | TFLOPs: 22.54 | +7: iteration 15990/ 37905 | consumed samples: 4093440 | consumed tokens: 8383365120 | elapsed time per iteration (s): 0.24 | learning rate: 1.335E-04 | global batch size: 256 | lm loss: 3.383108E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1047.793 | TFLOPs: 26.69 | +0: [2022-11-29 17:58:53,715] [INFO] [logging.py:68:log_dist] [Rank 0] step=16000, skipped=0, lr=[0.00013340211513853558, 0.00013340211513853558, 0.00013340211513853558], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 16000/ 37905 | consumed samples: 4096000 | consumed tokens: 8388608000 | elapsed time per iteration (s): 0.29 | learning rate: 1.334E-04 | global batch size: 256 | lm loss: 3.431358E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 896.245 | TFLOPs: 22.83 | +0: steps: 16000 loss: 3.3916 iter time (s): 0.238 samples/sec: 1074.245 +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 16000 | lm loss value: 3.262324E+00 | lm loss PPL: 2.611016E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 16000 to checkpoints_83moscar +0: [2022-11-29 17:58:53,807] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step16000 is begin to save! +0: [2022-11-29 17:58:53,811] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/layer_01-model_00-model_states.pt... +0: [2022-11-29 17:58:53,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/layer_01-model_00-model_states.pt. +0: [2022-11-29 17:58:53,893] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/layer_03-model_00-model_states.pt... +0: [2022-11-29 17:58:53,905] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/layer_03-model_00-model_states.pt. +0: [2022-11-29 17:58:53,905] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/layer_04-model_00-model_states.pt... +0: [2022-11-29 17:58:53,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/layer_04-model_00-model_states.pt. +0: [2022-11-29 17:58:53,917] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/layer_05-model_00-model_states.pt... +0: [2022-11-29 17:58:53,928] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/layer_05-model_00-model_states.pt. +0: [2022-11-29 17:58:53,929] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/layer_06-model_00-model_states.pt... +0: [2022-11-29 17:58:53,941] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/layer_06-model_00-model_states.pt. +0: [2022-11-29 17:58:53,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/layer_07-model_00-model_states.pt... +0: [2022-11-29 17:58:53,953] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/layer_07-model_00-model_states.pt. +0: [2022-11-29 17:58:53,953] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/layer_08-model_00-model_states.pt... +0: [2022-11-29 17:58:53,964] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/layer_08-model_00-model_states.pt. +0: [2022-11-29 17:58:53,964] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/layer_09-model_00-model_states.pt... +0: [2022-11-29 17:58:53,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/layer_09-model_00-model_states.pt. +0: [2022-11-29 17:58:53,976] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/layer_10-model_00-model_states.pt... +0: [2022-11-29 17:58:53,987] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/layer_10-model_00-model_states.pt. +0: [2022-11-29 17:58:53,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/layer_11-model_00-model_states.pt... +0: [2022-11-29 17:58:53,998] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/layer_11-model_00-model_states.pt. +0: [2022-11-29 17:58:53,998] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/layer_12-model_00-model_states.pt... +0: [2022-11-29 17:58:54,010] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/layer_12-model_00-model_states.pt. +0: [2022-11-29 17:58:54,010] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/layer_14-model_00-model_states.pt... +0: [2022-11-29 17:58:54,011] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/layer_14-model_00-model_states.pt. +0: [2022-11-29 17:58:54,011] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step16000/mp_rank_00_model_states.pt +0: [2022-11-29 17:58:54,011] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/mp_rank_00_model_states.pt... +0: [2022-11-29 17:58:54,013] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/mp_rank_00_model_states.pt. +0: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +4: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +5: [2022-11-29 17:58:54,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +2: [2022-11-29 17:58:54,050] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:58:54,050] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:58:54,050] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 17:58:54,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +5: [2022-11-29 17:58:54,050] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:58:54,050] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 17:58:54,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +1: [2022-11-29 17:58:54,051] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:58:54,051] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 17:58:54,051] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +4: [2022-11-29 17:58:54,051] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:58:54,051] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 17:58:54,051] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +5: [2022-11-29 17:58:54,052] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:58:54,052] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 17:58:54,052] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +2: [2022-11-29 17:58:54,052] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:58:54,052] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 17:58:54,052] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +0: [2022-11-29 17:58:54,052] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +4: [2022-11-29 17:58:54,052] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:58:54,052] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +4: [2022-11-29 17:58:54,052] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 17:58:54,052] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +2: [2022-11-29 17:58:54,053] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:58:54,053] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 17:58:54,053] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +0: [2022-11-29 17:58:54,053] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:58:54,053] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 17:58:54,053] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +4: [2022-11-29 17:58:54,053] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:58:54,053] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 17:58:54,053] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +7: [2022-11-29 17:58:54,053] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:58:54,053] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:58:54,053] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +0: [2022-11-29 17:58:54,053] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +7: [2022-11-29 17:58:54,053] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:58:54,053] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +7: [2022-11-29 17:58:54,053] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +0: [2022-11-29 17:58:54,053] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +7: [2022-11-29 17:58:54,053] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +1: [2022-11-29 17:58:54,053] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:58:54,054] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +7: [2022-11-29 17:58:54,054] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:58:54,054] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +7: [2022-11-29 17:58:54,054] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 17:58:54,054] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +0: [2022-11-29 17:58:54,054] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:58:54,054] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 17:58:54,054] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +4: [2022-11-29 17:58:54,054] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:58:54,054] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 17:58:54,054] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +5: [2022-11-29 17:58:54,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:58:54,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 17:58:54,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +5: [2022-11-29 17:58:54,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:58:54,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +2: [2022-11-29 17:58:54,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:58:54,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:58:54,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +2: [2022-11-29 17:58:54,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +1: [2022-11-29 17:58:54,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:58:54,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +2: [2022-11-29 17:58:54,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +1: [2022-11-29 17:58:54,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 17:58:54,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +1: [2022-11-29 17:58:54,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +2: [2022-11-29 17:58:54,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:58:54,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 17:58:54,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +7: [2022-11-29 17:58:54,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:58:54,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 17:58:54,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +0: [2022-11-29 17:58:54,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:58:54,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +4: [2022-11-29 17:58:54,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:58:54,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +4: [2022-11-29 17:58:54,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 17:58:54,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +2: [2022-11-29 17:58:54,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:58:54,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 17:58:54,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +5: [2022-11-29 17:58:54,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:58:54,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 17:58:54,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +0: [2022-11-29 17:58:54,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:58:54,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 17:58:54,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +1: [2022-11-29 17:58:54,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:58:54,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +5: [2022-11-29 17:58:54,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:58:54,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 17:58:54,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +1: [2022-11-29 17:58:54,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +4: [2022-11-29 17:58:54,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:58:54,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 17:58:54,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +7: [2022-11-29 17:58:54,058] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:58:54,058] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:58:54,058] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:58:54,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +1: [2022-11-29 17:58:54,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +7: [2022-11-29 17:58:54,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +2: [2022-11-29 17:58:54,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +1: [2022-11-29 17:58:54,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +2: [2022-11-29 17:58:54,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +4: [2022-11-29 17:58:54,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:58:54,059] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 17:58:54,059] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +7: [2022-11-29 17:58:54,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:58:54,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 17:58:54,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:58:54,059] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +1: [2022-11-29 17:58:54,059] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 17:58:54,059] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +7: [2022-11-29 17:58:54,059] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +1: [2022-11-29 17:58:54,059] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +1: [2022-11-29 17:58:54,059] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +2: [2022-11-29 17:58:54,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 17:58:54,060] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 17:58:54,060] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +5: [2022-11-29 17:58:54,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:58:54,060] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 17:58:54,060] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +5: [2022-11-29 17:58:54,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 17:58:54,060] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 17:58:54,060] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +7: [2022-11-29 17:58:54,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:58:54,060] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 17:58:54,060] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +0: [2022-11-29 17:58:54,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:58:54,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +7: [2022-11-29 17:58:54,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +0: [2022-11-29 17:58:54,060] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 17:58:54,060] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +7: [2022-11-29 17:58:54,060] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +0: [2022-11-29 17:58:54,060] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +0: [2022-11-29 17:58:54,060] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +7: [2022-11-29 17:58:54,060] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +4: [2022-11-29 17:58:54,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 17:58:54,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 17:58:54,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +3: [2022-11-29 17:58:54,069] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:58:54,069] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 17:58:54,069] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +6: [2022-11-29 17:58:54,069] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:58:54,069] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:58:54,069] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 17:58:54,069] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +3: [2022-11-29 17:58:54,069] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 17:58:54,069] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:58:54,069] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +3: [2022-11-29 17:58:54,069] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 17:58:54,069] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +6: [2022-11-29 17:58:54,069] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:58:54,069] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 17:58:54,069] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +6: [2022-11-29 17:58:54,069] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:58:54,069] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:58:54,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 17:58:54,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 17:58:54,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:58:54,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +6: [2022-11-29 17:58:54,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +6: [2022-11-29 17:58:54,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 17:58:54,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +6: [2022-11-29 17:58:54,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:58:54,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:58:54,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:58:54,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 17:58:54,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +3: [2022-11-29 17:58:54,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 17:58:54,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 17:58:54,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +3: [2022-11-29 17:58:54,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +3: [2022-11-29 17:58:54,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:58:54,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 17:58:54,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +6: [2022-11-29 17:58:54,071] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:58:54,071] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 17:58:54,071] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +6: [2022-11-29 17:58:54,071] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 17:58:54,071] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 17:58:54,071] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +3: [2022-11-29 17:58:54,071] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:58:54,071] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 17:58:54,071] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 17:58:54,072] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +3: [2022-11-29 17:58:54,072] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step16000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 17:58:54,072] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +0: successfully saved checkpoint at iteration 16000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 270.55 +7: iteration 16010/ 37905 | consumed samples: 4098560 | consumed tokens: 8393850880 | elapsed time per iteration (s): 0.28 | learning rate: 1.333E-04 | global batch size: 256 | lm loss: 3.417294E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 924.032 | TFLOPs: 23.54 | +7: iteration 16020/ 37905 | consumed samples: 4101120 | consumed tokens: 8399093760 | elapsed time per iteration (s): 0.26 | learning rate: 1.333E-04 | global batch size: 256 | lm loss: 3.389956E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1003.675 | TFLOPs: 25.57 | +7: iteration 16030/ 37905 | consumed samples: 4103680 | consumed tokens: 8404336640 | elapsed time per iteration (s): 0.24 | learning rate: 1.332E-04 | global batch size: 256 | lm loss: 3.394565E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.295 | TFLOPs: 27.67 | +7: iteration 16040/ 37905 | consumed samples: 4106240 | consumed tokens: 8409579520 | elapsed time per iteration (s): 0.25 | learning rate: 1.331E-04 | global batch size: 256 | lm loss: 3.395482E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1017.561 | TFLOPs: 25.92 | +7: iteration 16050/ 37905 | consumed samples: 4108800 | consumed tokens: 8414822400 | elapsed time per iteration (s): 0.23 | learning rate: 1.330E-04 | global batch size: 256 | lm loss: 3.394068E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.219 | TFLOPs: 27.95 | +7: iteration 16060/ 37905 | consumed samples: 4111360 | consumed tokens: 8420065280 | elapsed time per iteration (s): 0.24 | learning rate: 1.330E-04 | global batch size: 256 | lm loss: 3.392789E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1072.031 | TFLOPs: 27.31 | +7: iteration 16070/ 37905 | consumed samples: 4113920 | consumed tokens: 8425308160 | elapsed time per iteration (s): 0.23 | learning rate: 1.329E-04 | global batch size: 256 | lm loss: 3.423614E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.492 | TFLOPs: 27.98 | +7: iteration 16080/ 37905 | consumed samples: 4116480 | consumed tokens: 8430551040 | elapsed time per iteration (s): 0.25 | learning rate: 1.328E-04 | global batch size: 256 | lm loss: 3.415830E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1030.290 | TFLOPs: 26.25 | +7: iteration 16090/ 37905 | consumed samples: 4119040 | consumed tokens: 8435793920 | elapsed time per iteration (s): 0.24 | learning rate: 1.327E-04 | global batch size: 256 | lm loss: 3.390541E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.521 | TFLOPs: 27.27 | +7: iteration 16100/ 37905 | consumed samples: 4121600 | consumed tokens: 8441036800 | elapsed time per iteration (s): 0.26 | learning rate: 1.327E-04 | global batch size: 256 | lm loss: 3.393908E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 970.093 | TFLOPs: 24.71 | +7: iteration 16110/ 37905 | consumed samples: 4124160 | consumed tokens: 8446279680 | elapsed time per iteration (s): 0.24 | learning rate: 1.326E-04 | global batch size: 256 | lm loss: 3.386868E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1081.821 | TFLOPs: 27.56 | +7: iteration 16120/ 37905 | consumed samples: 4126720 | consumed tokens: 8451522560 | elapsed time per iteration (s): 0.23 | learning rate: 1.325E-04 | global batch size: 256 | lm loss: 3.423333E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.182 | TFLOPs: 28.36 | +7: iteration 16130/ 37905 | consumed samples: 4129280 | consumed tokens: 8456765440 | elapsed time per iteration (s): 0.49 | learning rate: 1.325E-04 | global batch size: 256 | lm loss: 3.396197E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 525.699 | TFLOPs: 13.39 | +7: iteration 16140/ 37905 | consumed samples: 4131840 | consumed tokens: 8462008320 | elapsed time per iteration (s): 0.23 | learning rate: 1.324E-04 | global batch size: 256 | lm loss: 3.404330E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.317 | TFLOPs: 28.23 | +7: iteration 16150/ 37905 | consumed samples: 4134400 | consumed tokens: 8467251200 | elapsed time per iteration (s): 0.25 | learning rate: 1.323E-04 | global batch size: 256 | lm loss: 3.402722E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1024.117 | TFLOPs: 26.09 | +7: iteration 16160/ 37905 | consumed samples: 4136960 | consumed tokens: 8472494080 | elapsed time per iteration (s): 0.24 | learning rate: 1.322E-04 | global batch size: 256 | lm loss: 3.398413E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1068.091 | TFLOPs: 27.21 | +7: iteration 16170/ 37905 | consumed samples: 4139520 | consumed tokens: 8477736960 | elapsed time per iteration (s): 0.45 | learning rate: 1.322E-04 | global batch size: 256 | lm loss: 3.402999E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 575.155 | TFLOPs: 14.65 | +7: iteration 16180/ 37905 | consumed samples: 4142080 | consumed tokens: 8482979840 | elapsed time per iteration (s): 0.29 | learning rate: 1.321E-04 | global batch size: 256 | lm loss: 3.388724E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 867.970 | TFLOPs: 22.11 | +7: iteration 16190/ 37905 | consumed samples: 4144640 | consumed tokens: 8488222720 | elapsed time per iteration (s): 0.24 | learning rate: 1.320E-04 | global batch size: 256 | lm loss: 3.371902E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1053.290 | TFLOPs: 26.83 | +7: iteration 16200/ 37905 | consumed samples: 4147200 | consumed tokens: 8493465600 | elapsed time per iteration (s): 0.23 | learning rate: 1.319E-04 | global batch size: 256 | lm loss: 3.411348E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.457 | TFLOPs: 28.39 | +7: iteration 16210/ 37905 | consumed samples: 4149760 | consumed tokens: 8498708480 | elapsed time per iteration (s): 0.23 | learning rate: 1.319E-04 | global batch size: 256 | lm loss: 3.439544E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.514 | TFLOPs: 27.81 | +7: iteration 16220/ 37905 | consumed samples: 4152320 | consumed tokens: 8503951360 | elapsed time per iteration (s): 0.23 | learning rate: 1.318E-04 | global batch size: 256 | lm loss: 3.421189E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.984 | TFLOPs: 28.38 | +7: iteration 16230/ 37905 | consumed samples: 4154880 | consumed tokens: 8509194240 | elapsed time per iteration (s): 0.23 | learning rate: 1.317E-04 | global batch size: 256 | lm loss: 3.413283E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.212 | TFLOPs: 28.26 | +7: iteration 16240/ 37905 | consumed samples: 4157440 | consumed tokens: 8514437120 | elapsed time per iteration (s): 0.23 | learning rate: 1.317E-04 | global batch size: 256 | lm loss: 3.409713E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.562 | TFLOPs: 28.34 | +7: iteration 16250/ 37905 | consumed samples: 4160000 | consumed tokens: 8519680000 | elapsed time per iteration (s): 0.23 | learning rate: 1.316E-04 | global batch size: 256 | lm loss: 3.402594E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.741 | TFLOPs: 28.55 | +7: iteration 16260/ 37905 | consumed samples: 4162560 | consumed tokens: 8524922880 | elapsed time per iteration (s): 0.23 | learning rate: 1.315E-04 | global batch size: 256 | lm loss: 3.423489E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.591 | TFLOPs: 28.32 | +7: iteration 16270/ 37905 | consumed samples: 4165120 | consumed tokens: 8530165760 | elapsed time per iteration (s): 0.23 | learning rate: 1.314E-04 | global batch size: 256 | lm loss: 3.401044E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.924 | TFLOPs: 28.48 | +7: iteration 16280/ 37905 | consumed samples: 4167680 | consumed tokens: 8535408640 | elapsed time per iteration (s): 0.23 | learning rate: 1.314E-04 | global batch size: 256 | lm loss: 3.394369E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.125 | TFLOPs: 28.51 | +7: iteration 16290/ 37905 | consumed samples: 4170240 | consumed tokens: 8540651520 | elapsed time per iteration (s): 0.23 | learning rate: 1.313E-04 | global batch size: 256 | lm loss: 3.412236E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.585 | TFLOPs: 28.45 | +7: iteration 16300/ 37905 | consumed samples: 4172800 | consumed tokens: 8545894400 | elapsed time per iteration (s): 0.23 | learning rate: 1.312E-04 | global batch size: 256 | lm loss: 3.418280E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.488 | TFLOPs: 28.06 | +7: iteration 16310/ 37905 | consumed samples: 4175360 | consumed tokens: 8551137280 | elapsed time per iteration (s): 0.25 | learning rate: 1.311E-04 | global batch size: 256 | lm loss: 3.385467E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1039.761 | TFLOPs: 26.49 | +7: iteration 16320/ 37905 | consumed samples: 4177920 | consumed tokens: 8556380160 | elapsed time per iteration (s): 0.25 | learning rate: 1.311E-04 | global batch size: 256 | lm loss: 3.409928E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1022.518 | TFLOPs: 26.05 | +7: iteration 16330/ 37905 | consumed samples: 4180480 | consumed tokens: 8561623040 | elapsed time per iteration (s): 0.24 | learning rate: 1.310E-04 | global batch size: 256 | lm loss: 3.369286E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.268 | TFLOPs: 27.67 | +7: iteration 16340/ 37905 | consumed samples: 4183040 | consumed tokens: 8566865920 | elapsed time per iteration (s): 0.35 | learning rate: 1.309E-04 | global batch size: 256 | lm loss: 3.396962E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 732.898 | TFLOPs: 18.67 | +7: iteration 16350/ 37905 | consumed samples: 4185600 | consumed tokens: 8572108800 | elapsed time per iteration (s): 0.24 | learning rate: 1.308E-04 | global batch size: 256 | lm loss: 3.430915E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1066.405 | TFLOPs: 27.17 | +7: iteration 16360/ 37905 | consumed samples: 4188160 | consumed tokens: 8577351680 | elapsed time per iteration (s): 0.26 | learning rate: 1.308E-04 | global batch size: 256 | lm loss: 3.408540E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 991.614 | TFLOPs: 25.26 | +7: iteration 16370/ 37905 | consumed samples: 4190720 | consumed tokens: 8582594560 | elapsed time per iteration (s): 0.24 | learning rate: 1.307E-04 | global batch size: 256 | lm loss: 3.434145E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.031 | TFLOPs: 27.46 | +7: iteration 16380/ 37905 | consumed samples: 4193280 | consumed tokens: 8587837440 | elapsed time per iteration (s): 0.23 | learning rate: 1.306E-04 | global batch size: 256 | lm loss: 3.392384E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.637 | TFLOPs: 27.94 | +7: iteration 16390/ 37905 | consumed samples: 4195840 | consumed tokens: 8593080320 | elapsed time per iteration (s): 0.26 | learning rate: 1.306E-04 | global batch size: 256 | lm loss: 3.406327E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 975.267 | TFLOPs: 24.85 | +7: iteration 16400/ 37905 | consumed samples: 4198400 | consumed tokens: 8598323200 | elapsed time per iteration (s): 0.23 | learning rate: 1.305E-04 | global batch size: 256 | lm loss: 3.371078E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.710 | TFLOPs: 28.35 | +7: iteration 16410/ 37905 | consumed samples: 4200960 | consumed tokens: 8603566080 | elapsed time per iteration (s): 0.23 | learning rate: 1.304E-04 | global batch size: 256 | lm loss: 3.429462E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.146 | TFLOPs: 28.43 | +7: iteration 16420/ 37905 | consumed samples: 4203520 | consumed tokens: 8608808960 | elapsed time per iteration (s): 0.26 | learning rate: 1.303E-04 | global batch size: 256 | lm loss: 3.403950E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 991.059 | TFLOPs: 25.25 | +7: iteration 16430/ 37905 | consumed samples: 4206080 | consumed tokens: 8614051840 | elapsed time per iteration (s): 0.23 | learning rate: 1.303E-04 | global batch size: 256 | lm loss: 3.390680E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.119 | TFLOPs: 28.51 | +7: iteration 16440/ 37905 | consumed samples: 4208640 | consumed tokens: 8619294720 | elapsed time per iteration (s): 0.28 | learning rate: 1.302E-04 | global batch size: 256 | lm loss: 3.378571E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 901.689 | TFLOPs: 22.97 | +7: iteration 16450/ 37905 | consumed samples: 4211200 | consumed tokens: 8624537600 | elapsed time per iteration (s): 0.25 | learning rate: 1.301E-04 | global batch size: 256 | lm loss: 3.392342E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1037.582 | TFLOPs: 26.43 | +7: iteration 16460/ 37905 | consumed samples: 4213760 | consumed tokens: 8629780480 | elapsed time per iteration (s): 0.29 | learning rate: 1.300E-04 | global batch size: 256 | lm loss: 3.401759E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 872.609 | TFLOPs: 22.23 | +7: iteration 16470/ 37905 | consumed samples: 4216320 | consumed tokens: 8635023360 | elapsed time per iteration (s): 0.25 | learning rate: 1.300E-04 | global batch size: 256 | lm loss: 3.422460E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1019.054 | TFLOPs: 25.96 | +7: iteration 16480/ 37905 | consumed samples: 4218880 | consumed tokens: 8640266240 | elapsed time per iteration (s): 0.25 | learning rate: 1.299E-04 | global batch size: 256 | lm loss: 3.398472E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1042.492 | TFLOPs: 26.56 | +7: iteration 16490/ 37905 | consumed samples: 4221440 | consumed tokens: 8645509120 | elapsed time per iteration (s): 0.24 | learning rate: 1.298E-04 | global batch size: 256 | lm loss: 3.395678E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.875 | TFLOPs: 27.69 | +7: iteration 16500/ 37905 | consumed samples: 4224000 | consumed tokens: 8650752000 | elapsed time per iteration (s): 0.32 | learning rate: 1.297E-04 | global batch size: 256 | lm loss: 3.404141E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 795.583 | TFLOPs: 20.27 | +7: iteration 16510/ 37905 | consumed samples: 4226560 | consumed tokens: 8655994880 | elapsed time per iteration (s): 0.25 | learning rate: 1.297E-04 | global batch size: 256 | lm loss: 3.379388E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1031.563 | TFLOPs: 26.28 | +7: iteration 16520/ 37905 | consumed samples: 4229120 | consumed tokens: 8661237760 | elapsed time per iteration (s): 0.85 | learning rate: 1.296E-04 | global batch size: 256 | lm loss: 3.412225E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 301.350 | TFLOPs: 7.68 | +7: iteration 16530/ 37905 | consumed samples: 4231680 | consumed tokens: 8666480640 | elapsed time per iteration (s): 0.24 | learning rate: 1.295E-04 | global batch size: 256 | lm loss: 3.412831E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1053.245 | TFLOPs: 26.83 | +7: iteration 16540/ 37905 | consumed samples: 4234240 | consumed tokens: 8671723520 | elapsed time per iteration (s): 0.25 | learning rate: 1.295E-04 | global batch size: 256 | lm loss: 3.388415E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1008.977 | TFLOPs: 25.70 | +7: iteration 16550/ 37905 | consumed samples: 4236800 | consumed tokens: 8676966400 | elapsed time per iteration (s): 0.24 | learning rate: 1.294E-04 | global batch size: 256 | lm loss: 3.399786E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1073.250 | TFLOPs: 27.34 | +7: iteration 16560/ 37905 | consumed samples: 4239360 | consumed tokens: 8682209280 | elapsed time per iteration (s): 0.28 | learning rate: 1.293E-04 | global batch size: 256 | lm loss: 3.424898E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 910.853 | TFLOPs: 23.20 | +7: iteration 16570/ 37905 | consumed samples: 4241920 | consumed tokens: 8687452160 | elapsed time per iteration (s): 0.23 | learning rate: 1.292E-04 | global batch size: 256 | lm loss: 3.405112E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.683 | TFLOPs: 28.29 | +7: iteration 16580/ 37905 | consumed samples: 4244480 | consumed tokens: 8692695040 | elapsed time per iteration (s): 0.24 | learning rate: 1.292E-04 | global batch size: 256 | lm loss: 3.391541E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1068.816 | TFLOPs: 27.23 | +7: iteration 16590/ 37905 | consumed samples: 4247040 | consumed tokens: 8697937920 | elapsed time per iteration (s): 0.23 | learning rate: 1.291E-04 | global batch size: 256 | lm loss: 3.398318E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.906 | TFLOPs: 27.79 | +7: iteration 16600/ 37905 | consumed samples: 4249600 | consumed tokens: 8703180800 | elapsed time per iteration (s): 0.24 | learning rate: 1.290E-04 | global batch size: 256 | lm loss: 3.402438E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1074.403 | TFLOPs: 27.37 | +7: iteration 16610/ 37905 | consumed samples: 4252160 | consumed tokens: 8708423680 | elapsed time per iteration (s): 0.24 | learning rate: 1.289E-04 | global batch size: 256 | lm loss: 3.382446E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1069.432 | TFLOPs: 27.24 | +7: iteration 16620/ 37905 | consumed samples: 4254720 | consumed tokens: 8713666560 | elapsed time per iteration (s): 0.24 | learning rate: 1.289E-04 | global batch size: 256 | lm loss: 3.429923E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.973 | TFLOPs: 27.67 | +7: iteration 16630/ 37905 | consumed samples: 4257280 | consumed tokens: 8718909440 | elapsed time per iteration (s): 0.23 | learning rate: 1.288E-04 | global batch size: 256 | lm loss: 3.429763E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.882 | TFLOPs: 28.48 | +7: iteration 16640/ 37905 | consumed samples: 4259840 | consumed tokens: 8724152320 | elapsed time per iteration (s): 0.24 | learning rate: 1.287E-04 | global batch size: 256 | lm loss: 3.389231E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.545 | TFLOPs: 27.48 | +7: iteration 16650/ 37905 | consumed samples: 4262400 | consumed tokens: 8729395200 | elapsed time per iteration (s): 0.30 | learning rate: 1.286E-04 | global batch size: 256 | lm loss: 3.404171E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 863.979 | TFLOPs: 22.01 | +7: iteration 16660/ 37905 | consumed samples: 4264960 | consumed tokens: 8734638080 | elapsed time per iteration (s): 0.23 | learning rate: 1.286E-04 | global batch size: 256 | lm loss: 3.396230E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.575 | TFLOPs: 27.96 | +7: iteration 16670/ 37905 | consumed samples: 4267520 | consumed tokens: 8739880960 | elapsed time per iteration (s): 0.23 | learning rate: 1.285E-04 | global batch size: 256 | lm loss: 3.378933E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.361 | TFLOPs: 28.11 | +7: iteration 16680/ 37905 | consumed samples: 4270080 | consumed tokens: 8745123840 | elapsed time per iteration (s): 0.24 | learning rate: 1.284E-04 | global batch size: 256 | lm loss: 3.397384E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1049.176 | TFLOPs: 26.73 | +7: iteration 16690/ 37905 | consumed samples: 4272640 | consumed tokens: 8750366720 | elapsed time per iteration (s): 0.23 | learning rate: 1.283E-04 | global batch size: 256 | lm loss: 3.404722E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.492 | TFLOPs: 28.01 | +7: iteration 16700/ 37905 | consumed samples: 4275200 | consumed tokens: 8755609600 | elapsed time per iteration (s): 0.24 | learning rate: 1.283E-04 | global batch size: 256 | lm loss: 3.394351E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.125 | TFLOPs: 27.47 | +7: iteration 16710/ 37905 | consumed samples: 4277760 | consumed tokens: 8760852480 | elapsed time per iteration (s): 0.39 | learning rate: 1.282E-04 | global batch size: 256 | lm loss: 3.402338E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 663.750 | TFLOPs: 16.91 | +7: iteration 16720/ 37905 | consumed samples: 4280320 | consumed tokens: 8766095360 | elapsed time per iteration (s): 0.32 | learning rate: 1.281E-04 | global batch size: 256 | lm loss: 3.393960E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 811.348 | TFLOPs: 20.67 | +7: iteration 16730/ 37905 | consumed samples: 4282880 | consumed tokens: 8771338240 | elapsed time per iteration (s): 0.25 | learning rate: 1.281E-04 | global batch size: 256 | lm loss: 3.420903E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1004.867 | TFLOPs: 25.60 | +7: iteration 16740/ 37905 | consumed samples: 4285440 | consumed tokens: 8776581120 | elapsed time per iteration (s): 0.24 | learning rate: 1.280E-04 | global batch size: 256 | lm loss: 3.386773E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.432 | TFLOPs: 27.27 | +7: iteration 16750/ 37905 | consumed samples: 4288000 | consumed tokens: 8781824000 | elapsed time per iteration (s): 0.24 | learning rate: 1.279E-04 | global batch size: 256 | lm loss: 3.421436E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.996 | TFLOPs: 27.49 | +7: iteration 16760/ 37905 | consumed samples: 4290560 | consumed tokens: 8787066880 | elapsed time per iteration (s): 0.23 | learning rate: 1.278E-04 | global batch size: 256 | lm loss: 3.423718E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.855 | TFLOPs: 27.92 | +7: iteration 16770/ 37905 | consumed samples: 4293120 | consumed tokens: 8792309760 | elapsed time per iteration (s): 0.23 | learning rate: 1.278E-04 | global batch size: 256 | lm loss: 3.379677E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.981 | TFLOPs: 28.40 | +7: iteration 16780/ 37905 | consumed samples: 4295680 | consumed tokens: 8797552640 | elapsed time per iteration (s): 0.23 | learning rate: 1.277E-04 | global batch size: 256 | lm loss: 3.434753E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.837 | TFLOPs: 28.50 | +7: iteration 16790/ 37905 | consumed samples: 4298240 | consumed tokens: 8802795520 | elapsed time per iteration (s): 0.23 | learning rate: 1.276E-04 | global batch size: 256 | lm loss: 3.414291E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.421 | TFLOPs: 28.39 | +7: iteration 16800/ 37905 | consumed samples: 4300800 | consumed tokens: 8808038400 | elapsed time per iteration (s): 0.23 | learning rate: 1.275E-04 | global batch size: 256 | lm loss: 3.405069E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.518 | TFLOPs: 28.44 | +7: iteration 16810/ 37905 | consumed samples: 4303360 | consumed tokens: 8813281280 | elapsed time per iteration (s): 0.23 | learning rate: 1.275E-04 | global batch size: 256 | lm loss: 3.411238E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.571 | TFLOPs: 28.34 | +7: iteration 16820/ 37905 | consumed samples: 4305920 | consumed tokens: 8818524160 | elapsed time per iteration (s): 0.23 | learning rate: 1.274E-04 | global batch size: 256 | lm loss: 3.421884E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.109 | TFLOPs: 28.51 | +7: iteration 16830/ 37905 | consumed samples: 4308480 | consumed tokens: 8823767040 | elapsed time per iteration (s): 0.26 | learning rate: 1.273E-04 | global batch size: 256 | lm loss: 3.392902E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 972.876 | TFLOPs: 24.78 | +7: iteration 16840/ 37905 | consumed samples: 4311040 | consumed tokens: 8829009920 | elapsed time per iteration (s): 0.23 | learning rate: 1.272E-04 | global batch size: 256 | lm loss: 3.394761E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.796 | TFLOPs: 28.48 | +7: iteration 16850/ 37905 | consumed samples: 4313600 | consumed tokens: 8834252800 | elapsed time per iteration (s): 0.39 | learning rate: 1.272E-04 | global batch size: 256 | lm loss: 3.396530E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 657.621 | TFLOPs: 16.75 | +7: iteration 16860/ 37905 | consumed samples: 4316160 | consumed tokens: 8839495680 | elapsed time per iteration (s): 0.23 | learning rate: 1.271E-04 | global batch size: 256 | lm loss: 3.425215E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.948 | TFLOPs: 28.17 | +7: iteration 16870/ 37905 | consumed samples: 4318720 | consumed tokens: 8844738560 | elapsed time per iteration (s): 0.42 | learning rate: 1.270E-04 | global batch size: 256 | lm loss: 3.394589E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 616.286 | TFLOPs: 15.70 | +7: iteration 16880/ 37905 | consumed samples: 4321280 | consumed tokens: 8849981440 | elapsed time per iteration (s): 0.28 | learning rate: 1.269E-04 | global batch size: 256 | lm loss: 3.392162E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 910.624 | TFLOPs: 23.20 | +7: iteration 16890/ 37905 | consumed samples: 4323840 | consumed tokens: 8855224320 | elapsed time per iteration (s): 0.25 | learning rate: 1.269E-04 | global batch size: 256 | lm loss: 3.408920E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1040.142 | TFLOPs: 26.50 | +7: iteration 16900/ 37905 | consumed samples: 4326400 | consumed tokens: 8860467200 | elapsed time per iteration (s): 0.52 | learning rate: 1.268E-04 | global batch size: 256 | lm loss: 3.391607E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 488.703 | TFLOPs: 12.45 | +7: iteration 16910/ 37905 | consumed samples: 4328960 | consumed tokens: 8865710080 | elapsed time per iteration (s): 0.41 | learning rate: 1.267E-04 | global batch size: 256 | lm loss: 3.361177E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 622.142 | TFLOPs: 15.85 | +7: iteration 16920/ 37905 | consumed samples: 4331520 | consumed tokens: 8870952960 | elapsed time per iteration (s): 0.26 | learning rate: 1.266E-04 | global batch size: 256 | lm loss: 3.404779E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 975.774 | TFLOPs: 24.86 | +7: iteration 16930/ 37905 | consumed samples: 4334080 | consumed tokens: 8876195840 | elapsed time per iteration (s): 0.28 | learning rate: 1.266E-04 | global batch size: 256 | lm loss: 3.433547E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 911.267 | TFLOPs: 23.21 | +7: iteration 16940/ 37905 | consumed samples: 4336640 | consumed tokens: 8881438720 | elapsed time per iteration (s): 0.29 | learning rate: 1.265E-04 | global batch size: 256 | lm loss: 3.393922E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 876.634 | TFLOPs: 22.33 | +7: iteration 16950/ 37905 | consumed samples: 4339200 | consumed tokens: 8886681600 | elapsed time per iteration (s): 0.23 | learning rate: 1.264E-04 | global batch size: 256 | lm loss: 3.423559E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.850 | TFLOPs: 28.25 | +7: iteration 16960/ 37905 | consumed samples: 4341760 | consumed tokens: 8891924480 | elapsed time per iteration (s): 0.23 | learning rate: 1.263E-04 | global batch size: 256 | lm loss: 3.379633E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.787 | TFLOPs: 28.27 | +7: iteration 16970/ 37905 | consumed samples: 4344320 | consumed tokens: 8897167360 | elapsed time per iteration (s): 0.25 | learning rate: 1.263E-04 | global batch size: 256 | lm loss: 3.384091E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1030.634 | TFLOPs: 26.26 | +7: iteration 16980/ 37905 | consumed samples: 4346880 | consumed tokens: 8902410240 | elapsed time per iteration (s): 0.23 | learning rate: 1.262E-04 | global batch size: 256 | lm loss: 3.401518E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.646 | TFLOPs: 27.91 | +7: iteration 16990/ 37905 | consumed samples: 4349440 | consumed tokens: 8907653120 | elapsed time per iteration (s): 0.23 | learning rate: 1.261E-04 | global batch size: 256 | lm loss: 3.362609E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.144 | TFLOPs: 28.38 | +7: iteration 17000/ 37905 | consumed samples: 4352000 | consumed tokens: 8912896000 | elapsed time per iteration (s): 0.23 | learning rate: 1.261E-04 | global batch size: 256 | lm loss: 3.414536E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.212 | TFLOPs: 28.36 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 17000 | lm loss value: 3.310949E+00 | lm loss PPL: 2.741112E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 17000 to checkpoints_83moscar +0: [2022-11-29 18:03:19,407] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step17000 is begin to save! +0: [2022-11-29 18:03:19,473] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:03:19,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:03:19,745] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:03:19,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:03:19,758] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:03:19,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:03:19,769] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:03:19,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:03:19,781] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:03:19,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:03:19,792] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:03:19,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:03:19,803] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:03:19,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:03:19,815] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:03:19,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:03:19,826] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:03:19,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:03:19,838] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:03:19,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:03:19,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:03:19,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:03:19,861] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:03:19,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:03:19,862] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step17000/mp_rank_00_model_states.pt +0: [2022-11-29 18:03:19,862] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:03:19,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:03:19,885] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:03:19,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:03:19,905] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:03:19,905] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:03:19,905] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +0: [2022-11-29 18:03:19,906] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:03:19,906] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:03:19,906] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +6: [2022-11-29 18:03:19,906] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:03:19,906] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:03:19,906] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +6: [2022-11-29 18:03:19,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:03:19,907] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:03:19,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +0: [2022-11-29 18:03:19,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:03:19,908] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:03:19,908] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +6: [2022-11-29 18:03:19,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:03:19,909] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:03:19,909] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +0: [2022-11-29 18:03:19,910] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:03:19,910] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:03:19,910] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +0: [2022-11-29 18:03:19,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:03:19,911] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:03:19,911] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +6: [2022-11-29 18:03:19,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:03:19,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:03:19,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +6: [2022-11-29 18:03:19,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:03:19,912] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:03:19,912] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +0: [2022-11-29 18:03:19,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:03:19,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:03:19,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +0: [2022-11-29 18:03:19,914] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:03:19,914] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:03:19,914] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +6: [2022-11-29 18:03:19,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:03:19,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:03:19,915] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +0: [2022-11-29 18:03:19,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +6: [2022-11-29 18:03:19,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:03:19,915] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +6: [2022-11-29 18:03:19,915] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:03:19,915] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +6: [2022-11-29 18:03:19,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:03:19,916] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:03:19,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +5: [2022-11-29 18:03:19,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:03:19,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:03:19,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +1: [2022-11-29 18:03:19,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:03:19,921] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:03:19,921] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +1: [2022-11-29 18:03:19,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:03:19,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:03:19,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +1: [2022-11-29 18:03:19,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:03:19,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:03:19,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +1: [2022-11-29 18:03:19,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:03:19,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:03:19,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +2: [2022-11-29 18:03:19,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:03:19,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:03:19,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +5: [2022-11-29 18:03:19,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:03:19,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:03:19,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +2: [2022-11-29 18:03:19,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:03:19,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:03:19,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +2: [2022-11-29 18:03:19,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:03:19,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +5: [2022-11-29 18:03:19,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +5: [2022-11-29 18:03:19,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:03:19,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:03:19,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:03:19,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +5: [2022-11-29 18:03:19,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +1: [2022-11-29 18:03:19,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:03:19,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +1: [2022-11-29 18:03:19,923] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:03:19,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +5: [2022-11-29 18:03:19,923] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:03:19,923] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:03:19,923] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:03:19,923] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +2: [2022-11-29 18:03:19,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:03:19,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:03:19,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:03:19,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +2: [2022-11-29 18:03:19,922] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:03:19,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +1: [2022-11-29 18:03:19,923] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:03:19,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +5: [2022-11-29 18:03:19,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +2: [2022-11-29 18:03:19,923] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:03:19,923] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:03:19,923] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:03:19,923] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:03:19,923] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +2: [2022-11-29 18:03:19,923] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +1: [2022-11-29 18:03:19,923] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +2: [2022-11-29 18:03:19,923] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +1: [2022-11-29 18:03:19,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +2: [2022-11-29 18:03:19,923] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:03:19,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +2: [2022-11-29 18:03:19,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +1: [2022-11-29 18:03:19,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +2: [2022-11-29 18:03:19,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +5: [2022-11-29 18:03:19,923] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:03:19,923] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:03:19,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +2: [2022-11-29 18:03:19,923] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:03:19,923] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:03:19,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +1: [2022-11-29 18:03:19,923] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:03:19,923] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:03:19,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +3: [2022-11-29 18:03:19,926] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:03:19,926] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:03:19,926] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:03:19,926] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:03:19,926] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +3: [2022-11-29 18:03:19,926] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +3: [2022-11-29 18:03:19,926] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:03:19,926] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:03:19,926] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:03:19,926] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:03:19,926] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:03:19,926] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:03:19,926] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:03:19,926] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +3: [2022-11-29 18:03:19,926] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:03:19,926] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +3: [2022-11-29 18:03:19,926] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:03:19,926] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:03:19,926] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +3: [2022-11-29 18:03:19,926] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +3: [2022-11-29 18:03:19,927] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:03:19,927] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:03:19,927] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +3: [2022-11-29 18:03:19,927] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +4: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:03:19,929] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +7: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:03:19,929] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:03:19,929] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +7: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:03:19,929] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:03:19,929] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +7: [2022-11-29 18:03:19,929] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +4: [2022-11-29 18:03:19,929] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:03:19,929] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:03:19,929] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +7: [2022-11-29 18:03:19,929] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:03:19,929] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +7: [2022-11-29 18:03:19,929] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:03:19,929] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +4: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +4: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +4: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +7: [2022-11-29 18:03:19,929] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:03:19,929] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +4: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +7: [2022-11-29 18:03:19,929] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step17000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +4: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +4: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +4: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +7: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +7: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +7: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +7: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +7: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +7: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +7: [2022-11-29 18:03:19,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +0: successfully saved checkpoint at iteration 17000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 591.49 +7: iteration 17010/ 37905 | consumed samples: 4354560 | consumed tokens: 8918138880 | elapsed time per iteration (s): 0.30 | learning rate: 1.260E-04 | global batch size: 256 | lm loss: 3.409237E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 853.491 | TFLOPs: 21.74 | +7: iteration 17020/ 37905 | consumed samples: 4357120 | consumed tokens: 8923381760 | elapsed time per iteration (s): 0.24 | learning rate: 1.259E-04 | global batch size: 256 | lm loss: 3.414679E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1076.376 | TFLOPs: 27.42 | +7: iteration 17030/ 37905 | consumed samples: 4359680 | consumed tokens: 8928624640 | elapsed time per iteration (s): 0.25 | learning rate: 1.258E-04 | global batch size: 256 | lm loss: 3.369599E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1035.828 | TFLOPs: 26.39 | +7: iteration 17040/ 37905 | consumed samples: 4362240 | consumed tokens: 8933867520 | elapsed time per iteration (s): 0.24 | learning rate: 1.258E-04 | global batch size: 256 | lm loss: 3.396489E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.728 | TFLOPs: 27.66 | +7: iteration 17050/ 37905 | consumed samples: 4364800 | consumed tokens: 8939110400 | elapsed time per iteration (s): 0.23 | learning rate: 1.257E-04 | global batch size: 256 | lm loss: 3.389753E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.996 | TFLOPs: 28.02 | +7: iteration 17060/ 37905 | consumed samples: 4367360 | consumed tokens: 8944353280 | elapsed time per iteration (s): 0.24 | learning rate: 1.256E-04 | global batch size: 256 | lm loss: 3.405930E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1046.517 | TFLOPs: 26.66 | +7: iteration 17070/ 37905 | consumed samples: 4369920 | consumed tokens: 8949596160 | elapsed time per iteration (s): 0.24 | learning rate: 1.255E-04 | global batch size: 256 | lm loss: 3.395230E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1083.301 | TFLOPs: 27.60 | +7: iteration 17080/ 37905 | consumed samples: 4372480 | consumed tokens: 8954839040 | elapsed time per iteration (s): 0.24 | learning rate: 1.255E-04 | global batch size: 256 | lm loss: 3.417669E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1061.331 | TFLOPs: 27.04 | +7: iteration 17090/ 37905 | consumed samples: 4375040 | consumed tokens: 8960081920 | elapsed time per iteration (s): 0.26 | learning rate: 1.254E-04 | global batch size: 256 | lm loss: 3.400872E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 978.113 | TFLOPs: 24.92 | +7: iteration 17100/ 37905 | consumed samples: 4377600 | consumed tokens: 8965324800 | elapsed time per iteration (s): 0.25 | learning rate: 1.253E-04 | global batch size: 256 | lm loss: 3.423627E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1027.105 | TFLOPs: 26.17 | +7: iteration 17110/ 37905 | consumed samples: 4380160 | consumed tokens: 8970567680 | elapsed time per iteration (s): 0.26 | learning rate: 1.252E-04 | global batch size: 256 | lm loss: 3.377118E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 983.461 | TFLOPs: 25.05 | +7: iteration 17120/ 37905 | consumed samples: 4382720 | consumed tokens: 8975810560 | elapsed time per iteration (s): 0.24 | learning rate: 1.252E-04 | global batch size: 256 | lm loss: 3.399826E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.824 | TFLOPs: 26.95 | +7: iteration 17130/ 37905 | consumed samples: 4385280 | consumed tokens: 8981053440 | elapsed time per iteration (s): 0.23 | learning rate: 1.251E-04 | global batch size: 256 | lm loss: 3.424894E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.364 | TFLOPs: 28.54 | +7: iteration 17140/ 37905 | consumed samples: 4387840 | consumed tokens: 8986296320 | elapsed time per iteration (s): 0.23 | learning rate: 1.250E-04 | global batch size: 256 | lm loss: 3.411437E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.140 | TFLOPs: 28.51 | +7: iteration 17150/ 37905 | consumed samples: 4390400 | consumed tokens: 8991539200 | elapsed time per iteration (s): 0.23 | learning rate: 1.249E-04 | global batch size: 256 | lm loss: 3.397421E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.150 | TFLOPs: 28.51 | +7: iteration 17160/ 37905 | consumed samples: 4392960 | consumed tokens: 8996782080 | elapsed time per iteration (s): 0.23 | learning rate: 1.249E-04 | global batch size: 256 | lm loss: 3.389468E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.139 | TFLOPs: 28.66 | +7: iteration 17170/ 37905 | consumed samples: 4395520 | consumed tokens: 9002024960 | elapsed time per iteration (s): 0.23 | learning rate: 1.248E-04 | global batch size: 256 | lm loss: 3.381162E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.895 | TFLOPs: 28.53 | +7: iteration 17180/ 37905 | consumed samples: 4398080 | consumed tokens: 9007267840 | elapsed time per iteration (s): 0.23 | learning rate: 1.247E-04 | global batch size: 256 | lm loss: 3.406319E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.054 | TFLOPs: 28.61 | +7: iteration 17190/ 37905 | consumed samples: 4400640 | consumed tokens: 9012510720 | elapsed time per iteration (s): 0.23 | learning rate: 1.246E-04 | global batch size: 256 | lm loss: 3.387248E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.959 | TFLOPs: 28.56 | +7: iteration 17200/ 37905 | consumed samples: 4403200 | consumed tokens: 9017753600 | elapsed time per iteration (s): 0.24 | learning rate: 1.246E-04 | global batch size: 256 | lm loss: 3.384959E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1063.429 | TFLOPs: 27.09 | +7: iteration 17210/ 37905 | consumed samples: 4405760 | consumed tokens: 9022996480 | elapsed time per iteration (s): 0.23 | learning rate: 1.245E-04 | global batch size: 256 | lm loss: 3.410545E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.660 | TFLOPs: 28.40 | +7: iteration 17220/ 37905 | consumed samples: 4408320 | consumed tokens: 9028239360 | elapsed time per iteration (s): 0.25 | learning rate: 1.244E-04 | global batch size: 256 | lm loss: 3.405780E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1009.874 | TFLOPs: 25.73 | +7: iteration 17230/ 37905 | consumed samples: 4410880 | consumed tokens: 9033482240 | elapsed time per iteration (s): 0.23 | learning rate: 1.243E-04 | global batch size: 256 | lm loss: 3.428760E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.246 | TFLOPs: 28.11 | +7: iteration 17240/ 37905 | consumed samples: 4413440 | consumed tokens: 9038725120 | elapsed time per iteration (s): 0.47 | learning rate: 1.243E-04 | global batch size: 256 | lm loss: 3.401963E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 543.799 | TFLOPs: 13.85 | +7: iteration 17250/ 37905 | consumed samples: 4416000 | consumed tokens: 9043968000 | elapsed time per iteration (s): 0.42 | learning rate: 1.242E-04 | global batch size: 256 | lm loss: 3.388060E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 604.217 | TFLOPs: 15.39 | +7: iteration 17260/ 37905 | consumed samples: 4418560 | consumed tokens: 9049210880 | elapsed time per iteration (s): 0.26 | learning rate: 1.241E-04 | global batch size: 256 | lm loss: 3.413844E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 980.602 | TFLOPs: 24.98 | +7: iteration 17270/ 37905 | consumed samples: 4421120 | consumed tokens: 9054453760 | elapsed time per iteration (s): 0.38 | learning rate: 1.240E-04 | global batch size: 256 | lm loss: 3.392362E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 677.322 | TFLOPs: 17.25 | +7: iteration 17280/ 37905 | consumed samples: 4423680 | consumed tokens: 9059696640 | elapsed time per iteration (s): 0.30 | learning rate: 1.240E-04 | global batch size: 256 | lm loss: 3.382703E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 856.970 | TFLOPs: 21.83 | +7: iteration 17290/ 37905 | consumed samples: 4426240 | consumed tokens: 9064939520 | elapsed time per iteration (s): 0.27 | learning rate: 1.239E-04 | global batch size: 256 | lm loss: 3.385364E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 957.621 | TFLOPs: 24.40 | +7: iteration 17300/ 37905 | consumed samples: 4428800 | consumed tokens: 9070182400 | elapsed time per iteration (s): 0.38 | learning rate: 1.238E-04 | global batch size: 256 | lm loss: 3.402910E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 669.248 | TFLOPs: 17.05 | +7: iteration 17310/ 37905 | consumed samples: 4431360 | consumed tokens: 9075425280 | elapsed time per iteration (s): 0.29 | learning rate: 1.237E-04 | global batch size: 256 | lm loss: 3.394830E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 891.443 | TFLOPs: 22.71 | +7: iteration 17320/ 37905 | consumed samples: 4433920 | consumed tokens: 9080668160 | elapsed time per iteration (s): 0.27 | learning rate: 1.237E-04 | global batch size: 256 | lm loss: 3.403876E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 964.992 | TFLOPs: 24.58 | +7: iteration 17330/ 37905 | consumed samples: 4436480 | consumed tokens: 9085911040 | elapsed time per iteration (s): 0.23 | learning rate: 1.236E-04 | global batch size: 256 | lm loss: 3.390204E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.309 | TFLOPs: 27.93 | +7: iteration 17340/ 37905 | consumed samples: 4439040 | consumed tokens: 9091153920 | elapsed time per iteration (s): 0.23 | learning rate: 1.235E-04 | global batch size: 256 | lm loss: 3.356549E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.485 | TFLOPs: 28.44 | +7: iteration 17350/ 37905 | consumed samples: 4441600 | consumed tokens: 9096396800 | elapsed time per iteration (s): 0.26 | learning rate: 1.235E-04 | global batch size: 256 | lm loss: 3.397003E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 998.696 | TFLOPs: 25.44 | +7: iteration 17360/ 37905 | consumed samples: 4444160 | consumed tokens: 9101639680 | elapsed time per iteration (s): 0.23 | learning rate: 1.234E-04 | global batch size: 256 | lm loss: 3.416441E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.621 | TFLOPs: 28.11 | +7: iteration 17370/ 37905 | consumed samples: 4446720 | consumed tokens: 9106882560 | elapsed time per iteration (s): 0.23 | learning rate: 1.233E-04 | global batch size: 256 | lm loss: 3.402431E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.029 | TFLOPs: 28.10 | +7: iteration 17380/ 37905 | consumed samples: 4449280 | consumed tokens: 9112125440 | elapsed time per iteration (s): 0.23 | learning rate: 1.232E-04 | global batch size: 256 | lm loss: 3.399375E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.572 | TFLOPs: 27.94 | +7: iteration 17390/ 37905 | consumed samples: 4451840 | consumed tokens: 9117368320 | elapsed time per iteration (s): 0.23 | learning rate: 1.232E-04 | global batch size: 256 | lm loss: 3.392539E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.741 | TFLOPs: 27.97 | +7: iteration 17400/ 37905 | consumed samples: 4454400 | consumed tokens: 9122611200 | elapsed time per iteration (s): 0.23 | learning rate: 1.231E-04 | global batch size: 256 | lm loss: 3.396667E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.584 | TFLOPs: 27.91 | +7: iteration 17410/ 37905 | consumed samples: 4456960 | consumed tokens: 9127854080 | elapsed time per iteration (s): 0.24 | learning rate: 1.230E-04 | global batch size: 256 | lm loss: 3.371431E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1054.336 | TFLOPs: 26.86 | +7: iteration 17420/ 37905 | consumed samples: 4459520 | consumed tokens: 9133096960 | elapsed time per iteration (s): 0.23 | learning rate: 1.229E-04 | global batch size: 256 | lm loss: 3.413420E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.794 | TFLOPs: 27.94 | +7: iteration 17430/ 37905 | consumed samples: 4462080 | consumed tokens: 9138339840 | elapsed time per iteration (s): 0.23 | learning rate: 1.229E-04 | global batch size: 256 | lm loss: 3.392440E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.344 | TFLOPs: 28.11 | +7: iteration 17440/ 37905 | consumed samples: 4464640 | consumed tokens: 9143582720 | elapsed time per iteration (s): 0.25 | learning rate: 1.228E-04 | global batch size: 256 | lm loss: 3.428856E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1008.041 | TFLOPs: 25.68 | +7: iteration 17450/ 37905 | consumed samples: 4467200 | consumed tokens: 9148825600 | elapsed time per iteration (s): 0.38 | learning rate: 1.227E-04 | global batch size: 256 | lm loss: 3.379082E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 678.669 | TFLOPs: 17.29 | +7: iteration 17460/ 37905 | consumed samples: 4469760 | consumed tokens: 9154068480 | elapsed time per iteration (s): 0.40 | learning rate: 1.226E-04 | global batch size: 256 | lm loss: 3.413318E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 645.983 | TFLOPs: 16.46 | +7: iteration 17470/ 37905 | consumed samples: 4472320 | consumed tokens: 9159311360 | elapsed time per iteration (s): 0.26 | learning rate: 1.226E-04 | global batch size: 256 | lm loss: 3.369334E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 980.809 | TFLOPs: 24.99 | +7: iteration 17480/ 37905 | consumed samples: 4474880 | consumed tokens: 9164554240 | elapsed time per iteration (s): 0.23 | learning rate: 1.225E-04 | global batch size: 256 | lm loss: 3.425222E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.326 | TFLOPs: 28.18 | +7: iteration 17490/ 37905 | consumed samples: 4477440 | consumed tokens: 9169797120 | elapsed time per iteration (s): 0.25 | learning rate: 1.224E-04 | global batch size: 256 | lm loss: 3.388305E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1033.997 | TFLOPs: 26.34 | +7: iteration 17500/ 37905 | consumed samples: 4480000 | consumed tokens: 9175040000 | elapsed time per iteration (s): 0.23 | learning rate: 1.223E-04 | global batch size: 256 | lm loss: 3.402391E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.521 | TFLOPs: 28.14 | +7: iteration 17510/ 37905 | consumed samples: 4482560 | consumed tokens: 9180282880 | elapsed time per iteration (s): 0.23 | learning rate: 1.223E-04 | global batch size: 256 | lm loss: 3.375092E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.771 | TFLOPs: 28.17 | +7: iteration 17520/ 37905 | consumed samples: 4485120 | consumed tokens: 9185525760 | elapsed time per iteration (s): 0.25 | learning rate: 1.222E-04 | global batch size: 256 | lm loss: 3.371446E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1031.837 | TFLOPs: 26.29 | +7: iteration 17530/ 37905 | consumed samples: 4487680 | consumed tokens: 9190768640 | elapsed time per iteration (s): 0.23 | learning rate: 1.221E-04 | global batch size: 256 | lm loss: 3.388924E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.810 | TFLOPs: 28.58 | +7: iteration 17540/ 37905 | consumed samples: 4490240 | consumed tokens: 9196011520 | elapsed time per iteration (s): 0.23 | learning rate: 1.220E-04 | global batch size: 256 | lm loss: 3.421399E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.950 | TFLOPs: 28.25 | +7: iteration 17550/ 37905 | consumed samples: 4492800 | consumed tokens: 9201254400 | elapsed time per iteration (s): 0.23 | learning rate: 1.220E-04 | global batch size: 256 | lm loss: 3.396000E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.143 | TFLOPs: 28.33 | +7: iteration 17560/ 37905 | consumed samples: 4495360 | consumed tokens: 9206497280 | elapsed time per iteration (s): 0.24 | learning rate: 1.219E-04 | global batch size: 256 | lm loss: 3.364850E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1068.455 | TFLOPs: 27.22 | +7: iteration 17570/ 37905 | consumed samples: 4497920 | consumed tokens: 9211740160 | elapsed time per iteration (s): 0.23 | learning rate: 1.218E-04 | global batch size: 256 | lm loss: 3.404128E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.142 | TFLOPs: 28.26 | +7: iteration 17580/ 37905 | consumed samples: 4500480 | consumed tokens: 9216983040 | elapsed time per iteration (s): 0.30 | learning rate: 1.217E-04 | global batch size: 256 | lm loss: 3.366401E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 855.003 | TFLOPs: 21.78 | +7: iteration 17590/ 37905 | consumed samples: 4503040 | consumed tokens: 9222225920 | elapsed time per iteration (s): 0.23 | learning rate: 1.217E-04 | global batch size: 256 | lm loss: 3.388712E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.241 | TFLOPs: 28.23 | +7: iteration 17600/ 37905 | consumed samples: 4505600 | consumed tokens: 9227468800 | elapsed time per iteration (s): 0.27 | learning rate: 1.216E-04 | global batch size: 256 | lm loss: 3.400337E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 963.538 | TFLOPs: 24.55 | +7: iteration 17610/ 37905 | consumed samples: 4508160 | consumed tokens: 9232711680 | elapsed time per iteration (s): 0.24 | learning rate: 1.215E-04 | global batch size: 256 | lm loss: 3.392441E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.747 | TFLOPs: 27.66 | +7: iteration 17620/ 37905 | consumed samples: 4510720 | consumed tokens: 9237954560 | elapsed time per iteration (s): 0.24 | learning rate: 1.214E-04 | global batch size: 256 | lm loss: 3.398421E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.832 | TFLOPs: 27.28 | +7: iteration 17630/ 37905 | consumed samples: 4513280 | consumed tokens: 9243197440 | elapsed time per iteration (s): 0.24 | learning rate: 1.214E-04 | global batch size: 256 | lm loss: 3.364433E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1067.901 | TFLOPs: 27.20 | +7: iteration 17640/ 37905 | consumed samples: 4515840 | consumed tokens: 9248440320 | elapsed time per iteration (s): 0.30 | learning rate: 1.213E-04 | global batch size: 256 | lm loss: 3.384472E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 862.921 | TFLOPs: 21.98 | +7: iteration 17650/ 37905 | consumed samples: 4518400 | consumed tokens: 9253683200 | elapsed time per iteration (s): 0.24 | learning rate: 1.212E-04 | global batch size: 256 | lm loss: 3.369072E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.325 | TFLOPs: 27.75 | +7: iteration 17660/ 37905 | consumed samples: 4520960 | consumed tokens: 9258926080 | elapsed time per iteration (s): 0.42 | learning rate: 1.211E-04 | global batch size: 256 | lm loss: 3.411066E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 607.791 | TFLOPs: 15.48 | +7: iteration 17670/ 37905 | consumed samples: 4523520 | consumed tokens: 9264168960 | elapsed time per iteration (s): 0.34 | learning rate: 1.211E-04 | global batch size: 256 | lm loss: 3.396681E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 762.052 | TFLOPs: 19.41 | +7: iteration 17680/ 37905 | consumed samples: 4526080 | consumed tokens: 9269411840 | elapsed time per iteration (s): 0.29 | learning rate: 1.210E-04 | global batch size: 256 | lm loss: 3.408776E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 870.656 | TFLOPs: 22.18 | +7: iteration 17690/ 37905 | consumed samples: 4528640 | consumed tokens: 9274654720 | elapsed time per iteration (s): 0.28 | learning rate: 1.209E-04 | global batch size: 256 | lm loss: 3.386692E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 913.810 | TFLOPs: 23.28 | +7: iteration 17700/ 37905 | consumed samples: 4531200 | consumed tokens: 9279897600 | elapsed time per iteration (s): 0.24 | learning rate: 1.208E-04 | global batch size: 256 | lm loss: 3.387495E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1048.877 | TFLOPs: 26.72 | +7: iteration 17710/ 37905 | consumed samples: 4533760 | consumed tokens: 9285140480 | elapsed time per iteration (s): 0.23 | learning rate: 1.208E-04 | global batch size: 256 | lm loss: 3.389598E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.476 | TFLOPs: 28.29 | +7: iteration 17720/ 37905 | consumed samples: 4536320 | consumed tokens: 9290383360 | elapsed time per iteration (s): 0.23 | learning rate: 1.207E-04 | global batch size: 256 | lm loss: 3.382096E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.128 | TFLOPs: 28.36 | +7: iteration 17730/ 37905 | consumed samples: 4538880 | consumed tokens: 9295626240 | elapsed time per iteration (s): 0.23 | learning rate: 1.206E-04 | global batch size: 256 | lm loss: 3.378239E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.931 | TFLOPs: 28.20 | +7: iteration 17740/ 37905 | consumed samples: 4541440 | consumed tokens: 9300869120 | elapsed time per iteration (s): 0.23 | learning rate: 1.205E-04 | global batch size: 256 | lm loss: 3.388100E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.671 | TFLOPs: 28.29 | +7: iteration 17750/ 37905 | consumed samples: 4544000 | consumed tokens: 9306112000 | elapsed time per iteration (s): 0.24 | learning rate: 1.205E-04 | global batch size: 256 | lm loss: 3.404014E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1075.741 | TFLOPs: 27.40 | +7: iteration 17760/ 37905 | consumed samples: 4546560 | consumed tokens: 9311354880 | elapsed time per iteration (s): 0.23 | learning rate: 1.204E-04 | global batch size: 256 | lm loss: 3.406450E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.176 | TFLOPs: 27.98 | +7: iteration 17770/ 37905 | consumed samples: 4549120 | consumed tokens: 9316597760 | elapsed time per iteration (s): 0.23 | learning rate: 1.203E-04 | global batch size: 256 | lm loss: 3.401432E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.494 | TFLOPs: 27.96 | +7: iteration 17780/ 37905 | consumed samples: 4551680 | consumed tokens: 9321840640 | elapsed time per iteration (s): 0.23 | learning rate: 1.202E-04 | global batch size: 256 | lm loss: 3.376671E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.261 | TFLOPs: 28.08 | +7: iteration 17790/ 37905 | consumed samples: 4554240 | consumed tokens: 9327083520 | elapsed time per iteration (s): 0.24 | learning rate: 1.202E-04 | global batch size: 256 | lm loss: 3.399244E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1063.101 | TFLOPs: 27.08 | +7: iteration 17800/ 37905 | consumed samples: 4556800 | consumed tokens: 9332326400 | elapsed time per iteration (s): 0.24 | learning rate: 1.201E-04 | global batch size: 256 | lm loss: 3.410643E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1046.930 | TFLOPs: 26.67 | +7: iteration 17810/ 37905 | consumed samples: 4559360 | consumed tokens: 9337569280 | elapsed time per iteration (s): 0.24 | learning rate: 1.200E-04 | global batch size: 256 | lm loss: 3.419748E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.365 | TFLOPs: 27.73 | +7: iteration 17820/ 37905 | consumed samples: 4561920 | consumed tokens: 9342812160 | elapsed time per iteration (s): 0.24 | learning rate: 1.199E-04 | global batch size: 256 | lm loss: 3.375883E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1071.804 | TFLOPs: 27.30 | +7: iteration 17830/ 37905 | consumed samples: 4564480 | consumed tokens: 9348055040 | elapsed time per iteration (s): 0.23 | learning rate: 1.199E-04 | global batch size: 256 | lm loss: 3.414149E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.182 | TFLOPs: 27.82 | +7: iteration 17840/ 37905 | consumed samples: 4567040 | consumed tokens: 9353297920 | elapsed time per iteration (s): 0.24 | learning rate: 1.198E-04 | global batch size: 256 | lm loss: 3.392105E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.988 | TFLOPs: 27.74 | +7: iteration 17850/ 37905 | consumed samples: 4569600 | consumed tokens: 9358540800 | elapsed time per iteration (s): 0.23 | learning rate: 1.197E-04 | global batch size: 256 | lm loss: 3.384052E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.894 | TFLOPs: 27.97 | +7: iteration 17860/ 37905 | consumed samples: 4572160 | consumed tokens: 9363783680 | elapsed time per iteration (s): 0.24 | learning rate: 1.196E-04 | global batch size: 256 | lm loss: 3.406436E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.018 | TFLOPs: 26.93 | +7: iteration 17870/ 37905 | consumed samples: 4574720 | consumed tokens: 9369026560 | elapsed time per iteration (s): 0.23 | learning rate: 1.196E-04 | global batch size: 256 | lm loss: 3.389444E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.259 | TFLOPs: 27.98 | +7: iteration 17880/ 37905 | consumed samples: 4577280 | consumed tokens: 9374269440 | elapsed time per iteration (s): 0.25 | learning rate: 1.195E-04 | global batch size: 256 | lm loss: 3.390637E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1013.521 | TFLOPs: 25.82 | +7: iteration 17890/ 37905 | consumed samples: 4579840 | consumed tokens: 9379512320 | elapsed time per iteration (s): 0.25 | learning rate: 1.194E-04 | global batch size: 256 | lm loss: 3.411373E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1034.851 | TFLOPs: 26.36 | +7: iteration 17900/ 37905 | consumed samples: 4582400 | consumed tokens: 9384755200 | elapsed time per iteration (s): 0.23 | learning rate: 1.193E-04 | global batch size: 256 | lm loss: 3.407097E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.290 | TFLOPs: 28.44 | +7: iteration 17910/ 37905 | consumed samples: 4584960 | consumed tokens: 9389998080 | elapsed time per iteration (s): 0.23 | learning rate: 1.193E-04 | global batch size: 256 | lm loss: 3.371235E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.359 | TFLOPs: 28.59 | +7: iteration 17920/ 37905 | consumed samples: 4587520 | consumed tokens: 9395240960 | elapsed time per iteration (s): 0.23 | learning rate: 1.192E-04 | global batch size: 256 | lm loss: 3.383977E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.708 | TFLOPs: 28.45 | +7: iteration 17930/ 37905 | consumed samples: 4590080 | consumed tokens: 9400483840 | elapsed time per iteration (s): 0.23 | learning rate: 1.191E-04 | global batch size: 256 | lm loss: 3.379087E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.776 | TFLOPs: 28.58 | +7: iteration 17940/ 37905 | consumed samples: 4592640 | consumed tokens: 9405726720 | elapsed time per iteration (s): 0.23 | learning rate: 1.190E-04 | global batch size: 256 | lm loss: 3.388098E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.138 | TFLOPs: 28.48 | +7: iteration 17950/ 37905 | consumed samples: 4595200 | consumed tokens: 9410969600 | elapsed time per iteration (s): 0.24 | learning rate: 1.190E-04 | global batch size: 256 | lm loss: 3.412098E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1055.591 | TFLOPs: 26.89 | +7: iteration 17960/ 37905 | consumed samples: 4597760 | consumed tokens: 9416212480 | elapsed time per iteration (s): 0.23 | learning rate: 1.189E-04 | global batch size: 256 | lm loss: 3.399673E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.109 | TFLOPs: 28.31 | +7: iteration 17970/ 37905 | consumed samples: 4600320 | consumed tokens: 9421455360 | elapsed time per iteration (s): 0.24 | learning rate: 1.188E-04 | global batch size: 256 | lm loss: 3.373752E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1058.731 | TFLOPs: 26.97 | +7: iteration 17980/ 37905 | consumed samples: 4602880 | consumed tokens: 9426698240 | elapsed time per iteration (s): 0.25 | learning rate: 1.187E-04 | global batch size: 256 | lm loss: 3.401487E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1039.293 | TFLOPs: 26.48 | +7: iteration 17990/ 37905 | consumed samples: 4605440 | consumed tokens: 9431941120 | elapsed time per iteration (s): 0.23 | learning rate: 1.187E-04 | global batch size: 256 | lm loss: 3.382702E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.797 | TFLOPs: 28.07 | +0: [2022-11-29 18:07:34,109] [INFO] [logging.py:68:log_dist] [Rank 0] step=18000, skipped=0, lr=[0.00011859190008696891, 0.00011859190008696891, 0.00011859190008696891], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +0: steps: 18000 loss: 3.4652 iter time (s): 0.259 samples/sec: 990.051 +7: iteration 18000/ 37905 | consumed samples: 4608000 | consumed tokens: 9437184000 | elapsed time per iteration (s): 0.23 | learning rate: 1.186E-04 | global batch size: 256 | lm loss: 3.422021E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.254 | TFLOPs: 28.21 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 18000 | lm loss value: 3.205813E+00 | lm loss PPL: 2.467555E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 18000 to checkpoints_83moscar +0: [2022-11-29 18:07:34,264] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step18000 is begin to save! +0: [2022-11-29 18:07:34,284] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:07:34,357] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:07:34,358] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:07:34,371] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:07:34,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:07:34,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:07:34,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:07:34,393] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:07:34,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:07:34,404] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:07:34,404] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:07:34,416] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:07:34,416] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:07:34,427] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:07:34,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:07:34,438] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:07:34,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:07:34,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:07:34,450] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:07:34,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:07:34,461] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:07:34,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:07:34,472] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:07:34,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:07:34,474] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step18000/mp_rank_00_model_states.pt +0: [2022-11-29 18:07:34,474] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:07:34,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:07:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:07:34,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:07:34,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:07:34,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +4: [2022-11-29 18:07:34,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:07:34,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +4: [2022-11-29 18:07:34,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:07:34,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +0: [2022-11-29 18:07:34,516] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:07:34,516] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:07:34,516] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +4: [2022-11-29 18:07:34,516] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:07:34,516] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:07:34,516] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +0: [2022-11-29 18:07:34,516] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:07:34,516] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:07:34,516] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:07:34,516] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +0: [2022-11-29 18:07:34,516] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +0: [2022-11-29 18:07:34,516] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:07:34,516] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:07:34,516] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +4: [2022-11-29 18:07:34,516] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:07:34,516] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:07:34,516] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +0: [2022-11-29 18:07:34,517] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:07:34,517] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:07:34,517] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +0: [2022-11-29 18:07:34,517] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +4: [2022-11-29 18:07:34,517] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +0: [2022-11-29 18:07:34,517] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +7: [2022-11-29 18:07:34,517] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:07:34,517] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:07:34,517] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +7: [2022-11-29 18:07:34,517] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:07:34,517] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:07:34,517] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:07:34,517] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +4: [2022-11-29 18:07:34,517] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +7: [2022-11-29 18:07:34,517] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +4: [2022-11-29 18:07:34,517] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:07:34,517] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +4: [2022-11-29 18:07:34,517] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +0: [2022-11-29 18:07:34,517] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:07:34,518] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:07:34,518] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +7: [2022-11-29 18:07:34,517] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:07:34,518] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:07:34,518] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +7: [2022-11-29 18:07:34,518] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:07:34,518] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:07:34,518] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +7: [2022-11-29 18:07:34,518] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:07:34,518] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:07:34,518] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +0: [2022-11-29 18:07:34,518] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:07:34,518] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:07:34,518] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +4: [2022-11-29 18:07:34,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:07:34,519] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +7: [2022-11-29 18:07:34,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:07:34,519] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +7: [2022-11-29 18:07:34,519] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:07:34,519] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +7: [2022-11-29 18:07:34,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:07:34,519] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:07:34,519] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +4: [2022-11-29 18:07:34,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:07:34,519] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:07:34,520] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +7: [2022-11-29 18:07:34,520] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:07:34,520] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:07:34,520] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +3: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:07:34,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:07:34,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:07:34,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:07:34,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:07:34,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:07:34,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:07:34,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +3: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +3: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +3: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +3: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +3: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +3: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +3: [2022-11-29 18:07:34,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +2: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +2: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:07:34,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:07:34,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:07:34,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:07:34,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:07:34,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:07:34,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +2: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:07:34,699] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:07:34,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +2: [2022-11-29 18:07:34,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:07:34,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +2: [2022-11-29 18:07:34,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +2: [2022-11-29 18:07:34,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +2: [2022-11-29 18:07:34,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +2: [2022-11-29 18:07:34,699] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:07:34,699] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:07:34,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +2: [2022-11-29 18:07:34,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +5: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:07:34,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:07:34,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:07:34,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:07:34,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:07:34,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:07:34,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:07:34,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +5: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +6: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +6: [2022-11-29 18:07:34,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:07:34,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +5: [2022-11-29 18:07:34,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +6: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +5: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +5: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +5: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +6: [2022-11-29 18:07:34,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:07:34,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +5: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +6: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +6: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +6: [2022-11-29 18:07:34,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:07:34,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +6: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +6: [2022-11-29 18:07:34,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +6: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +6: [2022-11-29 18:07:34,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +6: [2022-11-29 18:07:34,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +1: [2022-11-29 18:07:34,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:07:34,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:07:34,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:07:34,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:07:34,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:07:34,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:07:34,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:07:34,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:07:34,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:07:34,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:07:34,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:07:34,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:07:34,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:07:34,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:07:34,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +1: [2022-11-29 18:07:34,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +1: [2022-11-29 18:07:34,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +1: [2022-11-29 18:07:34,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +1: [2022-11-29 18:07:34,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +1: [2022-11-29 18:07:34,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +1: [2022-11-29 18:07:34,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +1: [2022-11-29 18:07:34,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:07:34,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step18000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:07:34,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +0: successfully saved checkpoint at iteration 18000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 568.07 +7: iteration 18010/ 37905 | consumed samples: 4610560 | consumed tokens: 9442426880 | elapsed time per iteration (s): 0.34 | learning rate: 1.185E-04 | global batch size: 256 | lm loss: 3.391726E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 757.154 | TFLOPs: 19.29 | +7: iteration 18020/ 37905 | consumed samples: 4613120 | consumed tokens: 9447669760 | elapsed time per iteration (s): 0.23 | learning rate: 1.184E-04 | global batch size: 256 | lm loss: 3.408008E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.802 | TFLOPs: 27.79 | +7: iteration 18030/ 37905 | consumed samples: 4615680 | consumed tokens: 9452912640 | elapsed time per iteration (s): 0.24 | learning rate: 1.184E-04 | global batch size: 256 | lm loss: 3.376293E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1052.393 | TFLOPs: 26.81 | +7: iteration 18040/ 37905 | consumed samples: 4618240 | consumed tokens: 9458155520 | elapsed time per iteration (s): 0.24 | learning rate: 1.183E-04 | global batch size: 256 | lm loss: 3.365632E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1053.552 | TFLOPs: 26.84 | +7: iteration 18050/ 37905 | consumed samples: 4620800 | consumed tokens: 9463398400 | elapsed time per iteration (s): 0.27 | learning rate: 1.182E-04 | global batch size: 256 | lm loss: 3.379274E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 962.772 | TFLOPs: 24.53 | +7: iteration 18060/ 37905 | consumed samples: 4623360 | consumed tokens: 9468641280 | elapsed time per iteration (s): 0.26 | learning rate: 1.181E-04 | global batch size: 256 | lm loss: 3.398405E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 984.875 | TFLOPs: 25.09 | +7: iteration 18070/ 37905 | consumed samples: 4625920 | consumed tokens: 9473884160 | elapsed time per iteration (s): 0.25 | learning rate: 1.181E-04 | global batch size: 256 | lm loss: 3.376603E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1020.917 | TFLOPs: 26.01 | +7: iteration 18080/ 37905 | consumed samples: 4628480 | consumed tokens: 9479127040 | elapsed time per iteration (s): 0.30 | learning rate: 1.180E-04 | global batch size: 256 | lm loss: 3.375725E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 844.104 | TFLOPs: 21.50 | +7: iteration 18090/ 37905 | consumed samples: 4631040 | consumed tokens: 9484369920 | elapsed time per iteration (s): 0.23 | learning rate: 1.179E-04 | global batch size: 256 | lm loss: 3.400861E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.288 | TFLOPs: 28.44 | +7: iteration 18100/ 37905 | consumed samples: 4633600 | consumed tokens: 9489612800 | elapsed time per iteration (s): 0.25 | learning rate: 1.178E-04 | global batch size: 256 | lm loss: 3.348798E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1017.353 | TFLOPs: 25.92 | +7: iteration 18110/ 37905 | consumed samples: 4636160 | consumed tokens: 9494855680 | elapsed time per iteration (s): 0.23 | learning rate: 1.178E-04 | global batch size: 256 | lm loss: 3.392655E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.905 | TFLOPs: 28.48 | +7: iteration 18120/ 37905 | consumed samples: 4638720 | consumed tokens: 9500098560 | elapsed time per iteration (s): 0.24 | learning rate: 1.177E-04 | global batch size: 256 | lm loss: 3.388160E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.761 | TFLOPs: 27.74 | +7: iteration 18130/ 37905 | consumed samples: 4641280 | consumed tokens: 9505341440 | elapsed time per iteration (s): 0.23 | learning rate: 1.176E-04 | global batch size: 256 | lm loss: 3.410946E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.068 | TFLOPs: 28.23 | +7: iteration 18140/ 37905 | consumed samples: 4643840 | consumed tokens: 9510584320 | elapsed time per iteration (s): 0.23 | learning rate: 1.175E-04 | global batch size: 256 | lm loss: 3.366737E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.322 | TFLOPs: 27.90 | +7: iteration 18150/ 37905 | consumed samples: 4646400 | consumed tokens: 9515827200 | elapsed time per iteration (s): 0.23 | learning rate: 1.175E-04 | global batch size: 256 | lm loss: 3.377418E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.202 | TFLOPs: 28.10 | +7: iteration 18160/ 37905 | consumed samples: 4648960 | consumed tokens: 9521070080 | elapsed time per iteration (s): 0.24 | learning rate: 1.174E-04 | global batch size: 256 | lm loss: 3.387524E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1075.716 | TFLOPs: 27.40 | +7: iteration 18170/ 37905 | consumed samples: 4651520 | consumed tokens: 9526312960 | elapsed time per iteration (s): 0.23 | learning rate: 1.173E-04 | global batch size: 256 | lm loss: 3.391854E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.360 | TFLOPs: 28.01 | +7: iteration 18180/ 37905 | consumed samples: 4654080 | consumed tokens: 9531555840 | elapsed time per iteration (s): 0.23 | learning rate: 1.172E-04 | global batch size: 256 | lm loss: 3.394557E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.135 | TFLOPs: 27.85 | +7: iteration 18190/ 37905 | consumed samples: 4656640 | consumed tokens: 9536798720 | elapsed time per iteration (s): 0.24 | learning rate: 1.172E-04 | global batch size: 256 | lm loss: 3.387508E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1072.390 | TFLOPs: 27.32 | +7: iteration 18200/ 37905 | consumed samples: 4659200 | consumed tokens: 9542041600 | elapsed time per iteration (s): 0.24 | learning rate: 1.171E-04 | global batch size: 256 | lm loss: 3.390157E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.451 | TFLOPs: 27.70 | +7: iteration 18210/ 37905 | consumed samples: 4661760 | consumed tokens: 9547284480 | elapsed time per iteration (s): 0.23 | learning rate: 1.170E-04 | global batch size: 256 | lm loss: 3.401687E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.621 | TFLOPs: 28.04 | +7: iteration 18220/ 37905 | consumed samples: 4664320 | consumed tokens: 9552527360 | elapsed time per iteration (s): 0.23 | learning rate: 1.169E-04 | global batch size: 256 | lm loss: 3.390031E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.137 | TFLOPs: 27.80 | +7: iteration 18230/ 37905 | consumed samples: 4666880 | consumed tokens: 9557770240 | elapsed time per iteration (s): 0.23 | learning rate: 1.169E-04 | global batch size: 256 | lm loss: 3.389574E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.530 | TFLOPs: 28.52 | +7: iteration 18240/ 37905 | consumed samples: 4669440 | consumed tokens: 9563013120 | elapsed time per iteration (s): 0.23 | learning rate: 1.168E-04 | global batch size: 256 | lm loss: 3.396347E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.895 | TFLOPs: 28.33 | +7: iteration 18250/ 37905 | consumed samples: 4672000 | consumed tokens: 9568256000 | elapsed time per iteration (s): 0.23 | learning rate: 1.167E-04 | global batch size: 256 | lm loss: 3.380313E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.791 | TFLOPs: 28.50 | +7: iteration 18260/ 37905 | consumed samples: 4674560 | consumed tokens: 9573498880 | elapsed time per iteration (s): 0.24 | learning rate: 1.166E-04 | global batch size: 256 | lm loss: 3.421403E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.150 | TFLOPs: 27.70 | +7: iteration 18270/ 37905 | consumed samples: 4677120 | consumed tokens: 9578741760 | elapsed time per iteration (s): 0.23 | learning rate: 1.166E-04 | global batch size: 256 | lm loss: 3.397028E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.475 | TFLOPs: 28.42 | +7: iteration 18280/ 37905 | consumed samples: 4679680 | consumed tokens: 9583984640 | elapsed time per iteration (s): 0.23 | learning rate: 1.165E-04 | global batch size: 256 | lm loss: 3.398433E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.460 | TFLOPs: 28.29 | +7: iteration 18290/ 37905 | consumed samples: 4682240 | consumed tokens: 9589227520 | elapsed time per iteration (s): 0.23 | learning rate: 1.164E-04 | global batch size: 256 | lm loss: 3.400359E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.357 | TFLOPs: 28.52 | +7: iteration 18300/ 37905 | consumed samples: 4684800 | consumed tokens: 9594470400 | elapsed time per iteration (s): 0.23 | learning rate: 1.163E-04 | global batch size: 256 | lm loss: 3.395024E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.443 | TFLOPs: 28.39 | +7: iteration 18310/ 37905 | consumed samples: 4687360 | consumed tokens: 9599713280 | elapsed time per iteration (s): 0.23 | learning rate: 1.163E-04 | global batch size: 256 | lm loss: 3.370727E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.796 | TFLOPs: 28.40 | +7: iteration 18320/ 37905 | consumed samples: 4689920 | consumed tokens: 9604956160 | elapsed time per iteration (s): 0.23 | learning rate: 1.162E-04 | global batch size: 256 | lm loss: 3.386414E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.999 | TFLOPs: 28.30 | +7: iteration 18330/ 37905 | consumed samples: 4692480 | consumed tokens: 9610199040 | elapsed time per iteration (s): 0.23 | learning rate: 1.161E-04 | global batch size: 256 | lm loss: 3.377211E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.860 | TFLOPs: 27.99 | +7: iteration 18340/ 37905 | consumed samples: 4695040 | consumed tokens: 9615441920 | elapsed time per iteration (s): 0.23 | learning rate: 1.160E-04 | global batch size: 256 | lm loss: 3.370565E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.471 | TFLOPs: 28.31 | +7: iteration 18350/ 37905 | consumed samples: 4697600 | consumed tokens: 9620684800 | elapsed time per iteration (s): 0.23 | learning rate: 1.160E-04 | global batch size: 256 | lm loss: 3.385668E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.442 | TFLOPs: 27.80 | +7: iteration 18360/ 37905 | consumed samples: 4700160 | consumed tokens: 9625927680 | elapsed time per iteration (s): 0.23 | learning rate: 1.159E-04 | global batch size: 256 | lm loss: 3.405783E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.075 | TFLOPs: 27.92 | +7: iteration 18370/ 37905 | consumed samples: 4702720 | consumed tokens: 9631170560 | elapsed time per iteration (s): 0.24 | learning rate: 1.158E-04 | global batch size: 256 | lm loss: 3.387815E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1062.581 | TFLOPs: 27.07 | +7: iteration 18380/ 37905 | consumed samples: 4705280 | consumed tokens: 9636413440 | elapsed time per iteration (s): 0.23 | learning rate: 1.157E-04 | global batch size: 256 | lm loss: 3.382199E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.032 | TFLOPs: 28.05 | +7: iteration 18390/ 37905 | consumed samples: 4707840 | consumed tokens: 9641656320 | elapsed time per iteration (s): 0.23 | learning rate: 1.157E-04 | global batch size: 256 | lm loss: 3.366621E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.677 | TFLOPs: 28.22 | +7: iteration 18400/ 37905 | consumed samples: 4710400 | consumed tokens: 9646899200 | elapsed time per iteration (s): 0.27 | learning rate: 1.156E-04 | global batch size: 256 | lm loss: 3.362809E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 959.757 | TFLOPs: 24.45 | +7: iteration 18410/ 37905 | consumed samples: 4712960 | consumed tokens: 9652142080 | elapsed time per iteration (s): 0.23 | learning rate: 1.155E-04 | global batch size: 256 | lm loss: 3.410767E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.896 | TFLOPs: 28.40 | +7: iteration 18420/ 37905 | consumed samples: 4715520 | consumed tokens: 9657384960 | elapsed time per iteration (s): 0.23 | learning rate: 1.154E-04 | global batch size: 256 | lm loss: 3.379261E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.493 | TFLOPs: 27.76 | +7: iteration 18430/ 37905 | consumed samples: 4718080 | consumed tokens: 9662627840 | elapsed time per iteration (s): 0.26 | learning rate: 1.154E-04 | global batch size: 256 | lm loss: 3.389709E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 985.096 | TFLOPs: 25.10 | +7: iteration 18440/ 37905 | consumed samples: 4720640 | consumed tokens: 9667870720 | elapsed time per iteration (s): 0.23 | learning rate: 1.153E-04 | global batch size: 256 | lm loss: 3.400084E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.453 | TFLOPs: 28.29 | +7: iteration 18450/ 37905 | consumed samples: 4723200 | consumed tokens: 9673113600 | elapsed time per iteration (s): 0.25 | learning rate: 1.152E-04 | global batch size: 256 | lm loss: 3.382677E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1037.881 | TFLOPs: 26.44 | +7: iteration 18460/ 37905 | consumed samples: 4725760 | consumed tokens: 9678356480 | elapsed time per iteration (s): 0.23 | learning rate: 1.151E-04 | global batch size: 256 | lm loss: 3.386284E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.853 | TFLOPs: 28.43 | +7: iteration 18470/ 37905 | consumed samples: 4728320 | consumed tokens: 9683599360 | elapsed time per iteration (s): 0.23 | learning rate: 1.151E-04 | global batch size: 256 | lm loss: 3.354767E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.774 | TFLOPs: 28.35 | +7: iteration 18480/ 37905 | consumed samples: 4730880 | consumed tokens: 9688842240 | elapsed time per iteration (s): 0.23 | learning rate: 1.150E-04 | global batch size: 256 | lm loss: 3.378470E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.367 | TFLOPs: 28.36 | +7: iteration 18490/ 37905 | consumed samples: 4733440 | consumed tokens: 9694085120 | elapsed time per iteration (s): 0.27 | learning rate: 1.149E-04 | global batch size: 256 | lm loss: 3.385324E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 963.001 | TFLOPs: 24.53 | +7: iteration 18500/ 37905 | consumed samples: 4736000 | consumed tokens: 9699328000 | elapsed time per iteration (s): 0.23 | learning rate: 1.148E-04 | global batch size: 256 | lm loss: 3.408551E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.985 | TFLOPs: 28.28 | +7: iteration 18510/ 37905 | consumed samples: 4738560 | consumed tokens: 9704570880 | elapsed time per iteration (s): 0.25 | learning rate: 1.148E-04 | global batch size: 256 | lm loss: 3.382239E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1043.550 | TFLOPs: 26.58 | +7: iteration 18520/ 37905 | consumed samples: 4741120 | consumed tokens: 9709813760 | elapsed time per iteration (s): 0.23 | learning rate: 1.147E-04 | global batch size: 256 | lm loss: 3.391525E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.086 | TFLOPs: 27.90 | +7: iteration 18530/ 37905 | consumed samples: 4743680 | consumed tokens: 9715056640 | elapsed time per iteration (s): 0.24 | learning rate: 1.146E-04 | global batch size: 256 | lm loss: 3.397136E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1048.416 | TFLOPs: 26.71 | +7: iteration 18540/ 37905 | consumed samples: 4746240 | consumed tokens: 9720299520 | elapsed time per iteration (s): 0.23 | learning rate: 1.145E-04 | global batch size: 256 | lm loss: 3.409557E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.764 | TFLOPs: 27.97 | +7: iteration 18550/ 37905 | consumed samples: 4748800 | consumed tokens: 9725542400 | elapsed time per iteration (s): 0.24 | learning rate: 1.145E-04 | global batch size: 256 | lm loss: 3.363487E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1080.961 | TFLOPs: 27.54 | +7: iteration 18560/ 37905 | consumed samples: 4751360 | consumed tokens: 9730785280 | elapsed time per iteration (s): 0.23 | learning rate: 1.144E-04 | global batch size: 256 | lm loss: 3.393708E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.607 | TFLOPs: 27.86 | +7: iteration 18570/ 37905 | consumed samples: 4753920 | consumed tokens: 9736028160 | elapsed time per iteration (s): 0.23 | learning rate: 1.143E-04 | global batch size: 256 | lm loss: 3.378032E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.489 | TFLOPs: 27.91 | +7: iteration 18580/ 37905 | consumed samples: 4756480 | consumed tokens: 9741271040 | elapsed time per iteration (s): 0.23 | learning rate: 1.142E-04 | global batch size: 256 | lm loss: 3.385548E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.049 | TFLOPs: 27.87 | +7: iteration 18590/ 37905 | consumed samples: 4759040 | consumed tokens: 9746513920 | elapsed time per iteration (s): 0.23 | learning rate: 1.142E-04 | global batch size: 256 | lm loss: 3.356482E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.394 | TFLOPs: 28.08 | +7: iteration 18600/ 37905 | consumed samples: 4761600 | consumed tokens: 9751756800 | elapsed time per iteration (s): 0.23 | learning rate: 1.141E-04 | global batch size: 256 | lm loss: 3.388103E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.204 | TFLOPs: 27.82 | +7: iteration 18610/ 37905 | consumed samples: 4764160 | consumed tokens: 9756999680 | elapsed time per iteration (s): 0.24 | learning rate: 1.140E-04 | global batch size: 256 | lm loss: 3.409237E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1082.467 | TFLOPs: 27.58 | +7: iteration 18620/ 37905 | consumed samples: 4766720 | consumed tokens: 9762242560 | elapsed time per iteration (s): 0.23 | learning rate: 1.139E-04 | global batch size: 256 | lm loss: 3.359496E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.716 | TFLOPs: 28.30 | +7: iteration 18630/ 37905 | consumed samples: 4769280 | consumed tokens: 9767485440 | elapsed time per iteration (s): 0.23 | learning rate: 1.139E-04 | global batch size: 256 | lm loss: 3.410343E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.666 | TFLOPs: 28.14 | +7: iteration 18640/ 37905 | consumed samples: 4771840 | consumed tokens: 9772728320 | elapsed time per iteration (s): 0.24 | learning rate: 1.138E-04 | global batch size: 256 | lm loss: 3.397137E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1084.498 | TFLOPs: 27.63 | +7: iteration 18650/ 37905 | consumed samples: 4774400 | consumed tokens: 9777971200 | elapsed time per iteration (s): 0.23 | learning rate: 1.137E-04 | global batch size: 256 | lm loss: 3.361926E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.577 | TFLOPs: 28.34 | +7: iteration 18660/ 37905 | consumed samples: 4776960 | consumed tokens: 9783214080 | elapsed time per iteration (s): 0.23 | learning rate: 1.136E-04 | global batch size: 256 | lm loss: 3.401418E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.684 | TFLOPs: 28.14 | +7: iteration 18670/ 37905 | consumed samples: 4779520 | consumed tokens: 9788456960 | elapsed time per iteration (s): 0.24 | learning rate: 1.136E-04 | global batch size: 256 | lm loss: 3.376082E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1061.313 | TFLOPs: 27.04 | +7: iteration 18680/ 37905 | consumed samples: 4782080 | consumed tokens: 9793699840 | elapsed time per iteration (s): 0.23 | learning rate: 1.135E-04 | global batch size: 256 | lm loss: 3.352880E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.878 | TFLOPs: 28.12 | +7: iteration 18690/ 37905 | consumed samples: 4784640 | consumed tokens: 9798942720 | elapsed time per iteration (s): 0.23 | learning rate: 1.134E-04 | global batch size: 256 | lm loss: 3.370768E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.364 | TFLOPs: 28.39 | +7: iteration 18700/ 37905 | consumed samples: 4787200 | consumed tokens: 9804185600 | elapsed time per iteration (s): 0.23 | learning rate: 1.133E-04 | global batch size: 256 | lm loss: 3.386808E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.285 | TFLOPs: 27.83 | +7: iteration 18710/ 37905 | consumed samples: 4789760 | consumed tokens: 9809428480 | elapsed time per iteration (s): 0.23 | learning rate: 1.133E-04 | global batch size: 256 | lm loss: 3.386613E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.760 | TFLOPs: 28.07 | +7: iteration 18720/ 37905 | consumed samples: 4792320 | consumed tokens: 9814671360 | elapsed time per iteration (s): 0.23 | learning rate: 1.132E-04 | global batch size: 256 | lm loss: 3.373566E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.131 | TFLOPs: 27.98 | +7: iteration 18730/ 37905 | consumed samples: 4794880 | consumed tokens: 9819914240 | elapsed time per iteration (s): 0.23 | learning rate: 1.131E-04 | global batch size: 256 | lm loss: 3.362193E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.666 | TFLOPs: 28.22 | +7: iteration 18740/ 37905 | consumed samples: 4797440 | consumed tokens: 9825157120 | elapsed time per iteration (s): 0.24 | learning rate: 1.130E-04 | global batch size: 256 | lm loss: 3.369204E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.659 | TFLOPs: 27.73 | +7: iteration 18750/ 37905 | consumed samples: 4800000 | consumed tokens: 9830400000 | elapsed time per iteration (s): 0.23 | learning rate: 1.130E-04 | global batch size: 256 | lm loss: 3.384335E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.120 | TFLOPs: 28.18 | +7: iteration 18760/ 37905 | consumed samples: 4802560 | consumed tokens: 9835642880 | elapsed time per iteration (s): 0.24 | learning rate: 1.129E-04 | global batch size: 256 | lm loss: 3.354095E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1066.307 | TFLOPs: 27.16 | +7: iteration 18770/ 37905 | consumed samples: 4805120 | consumed tokens: 9840885760 | elapsed time per iteration (s): 0.23 | learning rate: 1.128E-04 | global batch size: 256 | lm loss: 3.388953E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.046 | TFLOPs: 28.13 | +7: iteration 18780/ 37905 | consumed samples: 4807680 | consumed tokens: 9846128640 | elapsed time per iteration (s): 0.23 | learning rate: 1.127E-04 | global batch size: 256 | lm loss: 3.368798E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.181 | TFLOPs: 28.21 | +7: iteration 18790/ 37905 | consumed samples: 4810240 | consumed tokens: 9851371520 | elapsed time per iteration (s): 0.23 | learning rate: 1.127E-04 | global batch size: 256 | lm loss: 3.373659E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.265 | TFLOPs: 28.23 | +7: iteration 18800/ 37905 | consumed samples: 4812800 | consumed tokens: 9856614400 | elapsed time per iteration (s): 0.23 | learning rate: 1.126E-04 | global batch size: 256 | lm loss: 3.375288E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.632 | TFLOPs: 28.01 | +7: iteration 18810/ 37905 | consumed samples: 4815360 | consumed tokens: 9861857280 | elapsed time per iteration (s): 0.23 | learning rate: 1.125E-04 | global batch size: 256 | lm loss: 3.381054E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.744 | TFLOPs: 28.30 | +7: iteration 18820/ 37905 | consumed samples: 4817920 | consumed tokens: 9867100160 | elapsed time per iteration (s): 0.23 | learning rate: 1.124E-04 | global batch size: 256 | lm loss: 3.405235E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.379 | TFLOPs: 28.44 | +7: iteration 18830/ 37905 | consumed samples: 4820480 | consumed tokens: 9872343040 | elapsed time per iteration (s): 0.23 | learning rate: 1.124E-04 | global batch size: 256 | lm loss: 3.372877E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.071 | TFLOPs: 27.82 | +7: iteration 18840/ 37905 | consumed samples: 4823040 | consumed tokens: 9877585920 | elapsed time per iteration (s): 0.23 | learning rate: 1.123E-04 | global batch size: 256 | lm loss: 3.349292E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.020 | TFLOPs: 28.46 | +7: iteration 18850/ 37905 | consumed samples: 4825600 | consumed tokens: 9882828800 | elapsed time per iteration (s): 0.23 | learning rate: 1.122E-04 | global batch size: 256 | lm loss: 3.364623E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.590 | TFLOPs: 28.47 | +7: iteration 18860/ 37905 | consumed samples: 4828160 | consumed tokens: 9888071680 | elapsed time per iteration (s): 0.25 | learning rate: 1.121E-04 | global batch size: 256 | lm loss: 3.380617E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1030.185 | TFLOPs: 26.24 | +7: iteration 18870/ 37905 | consumed samples: 4830720 | consumed tokens: 9893314560 | elapsed time per iteration (s): 0.24 | learning rate: 1.120E-04 | global batch size: 256 | lm loss: 3.391520E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1060.343 | TFLOPs: 27.01 | +7: iteration 18880/ 37905 | consumed samples: 4833280 | consumed tokens: 9898557440 | elapsed time per iteration (s): 0.25 | learning rate: 1.120E-04 | global batch size: 256 | lm loss: 3.377541E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1012.238 | TFLOPs: 25.79 | +7: iteration 18890/ 37905 | consumed samples: 4835840 | consumed tokens: 9903800320 | elapsed time per iteration (s): 0.23 | learning rate: 1.119E-04 | global batch size: 256 | lm loss: 3.393000E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.545 | TFLOPs: 28.50 | +7: iteration 18900/ 37905 | consumed samples: 4838400 | consumed tokens: 9909043200 | elapsed time per iteration (s): 0.23 | learning rate: 1.118E-04 | global batch size: 256 | lm loss: 3.381573E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.092 | TFLOPs: 28.20 | +7: iteration 18910/ 37905 | consumed samples: 4840960 | consumed tokens: 9914286080 | elapsed time per iteration (s): 0.23 | learning rate: 1.117E-04 | global batch size: 256 | lm loss: 3.370177E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.732 | TFLOPs: 28.25 | +7: iteration 18920/ 37905 | consumed samples: 4843520 | consumed tokens: 9919528960 | elapsed time per iteration (s): 0.23 | learning rate: 1.117E-04 | global batch size: 256 | lm loss: 3.384044E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.530 | TFLOPs: 27.83 | +7: iteration 18930/ 37905 | consumed samples: 4846080 | consumed tokens: 9924771840 | elapsed time per iteration (s): 0.23 | learning rate: 1.116E-04 | global batch size: 256 | lm loss: 3.385414E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.110 | TFLOPs: 28.05 | +7: iteration 18940/ 37905 | consumed samples: 4848640 | consumed tokens: 9930014720 | elapsed time per iteration (s): 0.23 | learning rate: 1.115E-04 | global batch size: 256 | lm loss: 3.396514E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.549 | TFLOPs: 27.86 | +7: iteration 18950/ 37905 | consumed samples: 4851200 | consumed tokens: 9935257600 | elapsed time per iteration (s): 0.23 | learning rate: 1.114E-04 | global batch size: 256 | lm loss: 3.390842E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.579 | TFLOPs: 28.06 | +7: iteration 18960/ 37905 | consumed samples: 4853760 | consumed tokens: 9940500480 | elapsed time per iteration (s): 0.23 | learning rate: 1.114E-04 | global batch size: 256 | lm loss: 3.372091E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.189 | TFLOPs: 27.87 | +7: iteration 18970/ 37905 | consumed samples: 4856320 | consumed tokens: 9945743360 | elapsed time per iteration (s): 0.23 | learning rate: 1.113E-04 | global batch size: 256 | lm loss: 3.427357E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.084 | TFLOPs: 28.25 | +7: iteration 18980/ 37905 | consumed samples: 4858880 | consumed tokens: 9950986240 | elapsed time per iteration (s): 0.23 | learning rate: 1.112E-04 | global batch size: 256 | lm loss: 3.398173E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.452 | TFLOPs: 28.03 | +7: iteration 18990/ 37905 | consumed samples: 4861440 | consumed tokens: 9956229120 | elapsed time per iteration (s): 0.23 | learning rate: 1.111E-04 | global batch size: 256 | lm loss: 3.406767E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.021 | TFLOPs: 28.07 | +7: iteration 19000/ 37905 | consumed samples: 4864000 | consumed tokens: 9961472000 | elapsed time per iteration (s): 0.23 | learning rate: 1.111E-04 | global batch size: 256 | lm loss: 3.373698E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.404 | TFLOPs: 28.21 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 19000 | lm loss value: 3.317328E+00 | lm loss PPL: 2.758654E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 19000 to checkpoints_83moscar +0: [2022-11-29 18:11:31,531] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step19000 is begin to save! +0: [2022-11-29 18:11:31,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:11:31,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:11:31,628] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:11:31,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:11:31,642] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:11:31,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:11:31,654] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:11:31,666] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:11:31,666] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:11:31,678] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:11:31,678] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:11:31,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:11:31,690] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:11:31,702] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:11:31,703] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:11:31,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:11:31,715] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:11:31,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:11:31,727] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:11:31,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:11:31,739] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:11:31,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:11:31,751] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:11:31,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:11:31,753] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step19000/mp_rank_00_model_states.pt +0: [2022-11-29 18:11:31,753] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:11:31,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:11:31,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:11:31,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:11:31,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:11:31,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +5: [2022-11-29 18:11:31,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:11:31,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:11:31,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +7: [2022-11-29 18:11:31,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:11:31,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:11:31,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +3: [2022-11-29 18:11:31,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:11:31,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:11:31,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +0: [2022-11-29 18:11:31,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:11:31,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:11:31,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:11:31,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +1: [2022-11-29 18:11:31,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +6: [2022-11-29 18:11:31,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +1: [2022-11-29 18:11:31,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +4: [2022-11-29 18:11:31,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:11:31,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:11:31,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +3: [2022-11-29 18:11:31,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:11:31,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:11:31,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +7: [2022-11-29 18:11:31,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:11:31,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:11:31,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +0: [2022-11-29 18:11:31,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:11:31,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +1: [2022-11-29 18:11:31,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:11:31,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +6: [2022-11-29 18:11:31,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:11:31,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +6: [2022-11-29 18:11:31,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:11:31,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +0: [2022-11-29 18:11:31,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:11:31,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:11:31,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +4: [2022-11-29 18:11:31,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:11:31,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:11:31,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +5: [2022-11-29 18:11:31,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:11:31,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:11:31,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +7: [2022-11-29 18:11:31,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:11:31,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:11:31,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +3: [2022-11-29 18:11:31,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:11:31,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:11:31,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +6: [2022-11-29 18:11:31,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:11:31,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:11:31,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +1: [2022-11-29 18:11:31,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:11:31,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:11:31,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +0: [2022-11-29 18:11:31,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:11:31,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:11:31,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +5: [2022-11-29 18:11:31,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +4: [2022-11-29 18:11:31,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:11:31,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +5: [2022-11-29 18:11:31,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +4: [2022-11-29 18:11:31,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:11:31,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +4: [2022-11-29 18:11:31,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:11:31,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:11:31,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +6: [2022-11-29 18:11:31,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:11:31,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:11:31,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +0: [2022-11-29 18:11:31,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:11:31,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:11:31,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +7: [2022-11-29 18:11:31,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:11:31,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:11:31,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +3: [2022-11-29 18:11:31,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:11:31,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:11:31,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +5: [2022-11-29 18:11:31,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:11:31,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:11:31,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +7: [2022-11-29 18:11:31,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:11:31,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:11:31,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +0: [2022-11-29 18:11:31,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:11:31,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:11:31,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +1: [2022-11-29 18:11:31,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:11:31,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:11:31,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +5: [2022-11-29 18:11:31,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:11:31,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:11:31,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +3: [2022-11-29 18:11:31,804] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +5: [2022-11-29 18:11:31,804] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +3: [2022-11-29 18:11:31,804] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +1: [2022-11-29 18:11:31,805] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:11:31,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:11:31,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +6: [2022-11-29 18:11:31,806] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:11:31,806] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:11:31,806] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +4: [2022-11-29 18:11:31,806] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:11:31,806] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:11:31,806] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +0: [2022-11-29 18:11:31,806] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:11:31,806] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:11:31,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +5: [2022-11-29 18:11:31,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +0: [2022-11-29 18:11:31,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +5: [2022-11-29 18:11:31,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +7: [2022-11-29 18:11:31,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:11:31,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:11:31,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +3: [2022-11-29 18:11:31,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:11:31,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:11:31,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +1: [2022-11-29 18:11:31,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:11:31,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:11:31,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +4: [2022-11-29 18:11:31,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:11:31,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:11:31,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +6: [2022-11-29 18:11:31,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:11:31,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:11:31,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +3: [2022-11-29 18:11:31,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:11:31,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:11:31,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:11:31,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:11:31,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:11:31,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +5: [2022-11-29 18:11:31,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:11:31,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +0: [2022-11-29 18:11:31,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3: [2022-11-29 18:11:31,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:11:31,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +5: [2022-11-29 18:11:31,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +5: [2022-11-29 18:11:31,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +3: [2022-11-29 18:11:31,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:11:31,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +4: [2022-11-29 18:11:31,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:11:31,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:11:31,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +7: [2022-11-29 18:11:31,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:11:31,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:11:31,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +0: [2022-11-29 18:11:31,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:11:31,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:11:31,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +7: [2022-11-29 18:11:31,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:11:31,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:11:31,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +6: [2022-11-29 18:11:31,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:11:31,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:11:31,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +4: [2022-11-29 18:11:31,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:11:31,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:11:31,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +6: [2022-11-29 18:11:31,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:11:31,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:11:31,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +2: [2022-11-29 18:11:31,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:11:31,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:11:31,812] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:11:31,812] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:11:31,812] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +2: [2022-11-29 18:11:31,812] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +2: [2022-11-29 18:11:31,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:11:31,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:11:31,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +2: [2022-11-29 18:11:31,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:11:31,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:11:31,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:11:31,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:11:31,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:11:31,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +2: [2022-11-29 18:11:31,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +2: [2022-11-29 18:11:31,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:11:31,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:11:31,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:11:31,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +2: [2022-11-29 18:11:31,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +2: [2022-11-29 18:11:31,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:11:31,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:11:31,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +1: [2022-11-29 18:11:31,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:11:31,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step19000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:11:31,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +0: successfully saved checkpoint at iteration 19000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 289.71 +7: iteration 19010/ 37905 | consumed samples: 4866560 | consumed tokens: 9966714880 | elapsed time per iteration (s): 0.27 | learning rate: 1.110E-04 | global batch size: 256 | lm loss: 3.359549E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 933.722 | TFLOPs: 23.79 | +7: iteration 19020/ 37905 | consumed samples: 4869120 | consumed tokens: 9971957760 | elapsed time per iteration (s): 0.23 | learning rate: 1.109E-04 | global batch size: 256 | lm loss: 3.395628E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.934 | TFLOPs: 28.30 | +7: iteration 19030/ 37905 | consumed samples: 4871680 | consumed tokens: 9977200640 | elapsed time per iteration (s): 0.24 | learning rate: 1.108E-04 | global batch size: 256 | lm loss: 3.392034E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.587 | TFLOPs: 27.68 | +7: iteration 19040/ 37905 | consumed samples: 4874240 | consumed tokens: 9982443520 | elapsed time per iteration (s): 0.23 | learning rate: 1.108E-04 | global batch size: 256 | lm loss: 3.374979E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.236 | TFLOPs: 28.26 | +7: iteration 19050/ 37905 | consumed samples: 4876800 | consumed tokens: 9987686400 | elapsed time per iteration (s): 0.23 | learning rate: 1.107E-04 | global batch size: 256 | lm loss: 3.364996E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.947 | TFLOPs: 28.33 | +7: iteration 19060/ 37905 | consumed samples: 4879360 | consumed tokens: 9992929280 | elapsed time per iteration (s): 0.23 | learning rate: 1.106E-04 | global batch size: 256 | lm loss: 3.375139E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.216 | TFLOPs: 28.41 | +7: iteration 19070/ 37905 | consumed samples: 4881920 | consumed tokens: 9998172160 | elapsed time per iteration (s): 0.23 | learning rate: 1.105E-04 | global batch size: 256 | lm loss: 3.398404E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.515 | TFLOPs: 27.96 | +7: iteration 19080/ 37905 | consumed samples: 4884480 | consumed tokens: 10003415040 | elapsed time per iteration (s): 0.23 | learning rate: 1.105E-04 | global batch size: 256 | lm loss: 3.385328E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.674 | TFLOPs: 28.35 | +7: iteration 19090/ 37905 | consumed samples: 4887040 | consumed tokens: 10008657920 | elapsed time per iteration (s): 0.23 | learning rate: 1.104E-04 | global batch size: 256 | lm loss: 3.393145E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.712 | TFLOPs: 28.19 | +7: iteration 19100/ 37905 | consumed samples: 4889600 | consumed tokens: 10013900800 | elapsed time per iteration (s): 0.23 | learning rate: 1.103E-04 | global batch size: 256 | lm loss: 3.387781E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.298 | TFLOPs: 28.31 | +7: iteration 19110/ 37905 | consumed samples: 4892160 | consumed tokens: 10019143680 | elapsed time per iteration (s): 0.23 | learning rate: 1.102E-04 | global batch size: 256 | lm loss: 3.400372E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.251 | TFLOPs: 28.21 | +7: iteration 19120/ 37905 | consumed samples: 4894720 | consumed tokens: 10024386560 | elapsed time per iteration (s): 0.23 | learning rate: 1.102E-04 | global batch size: 256 | lm loss: 3.373184E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.019 | TFLOPs: 28.35 | +7: iteration 19130/ 37905 | consumed samples: 4897280 | consumed tokens: 10029629440 | elapsed time per iteration (s): 0.23 | learning rate: 1.101E-04 | global batch size: 256 | lm loss: 3.381047E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.830 | TFLOPs: 27.92 | +7: iteration 19140/ 37905 | consumed samples: 4899840 | consumed tokens: 10034872320 | elapsed time per iteration (s): 0.23 | learning rate: 1.100E-04 | global batch size: 256 | lm loss: 3.412088E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.064 | TFLOPs: 27.87 | +7: iteration 19150/ 37905 | consumed samples: 4902400 | consumed tokens: 10040115200 | elapsed time per iteration (s): 0.26 | learning rate: 1.099E-04 | global batch size: 256 | lm loss: 3.349136E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 972.798 | TFLOPs: 24.78 | +7: iteration 19160/ 37905 | consumed samples: 4904960 | consumed tokens: 10045358080 | elapsed time per iteration (s): 0.23 | learning rate: 1.099E-04 | global batch size: 256 | lm loss: 3.376294E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.829 | TFLOPs: 28.32 | +7: iteration 19170/ 37905 | consumed samples: 4907520 | consumed tokens: 10050600960 | elapsed time per iteration (s): 0.23 | learning rate: 1.098E-04 | global batch size: 256 | lm loss: 3.386100E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.379 | TFLOPs: 28.11 | +7: iteration 19180/ 37905 | consumed samples: 4910080 | consumed tokens: 10055843840 | elapsed time per iteration (s): 0.23 | learning rate: 1.097E-04 | global batch size: 256 | lm loss: 3.404501E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.980 | TFLOPs: 28.38 | +7: iteration 19190/ 37905 | consumed samples: 4912640 | consumed tokens: 10061086720 | elapsed time per iteration (s): 0.23 | learning rate: 1.096E-04 | global batch size: 256 | lm loss: 3.375172E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.391 | TFLOPs: 28.31 | +7: iteration 19200/ 37905 | consumed samples: 4915200 | consumed tokens: 10066329600 | elapsed time per iteration (s): 0.23 | learning rate: 1.096E-04 | global batch size: 256 | lm loss: 3.392055E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.522 | TFLOPs: 27.99 | +7: iteration 19210/ 37905 | consumed samples: 4917760 | consumed tokens: 10071572480 | elapsed time per iteration (s): 0.23 | learning rate: 1.095E-04 | global batch size: 256 | lm loss: 3.386455E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.802 | TFLOPs: 28.35 | +7: iteration 19220/ 37905 | consumed samples: 4920320 | consumed tokens: 10076815360 | elapsed time per iteration (s): 0.23 | learning rate: 1.094E-04 | global batch size: 256 | lm loss: 3.383587E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.915 | TFLOPs: 28.43 | +7: iteration 19230/ 37905 | consumed samples: 4922880 | consumed tokens: 10082058240 | elapsed time per iteration (s): 0.23 | learning rate: 1.093E-04 | global batch size: 256 | lm loss: 3.352944E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.578 | TFLOPs: 28.32 | +7: iteration 19240/ 37905 | consumed samples: 4925440 | consumed tokens: 10087301120 | elapsed time per iteration (s): 0.23 | learning rate: 1.093E-04 | global batch size: 256 | lm loss: 3.374112E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.145 | TFLOPs: 28.00 | +7: iteration 19250/ 37905 | consumed samples: 4928000 | consumed tokens: 10092544000 | elapsed time per iteration (s): 0.23 | learning rate: 1.092E-04 | global batch size: 256 | lm loss: 3.379364E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.998 | TFLOPs: 28.23 | +7: iteration 19260/ 37905 | consumed samples: 4930560 | consumed tokens: 10097786880 | elapsed time per iteration (s): 0.23 | learning rate: 1.091E-04 | global batch size: 256 | lm loss: 3.378445E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.736 | TFLOPs: 27.94 | +7: iteration 19270/ 37905 | consumed samples: 4933120 | consumed tokens: 10103029760 | elapsed time per iteration (s): 0.23 | learning rate: 1.090E-04 | global batch size: 256 | lm loss: 3.381534E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.159 | TFLOPs: 28.23 | +7: iteration 19280/ 37905 | consumed samples: 4935680 | consumed tokens: 10108272640 | elapsed time per iteration (s): 0.23 | learning rate: 1.090E-04 | global batch size: 256 | lm loss: 3.384371E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.644 | TFLOPs: 28.22 | +7: iteration 19290/ 37905 | consumed samples: 4938240 | consumed tokens: 10113515520 | elapsed time per iteration (s): 0.23 | learning rate: 1.089E-04 | global batch size: 256 | lm loss: 3.385960E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.732 | TFLOPs: 28.12 | +7: iteration 19300/ 37905 | consumed samples: 4940800 | consumed tokens: 10118758400 | elapsed time per iteration (s): 0.23 | learning rate: 1.088E-04 | global batch size: 256 | lm loss: 3.372786E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.670 | TFLOPs: 27.91 | +7: iteration 19310/ 37905 | consumed samples: 4943360 | consumed tokens: 10124001280 | elapsed time per iteration (s): 0.23 | learning rate: 1.087E-04 | global batch size: 256 | lm loss: 3.350222E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.068 | TFLOPs: 28.02 | +7: iteration 19320/ 37905 | consumed samples: 4945920 | consumed tokens: 10129244160 | elapsed time per iteration (s): 0.24 | learning rate: 1.087E-04 | global batch size: 256 | lm loss: 3.388072E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1073.970 | TFLOPs: 27.36 | +7: iteration 19330/ 37905 | consumed samples: 4948480 | consumed tokens: 10134487040 | elapsed time per iteration (s): 0.23 | learning rate: 1.086E-04 | global batch size: 256 | lm loss: 3.384926E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.628 | TFLOPs: 28.27 | +7: iteration 19340/ 37905 | consumed samples: 4951040 | consumed tokens: 10139729920 | elapsed time per iteration (s): 0.23 | learning rate: 1.085E-04 | global batch size: 256 | lm loss: 3.381663E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.569 | TFLOPs: 27.94 | +7: iteration 19350/ 37905 | consumed samples: 4953600 | consumed tokens: 10144972800 | elapsed time per iteration (s): 0.23 | learning rate: 1.084E-04 | global batch size: 256 | lm loss: 3.380627E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.353 | TFLOPs: 27.85 | +7: iteration 19360/ 37905 | consumed samples: 4956160 | consumed tokens: 10150215680 | elapsed time per iteration (s): 0.23 | learning rate: 1.084E-04 | global batch size: 256 | lm loss: 3.387905E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.917 | TFLOPs: 28.02 | +7: iteration 19370/ 37905 | consumed samples: 4958720 | consumed tokens: 10155458560 | elapsed time per iteration (s): 0.23 | learning rate: 1.083E-04 | global batch size: 256 | lm loss: 3.364976E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.642 | TFLOPs: 28.34 | +7: iteration 19380/ 37905 | consumed samples: 4961280 | consumed tokens: 10160701440 | elapsed time per iteration (s): 0.24 | learning rate: 1.082E-04 | global batch size: 256 | lm loss: 3.406173E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.485 | TFLOPs: 27.68 | +7: iteration 19390/ 37905 | consumed samples: 4963840 | consumed tokens: 10165944320 | elapsed time per iteration (s): 0.23 | learning rate: 1.081E-04 | global batch size: 256 | lm loss: 3.381017E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.661 | TFLOPs: 28.32 | +7: iteration 19400/ 37905 | consumed samples: 4966400 | consumed tokens: 10171187200 | elapsed time per iteration (s): 0.23 | learning rate: 1.081E-04 | global batch size: 256 | lm loss: 3.380628E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.424 | TFLOPs: 28.26 | +7: iteration 19410/ 37905 | consumed samples: 4968960 | consumed tokens: 10176430080 | elapsed time per iteration (s): 0.24 | learning rate: 1.080E-04 | global batch size: 256 | lm loss: 3.379299E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.207 | TFLOPs: 26.93 | +7: iteration 19420/ 37905 | consumed samples: 4971520 | consumed tokens: 10181672960 | elapsed time per iteration (s): 0.23 | learning rate: 1.079E-04 | global batch size: 256 | lm loss: 3.397731E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.351 | TFLOPs: 28.16 | +7: iteration 19430/ 37905 | consumed samples: 4974080 | consumed tokens: 10186915840 | elapsed time per iteration (s): 0.23 | learning rate: 1.078E-04 | global batch size: 256 | lm loss: 3.382574E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.017 | TFLOPs: 27.77 | +7: iteration 19440/ 37905 | consumed samples: 4976640 | consumed tokens: 10192158720 | elapsed time per iteration (s): 0.23 | learning rate: 1.078E-04 | global batch size: 256 | lm loss: 3.358015E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.534 | TFLOPs: 28.29 | +7: iteration 19450/ 37905 | consumed samples: 4979200 | consumed tokens: 10197401600 | elapsed time per iteration (s): 0.23 | learning rate: 1.077E-04 | global batch size: 256 | lm loss: 3.350653E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.307 | TFLOPs: 28.11 | +7: iteration 19460/ 37905 | consumed samples: 4981760 | consumed tokens: 10202644480 | elapsed time per iteration (s): 0.23 | learning rate: 1.076E-04 | global batch size: 256 | lm loss: 3.356087E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.693 | TFLOPs: 28.04 | +7: iteration 19470/ 37905 | consumed samples: 4984320 | consumed tokens: 10207887360 | elapsed time per iteration (s): 0.23 | learning rate: 1.075E-04 | global batch size: 256 | lm loss: 3.377738E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.087 | TFLOPs: 28.25 | +7: iteration 19480/ 37905 | consumed samples: 4986880 | consumed tokens: 10213130240 | elapsed time per iteration (s): 0.23 | learning rate: 1.075E-04 | global batch size: 256 | lm loss: 3.377092E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.322 | TFLOPs: 28.41 | +7: iteration 19490/ 37905 | consumed samples: 4989440 | consumed tokens: 10218373120 | elapsed time per iteration (s): 0.23 | learning rate: 1.074E-04 | global batch size: 256 | lm loss: 3.355153E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.534 | TFLOPs: 28.37 | +7: iteration 19500/ 37905 | consumed samples: 4992000 | consumed tokens: 10223616000 | elapsed time per iteration (s): 0.23 | learning rate: 1.073E-04 | global batch size: 256 | lm loss: 3.362777E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.865 | TFLOPs: 28.27 | +7: iteration 19510/ 37905 | consumed samples: 4994560 | consumed tokens: 10228858880 | elapsed time per iteration (s): 0.24 | learning rate: 1.072E-04 | global batch size: 256 | lm loss: 3.363448E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1061.493 | TFLOPs: 27.04 | +7: iteration 19520/ 37905 | consumed samples: 4997120 | consumed tokens: 10234101760 | elapsed time per iteration (s): 0.24 | learning rate: 1.072E-04 | global batch size: 256 | lm loss: 3.395726E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.342 | TFLOPs: 27.67 | +7: iteration 19530/ 37905 | consumed samples: 4999680 | consumed tokens: 10239344640 | elapsed time per iteration (s): 0.23 | learning rate: 1.071E-04 | global batch size: 256 | lm loss: 3.375275E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.979 | TFLOPs: 27.84 | +7: iteration 19540/ 37905 | consumed samples: 5002240 | consumed tokens: 10244587520 | elapsed time per iteration (s): 0.23 | learning rate: 1.070E-04 | global batch size: 256 | lm loss: 3.366373E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.547 | TFLOPs: 28.09 | +7: iteration 19550/ 37905 | consumed samples: 5004800 | consumed tokens: 10249830400 | elapsed time per iteration (s): 0.23 | learning rate: 1.069E-04 | global batch size: 256 | lm loss: 3.394328E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.739 | TFLOPs: 28.35 | +7: iteration 19560/ 37905 | consumed samples: 5007360 | consumed tokens: 10255073280 | elapsed time per iteration (s): 0.23 | learning rate: 1.069E-04 | global batch size: 256 | lm loss: 3.386649E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.036 | TFLOPs: 28.02 | +7: iteration 19570/ 37905 | consumed samples: 5009920 | consumed tokens: 10260316160 | elapsed time per iteration (s): 0.23 | learning rate: 1.068E-04 | global batch size: 256 | lm loss: 3.333447E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.751 | TFLOPs: 28.42 | +7: iteration 19580/ 37905 | consumed samples: 5012480 | consumed tokens: 10265559040 | elapsed time per iteration (s): 0.23 | learning rate: 1.067E-04 | global batch size: 256 | lm loss: 3.386121E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.000 | TFLOPs: 28.35 | +7: iteration 19590/ 37905 | consumed samples: 5015040 | consumed tokens: 10270801920 | elapsed time per iteration (s): 0.23 | learning rate: 1.066E-04 | global batch size: 256 | lm loss: 3.364650E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.588 | TFLOPs: 28.32 | +7: iteration 19600/ 37905 | consumed samples: 5017600 | consumed tokens: 10276044800 | elapsed time per iteration (s): 0.23 | learning rate: 1.066E-04 | global batch size: 256 | lm loss: 3.380507E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.902 | TFLOPs: 28.02 | +7: iteration 19610/ 37905 | consumed samples: 5020160 | consumed tokens: 10281287680 | elapsed time per iteration (s): 0.23 | learning rate: 1.065E-04 | global batch size: 256 | lm loss: 3.383001E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.834 | TFLOPs: 28.35 | +7: iteration 19620/ 37905 | consumed samples: 5022720 | consumed tokens: 10286530560 | elapsed time per iteration (s): 0.23 | learning rate: 1.064E-04 | global batch size: 256 | lm loss: 3.377256E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.467 | TFLOPs: 28.21 | +7: iteration 19630/ 37905 | consumed samples: 5025280 | consumed tokens: 10291773440 | elapsed time per iteration (s): 0.23 | learning rate: 1.063E-04 | global batch size: 256 | lm loss: 3.406049E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.004 | TFLOPs: 28.46 | +7: iteration 19640/ 37905 | consumed samples: 5027840 | consumed tokens: 10297016320 | elapsed time per iteration (s): 0.24 | learning rate: 1.062E-04 | global batch size: 256 | lm loss: 3.376342E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1071.556 | TFLOPs: 27.30 | +7: iteration 19650/ 37905 | consumed samples: 5030400 | consumed tokens: 10302259200 | elapsed time per iteration (s): 0.23 | learning rate: 1.062E-04 | global batch size: 256 | lm loss: 3.383743E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.107 | TFLOPs: 28.25 | +7: iteration 19660/ 37905 | consumed samples: 5032960 | consumed tokens: 10307502080 | elapsed time per iteration (s): 0.23 | learning rate: 1.061E-04 | global batch size: 256 | lm loss: 3.376216E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.197 | TFLOPs: 28.00 | +7: iteration 19670/ 37905 | consumed samples: 5035520 | consumed tokens: 10312744960 | elapsed time per iteration (s): 0.23 | learning rate: 1.060E-04 | global batch size: 256 | lm loss: 3.364930E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.658 | TFLOPs: 28.14 | +7: iteration 19680/ 37905 | consumed samples: 5038080 | consumed tokens: 10317987840 | elapsed time per iteration (s): 0.24 | learning rate: 1.059E-04 | global batch size: 256 | lm loss: 3.399534E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1065.466 | TFLOPs: 27.14 | +7: iteration 19690/ 37905 | consumed samples: 5040640 | consumed tokens: 10323230720 | elapsed time per iteration (s): 0.23 | learning rate: 1.059E-04 | global batch size: 256 | lm loss: 3.380365E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.277 | TFLOPs: 28.21 | +7: iteration 19700/ 37905 | consumed samples: 5043200 | consumed tokens: 10328473600 | elapsed time per iteration (s): 0.23 | learning rate: 1.058E-04 | global batch size: 256 | lm loss: 3.378048E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.673 | TFLOPs: 28.12 | +7: iteration 19710/ 37905 | consumed samples: 5045760 | consumed tokens: 10333716480 | elapsed time per iteration (s): 0.25 | learning rate: 1.057E-04 | global batch size: 256 | lm loss: 3.377043E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1017.117 | TFLOPs: 25.91 | +7: iteration 19720/ 37905 | consumed samples: 5048320 | consumed tokens: 10338959360 | elapsed time per iteration (s): 0.24 | learning rate: 1.056E-04 | global batch size: 256 | lm loss: 3.367089E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1082.512 | TFLOPs: 27.58 | +7: iteration 19730/ 37905 | consumed samples: 5050880 | consumed tokens: 10344202240 | elapsed time per iteration (s): 0.23 | learning rate: 1.056E-04 | global batch size: 256 | lm loss: 3.376872E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.143 | TFLOPs: 28.05 | +7: iteration 19740/ 37905 | consumed samples: 5053440 | consumed tokens: 10349445120 | elapsed time per iteration (s): 0.23 | learning rate: 1.055E-04 | global batch size: 256 | lm loss: 3.378136E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.777 | TFLOPs: 28.07 | +7: iteration 19750/ 37905 | consumed samples: 5056000 | consumed tokens: 10354688000 | elapsed time per iteration (s): 0.23 | learning rate: 1.054E-04 | global batch size: 256 | lm loss: 3.384774E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.531 | TFLOPs: 28.39 | +7: iteration 19760/ 37905 | consumed samples: 5058560 | consumed tokens: 10359930880 | elapsed time per iteration (s): 0.23 | learning rate: 1.053E-04 | global batch size: 256 | lm loss: 3.404306E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.619 | TFLOPs: 28.22 | +7: iteration 19770/ 37905 | consumed samples: 5061120 | consumed tokens: 10365173760 | elapsed time per iteration (s): 0.24 | learning rate: 1.053E-04 | global batch size: 256 | lm loss: 3.383949E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1084.990 | TFLOPs: 27.64 | +7: iteration 19780/ 37905 | consumed samples: 5063680 | consumed tokens: 10370416640 | elapsed time per iteration (s): 0.25 | learning rate: 1.052E-04 | global batch size: 256 | lm loss: 3.400366E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1009.979 | TFLOPs: 25.73 | +7: iteration 19790/ 37905 | consumed samples: 5066240 | consumed tokens: 10375659520 | elapsed time per iteration (s): 0.24 | learning rate: 1.051E-04 | global batch size: 256 | lm loss: 3.397082E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1064.526 | TFLOPs: 27.12 | +7: iteration 19800/ 37905 | consumed samples: 5068800 | consumed tokens: 10380902400 | elapsed time per iteration (s): 0.24 | learning rate: 1.050E-04 | global batch size: 256 | lm loss: 3.377542E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1047.389 | TFLOPs: 26.68 | +7: iteration 19810/ 37905 | consumed samples: 5071360 | consumed tokens: 10386145280 | elapsed time per iteration (s): 0.24 | learning rate: 1.050E-04 | global batch size: 256 | lm loss: 3.384347E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.938 | TFLOPs: 27.74 | +7: iteration 19820/ 37905 | consumed samples: 5073920 | consumed tokens: 10391388160 | elapsed time per iteration (s): 0.23 | learning rate: 1.049E-04 | global batch size: 256 | lm loss: 3.350402E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.976 | TFLOPs: 28.35 | +7: iteration 19830/ 37905 | consumed samples: 5076480 | consumed tokens: 10396631040 | elapsed time per iteration (s): 0.23 | learning rate: 1.048E-04 | global batch size: 256 | lm loss: 3.387315E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.261 | TFLOPs: 28.13 | +7: iteration 19840/ 37905 | consumed samples: 5079040 | consumed tokens: 10401873920 | elapsed time per iteration (s): 0.23 | learning rate: 1.047E-04 | global batch size: 256 | lm loss: 3.369381E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.703 | TFLOPs: 28.27 | +7: iteration 19850/ 37905 | consumed samples: 5081600 | consumed tokens: 10407116800 | elapsed time per iteration (s): 0.23 | learning rate: 1.047E-04 | global batch size: 256 | lm loss: 3.362402E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.389 | TFLOPs: 28.01 | +7: iteration 19860/ 37905 | consumed samples: 5084160 | consumed tokens: 10412359680 | elapsed time per iteration (s): 0.23 | learning rate: 1.046E-04 | global batch size: 256 | lm loss: 3.390303E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.118 | TFLOPs: 28.20 | +7: iteration 19870/ 37905 | consumed samples: 5086720 | consumed tokens: 10417602560 | elapsed time per iteration (s): 0.23 | learning rate: 1.045E-04 | global batch size: 256 | lm loss: 3.353900E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.340 | TFLOPs: 28.01 | +7: iteration 19880/ 37905 | consumed samples: 5089280 | consumed tokens: 10422845440 | elapsed time per iteration (s): 0.25 | learning rate: 1.044E-04 | global batch size: 256 | lm loss: 3.392612E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1027.107 | TFLOPs: 26.17 | +7: iteration 19890/ 37905 | consumed samples: 5091840 | consumed tokens: 10428088320 | elapsed time per iteration (s): 0.23 | learning rate: 1.044E-04 | global batch size: 256 | lm loss: 3.360184E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.244 | TFLOPs: 28.11 | +7: iteration 19900/ 37905 | consumed samples: 5094400 | consumed tokens: 10433331200 | elapsed time per iteration (s): 0.23 | learning rate: 1.043E-04 | global batch size: 256 | lm loss: 3.344049E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.366 | TFLOPs: 28.36 | +7: iteration 19910/ 37905 | consumed samples: 5096960 | consumed tokens: 10438574080 | elapsed time per iteration (s): 0.23 | learning rate: 1.042E-04 | global batch size: 256 | lm loss: 3.365824E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.721 | TFLOPs: 28.35 | +7: iteration 19920/ 37905 | consumed samples: 5099520 | consumed tokens: 10443816960 | elapsed time per iteration (s): 0.23 | learning rate: 1.041E-04 | global batch size: 256 | lm loss: 3.376059E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.470 | TFLOPs: 28.44 | +7: iteration 19930/ 37905 | consumed samples: 5102080 | consumed tokens: 10449059840 | elapsed time per iteration (s): 0.23 | learning rate: 1.041E-04 | global batch size: 256 | lm loss: 3.379426E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.013 | TFLOPs: 28.38 | +7: iteration 19940/ 37905 | consumed samples: 5104640 | consumed tokens: 10454302720 | elapsed time per iteration (s): 0.23 | learning rate: 1.040E-04 | global batch size: 256 | lm loss: 3.359045E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.892 | TFLOPs: 28.12 | +7: iteration 19950/ 37905 | consumed samples: 5107200 | consumed tokens: 10459545600 | elapsed time per iteration (s): 0.23 | learning rate: 1.039E-04 | global batch size: 256 | lm loss: 3.363341E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.503 | TFLOPs: 28.44 | +7: iteration 19960/ 37905 | consumed samples: 5109760 | consumed tokens: 10464788480 | elapsed time per iteration (s): 0.25 | learning rate: 1.038E-04 | global batch size: 256 | lm loss: 3.381095E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1023.146 | TFLOPs: 26.06 | +7: iteration 19970/ 37905 | consumed samples: 5112320 | consumed tokens: 10470031360 | elapsed time per iteration (s): 0.23 | learning rate: 1.038E-04 | global batch size: 256 | lm loss: 3.367461E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.596 | TFLOPs: 27.99 | +7: iteration 19980/ 37905 | consumed samples: 5114880 | consumed tokens: 10475274240 | elapsed time per iteration (s): 0.23 | learning rate: 1.037E-04 | global batch size: 256 | lm loss: 3.353454E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.627 | TFLOPs: 28.24 | +7: iteration 19990/ 37905 | consumed samples: 5117440 | consumed tokens: 10480517120 | elapsed time per iteration (s): 0.23 | learning rate: 1.036E-04 | global batch size: 256 | lm loss: 3.369203E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.064 | TFLOPs: 28.23 | +0: [2022-11-29 18:15:25,209] [INFO] [logging.py:68:log_dist] [Rank 0] step=20000, skipped=0, lr=[0.00010354137669750605, 0.00010354137669750605, 0.00010354137669750605], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 20000/ 37905 | consumed samples: 5120000 | consumed tokens: 10485760000 | elapsed time per iteration (s): 0.24 | learning rate: 1.035E-04 | global batch size: 256 | lm loss: 3.398103E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.000 | TFLOPs: 27.72 | +0: steps: 20000 loss: 3.4046 iter time (s): 0.234 samples/sec: 1095.573 +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 20000 | lm loss value: 3.264611E+00 | lm loss PPL: 2.616993E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 20000 to checkpoints_83moscar +0: [2022-11-29 18:15:25,301] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step20000 is begin to save! +0: [2022-11-29 18:15:25,307] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:15:25,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:15:25,389] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:15:25,401] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:15:25,402] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:15:25,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:15:25,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:15:25,427] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:15:25,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:15:25,439] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:15:25,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:15:25,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:15:25,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:15:25,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:15:25,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:15:25,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:15:25,475] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:15:25,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:15:25,487] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:15:25,499] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:15:25,499] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:15:25,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:15:25,511] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:15:25,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:15:25,513] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step20000/mp_rank_00_model_states.pt +0: [2022-11-29 18:15:25,513] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:15:25,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:15:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:15:25,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:15:25,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:15:25,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +4: [2022-11-29 18:15:25,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:15:25,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:15:25,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +6: [2022-11-29 18:15:25,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:15:25,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:15:25,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +1: [2022-11-29 18:15:25,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +6: [2022-11-29 18:15:25,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +1: [2022-11-29 18:15:25,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +2: [2022-11-29 18:15:25,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:15:25,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:15:25,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +7: [2022-11-29 18:15:25,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:15:25,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:15:25,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +3: [2022-11-29 18:15:25,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:15:25,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:15:25,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +0: [2022-11-29 18:15:25,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:15:25,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:15:25,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:15:25,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +3: [2022-11-29 18:15:25,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:15:25,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:15:25,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +1: [2022-11-29 18:15:25,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:15:25,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:15:25,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:15:25,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +2: [2022-11-29 18:15:25,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +5: [2022-11-29 18:15:25,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:15:25,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +5: [2022-11-29 18:15:25,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:15:25,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +4: [2022-11-29 18:15:25,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:15:25,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:15:25,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:15:25,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:15:25,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +5: [2022-11-29 18:15:25,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +6: [2022-11-29 18:15:25,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +4: [2022-11-29 18:15:25,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +5: [2022-11-29 18:15:25,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +6: [2022-11-29 18:15:25,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +7: [2022-11-29 18:15:25,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:15:25,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +0: [2022-11-29 18:15:25,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +2: [2022-11-29 18:15:25,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:15:25,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +2: [2022-11-29 18:15:25,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +0: [2022-11-29 18:15:25,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:15:25,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +0: [2022-11-29 18:15:25,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:15:25,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:15:25,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +0: [2022-11-29 18:15:25,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:15:25,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +7: [2022-11-29 18:15:25,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:15:25,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:15:25,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +6: [2022-11-29 18:15:25,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:15:25,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:15:25,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +1: [2022-11-29 18:15:25,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:15:25,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:15:25,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +2: [2022-11-29 18:15:25,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:15:25,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:15:25,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +4: [2022-11-29 18:15:25,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +2: [2022-11-29 18:15:25,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +4: [2022-11-29 18:15:25,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +3: [2022-11-29 18:15:25,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:15:25,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:15:25,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:15:25,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +5: [2022-11-29 18:15:25,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:15:25,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +3: [2022-11-29 18:15:25,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +5: [2022-11-29 18:15:25,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:15:25,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +5: [2022-11-29 18:15:25,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:15:25,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:15:25,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:15:25,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +0: [2022-11-29 18:15:25,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +7: [2022-11-29 18:15:25,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:15:25,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +7: [2022-11-29 18:15:25,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:15:25,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +6: [2022-11-29 18:15:25,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:15:25,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:15:25,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +2: [2022-11-29 18:15:25,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:15:25,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +1: [2022-11-29 18:15:25,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:15:25,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +1: [2022-11-29 18:15:25,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:15:25,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +4: [2022-11-29 18:15:25,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:15:25,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:15:25,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +0: [2022-11-29 18:15:25,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:15:25,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:15:25,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +7: [2022-11-29 18:15:25,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:15:25,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:15:25,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +3: [2022-11-29 18:15:25,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:15:25,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:15:25,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +1: [2022-11-29 18:15:25,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:15:25,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:15:25,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +5: [2022-11-29 18:15:25,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:15:25,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:15:25,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +6: [2022-11-29 18:15:25,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:15:25,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:15:25,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +4: [2022-11-29 18:15:25,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:15:25,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:15:25,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +3: [2022-11-29 18:15:25,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:15:25,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:15:25,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +6: [2022-11-29 18:15:25,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:15:25,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:15:25,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +0: [2022-11-29 18:15:25,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:15:25,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:15:25,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +1: [2022-11-29 18:15:25,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:15:25,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:15:25,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +5: [2022-11-29 18:15:25,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:15:25,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:15:25,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +2: [2022-11-29 18:15:25,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +5: [2022-11-29 18:15:25,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +2: [2022-11-29 18:15:25,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +7: [2022-11-29 18:15:25,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:15:25,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:15:25,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +2: [2022-11-29 18:15:25,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +7: [2022-11-29 18:15:25,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +2: [2022-11-29 18:15:25,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +4: [2022-11-29 18:15:25,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:15:25,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:15:25,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +0: [2022-11-29 18:15:25,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +4: [2022-11-29 18:15:25,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +0: [2022-11-29 18:15:25,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +6: [2022-11-29 18:15:25,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:15:25,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:15:25,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +6: [2022-11-29 18:15:25,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:15:25,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:15:25,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +5: [2022-11-29 18:15:25,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:15:25,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:15:25,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +7: [2022-11-29 18:15:25,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:15:25,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:15:25,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +5: [2022-11-29 18:15:25,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:15:25,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:15:25,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +0: [2022-11-29 18:15:25,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:15:25,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3: [2022-11-29 18:15:25,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:15:25,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +3: [2022-11-29 18:15:25,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:15:25,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:15:25,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +3: [2022-11-29 18:15:25,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +4: [2022-11-29 18:15:25,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:15:25,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +4: [2022-11-29 18:15:25,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +2: [2022-11-29 18:15:25,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:15:25,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +2: [2022-11-29 18:15:25,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:15:25,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +7: [2022-11-29 18:15:25,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:15:25,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:15:25,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +1: [2022-11-29 18:15:25,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:15:25,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step20000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:15:25,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +0: successfully saved checkpoint at iteration 20000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 267.51 +7: iteration 20010/ 37905 | consumed samples: 5122560 | consumed tokens: 10491002880 | elapsed time per iteration (s): 0.27 | learning rate: 1.035E-04 | global batch size: 256 | lm loss: 3.389190E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 964.938 | TFLOPs: 24.58 | +7: iteration 20020/ 37905 | consumed samples: 5125120 | consumed tokens: 10496245760 | elapsed time per iteration (s): 0.23 | learning rate: 1.034E-04 | global batch size: 256 | lm loss: 3.364721E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.386 | TFLOPs: 27.91 | +7: iteration 20030/ 37905 | consumed samples: 5127680 | consumed tokens: 10501488640 | elapsed time per iteration (s): 0.24 | learning rate: 1.033E-04 | global batch size: 256 | lm loss: 3.405791E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.332 | TFLOPs: 26.94 | +7: iteration 20040/ 37905 | consumed samples: 5130240 | consumed tokens: 10506731520 | elapsed time per iteration (s): 0.24 | learning rate: 1.032E-04 | global batch size: 256 | lm loss: 3.381470E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.223 | TFLOPs: 27.72 | +7: iteration 20050/ 37905 | consumed samples: 5132800 | consumed tokens: 10511974400 | elapsed time per iteration (s): 0.24 | learning rate: 1.032E-04 | global batch size: 256 | lm loss: 3.374627E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1084.811 | TFLOPs: 27.64 | +7: iteration 20060/ 37905 | consumed samples: 5135360 | consumed tokens: 10517217280 | elapsed time per iteration (s): 0.23 | learning rate: 1.031E-04 | global batch size: 256 | lm loss: 3.383987E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.942 | TFLOPs: 28.38 | +7: iteration 20070/ 37905 | consumed samples: 5137920 | consumed tokens: 10522460160 | elapsed time per iteration (s): 0.23 | learning rate: 1.030E-04 | global batch size: 256 | lm loss: 3.383961E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.172 | TFLOPs: 28.00 | +7: iteration 20080/ 37905 | consumed samples: 5140480 | consumed tokens: 10527703040 | elapsed time per iteration (s): 0.24 | learning rate: 1.029E-04 | global batch size: 256 | lm loss: 3.353871E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1082.995 | TFLOPs: 27.59 | +7: iteration 20090/ 37905 | consumed samples: 5143040 | consumed tokens: 10532945920 | elapsed time per iteration (s): 0.23 | learning rate: 1.029E-04 | global batch size: 256 | lm loss: 3.359008E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.941 | TFLOPs: 28.30 | +7: iteration 20100/ 37905 | consumed samples: 5145600 | consumed tokens: 10538188800 | elapsed time per iteration (s): 0.23 | learning rate: 1.028E-04 | global batch size: 256 | lm loss: 3.341235E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.229 | TFLOPs: 28.05 | +7: iteration 20110/ 37905 | consumed samples: 5148160 | consumed tokens: 10543431680 | elapsed time per iteration (s): 0.23 | learning rate: 1.027E-04 | global batch size: 256 | lm loss: 3.365664E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.651 | TFLOPs: 27.99 | +7: iteration 20120/ 37905 | consumed samples: 5150720 | consumed tokens: 10548674560 | elapsed time per iteration (s): 0.23 | learning rate: 1.026E-04 | global batch size: 256 | lm loss: 3.373999E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.991 | TFLOPs: 28.30 | +7: iteration 20130/ 37905 | consumed samples: 5153280 | consumed tokens: 10553917440 | elapsed time per iteration (s): 0.23 | learning rate: 1.026E-04 | global batch size: 256 | lm loss: 3.375481E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.410 | TFLOPs: 28.08 | +7: iteration 20140/ 37905 | consumed samples: 5155840 | consumed tokens: 10559160320 | elapsed time per iteration (s): 0.23 | learning rate: 1.025E-04 | global batch size: 256 | lm loss: 3.362998E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.422 | TFLOPs: 28.03 | +7: iteration 20150/ 37905 | consumed samples: 5158400 | consumed tokens: 10564403200 | elapsed time per iteration (s): 0.23 | learning rate: 1.024E-04 | global batch size: 256 | lm loss: 3.404667E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.561 | TFLOPs: 28.34 | +7: iteration 20160/ 37905 | consumed samples: 5160960 | consumed tokens: 10569646080 | elapsed time per iteration (s): 0.23 | learning rate: 1.023E-04 | global batch size: 256 | lm loss: 3.352665E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.827 | TFLOPs: 28.07 | +7: iteration 20170/ 37905 | consumed samples: 5163520 | consumed tokens: 10574888960 | elapsed time per iteration (s): 0.24 | learning rate: 1.023E-04 | global batch size: 256 | lm loss: 3.369901E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1069.229 | TFLOPs: 27.24 | +7: iteration 20180/ 37905 | consumed samples: 5166080 | consumed tokens: 10580131840 | elapsed time per iteration (s): 0.23 | learning rate: 1.022E-04 | global batch size: 256 | lm loss: 3.378373E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.025 | TFLOPs: 28.13 | +7: iteration 20190/ 37905 | consumed samples: 5168640 | consumed tokens: 10585374720 | elapsed time per iteration (s): 0.23 | learning rate: 1.021E-04 | global batch size: 256 | lm loss: 3.385722E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.475 | TFLOPs: 28.14 | +7: iteration 20200/ 37905 | consumed samples: 5171200 | consumed tokens: 10590617600 | elapsed time per iteration (s): 0.23 | learning rate: 1.020E-04 | global batch size: 256 | lm loss: 3.365840E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.159 | TFLOPs: 28.28 | +7: iteration 20210/ 37905 | consumed samples: 5173760 | consumed tokens: 10595860480 | elapsed time per iteration (s): 0.23 | learning rate: 1.020E-04 | global batch size: 256 | lm loss: 3.357465E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.101 | TFLOPs: 27.95 | +7: iteration 20220/ 37905 | consumed samples: 5176320 | consumed tokens: 10601103360 | elapsed time per iteration (s): 0.23 | learning rate: 1.019E-04 | global batch size: 256 | lm loss: 3.384947E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.955 | TFLOPs: 28.10 | +7: iteration 20230/ 37905 | consumed samples: 5178880 | consumed tokens: 10606346240 | elapsed time per iteration (s): 0.24 | learning rate: 1.018E-04 | global batch size: 256 | lm loss: 3.370502E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1080.727 | TFLOPs: 27.53 | +7: iteration 20240/ 37905 | consumed samples: 5181440 | consumed tokens: 10611589120 | elapsed time per iteration (s): 0.23 | learning rate: 1.017E-04 | global batch size: 256 | lm loss: 3.350430E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.725 | TFLOPs: 28.02 | +7: iteration 20250/ 37905 | consumed samples: 5184000 | consumed tokens: 10616832000 | elapsed time per iteration (s): 0.23 | learning rate: 1.017E-04 | global batch size: 256 | lm loss: 3.376524E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.333 | TFLOPs: 28.01 | +7: iteration 20260/ 37905 | consumed samples: 5186560 | consumed tokens: 10622074880 | elapsed time per iteration (s): 0.23 | learning rate: 1.016E-04 | global batch size: 256 | lm loss: 3.402428E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.545 | TFLOPs: 27.96 | +7: iteration 20270/ 37905 | consumed samples: 5189120 | consumed tokens: 10627317760 | elapsed time per iteration (s): 0.23 | learning rate: 1.015E-04 | global batch size: 256 | lm loss: 3.383941E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.095 | TFLOPs: 28.23 | +7: iteration 20280/ 37905 | consumed samples: 5191680 | consumed tokens: 10632560640 | elapsed time per iteration (s): 0.23 | learning rate: 1.014E-04 | global batch size: 256 | lm loss: 3.369481E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.624 | TFLOPs: 28.22 | +7: iteration 20290/ 37905 | consumed samples: 5194240 | consumed tokens: 10637803520 | elapsed time per iteration (s): 0.23 | learning rate: 1.014E-04 | global batch size: 256 | lm loss: 3.359899E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.381 | TFLOPs: 28.16 | +7: iteration 20300/ 37905 | consumed samples: 5196800 | consumed tokens: 10643046400 | elapsed time per iteration (s): 0.23 | learning rate: 1.013E-04 | global batch size: 256 | lm loss: 3.352649E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.383 | TFLOPs: 28.39 | +7: iteration 20310/ 37905 | consumed samples: 5199360 | consumed tokens: 10648289280 | elapsed time per iteration (s): 0.23 | learning rate: 1.012E-04 | global batch size: 256 | lm loss: 3.356305E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.780 | TFLOPs: 28.22 | +7: iteration 20320/ 37905 | consumed samples: 5201920 | consumed tokens: 10653532160 | elapsed time per iteration (s): 0.23 | learning rate: 1.011E-04 | global batch size: 256 | lm loss: 3.377965E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.743 | TFLOPs: 28.17 | +7: iteration 20330/ 37905 | consumed samples: 5204480 | consumed tokens: 10658775040 | elapsed time per iteration (s): 0.23 | learning rate: 1.011E-04 | global batch size: 256 | lm loss: 3.395870E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.668 | TFLOPs: 28.17 | +7: iteration 20340/ 37905 | consumed samples: 5207040 | consumed tokens: 10664017920 | elapsed time per iteration (s): 0.24 | learning rate: 1.010E-04 | global batch size: 256 | lm loss: 3.388805E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.195 | TFLOPs: 27.67 | +7: iteration 20350/ 37905 | consumed samples: 5209600 | consumed tokens: 10669260800 | elapsed time per iteration (s): 0.23 | learning rate: 1.009E-04 | global batch size: 256 | lm loss: 3.368607E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.668 | TFLOPs: 27.96 | +7: iteration 20360/ 37905 | consumed samples: 5212160 | consumed tokens: 10674503680 | elapsed time per iteration (s): 0.25 | learning rate: 1.008E-04 | global batch size: 256 | lm loss: 3.351910E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1022.971 | TFLOPs: 26.06 | +7: iteration 20370/ 37905 | consumed samples: 5214720 | consumed tokens: 10679746560 | elapsed time per iteration (s): 0.23 | learning rate: 1.008E-04 | global batch size: 256 | lm loss: 3.389919E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.827 | TFLOPs: 28.12 | +7: iteration 20380/ 37905 | consumed samples: 5217280 | consumed tokens: 10684989440 | elapsed time per iteration (s): 0.23 | learning rate: 1.007E-04 | global batch size: 256 | lm loss: 3.373289E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.634 | TFLOPs: 27.96 | +7: iteration 20390/ 37905 | consumed samples: 5219840 | consumed tokens: 10690232320 | elapsed time per iteration (s): 0.23 | learning rate: 1.006E-04 | global batch size: 256 | lm loss: 3.375216E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.203 | TFLOPs: 28.21 | +7: iteration 20400/ 37905 | consumed samples: 5222400 | consumed tokens: 10695475200 | elapsed time per iteration (s): 0.23 | learning rate: 1.005E-04 | global batch size: 256 | lm loss: 3.375798E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.439 | TFLOPs: 28.21 | +7: iteration 20410/ 37905 | consumed samples: 5224960 | consumed tokens: 10700718080 | elapsed time per iteration (s): 0.23 | learning rate: 1.005E-04 | global batch size: 256 | lm loss: 3.348057E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.423 | TFLOPs: 28.11 | +7: iteration 20420/ 37905 | consumed samples: 5227520 | consumed tokens: 10705960960 | elapsed time per iteration (s): 0.23 | learning rate: 1.004E-04 | global batch size: 256 | lm loss: 3.352244E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.842 | TFLOPs: 27.99 | +7: iteration 20430/ 37905 | consumed samples: 5230080 | consumed tokens: 10711203840 | elapsed time per iteration (s): 0.25 | learning rate: 1.003E-04 | global batch size: 256 | lm loss: 3.361686E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1037.417 | TFLOPs: 26.43 | +7: iteration 20440/ 37905 | consumed samples: 5232640 | consumed tokens: 10716446720 | elapsed time per iteration (s): 0.25 | learning rate: 1.002E-04 | global batch size: 256 | lm loss: 3.388409E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1036.570 | TFLOPs: 26.41 | +7: iteration 20450/ 37905 | consumed samples: 5235200 | consumed tokens: 10721689600 | elapsed time per iteration (s): 0.23 | learning rate: 1.002E-04 | global batch size: 256 | lm loss: 3.376256E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.507 | TFLOPs: 28.16 | +7: iteration 20460/ 37905 | consumed samples: 5237760 | consumed tokens: 10726932480 | elapsed time per iteration (s): 0.23 | learning rate: 1.001E-04 | global batch size: 256 | lm loss: 3.352937E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.465 | TFLOPs: 27.93 | +7: iteration 20470/ 37905 | consumed samples: 5240320 | consumed tokens: 10732175360 | elapsed time per iteration (s): 0.24 | learning rate: 1.000E-04 | global batch size: 256 | lm loss: 3.372741E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1083.957 | TFLOPs: 27.61 | +7: iteration 20480/ 37905 | consumed samples: 5242880 | consumed tokens: 10737418240 | elapsed time per iteration (s): 0.23 | learning rate: 9.994E-05 | global batch size: 256 | lm loss: 3.355220E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.646 | TFLOPs: 28.17 | +7: iteration 20490/ 37905 | consumed samples: 5245440 | consumed tokens: 10742661120 | elapsed time per iteration (s): 0.23 | learning rate: 9.987E-05 | global batch size: 256 | lm loss: 3.361306E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.802 | TFLOPs: 28.32 | +7: iteration 20500/ 37905 | consumed samples: 5248000 | consumed tokens: 10747904000 | elapsed time per iteration (s): 0.24 | learning rate: 9.979E-05 | global batch size: 256 | lm loss: 3.360581E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.530 | TFLOPs: 27.73 | +7: iteration 20510/ 37905 | consumed samples: 5250560 | consumed tokens: 10753146880 | elapsed time per iteration (s): 0.23 | learning rate: 9.972E-05 | global batch size: 256 | lm loss: 3.394273E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.693 | TFLOPs: 27.96 | +7: iteration 20520/ 37905 | consumed samples: 5253120 | consumed tokens: 10758389760 | elapsed time per iteration (s): 0.23 | learning rate: 9.964E-05 | global batch size: 256 | lm loss: 3.364449E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.074 | TFLOPs: 27.90 | +7: iteration 20530/ 37905 | consumed samples: 5255680 | consumed tokens: 10763632640 | elapsed time per iteration (s): 0.23 | learning rate: 9.957E-05 | global batch size: 256 | lm loss: 3.369920E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.710 | TFLOPs: 28.14 | +7: iteration 20540/ 37905 | consumed samples: 5258240 | consumed tokens: 10768875520 | elapsed time per iteration (s): 0.23 | learning rate: 9.949E-05 | global batch size: 256 | lm loss: 3.365838E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.998 | TFLOPs: 28.46 | +7: iteration 20550/ 37905 | consumed samples: 5260800 | consumed tokens: 10774118400 | elapsed time per iteration (s): 0.24 | learning rate: 9.942E-05 | global batch size: 256 | lm loss: 3.372211E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.421 | TFLOPs: 27.70 | +7: iteration 20560/ 37905 | consumed samples: 5263360 | consumed tokens: 10779361280 | elapsed time per iteration (s): 0.23 | learning rate: 9.934E-05 | global batch size: 256 | lm loss: 3.356876E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.932 | TFLOPs: 28.17 | +7: iteration 20570/ 37905 | consumed samples: 5265920 | consumed tokens: 10784604160 | elapsed time per iteration (s): 0.23 | learning rate: 9.927E-05 | global batch size: 256 | lm loss: 3.384793E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.674 | TFLOPs: 28.22 | +7: iteration 20580/ 37905 | consumed samples: 5268480 | consumed tokens: 10789847040 | elapsed time per iteration (s): 0.23 | learning rate: 9.919E-05 | global batch size: 256 | lm loss: 3.347036E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.533 | TFLOPs: 28.06 | +7: iteration 20590/ 37905 | consumed samples: 5271040 | consumed tokens: 10795089920 | elapsed time per iteration (s): 0.23 | learning rate: 9.912E-05 | global batch size: 256 | lm loss: 3.366277E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.461 | TFLOPs: 27.91 | +7: iteration 20600/ 37905 | consumed samples: 5273600 | consumed tokens: 10800332800 | elapsed time per iteration (s): 0.24 | learning rate: 9.904E-05 | global batch size: 256 | lm loss: 3.372885E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1054.649 | TFLOPs: 26.87 | +7: iteration 20610/ 37905 | consumed samples: 5276160 | consumed tokens: 10805575680 | elapsed time per iteration (s): 0.23 | learning rate: 9.897E-05 | global batch size: 256 | lm loss: 3.368311E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.780 | TFLOPs: 27.99 | +7: iteration 20620/ 37905 | consumed samples: 5278720 | consumed tokens: 10810818560 | elapsed time per iteration (s): 0.23 | learning rate: 9.889E-05 | global batch size: 256 | lm loss: 3.390453E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.738 | TFLOPs: 27.86 | +7: iteration 20630/ 37905 | consumed samples: 5281280 | consumed tokens: 10816061440 | elapsed time per iteration (s): 0.23 | learning rate: 9.882E-05 | global batch size: 256 | lm loss: 3.324229E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.091 | TFLOPs: 28.08 | +7: iteration 20640/ 37905 | consumed samples: 5283840 | consumed tokens: 10821304320 | elapsed time per iteration (s): 0.23 | learning rate: 9.874E-05 | global batch size: 256 | lm loss: 3.372346E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.694 | TFLOPs: 27.99 | +7: iteration 20650/ 37905 | consumed samples: 5286400 | consumed tokens: 10826547200 | elapsed time per iteration (s): 0.23 | learning rate: 9.867E-05 | global batch size: 256 | lm loss: 3.353895E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.700 | TFLOPs: 27.86 | +7: iteration 20660/ 37905 | consumed samples: 5288960 | consumed tokens: 10831790080 | elapsed time per iteration (s): 0.23 | learning rate: 9.859E-05 | global batch size: 256 | lm loss: 3.372100E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.799 | TFLOPs: 28.09 | +7: iteration 20670/ 37905 | consumed samples: 5291520 | consumed tokens: 10837032960 | elapsed time per iteration (s): 0.23 | learning rate: 9.852E-05 | global batch size: 256 | lm loss: 3.361672E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.223 | TFLOPs: 28.31 | +7: iteration 20680/ 37905 | consumed samples: 5294080 | consumed tokens: 10842275840 | elapsed time per iteration (s): 0.23 | learning rate: 9.844E-05 | global batch size: 256 | lm loss: 3.368526E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.524 | TFLOPs: 28.27 | +7: iteration 20690/ 37905 | consumed samples: 5296640 | consumed tokens: 10847518720 | elapsed time per iteration (s): 0.24 | learning rate: 9.837E-05 | global batch size: 256 | lm loss: 3.356274E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.226 | TFLOPs: 27.47 | +7: iteration 20700/ 37905 | consumed samples: 5299200 | consumed tokens: 10852761600 | elapsed time per iteration (s): 0.23 | learning rate: 9.829E-05 | global batch size: 256 | lm loss: 3.388643E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.569 | TFLOPs: 28.11 | +7: iteration 20710/ 37905 | consumed samples: 5301760 | consumed tokens: 10858004480 | elapsed time per iteration (s): 0.23 | learning rate: 9.822E-05 | global batch size: 256 | lm loss: 3.344371E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.430 | TFLOPs: 27.93 | +7: iteration 20720/ 37905 | consumed samples: 5304320 | consumed tokens: 10863247360 | elapsed time per iteration (s): 0.23 | learning rate: 9.815E-05 | global batch size: 256 | lm loss: 3.336272E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.174 | TFLOPs: 28.23 | +7: iteration 20730/ 37905 | consumed samples: 5306880 | consumed tokens: 10868490240 | elapsed time per iteration (s): 0.23 | learning rate: 9.807E-05 | global batch size: 256 | lm loss: 3.390791E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.907 | TFLOPs: 28.22 | +7: iteration 20740/ 37905 | consumed samples: 5309440 | consumed tokens: 10873733120 | elapsed time per iteration (s): 0.23 | learning rate: 9.800E-05 | global batch size: 256 | lm loss: 3.347947E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.468 | TFLOPs: 28.42 | +7: iteration 20750/ 37905 | consumed samples: 5312000 | consumed tokens: 10878976000 | elapsed time per iteration (s): 0.24 | learning rate: 9.792E-05 | global batch size: 256 | lm loss: 3.402028E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.248 | TFLOPs: 27.75 | +7: iteration 20760/ 37905 | consumed samples: 5314560 | consumed tokens: 10884218880 | elapsed time per iteration (s): 0.23 | learning rate: 9.785E-05 | global batch size: 256 | lm loss: 3.355705E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.579 | TFLOPs: 28.24 | +7: iteration 20770/ 37905 | consumed samples: 5317120 | consumed tokens: 10889461760 | elapsed time per iteration (s): 0.23 | learning rate: 9.777E-05 | global batch size: 256 | lm loss: 3.337258E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.827 | TFLOPs: 28.37 | +7: iteration 20780/ 37905 | consumed samples: 5319680 | consumed tokens: 10894704640 | elapsed time per iteration (s): 0.23 | learning rate: 9.770E-05 | global batch size: 256 | lm loss: 3.363345E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.432 | TFLOPs: 28.24 | +7: iteration 20790/ 37905 | consumed samples: 5322240 | consumed tokens: 10899947520 | elapsed time per iteration (s): 0.23 | learning rate: 9.762E-05 | global batch size: 256 | lm loss: 3.379823E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.859 | TFLOPs: 28.32 | +7: iteration 20800/ 37905 | consumed samples: 5324800 | consumed tokens: 10905190400 | elapsed time per iteration (s): 0.25 | learning rate: 9.755E-05 | global batch size: 256 | lm loss: 3.389347E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1036.697 | TFLOPs: 26.41 | +7: iteration 20810/ 37905 | consumed samples: 5327360 | consumed tokens: 10910433280 | elapsed time per iteration (s): 0.23 | learning rate: 9.747E-05 | global batch size: 256 | lm loss: 3.342432E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.965 | TFLOPs: 28.33 | +7: iteration 20820/ 37905 | consumed samples: 5329920 | consumed tokens: 10915676160 | elapsed time per iteration (s): 0.23 | learning rate: 9.740E-05 | global batch size: 256 | lm loss: 3.366866E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.536 | TFLOPs: 28.37 | +7: iteration 20830/ 37905 | consumed samples: 5332480 | consumed tokens: 10920919040 | elapsed time per iteration (s): 0.23 | learning rate: 9.732E-05 | global batch size: 256 | lm loss: 3.376273E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.121 | TFLOPs: 28.00 | +7: iteration 20840/ 37905 | consumed samples: 5335040 | consumed tokens: 10926161920 | elapsed time per iteration (s): 0.23 | learning rate: 9.725E-05 | global batch size: 256 | lm loss: 3.352793E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.275 | TFLOPs: 28.31 | +7: iteration 20850/ 37905 | consumed samples: 5337600 | consumed tokens: 10931404800 | elapsed time per iteration (s): 0.23 | learning rate: 9.718E-05 | global batch size: 256 | lm loss: 3.341645E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.818 | TFLOPs: 28.25 | +7: iteration 20860/ 37905 | consumed samples: 5340160 | consumed tokens: 10936647680 | elapsed time per iteration (s): 0.23 | learning rate: 9.710E-05 | global batch size: 256 | lm loss: 3.372779E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.951 | TFLOPs: 28.45 | +7: iteration 20870/ 37905 | consumed samples: 5342720 | consumed tokens: 10941890560 | elapsed time per iteration (s): 0.23 | learning rate: 9.703E-05 | global batch size: 256 | lm loss: 3.368546E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.256 | TFLOPs: 28.41 | +7: iteration 20880/ 37905 | consumed samples: 5345280 | consumed tokens: 10947133440 | elapsed time per iteration (s): 0.23 | learning rate: 9.695E-05 | global batch size: 256 | lm loss: 3.385481E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.940 | TFLOPs: 28.45 | +7: iteration 20890/ 37905 | consumed samples: 5347840 | consumed tokens: 10952376320 | elapsed time per iteration (s): 0.23 | learning rate: 9.688E-05 | global batch size: 256 | lm loss: 3.349490E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.613 | TFLOPs: 28.39 | +7: iteration 20900/ 37905 | consumed samples: 5350400 | consumed tokens: 10957619200 | elapsed time per iteration (s): 0.23 | learning rate: 9.680E-05 | global batch size: 256 | lm loss: 3.372613E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.835 | TFLOPs: 27.97 | +7: iteration 20910/ 37905 | consumed samples: 5352960 | consumed tokens: 10962862080 | elapsed time per iteration (s): 0.23 | learning rate: 9.673E-05 | global batch size: 256 | lm loss: 3.378903E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.967 | TFLOPs: 28.43 | +7: iteration 20920/ 37905 | consumed samples: 5355520 | consumed tokens: 10968104960 | elapsed time per iteration (s): 0.23 | learning rate: 9.665E-05 | global batch size: 256 | lm loss: 3.380054E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.817 | TFLOPs: 28.50 | +7: iteration 20930/ 37905 | consumed samples: 5358080 | consumed tokens: 10973347840 | elapsed time per iteration (s): 0.23 | learning rate: 9.658E-05 | global batch size: 256 | lm loss: 3.375826E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.194 | TFLOPs: 28.54 | +7: iteration 20940/ 37905 | consumed samples: 5360640 | consumed tokens: 10978590720 | elapsed time per iteration (s): 0.23 | learning rate: 9.650E-05 | global batch size: 256 | lm loss: 3.375327E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.529 | TFLOPs: 28.39 | +7: iteration 20950/ 37905 | consumed samples: 5363200 | consumed tokens: 10983833600 | elapsed time per iteration (s): 0.23 | learning rate: 9.643E-05 | global batch size: 256 | lm loss: 3.348073E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.231 | TFLOPs: 28.44 | +7: iteration 20960/ 37905 | consumed samples: 5365760 | consumed tokens: 10989076480 | elapsed time per iteration (s): 0.23 | learning rate: 9.636E-05 | global batch size: 256 | lm loss: 3.379393E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.176 | TFLOPs: 28.46 | +7: iteration 20970/ 37905 | consumed samples: 5368320 | consumed tokens: 10994319360 | elapsed time per iteration (s): 0.23 | learning rate: 9.628E-05 | global batch size: 256 | lm loss: 3.417225E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.394 | TFLOPs: 28.13 | +7: iteration 20980/ 37905 | consumed samples: 5370880 | consumed tokens: 10999562240 | elapsed time per iteration (s): 0.23 | learning rate: 9.621E-05 | global batch size: 256 | lm loss: 3.347510E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.557 | TFLOPs: 28.24 | +7: iteration 20990/ 37905 | consumed samples: 5373440 | consumed tokens: 11004805120 | elapsed time per iteration (s): 0.23 | learning rate: 9.613E-05 | global batch size: 256 | lm loss: 3.371799E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.258 | TFLOPs: 28.54 | +7: iteration 21000/ 37905 | consumed samples: 5376000 | consumed tokens: 11010048000 | elapsed time per iteration (s): 0.24 | learning rate: 9.606E-05 | global batch size: 256 | lm loss: 3.359230E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1053.403 | TFLOPs: 26.84 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 21000 | lm loss value: 3.360737E+00 | lm loss PPL: 2.881042E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 21000 to checkpoints_83moscar +0: [2022-11-29 18:19:18,603] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step21000 is begin to save! +0: [2022-11-29 18:19:18,609] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:19:18,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:19:18,691] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:19:18,703] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:19:18,704] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:19:18,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:19:18,716] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:19:18,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:19:18,728] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:19:18,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:19:18,740] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:19:18,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:19:18,752] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:19:18,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:19:18,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:19:18,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:19:18,776] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:19:18,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:19:18,787] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:19:18,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:19:18,800] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:19:18,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:19:18,811] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:19:18,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:19:18,813] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step21000/mp_rank_00_model_states.pt +0: [2022-11-29 18:19:18,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:19:18,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:19:18,834] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:19:18,834] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:19:18,834] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:19:18,834] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:19:18,834] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:19:18,834] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:19:18,834] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:19:18,834] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:19:18,834] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:19:18,834] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:19:18,834] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:19:18,834] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:19:18,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:19:18,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:19:18,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:19:18,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +3: [2022-11-29 18:19:18,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:19:18,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:19:18,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +7: [2022-11-29 18:19:18,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:19:18,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +5: [2022-11-29 18:19:18,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:19:18,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +5: [2022-11-29 18:19:18,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:19:18,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +1: [2022-11-29 18:19:18,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:19:18,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:19:18,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +4: [2022-11-29 18:19:18,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:19:18,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:19:18,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +2: [2022-11-29 18:19:18,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:19:18,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +3: [2022-11-29 18:19:18,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:19:18,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +3: [2022-11-29 18:19:18,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:19:18,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +0: [2022-11-29 18:19:18,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:19:18,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:19:18,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:19:18,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +1: [2022-11-29 18:19:18,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:19:18,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:19:18,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +5: [2022-11-29 18:19:18,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:19:18,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:19:18,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +5: [2022-11-29 18:19:18,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +6: [2022-11-29 18:19:18,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +5: [2022-11-29 18:19:18,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +6: [2022-11-29 18:19:18,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:19:18,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:19:18,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +3: [2022-11-29 18:19:18,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:19:18,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +0: [2022-11-29 18:19:18,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:19:18,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +0: [2022-11-29 18:19:18,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +5: [2022-11-29 18:19:18,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:19:18,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +7: [2022-11-29 18:19:18,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:19:18,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +7: [2022-11-29 18:19:18,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +5: [2022-11-29 18:19:18,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +7: [2022-11-29 18:19:18,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +6: [2022-11-29 18:19:18,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:19:18,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:19:18,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +0: [2022-11-29 18:19:18,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:19:18,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +1: [2022-11-29 18:19:18,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:19:18,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:19:18,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +2: [2022-11-29 18:19:18,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:19:18,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:19:18,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +4: [2022-11-29 18:19:18,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:19:18,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:19:18,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +2: [2022-11-29 18:19:18,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:19:18,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:19:18,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +3: [2022-11-29 18:19:18,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:19:18,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:19:18,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +3: [2022-11-29 18:19:18,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +4: [2022-11-29 18:19:18,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +3: [2022-11-29 18:19:18,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +1: [2022-11-29 18:19:18,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:19:18,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:19:18,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +0: [2022-11-29 18:19:18,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:19:18,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:19:18,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +7: [2022-11-29 18:19:18,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:19:18,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:19:18,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +5: [2022-11-29 18:19:18,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:19:18,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +6: [2022-11-29 18:19:18,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:19:18,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +6: [2022-11-29 18:19:18,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:19:18,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +4: [2022-11-29 18:19:18,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:19:18,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:19:18,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +2: [2022-11-29 18:19:18,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:19:18,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:19:18,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +0: [2022-11-29 18:19:18,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +2: [2022-11-29 18:19:18,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +0: [2022-11-29 18:19:18,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +5: [2022-11-29 18:19:18,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:19:18,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:19:18,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +5: [2022-11-29 18:19:18,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:19:18,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:19:18,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:19:18,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:19:18,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +2: [2022-11-29 18:19:18,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +7: [2022-11-29 18:19:18,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +5: [2022-11-29 18:19:18,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +3: [2022-11-29 18:19:18,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +7: [2022-11-29 18:19:18,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +3: [2022-11-29 18:19:18,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +2: [2022-11-29 18:19:18,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +6: [2022-11-29 18:19:18,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:19:18,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:19:18,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +1: [2022-11-29 18:19:18,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +6: [2022-11-29 18:19:18,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +1: [2022-11-29 18:19:18,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +1: [2022-11-29 18:19:18,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:19:18,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:19:18,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +0: [2022-11-29 18:19:18,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:19:18,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:19:18,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +7: [2022-11-29 18:19:18,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:19:18,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:19:18,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +6: [2022-11-29 18:19:18,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:19:18,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:19:18,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +3: [2022-11-29 18:19:18,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:19:18,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +4: [2022-11-29 18:19:18,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:19:18,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +4: [2022-11-29 18:19:18,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:19:18,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:19:18,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:19:18,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +2: [2022-11-29 18:19:18,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:19:18,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +2: [2022-11-29 18:19:18,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:19:18,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +0: [2022-11-29 18:19:18,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:19:18,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:19:18,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +6: [2022-11-29 18:19:18,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:19:18,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:19:18,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:19:18,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +5: [2022-11-29 18:19:18,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:19:18,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +3: [2022-11-29 18:19:18,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:19:18,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:19:18,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +5: [2022-11-29 18:19:18,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:19:18,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +3: [2022-11-29 18:19:18,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +5: [2022-11-29 18:19:18,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +1: [2022-11-29 18:19:18,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +5: [2022-11-29 18:19:18,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +4: [2022-11-29 18:19:18,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:19:18,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:19:18,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +0: [2022-11-29 18:19:18,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:19:18,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +7: [2022-11-29 18:19:18,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:19:18,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +3: [2022-11-29 18:19:18,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:19:18,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:19:18,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +3: [2022-11-29 18:19:18,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +7: [2022-11-29 18:19:18,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:19:18,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +7: [2022-11-29 18:19:18,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:19:18,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +6: [2022-11-29 18:19:18,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:19:18,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:19:18,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +4: [2022-11-29 18:19:18,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:19:18,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:19:18,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +7: [2022-11-29 18:19:18,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:19:18,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +2: [2022-11-29 18:19:18,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:19:18,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +2: [2022-11-29 18:19:18,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:19:18,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +2: [2022-11-29 18:19:18,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:19:18,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step21000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:19:18,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +0: successfully saved checkpoint at iteration 21000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 286.04 +7: iteration 21010/ 37905 | consumed samples: 5378560 | consumed tokens: 11015290880 | elapsed time per iteration (s): 0.26 | learning rate: 9.598E-05 | global batch size: 256 | lm loss: 3.341874E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 966.989 | TFLOPs: 24.63 | +7: iteration 21020/ 37905 | consumed samples: 5381120 | consumed tokens: 11020533760 | elapsed time per iteration (s): 0.23 | learning rate: 9.591E-05 | global batch size: 256 | lm loss: 3.365253E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.133 | TFLOPs: 28.64 | +7: iteration 21030/ 37905 | consumed samples: 5383680 | consumed tokens: 11025776640 | elapsed time per iteration (s): 0.23 | learning rate: 9.583E-05 | global batch size: 256 | lm loss: 3.382732E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.145 | TFLOPs: 28.51 | +7: iteration 21040/ 37905 | consumed samples: 5386240 | consumed tokens: 11031019520 | elapsed time per iteration (s): 0.23 | learning rate: 9.576E-05 | global batch size: 256 | lm loss: 3.358517E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.989 | TFLOPs: 28.58 | +7: iteration 21050/ 37905 | consumed samples: 5388800 | consumed tokens: 11036262400 | elapsed time per iteration (s): 0.23 | learning rate: 9.569E-05 | global batch size: 256 | lm loss: 3.389403E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.007 | TFLOPs: 28.61 | +7: iteration 21060/ 37905 | consumed samples: 5391360 | consumed tokens: 11041505280 | elapsed time per iteration (s): 0.23 | learning rate: 9.561E-05 | global batch size: 256 | lm loss: 3.394910E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.371 | TFLOPs: 28.64 | +7: iteration 21070/ 37905 | consumed samples: 5393920 | consumed tokens: 11046748160 | elapsed time per iteration (s): 0.23 | learning rate: 9.554E-05 | global batch size: 256 | lm loss: 3.356987E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.454 | TFLOPs: 28.49 | +7: iteration 21080/ 37905 | consumed samples: 5396480 | consumed tokens: 11051991040 | elapsed time per iteration (s): 0.24 | learning rate: 9.546E-05 | global batch size: 256 | lm loss: 3.394438E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1077.145 | TFLOPs: 27.44 | +7: iteration 21090/ 37905 | consumed samples: 5399040 | consumed tokens: 11057233920 | elapsed time per iteration (s): 0.24 | learning rate: 9.539E-05 | global batch size: 256 | lm loss: 3.383723E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1045.647 | TFLOPs: 26.64 | +7: iteration 21100/ 37905 | consumed samples: 5401600 | consumed tokens: 11062476800 | elapsed time per iteration (s): 0.23 | learning rate: 9.531E-05 | global batch size: 256 | lm loss: 3.362216E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.165 | TFLOPs: 28.64 | +7: iteration 21110/ 37905 | consumed samples: 5404160 | consumed tokens: 11067719680 | elapsed time per iteration (s): 0.23 | learning rate: 9.524E-05 | global batch size: 256 | lm loss: 3.372060E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.202 | TFLOPs: 28.66 | +7: iteration 21120/ 37905 | consumed samples: 5406720 | consumed tokens: 11072962560 | elapsed time per iteration (s): 0.23 | learning rate: 9.517E-05 | global batch size: 256 | lm loss: 3.366954E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.596 | TFLOPs: 28.62 | +7: iteration 21130/ 37905 | consumed samples: 5409280 | consumed tokens: 11078205440 | elapsed time per iteration (s): 0.23 | learning rate: 9.509E-05 | global batch size: 256 | lm loss: 3.344273E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.793 | TFLOPs: 28.68 | +7: iteration 21140/ 37905 | consumed samples: 5411840 | consumed tokens: 11083448320 | elapsed time per iteration (s): 0.23 | learning rate: 9.502E-05 | global batch size: 256 | lm loss: 3.384891E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.067 | TFLOPs: 28.69 | +7: iteration 21150/ 37905 | consumed samples: 5414400 | consumed tokens: 11088691200 | elapsed time per iteration (s): 0.23 | learning rate: 9.494E-05 | global batch size: 256 | lm loss: 3.365622E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.959 | TFLOPs: 28.48 | +7: iteration 21160/ 37905 | consumed samples: 5416960 | consumed tokens: 11093934080 | elapsed time per iteration (s): 0.31 | learning rate: 9.487E-05 | global batch size: 256 | lm loss: 3.353865E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 834.734 | TFLOPs: 21.26 | +7: iteration 21170/ 37905 | consumed samples: 5419520 | consumed tokens: 11099176960 | elapsed time per iteration (s): 0.23 | learning rate: 9.479E-05 | global batch size: 256 | lm loss: 3.376413E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.608 | TFLOPs: 28.68 | +7: iteration 21180/ 37905 | consumed samples: 5422080 | consumed tokens: 11104419840 | elapsed time per iteration (s): 0.23 | learning rate: 9.472E-05 | global batch size: 256 | lm loss: 3.369721E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.310 | TFLOPs: 28.59 | +7: iteration 21190/ 37905 | consumed samples: 5424640 | consumed tokens: 11109662720 | elapsed time per iteration (s): 0.23 | learning rate: 9.465E-05 | global batch size: 256 | lm loss: 3.350076E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.692 | TFLOPs: 28.63 | +7: iteration 21200/ 37905 | consumed samples: 5427200 | consumed tokens: 11114905600 | elapsed time per iteration (s): 0.23 | learning rate: 9.457E-05 | global batch size: 256 | lm loss: 3.380580E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.098 | TFLOPs: 28.64 | +7: iteration 21210/ 37905 | consumed samples: 5429760 | consumed tokens: 11120148480 | elapsed time per iteration (s): 0.23 | learning rate: 9.450E-05 | global batch size: 256 | lm loss: 3.339370E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.786 | TFLOPs: 28.65 | +7: iteration 21220/ 37905 | consumed samples: 5432320 | consumed tokens: 11125391360 | elapsed time per iteration (s): 0.23 | learning rate: 9.442E-05 | global batch size: 256 | lm loss: 3.370313E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.614 | TFLOPs: 28.68 | +7: iteration 21230/ 37905 | consumed samples: 5434880 | consumed tokens: 11130634240 | elapsed time per iteration (s): 0.23 | learning rate: 9.435E-05 | global batch size: 256 | lm loss: 3.362199E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.296 | TFLOPs: 28.67 | +7: iteration 21240/ 37905 | consumed samples: 5437440 | consumed tokens: 11135877120 | elapsed time per iteration (s): 0.23 | learning rate: 9.427E-05 | global batch size: 256 | lm loss: 3.378117E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.867 | TFLOPs: 28.71 | +7: iteration 21250/ 37905 | consumed samples: 5440000 | consumed tokens: 11141120000 | elapsed time per iteration (s): 0.24 | learning rate: 9.420E-05 | global batch size: 256 | lm loss: 3.367184E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1064.326 | TFLOPs: 27.11 | +7: iteration 21260/ 37905 | consumed samples: 5442560 | consumed tokens: 11146362880 | elapsed time per iteration (s): 0.23 | learning rate: 9.413E-05 | global batch size: 256 | lm loss: 3.354939E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.882 | TFLOPs: 28.66 | +7: iteration 21270/ 37905 | consumed samples: 5445120 | consumed tokens: 11151605760 | elapsed time per iteration (s): 0.23 | learning rate: 9.405E-05 | global batch size: 256 | lm loss: 3.357714E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.877 | TFLOPs: 28.66 | +7: iteration 21280/ 37905 | consumed samples: 5447680 | consumed tokens: 11156848640 | elapsed time per iteration (s): 0.23 | learning rate: 9.398E-05 | global batch size: 256 | lm loss: 3.357233E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.632 | TFLOPs: 28.65 | +7: iteration 21290/ 37905 | consumed samples: 5450240 | consumed tokens: 11162091520 | elapsed time per iteration (s): 0.23 | learning rate: 9.390E-05 | global batch size: 256 | lm loss: 3.377672E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.301 | TFLOPs: 28.69 | +7: iteration 21300/ 37905 | consumed samples: 5452800 | consumed tokens: 11167334400 | elapsed time per iteration (s): 0.23 | learning rate: 9.383E-05 | global batch size: 256 | lm loss: 3.339254E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.191 | TFLOPs: 28.72 | +7: iteration 21310/ 37905 | consumed samples: 5455360 | consumed tokens: 11172577280 | elapsed time per iteration (s): 0.23 | learning rate: 9.376E-05 | global batch size: 256 | lm loss: 3.371443E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.409 | TFLOPs: 28.62 | +7: iteration 21320/ 37905 | consumed samples: 5457920 | consumed tokens: 11177820160 | elapsed time per iteration (s): 0.23 | learning rate: 9.368E-05 | global batch size: 256 | lm loss: 3.358514E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.350 | TFLOPs: 28.72 | +7: iteration 21330/ 37905 | consumed samples: 5460480 | consumed tokens: 11183063040 | elapsed time per iteration (s): 0.23 | learning rate: 9.361E-05 | global batch size: 256 | lm loss: 3.379852E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.600 | TFLOPs: 28.73 | +7: iteration 21340/ 37905 | consumed samples: 5463040 | consumed tokens: 11188305920 | elapsed time per iteration (s): 0.23 | learning rate: 9.353E-05 | global batch size: 256 | lm loss: 3.335514E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.165 | TFLOPs: 27.77 | +7: iteration 21350/ 37905 | consumed samples: 5465600 | consumed tokens: 11193548800 | elapsed time per iteration (s): 0.23 | learning rate: 9.346E-05 | global batch size: 256 | lm loss: 3.359042E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.177 | TFLOPs: 28.46 | +7: iteration 21360/ 37905 | consumed samples: 5468160 | consumed tokens: 11198791680 | elapsed time per iteration (s): 0.23 | learning rate: 9.338E-05 | global batch size: 256 | lm loss: 3.365663E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.269 | TFLOPs: 28.67 | +7: iteration 21370/ 37905 | consumed samples: 5470720 | consumed tokens: 11204034560 | elapsed time per iteration (s): 0.23 | learning rate: 9.331E-05 | global batch size: 256 | lm loss: 3.368753E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.626 | TFLOPs: 28.55 | +7: iteration 21380/ 37905 | consumed samples: 5473280 | consumed tokens: 11209277440 | elapsed time per iteration (s): 0.23 | learning rate: 9.324E-05 | global batch size: 256 | lm loss: 3.364200E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.809 | TFLOPs: 28.53 | +7: iteration 21390/ 37905 | consumed samples: 5475840 | consumed tokens: 11214520320 | elapsed time per iteration (s): 0.23 | learning rate: 9.316E-05 | global batch size: 256 | lm loss: 3.353759E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.023 | TFLOPs: 28.63 | +7: iteration 21400/ 37905 | consumed samples: 5478400 | consumed tokens: 11219763200 | elapsed time per iteration (s): 0.23 | learning rate: 9.309E-05 | global batch size: 256 | lm loss: 3.387882E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.857 | TFLOPs: 28.60 | +7: iteration 21410/ 37905 | consumed samples: 5480960 | consumed tokens: 11225006080 | elapsed time per iteration (s): 0.23 | learning rate: 9.301E-05 | global batch size: 256 | lm loss: 3.359406E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.586 | TFLOPs: 27.94 | +7: iteration 21420/ 37905 | consumed samples: 5483520 | consumed tokens: 11230248960 | elapsed time per iteration (s): 0.23 | learning rate: 9.294E-05 | global batch size: 256 | lm loss: 3.385960E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.264 | TFLOPs: 28.46 | +7: iteration 21430/ 37905 | consumed samples: 5486080 | consumed tokens: 11235491840 | elapsed time per iteration (s): 0.24 | learning rate: 9.287E-05 | global batch size: 256 | lm loss: 3.383251E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.561 | TFLOPs: 27.65 | +7: iteration 21440/ 37905 | consumed samples: 5488640 | consumed tokens: 11240734720 | elapsed time per iteration (s): 0.26 | learning rate: 9.279E-05 | global batch size: 256 | lm loss: 3.371005E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 979.595 | TFLOPs: 24.96 | +7: iteration 21450/ 37905 | consumed samples: 5491200 | consumed tokens: 11245977600 | elapsed time per iteration (s): 0.24 | learning rate: 9.272E-05 | global batch size: 256 | lm loss: 3.352806E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1082.981 | TFLOPs: 27.59 | +7: iteration 21460/ 37905 | consumed samples: 5493760 | consumed tokens: 11251220480 | elapsed time per iteration (s): 0.26 | learning rate: 9.264E-05 | global batch size: 256 | lm loss: 3.341157E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 992.706 | TFLOPs: 25.29 | +7: iteration 21470/ 37905 | consumed samples: 5496320 | consumed tokens: 11256463360 | elapsed time per iteration (s): 0.28 | learning rate: 9.257E-05 | global batch size: 256 | lm loss: 3.370285E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 922.335 | TFLOPs: 23.50 | +7: iteration 21480/ 37905 | consumed samples: 5498880 | consumed tokens: 11261706240 | elapsed time per iteration (s): 0.35 | learning rate: 9.250E-05 | global batch size: 256 | lm loss: 3.363387E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 740.886 | TFLOPs: 18.87 | +7: iteration 21490/ 37905 | consumed samples: 5501440 | consumed tokens: 11266949120 | elapsed time per iteration (s): 0.25 | learning rate: 9.242E-05 | global batch size: 256 | lm loss: 3.369540E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1041.269 | TFLOPs: 26.53 | +7: iteration 21500/ 37905 | consumed samples: 5504000 | consumed tokens: 11272192000 | elapsed time per iteration (s): 0.27 | learning rate: 9.235E-05 | global batch size: 256 | lm loss: 3.357464E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 952.591 | TFLOPs: 24.27 | +7: iteration 21510/ 37905 | consumed samples: 5506560 | consumed tokens: 11277434880 | elapsed time per iteration (s): 0.24 | learning rate: 9.228E-05 | global batch size: 256 | lm loss: 3.388320E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1055.353 | TFLOPs: 26.89 | +7: iteration 21520/ 37905 | consumed samples: 5509120 | consumed tokens: 11282677760 | elapsed time per iteration (s): 0.23 | learning rate: 9.220E-05 | global batch size: 256 | lm loss: 3.380333E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.758 | TFLOPs: 27.81 | +7: iteration 21530/ 37905 | consumed samples: 5511680 | consumed tokens: 11287920640 | elapsed time per iteration (s): 0.23 | learning rate: 9.213E-05 | global batch size: 256 | lm loss: 3.379788E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.568 | TFLOPs: 27.86 | +7: iteration 21540/ 37905 | consumed samples: 5514240 | consumed tokens: 11293163520 | elapsed time per iteration (s): 0.23 | learning rate: 9.205E-05 | global batch size: 256 | lm loss: 3.361274E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.753 | TFLOPs: 28.45 | +7: iteration 21550/ 37905 | consumed samples: 5516800 | consumed tokens: 11298406400 | elapsed time per iteration (s): 0.23 | learning rate: 9.198E-05 | global batch size: 256 | lm loss: 3.358006E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.045 | TFLOPs: 28.56 | +7: iteration 21560/ 37905 | consumed samples: 5519360 | consumed tokens: 11303649280 | elapsed time per iteration (s): 0.23 | learning rate: 9.191E-05 | global batch size: 256 | lm loss: 3.372236E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.099 | TFLOPs: 28.56 | +7: iteration 21570/ 37905 | consumed samples: 5521920 | consumed tokens: 11308892160 | elapsed time per iteration (s): 0.23 | learning rate: 9.183E-05 | global batch size: 256 | lm loss: 3.337755E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.873 | TFLOPs: 28.63 | +7: iteration 21580/ 37905 | consumed samples: 5524480 | consumed tokens: 11314135040 | elapsed time per iteration (s): 0.23 | learning rate: 9.176E-05 | global batch size: 256 | lm loss: 3.325100E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.063 | TFLOPs: 28.69 | +7: iteration 21590/ 37905 | consumed samples: 5527040 | consumed tokens: 11319377920 | elapsed time per iteration (s): 0.23 | learning rate: 9.168E-05 | global batch size: 256 | lm loss: 3.330431E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.042 | TFLOPs: 28.61 | +7: iteration 21600/ 37905 | consumed samples: 5529600 | consumed tokens: 11324620800 | elapsed time per iteration (s): 0.23 | learning rate: 9.161E-05 | global batch size: 256 | lm loss: 3.349202E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.769 | TFLOPs: 28.65 | +7: iteration 21610/ 37905 | consumed samples: 5532160 | consumed tokens: 11329863680 | elapsed time per iteration (s): 0.37 | learning rate: 9.154E-05 | global batch size: 256 | lm loss: 3.358260E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 691.375 | TFLOPs: 17.61 | +7: iteration 21620/ 37905 | consumed samples: 5534720 | consumed tokens: 11335106560 | elapsed time per iteration (s): 0.23 | learning rate: 9.146E-05 | global batch size: 256 | lm loss: 3.353931E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.450 | TFLOPs: 28.54 | +7: iteration 21630/ 37905 | consumed samples: 5537280 | consumed tokens: 11340349440 | elapsed time per iteration (s): 0.24 | learning rate: 9.139E-05 | global batch size: 256 | lm loss: 3.363880E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1076.112 | TFLOPs: 27.41 | +7: iteration 21640/ 37905 | consumed samples: 5539840 | consumed tokens: 11345592320 | elapsed time per iteration (s): 0.23 | learning rate: 9.132E-05 | global batch size: 256 | lm loss: 3.353981E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.685 | TFLOPs: 27.99 | +7: iteration 21650/ 37905 | consumed samples: 5542400 | consumed tokens: 11350835200 | elapsed time per iteration (s): 0.23 | learning rate: 9.124E-05 | global batch size: 256 | lm loss: 3.339148E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.154 | TFLOPs: 28.08 | +7: iteration 21660/ 37905 | consumed samples: 5544960 | consumed tokens: 11356078080 | elapsed time per iteration (s): 0.25 | learning rate: 9.117E-05 | global batch size: 256 | lm loss: 3.367501E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1041.966 | TFLOPs: 26.54 | +7: iteration 21670/ 37905 | consumed samples: 5547520 | consumed tokens: 11361320960 | elapsed time per iteration (s): 0.61 | learning rate: 9.109E-05 | global batch size: 256 | lm loss: 3.365695E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 419.820 | TFLOPs: 10.69 | +7: iteration 21680/ 37905 | consumed samples: 5550080 | consumed tokens: 11366563840 | elapsed time per iteration (s): 0.46 | learning rate: 9.102E-05 | global batch size: 256 | lm loss: 3.365324E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 559.884 | TFLOPs: 14.26 | +7: iteration 21690/ 37905 | consumed samples: 5552640 | consumed tokens: 11371806720 | elapsed time per iteration (s): 0.25 | learning rate: 9.095E-05 | global batch size: 256 | lm loss: 3.353304E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1042.150 | TFLOPs: 26.55 | +7: iteration 21700/ 37905 | consumed samples: 5555200 | consumed tokens: 11377049600 | elapsed time per iteration (s): 0.23 | learning rate: 9.087E-05 | global batch size: 256 | lm loss: 3.362923E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.689 | TFLOPs: 27.89 | +7: iteration 21710/ 37905 | consumed samples: 5557760 | consumed tokens: 11382292480 | elapsed time per iteration (s): 0.26 | learning rate: 9.080E-05 | global batch size: 256 | lm loss: 3.372515E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 977.680 | TFLOPs: 24.91 | +7: iteration 21720/ 37905 | consumed samples: 5560320 | consumed tokens: 11387535360 | elapsed time per iteration (s): 0.23 | learning rate: 9.073E-05 | global batch size: 256 | lm loss: 3.373271E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.671 | TFLOPs: 27.76 | +7: iteration 21730/ 37905 | consumed samples: 5562880 | consumed tokens: 11392778240 | elapsed time per iteration (s): 0.23 | learning rate: 9.065E-05 | global batch size: 256 | lm loss: 3.392933E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.297 | TFLOPs: 28.41 | +7: iteration 21740/ 37905 | consumed samples: 5565440 | consumed tokens: 11398021120 | elapsed time per iteration (s): 0.23 | learning rate: 9.058E-05 | global batch size: 256 | lm loss: 3.349014E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.470 | TFLOPs: 28.49 | +7: iteration 21750/ 37905 | consumed samples: 5568000 | consumed tokens: 11403264000 | elapsed time per iteration (s): 0.23 | learning rate: 9.051E-05 | global batch size: 256 | lm loss: 3.382221E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.462 | TFLOPs: 28.49 | +7: iteration 21760/ 37905 | consumed samples: 5570560 | consumed tokens: 11408506880 | elapsed time per iteration (s): 0.23 | learning rate: 9.043E-05 | global batch size: 256 | lm loss: 3.344252E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.278 | TFLOPs: 28.49 | +7: iteration 21770/ 37905 | consumed samples: 5573120 | consumed tokens: 11413749760 | elapsed time per iteration (s): 0.23 | learning rate: 9.036E-05 | global batch size: 256 | lm loss: 3.374900E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.300 | TFLOPs: 28.41 | +7: iteration 21780/ 37905 | consumed samples: 5575680 | consumed tokens: 11418992640 | elapsed time per iteration (s): 0.24 | learning rate: 9.029E-05 | global batch size: 256 | lm loss: 3.385186E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1066.054 | TFLOPs: 27.16 | +7: iteration 21790/ 37905 | consumed samples: 5578240 | consumed tokens: 11424235520 | elapsed time per iteration (s): 0.23 | learning rate: 9.021E-05 | global batch size: 256 | lm loss: 3.355789E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.500 | TFLOPs: 28.21 | +7: iteration 21800/ 37905 | consumed samples: 5580800 | consumed tokens: 11429478400 | elapsed time per iteration (s): 0.25 | learning rate: 9.014E-05 | global batch size: 256 | lm loss: 3.356134E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1019.693 | TFLOPs: 25.98 | +7: iteration 21810/ 37905 | consumed samples: 5583360 | consumed tokens: 11434721280 | elapsed time per iteration (s): 0.23 | learning rate: 9.006E-05 | global batch size: 256 | lm loss: 3.362807E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.108 | TFLOPs: 28.15 | +7: iteration 21820/ 37905 | consumed samples: 5585920 | consumed tokens: 11439964160 | elapsed time per iteration (s): 0.25 | learning rate: 8.999E-05 | global batch size: 256 | lm loss: 3.348615E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1034.755 | TFLOPs: 26.36 | +7: iteration 21830/ 37905 | consumed samples: 5588480 | consumed tokens: 11445207040 | elapsed time per iteration (s): 0.24 | learning rate: 8.992E-05 | global batch size: 256 | lm loss: 3.360089E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1072.980 | TFLOPs: 27.33 | +7: iteration 21840/ 37905 | consumed samples: 5591040 | consumed tokens: 11450449920 | elapsed time per iteration (s): 0.24 | learning rate: 8.984E-05 | global batch size: 256 | lm loss: 3.360559E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1074.793 | TFLOPs: 27.38 | +7: iteration 21850/ 37905 | consumed samples: 5593600 | consumed tokens: 11455692800 | elapsed time per iteration (s): 0.25 | learning rate: 8.977E-05 | global batch size: 256 | lm loss: 3.377857E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1012.351 | TFLOPs: 25.79 | +7: iteration 21860/ 37905 | consumed samples: 5596160 | consumed tokens: 11460935680 | elapsed time per iteration (s): 0.30 | learning rate: 8.970E-05 | global batch size: 256 | lm loss: 3.351166E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 849.261 | TFLOPs: 21.64 | +7: iteration 21870/ 37905 | consumed samples: 5598720 | consumed tokens: 11466178560 | elapsed time per iteration (s): 0.26 | learning rate: 8.962E-05 | global batch size: 256 | lm loss: 3.357708E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 986.965 | TFLOPs: 25.14 | +7: iteration 21880/ 37905 | consumed samples: 5601280 | consumed tokens: 11471421440 | elapsed time per iteration (s): 0.27 | learning rate: 8.955E-05 | global batch size: 256 | lm loss: 3.357798E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 935.136 | TFLOPs: 23.82 | +7: iteration 21890/ 37905 | consumed samples: 5603840 | consumed tokens: 11476664320 | elapsed time per iteration (s): 0.24 | learning rate: 8.948E-05 | global batch size: 256 | lm loss: 3.359428E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.801 | TFLOPs: 27.74 | +7: iteration 21900/ 37905 | consumed samples: 5606400 | consumed tokens: 11481907200 | elapsed time per iteration (s): 0.23 | learning rate: 8.940E-05 | global batch size: 256 | lm loss: 3.354237E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.918 | TFLOPs: 28.00 | +7: iteration 21910/ 37905 | consumed samples: 5608960 | consumed tokens: 11487150080 | elapsed time per iteration (s): 0.23 | learning rate: 8.933E-05 | global batch size: 256 | lm loss: 3.378755E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.690 | TFLOPs: 28.32 | +7: iteration 21920/ 37905 | consumed samples: 5611520 | consumed tokens: 11492392960 | elapsed time per iteration (s): 0.23 | learning rate: 8.926E-05 | global batch size: 256 | lm loss: 3.403040E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.181 | TFLOPs: 28.23 | +7: iteration 21930/ 37905 | consumed samples: 5614080 | consumed tokens: 11497635840 | elapsed time per iteration (s): 0.23 | learning rate: 8.918E-05 | global batch size: 256 | lm loss: 3.368811E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.106 | TFLOPs: 28.53 | +7: iteration 21940/ 37905 | consumed samples: 5616640 | consumed tokens: 11502878720 | elapsed time per iteration (s): 0.24 | learning rate: 8.911E-05 | global batch size: 256 | lm loss: 3.376537E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1062.197 | TFLOPs: 27.06 | +7: iteration 21950/ 37905 | consumed samples: 5619200 | consumed tokens: 11508121600 | elapsed time per iteration (s): 0.23 | learning rate: 8.904E-05 | global batch size: 256 | lm loss: 3.362910E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.391 | TFLOPs: 28.54 | +7: iteration 21960/ 37905 | consumed samples: 5621760 | consumed tokens: 11513364480 | elapsed time per iteration (s): 0.23 | learning rate: 8.896E-05 | global batch size: 256 | lm loss: 3.380287E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.570 | TFLOPs: 28.55 | +7: iteration 21970/ 37905 | consumed samples: 5624320 | consumed tokens: 11518607360 | elapsed time per iteration (s): 0.23 | learning rate: 8.889E-05 | global batch size: 256 | lm loss: 3.366004E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.018 | TFLOPs: 28.56 | +7: iteration 21980/ 37905 | consumed samples: 5626880 | consumed tokens: 11523850240 | elapsed time per iteration (s): 0.23 | learning rate: 8.882E-05 | global batch size: 256 | lm loss: 3.374178E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.552 | TFLOPs: 28.57 | +7: iteration 21990/ 37905 | consumed samples: 5629440 | consumed tokens: 11529093120 | elapsed time per iteration (s): 0.23 | learning rate: 8.874E-05 | global batch size: 256 | lm loss: 3.368783E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.125 | TFLOPs: 28.31 | +0: [2022-11-29 18:23:23,001] [INFO] [logging.py:68:log_dist] [Rank 0] step=22000, skipped=0, lr=[8.86714956590028e-05, 8.86714956590028e-05, 8.86714956590028e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 22000/ 37905 | consumed samples: 5632000 | consumed tokens: 11534336000 | elapsed time per iteration (s): 0.23 | learning rate: 8.867E-05 | global batch size: 256 | lm loss: 3.344677E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.026 | TFLOPs: 28.20 | +0: steps: 22000 loss: 3.2640 iter time (s): 0.237 samples/sec: 1078.142 +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 22000 | lm loss value: 3.223797E+00 | lm loss PPL: 2.512333E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 22000 to checkpoints_83moscar +0: [2022-11-29 18:23:23,092] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step22000 is begin to save! +0: [2022-11-29 18:23:23,095] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:23:23,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:23:23,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:23:23,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:23:23,190] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:23:23,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:23:23,202] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:23:23,214] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:23:23,214] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:23:23,226] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:23:23,226] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:23:23,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:23:23,239] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:23:23,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:23:23,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:23:23,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:23:23,263] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:23:23,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:23:23,275] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:23:23,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:23:23,287] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:23:23,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:23:23,299] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:23:23,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:23:23,301] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step22000/mp_rank_00_model_states.pt +0: [2022-11-29 18:23:23,301] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:23:23,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:23:23,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:23:23,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:23:23,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:23:23,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +0: [2022-11-29 18:23:23,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:23:23,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:23:23,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:23:23,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +2: [2022-11-29 18:23:23,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:23:23,344] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:23:23,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +1: [2022-11-29 18:23:23,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:23:23,345] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:23:23,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +4: [2022-11-29 18:23:23,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:23:23,345] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:23:23,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +6: [2022-11-29 18:23:23,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:23:23,345] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:23:23,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +0: [2022-11-29 18:23:23,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:23:23,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:23:23,346] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +7: [2022-11-29 18:23:23,346] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +0: [2022-11-29 18:23:23,346] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +7: [2022-11-29 18:23:23,346] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +0: [2022-11-29 18:23:23,346] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:23:23,346] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +3: [2022-11-29 18:23:23,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:23:23,346] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:23:23,346] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +5: [2022-11-29 18:23:23,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:23:23,347] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:23:23,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:23:23,347] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +3: [2022-11-29 18:23:23,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:23:23,347] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +3: [2022-11-29 18:23:23,347] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +5: [2022-11-29 18:23:23,347] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +3: [2022-11-29 18:23:23,347] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +7: [2022-11-29 18:23:23,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:23:23,347] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:23:23,347] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +4: [2022-11-29 18:23:23,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:23:23,347] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:23:23,347] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +6: [2022-11-29 18:23:23,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:23:23,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:23:23,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +7: [2022-11-29 18:23:23,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:23:23,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:23:23,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +2: [2022-11-29 18:23:23,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:23:23,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:23:23,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +0: [2022-11-29 18:23:23,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +2: [2022-11-29 18:23:23,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +0: [2022-11-29 18:23:23,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +4: [2022-11-29 18:23:23,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:23:23,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:23:23,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +6: [2022-11-29 18:23:23,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:23:23,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:23:23,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +5: [2022-11-29 18:23:23,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:23:23,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:23:23,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +1: [2022-11-29 18:23:23,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:23:23,350] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:23:23,350] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +3: [2022-11-29 18:23:23,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:23:23,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:23:23,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +1: [2022-11-29 18:23:23,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:23:23,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:23:23,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +6: [2022-11-29 18:23:23,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:23:23,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:23:23,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +7: [2022-11-29 18:23:23,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:23:23,352] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:23:23,352] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +5: [2022-11-29 18:23:23,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:23:23,352] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:23:23,352] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +0: [2022-11-29 18:23:23,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:23:23,352] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:23:23,352] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +4: [2022-11-29 18:23:23,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:23:23,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:23:23,352] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +3: [2022-11-29 18:23:23,352] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +4: [2022-11-29 18:23:23,352] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +3: [2022-11-29 18:23:23,352] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +2: [2022-11-29 18:23:23,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:23:23,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:23:23,353] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:23:23,353] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:23:23,353] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +2: [2022-11-29 18:23:23,353] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +6: [2022-11-29 18:23:23,353] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:23:23,354] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:23:23,354] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +5: [2022-11-29 18:23:23,354] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:23:23,354] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:23:23,354] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +1: [2022-11-29 18:23:23,354] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:23:23,354] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:23:23,354] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +0: [2022-11-29 18:23:23,354] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:23:23,354] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:23:23,354] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +4: [2022-11-29 18:23:23,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:23:23,355] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:23:23,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +3: [2022-11-29 18:23:23,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:23:23,355] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:23:23,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +7: [2022-11-29 18:23:23,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:23:23,355] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:23:23,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +5: [2022-11-29 18:23:23,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:23:23,355] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +2: [2022-11-29 18:23:23,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:23:23,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +2: [2022-11-29 18:23:23,355] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:23:23,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +7: [2022-11-29 18:23:23,356] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:23:23,356] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:23:23,356] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +1: [2022-11-29 18:23:23,356] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:23:23,356] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:23:23,356] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +6: [2022-11-29 18:23:23,356] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:23:23,356] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:23:23,356] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +0: [2022-11-29 18:23:23,357] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:23:23,357] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:23:23,357] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +6: [2022-11-29 18:23:23,357] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:23:23,357] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:23:23,357] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +4: [2022-11-29 18:23:23,357] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:23:23,357] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:23:23,357] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +4: [2022-11-29 18:23:23,357] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:23:23,357] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:23:23,357] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +2: [2022-11-29 18:23:23,357] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:23:23,357] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +4: [2022-11-29 18:23:23,357] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +5: [2022-11-29 18:23:23,358] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:23:23,358] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:23:23,358] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +3: [2022-11-29 18:23:23,358] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:23:23,358] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +3: [2022-11-29 18:23:23,358] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +5: [2022-11-29 18:23:23,358] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:23:23,358] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +5: [2022-11-29 18:23:23,358] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +3: [2022-11-29 18:23:23,358] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +1: [2022-11-29 18:23:23,358] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:23:23,358] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +3: [2022-11-29 18:23:23,358] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +1: [2022-11-29 18:23:23,358] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:23:23,358] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +1: [2022-11-29 18:23:23,358] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:23:23,358] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:23:23,358] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +0: [2022-11-29 18:23:23,358] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:23:23,358] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:23:23,358] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:23:23,358] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:23:23,358] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +0: [2022-11-29 18:23:23,358] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +4: [2022-11-29 18:23:23,358] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:23:23,358] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:23:23,358] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +7: [2022-11-29 18:23:23,359] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:23:23,359] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:23:23,359] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +3: [2022-11-29 18:23:23,359] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:23:23,359] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +2: [2022-11-29 18:23:23,359] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:23:23,359] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +2: [2022-11-29 18:23:23,359] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:23:23,359] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +7: [2022-11-29 18:23:23,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:23:23,360] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:23:23,360] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +2: [2022-11-29 18:23:23,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:23:23,360] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step22000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:23:23,360] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +0: successfully saved checkpoint at iteration 22000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 272.20 +7: iteration 22010/ 37905 | consumed samples: 5634560 | consumed tokens: 11539578880 | elapsed time per iteration (s): 0.31 | learning rate: 8.860E-05 | global batch size: 256 | lm loss: 3.342640E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 818.871 | TFLOPs: 20.86 | +7: iteration 22020/ 37905 | consumed samples: 5637120 | consumed tokens: 11544821760 | elapsed time per iteration (s): 0.23 | learning rate: 8.853E-05 | global batch size: 256 | lm loss: 3.361939E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.038 | TFLOPs: 28.10 | +7: iteration 22030/ 37905 | consumed samples: 5639680 | consumed tokens: 11550064640 | elapsed time per iteration (s): 0.36 | learning rate: 8.845E-05 | global batch size: 256 | lm loss: 3.369196E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 702.964 | TFLOPs: 17.91 | +7: iteration 22040/ 37905 | consumed samples: 5642240 | consumed tokens: 11555307520 | elapsed time per iteration (s): 0.36 | learning rate: 8.838E-05 | global batch size: 256 | lm loss: 3.343331E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 719.098 | TFLOPs: 18.32 | +7: iteration 22050/ 37905 | consumed samples: 5644800 | consumed tokens: 11560550400 | elapsed time per iteration (s): 0.24 | learning rate: 8.831E-05 | global batch size: 256 | lm loss: 3.346527E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.023 | TFLOPs: 27.67 | +7: iteration 22060/ 37905 | consumed samples: 5647360 | consumed tokens: 11565793280 | elapsed time per iteration (s): 0.37 | learning rate: 8.823E-05 | global batch size: 256 | lm loss: 3.335278E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 691.231 | TFLOPs: 17.61 | +7: iteration 22070/ 37905 | consumed samples: 5649920 | consumed tokens: 11571036160 | elapsed time per iteration (s): 0.24 | learning rate: 8.816E-05 | global batch size: 256 | lm loss: 3.336179E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1045.447 | TFLOPs: 26.63 | +7: iteration 22080/ 37905 | consumed samples: 5652480 | consumed tokens: 11576279040 | elapsed time per iteration (s): 0.24 | learning rate: 8.809E-05 | global batch size: 256 | lm loss: 3.342618E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.618 | TFLOPs: 27.68 | +7: iteration 22090/ 37905 | consumed samples: 5655040 | consumed tokens: 11581521920 | elapsed time per iteration (s): 0.23 | learning rate: 8.801E-05 | global batch size: 256 | lm loss: 3.348763E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.488 | TFLOPs: 28.06 | +7: iteration 22100/ 37905 | consumed samples: 5657600 | consumed tokens: 11586764800 | elapsed time per iteration (s): 0.29 | learning rate: 8.794E-05 | global batch size: 256 | lm loss: 3.363602E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 884.478 | TFLOPs: 22.53 | +7: iteration 22110/ 37905 | consumed samples: 5660160 | consumed tokens: 11592007680 | elapsed time per iteration (s): 0.25 | learning rate: 8.787E-05 | global batch size: 256 | lm loss: 3.343119E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1035.563 | TFLOPs: 26.38 | +7: iteration 22120/ 37905 | consumed samples: 5662720 | consumed tokens: 11597250560 | elapsed time per iteration (s): 0.23 | learning rate: 8.779E-05 | global batch size: 256 | lm loss: 3.341933E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.911 | TFLOPs: 28.40 | +7: iteration 22130/ 37905 | consumed samples: 5665280 | consumed tokens: 11602493440 | elapsed time per iteration (s): 0.23 | learning rate: 8.772E-05 | global batch size: 256 | lm loss: 3.356574E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.004 | TFLOPs: 27.79 | +7: iteration 22140/ 37905 | consumed samples: 5667840 | consumed tokens: 11607736320 | elapsed time per iteration (s): 0.23 | learning rate: 8.765E-05 | global batch size: 256 | lm loss: 3.341074E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.385 | TFLOPs: 28.29 | +7: iteration 22150/ 37905 | consumed samples: 5670400 | consumed tokens: 11612979200 | elapsed time per iteration (s): 0.23 | learning rate: 8.758E-05 | global batch size: 256 | lm loss: 3.304479E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.585 | TFLOPs: 27.91 | +7: iteration 22160/ 37905 | consumed samples: 5672960 | consumed tokens: 11618222080 | elapsed time per iteration (s): 0.23 | learning rate: 8.750E-05 | global batch size: 256 | lm loss: 3.351430E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.636 | TFLOPs: 28.29 | +7: iteration 22170/ 37905 | consumed samples: 5675520 | consumed tokens: 11623464960 | elapsed time per iteration (s): 0.23 | learning rate: 8.743E-05 | global batch size: 256 | lm loss: 3.356811E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.411 | TFLOPs: 27.93 | +7: iteration 22180/ 37905 | consumed samples: 5678080 | consumed tokens: 11628707840 | elapsed time per iteration (s): 0.23 | learning rate: 8.736E-05 | global batch size: 256 | lm loss: 3.345829E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.537 | TFLOPs: 27.93 | +7: iteration 22190/ 37905 | consumed samples: 5680640 | consumed tokens: 11633950720 | elapsed time per iteration (s): 0.24 | learning rate: 8.728E-05 | global batch size: 256 | lm loss: 3.362470E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1061.372 | TFLOPs: 27.04 | +7: iteration 22200/ 37905 | consumed samples: 5683200 | consumed tokens: 11639193600 | elapsed time per iteration (s): 0.24 | learning rate: 8.721E-05 | global batch size: 256 | lm loss: 3.363354E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1068.027 | TFLOPs: 27.21 | +7: iteration 22210/ 37905 | consumed samples: 5685760 | consumed tokens: 11644436480 | elapsed time per iteration (s): 0.24 | learning rate: 8.714E-05 | global batch size: 256 | lm loss: 3.351737E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1049.216 | TFLOPs: 26.73 | +7: iteration 22220/ 37905 | consumed samples: 5688320 | consumed tokens: 11649679360 | elapsed time per iteration (s): 0.24 | learning rate: 8.706E-05 | global batch size: 256 | lm loss: 3.361853E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1055.676 | TFLOPs: 26.89 | +7: iteration 22230/ 37905 | consumed samples: 5690880 | consumed tokens: 11654922240 | elapsed time per iteration (s): 0.25 | learning rate: 8.699E-05 | global batch size: 256 | lm loss: 3.386770E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1023.798 | TFLOPs: 26.08 | +7: iteration 22240/ 37905 | consumed samples: 5693440 | consumed tokens: 11660165120 | elapsed time per iteration (s): 0.24 | learning rate: 8.692E-05 | global batch size: 256 | lm loss: 3.347549E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1063.372 | TFLOPs: 27.09 | +7: iteration 22250/ 37905 | consumed samples: 5696000 | consumed tokens: 11665408000 | elapsed time per iteration (s): 0.24 | learning rate: 8.685E-05 | global batch size: 256 | lm loss: 3.386235E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.766 | TFLOPs: 27.66 | +7: iteration 22260/ 37905 | consumed samples: 5698560 | consumed tokens: 11670650880 | elapsed time per iteration (s): 0.24 | learning rate: 8.677E-05 | global batch size: 256 | lm loss: 3.374455E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.254 | TFLOPs: 27.26 | +7: iteration 22270/ 37905 | consumed samples: 5701120 | consumed tokens: 11675893760 | elapsed time per iteration (s): 0.23 | learning rate: 8.670E-05 | global batch size: 256 | lm loss: 3.358981E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.476 | TFLOPs: 27.86 | +7: iteration 22280/ 37905 | consumed samples: 5703680 | consumed tokens: 11681136640 | elapsed time per iteration (s): 0.23 | learning rate: 8.663E-05 | global batch size: 256 | lm loss: 3.371574E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.310 | TFLOPs: 27.85 | +7: iteration 22290/ 37905 | consumed samples: 5706240 | consumed tokens: 11686379520 | elapsed time per iteration (s): 0.23 | learning rate: 8.656E-05 | global batch size: 256 | lm loss: 3.349832E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.068 | TFLOPs: 28.28 | +7: iteration 22300/ 37905 | consumed samples: 5708800 | consumed tokens: 11691622400 | elapsed time per iteration (s): 0.26 | learning rate: 8.648E-05 | global batch size: 256 | lm loss: 3.346330E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 985.960 | TFLOPs: 25.12 | +7: iteration 22310/ 37905 | consumed samples: 5711360 | consumed tokens: 11696865280 | elapsed time per iteration (s): 0.23 | learning rate: 8.641E-05 | global batch size: 256 | lm loss: 3.374506E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.344 | TFLOPs: 28.62 | +7: iteration 22320/ 37905 | consumed samples: 5713920 | consumed tokens: 11702108160 | elapsed time per iteration (s): 0.23 | learning rate: 8.634E-05 | global batch size: 256 | lm loss: 3.375255E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.521 | TFLOPs: 28.65 | +7: iteration 22330/ 37905 | consumed samples: 5716480 | consumed tokens: 11707351040 | elapsed time per iteration (s): 0.23 | learning rate: 8.626E-05 | global batch size: 256 | lm loss: 3.329593E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.976 | TFLOPs: 28.61 | +7: iteration 22340/ 37905 | consumed samples: 5719040 | consumed tokens: 11712593920 | elapsed time per iteration (s): 0.23 | learning rate: 8.619E-05 | global batch size: 256 | lm loss: 3.364196E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.657 | TFLOPs: 28.42 | +7: iteration 22350/ 37905 | consumed samples: 5721600 | consumed tokens: 11717836800 | elapsed time per iteration (s): 0.23 | learning rate: 8.612E-05 | global batch size: 256 | lm loss: 3.365522E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.102 | TFLOPs: 28.53 | +7: iteration 22360/ 37905 | consumed samples: 5724160 | consumed tokens: 11723079680 | elapsed time per iteration (s): 0.23 | learning rate: 8.605E-05 | global batch size: 256 | lm loss: 3.411708E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.334 | TFLOPs: 28.52 | +7: iteration 22370/ 37905 | consumed samples: 5726720 | consumed tokens: 11728322560 | elapsed time per iteration (s): 0.23 | learning rate: 8.597E-05 | global batch size: 256 | lm loss: 3.344761E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.498 | TFLOPs: 28.52 | +7: iteration 22380/ 37905 | consumed samples: 5729280 | consumed tokens: 11733565440 | elapsed time per iteration (s): 0.24 | learning rate: 8.590E-05 | global batch size: 256 | lm loss: 3.358181E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1066.519 | TFLOPs: 27.17 | +7: iteration 22390/ 37905 | consumed samples: 5731840 | consumed tokens: 11738808320 | elapsed time per iteration (s): 0.23 | learning rate: 8.583E-05 | global batch size: 256 | lm loss: 3.372186E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.067 | TFLOPs: 28.10 | +7: iteration 22400/ 37905 | consumed samples: 5734400 | consumed tokens: 11744051200 | elapsed time per iteration (s): 0.24 | learning rate: 8.576E-05 | global batch size: 256 | lm loss: 3.368846E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.597 | TFLOPs: 27.66 | +7: iteration 22410/ 37905 | consumed samples: 5736960 | consumed tokens: 11749294080 | elapsed time per iteration (s): 0.24 | learning rate: 8.568E-05 | global batch size: 256 | lm loss: 3.378026E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1083.880 | TFLOPs: 27.61 | +7: iteration 22420/ 37905 | consumed samples: 5739520 | consumed tokens: 11754536960 | elapsed time per iteration (s): 0.24 | learning rate: 8.561E-05 | global batch size: 256 | lm loss: 3.350389E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1075.121 | TFLOPs: 27.39 | +7: iteration 22430/ 37905 | consumed samples: 5742080 | consumed tokens: 11759779840 | elapsed time per iteration (s): 0.24 | learning rate: 8.554E-05 | global batch size: 256 | lm loss: 3.312342E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1079.306 | TFLOPs: 27.50 | +7: iteration 22440/ 37905 | consumed samples: 5744640 | consumed tokens: 11765022720 | elapsed time per iteration (s): 0.23 | learning rate: 8.547E-05 | global batch size: 256 | lm loss: 3.357026E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.758 | TFLOPs: 27.86 | +7: iteration 22450/ 37905 | consumed samples: 5747200 | consumed tokens: 11770265600 | elapsed time per iteration (s): 0.30 | learning rate: 8.539E-05 | global batch size: 256 | lm loss: 3.403290E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 864.387 | TFLOPs: 22.02 | +7: iteration 22460/ 37905 | consumed samples: 5749760 | consumed tokens: 11775508480 | elapsed time per iteration (s): 0.32 | learning rate: 8.532E-05 | global batch size: 256 | lm loss: 3.324857E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 793.857 | TFLOPs: 20.22 | +7: iteration 22470/ 37905 | consumed samples: 5752320 | consumed tokens: 11780751360 | elapsed time per iteration (s): 0.25 | learning rate: 8.525E-05 | global batch size: 256 | lm loss: 3.328919E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1030.857 | TFLOPs: 26.26 | +7: iteration 22480/ 37905 | consumed samples: 5754880 | consumed tokens: 11785994240 | elapsed time per iteration (s): 0.23 | learning rate: 8.518E-05 | global batch size: 256 | lm loss: 3.398020E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.264 | TFLOPs: 28.34 | +7: iteration 22490/ 37905 | consumed samples: 5757440 | consumed tokens: 11791237120 | elapsed time per iteration (s): 0.23 | learning rate: 8.510E-05 | global batch size: 256 | lm loss: 3.368008E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.404 | TFLOPs: 28.19 | +7: iteration 22500/ 37905 | consumed samples: 5760000 | consumed tokens: 11796480000 | elapsed time per iteration (s): 0.23 | learning rate: 8.503E-05 | global batch size: 256 | lm loss: 3.360550E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.150 | TFLOPs: 28.23 | +7: iteration 22510/ 37905 | consumed samples: 5762560 | consumed tokens: 11801722880 | elapsed time per iteration (s): 0.23 | learning rate: 8.496E-05 | global batch size: 256 | lm loss: 3.373406E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.373 | TFLOPs: 28.03 | +7: iteration 22520/ 37905 | consumed samples: 5765120 | consumed tokens: 11806965760 | elapsed time per iteration (s): 0.23 | learning rate: 8.489E-05 | global batch size: 256 | lm loss: 3.381656E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.820 | TFLOPs: 28.22 | +7: iteration 22530/ 37905 | consumed samples: 5767680 | consumed tokens: 11812208640 | elapsed time per iteration (s): 0.23 | learning rate: 8.481E-05 | global batch size: 256 | lm loss: 3.342503E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.100 | TFLOPs: 28.15 | +7: iteration 22540/ 37905 | consumed samples: 5770240 | consumed tokens: 11817451520 | elapsed time per iteration (s): 0.23 | learning rate: 8.474E-05 | global batch size: 256 | lm loss: 3.344098E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.250 | TFLOPs: 28.39 | +7: iteration 22550/ 37905 | consumed samples: 5772800 | consumed tokens: 11822694400 | elapsed time per iteration (s): 0.24 | learning rate: 8.467E-05 | global batch size: 256 | lm loss: 3.338358E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1075.113 | TFLOPs: 27.39 | +7: iteration 22560/ 37905 | consumed samples: 5775360 | consumed tokens: 11827937280 | elapsed time per iteration (s): 0.23 | learning rate: 8.460E-05 | global batch size: 256 | lm loss: 3.357213E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.998 | TFLOPs: 27.95 | +7: iteration 22570/ 37905 | consumed samples: 5777920 | consumed tokens: 11833180160 | elapsed time per iteration (s): 0.23 | learning rate: 8.452E-05 | global batch size: 256 | lm loss: 3.331732E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.679 | TFLOPs: 27.84 | +7: iteration 22580/ 37905 | consumed samples: 5780480 | consumed tokens: 11838423040 | elapsed time per iteration (s): 0.23 | learning rate: 8.445E-05 | global batch size: 256 | lm loss: 3.359895E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.911 | TFLOPs: 28.07 | +7: iteration 22590/ 37905 | consumed samples: 5783040 | consumed tokens: 11843665920 | elapsed time per iteration (s): 0.26 | learning rate: 8.438E-05 | global batch size: 256 | lm loss: 3.352533E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 995.605 | TFLOPs: 25.36 | +7: iteration 22600/ 37905 | consumed samples: 5785600 | consumed tokens: 11848908800 | elapsed time per iteration (s): 0.23 | learning rate: 8.431E-05 | global batch size: 256 | lm loss: 3.353283E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.442 | TFLOPs: 27.93 | +7: iteration 22610/ 37905 | consumed samples: 5788160 | consumed tokens: 11854151680 | elapsed time per iteration (s): 0.24 | learning rate: 8.424E-05 | global batch size: 256 | lm loss: 3.358205E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1069.604 | TFLOPs: 27.25 | +7: iteration 22620/ 37905 | consumed samples: 5790720 | consumed tokens: 11859394560 | elapsed time per iteration (s): 0.24 | learning rate: 8.416E-05 | global batch size: 256 | lm loss: 3.374729E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.870 | TFLOPs: 27.66 | +7: iteration 22630/ 37905 | consumed samples: 5793280 | consumed tokens: 11864637440 | elapsed time per iteration (s): 0.26 | learning rate: 8.409E-05 | global batch size: 256 | lm loss: 3.352897E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 994.665 | TFLOPs: 25.34 | +7: iteration 22640/ 37905 | consumed samples: 5795840 | consumed tokens: 11869880320 | elapsed time per iteration (s): 0.23 | learning rate: 8.402E-05 | global batch size: 256 | lm loss: 3.361390E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.384 | TFLOPs: 27.91 | +7: iteration 22650/ 37905 | consumed samples: 5798400 | consumed tokens: 11875123200 | elapsed time per iteration (s): 0.24 | learning rate: 8.395E-05 | global batch size: 256 | lm loss: 3.343463E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.634 | TFLOPs: 26.94 | +7: iteration 22660/ 37905 | consumed samples: 5800960 | consumed tokens: 11880366080 | elapsed time per iteration (s): 0.24 | learning rate: 8.388E-05 | global batch size: 256 | lm loss: 3.341378E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1077.623 | TFLOPs: 27.45 | +7: iteration 22670/ 37905 | consumed samples: 5803520 | consumed tokens: 11885608960 | elapsed time per iteration (s): 0.23 | learning rate: 8.380E-05 | global batch size: 256 | lm loss: 3.372377E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.003 | TFLOPs: 28.15 | +7: iteration 22680/ 37905 | consumed samples: 5806080 | consumed tokens: 11890851840 | elapsed time per iteration (s): 0.23 | learning rate: 8.373E-05 | global batch size: 256 | lm loss: 3.367429E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.248 | TFLOPs: 28.23 | +7: iteration 22690/ 37905 | consumed samples: 5808640 | consumed tokens: 11896094720 | elapsed time per iteration (s): 0.23 | learning rate: 8.366E-05 | global batch size: 256 | lm loss: 3.348860E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.987 | TFLOPs: 28.38 | +7: iteration 22700/ 37905 | consumed samples: 5811200 | consumed tokens: 11901337600 | elapsed time per iteration (s): 0.23 | learning rate: 8.359E-05 | global batch size: 256 | lm loss: 3.367387E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.895 | TFLOPs: 28.35 | +7: iteration 22710/ 37905 | consumed samples: 5813760 | consumed tokens: 11906580480 | elapsed time per iteration (s): 0.23 | learning rate: 8.352E-05 | global batch size: 256 | lm loss: 3.364306E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.950 | TFLOPs: 28.45 | +7: iteration 22720/ 37905 | consumed samples: 5816320 | consumed tokens: 11911823360 | elapsed time per iteration (s): 0.23 | learning rate: 8.344E-05 | global batch size: 256 | lm loss: 3.361821E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.405 | TFLOPs: 28.57 | +7: iteration 22730/ 37905 | consumed samples: 5818880 | consumed tokens: 11917066240 | elapsed time per iteration (s): 0.23 | learning rate: 8.337E-05 | global batch size: 256 | lm loss: 3.362291E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.518 | TFLOPs: 28.24 | +7: iteration 22740/ 37905 | consumed samples: 5821440 | consumed tokens: 11922309120 | elapsed time per iteration (s): 0.23 | learning rate: 8.330E-05 | global batch size: 256 | lm loss: 3.342749E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.813 | TFLOPs: 28.58 | +7: iteration 22750/ 37905 | consumed samples: 5824000 | consumed tokens: 11927552000 | elapsed time per iteration (s): 0.23 | learning rate: 8.323E-05 | global batch size: 256 | lm loss: 3.343612E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.096 | TFLOPs: 28.43 | +7: iteration 22760/ 37905 | consumed samples: 5826560 | consumed tokens: 11932794880 | elapsed time per iteration (s): 0.23 | learning rate: 8.316E-05 | global batch size: 256 | lm loss: 3.335925E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.461 | TFLOPs: 28.54 | +7: iteration 22770/ 37905 | consumed samples: 5829120 | consumed tokens: 11938037760 | elapsed time per iteration (s): 0.26 | learning rate: 8.308E-05 | global batch size: 256 | lm loss: 3.314598E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 999.126 | TFLOPs: 25.45 | +7: iteration 22780/ 37905 | consumed samples: 5831680 | consumed tokens: 11943280640 | elapsed time per iteration (s): 0.23 | learning rate: 8.301E-05 | global batch size: 256 | lm loss: 3.349538E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.363 | TFLOPs: 28.13 | +7: iteration 22790/ 37905 | consumed samples: 5834240 | consumed tokens: 11948523520 | elapsed time per iteration (s): 0.23 | learning rate: 8.294E-05 | global batch size: 256 | lm loss: 3.350694E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.486 | TFLOPs: 28.34 | +7: iteration 22800/ 37905 | consumed samples: 5836800 | consumed tokens: 11953766400 | elapsed time per iteration (s): 0.23 | learning rate: 8.287E-05 | global batch size: 256 | lm loss: 3.350978E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.782 | TFLOPs: 28.17 | +7: iteration 22810/ 37905 | consumed samples: 5839360 | consumed tokens: 11959009280 | elapsed time per iteration (s): 0.23 | learning rate: 8.280E-05 | global batch size: 256 | lm loss: 3.372005E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.781 | TFLOPs: 27.84 | +7: iteration 22820/ 37905 | consumed samples: 5841920 | consumed tokens: 11964252160 | elapsed time per iteration (s): 0.24 | learning rate: 8.272E-05 | global batch size: 256 | lm loss: 3.336958E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1082.216 | TFLOPs: 27.57 | +7: iteration 22830/ 37905 | consumed samples: 5844480 | consumed tokens: 11969495040 | elapsed time per iteration (s): 0.23 | learning rate: 8.265E-05 | global batch size: 256 | lm loss: 3.348942E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.583 | TFLOPs: 27.96 | +7: iteration 22840/ 37905 | consumed samples: 5847040 | consumed tokens: 11974737920 | elapsed time per iteration (s): 0.24 | learning rate: 8.258E-05 | global batch size: 256 | lm loss: 3.368345E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1072.058 | TFLOPs: 27.31 | +7: iteration 22850/ 37905 | consumed samples: 5849600 | consumed tokens: 11979980800 | elapsed time per iteration (s): 0.27 | learning rate: 8.251E-05 | global batch size: 256 | lm loss: 3.342330E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 941.165 | TFLOPs: 23.98 | +7: iteration 22860/ 37905 | consumed samples: 5852160 | consumed tokens: 11985223680 | elapsed time per iteration (s): 0.27 | learning rate: 8.244E-05 | global batch size: 256 | lm loss: 3.362666E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 953.455 | TFLOPs: 24.29 | +7: iteration 22870/ 37905 | consumed samples: 5854720 | consumed tokens: 11990466560 | elapsed time per iteration (s): 0.26 | learning rate: 8.237E-05 | global batch size: 256 | lm loss: 3.360761E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 966.182 | TFLOPs: 24.61 | +7: iteration 22880/ 37905 | consumed samples: 5857280 | consumed tokens: 11995709440 | elapsed time per iteration (s): 0.24 | learning rate: 8.229E-05 | global batch size: 256 | lm loss: 3.355914E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1046.208 | TFLOPs: 26.65 | +7: iteration 22890/ 37905 | consumed samples: 5859840 | consumed tokens: 12000952320 | elapsed time per iteration (s): 0.23 | learning rate: 8.222E-05 | global batch size: 256 | lm loss: 3.347014E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.476 | TFLOPs: 28.26 | +7: iteration 22900/ 37905 | consumed samples: 5862400 | consumed tokens: 12006195200 | elapsed time per iteration (s): 0.23 | learning rate: 8.215E-05 | global batch size: 256 | lm loss: 3.340343E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.166 | TFLOPs: 28.31 | +7: iteration 22910/ 37905 | consumed samples: 5864960 | consumed tokens: 12011438080 | elapsed time per iteration (s): 0.23 | learning rate: 8.208E-05 | global batch size: 256 | lm loss: 3.346897E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.964 | TFLOPs: 28.38 | +7: iteration 22920/ 37905 | consumed samples: 5867520 | consumed tokens: 12016680960 | elapsed time per iteration (s): 0.23 | learning rate: 8.201E-05 | global batch size: 256 | lm loss: 3.369479E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.371 | TFLOPs: 28.41 | +7: iteration 22930/ 37905 | consumed samples: 5870080 | consumed tokens: 12021923840 | elapsed time per iteration (s): 0.26 | learning rate: 8.194E-05 | global batch size: 256 | lm loss: 3.315961E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 967.658 | TFLOPs: 24.65 | +7: iteration 22940/ 37905 | consumed samples: 5872640 | consumed tokens: 12027166720 | elapsed time per iteration (s): 0.23 | learning rate: 8.186E-05 | global batch size: 256 | lm loss: 3.351653E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.036 | TFLOPs: 28.02 | +7: iteration 22950/ 37905 | consumed samples: 5875200 | consumed tokens: 12032409600 | elapsed time per iteration (s): 0.24 | learning rate: 8.179E-05 | global batch size: 256 | lm loss: 3.344181E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.752 | TFLOPs: 27.66 | +7: iteration 22960/ 37905 | consumed samples: 5877760 | consumed tokens: 12037652480 | elapsed time per iteration (s): 0.24 | learning rate: 8.172E-05 | global batch size: 256 | lm loss: 3.360000E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.888 | TFLOPs: 27.71 | +7: iteration 22970/ 37905 | consumed samples: 5880320 | consumed tokens: 12042895360 | elapsed time per iteration (s): 0.23 | learning rate: 8.165E-05 | global batch size: 256 | lm loss: 3.342647E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.440 | TFLOPs: 27.88 | +7: iteration 22980/ 37905 | consumed samples: 5882880 | consumed tokens: 12048138240 | elapsed time per iteration (s): 0.23 | learning rate: 8.158E-05 | global batch size: 256 | lm loss: 3.362689E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.130 | TFLOPs: 27.95 | +7: iteration 22990/ 37905 | consumed samples: 5885440 | consumed tokens: 12053381120 | elapsed time per iteration (s): 0.24 | learning rate: 8.151E-05 | global batch size: 256 | lm loss: 3.365763E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1067.840 | TFLOPs: 27.20 | +7: iteration 23000/ 37905 | consumed samples: 5888000 | consumed tokens: 12058624000 | elapsed time per iteration (s): 0.23 | learning rate: 8.143E-05 | global batch size: 256 | lm loss: 3.343931E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.168 | TFLOPs: 27.77 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 23000 | lm loss value: 3.238586E+00 | lm loss PPL: 2.549764E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 23000 to checkpoints_83moscar +0: [2022-11-29 18:27:26,289] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step23000 is begin to save! +0: [2022-11-29 18:27:26,292] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:27:26,373] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:27:26,374] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:27:26,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:27:26,387] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:27:26,398] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:27:26,398] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:27:26,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:27:26,410] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:27:26,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:27:26,422] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:27:26,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:27:26,433] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:27:26,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:27:26,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:27:26,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:27:26,456] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:27:26,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:27:26,468] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:27:26,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:27:26,480] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:27:26,491] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:27:26,491] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:27:26,492] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:27:26,493] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step23000/mp_rank_00_model_states.pt +0: [2022-11-29 18:27:26,493] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:27:26,495] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:27:26,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:27:26,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:27:26,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:27:26,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +0: [2022-11-29 18:27:26,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:27:26,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:27:26,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:27:26,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +7: [2022-11-29 18:27:26,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +3: [2022-11-29 18:27:26,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +7: [2022-11-29 18:27:26,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +0: [2022-11-29 18:27:26,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:27:26,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:27:26,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +4: [2022-11-29 18:27:26,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:27:26,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:27:26,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +0: [2022-11-29 18:27:26,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:27:26,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +5: [2022-11-29 18:27:26,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:27:26,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:27:26,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +2: [2022-11-29 18:27:26,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:27:26,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +1: [2022-11-29 18:27:26,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:27:26,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +1: [2022-11-29 18:27:26,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:27:26,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +2: [2022-11-29 18:27:26,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:27:26,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:27:26,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +1: [2022-11-29 18:27:26,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:27:26,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:27:26,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +7: [2022-11-29 18:27:26,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:27:26,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:27:26,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +7: [2022-11-29 18:27:26,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:27:26,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:27:26,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +1: [2022-11-29 18:27:26,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:27:26,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:27:26,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +5: [2022-11-29 18:27:26,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:27:26,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +2: [2022-11-29 18:27:26,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:27:26,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:27:26,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +5: [2022-11-29 18:27:26,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +7: [2022-11-29 18:27:26,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:27:26,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:27:26,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +4: [2022-11-29 18:27:26,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:27:26,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:27:26,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:27:26,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:27:26,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +4: [2022-11-29 18:27:26,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +3: [2022-11-29 18:27:26,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +4: [2022-11-29 18:27:26,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:27:26,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +0: [2022-11-29 18:27:26,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:27:26,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:27:26,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +0: [2022-11-29 18:27:26,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:27:26,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:27:26,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +5: [2022-11-29 18:27:26,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:27:26,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:27:26,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +1: [2022-11-29 18:27:26,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +5: [2022-11-29 18:27:26,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +1: [2022-11-29 18:27:26,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +3: [2022-11-29 18:27:26,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:27:26,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:27:26,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +2: [2022-11-29 18:27:26,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:27:26,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:27:26,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +1: [2022-11-29 18:27:26,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:27:26,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:27:26,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +5: [2022-11-29 18:27:26,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:27:26,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:27:26,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +0: [2022-11-29 18:27:26,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:27:26,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:27:26,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +7: [2022-11-29 18:27:26,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:27:26,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:27:26,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +7: [2022-11-29 18:27:26,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:27:26,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:27:26,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +1: [2022-11-29 18:27:26,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:27:26,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:27:26,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +0: [2022-11-29 18:27:26,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:27:26,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:27:26,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +4: [2022-11-29 18:27:26,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:27:26,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:27:26,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +4: [2022-11-29 18:27:26,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:27:26,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:27:26,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +3: [2022-11-29 18:27:26,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +4: [2022-11-29 18:27:26,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +3: [2022-11-29 18:27:26,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +5: [2022-11-29 18:27:26,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:27:26,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:27:26,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:27:26,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:27:26,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +2: [2022-11-29 18:27:26,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +5: [2022-11-29 18:27:26,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:27:26,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +2: [2022-11-29 18:27:26,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +0: [2022-11-29 18:27:26,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:27:26,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:27:26,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +2: [2022-11-29 18:27:26,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:27:26,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:27:26,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +4: [2022-11-29 18:27:26,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:27:26,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:27:26,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +2: [2022-11-29 18:27:26,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:27:26,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:27:26,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +5: [2022-11-29 18:27:26,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:27:26,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:27:26,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +5: [2022-11-29 18:27:26,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:27:26,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +3: [2022-11-29 18:27:26,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +3: [2022-11-29 18:27:26,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:27:26,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:27:26,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:27:26,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:27:26,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +3: [2022-11-29 18:27:26,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +2: [2022-11-29 18:27:26,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:27:26,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:27:26,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +1: [2022-11-29 18:27:26,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:27:26,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +4: [2022-11-29 18:27:26,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:27:26,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:27:26,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +0: [2022-11-29 18:27:26,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +4: [2022-11-29 18:27:26,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:27:26,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +0: [2022-11-29 18:27:26,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +4: [2022-11-29 18:27:26,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:27:26,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:27:26,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +3: [2022-11-29 18:27:26,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:27:26,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:27:26,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +1: [2022-11-29 18:27:26,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:27:26,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:27:26,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +7: [2022-11-29 18:27:26,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:27:26,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:27:26,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +7: [2022-11-29 18:27:26,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:27:26,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:27:26,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +6: [2022-11-29 18:27:26,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:27:26,551] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:27:26,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +6: [2022-11-29 18:27:26,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:27:26,551] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:27:26,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +6: [2022-11-29 18:27:26,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:27:26,551] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:27:26,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:27:26,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +6: [2022-11-29 18:27:26,551] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:27:26,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +6: [2022-11-29 18:27:26,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:27:26,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:27:26,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +6: [2022-11-29 18:27:26,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:27:26,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:27:26,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +6: [2022-11-29 18:27:26,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:27:26,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:27:26,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:27:26,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +6: [2022-11-29 18:27:26,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step23000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:27:26,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +0: successfully saved checkpoint at iteration 23000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 267.41 +7: iteration 23010/ 37905 | consumed samples: 5890560 | consumed tokens: 12063866880 | elapsed time per iteration (s): 0.27 | learning rate: 8.136E-05 | global batch size: 256 | lm loss: 3.348822E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 931.408 | TFLOPs: 23.73 | +7: iteration 23020/ 37905 | consumed samples: 5893120 | consumed tokens: 12069109760 | elapsed time per iteration (s): 0.24 | learning rate: 8.129E-05 | global batch size: 256 | lm loss: 3.361754E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1080.489 | TFLOPs: 27.53 | +7: iteration 23030/ 37905 | consumed samples: 5895680 | consumed tokens: 12074352640 | elapsed time per iteration (s): 0.24 | learning rate: 8.122E-05 | global batch size: 256 | lm loss: 3.374548E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.194 | TFLOPs: 27.72 | +7: iteration 23040/ 37905 | consumed samples: 5898240 | consumed tokens: 12079595520 | elapsed time per iteration (s): 0.23 | learning rate: 8.115E-05 | global batch size: 256 | lm loss: 3.382066E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.526 | TFLOPs: 27.83 | +7: iteration 23050/ 37905 | consumed samples: 5900800 | consumed tokens: 12084838400 | elapsed time per iteration (s): 0.24 | learning rate: 8.108E-05 | global batch size: 256 | lm loss: 3.353967E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1055.389 | TFLOPs: 26.89 | +7: iteration 23060/ 37905 | consumed samples: 5903360 | consumed tokens: 12090081280 | elapsed time per iteration (s): 0.23 | learning rate: 8.101E-05 | global batch size: 256 | lm loss: 3.340888E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.335 | TFLOPs: 28.21 | +7: iteration 23070/ 37905 | consumed samples: 5905920 | consumed tokens: 12095324160 | elapsed time per iteration (s): 0.23 | learning rate: 8.094E-05 | global batch size: 256 | lm loss: 3.352065E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.968 | TFLOPs: 28.35 | +7: iteration 23080/ 37905 | consumed samples: 5908480 | consumed tokens: 12100567040 | elapsed time per iteration (s): 0.23 | learning rate: 8.086E-05 | global batch size: 256 | lm loss: 3.360669E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.443 | TFLOPs: 28.42 | +7: iteration 23090/ 37905 | consumed samples: 5911040 | consumed tokens: 12105809920 | elapsed time per iteration (s): 0.25 | learning rate: 8.079E-05 | global batch size: 256 | lm loss: 3.340455E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1041.853 | TFLOPs: 26.54 | +7: iteration 23100/ 37905 | consumed samples: 5913600 | consumed tokens: 12111052800 | elapsed time per iteration (s): 0.23 | learning rate: 8.072E-05 | global batch size: 256 | lm loss: 3.373222E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.888 | TFLOPs: 28.55 | +7: iteration 23110/ 37905 | consumed samples: 5916160 | consumed tokens: 12116295680 | elapsed time per iteration (s): 0.23 | learning rate: 8.065E-05 | global batch size: 256 | lm loss: 3.330125E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.414 | TFLOPs: 28.52 | +7: iteration 23120/ 37905 | consumed samples: 5918720 | consumed tokens: 12121538560 | elapsed time per iteration (s): 0.23 | learning rate: 8.058E-05 | global batch size: 256 | lm loss: 3.327347E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.450 | TFLOPs: 28.44 | +7: iteration 23130/ 37905 | consumed samples: 5921280 | consumed tokens: 12126781440 | elapsed time per iteration (s): 0.23 | learning rate: 8.051E-05 | global batch size: 256 | lm loss: 3.373166E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.369 | TFLOPs: 28.52 | +7: iteration 23140/ 37905 | consumed samples: 5923840 | consumed tokens: 12132024320 | elapsed time per iteration (s): 0.23 | learning rate: 8.044E-05 | global batch size: 256 | lm loss: 3.339753E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.452 | TFLOPs: 28.14 | +7: iteration 23150/ 37905 | consumed samples: 5926400 | consumed tokens: 12137267200 | elapsed time per iteration (s): 0.23 | learning rate: 8.037E-05 | global batch size: 256 | lm loss: 3.354679E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.316 | TFLOPs: 28.31 | +7: iteration 23160/ 37905 | consumed samples: 5928960 | consumed tokens: 12142510080 | elapsed time per iteration (s): 0.23 | learning rate: 8.029E-05 | global batch size: 256 | lm loss: 3.351252E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.214 | TFLOPs: 28.05 | +7: iteration 23170/ 37905 | consumed samples: 5931520 | consumed tokens: 12147752960 | elapsed time per iteration (s): 0.23 | learning rate: 8.022E-05 | global batch size: 256 | lm loss: 3.361376E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.658 | TFLOPs: 28.37 | +7: iteration 23180/ 37905 | consumed samples: 5934080 | consumed tokens: 12152995840 | elapsed time per iteration (s): 0.23 | learning rate: 8.015E-05 | global batch size: 256 | lm loss: 3.352680E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.990 | TFLOPs: 28.23 | +7: iteration 23190/ 37905 | consumed samples: 5936640 | consumed tokens: 12158238720 | elapsed time per iteration (s): 0.23 | learning rate: 8.008E-05 | global batch size: 256 | lm loss: 3.313071E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.164 | TFLOPs: 27.98 | +7: iteration 23200/ 37905 | consumed samples: 5939200 | consumed tokens: 12163481600 | elapsed time per iteration (s): 0.23 | learning rate: 8.001E-05 | global batch size: 256 | lm loss: 3.378942E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.282 | TFLOPs: 28.08 | +7: iteration 23210/ 37905 | consumed samples: 5941760 | consumed tokens: 12168724480 | elapsed time per iteration (s): 0.23 | learning rate: 7.994E-05 | global batch size: 256 | lm loss: 3.347697E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.428 | TFLOPs: 27.93 | +7: iteration 23220/ 37905 | consumed samples: 5944320 | consumed tokens: 12173967360 | elapsed time per iteration (s): 0.23 | learning rate: 7.987E-05 | global batch size: 256 | lm loss: 3.367614E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.019 | TFLOPs: 27.84 | +7: iteration 23230/ 37905 | consumed samples: 5946880 | consumed tokens: 12179210240 | elapsed time per iteration (s): 0.23 | learning rate: 7.980E-05 | global batch size: 256 | lm loss: 3.367213E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.381 | TFLOPs: 28.31 | +7: iteration 23240/ 37905 | consumed samples: 5949440 | consumed tokens: 12184453120 | elapsed time per iteration (s): 0.24 | learning rate: 7.973E-05 | global batch size: 256 | lm loss: 3.341632E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.204 | TFLOPs: 27.67 | +7: iteration 23250/ 37905 | consumed samples: 5952000 | consumed tokens: 12189696000 | elapsed time per iteration (s): 0.23 | learning rate: 7.965E-05 | global batch size: 256 | lm loss: 3.333809E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.372 | TFLOPs: 27.85 | +7: iteration 23260/ 37905 | consumed samples: 5954560 | consumed tokens: 12194938880 | elapsed time per iteration (s): 0.23 | learning rate: 7.958E-05 | global batch size: 256 | lm loss: 3.330973E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.925 | TFLOPs: 28.20 | +7: iteration 23270/ 37905 | consumed samples: 5957120 | consumed tokens: 12200181760 | elapsed time per iteration (s): 0.23 | learning rate: 7.951E-05 | global batch size: 256 | lm loss: 3.344856E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.768 | TFLOPs: 28.09 | +7: iteration 23280/ 37905 | consumed samples: 5959680 | consumed tokens: 12205424640 | elapsed time per iteration (s): 0.23 | learning rate: 7.944E-05 | global batch size: 256 | lm loss: 3.363636E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.295 | TFLOPs: 28.03 | +7: iteration 23290/ 37905 | consumed samples: 5962240 | consumed tokens: 12210667520 | elapsed time per iteration (s): 0.23 | learning rate: 7.937E-05 | global batch size: 256 | lm loss: 3.372316E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.992 | TFLOPs: 28.25 | +7: iteration 23300/ 37905 | consumed samples: 5964800 | consumed tokens: 12215910400 | elapsed time per iteration (s): 0.23 | learning rate: 7.930E-05 | global batch size: 256 | lm loss: 3.356089E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.977 | TFLOPs: 27.79 | +7: iteration 23310/ 37905 | consumed samples: 5967360 | consumed tokens: 12221153280 | elapsed time per iteration (s): 0.23 | learning rate: 7.923E-05 | global batch size: 256 | lm loss: 3.353410E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.228 | TFLOPs: 28.26 | +7: iteration 23320/ 37905 | consumed samples: 5969920 | consumed tokens: 12226396160 | elapsed time per iteration (s): 0.23 | learning rate: 7.916E-05 | global batch size: 256 | lm loss: 3.370066E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.965 | TFLOPs: 28.25 | +7: iteration 23330/ 37905 | consumed samples: 5972480 | consumed tokens: 12231639040 | elapsed time per iteration (s): 0.24 | learning rate: 7.909E-05 | global batch size: 256 | lm loss: 3.363881E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.187 | TFLOPs: 27.47 | +7: iteration 23340/ 37905 | consumed samples: 5975040 | consumed tokens: 12236881920 | elapsed time per iteration (s): 0.23 | learning rate: 7.902E-05 | global batch size: 256 | lm loss: 3.342028E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.624 | TFLOPs: 28.24 | +7: iteration 23350/ 37905 | consumed samples: 5977600 | consumed tokens: 12242124800 | elapsed time per iteration (s): 0.24 | learning rate: 7.895E-05 | global batch size: 256 | lm loss: 3.344032E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1079.324 | TFLOPs: 27.50 | +7: iteration 23360/ 37905 | consumed samples: 5980160 | consumed tokens: 12247367680 | elapsed time per iteration (s): 0.23 | learning rate: 7.888E-05 | global batch size: 256 | lm loss: 3.363315E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.735 | TFLOPs: 28.09 | +7: iteration 23370/ 37905 | consumed samples: 5982720 | consumed tokens: 12252610560 | elapsed time per iteration (s): 0.24 | learning rate: 7.881E-05 | global batch size: 256 | lm loss: 3.343890E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.415 | TFLOPs: 27.70 | +7: iteration 23380/ 37905 | consumed samples: 5985280 | consumed tokens: 12257853440 | elapsed time per iteration (s): 0.23 | learning rate: 7.873E-05 | global batch size: 256 | lm loss: 3.359217E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.517 | TFLOPs: 27.83 | +7: iteration 23390/ 37905 | consumed samples: 5987840 | consumed tokens: 12263096320 | elapsed time per iteration (s): 0.24 | learning rate: 7.866E-05 | global batch size: 256 | lm loss: 3.327407E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.520 | TFLOPs: 27.70 | +7: iteration 23400/ 37905 | consumed samples: 5990400 | consumed tokens: 12268339200 | elapsed time per iteration (s): 0.24 | learning rate: 7.859E-05 | global batch size: 256 | lm loss: 3.348899E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.072 | TFLOPs: 27.69 | +7: iteration 23410/ 37905 | consumed samples: 5992960 | consumed tokens: 12273582080 | elapsed time per iteration (s): 0.24 | learning rate: 7.852E-05 | global batch size: 256 | lm loss: 3.350114E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1072.542 | TFLOPs: 27.32 | +7: iteration 23420/ 37905 | consumed samples: 5995520 | consumed tokens: 12278824960 | elapsed time per iteration (s): 0.24 | learning rate: 7.845E-05 | global batch size: 256 | lm loss: 3.357437E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.790 | TFLOPs: 27.71 | +7: iteration 23430/ 37905 | consumed samples: 5998080 | consumed tokens: 12284067840 | elapsed time per iteration (s): 0.23 | learning rate: 7.838E-05 | global batch size: 256 | lm loss: 3.355391E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.012 | TFLOPs: 27.79 | +7: iteration 23440/ 37905 | consumed samples: 6000640 | consumed tokens: 12289310720 | elapsed time per iteration (s): 0.23 | learning rate: 7.831E-05 | global batch size: 256 | lm loss: 3.350736E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.516 | TFLOPs: 27.88 | +7: iteration 23450/ 37905 | consumed samples: 6003200 | consumed tokens: 12294553600 | elapsed time per iteration (s): 0.23 | learning rate: 7.824E-05 | global batch size: 256 | lm loss: 3.366104E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.983 | TFLOPs: 28.43 | +7: iteration 23460/ 37905 | consumed samples: 6005760 | consumed tokens: 12299796480 | elapsed time per iteration (s): 0.23 | learning rate: 7.817E-05 | global batch size: 256 | lm loss: 3.331575E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.708 | TFLOPs: 28.40 | +7: iteration 23470/ 37905 | consumed samples: 6008320 | consumed tokens: 12305039360 | elapsed time per iteration (s): 0.23 | learning rate: 7.810E-05 | global batch size: 256 | lm loss: 3.348038E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.149 | TFLOPs: 28.23 | +7: iteration 23480/ 37905 | consumed samples: 6010880 | consumed tokens: 12310282240 | elapsed time per iteration (s): 0.23 | learning rate: 7.803E-05 | global batch size: 256 | lm loss: 3.336391E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.646 | TFLOPs: 28.32 | +7: iteration 23490/ 37905 | consumed samples: 6013440 | consumed tokens: 12315525120 | elapsed time per iteration (s): 0.25 | learning rate: 7.796E-05 | global batch size: 256 | lm loss: 3.359483E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1044.872 | TFLOPs: 26.62 | +7: iteration 23500/ 37905 | consumed samples: 6016000 | consumed tokens: 12320768000 | elapsed time per iteration (s): 0.23 | learning rate: 7.789E-05 | global batch size: 256 | lm loss: 3.351482E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.741 | TFLOPs: 28.53 | +7: iteration 23510/ 37905 | consumed samples: 6018560 | consumed tokens: 12326010880 | elapsed time per iteration (s): 0.23 | learning rate: 7.782E-05 | global batch size: 256 | lm loss: 3.346140E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.725 | TFLOPs: 28.30 | +7: iteration 23520/ 37905 | consumed samples: 6021120 | consumed tokens: 12331253760 | elapsed time per iteration (s): 0.23 | learning rate: 7.775E-05 | global batch size: 256 | lm loss: 3.360664E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.431 | TFLOPs: 28.36 | +7: iteration 23530/ 37905 | consumed samples: 6023680 | consumed tokens: 12336496640 | elapsed time per iteration (s): 0.23 | learning rate: 7.768E-05 | global batch size: 256 | lm loss: 3.349324E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.777 | TFLOPs: 28.32 | +7: iteration 23540/ 37905 | consumed samples: 6026240 | consumed tokens: 12341739520 | elapsed time per iteration (s): 0.23 | learning rate: 7.761E-05 | global batch size: 256 | lm loss: 3.360173E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.173 | TFLOPs: 28.26 | +7: iteration 23550/ 37905 | consumed samples: 6028800 | consumed tokens: 12346982400 | elapsed time per iteration (s): 0.23 | learning rate: 7.754E-05 | global batch size: 256 | lm loss: 3.380095E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.063 | TFLOPs: 28.33 | +7: iteration 23560/ 37905 | consumed samples: 6031360 | consumed tokens: 12352225280 | elapsed time per iteration (s): 0.23 | learning rate: 7.747E-05 | global batch size: 256 | lm loss: 3.359658E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.498 | TFLOPs: 28.39 | +7: iteration 23570/ 37905 | consumed samples: 6033920 | consumed tokens: 12357468160 | elapsed time per iteration (s): 0.24 | learning rate: 7.740E-05 | global batch size: 256 | lm loss: 3.346424E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1073.783 | TFLOPs: 27.35 | +7: iteration 23580/ 37905 | consumed samples: 6036480 | consumed tokens: 12362711040 | elapsed time per iteration (s): 0.25 | learning rate: 7.733E-05 | global batch size: 256 | lm loss: 3.353214E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1025.806 | TFLOPs: 26.13 | +7: iteration 23590/ 37905 | consumed samples: 6039040 | consumed tokens: 12367953920 | elapsed time per iteration (s): 0.23 | learning rate: 7.726E-05 | global batch size: 256 | lm loss: 3.350151E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.815 | TFLOPs: 28.15 | +7: iteration 23600/ 37905 | consumed samples: 6041600 | consumed tokens: 12373196800 | elapsed time per iteration (s): 0.23 | learning rate: 7.719E-05 | global batch size: 256 | lm loss: 3.333480E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.763 | TFLOPs: 28.25 | +7: iteration 23610/ 37905 | consumed samples: 6044160 | consumed tokens: 12378439680 | elapsed time per iteration (s): 0.24 | learning rate: 7.712E-05 | global batch size: 256 | lm loss: 3.350541E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.781 | TFLOPs: 27.71 | +7: iteration 23620/ 37905 | consumed samples: 6046720 | consumed tokens: 12383682560 | elapsed time per iteration (s): 0.23 | learning rate: 7.705E-05 | global batch size: 256 | lm loss: 3.351564E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.797 | TFLOPs: 27.97 | +7: iteration 23630/ 37905 | consumed samples: 6049280 | consumed tokens: 12388925440 | elapsed time per iteration (s): 0.24 | learning rate: 7.698E-05 | global batch size: 256 | lm loss: 3.323395E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1077.995 | TFLOPs: 27.46 | +7: iteration 23640/ 37905 | consumed samples: 6051840 | consumed tokens: 12394168320 | elapsed time per iteration (s): 0.23 | learning rate: 7.691E-05 | global batch size: 256 | lm loss: 3.344622E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.249 | TFLOPs: 28.08 | +7: iteration 23650/ 37905 | consumed samples: 6054400 | consumed tokens: 12399411200 | elapsed time per iteration (s): 0.23 | learning rate: 7.684E-05 | global batch size: 256 | lm loss: 3.372759E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.314 | TFLOPs: 28.31 | +7: iteration 23660/ 37905 | consumed samples: 6056960 | consumed tokens: 12404654080 | elapsed time per iteration (s): 0.23 | learning rate: 7.677E-05 | global batch size: 256 | lm loss: 3.343549E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.041 | TFLOPs: 28.35 | +7: iteration 23670/ 37905 | consumed samples: 6059520 | consumed tokens: 12409896960 | elapsed time per iteration (s): 0.24 | learning rate: 7.670E-05 | global batch size: 256 | lm loss: 3.351459E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1062.812 | TFLOPs: 27.08 | +7: iteration 23680/ 37905 | consumed samples: 6062080 | consumed tokens: 12415139840 | elapsed time per iteration (s): 0.23 | learning rate: 7.663E-05 | global batch size: 256 | lm loss: 3.333770E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.630 | TFLOPs: 28.09 | +7: iteration 23690/ 37905 | consumed samples: 6064640 | consumed tokens: 12420382720 | elapsed time per iteration (s): 0.24 | learning rate: 7.656E-05 | global batch size: 256 | lm loss: 3.344989E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1082.134 | TFLOPs: 27.57 | +7: iteration 23700/ 37905 | consumed samples: 6067200 | consumed tokens: 12425625600 | elapsed time per iteration (s): 0.23 | learning rate: 7.649E-05 | global batch size: 256 | lm loss: 3.333735E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.127 | TFLOPs: 28.26 | +7: iteration 23710/ 37905 | consumed samples: 6069760 | consumed tokens: 12430868480 | elapsed time per iteration (s): 0.23 | learning rate: 7.642E-05 | global batch size: 256 | lm loss: 3.345737E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.538 | TFLOPs: 28.14 | +7: iteration 23720/ 37905 | consumed samples: 6072320 | consumed tokens: 12436111360 | elapsed time per iteration (s): 0.23 | learning rate: 7.635E-05 | global batch size: 256 | lm loss: 3.367915E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.186 | TFLOPs: 28.36 | +7: iteration 23730/ 37905 | consumed samples: 6074880 | consumed tokens: 12441354240 | elapsed time per iteration (s): 0.23 | learning rate: 7.628E-05 | global batch size: 256 | lm loss: 3.359571E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.403 | TFLOPs: 28.11 | +7: iteration 23740/ 37905 | consumed samples: 6077440 | consumed tokens: 12446597120 | elapsed time per iteration (s): 0.24 | learning rate: 7.621E-05 | global batch size: 256 | lm loss: 3.341003E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1067.406 | TFLOPs: 27.19 | +7: iteration 23750/ 37905 | consumed samples: 6080000 | consumed tokens: 12451840000 | elapsed time per iteration (s): 0.23 | learning rate: 7.614E-05 | global batch size: 256 | lm loss: 3.355557E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.899 | TFLOPs: 27.92 | +7: iteration 23760/ 37905 | consumed samples: 6082560 | consumed tokens: 12457082880 | elapsed time per iteration (s): 0.23 | learning rate: 7.607E-05 | global batch size: 256 | lm loss: 3.363641E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.681 | TFLOPs: 27.84 | +7: iteration 23770/ 37905 | consumed samples: 6085120 | consumed tokens: 12462325760 | elapsed time per iteration (s): 0.23 | learning rate: 7.600E-05 | global batch size: 256 | lm loss: 3.355288E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.328 | TFLOPs: 28.06 | +7: iteration 23780/ 37905 | consumed samples: 6087680 | consumed tokens: 12467568640 | elapsed time per iteration (s): 0.24 | learning rate: 7.593E-05 | global batch size: 256 | lm loss: 3.321299E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1082.428 | TFLOPs: 27.58 | +7: iteration 23790/ 37905 | consumed samples: 6090240 | consumed tokens: 12472811520 | elapsed time per iteration (s): 0.23 | learning rate: 7.586E-05 | global batch size: 256 | lm loss: 3.360303E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.373 | TFLOPs: 27.88 | +7: iteration 23800/ 37905 | consumed samples: 6092800 | consumed tokens: 12478054400 | elapsed time per iteration (s): 0.23 | learning rate: 7.579E-05 | global batch size: 256 | lm loss: 3.350712E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.375 | TFLOPs: 27.96 | +7: iteration 23810/ 37905 | consumed samples: 6095360 | consumed tokens: 12483297280 | elapsed time per iteration (s): 0.23 | learning rate: 7.572E-05 | global batch size: 256 | lm loss: 3.335511E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.603 | TFLOPs: 28.34 | +7: iteration 23820/ 37905 | consumed samples: 6097920 | consumed tokens: 12488540160 | elapsed time per iteration (s): 0.24 | learning rate: 7.565E-05 | global batch size: 256 | lm loss: 3.336315E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1077.569 | TFLOPs: 27.45 | +7: iteration 23830/ 37905 | consumed samples: 6100480 | consumed tokens: 12493783040 | elapsed time per iteration (s): 0.25 | learning rate: 7.558E-05 | global batch size: 256 | lm loss: 3.342881E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1022.735 | TFLOPs: 26.05 | +7: iteration 23840/ 37905 | consumed samples: 6103040 | consumed tokens: 12499025920 | elapsed time per iteration (s): 0.23 | learning rate: 7.551E-05 | global batch size: 256 | lm loss: 3.344526E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.071 | TFLOPs: 28.25 | +7: iteration 23850/ 37905 | consumed samples: 6105600 | consumed tokens: 12504268800 | elapsed time per iteration (s): 0.23 | learning rate: 7.544E-05 | global batch size: 256 | lm loss: 3.334648E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.627 | TFLOPs: 28.29 | +7: iteration 23860/ 37905 | consumed samples: 6108160 | consumed tokens: 12509511680 | elapsed time per iteration (s): 0.23 | learning rate: 7.537E-05 | global batch size: 256 | lm loss: 3.334214E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.722 | TFLOPs: 28.35 | +7: iteration 23870/ 37905 | consumed samples: 6110720 | consumed tokens: 12514754560 | elapsed time per iteration (s): 0.23 | learning rate: 7.530E-05 | global batch size: 256 | lm loss: 3.394082E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.735 | TFLOPs: 28.14 | +7: iteration 23880/ 37905 | consumed samples: 6113280 | consumed tokens: 12519997440 | elapsed time per iteration (s): 0.23 | learning rate: 7.523E-05 | global batch size: 256 | lm loss: 3.345071E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.797 | TFLOPs: 28.35 | +7: iteration 23890/ 37905 | consumed samples: 6115840 | consumed tokens: 12525240320 | elapsed time per iteration (s): 0.23 | learning rate: 7.516E-05 | global batch size: 256 | lm loss: 3.336433E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.420 | TFLOPs: 28.39 | +7: iteration 23900/ 37905 | consumed samples: 6118400 | consumed tokens: 12530483200 | elapsed time per iteration (s): 0.23 | learning rate: 7.509E-05 | global batch size: 256 | lm loss: 3.347924E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.737 | TFLOPs: 28.40 | +7: iteration 23910/ 37905 | consumed samples: 6120960 | consumed tokens: 12535726080 | elapsed time per iteration (s): 0.23 | learning rate: 7.502E-05 | global batch size: 256 | lm loss: 3.364173E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.664 | TFLOPs: 28.24 | +7: iteration 23920/ 37905 | consumed samples: 6123520 | consumed tokens: 12540968960 | elapsed time per iteration (s): 0.23 | learning rate: 7.495E-05 | global batch size: 256 | lm loss: 3.357859E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.831 | TFLOPs: 28.15 | +7: iteration 23930/ 37905 | consumed samples: 6126080 | consumed tokens: 12546211840 | elapsed time per iteration (s): 0.25 | learning rate: 7.488E-05 | global batch size: 256 | lm loss: 3.365015E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1028.981 | TFLOPs: 26.21 | +7: iteration 23940/ 37905 | consumed samples: 6128640 | consumed tokens: 12551454720 | elapsed time per iteration (s): 0.23 | learning rate: 7.481E-05 | global batch size: 256 | lm loss: 3.345584E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.846 | TFLOPs: 28.22 | +7: iteration 23950/ 37905 | consumed samples: 6131200 | consumed tokens: 12556697600 | elapsed time per iteration (s): 0.23 | learning rate: 7.474E-05 | global batch size: 256 | lm loss: 3.340880E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.973 | TFLOPs: 27.82 | +7: iteration 23960/ 37905 | consumed samples: 6133760 | consumed tokens: 12561940480 | elapsed time per iteration (s): 0.23 | learning rate: 7.468E-05 | global batch size: 256 | lm loss: 3.366565E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.059 | TFLOPs: 28.28 | +7: iteration 23970/ 37905 | consumed samples: 6136320 | consumed tokens: 12567183360 | elapsed time per iteration (s): 0.23 | learning rate: 7.461E-05 | global batch size: 256 | lm loss: 3.353337E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.492 | TFLOPs: 27.93 | +7: iteration 23980/ 37905 | consumed samples: 6138880 | consumed tokens: 12572426240 | elapsed time per iteration (s): 0.23 | learning rate: 7.454E-05 | global batch size: 256 | lm loss: 3.324840E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.966 | TFLOPs: 28.20 | +7: iteration 23990/ 37905 | consumed samples: 6141440 | consumed tokens: 12577669120 | elapsed time per iteration (s): 0.24 | learning rate: 7.447E-05 | global batch size: 256 | lm loss: 3.364098E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1067.930 | TFLOPs: 27.21 | +0: [2022-11-29 18:31:20,047] [INFO] [logging.py:68:log_dist] [Rank 0] step=24000, skipped=0, lr=[7.439815524319269e-05, 7.439815524319269e-05, 7.439815524319269e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +0: steps: 24000 loss: 3.4312 iter time (s): 0.237 samples/sec: 1079.590 +7: iteration 24000/ 37905 | consumed samples: 6144000 | consumed tokens: 12582912000 | elapsed time per iteration (s): 0.23 | learning rate: 7.440E-05 | global batch size: 256 | lm loss: 3.374314E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.391 | TFLOPs: 28.03 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 24000 | lm loss value: 3.203718E+00 | lm loss PPL: 2.462392E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 24000 to checkpoints_83moscar +0: [2022-11-29 18:31:20,154] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step24000 is begin to save! +0: [2022-11-29 18:31:20,158] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:31:20,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:31:20,238] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:31:20,250] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:31:20,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:31:20,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:31:20,263] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:31:20,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:31:20,275] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:31:20,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:31:20,287] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:31:20,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:31:20,299] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:31:20,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:31:20,311] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:31:20,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:31:20,322] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:31:20,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:31:20,334] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:31:20,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:31:20,346] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:31:20,358] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:31:20,358] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:31:20,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:31:20,360] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step24000/mp_rank_00_model_states.pt +0: [2022-11-29 18:31:20,360] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:31:20,363] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:31:20,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:31:20,401] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:31:20,401] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:31:20,401] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +7: [2022-11-29 18:31:20,401] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:31:20,401] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +1: [2022-11-29 18:31:20,401] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:31:20,401] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +1: [2022-11-29 18:31:20,401] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:31:20,401] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +5: [2022-11-29 18:31:20,402] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:31:20,402] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:31:20,403] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +6: [2022-11-29 18:31:20,402] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:31:20,403] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:31:20,403] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +3: [2022-11-29 18:31:20,403] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:31:20,403] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:31:20,403] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +0: [2022-11-29 18:31:20,403] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:31:20,404] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:31:20,404] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:31:20,404] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +1: [2022-11-29 18:31:20,404] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:31:20,404] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:31:20,404] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +0: [2022-11-29 18:31:20,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:31:20,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +7: [2022-11-29 18:31:20,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:31:20,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:31:20,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +6: [2022-11-29 18:31:20,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:31:20,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:31:20,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +6: [2022-11-29 18:31:20,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:31:20,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +5: [2022-11-29 18:31:20,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:31:20,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +5: [2022-11-29 18:31:20,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:31:20,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +1: [2022-11-29 18:31:20,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:31:20,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:31:20,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +0: [2022-11-29 18:31:20,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:31:20,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:31:20,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +2: [2022-11-29 18:31:20,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:31:20,406] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:31:20,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +3: [2022-11-29 18:31:20,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:31:20,406] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:31:20,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +4: [2022-11-29 18:31:20,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:31:20,406] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:31:20,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +0: [2022-11-29 18:31:20,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:31:20,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:31:20,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +7: [2022-11-29 18:31:20,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:31:20,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:31:20,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +3: [2022-11-29 18:31:20,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:31:20,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:31:20,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +1: [2022-11-29 18:31:20,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:31:20,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:31:20,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +7: [2022-11-29 18:31:20,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:31:20,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:31:20,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +5: [2022-11-29 18:31:20,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:31:20,408] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +4: [2022-11-29 18:31:20,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:31:20,408] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:31:20,408] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +5: [2022-11-29 18:31:20,408] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +3: [2022-11-29 18:31:20,408] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +4: [2022-11-29 18:31:20,408] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +3: [2022-11-29 18:31:20,408] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +6: [2022-11-29 18:31:20,408] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:31:20,408] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:31:20,408] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +2: [2022-11-29 18:31:20,408] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:31:20,408] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:31:20,408] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +2: [2022-11-29 18:31:20,408] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:31:20,408] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:31:20,408] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +0: [2022-11-29 18:31:20,408] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:31:20,408] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:31:20,408] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +6: [2022-11-29 18:31:20,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:31:20,409] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:31:20,409] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +4: [2022-11-29 18:31:20,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:31:20,409] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:31:20,409] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +7: [2022-11-29 18:31:20,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:31:20,409] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:31:20,409] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +1: [2022-11-29 18:31:20,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:31:20,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:31:20,410] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +2: [2022-11-29 18:31:20,410] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +1: [2022-11-29 18:31:20,410] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +2: [2022-11-29 18:31:20,410] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +5: [2022-11-29 18:31:20,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:31:20,410] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:31:20,410] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +4: [2022-11-29 18:31:20,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:31:20,411] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +5: [2022-11-29 18:31:20,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:31:20,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:31:20,411] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +5: [2022-11-29 18:31:20,411] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +7: [2022-11-29 18:31:20,411] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +5: [2022-11-29 18:31:20,411] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +7: [2022-11-29 18:31:20,411] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +3: [2022-11-29 18:31:20,411] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:31:20,411] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:31:20,411] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +5: [2022-11-29 18:31:20,411] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:31:20,411] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:31:20,412] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +0: [2022-11-29 18:31:20,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:31:20,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:31:20,412] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +0: [2022-11-29 18:31:20,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:31:20,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:31:20,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +7: [2022-11-29 18:31:20,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +0: [2022-11-29 18:31:20,412] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +7: [2022-11-29 18:31:20,412] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +1: [2022-11-29 18:31:20,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:31:20,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:31:20,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +6: [2022-11-29 18:31:20,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:31:20,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:31:20,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +4: [2022-11-29 18:31:20,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:31:20,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +4: [2022-11-29 18:31:20,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +6: [2022-11-29 18:31:20,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +6: [2022-11-29 18:31:20,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +4: [2022-11-29 18:31:20,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +1: [2022-11-29 18:31:20,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:31:20,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +3: [2022-11-29 18:31:20,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:31:20,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +3: [2022-11-29 18:31:20,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:31:20,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +1: [2022-11-29 18:31:20,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:31:20,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:31:20,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +0: [2022-11-29 18:31:20,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:31:20,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:31:20,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +3: [2022-11-29 18:31:20,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:31:20,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +2: [2022-11-29 18:31:20,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:31:20,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:31:20,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:31:20,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:31:20,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +7: [2022-11-29 18:31:20,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +2: [2022-11-29 18:31:20,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +0: [2022-11-29 18:31:20,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +2: [2022-11-29 18:31:20,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:31:20,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +7: [2022-11-29 18:31:20,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +0: [2022-11-29 18:31:20,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +2: [2022-11-29 18:31:20,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +5: [2022-11-29 18:31:20,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:31:20,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:31:20,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:31:20,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +3: [2022-11-29 18:31:20,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +6: [2022-11-29 18:31:20,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:31:20,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +6: [2022-11-29 18:31:20,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:31:20,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +4: [2022-11-29 18:31:20,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:31:20,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:31:20,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +2: [2022-11-29 18:31:20,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:31:20,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +5: [2022-11-29 18:31:20,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:31:20,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +5: [2022-11-29 18:31:20,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:31:20,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +4: [2022-11-29 18:31:20,416] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:31:20,416] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step24000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:31:20,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +0: successfully saved checkpoint at iteration 24000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 264.77 +7: iteration 24010/ 37905 | consumed samples: 6146560 | consumed tokens: 12588154880 | elapsed time per iteration (s): 0.27 | learning rate: 7.433E-05 | global batch size: 256 | lm loss: 3.338830E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 960.421 | TFLOPs: 24.47 | +7: iteration 24020/ 37905 | consumed samples: 6149120 | consumed tokens: 12593397760 | elapsed time per iteration (s): 0.23 | learning rate: 7.426E-05 | global batch size: 256 | lm loss: 3.351563E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.278 | TFLOPs: 28.06 | +7: iteration 24030/ 37905 | consumed samples: 6151680 | consumed tokens: 12598640640 | elapsed time per iteration (s): 0.23 | learning rate: 7.419E-05 | global batch size: 256 | lm loss: 3.335365E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.411 | TFLOPs: 28.03 | +7: iteration 24040/ 37905 | consumed samples: 6154240 | consumed tokens: 12603883520 | elapsed time per iteration (s): 0.23 | learning rate: 7.412E-05 | global batch size: 256 | lm loss: 3.350500E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.877 | TFLOPs: 27.76 | +7: iteration 24050/ 37905 | consumed samples: 6156800 | consumed tokens: 12609126400 | elapsed time per iteration (s): 0.23 | learning rate: 7.405E-05 | global batch size: 256 | lm loss: 3.358732E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.335 | TFLOPs: 28.01 | +7: iteration 24060/ 37905 | consumed samples: 6159360 | consumed tokens: 12614369280 | elapsed time per iteration (s): 0.23 | learning rate: 7.398E-05 | global batch size: 256 | lm loss: 3.372538E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.463 | TFLOPs: 27.81 | +7: iteration 24070/ 37905 | consumed samples: 6161920 | consumed tokens: 12619612160 | elapsed time per iteration (s): 0.23 | learning rate: 7.391E-05 | global batch size: 256 | lm loss: 3.341471E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.467 | TFLOPs: 27.96 | +7: iteration 24080/ 37905 | consumed samples: 6164480 | consumed tokens: 12624855040 | elapsed time per iteration (s): 0.24 | learning rate: 7.385E-05 | global batch size: 256 | lm loss: 3.346010E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1075.535 | TFLOPs: 27.40 | +7: iteration 24090/ 37905 | consumed samples: 6167040 | consumed tokens: 12630097920 | elapsed time per iteration (s): 0.23 | learning rate: 7.378E-05 | global batch size: 256 | lm loss: 3.357978E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.599 | TFLOPs: 28.32 | +7: iteration 24100/ 37905 | consumed samples: 6169600 | consumed tokens: 12635340800 | elapsed time per iteration (s): 0.23 | learning rate: 7.371E-05 | global batch size: 256 | lm loss: 3.349238E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.012 | TFLOPs: 27.77 | +7: iteration 24110/ 37905 | consumed samples: 6172160 | consumed tokens: 12640583680 | elapsed time per iteration (s): 0.23 | learning rate: 7.364E-05 | global batch size: 256 | lm loss: 3.334907E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.539 | TFLOPs: 28.32 | +7: iteration 24120/ 37905 | consumed samples: 6174720 | consumed tokens: 12645826560 | elapsed time per iteration (s): 0.24 | learning rate: 7.357E-05 | global batch size: 256 | lm loss: 3.349142E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.662 | TFLOPs: 27.68 | +7: iteration 24130/ 37905 | consumed samples: 6177280 | consumed tokens: 12651069440 | elapsed time per iteration (s): 0.24 | learning rate: 7.350E-05 | global batch size: 256 | lm loss: 3.332383E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1058.104 | TFLOPs: 26.96 | +7: iteration 24140/ 37905 | consumed samples: 6179840 | consumed tokens: 12656312320 | elapsed time per iteration (s): 0.24 | learning rate: 7.343E-05 | global batch size: 256 | lm loss: 3.342381E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.224 | TFLOPs: 27.65 | +7: iteration 24150/ 37905 | consumed samples: 6182400 | consumed tokens: 12661555200 | elapsed time per iteration (s): 0.23 | learning rate: 7.336E-05 | global batch size: 256 | lm loss: 3.314149E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.605 | TFLOPs: 27.78 | +7: iteration 24160/ 37905 | consumed samples: 6184960 | consumed tokens: 12666798080 | elapsed time per iteration (s): 0.23 | learning rate: 7.329E-05 | global batch size: 256 | lm loss: 3.368469E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.261 | TFLOPs: 28.03 | +7: iteration 24170/ 37905 | consumed samples: 6187520 | consumed tokens: 12672040960 | elapsed time per iteration (s): 0.23 | learning rate: 7.323E-05 | global batch size: 256 | lm loss: 3.382230E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.857 | TFLOPs: 28.12 | +7: iteration 24180/ 37905 | consumed samples: 6190080 | consumed tokens: 12677283840 | elapsed time per iteration (s): 0.23 | learning rate: 7.316E-05 | global batch size: 256 | lm loss: 3.338599E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.919 | TFLOPs: 28.02 | +7: iteration 24190/ 37905 | consumed samples: 6192640 | consumed tokens: 12682526720 | elapsed time per iteration (s): 0.23 | learning rate: 7.309E-05 | global batch size: 256 | lm loss: 3.345940E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.693 | TFLOPs: 28.17 | +7: iteration 24200/ 37905 | consumed samples: 6195200 | consumed tokens: 12687769600 | elapsed time per iteration (s): 0.23 | learning rate: 7.302E-05 | global batch size: 256 | lm loss: 3.363781E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.749 | TFLOPs: 27.84 | +7: iteration 24210/ 37905 | consumed samples: 6197760 | consumed tokens: 12693012480 | elapsed time per iteration (s): 0.25 | learning rate: 7.295E-05 | global batch size: 256 | lm loss: 3.328552E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1003.933 | TFLOPs: 25.58 | +7: iteration 24220/ 37905 | consumed samples: 6200320 | consumed tokens: 12698255360 | elapsed time per iteration (s): 0.25 | learning rate: 7.288E-05 | global batch size: 256 | lm loss: 3.350736E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1011.907 | TFLOPs: 25.78 | +7: iteration 24230/ 37905 | consumed samples: 6202880 | consumed tokens: 12703498240 | elapsed time per iteration (s): 0.23 | learning rate: 7.281E-05 | global batch size: 256 | lm loss: 3.355110E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.681 | TFLOPs: 28.29 | +7: iteration 24240/ 37905 | consumed samples: 6205440 | consumed tokens: 12708741120 | elapsed time per iteration (s): 0.23 | learning rate: 7.274E-05 | global batch size: 256 | lm loss: 3.332453E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.918 | TFLOPs: 28.33 | +7: iteration 24250/ 37905 | consumed samples: 6208000 | consumed tokens: 12713984000 | elapsed time per iteration (s): 0.23 | learning rate: 7.268E-05 | global batch size: 256 | lm loss: 3.346121E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.595 | TFLOPs: 28.42 | +7: iteration 24260/ 37905 | consumed samples: 6210560 | consumed tokens: 12719226880 | elapsed time per iteration (s): 0.23 | learning rate: 7.261E-05 | global batch size: 256 | lm loss: 3.337905E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.731 | TFLOPs: 28.40 | +7: iteration 24270/ 37905 | consumed samples: 6213120 | consumed tokens: 12724469760 | elapsed time per iteration (s): 0.23 | learning rate: 7.254E-05 | global batch size: 256 | lm loss: 3.377580E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.356 | TFLOPs: 28.36 | +7: iteration 24280/ 37905 | consumed samples: 6215680 | consumed tokens: 12729712640 | elapsed time per iteration (s): 0.23 | learning rate: 7.247E-05 | global batch size: 256 | lm loss: 3.337975E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.845 | TFLOPs: 28.30 | +7: iteration 24290/ 37905 | consumed samples: 6218240 | consumed tokens: 12734955520 | elapsed time per iteration (s): 0.24 | learning rate: 7.240E-05 | global batch size: 256 | lm loss: 3.351032E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.630 | TFLOPs: 27.73 | +7: iteration 24300/ 37905 | consumed samples: 6220800 | consumed tokens: 12740198400 | elapsed time per iteration (s): 0.23 | learning rate: 7.233E-05 | global batch size: 256 | lm loss: 3.375681E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.116 | TFLOPs: 28.15 | +7: iteration 24310/ 37905 | consumed samples: 6223360 | consumed tokens: 12745441280 | elapsed time per iteration (s): 0.23 | learning rate: 7.227E-05 | global batch size: 256 | lm loss: 3.342968E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.233 | TFLOPs: 28.18 | +7: iteration 24320/ 37905 | consumed samples: 6225920 | consumed tokens: 12750684160 | elapsed time per iteration (s): 0.23 | learning rate: 7.220E-05 | global batch size: 256 | lm loss: 3.364003E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.661 | TFLOPs: 28.47 | +7: iteration 24330/ 37905 | consumed samples: 6228480 | consumed tokens: 12755927040 | elapsed time per iteration (s): 0.23 | learning rate: 7.213E-05 | global batch size: 256 | lm loss: 3.364182E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.623 | TFLOPs: 28.14 | +7: iteration 24340/ 37905 | consumed samples: 6231040 | consumed tokens: 12761169920 | elapsed time per iteration (s): 0.23 | learning rate: 7.206E-05 | global batch size: 256 | lm loss: 3.343747E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.220 | TFLOPs: 28.23 | +7: iteration 24350/ 37905 | consumed samples: 6233600 | consumed tokens: 12766412800 | elapsed time per iteration (s): 0.24 | learning rate: 7.199E-05 | global batch size: 256 | lm loss: 3.347168E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1082.049 | TFLOPs: 27.57 | +7: iteration 24360/ 37905 | consumed samples: 6236160 | consumed tokens: 12771655680 | elapsed time per iteration (s): 0.23 | learning rate: 7.192E-05 | global batch size: 256 | lm loss: 3.333981E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.646 | TFLOPs: 27.94 | +7: iteration 24370/ 37905 | consumed samples: 6238720 | consumed tokens: 12776898560 | elapsed time per iteration (s): 0.23 | learning rate: 7.186E-05 | global batch size: 256 | lm loss: 3.353254E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.140 | TFLOPs: 28.05 | +7: iteration 24380/ 37905 | consumed samples: 6241280 | consumed tokens: 12782141440 | elapsed time per iteration (s): 0.24 | learning rate: 7.179E-05 | global batch size: 256 | lm loss: 3.318489E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1075.675 | TFLOPs: 27.40 | +7: iteration 24390/ 37905 | consumed samples: 6243840 | consumed tokens: 12787384320 | elapsed time per iteration (s): 0.23 | learning rate: 7.172E-05 | global batch size: 256 | lm loss: 3.375742E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.341 | TFLOPs: 28.21 | +7: iteration 24400/ 37905 | consumed samples: 6246400 | consumed tokens: 12792627200 | elapsed time per iteration (s): 0.23 | learning rate: 7.165E-05 | global batch size: 256 | lm loss: 3.348079E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.586 | TFLOPs: 28.32 | +7: iteration 24410/ 37905 | consumed samples: 6248960 | consumed tokens: 12797870080 | elapsed time per iteration (s): 0.23 | learning rate: 7.158E-05 | global batch size: 256 | lm loss: 3.359776E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.096 | TFLOPs: 28.20 | +7: iteration 24420/ 37905 | consumed samples: 6251520 | consumed tokens: 12803112960 | elapsed time per iteration (s): 0.23 | learning rate: 7.151E-05 | global batch size: 256 | lm loss: 3.358039E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.953 | TFLOPs: 28.20 | +7: iteration 24430/ 37905 | consumed samples: 6254080 | consumed tokens: 12808355840 | elapsed time per iteration (s): 0.23 | learning rate: 7.145E-05 | global batch size: 256 | lm loss: 3.350174E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.069 | TFLOPs: 27.77 | +7: iteration 24440/ 37905 | consumed samples: 6256640 | consumed tokens: 12813598720 | elapsed time per iteration (s): 0.23 | learning rate: 7.138E-05 | global batch size: 256 | lm loss: 3.356853E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.462 | TFLOPs: 28.19 | +7: iteration 24450/ 37905 | consumed samples: 6259200 | consumed tokens: 12818841600 | elapsed time per iteration (s): 0.23 | learning rate: 7.131E-05 | global batch size: 256 | lm loss: 3.375420E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.440 | TFLOPs: 28.19 | +7: iteration 24460/ 37905 | consumed samples: 6261760 | consumed tokens: 12824084480 | elapsed time per iteration (s): 0.23 | learning rate: 7.124E-05 | global batch size: 256 | lm loss: 3.366962E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.825 | TFLOPs: 28.09 | +7: iteration 24470/ 37905 | consumed samples: 6264320 | consumed tokens: 12829327360 | elapsed time per iteration (s): 0.24 | learning rate: 7.117E-05 | global batch size: 256 | lm loss: 3.383902E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1055.872 | TFLOPs: 26.90 | +7: iteration 24480/ 37905 | consumed samples: 6266880 | consumed tokens: 12834570240 | elapsed time per iteration (s): 0.23 | learning rate: 7.111E-05 | global batch size: 256 | lm loss: 3.357370E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.243 | TFLOPs: 27.88 | +7: iteration 24490/ 37905 | consumed samples: 6269440 | consumed tokens: 12839813120 | elapsed time per iteration (s): 0.23 | learning rate: 7.104E-05 | global batch size: 256 | lm loss: 3.363885E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.746 | TFLOPs: 28.04 | +7: iteration 24500/ 37905 | consumed samples: 6272000 | consumed tokens: 12845056000 | elapsed time per iteration (s): 0.24 | learning rate: 7.097E-05 | global batch size: 256 | lm loss: 3.369354E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1084.974 | TFLOPs: 27.64 | +7: iteration 24510/ 37905 | consumed samples: 6274560 | consumed tokens: 12850298880 | elapsed time per iteration (s): 0.24 | learning rate: 7.090E-05 | global batch size: 256 | lm loss: 3.331626E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.548 | TFLOPs: 27.71 | +7: iteration 24520/ 37905 | consumed samples: 6277120 | consumed tokens: 12855541760 | elapsed time per iteration (s): 0.23 | learning rate: 7.083E-05 | global batch size: 256 | lm loss: 3.372615E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.782 | TFLOPs: 28.07 | +7: iteration 24530/ 37905 | consumed samples: 6279680 | consumed tokens: 12860784640 | elapsed time per iteration (s): 0.23 | learning rate: 7.077E-05 | global batch size: 256 | lm loss: 3.368202E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.697 | TFLOPs: 27.99 | +7: iteration 24540/ 37905 | consumed samples: 6282240 | consumed tokens: 12866027520 | elapsed time per iteration (s): 0.23 | learning rate: 7.070E-05 | global batch size: 256 | lm loss: 3.338534E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.547 | TFLOPs: 28.04 | +7: iteration 24550/ 37905 | consumed samples: 6284800 | consumed tokens: 12871270400 | elapsed time per iteration (s): 0.23 | learning rate: 7.063E-05 | global batch size: 256 | lm loss: 3.337326E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.465 | TFLOPs: 28.09 | +7: iteration 24560/ 37905 | consumed samples: 6287360 | consumed tokens: 12876513280 | elapsed time per iteration (s): 0.23 | learning rate: 7.056E-05 | global batch size: 256 | lm loss: 3.349286E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.088 | TFLOPs: 28.18 | +7: iteration 24570/ 37905 | consumed samples: 6289920 | consumed tokens: 12881756160 | elapsed time per iteration (s): 0.25 | learning rate: 7.050E-05 | global batch size: 256 | lm loss: 3.342390E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1022.619 | TFLOPs: 26.05 | +7: iteration 24580/ 37905 | consumed samples: 6292480 | consumed tokens: 12886999040 | elapsed time per iteration (s): 0.23 | learning rate: 7.043E-05 | global batch size: 256 | lm loss: 3.317482E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.240 | TFLOPs: 28.16 | +7: iteration 24590/ 37905 | consumed samples: 6295040 | consumed tokens: 12892241920 | elapsed time per iteration (s): 0.23 | learning rate: 7.036E-05 | global batch size: 256 | lm loss: 3.362712E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.238 | TFLOPs: 27.80 | +7: iteration 24600/ 37905 | consumed samples: 6297600 | consumed tokens: 12897484800 | elapsed time per iteration (s): 0.23 | learning rate: 7.029E-05 | global batch size: 256 | lm loss: 3.338647E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.695 | TFLOPs: 28.30 | +7: iteration 24610/ 37905 | consumed samples: 6300160 | consumed tokens: 12902727680 | elapsed time per iteration (s): 0.23 | learning rate: 7.023E-05 | global batch size: 256 | lm loss: 3.358383E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.241 | TFLOPs: 28.33 | +7: iteration 24620/ 37905 | consumed samples: 6302720 | consumed tokens: 12907970560 | elapsed time per iteration (s): 0.23 | learning rate: 7.016E-05 | global batch size: 256 | lm loss: 3.357583E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.345 | TFLOPs: 28.44 | +7: iteration 24630/ 37905 | consumed samples: 6305280 | consumed tokens: 12913213440 | elapsed time per iteration (s): 0.23 | learning rate: 7.009E-05 | global batch size: 256 | lm loss: 3.348402E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.628 | TFLOPs: 28.27 | +7: iteration 24640/ 37905 | consumed samples: 6307840 | consumed tokens: 12918456320 | elapsed time per iteration (s): 0.23 | learning rate: 7.002E-05 | global batch size: 256 | lm loss: 3.356052E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.448 | TFLOPs: 28.37 | +7: iteration 24650/ 37905 | consumed samples: 6310400 | consumed tokens: 12923699200 | elapsed time per iteration (s): 0.23 | learning rate: 6.996E-05 | global batch size: 256 | lm loss: 3.350899E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.244 | TFLOPs: 28.18 | +7: iteration 24660/ 37905 | consumed samples: 6312960 | consumed tokens: 12928942080 | elapsed time per iteration (s): 0.23 | learning rate: 6.989E-05 | global batch size: 256 | lm loss: 3.356813E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.366 | TFLOPs: 28.41 | +7: iteration 24670/ 37905 | consumed samples: 6315520 | consumed tokens: 12934184960 | elapsed time per iteration (s): 0.23 | learning rate: 6.982E-05 | global batch size: 256 | lm loss: 3.362310E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.843 | TFLOPs: 28.10 | +7: iteration 24680/ 37905 | consumed samples: 6318080 | consumed tokens: 12939427840 | elapsed time per iteration (s): 0.23 | learning rate: 6.975E-05 | global batch size: 256 | lm loss: 3.364015E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.839 | TFLOPs: 28.20 | +7: iteration 24690/ 37905 | consumed samples: 6320640 | consumed tokens: 12944670720 | elapsed time per iteration (s): 0.23 | learning rate: 6.969E-05 | global batch size: 256 | lm loss: 3.324761E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.145 | TFLOPs: 28.23 | +7: iteration 24700/ 37905 | consumed samples: 6323200 | consumed tokens: 12949913600 | elapsed time per iteration (s): 0.23 | learning rate: 6.962E-05 | global batch size: 256 | lm loss: 3.361641E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.013 | TFLOPs: 28.20 | +7: iteration 24710/ 37905 | consumed samples: 6325760 | consumed tokens: 12955156480 | elapsed time per iteration (s): 0.23 | learning rate: 6.955E-05 | global batch size: 256 | lm loss: 3.354747E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.313 | TFLOPs: 28.18 | +7: iteration 24720/ 37905 | consumed samples: 6328320 | consumed tokens: 12960399360 | elapsed time per iteration (s): 0.23 | learning rate: 6.948E-05 | global batch size: 256 | lm loss: 3.352001E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.141 | TFLOPs: 28.26 | +7: iteration 24730/ 37905 | consumed samples: 6330880 | consumed tokens: 12965642240 | elapsed time per iteration (s): 0.23 | learning rate: 6.942E-05 | global batch size: 256 | lm loss: 3.329694E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.959 | TFLOPs: 28.25 | +7: iteration 24740/ 37905 | consumed samples: 6333440 | consumed tokens: 12970885120 | elapsed time per iteration (s): 0.23 | learning rate: 6.935E-05 | global batch size: 256 | lm loss: 3.324559E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.033 | TFLOPs: 28.25 | +7: iteration 24750/ 37905 | consumed samples: 6336000 | consumed tokens: 12976128000 | elapsed time per iteration (s): 0.23 | learning rate: 6.928E-05 | global batch size: 256 | lm loss: 3.340078E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.206 | TFLOPs: 28.23 | +7: iteration 24760/ 37905 | consumed samples: 6338560 | consumed tokens: 12981370880 | elapsed time per iteration (s): 0.23 | learning rate: 6.921E-05 | global batch size: 256 | lm loss: 3.356615E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.670 | TFLOPs: 27.94 | +7: iteration 24770/ 37905 | consumed samples: 6341120 | consumed tokens: 12986613760 | elapsed time per iteration (s): 0.23 | learning rate: 6.915E-05 | global batch size: 256 | lm loss: 3.368491E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.137 | TFLOPs: 28.10 | +7: iteration 24780/ 37905 | consumed samples: 6343680 | consumed tokens: 12991856640 | elapsed time per iteration (s): 0.25 | learning rate: 6.908E-05 | global batch size: 256 | lm loss: 3.357373E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1025.803 | TFLOPs: 26.13 | +7: iteration 24790/ 37905 | consumed samples: 6346240 | consumed tokens: 12997099520 | elapsed time per iteration (s): 0.23 | learning rate: 6.901E-05 | global batch size: 256 | lm loss: 3.351677E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.877 | TFLOPs: 28.25 | +7: iteration 24800/ 37905 | consumed samples: 6348800 | consumed tokens: 13002342400 | elapsed time per iteration (s): 0.24 | learning rate: 6.895E-05 | global batch size: 256 | lm loss: 3.334933E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.193 | TFLOPs: 27.65 | +7: iteration 24810/ 37905 | consumed samples: 6351360 | consumed tokens: 13007585280 | elapsed time per iteration (s): 0.23 | learning rate: 6.888E-05 | global batch size: 256 | lm loss: 3.364849E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.491 | TFLOPs: 28.19 | +7: iteration 24820/ 37905 | consumed samples: 6353920 | consumed tokens: 13012828160 | elapsed time per iteration (s): 0.23 | learning rate: 6.881E-05 | global batch size: 256 | lm loss: 3.356194E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.649 | TFLOPs: 28.14 | +7: iteration 24830/ 37905 | consumed samples: 6356480 | consumed tokens: 13018071040 | elapsed time per iteration (s): 0.23 | learning rate: 6.875E-05 | global batch size: 256 | lm loss: 3.327269E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.931 | TFLOPs: 28.38 | +7: iteration 24840/ 37905 | consumed samples: 6359040 | consumed tokens: 13023313920 | elapsed time per iteration (s): 0.23 | learning rate: 6.868E-05 | global batch size: 256 | lm loss: 3.320916E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.497 | TFLOPs: 27.98 | +7: iteration 24850/ 37905 | consumed samples: 6361600 | consumed tokens: 13028556800 | elapsed time per iteration (s): 0.23 | learning rate: 6.861E-05 | global batch size: 256 | lm loss: 3.345303E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.634 | TFLOPs: 28.32 | +7: iteration 24860/ 37905 | consumed samples: 6364160 | consumed tokens: 13033799680 | elapsed time per iteration (s): 0.26 | learning rate: 6.854E-05 | global batch size: 256 | lm loss: 3.363919E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 978.260 | TFLOPs: 24.92 | +7: iteration 24870/ 37905 | consumed samples: 6366720 | consumed tokens: 13039042560 | elapsed time per iteration (s): 0.23 | learning rate: 6.848E-05 | global batch size: 256 | lm loss: 3.350295E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.165 | TFLOPs: 28.10 | +7: iteration 24880/ 37905 | consumed samples: 6369280 | consumed tokens: 13044285440 | elapsed time per iteration (s): 0.23 | learning rate: 6.841E-05 | global batch size: 256 | lm loss: 3.348256E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.363 | TFLOPs: 27.98 | +7: iteration 24890/ 37905 | consumed samples: 6371840 | consumed tokens: 13049528320 | elapsed time per iteration (s): 0.23 | learning rate: 6.834E-05 | global batch size: 256 | lm loss: 3.359626E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.828 | TFLOPs: 27.87 | +7: iteration 24900/ 37905 | consumed samples: 6374400 | consumed tokens: 13054771200 | elapsed time per iteration (s): 0.23 | learning rate: 6.828E-05 | global batch size: 256 | lm loss: 3.345061E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.215 | TFLOPs: 27.95 | +7: iteration 24910/ 37905 | consumed samples: 6376960 | consumed tokens: 13060014080 | elapsed time per iteration (s): 0.23 | learning rate: 6.821E-05 | global batch size: 256 | lm loss: 3.310001E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.162 | TFLOPs: 27.90 | +7: iteration 24920/ 37905 | consumed samples: 6379520 | consumed tokens: 13065256960 | elapsed time per iteration (s): 0.23 | learning rate: 6.814E-05 | global batch size: 256 | lm loss: 3.360705E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.570 | TFLOPs: 28.11 | +7: iteration 24930/ 37905 | consumed samples: 6382080 | consumed tokens: 13070499840 | elapsed time per iteration (s): 0.24 | learning rate: 6.808E-05 | global batch size: 256 | lm loss: 3.326057E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.432 | TFLOPs: 27.73 | +7: iteration 24940/ 37905 | consumed samples: 6384640 | consumed tokens: 13075742720 | elapsed time per iteration (s): 0.23 | learning rate: 6.801E-05 | global batch size: 256 | lm loss: 3.406757E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.085 | TFLOPs: 28.25 | +7: iteration 24950/ 37905 | consumed samples: 6387200 | consumed tokens: 13080985600 | elapsed time per iteration (s): 0.23 | learning rate: 6.794E-05 | global batch size: 256 | lm loss: 3.349358E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.793 | TFLOPs: 28.20 | +7: iteration 24960/ 37905 | consumed samples: 6389760 | consumed tokens: 13086228480 | elapsed time per iteration (s): 0.23 | learning rate: 6.788E-05 | global batch size: 256 | lm loss: 3.360162E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.800 | TFLOPs: 28.07 | +7: iteration 24970/ 37905 | consumed samples: 6392320 | consumed tokens: 13091471360 | elapsed time per iteration (s): 0.23 | learning rate: 6.781E-05 | global batch size: 256 | lm loss: 3.372959E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.884 | TFLOPs: 28.02 | +7: iteration 24980/ 37905 | consumed samples: 6394880 | consumed tokens: 13096714240 | elapsed time per iteration (s): 0.23 | learning rate: 6.774E-05 | global batch size: 256 | lm loss: 3.350080E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.245 | TFLOPs: 28.33 | +7: iteration 24990/ 37905 | consumed samples: 6397440 | consumed tokens: 13101957120 | elapsed time per iteration (s): 0.23 | learning rate: 6.768E-05 | global batch size: 256 | lm loss: 3.349932E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.969 | TFLOPs: 28.17 | +7: iteration 25000/ 37905 | consumed samples: 6400000 | consumed tokens: 13107200000 | elapsed time per iteration (s): 0.23 | learning rate: 6.761E-05 | global batch size: 256 | lm loss: 3.345831E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.320 | TFLOPs: 28.39 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 25000 | lm loss value: 3.142170E+00 | lm loss PPL: 2.315406E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 25000 to checkpoints_83moscar +0: [2022-11-29 18:35:14,021] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step25000 is begin to save! +0: [2022-11-29 18:35:14,026] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:35:14,106] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:35:14,106] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:35:14,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:35:14,119] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:35:14,131] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:35:14,131] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:35:14,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:35:14,143] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:35:14,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:35:14,155] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:35:14,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:35:14,166] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:35:14,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:35:14,178] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:35:14,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:35:14,190] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:35:14,201] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:35:14,201] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:35:14,213] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:35:14,213] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:35:14,225] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:35:14,225] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:35:14,226] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:35:14,226] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step25000/mp_rank_00_model_states.pt +0: [2022-11-29 18:35:14,226] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:35:14,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:35:14,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:35:14,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:35:14,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:35:14,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:35:14,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +1: [2022-11-29 18:35:14,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:35:14,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:35:14,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +2: [2022-11-29 18:35:14,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:35:14,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:35:14,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +0: [2022-11-29 18:35:14,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:35:14,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +3: [2022-11-29 18:35:14,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:35:14,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:35:14,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +7: [2022-11-29 18:35:14,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +5: [2022-11-29 18:35:14,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:35:14,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +7: [2022-11-29 18:35:14,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +5: [2022-11-29 18:35:14,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:35:14,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +6: [2022-11-29 18:35:14,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:35:14,270] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:35:14,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +2: [2022-11-29 18:35:14,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:35:14,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:35:14,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +6: [2022-11-29 18:35:14,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +2: [2022-11-29 18:35:14,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +6: [2022-11-29 18:35:14,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +4: [2022-11-29 18:35:14,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:35:14,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:35:14,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:35:14,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +0: [2022-11-29 18:35:14,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:35:14,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +5: [2022-11-29 18:35:14,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:35:14,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:35:14,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +3: [2022-11-29 18:35:14,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:35:14,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:35:14,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +0: [2022-11-29 18:35:14,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3: [2022-11-29 18:35:14,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +0: [2022-11-29 18:35:14,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +1: [2022-11-29 18:35:14,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:35:14,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:35:14,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +7: [2022-11-29 18:35:14,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:35:14,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:35:14,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +0: [2022-11-29 18:35:14,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:35:14,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +1: [2022-11-29 18:35:14,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:35:14,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +2: [2022-11-29 18:35:14,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:35:14,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +2: [2022-11-29 18:35:14,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +1: [2022-11-29 18:35:14,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +2: [2022-11-29 18:35:14,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +5: [2022-11-29 18:35:14,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:35:14,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:35:14,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +6: [2022-11-29 18:35:14,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:35:14,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:35:14,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +4: [2022-11-29 18:35:14,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:35:14,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:35:14,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +7: [2022-11-29 18:35:14,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:35:14,275] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:35:14,275] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +6: [2022-11-29 18:35:14,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:35:14,275] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:35:14,275] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +6: [2022-11-29 18:35:14,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:35:14,276] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +4: [2022-11-29 18:35:14,276] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:35:14,276] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:35:14,276] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +3: [2022-11-29 18:35:14,276] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +4: [2022-11-29 18:35:14,276] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +3: [2022-11-29 18:35:14,276] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +4: [2022-11-29 18:35:14,276] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +1: [2022-11-29 18:35:14,276] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:35:14,276] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:35:14,276] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +2: [2022-11-29 18:35:14,276] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:35:14,276] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:35:14,276] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +7: [2022-11-29 18:35:14,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:35:14,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +0: [2022-11-29 18:35:14,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:35:14,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +0: [2022-11-29 18:35:14,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:35:14,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +5: [2022-11-29 18:35:14,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:35:14,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:35:14,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +3: [2022-11-29 18:35:14,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:35:14,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:35:14,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:35:14,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +2: [2022-11-29 18:35:14,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:35:14,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +1: [2022-11-29 18:35:14,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:35:14,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:35:14,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +4: [2022-11-29 18:35:14,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:35:14,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:35:14,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:35:14,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +5: [2022-11-29 18:35:14,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +4: [2022-11-29 18:35:14,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +5: [2022-11-29 18:35:14,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +3: [2022-11-29 18:35:14,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:35:14,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +4: [2022-11-29 18:35:14,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:35:14,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:35:14,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +1: [2022-11-29 18:35:14,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:35:14,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:35:14,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +7: [2022-11-29 18:35:14,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:35:14,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:35:14,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +0: [2022-11-29 18:35:14,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:35:14,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:35:14,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +0: [2022-11-29 18:35:14,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:35:14,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:35:14,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +1: [2022-11-29 18:35:14,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:35:14,280] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:35:14,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +6: [2022-11-29 18:35:14,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:35:14,280] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:35:14,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +6: [2022-11-29 18:35:14,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:35:14,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:35:14,280] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:35:14,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +2: [2022-11-29 18:35:14,280] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:35:14,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +2: [2022-11-29 18:35:14,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:35:14,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:35:14,280] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +7: [2022-11-29 18:35:14,280] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +2: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +4: [2022-11-29 18:35:14,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +4: [2022-11-29 18:35:14,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +6: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +3: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:35:14,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +3: [2022-11-29 18:35:14,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +1: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +7: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:35:14,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +5: [2022-11-29 18:35:14,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +7: [2022-11-29 18:35:14,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +1: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +7: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +3: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:35:14,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +2: [2022-11-29 18:35:14,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +4: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:35:14,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +4: [2022-11-29 18:35:14,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +5: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:35:14,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +0: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +5: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +5: [2022-11-29 18:35:14,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +4: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +5: [2022-11-29 18:35:14,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +7: [2022-11-29 18:35:14,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:35:14,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:35:14,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +4: [2022-11-29 18:35:14,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:35:14,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step25000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:35:14,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +0: successfully saved checkpoint at iteration 25000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 264.31 +7: iteration 25010/ 37905 | consumed samples: 6402560 | consumed tokens: 13112442880 | elapsed time per iteration (s): 0.27 | learning rate: 6.754E-05 | global batch size: 256 | lm loss: 3.360313E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 950.499 | TFLOPs: 24.21 | +7: iteration 25020/ 37905 | consumed samples: 6405120 | consumed tokens: 13117685760 | elapsed time per iteration (s): 0.23 | learning rate: 6.748E-05 | global batch size: 256 | lm loss: 3.361127E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.878 | TFLOPs: 28.38 | +7: iteration 25030/ 37905 | consumed samples: 6407680 | consumed tokens: 13122928640 | elapsed time per iteration (s): 0.24 | learning rate: 6.741E-05 | global batch size: 256 | lm loss: 3.337259E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1080.116 | TFLOPs: 27.52 | +7: iteration 25040/ 37905 | consumed samples: 6410240 | consumed tokens: 13128171520 | elapsed time per iteration (s): 0.23 | learning rate: 6.735E-05 | global batch size: 256 | lm loss: 3.340519E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.548 | TFLOPs: 28.34 | +7: iteration 25050/ 37905 | consumed samples: 6412800 | consumed tokens: 13133414400 | elapsed time per iteration (s): 0.23 | learning rate: 6.728E-05 | global batch size: 256 | lm loss: 3.383273E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.218 | TFLOPs: 28.49 | +7: iteration 25060/ 37905 | consumed samples: 6415360 | consumed tokens: 13138657280 | elapsed time per iteration (s): 0.23 | learning rate: 6.721E-05 | global batch size: 256 | lm loss: 3.344899E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.577 | TFLOPs: 28.37 | +7: iteration 25070/ 37905 | consumed samples: 6417920 | consumed tokens: 13143900160 | elapsed time per iteration (s): 0.23 | learning rate: 6.715E-05 | global batch size: 256 | lm loss: 3.337960E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.465 | TFLOPs: 28.29 | +7: iteration 25080/ 37905 | consumed samples: 6420480 | consumed tokens: 13149143040 | elapsed time per iteration (s): 0.23 | learning rate: 6.708E-05 | global batch size: 256 | lm loss: 3.334819E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.855 | TFLOPs: 28.40 | +7: iteration 25090/ 37905 | consumed samples: 6423040 | consumed tokens: 13154385920 | elapsed time per iteration (s): 0.23 | learning rate: 6.701E-05 | global batch size: 256 | lm loss: 3.320137E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.010 | TFLOPs: 28.30 | +7: iteration 25100/ 37905 | consumed samples: 6425600 | consumed tokens: 13159628800 | elapsed time per iteration (s): 0.23 | learning rate: 6.695E-05 | global batch size: 256 | lm loss: 3.351811E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.540 | TFLOPs: 28.34 | +7: iteration 25110/ 37905 | consumed samples: 6428160 | consumed tokens: 13164871680 | elapsed time per iteration (s): 0.23 | learning rate: 6.688E-05 | global batch size: 256 | lm loss: 3.346139E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.726 | TFLOPs: 27.79 | +7: iteration 25120/ 37905 | consumed samples: 6430720 | consumed tokens: 13170114560 | elapsed time per iteration (s): 0.23 | learning rate: 6.682E-05 | global batch size: 256 | lm loss: 3.326305E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.373 | TFLOPs: 28.06 | +7: iteration 25130/ 37905 | consumed samples: 6433280 | consumed tokens: 13175357440 | elapsed time per iteration (s): 0.23 | learning rate: 6.675E-05 | global batch size: 256 | lm loss: 3.347355E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.053 | TFLOPs: 28.07 | +7: iteration 25140/ 37905 | consumed samples: 6435840 | consumed tokens: 13180600320 | elapsed time per iteration (s): 0.23 | learning rate: 6.668E-05 | global batch size: 256 | lm loss: 3.370153E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.802 | TFLOPs: 28.02 | +7: iteration 25150/ 37905 | consumed samples: 6438400 | consumed tokens: 13185843200 | elapsed time per iteration (s): 0.24 | learning rate: 6.662E-05 | global batch size: 256 | lm loss: 3.325254E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1079.335 | TFLOPs: 27.50 | +7: iteration 25160/ 37905 | consumed samples: 6440960 | consumed tokens: 13191086080 | elapsed time per iteration (s): 0.23 | learning rate: 6.655E-05 | global batch size: 256 | lm loss: 3.346922E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.048 | TFLOPs: 28.41 | +7: iteration 25170/ 37905 | consumed samples: 6443520 | consumed tokens: 13196328960 | elapsed time per iteration (s): 0.23 | learning rate: 6.649E-05 | global batch size: 256 | lm loss: 3.379512E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.341 | TFLOPs: 28.11 | +7: iteration 25180/ 37905 | consumed samples: 6446080 | consumed tokens: 13201571840 | elapsed time per iteration (s): 0.23 | learning rate: 6.642E-05 | global batch size: 256 | lm loss: 3.348327E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.658 | TFLOPs: 28.32 | +7: iteration 25190/ 37905 | consumed samples: 6448640 | consumed tokens: 13206814720 | elapsed time per iteration (s): 0.23 | learning rate: 6.635E-05 | global batch size: 256 | lm loss: 3.340335E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.004 | TFLOPs: 28.07 | +7: iteration 25200/ 37905 | consumed samples: 6451200 | consumed tokens: 13212057600 | elapsed time per iteration (s): 0.23 | learning rate: 6.629E-05 | global batch size: 256 | lm loss: 3.336796E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.316 | TFLOPs: 28.06 | +7: iteration 25210/ 37905 | consumed samples: 6453760 | consumed tokens: 13217300480 | elapsed time per iteration (s): 0.23 | learning rate: 6.622E-05 | global batch size: 256 | lm loss: 3.325509E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.658 | TFLOPs: 28.32 | +7: iteration 25220/ 37905 | consumed samples: 6456320 | consumed tokens: 13222543360 | elapsed time per iteration (s): 0.23 | learning rate: 6.616E-05 | global batch size: 256 | lm loss: 3.338681E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.453 | TFLOPs: 27.80 | +7: iteration 25230/ 37905 | consumed samples: 6458880 | consumed tokens: 13227786240 | elapsed time per iteration (s): 0.23 | learning rate: 6.609E-05 | global batch size: 256 | lm loss: 3.346786E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.866 | TFLOPs: 28.27 | +7: iteration 25240/ 37905 | consumed samples: 6461440 | consumed tokens: 13233029120 | elapsed time per iteration (s): 0.23 | learning rate: 6.602E-05 | global batch size: 256 | lm loss: 3.353928E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.084 | TFLOPs: 28.00 | +7: iteration 25250/ 37905 | consumed samples: 6464000 | consumed tokens: 13238272000 | elapsed time per iteration (s): 0.23 | learning rate: 6.596E-05 | global batch size: 256 | lm loss: 3.361551E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.631 | TFLOPs: 28.45 | +7: iteration 25260/ 37905 | consumed samples: 6466560 | consumed tokens: 13243514880 | elapsed time per iteration (s): 0.23 | learning rate: 6.589E-05 | global batch size: 256 | lm loss: 3.355649E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.429 | TFLOPs: 27.83 | +7: iteration 25270/ 37905 | consumed samples: 6469120 | consumed tokens: 13248757760 | elapsed time per iteration (s): 0.23 | learning rate: 6.583E-05 | global batch size: 256 | lm loss: 3.319436E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.333 | TFLOPs: 27.93 | +7: iteration 25280/ 37905 | consumed samples: 6471680 | consumed tokens: 13254000640 | elapsed time per iteration (s): 0.23 | learning rate: 6.576E-05 | global batch size: 256 | lm loss: 3.328248E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.896 | TFLOPs: 28.07 | +7: iteration 25290/ 37905 | consumed samples: 6474240 | consumed tokens: 13259243520 | elapsed time per iteration (s): 0.23 | learning rate: 6.570E-05 | global batch size: 256 | lm loss: 3.348894E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.027 | TFLOPs: 28.15 | +7: iteration 25300/ 37905 | consumed samples: 6476800 | consumed tokens: 13264486400 | elapsed time per iteration (s): 0.23 | learning rate: 6.563E-05 | global batch size: 256 | lm loss: 3.351541E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.614 | TFLOPs: 28.39 | +7: iteration 25310/ 37905 | consumed samples: 6479360 | consumed tokens: 13269729280 | elapsed time per iteration (s): 0.23 | learning rate: 6.556E-05 | global batch size: 256 | lm loss: 3.343317E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.674 | TFLOPs: 28.24 | +7: iteration 25320/ 37905 | consumed samples: 6481920 | consumed tokens: 13274972160 | elapsed time per iteration (s): 0.23 | learning rate: 6.550E-05 | global batch size: 256 | lm loss: 3.356926E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.424 | TFLOPs: 28.42 | +7: iteration 25330/ 37905 | consumed samples: 6484480 | consumed tokens: 13280215040 | elapsed time per iteration (s): 0.23 | learning rate: 6.543E-05 | global batch size: 256 | lm loss: 3.367348E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.515 | TFLOPs: 28.24 | +7: iteration 25340/ 37905 | consumed samples: 6487040 | consumed tokens: 13285457920 | elapsed time per iteration (s): 0.23 | learning rate: 6.537E-05 | global batch size: 256 | lm loss: 3.340765E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.063 | TFLOPs: 28.41 | +7: iteration 25350/ 37905 | consumed samples: 6489600 | consumed tokens: 13290700800 | elapsed time per iteration (s): 0.23 | learning rate: 6.530E-05 | global batch size: 256 | lm loss: 3.340676E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.942 | TFLOPs: 28.12 | +7: iteration 25360/ 37905 | consumed samples: 6492160 | consumed tokens: 13295943680 | elapsed time per iteration (s): 0.23 | learning rate: 6.524E-05 | global batch size: 256 | lm loss: 3.346278E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.324 | TFLOPs: 28.34 | +7: iteration 25370/ 37905 | consumed samples: 6494720 | consumed tokens: 13301186560 | elapsed time per iteration (s): 0.23 | learning rate: 6.517E-05 | global batch size: 256 | lm loss: 3.319054E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.095 | TFLOPs: 28.31 | +7: iteration 25380/ 37905 | consumed samples: 6497280 | consumed tokens: 13306429440 | elapsed time per iteration (s): 0.23 | learning rate: 6.511E-05 | global batch size: 256 | lm loss: 3.344340E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.575 | TFLOPs: 28.50 | +7: iteration 25390/ 37905 | consumed samples: 6499840 | consumed tokens: 13311672320 | elapsed time per iteration (s): 0.23 | learning rate: 6.504E-05 | global batch size: 256 | lm loss: 3.324495E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.002 | TFLOPs: 28.23 | +7: iteration 25400/ 37905 | consumed samples: 6502400 | consumed tokens: 13316915200 | elapsed time per iteration (s): 0.23 | learning rate: 6.498E-05 | global batch size: 256 | lm loss: 3.323198E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.334 | TFLOPs: 28.41 | +7: iteration 25410/ 37905 | consumed samples: 6504960 | consumed tokens: 13322158080 | elapsed time per iteration (s): 0.23 | learning rate: 6.491E-05 | global batch size: 256 | lm loss: 3.327120E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.088 | TFLOPs: 28.28 | +7: iteration 25420/ 37905 | consumed samples: 6507520 | consumed tokens: 13327400960 | elapsed time per iteration (s): 0.23 | learning rate: 6.485E-05 | global batch size: 256 | lm loss: 3.325056E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.683 | TFLOPs: 28.29 | +7: iteration 25430/ 37905 | consumed samples: 6510080 | consumed tokens: 13332643840 | elapsed time per iteration (s): 0.25 | learning rate: 6.478E-05 | global batch size: 256 | lm loss: 3.337186E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1036.055 | TFLOPs: 26.39 | +7: iteration 25440/ 37905 | consumed samples: 6512640 | consumed tokens: 13337886720 | elapsed time per iteration (s): 0.23 | learning rate: 6.472E-05 | global batch size: 256 | lm loss: 3.341626E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.288 | TFLOPs: 28.46 | +7: iteration 25450/ 37905 | consumed samples: 6515200 | consumed tokens: 13343129600 | elapsed time per iteration (s): 0.23 | learning rate: 6.465E-05 | global batch size: 256 | lm loss: 3.336616E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.727 | TFLOPs: 28.27 | +7: iteration 25460/ 37905 | consumed samples: 6517760 | consumed tokens: 13348372480 | elapsed time per iteration (s): 0.23 | learning rate: 6.459E-05 | global batch size: 256 | lm loss: 3.344203E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.481 | TFLOPs: 28.39 | +7: iteration 25470/ 37905 | consumed samples: 6520320 | consumed tokens: 13353615360 | elapsed time per iteration (s): 0.23 | learning rate: 6.452E-05 | global batch size: 256 | lm loss: 3.344575E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.302 | TFLOPs: 28.23 | +7: iteration 25480/ 37905 | consumed samples: 6522880 | consumed tokens: 13358858240 | elapsed time per iteration (s): 0.23 | learning rate: 6.446E-05 | global batch size: 256 | lm loss: 3.324197E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.669 | TFLOPs: 28.37 | +7: iteration 25490/ 37905 | consumed samples: 6525440 | consumed tokens: 13364101120 | elapsed time per iteration (s): 0.23 | learning rate: 6.439E-05 | global batch size: 256 | lm loss: 3.334136E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.954 | TFLOPs: 28.35 | +7: iteration 25500/ 37905 | consumed samples: 6528000 | consumed tokens: 13369344000 | elapsed time per iteration (s): 0.23 | learning rate: 6.433E-05 | global batch size: 256 | lm loss: 3.334675E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.414 | TFLOPs: 27.93 | +7: iteration 25510/ 37905 | consumed samples: 6530560 | consumed tokens: 13374586880 | elapsed time per iteration (s): 0.26 | learning rate: 6.426E-05 | global batch size: 256 | lm loss: 3.349481E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1002.674 | TFLOPs: 25.54 | +7: iteration 25520/ 37905 | consumed samples: 6533120 | consumed tokens: 13379829760 | elapsed time per iteration (s): 0.23 | learning rate: 6.420E-05 | global batch size: 256 | lm loss: 3.351032E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.237 | TFLOPs: 28.28 | +7: iteration 25530/ 37905 | consumed samples: 6535680 | consumed tokens: 13385072640 | elapsed time per iteration (s): 0.23 | learning rate: 6.413E-05 | global batch size: 256 | lm loss: 3.364924E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.102 | TFLOPs: 28.23 | +7: iteration 25540/ 37905 | consumed samples: 6538240 | consumed tokens: 13390315520 | elapsed time per iteration (s): 0.23 | learning rate: 6.407E-05 | global batch size: 256 | lm loss: 3.352723E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.969 | TFLOPs: 28.43 | +7: iteration 25550/ 37905 | consumed samples: 6540800 | consumed tokens: 13395558400 | elapsed time per iteration (s): 0.23 | learning rate: 6.400E-05 | global batch size: 256 | lm loss: 3.326237E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.579 | TFLOPs: 28.34 | +7: iteration 25560/ 37905 | consumed samples: 6543360 | consumed tokens: 13400801280 | elapsed time per iteration (s): 0.23 | learning rate: 6.394E-05 | global batch size: 256 | lm loss: 3.338702E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.469 | TFLOPs: 27.83 | +7: iteration 25570/ 37905 | consumed samples: 6545920 | consumed tokens: 13406044160 | elapsed time per iteration (s): 0.23 | learning rate: 6.387E-05 | global batch size: 256 | lm loss: 3.344511E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.651 | TFLOPs: 28.24 | +7: iteration 25580/ 37905 | consumed samples: 6548480 | consumed tokens: 13411287040 | elapsed time per iteration (s): 0.24 | learning rate: 6.381E-05 | global batch size: 256 | lm loss: 3.351562E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1081.309 | TFLOPs: 27.55 | +7: iteration 25590/ 37905 | consumed samples: 6551040 | consumed tokens: 13416529920 | elapsed time per iteration (s): 0.23 | learning rate: 6.374E-05 | global batch size: 256 | lm loss: 3.349496E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.445 | TFLOPs: 28.26 | +7: iteration 25600/ 37905 | consumed samples: 6553600 | consumed tokens: 13421772800 | elapsed time per iteration (s): 0.23 | learning rate: 6.368E-05 | global batch size: 256 | lm loss: 3.339036E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.003 | TFLOPs: 28.05 | +7: iteration 25610/ 37905 | consumed samples: 6556160 | consumed tokens: 13427015680 | elapsed time per iteration (s): 0.23 | learning rate: 6.361E-05 | global batch size: 256 | lm loss: 3.344139E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.471 | TFLOPs: 28.49 | +7: iteration 25620/ 37905 | consumed samples: 6558720 | consumed tokens: 13432258560 | elapsed time per iteration (s): 0.23 | learning rate: 6.355E-05 | global batch size: 256 | lm loss: 3.326065E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.176 | TFLOPs: 28.18 | +7: iteration 25630/ 37905 | consumed samples: 6561280 | consumed tokens: 13437501440 | elapsed time per iteration (s): 0.23 | learning rate: 6.348E-05 | global batch size: 256 | lm loss: 3.327836E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.823 | TFLOPs: 28.32 | +7: iteration 25640/ 37905 | consumed samples: 6563840 | consumed tokens: 13442744320 | elapsed time per iteration (s): 0.23 | learning rate: 6.342E-05 | global batch size: 256 | lm loss: 3.341817E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.353 | TFLOPs: 28.26 | +7: iteration 25650/ 37905 | consumed samples: 6566400 | consumed tokens: 13447987200 | elapsed time per iteration (s): 0.23 | learning rate: 6.336E-05 | global batch size: 256 | lm loss: 3.332202E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.894 | TFLOPs: 28.45 | +7: iteration 25660/ 37905 | consumed samples: 6568960 | consumed tokens: 13453230080 | elapsed time per iteration (s): 0.23 | learning rate: 6.329E-05 | global batch size: 256 | lm loss: 3.356571E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.082 | TFLOPs: 28.30 | +7: iteration 25670/ 37905 | consumed samples: 6571520 | consumed tokens: 13458472960 | elapsed time per iteration (s): 0.23 | learning rate: 6.323E-05 | global batch size: 256 | lm loss: 3.337622E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.034 | TFLOPs: 28.23 | +7: iteration 25680/ 37905 | consumed samples: 6574080 | consumed tokens: 13463715840 | elapsed time per iteration (s): 0.25 | learning rate: 6.316E-05 | global batch size: 256 | lm loss: 3.334482E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1011.084 | TFLOPs: 25.76 | +7: iteration 25690/ 37905 | consumed samples: 6576640 | consumed tokens: 13468958720 | elapsed time per iteration (s): 0.23 | learning rate: 6.310E-05 | global batch size: 256 | lm loss: 3.322738E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.923 | TFLOPs: 28.30 | +7: iteration 25700/ 37905 | consumed samples: 6579200 | consumed tokens: 13474201600 | elapsed time per iteration (s): 0.23 | learning rate: 6.303E-05 | global batch size: 256 | lm loss: 3.358221E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.535 | TFLOPs: 28.49 | +7: iteration 25710/ 37905 | consumed samples: 6581760 | consumed tokens: 13479444480 | elapsed time per iteration (s): 0.23 | learning rate: 6.297E-05 | global batch size: 256 | lm loss: 3.323869E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.041 | TFLOPs: 28.00 | +7: iteration 25720/ 37905 | consumed samples: 6584320 | consumed tokens: 13484687360 | elapsed time per iteration (s): 0.23 | learning rate: 6.291E-05 | global batch size: 256 | lm loss: 3.345109E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.711 | TFLOPs: 28.45 | +7: iteration 25730/ 37905 | consumed samples: 6586880 | consumed tokens: 13489930240 | elapsed time per iteration (s): 0.23 | learning rate: 6.284E-05 | global batch size: 256 | lm loss: 3.310054E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.170 | TFLOPs: 28.49 | +7: iteration 25740/ 37905 | consumed samples: 6589440 | consumed tokens: 13495173120 | elapsed time per iteration (s): 0.23 | learning rate: 6.278E-05 | global batch size: 256 | lm loss: 3.332877E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.415 | TFLOPs: 28.31 | +7: iteration 25750/ 37905 | consumed samples: 6592000 | consumed tokens: 13500416000 | elapsed time per iteration (s): 0.23 | learning rate: 6.271E-05 | global batch size: 256 | lm loss: 3.362246E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.739 | TFLOPs: 28.53 | +7: iteration 25760/ 37905 | consumed samples: 6594560 | consumed tokens: 13505658880 | elapsed time per iteration (s): 0.25 | learning rate: 6.265E-05 | global batch size: 256 | lm loss: 3.358419E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1030.604 | TFLOPs: 26.25 | +7: iteration 25770/ 37905 | consumed samples: 6597120 | consumed tokens: 13510901760 | elapsed time per iteration (s): 0.23 | learning rate: 6.258E-05 | global batch size: 256 | lm loss: 3.341863E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.024 | TFLOPs: 28.28 | +7: iteration 25780/ 37905 | consumed samples: 6599680 | consumed tokens: 13516144640 | elapsed time per iteration (s): 0.23 | learning rate: 6.252E-05 | global batch size: 256 | lm loss: 3.328460E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.577 | TFLOPs: 28.44 | +7: iteration 25790/ 37905 | consumed samples: 6602240 | consumed tokens: 13521387520 | elapsed time per iteration (s): 0.23 | learning rate: 6.246E-05 | global batch size: 256 | lm loss: 3.325786E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.190 | TFLOPs: 28.49 | +7: iteration 25800/ 37905 | consumed samples: 6604800 | consumed tokens: 13526630400 | elapsed time per iteration (s): 0.23 | learning rate: 6.239E-05 | global batch size: 256 | lm loss: 3.349763E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.693 | TFLOPs: 28.37 | +7: iteration 25810/ 37905 | consumed samples: 6607360 | consumed tokens: 13531873280 | elapsed time per iteration (s): 0.23 | learning rate: 6.233E-05 | global batch size: 256 | lm loss: 3.299829E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.799 | TFLOPs: 28.22 | +7: iteration 25820/ 37905 | consumed samples: 6609920 | consumed tokens: 13537116160 | elapsed time per iteration (s): 0.23 | learning rate: 6.226E-05 | global batch size: 256 | lm loss: 3.328794E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.709 | TFLOPs: 28.24 | +7: iteration 25830/ 37905 | consumed samples: 6612480 | consumed tokens: 13542359040 | elapsed time per iteration (s): 0.23 | learning rate: 6.220E-05 | global batch size: 256 | lm loss: 3.348916E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.119 | TFLOPs: 28.41 | +7: iteration 25840/ 37905 | consumed samples: 6615040 | consumed tokens: 13547601920 | elapsed time per iteration (s): 0.23 | learning rate: 6.214E-05 | global batch size: 256 | lm loss: 3.306496E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.444 | TFLOPs: 28.29 | +7: iteration 25850/ 37905 | consumed samples: 6617600 | consumed tokens: 13552844800 | elapsed time per iteration (s): 0.23 | learning rate: 6.207E-05 | global batch size: 256 | lm loss: 3.370057E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.961 | TFLOPs: 28.05 | +7: iteration 25860/ 37905 | consumed samples: 6620160 | consumed tokens: 13558087680 | elapsed time per iteration (s): 0.23 | learning rate: 6.201E-05 | global batch size: 256 | lm loss: 3.325085E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.900 | TFLOPs: 27.99 | +7: iteration 25870/ 37905 | consumed samples: 6622720 | consumed tokens: 13563330560 | elapsed time per iteration (s): 0.23 | learning rate: 6.195E-05 | global batch size: 256 | lm loss: 3.341565E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.015 | TFLOPs: 28.28 | +7: iteration 25880/ 37905 | consumed samples: 6625280 | consumed tokens: 13568573440 | elapsed time per iteration (s): 0.23 | learning rate: 6.188E-05 | global batch size: 256 | lm loss: 3.349461E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.145 | TFLOPs: 28.20 | +7: iteration 25890/ 37905 | consumed samples: 6627840 | consumed tokens: 13573816320 | elapsed time per iteration (s): 0.23 | learning rate: 6.182E-05 | global batch size: 256 | lm loss: 3.352333E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.050 | TFLOPs: 28.28 | +7: iteration 25900/ 37905 | consumed samples: 6630400 | consumed tokens: 13579059200 | elapsed time per iteration (s): 0.23 | learning rate: 6.175E-05 | global batch size: 256 | lm loss: 3.332202E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.869 | TFLOPs: 28.30 | +7: iteration 25910/ 37905 | consumed samples: 6632960 | consumed tokens: 13584302080 | elapsed time per iteration (s): 0.23 | learning rate: 6.169E-05 | global batch size: 256 | lm loss: 3.320980E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.758 | TFLOPs: 28.45 | +7: iteration 25920/ 37905 | consumed samples: 6635520 | consumed tokens: 13589544960 | elapsed time per iteration (s): 0.23 | learning rate: 6.163E-05 | global batch size: 256 | lm loss: 3.348598E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.511 | TFLOPs: 28.06 | +7: iteration 25930/ 37905 | consumed samples: 6638080 | consumed tokens: 13594787840 | elapsed time per iteration (s): 0.23 | learning rate: 6.156E-05 | global batch size: 256 | lm loss: 3.361160E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.579 | TFLOPs: 28.47 | +7: iteration 25940/ 37905 | consumed samples: 6640640 | consumed tokens: 13600030720 | elapsed time per iteration (s): 0.23 | learning rate: 6.150E-05 | global batch size: 256 | lm loss: 3.296135E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.392 | TFLOPs: 28.39 | +7: iteration 25950/ 37905 | consumed samples: 6643200 | consumed tokens: 13605273600 | elapsed time per iteration (s): 0.23 | learning rate: 6.144E-05 | global batch size: 256 | lm loss: 3.335635E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.578 | TFLOPs: 28.39 | +7: iteration 25960/ 37905 | consumed samples: 6645760 | consumed tokens: 13610516480 | elapsed time per iteration (s): 0.23 | learning rate: 6.137E-05 | global batch size: 256 | lm loss: 3.358166E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.224 | TFLOPs: 28.39 | +7: iteration 25970/ 37905 | consumed samples: 6648320 | consumed tokens: 13615759360 | elapsed time per iteration (s): 0.23 | learning rate: 6.131E-05 | global batch size: 256 | lm loss: 3.319447E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.143 | TFLOPs: 27.98 | +7: iteration 25980/ 37905 | consumed samples: 6650880 | consumed tokens: 13621002240 | elapsed time per iteration (s): 0.23 | learning rate: 6.125E-05 | global batch size: 256 | lm loss: 3.339035E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.326 | TFLOPs: 28.34 | +7: iteration 25990/ 37905 | consumed samples: 6653440 | consumed tokens: 13626245120 | elapsed time per iteration (s): 0.23 | learning rate: 6.118E-05 | global batch size: 256 | lm loss: 3.347469E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.450 | TFLOPs: 28.24 | +0: [2022-11-29 18:39:06,070] [INFO] [logging.py:68:log_dist] [Rank 0] step=26000, skipped=0, lr=[6.112056897407288e-05, 6.112056897407288e-05, 6.112056897407288e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +0: steps: 26000 loss: 3.3360 iter time (s): 0.232 samples/sec: 1105.415 +7: iteration 26000/ 37905 | consumed samples: 6656000 | consumed tokens: 13631488000 | elapsed time per iteration (s): 0.23 | learning rate: 6.112E-05 | global batch size: 256 | lm loss: 3.324079E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.287 | TFLOPs: 28.16 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 26000 | lm loss value: 3.207035E+00 | lm loss PPL: 2.470571E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 26000 to checkpoints_83moscar +0: [2022-11-29 18:39:06,179] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step26000 is begin to save! +0: [2022-11-29 18:39:06,182] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:39:06,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:39:06,263] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:39:06,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:39:06,276] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:39:06,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:39:06,287] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:39:06,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:39:06,299] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:39:06,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:39:06,311] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:39:06,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:39:06,323] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:39:06,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:39:06,334] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:39:06,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:39:06,346] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:39:06,357] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:39:06,358] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:39:06,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:39:06,369] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:39:06,381] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:39:06,381] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:39:06,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:39:06,382] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step26000/mp_rank_00_model_states.pt +0: [2022-11-29 18:39:06,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:39:06,384] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:39:06,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:39:06,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:39:06,421] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:39:06,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +5: [2022-11-29 18:39:06,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:39:06,422] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:39:06,422] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +0: [2022-11-29 18:39:06,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:39:06,423] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:39:06,423] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:39:06,423] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +3: [2022-11-29 18:39:06,423] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:39:06,423] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:39:06,424] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +1: [2022-11-29 18:39:06,424] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +3: [2022-11-29 18:39:06,424] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +1: [2022-11-29 18:39:06,424] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +0: [2022-11-29 18:39:06,424] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:39:06,424] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:39:06,424] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3: [2022-11-29 18:39:06,424] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +5: [2022-11-29 18:39:06,424] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:39:06,424] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +0: [2022-11-29 18:39:06,424] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +7: [2022-11-29 18:39:06,424] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:39:06,424] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:39:06,424] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +7: [2022-11-29 18:39:06,424] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:39:06,424] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +0: [2022-11-29 18:39:06,424] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:39:06,424] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +4: [2022-11-29 18:39:06,424] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:39:06,424] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:39:06,424] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +4: [2022-11-29 18:39:06,424] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:39:06,424] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:39:06,424] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +6: [2022-11-29 18:39:06,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:39:06,425] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:39:06,425] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +2: [2022-11-29 18:39:06,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:39:06,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:39:06,425] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +7: [2022-11-29 18:39:06,425] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +2: [2022-11-29 18:39:06,425] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +7: [2022-11-29 18:39:06,425] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +1: [2022-11-29 18:39:06,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:39:06,425] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:39:06,425] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +1: [2022-11-29 18:39:06,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:39:06,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:39:06,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +6: [2022-11-29 18:39:06,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:39:06,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:39:06,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +3: [2022-11-29 18:39:06,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:39:06,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +5: [2022-11-29 18:39:06,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:39:06,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +5: [2022-11-29 18:39:06,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:39:06,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:39:06,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:39:06,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +5: [2022-11-29 18:39:06,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +7: [2022-11-29 18:39:06,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:39:06,426] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:39:06,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +0: [2022-11-29 18:39:06,427] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:39:06,427] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:39:06,427] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +4: [2022-11-29 18:39:06,427] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +0: [2022-11-29 18:39:06,427] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +4: [2022-11-29 18:39:06,427] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +0: [2022-11-29 18:39:06,427] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:39:06,427] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:39:06,427] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +0: [2022-11-29 18:39:06,427] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +6: [2022-11-29 18:39:06,427] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +0: [2022-11-29 18:39:06,427] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +3: [2022-11-29 18:39:06,427] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:39:06,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:39:06,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +1: [2022-11-29 18:39:06,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:39:06,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:39:06,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +2: [2022-11-29 18:39:06,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:39:06,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:39:06,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +4: [2022-11-29 18:39:06,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:39:06,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:39:06,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +6: [2022-11-29 18:39:06,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:39:06,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:39:06,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +7: [2022-11-29 18:39:06,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:39:06,428] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:39:06,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +5: [2022-11-29 18:39:06,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:39:06,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:39:06,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +2: [2022-11-29 18:39:06,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:39:06,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:39:06,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +0: [2022-11-29 18:39:06,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:39:06,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:39:06,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +1: [2022-11-29 18:39:06,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:39:06,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +4: [2022-11-29 18:39:06,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:39:06,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +4: [2022-11-29 18:39:06,429] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:39:06,429] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +3: [2022-11-29 18:39:06,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:39:06,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +7: [2022-11-29 18:39:06,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:39:06,430] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +7: [2022-11-29 18:39:06,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:39:06,430] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +3: [2022-11-29 18:39:06,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:39:06,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:39:06,430] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +2: [2022-11-29 18:39:06,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:39:06,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:39:06,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:39:06,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +1: [2022-11-29 18:39:06,431] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +2: [2022-11-29 18:39:06,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +6: [2022-11-29 18:39:06,430] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +1: [2022-11-29 18:39:06,431] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +2: [2022-11-29 18:39:06,431] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +6: [2022-11-29 18:39:06,431] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:39:06,431] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:39:06,431] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +5: [2022-11-29 18:39:06,431] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:39:06,431] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:39:06,431] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:39:06,431] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +2: [2022-11-29 18:39:06,431] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +7: [2022-11-29 18:39:06,431] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:39:06,431] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +3: [2022-11-29 18:39:06,431] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:39:06,431] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:39:06,431] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +3: [2022-11-29 18:39:06,431] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +0: [2022-11-29 18:39:06,431] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +7: [2022-11-29 18:39:06,431] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +3: [2022-11-29 18:39:06,431] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +0: [2022-11-29 18:39:06,431] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +1: [2022-11-29 18:39:06,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:39:06,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:39:06,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +4: [2022-11-29 18:39:06,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:39:06,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:39:06,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +2: [2022-11-29 18:39:06,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +4: [2022-11-29 18:39:06,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +2: [2022-11-29 18:39:06,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +4: [2022-11-29 18:39:06,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:39:06,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:39:06,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +7: [2022-11-29 18:39:06,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +4: [2022-11-29 18:39:06,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +6: [2022-11-29 18:39:06,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:39:06,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +6: [2022-11-29 18:39:06,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:39:06,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +2: [2022-11-29 18:39:06,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:39:06,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:39:06,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +0: [2022-11-29 18:39:06,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:39:06,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:39:06,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +4: [2022-11-29 18:39:06,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:39:06,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:39:06,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +3: [2022-11-29 18:39:06,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:39:06,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:39:06,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +5: [2022-11-29 18:39:06,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:39:06,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +3: [2022-11-29 18:39:06,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +0: [2022-11-29 18:39:06,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:39:06,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +1: [2022-11-29 18:39:06,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:39:06,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +1: [2022-11-29 18:39:06,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +6: [2022-11-29 18:39:06,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:39:06,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +6: [2022-11-29 18:39:06,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:39:06,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +5: [2022-11-29 18:39:06,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:39:06,434] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step26000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:39:06,434] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +0: successfully saved checkpoint at iteration 26000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 258.35 +7: iteration 26010/ 37905 | consumed samples: 6658560 | consumed tokens: 13636730880 | elapsed time per iteration (s): 0.26 | learning rate: 6.106E-05 | global batch size: 256 | lm loss: 3.334237E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 975.963 | TFLOPs: 24.86 | +7: iteration 26020/ 37905 | consumed samples: 6661120 | consumed tokens: 13641973760 | elapsed time per iteration (s): 0.23 | learning rate: 6.099E-05 | global batch size: 256 | lm loss: 3.324125E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.264 | TFLOPs: 28.41 | +7: iteration 26030/ 37905 | consumed samples: 6663680 | consumed tokens: 13647216640 | elapsed time per iteration (s): 0.23 | learning rate: 6.093E-05 | global batch size: 256 | lm loss: 3.359908E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.358 | TFLOPs: 28.16 | +7: iteration 26040/ 37905 | consumed samples: 6666240 | consumed tokens: 13652459520 | elapsed time per iteration (s): 0.23 | learning rate: 6.087E-05 | global batch size: 256 | lm loss: 3.352880E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.979 | TFLOPs: 28.05 | +7: iteration 26050/ 37905 | consumed samples: 6668800 | consumed tokens: 13657702400 | elapsed time per iteration (s): 0.23 | learning rate: 6.080E-05 | global batch size: 256 | lm loss: 3.296062E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.252 | TFLOPs: 27.85 | +7: iteration 26060/ 37905 | consumed samples: 6671360 | consumed tokens: 13662945280 | elapsed time per iteration (s): 0.23 | learning rate: 6.074E-05 | global batch size: 256 | lm loss: 3.317011E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.605 | TFLOPs: 28.29 | +7: iteration 26070/ 37905 | consumed samples: 6673920 | consumed tokens: 13668188160 | elapsed time per iteration (s): 0.24 | learning rate: 6.068E-05 | global batch size: 256 | lm loss: 3.315719E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1071.881 | TFLOPs: 27.31 | +7: iteration 26080/ 37905 | consumed samples: 6676480 | consumed tokens: 13673431040 | elapsed time per iteration (s): 0.23 | learning rate: 6.062E-05 | global batch size: 256 | lm loss: 3.329080E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.019 | TFLOPs: 28.30 | +7: iteration 26090/ 37905 | consumed samples: 6679040 | consumed tokens: 13678673920 | elapsed time per iteration (s): 0.23 | learning rate: 6.055E-05 | global batch size: 256 | lm loss: 3.369703E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.191 | TFLOPs: 28.38 | +7: iteration 26100/ 37905 | consumed samples: 6681600 | consumed tokens: 13683916800 | elapsed time per iteration (s): 0.23 | learning rate: 6.049E-05 | global batch size: 256 | lm loss: 3.358991E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.958 | TFLOPs: 28.48 | +7: iteration 26110/ 37905 | consumed samples: 6684160 | consumed tokens: 13689159680 | elapsed time per iteration (s): 0.23 | learning rate: 6.043E-05 | global batch size: 256 | lm loss: 3.354988E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.032 | TFLOPs: 28.30 | +7: iteration 26120/ 37905 | consumed samples: 6686720 | consumed tokens: 13694402560 | elapsed time per iteration (s): 0.23 | learning rate: 6.036E-05 | global batch size: 256 | lm loss: 3.328493E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.996 | TFLOPs: 28.38 | +7: iteration 26130/ 37905 | consumed samples: 6689280 | consumed tokens: 13699645440 | elapsed time per iteration (s): 0.23 | learning rate: 6.030E-05 | global batch size: 256 | lm loss: 3.317975E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.871 | TFLOPs: 28.35 | +7: iteration 26140/ 37905 | consumed samples: 6691840 | consumed tokens: 13704888320 | elapsed time per iteration (s): 0.23 | learning rate: 6.024E-05 | global batch size: 256 | lm loss: 3.327298E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.383 | TFLOPs: 28.29 | +7: iteration 26150/ 37905 | consumed samples: 6694400 | consumed tokens: 13710131200 | elapsed time per iteration (s): 0.24 | learning rate: 6.018E-05 | global batch size: 256 | lm loss: 3.356573E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.665 | TFLOPs: 27.28 | +7: iteration 26160/ 37905 | consumed samples: 6696960 | consumed tokens: 13715374080 | elapsed time per iteration (s): 0.25 | learning rate: 6.011E-05 | global batch size: 256 | lm loss: 3.300597E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1021.193 | TFLOPs: 26.02 | +7: iteration 26170/ 37905 | consumed samples: 6699520 | consumed tokens: 13720616960 | elapsed time per iteration (s): 0.23 | learning rate: 6.005E-05 | global batch size: 256 | lm loss: 3.318120E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.321 | TFLOPs: 28.49 | +7: iteration 26180/ 37905 | consumed samples: 6702080 | consumed tokens: 13725859840 | elapsed time per iteration (s): 0.23 | learning rate: 5.999E-05 | global batch size: 256 | lm loss: 3.348172E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.197 | TFLOPs: 28.46 | +7: iteration 26190/ 37905 | consumed samples: 6704640 | consumed tokens: 13731102720 | elapsed time per iteration (s): 0.23 | learning rate: 5.992E-05 | global batch size: 256 | lm loss: 3.332785E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.855 | TFLOPs: 28.38 | +7: iteration 26200/ 37905 | consumed samples: 6707200 | consumed tokens: 13736345600 | elapsed time per iteration (s): 0.23 | learning rate: 5.986E-05 | global batch size: 256 | lm loss: 3.366151E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.954 | TFLOPs: 28.38 | +7: iteration 26210/ 37905 | consumed samples: 6709760 | consumed tokens: 13741588480 | elapsed time per iteration (s): 0.23 | learning rate: 5.980E-05 | global batch size: 256 | lm loss: 3.324079E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.215 | TFLOPs: 28.18 | +7: iteration 26220/ 37905 | consumed samples: 6712320 | consumed tokens: 13746831360 | elapsed time per iteration (s): 0.23 | learning rate: 5.974E-05 | global batch size: 256 | lm loss: 3.340197E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.448 | TFLOPs: 28.34 | +7: iteration 26230/ 37905 | consumed samples: 6714880 | consumed tokens: 13752074240 | elapsed time per iteration (s): 0.23 | learning rate: 5.967E-05 | global batch size: 256 | lm loss: 3.324932E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.829 | TFLOPs: 28.53 | +7: iteration 26240/ 37905 | consumed samples: 6717440 | consumed tokens: 13757317120 | elapsed time per iteration (s): 0.23 | learning rate: 5.961E-05 | global batch size: 256 | lm loss: 3.354072E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.114 | TFLOPs: 28.10 | +7: iteration 26250/ 37905 | consumed samples: 6720000 | consumed tokens: 13762560000 | elapsed time per iteration (s): 0.23 | learning rate: 5.955E-05 | global batch size: 256 | lm loss: 3.316372E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.621 | TFLOPs: 28.52 | +7: iteration 26260/ 37905 | consumed samples: 6722560 | consumed tokens: 13767802880 | elapsed time per iteration (s): 0.23 | learning rate: 5.949E-05 | global batch size: 256 | lm loss: 3.344550E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.324 | TFLOPs: 28.26 | +7: iteration 26270/ 37905 | consumed samples: 6725120 | consumed tokens: 13773045760 | elapsed time per iteration (s): 0.23 | learning rate: 5.943E-05 | global batch size: 256 | lm loss: 3.350190E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.248 | TFLOPs: 28.41 | +7: iteration 26280/ 37905 | consumed samples: 6727680 | consumed tokens: 13778288640 | elapsed time per iteration (s): 0.23 | learning rate: 5.936E-05 | global batch size: 256 | lm loss: 3.350320E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.814 | TFLOPs: 28.45 | +7: iteration 26290/ 37905 | consumed samples: 6730240 | consumed tokens: 13783531520 | elapsed time per iteration (s): 0.23 | learning rate: 5.930E-05 | global batch size: 256 | lm loss: 3.334575E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.131 | TFLOPs: 28.43 | +7: iteration 26300/ 37905 | consumed samples: 6732800 | consumed tokens: 13788774400 | elapsed time per iteration (s): 0.23 | learning rate: 5.924E-05 | global batch size: 256 | lm loss: 3.329891E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.712 | TFLOPs: 28.58 | +7: iteration 26310/ 37905 | consumed samples: 6735360 | consumed tokens: 13794017280 | elapsed time per iteration (s): 0.23 | learning rate: 5.918E-05 | global batch size: 256 | lm loss: 3.358992E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.222 | TFLOPs: 28.56 | +7: iteration 26320/ 37905 | consumed samples: 6737920 | consumed tokens: 13799260160 | elapsed time per iteration (s): 0.23 | learning rate: 5.911E-05 | global batch size: 256 | lm loss: 3.338424E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.244 | TFLOPs: 28.41 | +7: iteration 26330/ 37905 | consumed samples: 6740480 | consumed tokens: 13804503040 | elapsed time per iteration (s): 0.25 | learning rate: 5.905E-05 | global batch size: 256 | lm loss: 3.339753E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1011.851 | TFLOPs: 25.78 | +7: iteration 26340/ 37905 | consumed samples: 6743040 | consumed tokens: 13809745920 | elapsed time per iteration (s): 0.23 | learning rate: 5.899E-05 | global batch size: 256 | lm loss: 3.322858E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.519 | TFLOPs: 28.42 | +7: iteration 26350/ 37905 | consumed samples: 6745600 | consumed tokens: 13814988800 | elapsed time per iteration (s): 0.23 | learning rate: 5.893E-05 | global batch size: 256 | lm loss: 3.329554E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.949 | TFLOPs: 28.40 | +7: iteration 26360/ 37905 | consumed samples: 6748160 | consumed tokens: 13820231680 | elapsed time per iteration (s): 0.23 | learning rate: 5.887E-05 | global batch size: 256 | lm loss: 3.349515E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.453 | TFLOPs: 28.37 | +7: iteration 26370/ 37905 | consumed samples: 6750720 | consumed tokens: 13825474560 | elapsed time per iteration (s): 0.23 | learning rate: 5.880E-05 | global batch size: 256 | lm loss: 3.340189E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.329 | TFLOPs: 28.29 | +7: iteration 26380/ 37905 | consumed samples: 6753280 | consumed tokens: 13830717440 | elapsed time per iteration (s): 0.23 | learning rate: 5.874E-05 | global batch size: 256 | lm loss: 3.344557E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.226 | TFLOPs: 28.49 | +7: iteration 26390/ 37905 | consumed samples: 6755840 | consumed tokens: 13835960320 | elapsed time per iteration (s): 0.23 | learning rate: 5.868E-05 | global batch size: 256 | lm loss: 3.322402E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.856 | TFLOPs: 27.97 | +7: iteration 26400/ 37905 | consumed samples: 6758400 | consumed tokens: 13841203200 | elapsed time per iteration (s): 0.23 | learning rate: 5.862E-05 | global batch size: 256 | lm loss: 3.341761E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.956 | TFLOPs: 28.02 | +7: iteration 26410/ 37905 | consumed samples: 6760960 | consumed tokens: 13846446080 | elapsed time per iteration (s): 0.25 | learning rate: 5.856E-05 | global batch size: 256 | lm loss: 3.335581E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1040.312 | TFLOPs: 26.50 | +7: iteration 26420/ 37905 | consumed samples: 6763520 | consumed tokens: 13851688960 | elapsed time per iteration (s): 0.23 | learning rate: 5.849E-05 | global batch size: 256 | lm loss: 3.356855E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.606 | TFLOPs: 28.19 | +7: iteration 26430/ 37905 | consumed samples: 6766080 | consumed tokens: 13856931840 | elapsed time per iteration (s): 0.23 | learning rate: 5.843E-05 | global batch size: 256 | lm loss: 3.348689E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.660 | TFLOPs: 28.42 | +7: iteration 26440/ 37905 | consumed samples: 6768640 | consumed tokens: 13862174720 | elapsed time per iteration (s): 0.23 | learning rate: 5.837E-05 | global batch size: 256 | lm loss: 3.323953E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.259 | TFLOPs: 28.13 | +7: iteration 26450/ 37905 | consumed samples: 6771200 | consumed tokens: 13867417600 | elapsed time per iteration (s): 0.23 | learning rate: 5.831E-05 | global batch size: 256 | lm loss: 3.338762E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.865 | TFLOPs: 28.27 | +7: iteration 26460/ 37905 | consumed samples: 6773760 | consumed tokens: 13872660480 | elapsed time per iteration (s): 0.23 | learning rate: 5.825E-05 | global batch size: 256 | lm loss: 3.315601E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.456 | TFLOPs: 27.83 | +7: iteration 26470/ 37905 | consumed samples: 6776320 | consumed tokens: 13877903360 | elapsed time per iteration (s): 0.23 | learning rate: 5.819E-05 | global batch size: 256 | lm loss: 3.338134E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.141 | TFLOPs: 28.41 | +7: iteration 26480/ 37905 | consumed samples: 6778880 | consumed tokens: 13883146240 | elapsed time per iteration (s): 0.23 | learning rate: 5.812E-05 | global batch size: 256 | lm loss: 3.341590E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.023 | TFLOPs: 28.15 | +7: iteration 26490/ 37905 | consumed samples: 6781440 | consumed tokens: 13888389120 | elapsed time per iteration (s): 0.23 | learning rate: 5.806E-05 | global batch size: 256 | lm loss: 3.342674E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.637 | TFLOPs: 28.42 | +7: iteration 26500/ 37905 | consumed samples: 6784000 | consumed tokens: 13893632000 | elapsed time per iteration (s): 0.23 | learning rate: 5.800E-05 | global batch size: 256 | lm loss: 3.338165E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.039 | TFLOPs: 28.33 | +7: iteration 26510/ 37905 | consumed samples: 6786560 | consumed tokens: 13898874880 | elapsed time per iteration (s): 0.23 | learning rate: 5.794E-05 | global batch size: 256 | lm loss: 3.356659E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.891 | TFLOPs: 28.53 | +7: iteration 26520/ 37905 | consumed samples: 6789120 | consumed tokens: 13904117760 | elapsed time per iteration (s): 0.25 | learning rate: 5.788E-05 | global batch size: 256 | lm loss: 3.319917E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1025.061 | TFLOPs: 26.11 | +7: iteration 26530/ 37905 | consumed samples: 6791680 | consumed tokens: 13909360640 | elapsed time per iteration (s): 0.23 | learning rate: 5.782E-05 | global batch size: 256 | lm loss: 3.340427E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.135 | TFLOPs: 28.54 | +7: iteration 26540/ 37905 | consumed samples: 6794240 | consumed tokens: 13914603520 | elapsed time per iteration (s): 0.23 | learning rate: 5.776E-05 | global batch size: 256 | lm loss: 3.352929E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.226 | TFLOPs: 28.49 | +7: iteration 26550/ 37905 | consumed samples: 6796800 | consumed tokens: 13919846400 | elapsed time per iteration (s): 0.23 | learning rate: 5.769E-05 | global batch size: 256 | lm loss: 3.333453E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.189 | TFLOPs: 28.36 | +7: iteration 26560/ 37905 | consumed samples: 6799360 | consumed tokens: 13925089280 | elapsed time per iteration (s): 0.23 | learning rate: 5.763E-05 | global batch size: 256 | lm loss: 3.361293E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.824 | TFLOPs: 28.55 | +7: iteration 26570/ 37905 | consumed samples: 6801920 | consumed tokens: 13930332160 | elapsed time per iteration (s): 0.23 | learning rate: 5.757E-05 | global batch size: 256 | lm loss: 3.339133E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.953 | TFLOPs: 28.48 | +7: iteration 26580/ 37905 | consumed samples: 6804480 | consumed tokens: 13935575040 | elapsed time per iteration (s): 0.23 | learning rate: 5.751E-05 | global batch size: 256 | lm loss: 3.356635E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.742 | TFLOPs: 28.35 | +7: iteration 26590/ 37905 | consumed samples: 6807040 | consumed tokens: 13940817920 | elapsed time per iteration (s): 0.23 | learning rate: 5.745E-05 | global batch size: 256 | lm loss: 3.348800E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.701 | TFLOPs: 28.22 | +7: iteration 26600/ 37905 | consumed samples: 6809600 | consumed tokens: 13946060800 | elapsed time per iteration (s): 0.23 | learning rate: 5.739E-05 | global batch size: 256 | lm loss: 3.336303E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.694 | TFLOPs: 28.40 | +7: iteration 26610/ 37905 | consumed samples: 6812160 | consumed tokens: 13951303680 | elapsed time per iteration (s): 0.23 | learning rate: 5.733E-05 | global batch size: 256 | lm loss: 3.320604E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.357 | TFLOPs: 28.16 | +7: iteration 26620/ 37905 | consumed samples: 6814720 | consumed tokens: 13956546560 | elapsed time per iteration (s): 0.23 | learning rate: 5.727E-05 | global batch size: 256 | lm loss: 3.320277E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.527 | TFLOPs: 28.32 | +7: iteration 26630/ 37905 | consumed samples: 6817280 | consumed tokens: 13961789440 | elapsed time per iteration (s): 0.23 | learning rate: 5.720E-05 | global batch size: 256 | lm loss: 3.348292E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.398 | TFLOPs: 28.31 | +7: iteration 26640/ 37905 | consumed samples: 6819840 | consumed tokens: 13967032320 | elapsed time per iteration (s): 0.23 | learning rate: 5.714E-05 | global batch size: 256 | lm loss: 3.324712E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.294 | TFLOPs: 28.51 | +7: iteration 26650/ 37905 | consumed samples: 6822400 | consumed tokens: 13972275200 | elapsed time per iteration (s): 0.23 | learning rate: 5.708E-05 | global batch size: 256 | lm loss: 3.360487E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.335 | TFLOPs: 28.29 | +7: iteration 26660/ 37905 | consumed samples: 6824960 | consumed tokens: 13977518080 | elapsed time per iteration (s): 0.23 | learning rate: 5.702E-05 | global batch size: 256 | lm loss: 3.321394E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.658 | TFLOPs: 28.40 | +7: iteration 26670/ 37905 | consumed samples: 6827520 | consumed tokens: 13982760960 | elapsed time per iteration (s): 0.23 | learning rate: 5.696E-05 | global batch size: 256 | lm loss: 3.338759E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.085 | TFLOPs: 28.48 | +7: iteration 26680/ 37905 | consumed samples: 6830080 | consumed tokens: 13988003840 | elapsed time per iteration (s): 0.23 | learning rate: 5.690E-05 | global batch size: 256 | lm loss: 3.358637E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.931 | TFLOPs: 28.33 | +7: iteration 26690/ 37905 | consumed samples: 6832640 | consumed tokens: 13993246720 | elapsed time per iteration (s): 0.23 | learning rate: 5.684E-05 | global batch size: 256 | lm loss: 3.354803E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.049 | TFLOPs: 28.46 | +7: iteration 26700/ 37905 | consumed samples: 6835200 | consumed tokens: 13998489600 | elapsed time per iteration (s): 0.23 | learning rate: 5.678E-05 | global batch size: 256 | lm loss: 3.365889E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.134 | TFLOPs: 28.36 | +7: iteration 26710/ 37905 | consumed samples: 6837760 | consumed tokens: 14003732480 | elapsed time per iteration (s): 0.23 | learning rate: 5.672E-05 | global batch size: 256 | lm loss: 3.336669E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.729 | TFLOPs: 28.45 | +7: iteration 26720/ 37905 | consumed samples: 6840320 | consumed tokens: 14008975360 | elapsed time per iteration (s): 0.25 | learning rate: 5.666E-05 | global batch size: 256 | lm loss: 3.322359E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1034.918 | TFLOPs: 26.36 | +7: iteration 26730/ 37905 | consumed samples: 6842880 | consumed tokens: 14014218240 | elapsed time per iteration (s): 0.23 | learning rate: 5.660E-05 | global batch size: 256 | lm loss: 3.341304E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.434 | TFLOPs: 28.29 | +7: iteration 26740/ 37905 | consumed samples: 6845440 | consumed tokens: 14019461120 | elapsed time per iteration (s): 0.23 | learning rate: 5.654E-05 | global batch size: 256 | lm loss: 3.328043E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.217 | TFLOPs: 28.26 | +7: iteration 26750/ 37905 | consumed samples: 6848000 | consumed tokens: 14024704000 | elapsed time per iteration (s): 0.23 | learning rate: 5.648E-05 | global batch size: 256 | lm loss: 3.303391E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.306 | TFLOPs: 28.31 | +7: iteration 26760/ 37905 | consumed samples: 6850560 | consumed tokens: 14029946880 | elapsed time per iteration (s): 0.23 | learning rate: 5.641E-05 | global batch size: 256 | lm loss: 3.341344E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.854 | TFLOPs: 28.07 | +7: iteration 26770/ 37905 | consumed samples: 6853120 | consumed tokens: 14035189760 | elapsed time per iteration (s): 0.23 | learning rate: 5.635E-05 | global batch size: 256 | lm loss: 3.344095E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.206 | TFLOPs: 28.05 | +7: iteration 26780/ 37905 | consumed samples: 6855680 | consumed tokens: 14040432640 | elapsed time per iteration (s): 0.23 | learning rate: 5.629E-05 | global batch size: 256 | lm loss: 3.351318E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.672 | TFLOPs: 28.14 | +7: iteration 26790/ 37905 | consumed samples: 6858240 | consumed tokens: 14045675520 | elapsed time per iteration (s): 0.23 | learning rate: 5.623E-05 | global batch size: 256 | lm loss: 3.310812E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.161 | TFLOPs: 28.46 | +7: iteration 26800/ 37905 | consumed samples: 6860800 | consumed tokens: 14050918400 | elapsed time per iteration (s): 0.23 | learning rate: 5.617E-05 | global batch size: 256 | lm loss: 3.340653E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.733 | TFLOPs: 28.07 | +7: iteration 26810/ 37905 | consumed samples: 6863360 | consumed tokens: 14056161280 | elapsed time per iteration (s): 0.25 | learning rate: 5.611E-05 | global batch size: 256 | lm loss: 3.330215E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1035.277 | TFLOPs: 26.37 | +7: iteration 26820/ 37905 | consumed samples: 6865920 | consumed tokens: 14061404160 | elapsed time per iteration (s): 0.23 | learning rate: 5.605E-05 | global batch size: 256 | lm loss: 3.314161E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.743 | TFLOPs: 28.42 | +7: iteration 26830/ 37905 | consumed samples: 6868480 | consumed tokens: 14066647040 | elapsed time per iteration (s): 0.23 | learning rate: 5.599E-05 | global batch size: 256 | lm loss: 3.349836E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.500 | TFLOPs: 28.49 | +7: iteration 26840/ 37905 | consumed samples: 6871040 | consumed tokens: 14071889920 | elapsed time per iteration (s): 0.23 | learning rate: 5.593E-05 | global batch size: 256 | lm loss: 3.321482E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.196 | TFLOPs: 28.44 | +7: iteration 26850/ 37905 | consumed samples: 6873600 | consumed tokens: 14077132800 | elapsed time per iteration (s): 0.23 | learning rate: 5.587E-05 | global batch size: 256 | lm loss: 3.341730E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.511 | TFLOPs: 28.44 | +7: iteration 26860/ 37905 | consumed samples: 6876160 | consumed tokens: 14082375680 | elapsed time per iteration (s): 0.23 | learning rate: 5.581E-05 | global batch size: 256 | lm loss: 3.332537E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.691 | TFLOPs: 28.42 | +7: iteration 26870/ 37905 | consumed samples: 6878720 | consumed tokens: 14087618560 | elapsed time per iteration (s): 0.23 | learning rate: 5.575E-05 | global batch size: 256 | lm loss: 3.369290E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.070 | TFLOPs: 27.82 | +7: iteration 26880/ 37905 | consumed samples: 6881280 | consumed tokens: 14092861440 | elapsed time per iteration (s): 0.23 | learning rate: 5.569E-05 | global batch size: 256 | lm loss: 3.329741E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.825 | TFLOPs: 28.53 | +7: iteration 26890/ 37905 | consumed samples: 6883840 | consumed tokens: 14098104320 | elapsed time per iteration (s): 0.23 | learning rate: 5.563E-05 | global batch size: 256 | lm loss: 3.332217E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.479 | TFLOPs: 28.26 | +7: iteration 26900/ 37905 | consumed samples: 6886400 | consumed tokens: 14103347200 | elapsed time per iteration (s): 0.23 | learning rate: 5.557E-05 | global batch size: 256 | lm loss: 3.366449E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.954 | TFLOPs: 28.51 | +7: iteration 26910/ 37905 | consumed samples: 6888960 | consumed tokens: 14108590080 | elapsed time per iteration (s): 0.23 | learning rate: 5.551E-05 | global batch size: 256 | lm loss: 3.328843E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.207 | TFLOPs: 28.51 | +7: iteration 26920/ 37905 | consumed samples: 6891520 | consumed tokens: 14113832960 | elapsed time per iteration (s): 0.23 | learning rate: 5.545E-05 | global batch size: 256 | lm loss: 3.360895E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.414 | TFLOPs: 28.52 | +7: iteration 26930/ 37905 | consumed samples: 6894080 | consumed tokens: 14119075840 | elapsed time per iteration (s): 0.23 | learning rate: 5.539E-05 | global batch size: 256 | lm loss: 3.374997E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.089 | TFLOPs: 28.41 | +7: iteration 26940/ 37905 | consumed samples: 6896640 | consumed tokens: 14124318720 | elapsed time per iteration (s): 0.23 | learning rate: 5.533E-05 | global batch size: 256 | lm loss: 3.329552E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.796 | TFLOPs: 28.40 | +7: iteration 26950/ 37905 | consumed samples: 6899200 | consumed tokens: 14129561600 | elapsed time per iteration (s): 0.23 | learning rate: 5.527E-05 | global batch size: 256 | lm loss: 3.356467E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.745 | TFLOPs: 28.45 | +7: iteration 26960/ 37905 | consumed samples: 6901760 | consumed tokens: 14134804480 | elapsed time per iteration (s): 0.23 | learning rate: 5.521E-05 | global batch size: 256 | lm loss: 3.334298E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.526 | TFLOPs: 28.29 | +7: iteration 26970/ 37905 | consumed samples: 6904320 | consumed tokens: 14140047360 | elapsed time per iteration (s): 0.23 | learning rate: 5.515E-05 | global batch size: 256 | lm loss: 3.316142E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.652 | TFLOPs: 28.17 | +7: iteration 26980/ 37905 | consumed samples: 6906880 | consumed tokens: 14145290240 | elapsed time per iteration (s): 0.25 | learning rate: 5.509E-05 | global batch size: 256 | lm loss: 3.321652E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1023.073 | TFLOPs: 26.06 | +7: iteration 26990/ 37905 | consumed samples: 6909440 | consumed tokens: 14150533120 | elapsed time per iteration (s): 0.23 | learning rate: 5.503E-05 | global batch size: 256 | lm loss: 3.332732E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.676 | TFLOPs: 28.17 | +7: iteration 27000/ 37905 | consumed samples: 6912000 | consumed tokens: 14155776000 | elapsed time per iteration (s): 0.23 | learning rate: 5.497E-05 | global batch size: 256 | lm loss: 3.319374E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.177 | TFLOPs: 28.00 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 27000 | lm loss value: 3.185436E+00 | lm loss PPL: 2.417782E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 27000 to checkpoints_83moscar +0: [2022-11-29 18:42:58,223] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step27000 is begin to save! +0: [2022-11-29 18:42:58,227] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:42:58,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:42:58,305] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:42:58,319] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:42:58,320] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:42:58,331] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:42:58,331] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:42:58,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:42:58,343] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:42:58,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:42:58,355] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:42:58,366] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:42:58,367] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:42:58,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:42:58,378] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:42:58,390] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:42:58,390] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:42:58,401] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:42:58,401] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:42:58,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:42:58,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:42:58,424] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:42:58,424] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:42:58,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:42:58,426] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step27000/mp_rank_00_model_states.pt +0: [2022-11-29 18:42:58,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:42:58,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:42:58,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:42:58,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:42:58,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:42:58,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:42:58,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:42:58,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:42:58,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:42:58,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:42:58,445] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:42:58,464] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:42:58,464] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:42:58,464] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:42:58,464] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +3: [2022-11-29 18:42:58,464] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +0: [2022-11-29 18:42:58,464] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:42:58,464] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +5: [2022-11-29 18:42:58,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:42:58,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:42:58,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +7: [2022-11-29 18:42:58,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:42:58,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:42:58,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +1: [2022-11-29 18:42:58,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:42:58,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:42:58,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +2: [2022-11-29 18:42:58,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:42:58,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:42:58,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +4: [2022-11-29 18:42:58,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:42:58,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:42:58,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +7: [2022-11-29 18:42:58,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:42:58,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:42:58,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +6: [2022-11-29 18:42:58,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:42:58,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:42:58,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +0: [2022-11-29 18:42:58,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:42:58,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +0: [2022-11-29 18:42:58,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:42:58,467] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:42:58,467] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +1: [2022-11-29 18:42:58,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:42:58,467] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:42:58,467] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +2: [2022-11-29 18:42:58,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:42:58,467] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:42:58,467] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +3: [2022-11-29 18:42:58,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:42:58,467] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:42:58,467] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +5: [2022-11-29 18:42:58,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:42:58,467] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:42:58,467] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +7: [2022-11-29 18:42:58,468] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:42:58,468] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:42:58,468] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +4: [2022-11-29 18:42:58,468] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:42:58,469] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:42:58,469] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +3: [2022-11-29 18:42:58,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:42:58,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:42:58,469] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +5: [2022-11-29 18:42:58,469] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +3: [2022-11-29 18:42:58,469] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +5: [2022-11-29 18:42:58,469] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +6: [2022-11-29 18:42:58,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:42:58,469] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:42:58,469] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +2: [2022-11-29 18:42:58,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:42:58,469] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +6: [2022-11-29 18:42:58,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:42:58,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:42:58,469] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +2: [2022-11-29 18:42:58,469] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +6: [2022-11-29 18:42:58,469] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +5: [2022-11-29 18:42:58,469] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +7: [2022-11-29 18:42:58,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:42:58,469] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +7: [2022-11-29 18:42:58,469] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:42:58,469] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +1: [2022-11-29 18:42:58,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:42:58,470] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:42:58,470] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +0: [2022-11-29 18:42:58,470] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:42:58,470] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:42:58,470] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:42:58,470] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:42:58,470] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +0: [2022-11-29 18:42:58,470] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +4: [2022-11-29 18:42:58,470] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:42:58,470] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:42:58,470] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:42:58,470] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +2: [2022-11-29 18:42:58,470] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:42:58,470] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +3: [2022-11-29 18:42:58,470] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:42:58,470] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:42:58,470] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +7: [2022-11-29 18:42:58,470] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +3: [2022-11-29 18:42:58,470] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +6: [2022-11-29 18:42:58,470] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:42:58,470] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +6: [2022-11-29 18:42:58,470] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:42:58,470] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +0: [2022-11-29 18:42:58,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:42:58,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +4: [2022-11-29 18:42:58,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:42:58,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +4: [2022-11-29 18:42:58,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:42:58,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +1: [2022-11-29 18:42:58,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:42:58,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:42:58,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:42:58,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:42:58,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +1: [2022-11-29 18:42:58,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +7: [2022-11-29 18:42:58,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:42:58,472] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:42:58,472] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +3: [2022-11-29 18:42:58,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:42:58,472] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:42:58,472] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +0: [2022-11-29 18:42:58,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:42:58,472] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:42:58,472] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +2: [2022-11-29 18:42:58,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:42:58,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:42:58,472] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:42:58,472] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:42:58,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +2: [2022-11-29 18:42:58,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +6: [2022-11-29 18:42:58,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:42:58,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:42:58,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:42:58,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:42:58,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +4: [2022-11-29 18:42:58,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:42:58,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:42:58,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +3: [2022-11-29 18:42:58,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:42:58,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +5: [2022-11-29 18:42:58,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +4: [2022-11-29 18:42:58,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +3: [2022-11-29 18:42:58,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +1: [2022-11-29 18:42:58,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:42:58,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +3: [2022-11-29 18:42:58,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +1: [2022-11-29 18:42:58,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:42:58,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +3: [2022-11-29 18:42:58,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:42:58,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:42:58,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +6: [2022-11-29 18:42:58,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:42:58,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:42:58,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +0: [2022-11-29 18:42:58,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:42:58,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:42:58,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +6: [2022-11-29 18:42:58,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:42:58,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:42:58,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +4: [2022-11-29 18:42:58,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:42:58,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:42:58,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +7: [2022-11-29 18:42:58,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:42:58,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +4: [2022-11-29 18:42:58,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:42:58,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +4: [2022-11-29 18:42:58,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:42:58,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +3: [2022-11-29 18:42:58,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:42:58,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:42:58,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +7: [2022-11-29 18:42:58,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:42:58,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:42:58,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +5: [2022-11-29 18:42:58,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +1: [2022-11-29 18:42:58,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:42:58,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:42:58,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +5: [2022-11-29 18:42:58,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +1: [2022-11-29 18:42:58,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +2: [2022-11-29 18:42:58,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:42:58,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +1: [2022-11-29 18:42:58,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +6: [2022-11-29 18:42:58,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:42:58,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:42:58,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +2: [2022-11-29 18:42:58,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +6: [2022-11-29 18:42:58,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +2: [2022-11-29 18:42:58,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +1: [2022-11-29 18:42:58,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:42:58,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +5: [2022-11-29 18:42:58,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:42:58,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +5: [2022-11-29 18:42:58,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:42:58,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +0: [2022-11-29 18:42:58,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:42:58,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step27000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:42:58,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +0: successfully saved checkpoint at iteration 27000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 255.38 +7: iteration 27010/ 37905 | consumed samples: 6914560 | consumed tokens: 14161018880 | elapsed time per iteration (s): 0.26 | learning rate: 5.491E-05 | global batch size: 256 | lm loss: 3.329903E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 979.716 | TFLOPs: 24.96 | +7: iteration 27020/ 37905 | consumed samples: 6917120 | consumed tokens: 14166261760 | elapsed time per iteration (s): 0.23 | learning rate: 5.485E-05 | global batch size: 256 | lm loss: 3.313580E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.090 | TFLOPs: 28.43 | +7: iteration 27030/ 37905 | consumed samples: 6919680 | consumed tokens: 14171504640 | elapsed time per iteration (s): 0.23 | learning rate: 5.479E-05 | global batch size: 256 | lm loss: 3.320103E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.458 | TFLOPs: 28.19 | +7: iteration 27040/ 37905 | consumed samples: 6922240 | consumed tokens: 14176747520 | elapsed time per iteration (s): 0.23 | learning rate: 5.473E-05 | global batch size: 256 | lm loss: 3.338741E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.446 | TFLOPs: 28.42 | +7: iteration 27050/ 37905 | consumed samples: 6924800 | consumed tokens: 14181990400 | elapsed time per iteration (s): 0.23 | learning rate: 5.467E-05 | global batch size: 256 | lm loss: 3.287562E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.734 | TFLOPs: 28.42 | +7: iteration 27060/ 37905 | consumed samples: 6927360 | consumed tokens: 14187233280 | elapsed time per iteration (s): 0.24 | learning rate: 5.462E-05 | global batch size: 256 | lm loss: 3.369817E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1068.057 | TFLOPs: 27.21 | +7: iteration 27070/ 37905 | consumed samples: 6929920 | consumed tokens: 14192476160 | elapsed time per iteration (s): 0.23 | learning rate: 5.456E-05 | global batch size: 256 | lm loss: 3.345789E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.747 | TFLOPs: 28.42 | +7: iteration 27080/ 37905 | consumed samples: 6932480 | consumed tokens: 14197719040 | elapsed time per iteration (s): 0.23 | learning rate: 5.450E-05 | global batch size: 256 | lm loss: 3.300394E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.579 | TFLOPs: 27.76 | +7: iteration 27090/ 37905 | consumed samples: 6935040 | consumed tokens: 14202961920 | elapsed time per iteration (s): 0.23 | learning rate: 5.444E-05 | global batch size: 256 | lm loss: 3.344017E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.294 | TFLOPs: 28.44 | +7: iteration 27100/ 37905 | consumed samples: 6937600 | consumed tokens: 14208204800 | elapsed time per iteration (s): 0.23 | learning rate: 5.438E-05 | global batch size: 256 | lm loss: 3.317552E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.199 | TFLOPs: 28.33 | +7: iteration 27110/ 37905 | consumed samples: 6940160 | consumed tokens: 14213447680 | elapsed time per iteration (s): 0.23 | learning rate: 5.432E-05 | global batch size: 256 | lm loss: 3.359234E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.172 | TFLOPs: 28.51 | +7: iteration 27120/ 37905 | consumed samples: 6942720 | consumed tokens: 14218690560 | elapsed time per iteration (s): 0.23 | learning rate: 5.426E-05 | global batch size: 256 | lm loss: 3.358702E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.048 | TFLOPs: 28.46 | +7: iteration 27130/ 37905 | consumed samples: 6945280 | consumed tokens: 14223933440 | elapsed time per iteration (s): 0.23 | learning rate: 5.420E-05 | global batch size: 256 | lm loss: 3.332275E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.911 | TFLOPs: 28.25 | +7: iteration 27140/ 37905 | consumed samples: 6947840 | consumed tokens: 14229176320 | elapsed time per iteration (s): 0.23 | learning rate: 5.414E-05 | global batch size: 256 | lm loss: 3.322939E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.189 | TFLOPs: 28.05 | +7: iteration 27150/ 37905 | consumed samples: 6950400 | consumed tokens: 14234419200 | elapsed time per iteration (s): 0.24 | learning rate: 5.408E-05 | global batch size: 256 | lm loss: 3.332854E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1071.713 | TFLOPs: 27.30 | +7: iteration 27160/ 37905 | consumed samples: 6952960 | consumed tokens: 14239662080 | elapsed time per iteration (s): 0.23 | learning rate: 5.402E-05 | global batch size: 256 | lm loss: 3.326682E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.514 | TFLOPs: 28.34 | +7: iteration 27170/ 37905 | consumed samples: 6955520 | consumed tokens: 14244904960 | elapsed time per iteration (s): 0.24 | learning rate: 5.396E-05 | global batch size: 256 | lm loss: 3.343607E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1063.217 | TFLOPs: 27.09 | +7: iteration 27180/ 37905 | consumed samples: 6958080 | consumed tokens: 14250147840 | elapsed time per iteration (s): 0.23 | learning rate: 5.391E-05 | global batch size: 256 | lm loss: 3.311249E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.570 | TFLOPs: 28.34 | +7: iteration 27190/ 37905 | consumed samples: 6960640 | consumed tokens: 14255390720 | elapsed time per iteration (s): 0.23 | learning rate: 5.385E-05 | global batch size: 256 | lm loss: 3.356969E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.456 | TFLOPs: 28.47 | +7: iteration 27200/ 37905 | consumed samples: 6963200 | consumed tokens: 14260633600 | elapsed time per iteration (s): 0.23 | learning rate: 5.379E-05 | global batch size: 256 | lm loss: 3.324480E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.669 | TFLOPs: 28.47 | +7: iteration 27210/ 37905 | consumed samples: 6965760 | consumed tokens: 14265876480 | elapsed time per iteration (s): 0.23 | learning rate: 5.373E-05 | global batch size: 256 | lm loss: 3.327851E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.771 | TFLOPs: 28.42 | +7: iteration 27220/ 37905 | consumed samples: 6968320 | consumed tokens: 14271119360 | elapsed time per iteration (s): 0.23 | learning rate: 5.367E-05 | global batch size: 256 | lm loss: 3.326224E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.831 | TFLOPs: 28.50 | +7: iteration 27230/ 37905 | consumed samples: 6970880 | consumed tokens: 14276362240 | elapsed time per iteration (s): 0.23 | learning rate: 5.361E-05 | global batch size: 256 | lm loss: 3.330311E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.879 | TFLOPs: 28.58 | +7: iteration 27240/ 37905 | consumed samples: 6973440 | consumed tokens: 14281605120 | elapsed time per iteration (s): 0.23 | learning rate: 5.355E-05 | global batch size: 256 | lm loss: 3.341942E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.260 | TFLOPs: 28.54 | +7: iteration 27250/ 37905 | consumed samples: 6976000 | consumed tokens: 14286848000 | elapsed time per iteration (s): 0.23 | learning rate: 5.349E-05 | global batch size: 256 | lm loss: 3.341048E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.132 | TFLOPs: 28.59 | +7: iteration 27260/ 37905 | consumed samples: 6978560 | consumed tokens: 14292090880 | elapsed time per iteration (s): 0.23 | learning rate: 5.344E-05 | global batch size: 256 | lm loss: 3.328778E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.769 | TFLOPs: 28.45 | +7: iteration 27270/ 37905 | consumed samples: 6981120 | consumed tokens: 14297333760 | elapsed time per iteration (s): 0.23 | learning rate: 5.338E-05 | global batch size: 256 | lm loss: 3.335768E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.991 | TFLOPs: 28.58 | +7: iteration 27280/ 37905 | consumed samples: 6983680 | consumed tokens: 14302576640 | elapsed time per iteration (s): 0.23 | learning rate: 5.332E-05 | global batch size: 256 | lm loss: 3.320302E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.329 | TFLOPs: 28.49 | +7: iteration 27290/ 37905 | consumed samples: 6986240 | consumed tokens: 14307819520 | elapsed time per iteration (s): 0.23 | learning rate: 5.326E-05 | global batch size: 256 | lm loss: 3.325516E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.848 | TFLOPs: 28.53 | +7: iteration 27300/ 37905 | consumed samples: 6988800 | consumed tokens: 14313062400 | elapsed time per iteration (s): 0.23 | learning rate: 5.320E-05 | global batch size: 256 | lm loss: 3.374168E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.731 | TFLOPs: 28.25 | +7: iteration 27310/ 37905 | consumed samples: 6991360 | consumed tokens: 14318305280 | elapsed time per iteration (s): 0.23 | learning rate: 5.314E-05 | global batch size: 256 | lm loss: 3.328127E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.870 | TFLOPs: 28.45 | +7: iteration 27320/ 37905 | consumed samples: 6993920 | consumed tokens: 14323548160 | elapsed time per iteration (s): 0.23 | learning rate: 5.308E-05 | global batch size: 256 | lm loss: 3.316466E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.445 | TFLOPs: 28.39 | +7: iteration 27330/ 37905 | consumed samples: 6996480 | consumed tokens: 14328791040 | elapsed time per iteration (s): 0.23 | learning rate: 5.303E-05 | global batch size: 256 | lm loss: 3.350837E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.777 | TFLOPs: 28.48 | +7: iteration 27340/ 37905 | consumed samples: 6999040 | consumed tokens: 14334033920 | elapsed time per iteration (s): 0.23 | learning rate: 5.297E-05 | global batch size: 256 | lm loss: 3.331646E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.987 | TFLOPs: 28.35 | +7: iteration 27350/ 37905 | consumed samples: 7001600 | consumed tokens: 14339276800 | elapsed time per iteration (s): 0.23 | learning rate: 5.291E-05 | global batch size: 256 | lm loss: 3.322880E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.710 | TFLOPs: 28.35 | +7: iteration 27360/ 37905 | consumed samples: 7004160 | consumed tokens: 14344519680 | elapsed time per iteration (s): 0.23 | learning rate: 5.285E-05 | global batch size: 256 | lm loss: 3.340531E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.003 | TFLOPs: 28.23 | +7: iteration 27370/ 37905 | consumed samples: 7006720 | consumed tokens: 14349762560 | elapsed time per iteration (s): 0.23 | learning rate: 5.279E-05 | global batch size: 256 | lm loss: 3.356922E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.042 | TFLOPs: 27.85 | +7: iteration 27380/ 37905 | consumed samples: 7009280 | consumed tokens: 14355005440 | elapsed time per iteration (s): 0.23 | learning rate: 5.274E-05 | global batch size: 256 | lm loss: 3.298418E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.415 | TFLOPs: 28.31 | +7: iteration 27390/ 37905 | consumed samples: 7011840 | consumed tokens: 14360248320 | elapsed time per iteration (s): 0.23 | learning rate: 5.268E-05 | global batch size: 256 | lm loss: 3.380074E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.987 | TFLOPs: 28.35 | +7: iteration 27400/ 37905 | consumed samples: 7014400 | consumed tokens: 14365491200 | elapsed time per iteration (s): 0.23 | learning rate: 5.262E-05 | global batch size: 256 | lm loss: 3.373131E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.887 | TFLOPs: 28.12 | +7: iteration 27410/ 37905 | consumed samples: 7016960 | consumed tokens: 14370734080 | elapsed time per iteration (s): 0.23 | learning rate: 5.256E-05 | global batch size: 256 | lm loss: 3.340089E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.703 | TFLOPs: 28.58 | +7: iteration 27420/ 37905 | consumed samples: 7019520 | consumed tokens: 14375976960 | elapsed time per iteration (s): 0.23 | learning rate: 5.250E-05 | global batch size: 256 | lm loss: 3.330659E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.634 | TFLOPs: 28.50 | +7: iteration 27430/ 37905 | consumed samples: 7022080 | consumed tokens: 14381219840 | elapsed time per iteration (s): 0.23 | learning rate: 5.245E-05 | global batch size: 256 | lm loss: 3.337642E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.635 | TFLOPs: 28.52 | +7: iteration 27440/ 37905 | consumed samples: 7024640 | consumed tokens: 14386462720 | elapsed time per iteration (s): 0.23 | learning rate: 5.239E-05 | global batch size: 256 | lm loss: 3.327670E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.157 | TFLOPs: 28.41 | +7: iteration 27450/ 37905 | consumed samples: 7027200 | consumed tokens: 14391705600 | elapsed time per iteration (s): 0.24 | learning rate: 5.233E-05 | global batch size: 256 | lm loss: 3.305205E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1065.049 | TFLOPs: 27.13 | +7: iteration 27460/ 37905 | consumed samples: 7029760 | consumed tokens: 14396948480 | elapsed time per iteration (s): 0.25 | learning rate: 5.227E-05 | global batch size: 256 | lm loss: 3.342260E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1024.041 | TFLOPs: 26.09 | +7: iteration 27470/ 37905 | consumed samples: 7032320 | consumed tokens: 14402191360 | elapsed time per iteration (s): 0.23 | learning rate: 5.221E-05 | global batch size: 256 | lm loss: 3.312442E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.693 | TFLOPs: 28.35 | +7: iteration 27480/ 37905 | consumed samples: 7034880 | consumed tokens: 14407434240 | elapsed time per iteration (s): 0.23 | learning rate: 5.216E-05 | global batch size: 256 | lm loss: 3.352988E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.776 | TFLOPs: 28.45 | +7: iteration 27490/ 37905 | consumed samples: 7037440 | consumed tokens: 14412677120 | elapsed time per iteration (s): 0.23 | learning rate: 5.210E-05 | global batch size: 256 | lm loss: 3.318932E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.210 | TFLOPs: 28.54 | +7: iteration 27500/ 37905 | consumed samples: 7040000 | consumed tokens: 14417920000 | elapsed time per iteration (s): 0.23 | learning rate: 5.204E-05 | global batch size: 256 | lm loss: 3.308391E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.550 | TFLOPs: 28.37 | +7: iteration 27510/ 37905 | consumed samples: 7042560 | consumed tokens: 14423162880 | elapsed time per iteration (s): 0.23 | learning rate: 5.198E-05 | global batch size: 256 | lm loss: 3.337313E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.548 | TFLOPs: 28.39 | +7: iteration 27520/ 37905 | consumed samples: 7045120 | consumed tokens: 14428405760 | elapsed time per iteration (s): 0.23 | learning rate: 5.193E-05 | global batch size: 256 | lm loss: 3.329768E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.132 | TFLOPs: 28.26 | +7: iteration 27530/ 37905 | consumed samples: 7047680 | consumed tokens: 14433648640 | elapsed time per iteration (s): 0.24 | learning rate: 5.187E-05 | global batch size: 256 | lm loss: 3.315791E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1076.992 | TFLOPs: 27.44 | +7: iteration 27540/ 37905 | consumed samples: 7050240 | consumed tokens: 14438891520 | elapsed time per iteration (s): 0.23 | learning rate: 5.181E-05 | global batch size: 256 | lm loss: 3.324940E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.225 | TFLOPs: 28.31 | +7: iteration 27550/ 37905 | consumed samples: 7052800 | consumed tokens: 14444134400 | elapsed time per iteration (s): 0.23 | learning rate: 5.175E-05 | global batch size: 256 | lm loss: 3.334897E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.647 | TFLOPs: 28.52 | +7: iteration 27560/ 37905 | consumed samples: 7055360 | consumed tokens: 14449377280 | elapsed time per iteration (s): 0.23 | learning rate: 5.170E-05 | global batch size: 256 | lm loss: 3.347338E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.492 | TFLOPs: 28.39 | +7: iteration 27570/ 37905 | consumed samples: 7057920 | consumed tokens: 14454620160 | elapsed time per iteration (s): 0.23 | learning rate: 5.164E-05 | global batch size: 256 | lm loss: 3.321155E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.335 | TFLOPs: 28.39 | +7: iteration 27580/ 37905 | consumed samples: 7060480 | consumed tokens: 14459863040 | elapsed time per iteration (s): 0.23 | learning rate: 5.158E-05 | global batch size: 256 | lm loss: 3.308069E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.617 | TFLOPs: 28.22 | +7: iteration 27590/ 37905 | consumed samples: 7063040 | consumed tokens: 14465105920 | elapsed time per iteration (s): 0.23 | learning rate: 5.152E-05 | global batch size: 256 | lm loss: 3.322163E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.211 | TFLOPs: 28.36 | +7: iteration 27600/ 37905 | consumed samples: 7065600 | consumed tokens: 14470348800 | elapsed time per iteration (s): 0.23 | learning rate: 5.147E-05 | global batch size: 256 | lm loss: 3.325589E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.994 | TFLOPs: 28.25 | +7: iteration 27610/ 37905 | consumed samples: 7068160 | consumed tokens: 14475591680 | elapsed time per iteration (s): 0.23 | learning rate: 5.141E-05 | global batch size: 256 | lm loss: 3.354424E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.068 | TFLOPs: 28.46 | +7: iteration 27620/ 37905 | consumed samples: 7070720 | consumed tokens: 14480834560 | elapsed time per iteration (s): 0.23 | learning rate: 5.135E-05 | global batch size: 256 | lm loss: 3.330152E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.687 | TFLOPs: 28.40 | +7: iteration 27630/ 37905 | consumed samples: 7073280 | consumed tokens: 14486077440 | elapsed time per iteration (s): 0.24 | learning rate: 5.129E-05 | global batch size: 256 | lm loss: 3.312259E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1063.243 | TFLOPs: 27.09 | +7: iteration 27640/ 37905 | consumed samples: 7075840 | consumed tokens: 14491320320 | elapsed time per iteration (s): 0.23 | learning rate: 5.124E-05 | global batch size: 256 | lm loss: 3.327528E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.163 | TFLOPs: 28.38 | +7: iteration 27650/ 37905 | consumed samples: 7078400 | consumed tokens: 14496563200 | elapsed time per iteration (s): 0.23 | learning rate: 5.118E-05 | global batch size: 256 | lm loss: 3.339284E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.973 | TFLOPs: 28.51 | +7: iteration 27660/ 37905 | consumed samples: 7080960 | consumed tokens: 14501806080 | elapsed time per iteration (s): 0.23 | learning rate: 5.112E-05 | global batch size: 256 | lm loss: 3.333553E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.406 | TFLOPs: 28.47 | +7: iteration 27670/ 37905 | consumed samples: 7083520 | consumed tokens: 14507048960 | elapsed time per iteration (s): 0.23 | learning rate: 5.107E-05 | global batch size: 256 | lm loss: 3.313299E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.158 | TFLOPs: 28.36 | +7: iteration 27680/ 37905 | consumed samples: 7086080 | consumed tokens: 14512291840 | elapsed time per iteration (s): 0.23 | learning rate: 5.101E-05 | global batch size: 256 | lm loss: 3.310174E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.834 | TFLOPs: 28.32 | +7: iteration 27690/ 37905 | consumed samples: 7088640 | consumed tokens: 14517534720 | elapsed time per iteration (s): 0.23 | learning rate: 5.095E-05 | global batch size: 256 | lm loss: 3.327095E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.705 | TFLOPs: 28.37 | +7: iteration 27700/ 37905 | consumed samples: 7091200 | consumed tokens: 14522777600 | elapsed time per iteration (s): 0.23 | learning rate: 5.090E-05 | global batch size: 256 | lm loss: 3.341047E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.621 | TFLOPs: 28.22 | +7: iteration 27710/ 37905 | consumed samples: 7093760 | consumed tokens: 14528020480 | elapsed time per iteration (s): 0.25 | learning rate: 5.084E-05 | global batch size: 256 | lm loss: 3.339055E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1031.285 | TFLOPs: 26.27 | +7: iteration 27720/ 37905 | consumed samples: 7096320 | consumed tokens: 14533263360 | elapsed time per iteration (s): 0.23 | learning rate: 5.078E-05 | global batch size: 256 | lm loss: 3.355454E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.325 | TFLOPs: 28.49 | +7: iteration 27730/ 37905 | consumed samples: 7098880 | consumed tokens: 14538506240 | elapsed time per iteration (s): 0.23 | learning rate: 5.073E-05 | global batch size: 256 | lm loss: 3.337551E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.299 | TFLOPs: 28.16 | +7: iteration 27740/ 37905 | consumed samples: 7101440 | consumed tokens: 14543749120 | elapsed time per iteration (s): 0.23 | learning rate: 5.067E-05 | global batch size: 256 | lm loss: 3.322878E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.669 | TFLOPs: 28.40 | +7: iteration 27750/ 37905 | consumed samples: 7104000 | consumed tokens: 14548992000 | elapsed time per iteration (s): 0.23 | learning rate: 5.061E-05 | global batch size: 256 | lm loss: 3.341516E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.245 | TFLOPs: 28.33 | +7: iteration 27760/ 37905 | consumed samples: 7106560 | consumed tokens: 14554234880 | elapsed time per iteration (s): 0.23 | learning rate: 5.056E-05 | global batch size: 256 | lm loss: 3.334675E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.584 | TFLOPs: 28.47 | +7: iteration 27770/ 37905 | consumed samples: 7109120 | consumed tokens: 14559477760 | elapsed time per iteration (s): 0.23 | learning rate: 5.050E-05 | global batch size: 256 | lm loss: 3.320154E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.123 | TFLOPs: 28.51 | +7: iteration 27780/ 37905 | consumed samples: 7111680 | consumed tokens: 14564720640 | elapsed time per iteration (s): 0.23 | learning rate: 5.044E-05 | global batch size: 256 | lm loss: 3.340799E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.555 | TFLOPs: 28.42 | +7: iteration 27790/ 37905 | consumed samples: 7114240 | consumed tokens: 14569963520 | elapsed time per iteration (s): 0.23 | learning rate: 5.039E-05 | global batch size: 256 | lm loss: 3.322154E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.662 | TFLOPs: 28.45 | +7: iteration 27800/ 37905 | consumed samples: 7116800 | consumed tokens: 14575206400 | elapsed time per iteration (s): 0.23 | learning rate: 5.033E-05 | global batch size: 256 | lm loss: 3.328461E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.183 | TFLOPs: 28.51 | +7: iteration 27810/ 37905 | consumed samples: 7119360 | consumed tokens: 14580449280 | elapsed time per iteration (s): 0.23 | learning rate: 5.027E-05 | global batch size: 256 | lm loss: 3.316982E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.079 | TFLOPs: 28.43 | +7: iteration 27820/ 37905 | consumed samples: 7121920 | consumed tokens: 14585692160 | elapsed time per iteration (s): 0.24 | learning rate: 5.022E-05 | global batch size: 256 | lm loss: 3.335046E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1060.960 | TFLOPs: 27.03 | +7: iteration 27830/ 37905 | consumed samples: 7124480 | consumed tokens: 14590935040 | elapsed time per iteration (s): 0.23 | learning rate: 5.016E-05 | global batch size: 256 | lm loss: 3.319409E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.190 | TFLOPs: 28.33 | +7: iteration 27840/ 37905 | consumed samples: 7127040 | consumed tokens: 14596177920 | elapsed time per iteration (s): 0.23 | learning rate: 5.010E-05 | global batch size: 256 | lm loss: 3.324339E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.496 | TFLOPs: 28.49 | +7: iteration 27850/ 37905 | consumed samples: 7129600 | consumed tokens: 14601420800 | elapsed time per iteration (s): 0.23 | learning rate: 5.005E-05 | global batch size: 256 | lm loss: 3.336947E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.438 | TFLOPs: 28.11 | +7: iteration 27860/ 37905 | consumed samples: 7132160 | consumed tokens: 14606663680 | elapsed time per iteration (s): 0.23 | learning rate: 4.999E-05 | global batch size: 256 | lm loss: 3.344879E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.713 | TFLOPs: 28.47 | +7: iteration 27870/ 37905 | consumed samples: 7134720 | consumed tokens: 14611906560 | elapsed time per iteration (s): 0.23 | learning rate: 4.994E-05 | global batch size: 256 | lm loss: 3.334631E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.044 | TFLOPs: 28.18 | +7: iteration 27880/ 37905 | consumed samples: 7137280 | consumed tokens: 14617149440 | elapsed time per iteration (s): 0.23 | learning rate: 4.988E-05 | global batch size: 256 | lm loss: 3.356056E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.328 | TFLOPs: 28.41 | +7: iteration 27890/ 37905 | consumed samples: 7139840 | consumed tokens: 14622392320 | elapsed time per iteration (s): 0.23 | learning rate: 4.982E-05 | global batch size: 256 | lm loss: 3.335598E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.889 | TFLOPs: 28.17 | +7: iteration 27900/ 37905 | consumed samples: 7142400 | consumed tokens: 14627635200 | elapsed time per iteration (s): 0.23 | learning rate: 4.977E-05 | global batch size: 256 | lm loss: 3.335187E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.928 | TFLOPs: 28.43 | +7: iteration 27910/ 37905 | consumed samples: 7144960 | consumed tokens: 14632878080 | elapsed time per iteration (s): 0.23 | learning rate: 4.971E-05 | global batch size: 256 | lm loss: 3.323050E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.220 | TFLOPs: 28.08 | +7: iteration 27920/ 37905 | consumed samples: 7147520 | consumed tokens: 14638120960 | elapsed time per iteration (s): 0.23 | learning rate: 4.966E-05 | global batch size: 256 | lm loss: 3.337058E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.341 | TFLOPs: 28.44 | +7: iteration 27930/ 37905 | consumed samples: 7150080 | consumed tokens: 14643363840 | elapsed time per iteration (s): 0.23 | learning rate: 4.960E-05 | global batch size: 256 | lm loss: 3.336311E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.755 | TFLOPs: 28.42 | +7: iteration 27940/ 37905 | consumed samples: 7152640 | consumed tokens: 14648606720 | elapsed time per iteration (s): 0.23 | learning rate: 4.954E-05 | global batch size: 256 | lm loss: 3.318068E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.299 | TFLOPs: 28.46 | +7: iteration 27950/ 37905 | consumed samples: 7155200 | consumed tokens: 14653849600 | elapsed time per iteration (s): 0.23 | learning rate: 4.949E-05 | global batch size: 256 | lm loss: 3.344954E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.508 | TFLOPs: 28.49 | +7: iteration 27960/ 37905 | consumed samples: 7157760 | consumed tokens: 14659092480 | elapsed time per iteration (s): 0.23 | learning rate: 4.943E-05 | global batch size: 256 | lm loss: 3.335496E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.060 | TFLOPs: 28.51 | +7: iteration 27970/ 37905 | consumed samples: 7160320 | consumed tokens: 14664335360 | elapsed time per iteration (s): 0.23 | learning rate: 4.938E-05 | global batch size: 256 | lm loss: 3.365319E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.698 | TFLOPs: 28.47 | +7: iteration 27980/ 37905 | consumed samples: 7162880 | consumed tokens: 14669578240 | elapsed time per iteration (s): 0.23 | learning rate: 4.932E-05 | global batch size: 256 | lm loss: 3.323325E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.796 | TFLOPs: 28.48 | +7: iteration 27990/ 37905 | consumed samples: 7165440 | consumed tokens: 14674821120 | elapsed time per iteration (s): 0.23 | learning rate: 4.927E-05 | global batch size: 256 | lm loss: 3.328400E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.521 | TFLOPs: 28.47 | +0: [2022-11-29 18:46:49,322] [INFO] [logging.py:68:log_dist] [Rank 0] step=28000, skipped=0, lr=[4.9210099955882125e-05, 4.9210099955882125e-05, 4.9210099955882125e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +0: steps: 28000 loss: 3.3144 iter time (s): 0.230 samples/sec: 1112.056 +7: iteration 28000/ 37905 | consumed samples: 7168000 | consumed tokens: 14680064000 | elapsed time per iteration (s): 0.23 | learning rate: 4.921E-05 | global batch size: 256 | lm loss: 3.322979E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.464 | TFLOPs: 28.44 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 28000 | lm loss value: 3.276991E+00 | lm loss PPL: 2.649592E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 28000 to checkpoints_83moscar +0: [2022-11-29 18:46:49,428] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step28000 is begin to save! +0: [2022-11-29 18:46:49,433] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:46:49,509] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:46:49,510] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:46:49,523] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:46:49,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:46:49,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:46:49,536] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:46:49,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:46:49,547] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:46:49,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:46:49,559] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:46:49,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:46:49,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:46:49,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:46:49,581] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:46:49,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:46:49,593] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:46:49,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:46:49,604] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:46:49,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:46:49,616] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:46:49,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:46:49,627] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:46:49,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:46:49,628] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step28000/mp_rank_00_model_states.pt +0: [2022-11-29 18:46:49,629] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:46:49,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:46:49,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:46:49,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:46:49,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:46:49,667] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:46:49,667] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +5: [2022-11-29 18:46:49,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:46:49,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:46:49,667] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +6: [2022-11-29 18:46:49,667] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +5: [2022-11-29 18:46:49,667] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +6: [2022-11-29 18:46:49,668] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +7: [2022-11-29 18:46:49,668] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:46:49,668] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:46:49,668] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +5: [2022-11-29 18:46:49,668] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +7: [2022-11-29 18:46:49,668] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +5: [2022-11-29 18:46:49,668] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +3: [2022-11-29 18:46:49,668] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:46:49,668] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:46:49,668] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +2: [2022-11-29 18:46:49,668] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:46:49,668] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:46:49,668] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +1: [2022-11-29 18:46:49,668] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:46:49,668] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +0: [2022-11-29 18:46:49,668] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +1: [2022-11-29 18:46:49,669] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +0: [2022-11-29 18:46:49,669] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +3: [2022-11-29 18:46:49,669] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:46:49,669] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +7: [2022-11-29 18:46:49,669] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:46:49,669] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +7: [2022-11-29 18:46:49,669] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:46:49,669] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +0: [2022-11-29 18:46:49,669] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:46:49,669] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +4: [2022-11-29 18:46:49,669] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:46:49,669] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +4: [2022-11-29 18:46:49,669] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:46:49,669] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +6: [2022-11-29 18:46:49,669] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:46:49,669] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:46:49,669] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:46:49,670] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +2: [2022-11-29 18:46:49,669] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:46:49,670] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +2: [2022-11-29 18:46:49,670] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +6: [2022-11-29 18:46:49,670] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +2: [2022-11-29 18:46:49,670] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +1: [2022-11-29 18:46:49,670] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +2: [2022-11-29 18:46:49,670] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +2: [2022-11-29 18:46:49,670] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +7: [2022-11-29 18:46:49,670] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:46:49,670] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:46:49,670] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +5: [2022-11-29 18:46:49,670] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +3: [2022-11-29 18:46:49,670] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:46:49,670] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +5: [2022-11-29 18:46:49,670] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +3: [2022-11-29 18:46:49,670] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:46:49,670] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +6: [2022-11-29 18:46:49,670] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:46:49,670] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:46:49,670] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:46:49,670] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +4: [2022-11-29 18:46:49,670] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:46:49,670] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +0: [2022-11-29 18:46:49,670] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:46:49,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:46:49,671] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +5: [2022-11-29 18:46:49,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:46:49,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:46:49,671] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +1: [2022-11-29 18:46:49,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:46:49,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:46:49,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +6: [2022-11-29 18:46:49,672] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:46:49,672] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:46:49,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +7: [2022-11-29 18:46:49,672] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:46:49,672] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:46:49,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +3: [2022-11-29 18:46:49,672] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:46:49,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +4: [2022-11-29 18:46:49,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:46:49,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +4: [2022-11-29 18:46:49,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:46:49,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +3: [2022-11-29 18:46:49,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:46:49,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:46:49,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +0: [2022-11-29 18:46:49,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:46:49,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:46:49,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +0: [2022-11-29 18:46:49,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:46:49,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:46:49,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +2: [2022-11-29 18:46:49,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:46:49,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:46:49,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +1: [2022-11-29 18:46:49,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:46:49,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:46:49,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +7: [2022-11-29 18:46:49,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:46:49,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:46:49,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +7: [2022-11-29 18:46:49,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +1: [2022-11-29 18:46:49,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:46:49,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +7: [2022-11-29 18:46:49,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +1: [2022-11-29 18:46:49,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:46:49,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +4: [2022-11-29 18:46:49,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:46:49,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:46:49,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +5: [2022-11-29 18:46:49,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:46:49,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:46:49,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +3: [2022-11-29 18:46:49,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:46:49,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:46:49,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +6: [2022-11-29 18:46:49,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:46:49,675] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:46:49,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +0: [2022-11-29 18:46:49,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:46:49,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:46:49,675] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:46:49,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +7: [2022-11-29 18:46:49,675] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +5: [2022-11-29 18:46:49,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:46:49,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +5: [2022-11-29 18:46:49,675] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:46:49,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +4: [2022-11-29 18:46:49,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:46:49,675] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 18:46:49,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +6: [2022-11-29 18:46:49,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:46:49,675] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:46:49,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +5: [2022-11-29 18:46:49,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:46:49,675] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:46:49,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +2: [2022-11-29 18:46:49,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:46:49,676] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:46:49,676] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +1: [2022-11-29 18:46:49,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:46:49,676] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:46:49,676] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +1: [2022-11-29 18:46:49,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:46:49,676] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:46:49,676] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +6: [2022-11-29 18:46:49,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:46:49,676] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:46:49,676] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +0: [2022-11-29 18:46:49,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:46:49,677] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:46:49,677] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +2: [2022-11-29 18:46:49,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:46:49,677] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +7: [2022-11-29 18:46:49,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:46:49,677] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +7: [2022-11-29 18:46:49,677] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 18:46:49,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:46:49,677] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +7: [2022-11-29 18:46:49,677] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:46:49,677] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +4: [2022-11-29 18:46:49,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:46:49,677] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:46:49,677] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +5: [2022-11-29 18:46:49,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:46:49,677] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:46:49,677] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +6: [2022-11-29 18:46:49,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:46:49,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:46:49,677] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:46:49,677] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +2: [2022-11-29 18:46:49,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:46:49,677] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +2: [2022-11-29 18:46:49,677] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +3: [2022-11-29 18:46:49,677] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +2: [2022-11-29 18:46:49,677] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +4: [2022-11-29 18:46:49,678] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:46:49,678] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:46:49,678] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +0: [2022-11-29 18:46:49,678] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +4: [2022-11-29 18:46:49,678] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +0: [2022-11-29 18:46:49,678] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +4: [2022-11-29 18:46:49,678] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:46:49,678] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:46:49,678] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +3: [2022-11-29 18:46:49,678] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:46:49,678] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step28000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:46:49,678] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +0: successfully saved checkpoint at iteration 28000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 268.24 +7: iteration 28010/ 37905 | consumed samples: 7170560 | consumed tokens: 14685306880 | elapsed time per iteration (s): 0.26 | learning rate: 4.915E-05 | global batch size: 256 | lm loss: 3.298883E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 968.130 | TFLOPs: 24.66 | +7: iteration 28020/ 37905 | consumed samples: 7173120 | consumed tokens: 14690549760 | elapsed time per iteration (s): 0.24 | learning rate: 4.910E-05 | global batch size: 256 | lm loss: 3.342070E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1083.465 | TFLOPs: 27.60 | +7: iteration 28030/ 37905 | consumed samples: 7175680 | consumed tokens: 14695792640 | elapsed time per iteration (s): 0.23 | learning rate: 4.904E-05 | global batch size: 256 | lm loss: 3.342849E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.994 | TFLOPs: 28.46 | +7: iteration 28040/ 37905 | consumed samples: 7178240 | consumed tokens: 14701035520 | elapsed time per iteration (s): 0.23 | learning rate: 4.899E-05 | global batch size: 256 | lm loss: 3.334898E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.925 | TFLOPs: 28.48 | +7: iteration 28050/ 37905 | consumed samples: 7180800 | consumed tokens: 14706278400 | elapsed time per iteration (s): 0.23 | learning rate: 4.893E-05 | global batch size: 256 | lm loss: 3.335248E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.833 | TFLOPs: 28.45 | +7: iteration 28060/ 37905 | consumed samples: 7183360 | consumed tokens: 14711521280 | elapsed time per iteration (s): 0.23 | learning rate: 4.888E-05 | global batch size: 256 | lm loss: 3.319196E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.849 | TFLOPs: 28.48 | +7: iteration 28070/ 37905 | consumed samples: 7185920 | consumed tokens: 14716764160 | elapsed time per iteration (s): 0.23 | learning rate: 4.882E-05 | global batch size: 256 | lm loss: 3.303857E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.959 | TFLOPs: 28.48 | +7: iteration 28080/ 37905 | consumed samples: 7188480 | consumed tokens: 14722007040 | elapsed time per iteration (s): 0.23 | learning rate: 4.877E-05 | global batch size: 256 | lm loss: 3.335880E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.887 | TFLOPs: 28.38 | +7: iteration 28090/ 37905 | consumed samples: 7191040 | consumed tokens: 14727249920 | elapsed time per iteration (s): 0.23 | learning rate: 4.871E-05 | global batch size: 256 | lm loss: 3.345077E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.877 | TFLOPs: 28.33 | +7: iteration 28100/ 37905 | consumed samples: 7193600 | consumed tokens: 14732492800 | elapsed time per iteration (s): 0.24 | learning rate: 4.866E-05 | global batch size: 256 | lm loss: 3.358077E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1054.056 | TFLOPs: 26.85 | +7: iteration 28110/ 37905 | consumed samples: 7196160 | consumed tokens: 14737735680 | elapsed time per iteration (s): 0.24 | learning rate: 4.860E-05 | global batch size: 256 | lm loss: 3.293698E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1055.947 | TFLOPs: 26.90 | +7: iteration 28120/ 37905 | consumed samples: 7198720 | consumed tokens: 14742978560 | elapsed time per iteration (s): 0.23 | learning rate: 4.855E-05 | global batch size: 256 | lm loss: 3.331175E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.797 | TFLOPs: 28.22 | +7: iteration 28130/ 37905 | consumed samples: 7201280 | consumed tokens: 14748221440 | elapsed time per iteration (s): 0.23 | learning rate: 4.849E-05 | global batch size: 256 | lm loss: 3.344231E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.551 | TFLOPs: 28.50 | +7: iteration 28140/ 37905 | consumed samples: 7203840 | consumed tokens: 14753464320 | elapsed time per iteration (s): 0.23 | learning rate: 4.844E-05 | global batch size: 256 | lm loss: 3.343051E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.133 | TFLOPs: 28.28 | +7: iteration 28150/ 37905 | consumed samples: 7206400 | consumed tokens: 14758707200 | elapsed time per iteration (s): 0.23 | learning rate: 4.838E-05 | global batch size: 256 | lm loss: 3.333601E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.949 | TFLOPs: 28.45 | +7: iteration 28160/ 37905 | consumed samples: 7208960 | consumed tokens: 14763950080 | elapsed time per iteration (s): 0.23 | learning rate: 4.833E-05 | global batch size: 256 | lm loss: 3.325675E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.804 | TFLOPs: 28.48 | +7: iteration 28170/ 37905 | consumed samples: 7211520 | consumed tokens: 14769192960 | elapsed time per iteration (s): 0.23 | learning rate: 4.827E-05 | global batch size: 256 | lm loss: 3.332154E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.803 | TFLOPs: 28.48 | +7: iteration 28180/ 37905 | consumed samples: 7214080 | consumed tokens: 14774435840 | elapsed time per iteration (s): 0.23 | learning rate: 4.822E-05 | global batch size: 256 | lm loss: 3.339156E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.043 | TFLOPs: 28.46 | +7: iteration 28190/ 37905 | consumed samples: 7216640 | consumed tokens: 14779678720 | elapsed time per iteration (s): 0.23 | learning rate: 4.816E-05 | global batch size: 256 | lm loss: 3.347312E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.775 | TFLOPs: 28.50 | +7: iteration 28200/ 37905 | consumed samples: 7219200 | consumed tokens: 14784921600 | elapsed time per iteration (s): 0.23 | learning rate: 4.811E-05 | global batch size: 256 | lm loss: 3.321077E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.813 | TFLOPs: 28.45 | +7: iteration 28210/ 37905 | consumed samples: 7221760 | consumed tokens: 14790164480 | elapsed time per iteration (s): 0.23 | learning rate: 4.805E-05 | global batch size: 256 | lm loss: 3.327192E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.408 | TFLOPs: 28.49 | +7: iteration 28220/ 37905 | consumed samples: 7224320 | consumed tokens: 14795407360 | elapsed time per iteration (s): 0.23 | learning rate: 4.800E-05 | global batch size: 256 | lm loss: 3.317253E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.910 | TFLOPs: 28.38 | +7: iteration 28230/ 37905 | consumed samples: 7226880 | consumed tokens: 14800650240 | elapsed time per iteration (s): 0.23 | learning rate: 4.794E-05 | global batch size: 256 | lm loss: 3.326168E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.856 | TFLOPs: 28.50 | +7: iteration 28240/ 37905 | consumed samples: 7229440 | consumed tokens: 14805893120 | elapsed time per iteration (s): 0.23 | learning rate: 4.789E-05 | global batch size: 256 | lm loss: 3.328403E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.430 | TFLOPs: 28.54 | +7: iteration 28250/ 37905 | consumed samples: 7232000 | consumed tokens: 14811136000 | elapsed time per iteration (s): 0.23 | learning rate: 4.783E-05 | global batch size: 256 | lm loss: 3.344994E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.501 | TFLOPs: 28.54 | +7: iteration 28260/ 37905 | consumed samples: 7234560 | consumed tokens: 14816378880 | elapsed time per iteration (s): 0.23 | learning rate: 4.778E-05 | global batch size: 256 | lm loss: 3.338591E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.065 | TFLOPs: 28.48 | +7: iteration 28270/ 37905 | consumed samples: 7237120 | consumed tokens: 14821621760 | elapsed time per iteration (s): 0.23 | learning rate: 4.773E-05 | global batch size: 256 | lm loss: 3.297566E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.620 | TFLOPs: 28.55 | +7: iteration 28280/ 37905 | consumed samples: 7239680 | consumed tokens: 14826864640 | elapsed time per iteration (s): 0.24 | learning rate: 4.767E-05 | global batch size: 256 | lm loss: 3.324332E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1045.901 | TFLOPs: 26.64 | +7: iteration 28290/ 37905 | consumed samples: 7242240 | consumed tokens: 14832107520 | elapsed time per iteration (s): 0.23 | learning rate: 4.762E-05 | global batch size: 256 | lm loss: 3.313478E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.710 | TFLOPs: 28.58 | +7: iteration 28300/ 37905 | consumed samples: 7244800 | consumed tokens: 14837350400 | elapsed time per iteration (s): 0.23 | learning rate: 4.756E-05 | global batch size: 256 | lm loss: 3.333391E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.130 | TFLOPs: 28.54 | +7: iteration 28310/ 37905 | consumed samples: 7247360 | consumed tokens: 14842593280 | elapsed time per iteration (s): 0.23 | learning rate: 4.751E-05 | global batch size: 256 | lm loss: 3.332587E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.274 | TFLOPs: 28.51 | +7: iteration 28320/ 37905 | consumed samples: 7249920 | consumed tokens: 14847836160 | elapsed time per iteration (s): 0.23 | learning rate: 4.745E-05 | global batch size: 256 | lm loss: 3.341621E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.314 | TFLOPs: 28.46 | +7: iteration 28330/ 37905 | consumed samples: 7252480 | consumed tokens: 14853079040 | elapsed time per iteration (s): 0.23 | learning rate: 4.740E-05 | global batch size: 256 | lm loss: 3.327348E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.841 | TFLOPs: 28.30 | +7: iteration 28340/ 37905 | consumed samples: 7255040 | consumed tokens: 14858321920 | elapsed time per iteration (s): 0.23 | learning rate: 4.735E-05 | global batch size: 256 | lm loss: 3.321967E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.495 | TFLOPs: 28.60 | +7: iteration 28350/ 37905 | consumed samples: 7257600 | consumed tokens: 14863564800 | elapsed time per iteration (s): 0.23 | learning rate: 4.729E-05 | global batch size: 256 | lm loss: 3.327904E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.242 | TFLOPs: 28.49 | +7: iteration 28360/ 37905 | consumed samples: 7260160 | consumed tokens: 14868807680 | elapsed time per iteration (s): 0.23 | learning rate: 4.724E-05 | global batch size: 256 | lm loss: 3.330660E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.493 | TFLOPs: 28.49 | +7: iteration 28370/ 37905 | consumed samples: 7262720 | consumed tokens: 14874050560 | elapsed time per iteration (s): 0.24 | learning rate: 4.718E-05 | global batch size: 256 | lm loss: 3.330654E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1083.545 | TFLOPs: 27.60 | +7: iteration 28380/ 37905 | consumed samples: 7265280 | consumed tokens: 14879293440 | elapsed time per iteration (s): 0.23 | learning rate: 4.713E-05 | global batch size: 256 | lm loss: 3.313968E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.202 | TFLOPs: 28.59 | +7: iteration 28390/ 37905 | consumed samples: 7267840 | consumed tokens: 14884536320 | elapsed time per iteration (s): 0.23 | learning rate: 4.708E-05 | global batch size: 256 | lm loss: 3.320919E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.189 | TFLOPs: 28.23 | +7: iteration 28400/ 37905 | consumed samples: 7270400 | consumed tokens: 14889779200 | elapsed time per iteration (s): 0.23 | learning rate: 4.702E-05 | global batch size: 256 | lm loss: 3.335498E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.521 | TFLOPs: 28.47 | +7: iteration 28410/ 37905 | consumed samples: 7272960 | consumed tokens: 14895022080 | elapsed time per iteration (s): 0.23 | learning rate: 4.697E-05 | global batch size: 256 | lm loss: 3.318253E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.041 | TFLOPs: 28.56 | +7: iteration 28420/ 37905 | consumed samples: 7275520 | consumed tokens: 14900264960 | elapsed time per iteration (s): 0.23 | learning rate: 4.691E-05 | global batch size: 256 | lm loss: 3.325311E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.080 | TFLOPs: 28.38 | +7: iteration 28430/ 37905 | consumed samples: 7278080 | consumed tokens: 14905507840 | elapsed time per iteration (s): 0.23 | learning rate: 4.686E-05 | global batch size: 256 | lm loss: 3.334266E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.727 | TFLOPs: 28.17 | +7: iteration 28440/ 37905 | consumed samples: 7280640 | consumed tokens: 14910750720 | elapsed time per iteration (s): 0.23 | learning rate: 4.681E-05 | global batch size: 256 | lm loss: 3.294167E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.764 | TFLOPs: 28.45 | +7: iteration 28450/ 37905 | consumed samples: 7283200 | consumed tokens: 14915993600 | elapsed time per iteration (s): 0.23 | learning rate: 4.675E-05 | global batch size: 256 | lm loss: 3.321868E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.832 | TFLOPs: 27.89 | +7: iteration 28460/ 37905 | consumed samples: 7285760 | consumed tokens: 14921236480 | elapsed time per iteration (s): 0.23 | learning rate: 4.670E-05 | global batch size: 256 | lm loss: 3.331149E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.128 | TFLOPs: 28.51 | +7: iteration 28470/ 37905 | consumed samples: 7288320 | consumed tokens: 14926479360 | elapsed time per iteration (s): 0.23 | learning rate: 4.665E-05 | global batch size: 256 | lm loss: 3.295978E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.176 | TFLOPs: 28.03 | +7: iteration 28480/ 37905 | consumed samples: 7290880 | consumed tokens: 14931722240 | elapsed time per iteration (s): 0.23 | learning rate: 4.659E-05 | global batch size: 256 | lm loss: 3.338471E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.542 | TFLOPs: 28.50 | +7: iteration 28490/ 37905 | consumed samples: 7293440 | consumed tokens: 14936965120 | elapsed time per iteration (s): 0.23 | learning rate: 4.654E-05 | global batch size: 256 | lm loss: 3.340910E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.691 | TFLOPs: 28.47 | +7: iteration 28500/ 37905 | consumed samples: 7296000 | consumed tokens: 14942208000 | elapsed time per iteration (s): 0.23 | learning rate: 4.649E-05 | global batch size: 256 | lm loss: 3.326777E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.296 | TFLOPs: 28.46 | +7: iteration 28510/ 37905 | consumed samples: 7298560 | consumed tokens: 14947450880 | elapsed time per iteration (s): 0.23 | learning rate: 4.643E-05 | global batch size: 256 | lm loss: 3.334758E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.280 | TFLOPs: 28.36 | +7: iteration 28520/ 37905 | consumed samples: 7301120 | consumed tokens: 14952693760 | elapsed time per iteration (s): 0.23 | learning rate: 4.638E-05 | global batch size: 256 | lm loss: 3.341202E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.522 | TFLOPs: 28.62 | +7: iteration 28530/ 37905 | consumed samples: 7303680 | consumed tokens: 14957936640 | elapsed time per iteration (s): 0.23 | learning rate: 4.633E-05 | global batch size: 256 | lm loss: 3.311647E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.479 | TFLOPs: 28.62 | +7: iteration 28540/ 37905 | consumed samples: 7306240 | consumed tokens: 14963179520 | elapsed time per iteration (s): 0.23 | learning rate: 4.627E-05 | global batch size: 256 | lm loss: 3.344013E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.777 | TFLOPs: 28.60 | +7: iteration 28550/ 37905 | consumed samples: 7308800 | consumed tokens: 14968422400 | elapsed time per iteration (s): 0.23 | learning rate: 4.622E-05 | global batch size: 256 | lm loss: 3.344228E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.640 | TFLOPs: 28.42 | +7: iteration 28560/ 37905 | consumed samples: 7311360 | consumed tokens: 14973665280 | elapsed time per iteration (s): 0.23 | learning rate: 4.617E-05 | global batch size: 256 | lm loss: 3.367134E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.097 | TFLOPs: 28.59 | +7: iteration 28570/ 37905 | consumed samples: 7313920 | consumed tokens: 14978908160 | elapsed time per iteration (s): 0.23 | learning rate: 4.611E-05 | global batch size: 256 | lm loss: 3.355606E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.051 | TFLOPs: 28.58 | +7: iteration 28580/ 37905 | consumed samples: 7316480 | consumed tokens: 14984151040 | elapsed time per iteration (s): 0.23 | learning rate: 4.606E-05 | global batch size: 256 | lm loss: 3.327592E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.679 | TFLOPs: 28.47 | +7: iteration 28590/ 37905 | consumed samples: 7319040 | consumed tokens: 14989393920 | elapsed time per iteration (s): 0.23 | learning rate: 4.601E-05 | global batch size: 256 | lm loss: 3.340666E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.702 | TFLOPs: 28.52 | +7: iteration 28600/ 37905 | consumed samples: 7321600 | consumed tokens: 14994636800 | elapsed time per iteration (s): 0.23 | learning rate: 4.595E-05 | global batch size: 256 | lm loss: 3.331606E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.396 | TFLOPs: 28.57 | +7: iteration 28610/ 37905 | consumed samples: 7324160 | consumed tokens: 14999879680 | elapsed time per iteration (s): 0.23 | learning rate: 4.590E-05 | global batch size: 256 | lm loss: 3.336629E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.664 | TFLOPs: 28.65 | +7: iteration 28620/ 37905 | consumed samples: 7326720 | consumed tokens: 15005122560 | elapsed time per iteration (s): 0.23 | learning rate: 4.585E-05 | global batch size: 256 | lm loss: 3.322689E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.916 | TFLOPs: 28.61 | +7: iteration 28630/ 37905 | consumed samples: 7329280 | consumed tokens: 15010365440 | elapsed time per iteration (s): 0.23 | learning rate: 4.580E-05 | global batch size: 256 | lm loss: 3.330093E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.471 | TFLOPs: 28.57 | +7: iteration 28640/ 37905 | consumed samples: 7331840 | consumed tokens: 15015608320 | elapsed time per iteration (s): 0.23 | learning rate: 4.574E-05 | global batch size: 256 | lm loss: 3.301827E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.619 | TFLOPs: 28.52 | +7: iteration 28650/ 37905 | consumed samples: 7334400 | consumed tokens: 15020851200 | elapsed time per iteration (s): 0.23 | learning rate: 4.569E-05 | global batch size: 256 | lm loss: 3.319783E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.738 | TFLOPs: 28.55 | +7: iteration 28660/ 37905 | consumed samples: 7336960 | consumed tokens: 15026094080 | elapsed time per iteration (s): 0.23 | learning rate: 4.564E-05 | global batch size: 256 | lm loss: 3.330058E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.878 | TFLOPs: 28.53 | +7: iteration 28670/ 37905 | consumed samples: 7339520 | consumed tokens: 15031336960 | elapsed time per iteration (s): 0.23 | learning rate: 4.559E-05 | global batch size: 256 | lm loss: 3.304207E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.843 | TFLOPs: 28.60 | +7: iteration 28680/ 37905 | consumed samples: 7342080 | consumed tokens: 15036579840 | elapsed time per iteration (s): 0.23 | learning rate: 4.553E-05 | global batch size: 256 | lm loss: 3.336988E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.753 | TFLOPs: 28.50 | +7: iteration 28690/ 37905 | consumed samples: 7344640 | consumed tokens: 15041822720 | elapsed time per iteration (s): 0.23 | learning rate: 4.548E-05 | global batch size: 256 | lm loss: 3.335154E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.986 | TFLOPs: 28.56 | +7: iteration 28700/ 37905 | consumed samples: 7347200 | consumed tokens: 15047065600 | elapsed time per iteration (s): 0.23 | learning rate: 4.543E-05 | global batch size: 256 | lm loss: 3.349335E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.637 | TFLOPs: 28.70 | +7: iteration 28710/ 37905 | consumed samples: 7349760 | consumed tokens: 15052308480 | elapsed time per iteration (s): 0.23 | learning rate: 4.537E-05 | global batch size: 256 | lm loss: 3.323036E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.596 | TFLOPs: 28.65 | +7: iteration 28720/ 37905 | consumed samples: 7352320 | consumed tokens: 15057551360 | elapsed time per iteration (s): 0.23 | learning rate: 4.532E-05 | global batch size: 256 | lm loss: 3.344402E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.882 | TFLOPs: 28.71 | +7: iteration 28730/ 37905 | consumed samples: 7354880 | consumed tokens: 15062794240 | elapsed time per iteration (s): 0.23 | learning rate: 4.527E-05 | global batch size: 256 | lm loss: 3.333839E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.370 | TFLOPs: 28.52 | +7: iteration 28740/ 37905 | consumed samples: 7357440 | consumed tokens: 15068037120 | elapsed time per iteration (s): 0.23 | learning rate: 4.522E-05 | global batch size: 256 | lm loss: 3.333972E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.352 | TFLOPs: 28.62 | +7: iteration 28750/ 37905 | consumed samples: 7360000 | consumed tokens: 15073280000 | elapsed time per iteration (s): 0.23 | learning rate: 4.517E-05 | global batch size: 256 | lm loss: 3.323308E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.860 | TFLOPs: 28.68 | +7: iteration 28760/ 37905 | consumed samples: 7362560 | consumed tokens: 15078522880 | elapsed time per iteration (s): 0.23 | learning rate: 4.511E-05 | global batch size: 256 | lm loss: 3.327332E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.266 | TFLOPs: 28.54 | +7: iteration 28770/ 37905 | consumed samples: 7365120 | consumed tokens: 15083765760 | elapsed time per iteration (s): 0.24 | learning rate: 4.506E-05 | global batch size: 256 | lm loss: 3.326802E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.261 | TFLOPs: 27.70 | +7: iteration 28780/ 37905 | consumed samples: 7367680 | consumed tokens: 15089008640 | elapsed time per iteration (s): 0.23 | learning rate: 4.501E-05 | global batch size: 256 | lm loss: 3.296567E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.315 | TFLOPs: 28.13 | +7: iteration 28790/ 37905 | consumed samples: 7370240 | consumed tokens: 15094251520 | elapsed time per iteration (s): 0.23 | learning rate: 4.496E-05 | global batch size: 256 | lm loss: 3.359885E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.583 | TFLOPs: 28.60 | +7: iteration 28800/ 37905 | consumed samples: 7372800 | consumed tokens: 15099494400 | elapsed time per iteration (s): 0.23 | learning rate: 4.490E-05 | global batch size: 256 | lm loss: 3.330428E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.299 | TFLOPs: 28.62 | +7: iteration 28810/ 37905 | consumed samples: 7375360 | consumed tokens: 15104737280 | elapsed time per iteration (s): 0.23 | learning rate: 4.485E-05 | global batch size: 256 | lm loss: 3.333342E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.708 | TFLOPs: 28.55 | +7: iteration 28820/ 37905 | consumed samples: 7377920 | consumed tokens: 15109980160 | elapsed time per iteration (s): 0.24 | learning rate: 4.480E-05 | global batch size: 256 | lm loss: 3.333714E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.324 | TFLOPs: 27.65 | +7: iteration 28830/ 37905 | consumed samples: 7380480 | consumed tokens: 15115223040 | elapsed time per iteration (s): 0.23 | learning rate: 4.475E-05 | global batch size: 256 | lm loss: 3.341037E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.391 | TFLOPs: 28.62 | +7: iteration 28840/ 37905 | consumed samples: 7383040 | consumed tokens: 15120465920 | elapsed time per iteration (s): 0.23 | learning rate: 4.470E-05 | global batch size: 256 | lm loss: 3.324994E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.430 | TFLOPs: 28.62 | +7: iteration 28850/ 37905 | consumed samples: 7385600 | consumed tokens: 15125708800 | elapsed time per iteration (s): 0.23 | learning rate: 4.465E-05 | global batch size: 256 | lm loss: 3.307753E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.493 | TFLOPs: 28.14 | +7: iteration 28860/ 37905 | consumed samples: 7388160 | consumed tokens: 15130951680 | elapsed time per iteration (s): 0.23 | learning rate: 4.459E-05 | global batch size: 256 | lm loss: 3.324618E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.446 | TFLOPs: 28.57 | +7: iteration 28870/ 37905 | consumed samples: 7390720 | consumed tokens: 15136194560 | elapsed time per iteration (s): 0.23 | learning rate: 4.454E-05 | global batch size: 256 | lm loss: 3.342814E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.759 | TFLOPs: 28.63 | +7: iteration 28880/ 37905 | consumed samples: 7393280 | consumed tokens: 15141437440 | elapsed time per iteration (s): 0.23 | learning rate: 4.449E-05 | global batch size: 256 | lm loss: 3.338358E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.890 | TFLOPs: 28.63 | +7: iteration 28890/ 37905 | consumed samples: 7395840 | consumed tokens: 15146680320 | elapsed time per iteration (s): 0.23 | learning rate: 4.444E-05 | global batch size: 256 | lm loss: 3.352785E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.933 | TFLOPs: 28.66 | +7: iteration 28900/ 37905 | consumed samples: 7398400 | consumed tokens: 15151923200 | elapsed time per iteration (s): 0.23 | learning rate: 4.439E-05 | global batch size: 256 | lm loss: 3.347918E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.091 | TFLOPs: 28.61 | +7: iteration 28910/ 37905 | consumed samples: 7400960 | consumed tokens: 15157166080 | elapsed time per iteration (s): 0.23 | learning rate: 4.434E-05 | global batch size: 256 | lm loss: 3.325527E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.746 | TFLOPs: 28.63 | +7: iteration 28920/ 37905 | consumed samples: 7403520 | consumed tokens: 15162408960 | elapsed time per iteration (s): 0.23 | learning rate: 4.428E-05 | global batch size: 256 | lm loss: 3.326464E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.735 | TFLOPs: 28.53 | +7: iteration 28930/ 37905 | consumed samples: 7406080 | consumed tokens: 15167651840 | elapsed time per iteration (s): 0.23 | learning rate: 4.423E-05 | global batch size: 256 | lm loss: 3.347379E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.141 | TFLOPs: 27.85 | +7: iteration 28940/ 37905 | consumed samples: 7408640 | consumed tokens: 15172894720 | elapsed time per iteration (s): 0.23 | learning rate: 4.418E-05 | global batch size: 256 | lm loss: 3.349834E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.090 | TFLOPs: 28.56 | +7: iteration 28950/ 37905 | consumed samples: 7411200 | consumed tokens: 15178137600 | elapsed time per iteration (s): 0.23 | learning rate: 4.413E-05 | global batch size: 256 | lm loss: 3.337976E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.671 | TFLOPs: 28.52 | +7: iteration 28960/ 37905 | consumed samples: 7413760 | consumed tokens: 15183380480 | elapsed time per iteration (s): 0.23 | learning rate: 4.408E-05 | global batch size: 256 | lm loss: 3.356139E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.038 | TFLOPs: 28.43 | +7: iteration 28970/ 37905 | consumed samples: 7416320 | consumed tokens: 15188623360 | elapsed time per iteration (s): 0.23 | learning rate: 4.403E-05 | global batch size: 256 | lm loss: 3.312778E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.313 | TFLOPs: 28.57 | +7: iteration 28980/ 37905 | consumed samples: 7418880 | consumed tokens: 15193866240 | elapsed time per iteration (s): 0.23 | learning rate: 4.398E-05 | global batch size: 256 | lm loss: 3.333442E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.002 | TFLOPs: 28.48 | +7: iteration 28990/ 37905 | consumed samples: 7421440 | consumed tokens: 15199109120 | elapsed time per iteration (s): 0.23 | learning rate: 4.392E-05 | global batch size: 256 | lm loss: 3.341189E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.658 | TFLOPs: 28.45 | +7: iteration 29000/ 37905 | consumed samples: 7424000 | consumed tokens: 15204352000 | elapsed time per iteration (s): 0.23 | learning rate: 4.387E-05 | global batch size: 256 | lm loss: 3.325834E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.973 | TFLOPs: 28.56 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 29000 | lm loss value: 3.216117E+00 | lm loss PPL: 2.493113E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 29000 to checkpoints_83moscar +0: [2022-11-29 18:50:39,421] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step29000 is begin to save! +0: [2022-11-29 18:50:39,425] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:50:39,499] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:50:39,499] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:50:39,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:50:39,511] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:50:39,522] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:50:39,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:50:39,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:50:39,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:50:39,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:50:39,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:50:39,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:50:39,556] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:50:39,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:50:39,568] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:50:39,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:50:39,579] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:50:39,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:50:39,590] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:50:39,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:50:39,602] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:50:39,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:50:39,613] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:50:39,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:50:39,615] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step29000/mp_rank_00_model_states.pt +0: [2022-11-29 18:50:39,615] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:50:39,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:50:39,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:50:39,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:50:39,654] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +0: [2022-11-29 18:50:39,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:50:39,654] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +2: [2022-11-29 18:50:39,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:50:39,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:50:39,654] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:50:39,654] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +4: [2022-11-29 18:50:39,654] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:50:39,654] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +3: [2022-11-29 18:50:39,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:50:39,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:50:39,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +7: [2022-11-29 18:50:39,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:50:39,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:50:39,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +6: [2022-11-29 18:50:39,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:50:39,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +1: [2022-11-29 18:50:39,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:50:39,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +1: [2022-11-29 18:50:39,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:50:39,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +6: [2022-11-29 18:50:39,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:50:39,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:50:39,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +0: [2022-11-29 18:50:39,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:50:39,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:50:39,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +0: [2022-11-29 18:50:39,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 18:50:39,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +5: [2022-11-29 18:50:39,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:50:39,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:50:39,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +2: [2022-11-29 18:50:39,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:50:39,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:50:39,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +7: [2022-11-29 18:50:39,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:50:39,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +3: [2022-11-29 18:50:39,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:50:39,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +3: [2022-11-29 18:50:39,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:50:39,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:50:39,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +6: [2022-11-29 18:50:39,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:50:39,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:50:39,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +6: [2022-11-29 18:50:39,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:50:39,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +4: [2022-11-29 18:50:39,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:50:39,657] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 18:50:39,657] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +4: [2022-11-29 18:50:39,657] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:50:39,657] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:50:39,657] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:50:39,657] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +4: [2022-11-29 18:50:39,657] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:50:39,657] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +7: [2022-11-29 18:50:39,657] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:50:39,657] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:50:39,657] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +0: [2022-11-29 18:50:39,657] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:50:39,657] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:50:39,657] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +5: [2022-11-29 18:50:39,658] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:50:39,658] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:50:39,658] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +1: [2022-11-29 18:50:39,658] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:50:39,658] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:50:39,658] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +2: [2022-11-29 18:50:39,658] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:50:39,658] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:50:39,658] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +7: [2022-11-29 18:50:39,658] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:50:39,658] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:50:39,658] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +3: [2022-11-29 18:50:39,658] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +7: [2022-11-29 18:50:39,658] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +3: [2022-11-29 18:50:39,658] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +6: [2022-11-29 18:50:39,659] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:50:39,659] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:50:39,659] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +0: [2022-11-29 18:50:39,659] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:50:39,659] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:50:39,659] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +1: [2022-11-29 18:50:39,659] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:50:39,659] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:50:39,659] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +3: [2022-11-29 18:50:39,659] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:50:39,659] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:50:39,659] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +5: [2022-11-29 18:50:39,659] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:50:39,659] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:50:39,659] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +4: [2022-11-29 18:50:39,659] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:50:39,659] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +5: [2022-11-29 18:50:39,659] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +2: [2022-11-29 18:50:39,659] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +4: [2022-11-29 18:50:39,659] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:50:39,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +7: [2022-11-29 18:50:39,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:50:39,660] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:50:39,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +1: [2022-11-29 18:50:39,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:50:39,660] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:50:39,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +2: [2022-11-29 18:50:39,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:50:39,660] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:50:39,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +0: [2022-11-29 18:50:39,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:50:39,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:50:39,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:50:39,661] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +7: [2022-11-29 18:50:39,661] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +5: [2022-11-29 18:50:39,661] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +0: [2022-11-29 18:50:39,661] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +7: [2022-11-29 18:50:39,661] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +5: [2022-11-29 18:50:39,661] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +6: [2022-11-29 18:50:39,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:50:39,661] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:50:39,661] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +6: [2022-11-29 18:50:39,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:50:39,661] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:50:39,661] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +0: [2022-11-29 18:50:39,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:50:39,661] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:50:39,661] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +3: [2022-11-29 18:50:39,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:50:39,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:50:39,661] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +3: [2022-11-29 18:50:39,661] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:50:39,661] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +4: [2022-11-29 18:50:39,661] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +2: [2022-11-29 18:50:39,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:50:39,662] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:50:39,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +1: [2022-11-29 18:50:39,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:50:39,662] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:50:39,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +4: [2022-11-29 18:50:39,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:50:39,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:50:39,662] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +6: [2022-11-29 18:50:39,662] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +4: [2022-11-29 18:50:39,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +6: [2022-11-29 18:50:39,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +5: [2022-11-29 18:50:39,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:50:39,662] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:50:39,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +0: [2022-11-29 18:50:39,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:50:39,662] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:50:39,663] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +3: [2022-11-29 18:50:39,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:50:39,663] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:50:39,663] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +7: [2022-11-29 18:50:39,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:50:39,663] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +4: [2022-11-29 18:50:39,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:50:39,663] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +4: [2022-11-29 18:50:39,663] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:50:39,663] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +7: [2022-11-29 18:50:39,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:50:39,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:50:39,663] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +6: [2022-11-29 18:50:39,663] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +7: [2022-11-29 18:50:39,663] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +6: [2022-11-29 18:50:39,663] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +2: [2022-11-29 18:50:39,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:50:39,663] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:50:39,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:50:39,663] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +2: [2022-11-29 18:50:39,663] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:50:39,664] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +0: [2022-11-29 18:50:39,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:50:39,664] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 18:50:39,664] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +1: [2022-11-29 18:50:39,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:50:39,664] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:50:39,664] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +1: [2022-11-29 18:50:39,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:50:39,664] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 18:50:39,664] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +1: [2022-11-29 18:50:39,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:50:39,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:50:39,664] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +3: [2022-11-29 18:50:39,664] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +1: [2022-11-29 18:50:39,664] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +3: [2022-11-29 18:50:39,664] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +4: [2022-11-29 18:50:39,666] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:50:39,666] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:50:39,666] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +5: [2022-11-29 18:50:39,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:50:39,667] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step29000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:50:39,667] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +0: successfully saved checkpoint at iteration 29000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 250.44 +7: iteration 29010/ 37905 | consumed samples: 7426560 | consumed tokens: 15209594880 | elapsed time per iteration (s): 0.26 | learning rate: 4.382E-05 | global batch size: 256 | lm loss: 3.335167E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 986.696 | TFLOPs: 25.14 | +7: iteration 29020/ 37905 | consumed samples: 7429120 | consumed tokens: 15214837760 | elapsed time per iteration (s): 0.25 | learning rate: 4.377E-05 | global batch size: 256 | lm loss: 3.344816E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1040.303 | TFLOPs: 26.50 | +7: iteration 29030/ 37905 | consumed samples: 7431680 | consumed tokens: 15220080640 | elapsed time per iteration (s): 0.23 | learning rate: 4.372E-05 | global batch size: 256 | lm loss: 3.316264E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.378 | TFLOPs: 28.75 | +7: iteration 29040/ 37905 | consumed samples: 7434240 | consumed tokens: 15225323520 | elapsed time per iteration (s): 0.23 | learning rate: 4.367E-05 | global batch size: 256 | lm loss: 3.329678E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.892 | TFLOPs: 28.73 | +7: iteration 29050/ 37905 | consumed samples: 7436800 | consumed tokens: 15230566400 | elapsed time per iteration (s): 0.23 | learning rate: 4.362E-05 | global batch size: 256 | lm loss: 3.326096E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.043 | TFLOPs: 28.51 | +7: iteration 29060/ 37905 | consumed samples: 7439360 | consumed tokens: 15235809280 | elapsed time per iteration (s): 0.23 | learning rate: 4.357E-05 | global batch size: 256 | lm loss: 3.327914E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.982 | TFLOPs: 28.71 | +7: iteration 29070/ 37905 | consumed samples: 7441920 | consumed tokens: 15241052160 | elapsed time per iteration (s): 0.23 | learning rate: 4.352E-05 | global batch size: 256 | lm loss: 3.310552E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.653 | TFLOPs: 28.60 | +7: iteration 29080/ 37905 | consumed samples: 7444480 | consumed tokens: 15246295040 | elapsed time per iteration (s): 0.24 | learning rate: 4.347E-05 | global batch size: 256 | lm loss: 3.333540E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1050.683 | TFLOPs: 26.77 | +7: iteration 29090/ 37905 | consumed samples: 7447040 | consumed tokens: 15251537920 | elapsed time per iteration (s): 0.23 | learning rate: 4.342E-05 | global batch size: 256 | lm loss: 3.339651E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.188 | TFLOPs: 28.69 | +7: iteration 29100/ 37905 | consumed samples: 7449600 | consumed tokens: 15256780800 | elapsed time per iteration (s): 0.23 | learning rate: 4.336E-05 | global batch size: 256 | lm loss: 3.351627E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.412 | TFLOPs: 28.52 | +7: iteration 29110/ 37905 | consumed samples: 7452160 | consumed tokens: 15262023680 | elapsed time per iteration (s): 0.23 | learning rate: 4.331E-05 | global batch size: 256 | lm loss: 3.316714E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.898 | TFLOPs: 28.71 | +7: iteration 29120/ 37905 | consumed samples: 7454720 | consumed tokens: 15267266560 | elapsed time per iteration (s): 0.24 | learning rate: 4.326E-05 | global batch size: 256 | lm loss: 3.330210E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1055.969 | TFLOPs: 26.90 | +7: iteration 29130/ 37905 | consumed samples: 7457280 | consumed tokens: 15272509440 | elapsed time per iteration (s): 0.23 | learning rate: 4.321E-05 | global batch size: 256 | lm loss: 3.329585E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.633 | TFLOPs: 28.70 | +7: iteration 29140/ 37905 | consumed samples: 7459840 | consumed tokens: 15277752320 | elapsed time per iteration (s): 0.23 | learning rate: 4.316E-05 | global batch size: 256 | lm loss: 3.340022E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.248 | TFLOPs: 28.51 | +7: iteration 29150/ 37905 | consumed samples: 7462400 | consumed tokens: 15282995200 | elapsed time per iteration (s): 0.23 | learning rate: 4.311E-05 | global batch size: 256 | lm loss: 3.363210E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.931 | TFLOPs: 28.40 | +7: iteration 29160/ 37905 | consumed samples: 7464960 | consumed tokens: 15288238080 | elapsed time per iteration (s): 0.23 | learning rate: 4.306E-05 | global batch size: 256 | lm loss: 3.356244E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.652 | TFLOPs: 28.70 | +7: iteration 29170/ 37905 | consumed samples: 7467520 | consumed tokens: 15293480960 | elapsed time per iteration (s): 0.23 | learning rate: 4.301E-05 | global batch size: 256 | lm loss: 3.321917E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.880 | TFLOPs: 28.66 | +7: iteration 29180/ 37905 | consumed samples: 7470080 | consumed tokens: 15298723840 | elapsed time per iteration (s): 0.23 | learning rate: 4.296E-05 | global batch size: 256 | lm loss: 3.329609E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.608 | TFLOPs: 28.73 | +7: iteration 29190/ 37905 | consumed samples: 7472640 | consumed tokens: 15303966720 | elapsed time per iteration (s): 0.23 | learning rate: 4.291E-05 | global batch size: 256 | lm loss: 3.337071E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.919 | TFLOPs: 28.66 | +7: iteration 29200/ 37905 | consumed samples: 7475200 | consumed tokens: 15309209600 | elapsed time per iteration (s): 0.23 | learning rate: 4.286E-05 | global batch size: 256 | lm loss: 3.361766E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.675 | TFLOPs: 28.68 | +7: iteration 29210/ 37905 | consumed samples: 7477760 | consumed tokens: 15314452480 | elapsed time per iteration (s): 0.23 | learning rate: 4.281E-05 | global batch size: 256 | lm loss: 3.339742E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.510 | TFLOPs: 28.67 | +7: iteration 29220/ 37905 | consumed samples: 7480320 | consumed tokens: 15319695360 | elapsed time per iteration (s): 0.23 | learning rate: 4.276E-05 | global batch size: 256 | lm loss: 3.303431E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.401 | TFLOPs: 28.75 | +7: iteration 29230/ 37905 | consumed samples: 7482880 | consumed tokens: 15324938240 | elapsed time per iteration (s): 0.23 | learning rate: 4.271E-05 | global batch size: 256 | lm loss: 3.319727E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.963 | TFLOPs: 28.74 | +7: iteration 29240/ 37905 | consumed samples: 7485440 | consumed tokens: 15330181120 | elapsed time per iteration (s): 0.23 | learning rate: 4.266E-05 | global batch size: 256 | lm loss: 3.339238E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.623 | TFLOPs: 28.70 | +7: iteration 29250/ 37905 | consumed samples: 7488000 | consumed tokens: 15335424000 | elapsed time per iteration (s): 0.23 | learning rate: 4.261E-05 | global batch size: 256 | lm loss: 3.320872E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.406 | TFLOPs: 28.62 | +7: iteration 29260/ 37905 | consumed samples: 7490560 | consumed tokens: 15340666880 | elapsed time per iteration (s): 0.23 | learning rate: 4.256E-05 | global batch size: 256 | lm loss: 3.314109E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.901 | TFLOPs: 28.68 | +7: iteration 29270/ 37905 | consumed samples: 7493120 | consumed tokens: 15345909760 | elapsed time per iteration (s): 0.23 | learning rate: 4.251E-05 | global batch size: 256 | lm loss: 3.308339E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.375 | TFLOPs: 28.62 | +7: iteration 29280/ 37905 | consumed samples: 7495680 | consumed tokens: 15351152640 | elapsed time per iteration (s): 0.23 | learning rate: 4.246E-05 | global batch size: 256 | lm loss: 3.307166E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.230 | TFLOPs: 28.72 | +7: iteration 29290/ 37905 | consumed samples: 7498240 | consumed tokens: 15356395520 | elapsed time per iteration (s): 0.23 | learning rate: 4.241E-05 | global batch size: 256 | lm loss: 3.310687E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.906 | TFLOPs: 28.66 | +7: iteration 29300/ 37905 | consumed samples: 7500800 | consumed tokens: 15361638400 | elapsed time per iteration (s): 0.23 | learning rate: 4.236E-05 | global batch size: 256 | lm loss: 3.317484E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.302 | TFLOPs: 28.64 | +7: iteration 29310/ 37905 | consumed samples: 7503360 | consumed tokens: 15366881280 | elapsed time per iteration (s): 0.23 | learning rate: 4.231E-05 | global batch size: 256 | lm loss: 3.332832E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.053 | TFLOPs: 28.69 | +7: iteration 29320/ 37905 | consumed samples: 7505920 | consumed tokens: 15372124160 | elapsed time per iteration (s): 0.23 | learning rate: 4.226E-05 | global batch size: 256 | lm loss: 3.338245E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.843 | TFLOPs: 28.66 | +7: iteration 29330/ 37905 | consumed samples: 7508480 | consumed tokens: 15377367040 | elapsed time per iteration (s): 0.25 | learning rate: 4.221E-05 | global batch size: 256 | lm loss: 3.312532E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1039.248 | TFLOPs: 26.47 | +7: iteration 29340/ 37905 | consumed samples: 7511040 | consumed tokens: 15382609920 | elapsed time per iteration (s): 0.23 | learning rate: 4.216E-05 | global batch size: 256 | lm loss: 3.350965E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.359 | TFLOPs: 28.57 | +7: iteration 29350/ 37905 | consumed samples: 7513600 | consumed tokens: 15387852800 | elapsed time per iteration (s): 0.23 | learning rate: 4.211E-05 | global batch size: 256 | lm loss: 3.309086E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.510 | TFLOPs: 28.62 | +7: iteration 29360/ 37905 | consumed samples: 7516160 | consumed tokens: 15393095680 | elapsed time per iteration (s): 0.23 | learning rate: 4.206E-05 | global batch size: 256 | lm loss: 3.345267E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.042 | TFLOPs: 28.66 | +7: iteration 29370/ 37905 | consumed samples: 7518720 | consumed tokens: 15398338560 | elapsed time per iteration (s): 0.23 | learning rate: 4.201E-05 | global batch size: 256 | lm loss: 3.297648E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.337 | TFLOPs: 28.72 | +7: iteration 29380/ 37905 | consumed samples: 7521280 | consumed tokens: 15403581440 | elapsed time per iteration (s): 0.23 | learning rate: 4.196E-05 | global batch size: 256 | lm loss: 3.323373E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.276 | TFLOPs: 28.69 | +7: iteration 29390/ 37905 | consumed samples: 7523840 | consumed tokens: 15408824320 | elapsed time per iteration (s): 0.23 | learning rate: 4.192E-05 | global batch size: 256 | lm loss: 3.324734E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.450 | TFLOPs: 28.42 | +7: iteration 29400/ 37905 | consumed samples: 7526400 | consumed tokens: 15414067200 | elapsed time per iteration (s): 0.23 | learning rate: 4.187E-05 | global batch size: 256 | lm loss: 3.313496E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.219 | TFLOPs: 28.64 | +7: iteration 29410/ 37905 | consumed samples: 7528960 | consumed tokens: 15419310080 | elapsed time per iteration (s): 0.23 | learning rate: 4.182E-05 | global batch size: 256 | lm loss: 3.317434E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.561 | TFLOPs: 28.39 | +7: iteration 29420/ 37905 | consumed samples: 7531520 | consumed tokens: 15424552960 | elapsed time per iteration (s): 0.23 | learning rate: 4.177E-05 | global batch size: 256 | lm loss: 3.338918E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.740 | TFLOPs: 27.81 | +7: iteration 29430/ 37905 | consumed samples: 7534080 | consumed tokens: 15429795840 | elapsed time per iteration (s): 0.23 | learning rate: 4.172E-05 | global batch size: 256 | lm loss: 3.356501E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.650 | TFLOPs: 28.29 | +7: iteration 29440/ 37905 | consumed samples: 7536640 | consumed tokens: 15435038720 | elapsed time per iteration (s): 0.23 | learning rate: 4.167E-05 | global batch size: 256 | lm loss: 3.326356E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.006 | TFLOPs: 28.71 | +7: iteration 29450/ 37905 | consumed samples: 7539200 | consumed tokens: 15440281600 | elapsed time per iteration (s): 0.23 | learning rate: 4.162E-05 | global batch size: 256 | lm loss: 3.328909E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.696 | TFLOPs: 28.70 | +7: iteration 29460/ 37905 | consumed samples: 7541760 | consumed tokens: 15445524480 | elapsed time per iteration (s): 0.23 | learning rate: 4.157E-05 | global batch size: 256 | lm loss: 3.305853E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.403 | TFLOPs: 28.70 | +7: iteration 29470/ 37905 | consumed samples: 7544320 | consumed tokens: 15450767360 | elapsed time per iteration (s): 0.23 | learning rate: 4.152E-05 | global batch size: 256 | lm loss: 3.307738E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.595 | TFLOPs: 28.65 | +7: iteration 29480/ 37905 | consumed samples: 7546880 | consumed tokens: 15456010240 | elapsed time per iteration (s): 0.23 | learning rate: 4.147E-05 | global batch size: 256 | lm loss: 3.320705E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.091 | TFLOPs: 28.69 | +7: iteration 29490/ 37905 | consumed samples: 7549440 | consumed tokens: 15461253120 | elapsed time per iteration (s): 0.23 | learning rate: 4.143E-05 | global batch size: 256 | lm loss: 3.331384E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.495 | TFLOPs: 28.04 | +7: iteration 29500/ 37905 | consumed samples: 7552000 | consumed tokens: 15466496000 | elapsed time per iteration (s): 0.23 | learning rate: 4.138E-05 | global batch size: 256 | lm loss: 3.295029E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.654 | TFLOPs: 28.68 | +7: iteration 29510/ 37905 | consumed samples: 7554560 | consumed tokens: 15471738880 | elapsed time per iteration (s): 0.23 | learning rate: 4.133E-05 | global batch size: 256 | lm loss: 3.323854E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.650 | TFLOPs: 28.65 | +7: iteration 29520/ 37905 | consumed samples: 7557120 | consumed tokens: 15476981760 | elapsed time per iteration (s): 0.23 | learning rate: 4.128E-05 | global batch size: 256 | lm loss: 3.322832E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.706 | TFLOPs: 28.68 | +7: iteration 29530/ 37905 | consumed samples: 7559680 | consumed tokens: 15482224640 | elapsed time per iteration (s): 0.23 | learning rate: 4.123E-05 | global batch size: 256 | lm loss: 3.298672E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.927 | TFLOPs: 28.79 | +7: iteration 29540/ 37905 | consumed samples: 7562240 | consumed tokens: 15487467520 | elapsed time per iteration (s): 0.23 | learning rate: 4.118E-05 | global batch size: 256 | lm loss: 3.306839E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.979 | TFLOPs: 28.68 | +7: iteration 29550/ 37905 | consumed samples: 7564800 | consumed tokens: 15492710400 | elapsed time per iteration (s): 0.23 | learning rate: 4.113E-05 | global batch size: 256 | lm loss: 3.317619E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.517 | TFLOPs: 28.67 | +7: iteration 29560/ 37905 | consumed samples: 7567360 | consumed tokens: 15497953280 | elapsed time per iteration (s): 0.23 | learning rate: 4.108E-05 | global batch size: 256 | lm loss: 3.320807E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.773 | TFLOPs: 28.78 | +7: iteration 29570/ 37905 | consumed samples: 7569920 | consumed tokens: 15503196160 | elapsed time per iteration (s): 0.23 | learning rate: 4.104E-05 | global batch size: 256 | lm loss: 3.323078E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.556 | TFLOPs: 28.78 | +7: iteration 29580/ 37905 | consumed samples: 7572480 | consumed tokens: 15508439040 | elapsed time per iteration (s): 0.23 | learning rate: 4.099E-05 | global batch size: 256 | lm loss: 3.333744E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.864 | TFLOPs: 28.78 | +7: iteration 29590/ 37905 | consumed samples: 7575040 | consumed tokens: 15513681920 | elapsed time per iteration (s): 0.25 | learning rate: 4.094E-05 | global batch size: 256 | lm loss: 3.352169E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1044.602 | TFLOPs: 26.61 | +7: iteration 29600/ 37905 | consumed samples: 7577600 | consumed tokens: 15518924800 | elapsed time per iteration (s): 0.23 | learning rate: 4.089E-05 | global batch size: 256 | lm loss: 3.338847E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.128 | TFLOPs: 28.79 | +7: iteration 29610/ 37905 | consumed samples: 7580160 | consumed tokens: 15524167680 | elapsed time per iteration (s): 0.23 | learning rate: 4.084E-05 | global batch size: 256 | lm loss: 3.316197E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.394 | TFLOPs: 28.75 | +7: iteration 29620/ 37905 | consumed samples: 7582720 | consumed tokens: 15529410560 | elapsed time per iteration (s): 0.23 | learning rate: 4.080E-05 | global batch size: 256 | lm loss: 3.330136E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.975 | TFLOPs: 28.76 | +7: iteration 29630/ 37905 | consumed samples: 7585280 | consumed tokens: 15534653440 | elapsed time per iteration (s): 0.23 | learning rate: 4.075E-05 | global batch size: 256 | lm loss: 3.323574E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.386 | TFLOPs: 28.72 | +7: iteration 29640/ 37905 | consumed samples: 7587840 | consumed tokens: 15539896320 | elapsed time per iteration (s): 0.24 | learning rate: 4.070E-05 | global batch size: 256 | lm loss: 3.339295E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.893 | TFLOPs: 27.71 | +7: iteration 29650/ 37905 | consumed samples: 7590400 | consumed tokens: 15545139200 | elapsed time per iteration (s): 0.23 | learning rate: 4.065E-05 | global batch size: 256 | lm loss: 3.305492E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.337 | TFLOPs: 28.74 | +7: iteration 29660/ 37905 | consumed samples: 7592960 | consumed tokens: 15550382080 | elapsed time per iteration (s): 0.23 | learning rate: 4.060E-05 | global batch size: 256 | lm loss: 3.337868E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.803 | TFLOPs: 28.68 | +7: iteration 29670/ 37905 | consumed samples: 7595520 | consumed tokens: 15555624960 | elapsed time per iteration (s): 0.23 | learning rate: 4.055E-05 | global batch size: 256 | lm loss: 3.352543E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.659 | TFLOPs: 28.63 | +7: iteration 29680/ 37905 | consumed samples: 7598080 | consumed tokens: 15560867840 | elapsed time per iteration (s): 0.25 | learning rate: 4.051E-05 | global batch size: 256 | lm loss: 3.326092E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1037.416 | TFLOPs: 26.43 | +7: iteration 29690/ 37905 | consumed samples: 7600640 | consumed tokens: 15566110720 | elapsed time per iteration (s): 0.23 | learning rate: 4.046E-05 | global batch size: 256 | lm loss: 3.323985E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.385 | TFLOPs: 28.69 | +7: iteration 29700/ 37905 | consumed samples: 7603200 | consumed tokens: 15571353600 | elapsed time per iteration (s): 0.23 | learning rate: 4.041E-05 | global batch size: 256 | lm loss: 3.321125E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.966 | TFLOPs: 28.63 | +7: iteration 29710/ 37905 | consumed samples: 7605760 | consumed tokens: 15576596480 | elapsed time per iteration (s): 0.23 | learning rate: 4.036E-05 | global batch size: 256 | lm loss: 3.315728E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.882 | TFLOPs: 28.66 | +7: iteration 29720/ 37905 | consumed samples: 7608320 | consumed tokens: 15581839360 | elapsed time per iteration (s): 0.23 | learning rate: 4.032E-05 | global batch size: 256 | lm loss: 3.320456E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.371 | TFLOPs: 28.72 | +7: iteration 29730/ 37905 | consumed samples: 7610880 | consumed tokens: 15587082240 | elapsed time per iteration (s): 0.23 | learning rate: 4.027E-05 | global batch size: 256 | lm loss: 3.332983E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.054 | TFLOPs: 28.76 | +7: iteration 29740/ 37905 | consumed samples: 7613440 | consumed tokens: 15592325120 | elapsed time per iteration (s): 0.23 | learning rate: 4.022E-05 | global batch size: 256 | lm loss: 3.323917E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.646 | TFLOPs: 28.68 | +7: iteration 29750/ 37905 | consumed samples: 7616000 | consumed tokens: 15597568000 | elapsed time per iteration (s): 0.23 | learning rate: 4.017E-05 | global batch size: 256 | lm loss: 3.322379E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.164 | TFLOPs: 28.26 | +7: iteration 29760/ 37905 | consumed samples: 7618560 | consumed tokens: 15602810880 | elapsed time per iteration (s): 0.23 | learning rate: 4.013E-05 | global batch size: 256 | lm loss: 3.331382E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.079 | TFLOPs: 28.25 | +7: iteration 29770/ 37905 | consumed samples: 7621120 | consumed tokens: 15608053760 | elapsed time per iteration (s): 0.23 | learning rate: 4.008E-05 | global batch size: 256 | lm loss: 3.337708E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.344 | TFLOPs: 28.67 | +7: iteration 29780/ 37905 | consumed samples: 7623680 | consumed tokens: 15613296640 | elapsed time per iteration (s): 0.23 | learning rate: 4.003E-05 | global batch size: 256 | lm loss: 3.321367E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.951 | TFLOPs: 28.23 | +7: iteration 29790/ 37905 | consumed samples: 7626240 | consumed tokens: 15618539520 | elapsed time per iteration (s): 0.23 | learning rate: 3.998E-05 | global batch size: 256 | lm loss: 3.341122E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.282 | TFLOPs: 28.69 | +7: iteration 29800/ 37905 | consumed samples: 7628800 | consumed tokens: 15623782400 | elapsed time per iteration (s): 0.23 | learning rate: 3.994E-05 | global batch size: 256 | lm loss: 3.353889E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.805 | TFLOPs: 28.65 | +7: iteration 29810/ 37905 | consumed samples: 7631360 | consumed tokens: 15629025280 | elapsed time per iteration (s): 0.23 | learning rate: 3.989E-05 | global batch size: 256 | lm loss: 3.321304E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.830 | TFLOPs: 28.68 | +7: iteration 29820/ 37905 | consumed samples: 7633920 | consumed tokens: 15634268160 | elapsed time per iteration (s): 0.23 | learning rate: 3.984E-05 | global batch size: 256 | lm loss: 3.337597E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.139 | TFLOPs: 28.51 | +7: iteration 29830/ 37905 | consumed samples: 7636480 | consumed tokens: 15639511040 | elapsed time per iteration (s): 0.23 | learning rate: 3.979E-05 | global batch size: 256 | lm loss: 3.317682E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.931 | TFLOPs: 28.63 | +7: iteration 29840/ 37905 | consumed samples: 7639040 | consumed tokens: 15644753920 | elapsed time per iteration (s): 0.23 | learning rate: 3.975E-05 | global batch size: 256 | lm loss: 3.330559E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.919 | TFLOPs: 28.63 | +7: iteration 29850/ 37905 | consumed samples: 7641600 | consumed tokens: 15649996800 | elapsed time per iteration (s): 0.23 | learning rate: 3.970E-05 | global batch size: 256 | lm loss: 3.346377E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.160 | TFLOPs: 28.61 | +7: iteration 29860/ 37905 | consumed samples: 7644160 | consumed tokens: 15655239680 | elapsed time per iteration (s): 0.23 | learning rate: 3.965E-05 | global batch size: 256 | lm loss: 3.298358E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.407 | TFLOPs: 28.62 | +7: iteration 29870/ 37905 | consumed samples: 7646720 | consumed tokens: 15660482560 | elapsed time per iteration (s): 0.23 | learning rate: 3.961E-05 | global batch size: 256 | lm loss: 3.319057E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.138 | TFLOPs: 28.56 | +7: iteration 29880/ 37905 | consumed samples: 7649280 | consumed tokens: 15665725440 | elapsed time per iteration (s): 0.23 | learning rate: 3.956E-05 | global batch size: 256 | lm loss: 3.289118E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.646 | TFLOPs: 28.65 | +7: iteration 29890/ 37905 | consumed samples: 7651840 | consumed tokens: 15670968320 | elapsed time per iteration (s): 0.23 | learning rate: 3.951E-05 | global batch size: 256 | lm loss: 3.336617E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.013 | TFLOPs: 28.61 | +7: iteration 29900/ 37905 | consumed samples: 7654400 | consumed tokens: 15676211200 | elapsed time per iteration (s): 0.23 | learning rate: 3.947E-05 | global batch size: 256 | lm loss: 3.324986E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.241 | TFLOPs: 28.54 | +7: iteration 29910/ 37905 | consumed samples: 7656960 | consumed tokens: 15681454080 | elapsed time per iteration (s): 0.23 | learning rate: 3.942E-05 | global batch size: 256 | lm loss: 3.349503E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.494 | TFLOPs: 28.29 | +7: iteration 29920/ 37905 | consumed samples: 7659520 | consumed tokens: 15686696960 | elapsed time per iteration (s): 0.23 | learning rate: 3.937E-05 | global batch size: 256 | lm loss: 3.313522E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.880 | TFLOPs: 28.50 | +7: iteration 29930/ 37905 | consumed samples: 7662080 | consumed tokens: 15691939840 | elapsed time per iteration (s): 0.23 | learning rate: 3.933E-05 | global batch size: 256 | lm loss: 3.333324E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.240 | TFLOPs: 28.51 | +7: iteration 29940/ 37905 | consumed samples: 7664640 | consumed tokens: 15697182720 | elapsed time per iteration (s): 0.23 | learning rate: 3.928E-05 | global batch size: 256 | lm loss: 3.336943E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.894 | TFLOPs: 28.61 | +7: iteration 29950/ 37905 | consumed samples: 7667200 | consumed tokens: 15702425600 | elapsed time per iteration (s): 0.23 | learning rate: 3.923E-05 | global batch size: 256 | lm loss: 3.309348E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.391 | TFLOPs: 28.01 | +7: iteration 29960/ 37905 | consumed samples: 7669760 | consumed tokens: 15707668480 | elapsed time per iteration (s): 0.23 | learning rate: 3.919E-05 | global batch size: 256 | lm loss: 3.329012E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.013 | TFLOPs: 28.71 | +7: iteration 29970/ 37905 | consumed samples: 7672320 | consumed tokens: 15712911360 | elapsed time per iteration (s): 0.23 | learning rate: 3.914E-05 | global batch size: 256 | lm loss: 3.324152E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.902 | TFLOPs: 28.73 | +7: iteration 29980/ 37905 | consumed samples: 7674880 | consumed tokens: 15718154240 | elapsed time per iteration (s): 0.23 | learning rate: 3.909E-05 | global batch size: 256 | lm loss: 3.309459E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.016 | TFLOPs: 28.66 | +7: iteration 29990/ 37905 | consumed samples: 7677440 | consumed tokens: 15723397120 | elapsed time per iteration (s): 0.23 | learning rate: 3.905E-05 | global batch size: 256 | lm loss: 3.336629E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.101 | TFLOPs: 28.15 | +0: [2022-11-29 18:54:28,718] [INFO] [logging.py:68:log_dist] [Rank 0] step=30000, skipped=0, lr=[3.899987415428045e-05, 3.899987415428045e-05, 3.899987415428045e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 30000/ 37905 | consumed samples: 7680000 | consumed tokens: 15728640000 | elapsed time per iteration (s): 0.23 | learning rate: 3.900E-05 | global batch size: 256 | lm loss: 3.339225E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.723 | TFLOPs: 28.68 | +0: steps: 30000 loss: 3.3974 iter time (s): 0.228 samples/sec: 1121.367 +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 30000 | lm loss value: 3.145859E+00 | lm loss PPL: 2.323964E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 30000 to checkpoints_83moscar +0: [2022-11-29 18:54:28,808] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step30000 is begin to save! +0: [2022-11-29 18:54:28,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:54:28,895] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:54:28,896] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:54:28,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:54:28,908] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:54:28,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:54:28,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:54:28,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:54:28,931] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:54:28,942] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:54:28,943] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:54:28,954] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:54:28,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:54:28,965] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:54:28,965] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:54:28,976] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:54:28,977] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:54:28,988] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:54:28,988] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:54:28,999] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:54:28,999] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:54:29,011] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:54:29,011] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:54:29,012] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:54:29,013] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step30000/mp_rank_00_model_states.pt +0: [2022-11-29 18:54:29,013] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:54:29,015] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:54:29,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:54:29,052] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:54:29,052] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:54:29,052] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +3: [2022-11-29 18:54:29,053] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:54:29,053] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:54:29,053] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +0: [2022-11-29 18:54:29,053] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:54:29,053] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:54:29,054] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:54:29,054] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +2: [2022-11-29 18:54:29,054] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:54:29,054] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:54:29,054] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +1: [2022-11-29 18:54:29,054] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:54:29,054] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:54:29,054] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +5: [2022-11-29 18:54:29,054] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:54:29,054] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +1: [2022-11-29 18:54:29,054] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +4: [2022-11-29 18:54:29,054] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +5: [2022-11-29 18:54:29,054] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 18:54:29,054] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +0: [2022-11-29 18:54:29,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +1: [2022-11-29 18:54:29,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:54:29,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +1: [2022-11-29 18:54:29,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:54:29,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +3: [2022-11-29 18:54:29,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:54:29,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 18:54:29,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +1: [2022-11-29 18:54:29,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:54:29,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:54:29,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +7: [2022-11-29 18:54:29,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:54:29,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:54:29,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:54:29,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 18:54:29,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +7: [2022-11-29 18:54:29,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +0: [2022-11-29 18:54:29,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:54:29,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +4: [2022-11-29 18:54:29,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:54:29,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +4: [2022-11-29 18:54:29,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:54:29,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +2: [2022-11-29 18:54:29,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:54:29,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:54:29,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +5: [2022-11-29 18:54:29,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:54:29,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:54:29,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +5: [2022-11-29 18:54:29,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:54:29,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:54:29,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 18:54:29,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +3: [2022-11-29 18:54:29,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +5: [2022-11-29 18:54:29,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +7: [2022-11-29 18:54:29,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:54:29,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:54:29,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:54:29,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +4: [2022-11-29 18:54:29,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:54:29,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +0: [2022-11-29 18:54:29,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:54:29,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 18:54:29,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +0: [2022-11-29 18:54:29,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:54:29,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 18:54:29,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +3: [2022-11-29 18:54:29,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:54:29,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +6: [2022-11-29 18:54:29,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:54:29,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +3: [2022-11-29 18:54:29,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +6: [2022-11-29 18:54:29,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +2: [2022-11-29 18:54:29,058] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:54:29,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 18:54:29,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +7: [2022-11-29 18:54:29,058] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:54:29,058] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:54:29,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +1: [2022-11-29 18:54:29,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +7: [2022-11-29 18:54:29,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +1: [2022-11-29 18:54:29,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +6: [2022-11-29 18:54:29,058] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:54:29,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:54:29,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +1: [2022-11-29 18:54:29,058] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:54:29,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:54:29,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +5: [2022-11-29 18:54:29,058] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:54:29,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:54:29,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +3: [2022-11-29 18:54:29,058] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:54:29,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:54:29,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +6: [2022-11-29 18:54:29,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:54:29,059] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:54:29,059] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +4: [2022-11-29 18:54:29,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:54:29,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:54:29,059] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +7: [2022-11-29 18:54:29,059] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +4: [2022-11-29 18:54:29,059] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +7: [2022-11-29 18:54:29,059] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +3: [2022-11-29 18:54:29,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:54:29,059] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:54:29,059] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +5: [2022-11-29 18:54:29,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:54:29,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:54:29,059] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 18:54:29,059] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +4: [2022-11-29 18:54:29,059] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:54:29,060] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +2: [2022-11-29 18:54:29,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:54:29,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:54:29,060] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +0: [2022-11-29 18:54:29,060] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +2: [2022-11-29 18:54:29,060] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +0: [2022-11-29 18:54:29,060] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +2: [2022-11-29 18:54:29,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:54:29,060] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:54:29,060] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +1: [2022-11-29 18:54:29,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:54:29,060] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 18:54:29,060] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +0: [2022-11-29 18:54:29,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:54:29,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:54:29,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +2: [2022-11-29 18:54:29,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:54:29,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 18:54:29,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +6: [2022-11-29 18:54:29,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:54:29,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:54:29,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:54:29,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +4: [2022-11-29 18:54:29,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:54:29,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +5: [2022-11-29 18:54:29,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:54:29,062] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 18:54:29,062] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +1: [2022-11-29 18:54:29,062] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:54:29,062] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 18:54:29,062] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +4: [2022-11-29 18:54:29,062] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:54:29,062] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:54:29,062] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +6: [2022-11-29 18:54:29,062] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:54:29,062] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:54:29,062] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +6: [2022-11-29 18:54:29,062] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +6: [2022-11-29 18:54:29,062] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 18:54:29,062] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +5: [2022-11-29 18:54:29,062] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:54:29,062] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 18:54:29,062] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +7: [2022-11-29 18:54:29,062] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:54:29,063] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +0: [2022-11-29 18:54:29,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:54:29,063] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +0: [2022-11-29 18:54:29,063] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 18:54:29,063] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +7: [2022-11-29 18:54:29,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:54:29,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:54:29,063] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +5: [2022-11-29 18:54:29,063] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +7: [2022-11-29 18:54:29,063] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +5: [2022-11-29 18:54:29,063] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +4: [2022-11-29 18:54:29,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:54:29,063] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 18:54:29,063] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +7: [2022-11-29 18:54:29,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:54:29,063] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 18:54:29,063] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +3: [2022-11-29 18:54:29,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:54:29,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:54:29,063] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:54:29,063] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +0: [2022-11-29 18:54:29,063] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +2: [2022-11-29 18:54:29,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:54:29,063] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +2: [2022-11-29 18:54:29,063] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:54:29,064] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +2: [2022-11-29 18:54:29,064] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:54:29,064] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 18:54:29,064] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +3: [2022-11-29 18:54:29,064] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:54:29,064] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:54:29,064] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +1: [2022-11-29 18:54:29,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:54:29,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step30000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 18:54:29,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +0: successfully saved checkpoint at iteration 30000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 263.11 +7: iteration 30010/ 37905 | consumed samples: 7682560 | consumed tokens: 15733882880 | elapsed time per iteration (s): 0.26 | learning rate: 3.895E-05 | global batch size: 256 | lm loss: 3.285838E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 976.517 | TFLOPs: 24.88 | +7: iteration 30020/ 37905 | consumed samples: 7685120 | consumed tokens: 15739125760 | elapsed time per iteration (s): 0.23 | learning rate: 3.891E-05 | global batch size: 256 | lm loss: 3.301496E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.881 | TFLOPs: 28.78 | +7: iteration 30030/ 37905 | consumed samples: 7687680 | consumed tokens: 15744368640 | elapsed time per iteration (s): 0.23 | learning rate: 3.886E-05 | global batch size: 256 | lm loss: 3.301265E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.091 | TFLOPs: 28.76 | +7: iteration 30040/ 37905 | consumed samples: 7690240 | consumed tokens: 15749611520 | elapsed time per iteration (s): 0.23 | learning rate: 3.882E-05 | global batch size: 256 | lm loss: 3.348471E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.590 | TFLOPs: 28.80 | +7: iteration 30050/ 37905 | consumed samples: 7692800 | consumed tokens: 15754854400 | elapsed time per iteration (s): 0.23 | learning rate: 3.877E-05 | global batch size: 256 | lm loss: 3.334138E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.994 | TFLOPs: 28.74 | +7: iteration 30060/ 37905 | consumed samples: 7695360 | consumed tokens: 15760097280 | elapsed time per iteration (s): 0.23 | learning rate: 3.872E-05 | global batch size: 256 | lm loss: 3.326602E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.915 | TFLOPs: 28.68 | +7: iteration 30070/ 37905 | consumed samples: 7697920 | consumed tokens: 15765340160 | elapsed time per iteration (s): 0.25 | learning rate: 3.868E-05 | global batch size: 256 | lm loss: 3.350653E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1038.742 | TFLOPs: 26.46 | +7: iteration 30080/ 37905 | consumed samples: 7700480 | consumed tokens: 15770583040 | elapsed time per iteration (s): 0.24 | learning rate: 3.863E-05 | global batch size: 256 | lm loss: 3.323735E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.466 | TFLOPs: 27.73 | +7: iteration 30090/ 37905 | consumed samples: 7703040 | consumed tokens: 15775825920 | elapsed time per iteration (s): 0.23 | learning rate: 3.859E-05 | global batch size: 256 | lm loss: 3.309145E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.619 | TFLOPs: 28.60 | +7: iteration 30100/ 37905 | consumed samples: 7705600 | consumed tokens: 15781068800 | elapsed time per iteration (s): 0.23 | learning rate: 3.854E-05 | global batch size: 256 | lm loss: 3.339029E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.538 | TFLOPs: 28.70 | +7: iteration 30110/ 37905 | consumed samples: 7708160 | consumed tokens: 15786311680 | elapsed time per iteration (s): 0.23 | learning rate: 3.849E-05 | global batch size: 256 | lm loss: 3.322818E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.589 | TFLOPs: 28.62 | +7: iteration 30120/ 37905 | consumed samples: 7710720 | consumed tokens: 15791554560 | elapsed time per iteration (s): 0.23 | learning rate: 3.845E-05 | global batch size: 256 | lm loss: 3.304965E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.884 | TFLOPs: 28.73 | +7: iteration 30130/ 37905 | consumed samples: 7713280 | consumed tokens: 15796797440 | elapsed time per iteration (s): 0.23 | learning rate: 3.840E-05 | global batch size: 256 | lm loss: 3.314509E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.692 | TFLOPs: 28.68 | +7: iteration 30140/ 37905 | consumed samples: 7715840 | consumed tokens: 15802040320 | elapsed time per iteration (s): 0.23 | learning rate: 3.836E-05 | global batch size: 256 | lm loss: 3.347651E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.092 | TFLOPs: 28.13 | +7: iteration 30150/ 37905 | consumed samples: 7718400 | consumed tokens: 15807283200 | elapsed time per iteration (s): 0.23 | learning rate: 3.831E-05 | global batch size: 256 | lm loss: 3.324256E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.194 | TFLOPs: 28.61 | +7: iteration 30160/ 37905 | consumed samples: 7720960 | consumed tokens: 15812526080 | elapsed time per iteration (s): 0.23 | learning rate: 3.827E-05 | global batch size: 256 | lm loss: 3.341059E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.129 | TFLOPs: 28.59 | +7: iteration 30170/ 37905 | consumed samples: 7723520 | consumed tokens: 15817768960 | elapsed time per iteration (s): 0.23 | learning rate: 3.822E-05 | global batch size: 256 | lm loss: 3.300782E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.229 | TFLOPs: 28.64 | +7: iteration 30180/ 37905 | consumed samples: 7726080 | consumed tokens: 15823011840 | elapsed time per iteration (s): 0.23 | learning rate: 3.817E-05 | global batch size: 256 | lm loss: 3.341695E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.236 | TFLOPs: 28.67 | +7: iteration 30190/ 37905 | consumed samples: 7728640 | consumed tokens: 15828254720 | elapsed time per iteration (s): 0.23 | learning rate: 3.813E-05 | global batch size: 256 | lm loss: 3.364968E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.757 | TFLOPs: 28.53 | +7: iteration 30200/ 37905 | consumed samples: 7731200 | consumed tokens: 15833497600 | elapsed time per iteration (s): 0.23 | learning rate: 3.808E-05 | global batch size: 256 | lm loss: 3.335720E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.545 | TFLOPs: 28.60 | +7: iteration 30210/ 37905 | consumed samples: 7733760 | consumed tokens: 15838740480 | elapsed time per iteration (s): 0.23 | learning rate: 3.804E-05 | global batch size: 256 | lm loss: 3.291320E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.836 | TFLOPs: 28.27 | +7: iteration 30220/ 37905 | consumed samples: 7736320 | consumed tokens: 15843983360 | elapsed time per iteration (s): 0.23 | learning rate: 3.799E-05 | global batch size: 256 | lm loss: 3.323170E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.312 | TFLOPs: 28.69 | +7: iteration 30230/ 37905 | consumed samples: 7738880 | consumed tokens: 15849226240 | elapsed time per iteration (s): 0.23 | learning rate: 3.795E-05 | global batch size: 256 | lm loss: 3.362861E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.002 | TFLOPs: 28.69 | +7: iteration 30240/ 37905 | consumed samples: 7741440 | consumed tokens: 15854469120 | elapsed time per iteration (s): 0.23 | learning rate: 3.790E-05 | global batch size: 256 | lm loss: 3.342221E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.831 | TFLOPs: 28.60 | +7: iteration 30250/ 37905 | consumed samples: 7744000 | consumed tokens: 15859712000 | elapsed time per iteration (s): 0.24 | learning rate: 3.786E-05 | global batch size: 256 | lm loss: 3.332235E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1068.011 | TFLOPs: 27.21 | +7: iteration 30260/ 37905 | consumed samples: 7746560 | consumed tokens: 15864954880 | elapsed time per iteration (s): 0.23 | learning rate: 3.781E-05 | global batch size: 256 | lm loss: 3.314394E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.846 | TFLOPs: 28.73 | +7: iteration 30270/ 37905 | consumed samples: 7749120 | consumed tokens: 15870197760 | elapsed time per iteration (s): 0.23 | learning rate: 3.777E-05 | global batch size: 256 | lm loss: 3.349133E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1132.457 | TFLOPs: 28.85 | +7: iteration 30280/ 37905 | consumed samples: 7751680 | consumed tokens: 15875440640 | elapsed time per iteration (s): 0.23 | learning rate: 3.772E-05 | global batch size: 256 | lm loss: 3.298938E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.933 | TFLOPs: 28.79 | +7: iteration 30290/ 37905 | consumed samples: 7754240 | consumed tokens: 15880683520 | elapsed time per iteration (s): 0.23 | learning rate: 3.768E-05 | global batch size: 256 | lm loss: 3.330964E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.996 | TFLOPs: 28.76 | +7: iteration 30300/ 37905 | consumed samples: 7756800 | consumed tokens: 15885926400 | elapsed time per iteration (s): 0.23 | learning rate: 3.763E-05 | global batch size: 256 | lm loss: 3.311493E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.242 | TFLOPs: 28.56 | +7: iteration 30310/ 37905 | consumed samples: 7759360 | consumed tokens: 15891169280 | elapsed time per iteration (s): 0.23 | learning rate: 3.759E-05 | global batch size: 256 | lm loss: 3.317888E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1131.367 | TFLOPs: 28.82 | +7: iteration 30320/ 37905 | consumed samples: 7761920 | consumed tokens: 15896412160 | elapsed time per iteration (s): 0.23 | learning rate: 3.754E-05 | global batch size: 256 | lm loss: 3.353241E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.461 | TFLOPs: 28.70 | +7: iteration 30330/ 37905 | consumed samples: 7764480 | consumed tokens: 15901655040 | elapsed time per iteration (s): 0.23 | learning rate: 3.750E-05 | global batch size: 256 | lm loss: 3.294197E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.565 | TFLOPs: 28.80 | +7: iteration 30340/ 37905 | consumed samples: 7767040 | consumed tokens: 15906897920 | elapsed time per iteration (s): 0.24 | learning rate: 3.745E-05 | global batch size: 256 | lm loss: 3.296783E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.614 | TFLOPs: 27.48 | +7: iteration 30350/ 37905 | consumed samples: 7769600 | consumed tokens: 15912140800 | elapsed time per iteration (s): 0.23 | learning rate: 3.741E-05 | global batch size: 256 | lm loss: 3.325623E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.508 | TFLOPs: 28.04 | +7: iteration 30360/ 37905 | consumed samples: 7772160 | consumed tokens: 15917383680 | elapsed time per iteration (s): 0.23 | learning rate: 3.737E-05 | global batch size: 256 | lm loss: 3.348677E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.633 | TFLOPs: 28.73 | +7: iteration 30370/ 37905 | consumed samples: 7774720 | consumed tokens: 15922626560 | elapsed time per iteration (s): 0.23 | learning rate: 3.732E-05 | global batch size: 256 | lm loss: 3.311657E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.103 | TFLOPs: 28.71 | +7: iteration 30380/ 37905 | consumed samples: 7777280 | consumed tokens: 15927869440 | elapsed time per iteration (s): 0.23 | learning rate: 3.728E-05 | global batch size: 256 | lm loss: 3.311021E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.909 | TFLOPs: 28.15 | +7: iteration 30390/ 37905 | consumed samples: 7779840 | consumed tokens: 15933112320 | elapsed time per iteration (s): 0.23 | learning rate: 3.723E-05 | global batch size: 256 | lm loss: 3.352658E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.485 | TFLOPs: 28.54 | +7: iteration 30400/ 37905 | consumed samples: 7782400 | consumed tokens: 15938355200 | elapsed time per iteration (s): 0.23 | learning rate: 3.719E-05 | global batch size: 256 | lm loss: 3.328450E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.934 | TFLOPs: 28.68 | +7: iteration 30410/ 37905 | consumed samples: 7784960 | consumed tokens: 15943598080 | elapsed time per iteration (s): 0.23 | learning rate: 3.714E-05 | global batch size: 256 | lm loss: 3.355536E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.498 | TFLOPs: 28.75 | +7: iteration 30420/ 37905 | consumed samples: 7787520 | consumed tokens: 15948840960 | elapsed time per iteration (s): 0.23 | learning rate: 3.710E-05 | global batch size: 256 | lm loss: 3.314703E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.492 | TFLOPs: 28.37 | +7: iteration 30430/ 37905 | consumed samples: 7790080 | consumed tokens: 15954083840 | elapsed time per iteration (s): 0.23 | learning rate: 3.706E-05 | global batch size: 256 | lm loss: 3.305442E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.101 | TFLOPs: 28.71 | +7: iteration 30440/ 37905 | consumed samples: 7792640 | consumed tokens: 15959326720 | elapsed time per iteration (s): 0.24 | learning rate: 3.701E-05 | global batch size: 256 | lm loss: 3.319253E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1050.785 | TFLOPs: 26.77 | +7: iteration 30450/ 37905 | consumed samples: 7795200 | consumed tokens: 15964569600 | elapsed time per iteration (s): 0.23 | learning rate: 3.697E-05 | global batch size: 256 | lm loss: 3.320589E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.799 | TFLOPs: 28.81 | +7: iteration 30460/ 37905 | consumed samples: 7797760 | consumed tokens: 15969812480 | elapsed time per iteration (s): 0.23 | learning rate: 3.692E-05 | global batch size: 256 | lm loss: 3.314874E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.230 | TFLOPs: 28.56 | +7: iteration 30470/ 37905 | consumed samples: 7800320 | consumed tokens: 15975055360 | elapsed time per iteration (s): 0.23 | learning rate: 3.688E-05 | global batch size: 256 | lm loss: 3.319996E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.872 | TFLOPs: 28.53 | +7: iteration 30480/ 37905 | consumed samples: 7802880 | consumed tokens: 15980298240 | elapsed time per iteration (s): 0.23 | learning rate: 3.684E-05 | global batch size: 256 | lm loss: 3.325621E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.641 | TFLOPs: 27.91 | +7: iteration 30490/ 37905 | consumed samples: 7805440 | consumed tokens: 15985541120 | elapsed time per iteration (s): 0.23 | learning rate: 3.679E-05 | global batch size: 256 | lm loss: 3.326538E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.698 | TFLOPs: 28.78 | +7: iteration 30500/ 37905 | consumed samples: 7808000 | consumed tokens: 15990784000 | elapsed time per iteration (s): 0.23 | learning rate: 3.675E-05 | global batch size: 256 | lm loss: 3.338574E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1131.026 | TFLOPs: 28.81 | +7: iteration 30510/ 37905 | consumed samples: 7810560 | consumed tokens: 15996026880 | elapsed time per iteration (s): 0.23 | learning rate: 3.670E-05 | global batch size: 256 | lm loss: 3.328519E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.594 | TFLOPs: 28.80 | +7: iteration 30520/ 37905 | consumed samples: 7813120 | consumed tokens: 16001269760 | elapsed time per iteration (s): 0.23 | learning rate: 3.666E-05 | global batch size: 256 | lm loss: 3.289561E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1131.301 | TFLOPs: 28.82 | +7: iteration 30530/ 37905 | consumed samples: 7815680 | consumed tokens: 16006512640 | elapsed time per iteration (s): 0.23 | learning rate: 3.662E-05 | global batch size: 256 | lm loss: 3.319391E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.586 | TFLOPs: 28.62 | +7: iteration 30540/ 37905 | consumed samples: 7818240 | consumed tokens: 16011755520 | elapsed time per iteration (s): 0.23 | learning rate: 3.657E-05 | global batch size: 256 | lm loss: 3.334476E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.482 | TFLOPs: 28.67 | +7: iteration 30550/ 37905 | consumed samples: 7820800 | consumed tokens: 16016998400 | elapsed time per iteration (s): 0.23 | learning rate: 3.653E-05 | global batch size: 256 | lm loss: 3.326196E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.377 | TFLOPs: 28.59 | +7: iteration 30560/ 37905 | consumed samples: 7823360 | consumed tokens: 16022241280 | elapsed time per iteration (s): 0.23 | learning rate: 3.649E-05 | global batch size: 256 | lm loss: 3.325817E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.229 | TFLOPs: 28.00 | +7: iteration 30570/ 37905 | consumed samples: 7825920 | consumed tokens: 16027484160 | elapsed time per iteration (s): 0.23 | learning rate: 3.644E-05 | global batch size: 256 | lm loss: 3.318776E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.472 | TFLOPs: 28.67 | +7: iteration 30580/ 37905 | consumed samples: 7828480 | consumed tokens: 16032727040 | elapsed time per iteration (s): 0.23 | learning rate: 3.640E-05 | global batch size: 256 | lm loss: 3.316251E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.866 | TFLOPs: 28.68 | +7: iteration 30590/ 37905 | consumed samples: 7831040 | consumed tokens: 16037969920 | elapsed time per iteration (s): 0.23 | learning rate: 3.636E-05 | global batch size: 256 | lm loss: 3.329066E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.223 | TFLOPs: 28.72 | +7: iteration 30600/ 37905 | consumed samples: 7833600 | consumed tokens: 16043212800 | elapsed time per iteration (s): 0.23 | learning rate: 3.631E-05 | global batch size: 256 | lm loss: 3.277071E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.911 | TFLOPs: 27.99 | +7: iteration 30610/ 37905 | consumed samples: 7836160 | consumed tokens: 16048455680 | elapsed time per iteration (s): 0.23 | learning rate: 3.627E-05 | global batch size: 256 | lm loss: 3.349814E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.069 | TFLOPs: 28.71 | +7: iteration 30620/ 37905 | consumed samples: 7838720 | consumed tokens: 16053698560 | elapsed time per iteration (s): 0.23 | learning rate: 3.623E-05 | global batch size: 256 | lm loss: 3.327613E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.781 | TFLOPs: 28.68 | +7: iteration 30630/ 37905 | consumed samples: 7841280 | consumed tokens: 16058941440 | elapsed time per iteration (s): 0.23 | learning rate: 3.618E-05 | global batch size: 256 | lm loss: 3.342648E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.760 | TFLOPs: 28.35 | +7: iteration 30640/ 37905 | consumed samples: 7843840 | consumed tokens: 16064184320 | elapsed time per iteration (s): 0.23 | learning rate: 3.614E-05 | global batch size: 256 | lm loss: 3.340500E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.376 | TFLOPs: 28.75 | +7: iteration 30650/ 37905 | consumed samples: 7846400 | consumed tokens: 16069427200 | elapsed time per iteration (s): 0.23 | learning rate: 3.610E-05 | global batch size: 256 | lm loss: 3.345251E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.916 | TFLOPs: 28.33 | +7: iteration 30660/ 37905 | consumed samples: 7848960 | consumed tokens: 16074670080 | elapsed time per iteration (s): 0.23 | learning rate: 3.605E-05 | global batch size: 256 | lm loss: 3.340315E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.344 | TFLOPs: 28.52 | +7: iteration 30670/ 37905 | consumed samples: 7851520 | consumed tokens: 16079912960 | elapsed time per iteration (s): 0.23 | learning rate: 3.601E-05 | global batch size: 256 | lm loss: 3.333261E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.131 | TFLOPs: 28.59 | +7: iteration 30680/ 37905 | consumed samples: 7854080 | consumed tokens: 16085155840 | elapsed time per iteration (s): 0.23 | learning rate: 3.597E-05 | global batch size: 256 | lm loss: 3.335056E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.360 | TFLOPs: 28.80 | +7: iteration 30690/ 37905 | consumed samples: 7856640 | consumed tokens: 16090398720 | elapsed time per iteration (s): 0.23 | learning rate: 3.593E-05 | global batch size: 256 | lm loss: 3.307508E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.743 | TFLOPs: 28.75 | +7: iteration 30700/ 37905 | consumed samples: 7859200 | consumed tokens: 16095641600 | elapsed time per iteration (s): 0.23 | learning rate: 3.588E-05 | global batch size: 256 | lm loss: 3.316306E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.281 | TFLOPs: 28.77 | +7: iteration 30710/ 37905 | consumed samples: 7861760 | consumed tokens: 16100884480 | elapsed time per iteration (s): 0.23 | learning rate: 3.584E-05 | global batch size: 256 | lm loss: 3.310652E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.833 | TFLOPs: 28.76 | +7: iteration 30720/ 37905 | consumed samples: 7864320 | consumed tokens: 16106127360 | elapsed time per iteration (s): 0.23 | learning rate: 3.580E-05 | global batch size: 256 | lm loss: 3.293383E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.630 | TFLOPs: 28.68 | +7: iteration 30730/ 37905 | consumed samples: 7866880 | consumed tokens: 16111370240 | elapsed time per iteration (s): 0.23 | learning rate: 3.575E-05 | global batch size: 256 | lm loss: 3.320333E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.072 | TFLOPs: 27.77 | +7: iteration 30740/ 37905 | consumed samples: 7869440 | consumed tokens: 16116613120 | elapsed time per iteration (s): 0.23 | learning rate: 3.571E-05 | global batch size: 256 | lm loss: 3.337396E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.278 | TFLOPs: 27.83 | +7: iteration 30750/ 37905 | consumed samples: 7872000 | consumed tokens: 16121856000 | elapsed time per iteration (s): 0.23 | learning rate: 3.567E-05 | global batch size: 256 | lm loss: 3.322201E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.469 | TFLOPs: 28.75 | +7: iteration 30760/ 37905 | consumed samples: 7874560 | consumed tokens: 16127098880 | elapsed time per iteration (s): 0.23 | learning rate: 3.563E-05 | global batch size: 256 | lm loss: 3.366527E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.567 | TFLOPs: 28.70 | +7: iteration 30770/ 37905 | consumed samples: 7877120 | consumed tokens: 16132341760 | elapsed time per iteration (s): 0.23 | learning rate: 3.558E-05 | global batch size: 256 | lm loss: 3.331041E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.690 | TFLOPs: 28.32 | +7: iteration 30780/ 37905 | consumed samples: 7879680 | consumed tokens: 16137584640 | elapsed time per iteration (s): 0.23 | learning rate: 3.554E-05 | global batch size: 256 | lm loss: 3.319813E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.240 | TFLOPs: 28.72 | +7: iteration 30790/ 37905 | consumed samples: 7882240 | consumed tokens: 16142827520 | elapsed time per iteration (s): 0.23 | learning rate: 3.550E-05 | global batch size: 256 | lm loss: 3.319653E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.342 | TFLOPs: 28.69 | +7: iteration 30800/ 37905 | consumed samples: 7884800 | consumed tokens: 16148070400 | elapsed time per iteration (s): 0.23 | learning rate: 3.546E-05 | global batch size: 256 | lm loss: 3.317849E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.588 | TFLOPs: 28.70 | +7: iteration 30810/ 37905 | consumed samples: 7887360 | consumed tokens: 16153313280 | elapsed time per iteration (s): 0.23 | learning rate: 3.542E-05 | global batch size: 256 | lm loss: 3.320396E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.166 | TFLOPs: 28.74 | +7: iteration 30820/ 37905 | consumed samples: 7889920 | consumed tokens: 16158556160 | elapsed time per iteration (s): 0.23 | learning rate: 3.537E-05 | global batch size: 256 | lm loss: 3.315646E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.868 | TFLOPs: 28.71 | +7: iteration 30830/ 37905 | consumed samples: 7892480 | consumed tokens: 16163799040 | elapsed time per iteration (s): 0.23 | learning rate: 3.533E-05 | global batch size: 256 | lm loss: 3.300454E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.417 | TFLOPs: 28.67 | +7: iteration 30840/ 37905 | consumed samples: 7895040 | consumed tokens: 16169041920 | elapsed time per iteration (s): 0.23 | learning rate: 3.529E-05 | global batch size: 256 | lm loss: 3.324953E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.826 | TFLOPs: 28.45 | +7: iteration 30850/ 37905 | consumed samples: 7897600 | consumed tokens: 16174284800 | elapsed time per iteration (s): 0.23 | learning rate: 3.525E-05 | global batch size: 256 | lm loss: 3.302943E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.105 | TFLOPs: 28.69 | +7: iteration 30860/ 37905 | consumed samples: 7900160 | consumed tokens: 16179527680 | elapsed time per iteration (s): 0.23 | learning rate: 3.521E-05 | global batch size: 256 | lm loss: 3.311124E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.183 | TFLOPs: 28.69 | +7: iteration 30870/ 37905 | consumed samples: 7902720 | consumed tokens: 16184770560 | elapsed time per iteration (s): 0.23 | learning rate: 3.516E-05 | global batch size: 256 | lm loss: 3.339103E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.610 | TFLOPs: 28.75 | +7: iteration 30880/ 37905 | consumed samples: 7905280 | consumed tokens: 16190013440 | elapsed time per iteration (s): 0.23 | learning rate: 3.512E-05 | global batch size: 256 | lm loss: 3.314863E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.143 | TFLOPs: 28.66 | +7: iteration 30890/ 37905 | consumed samples: 7907840 | consumed tokens: 16195256320 | elapsed time per iteration (s): 0.23 | learning rate: 3.508E-05 | global batch size: 256 | lm loss: 3.324889E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.851 | TFLOPs: 28.53 | +7: iteration 30900/ 37905 | consumed samples: 7910400 | consumed tokens: 16200499200 | elapsed time per iteration (s): 0.23 | learning rate: 3.504E-05 | global batch size: 256 | lm loss: 3.319374E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.294 | TFLOPs: 28.54 | +7: iteration 30910/ 37905 | consumed samples: 7912960 | consumed tokens: 16205742080 | elapsed time per iteration (s): 0.23 | learning rate: 3.500E-05 | global batch size: 256 | lm loss: 3.313008E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.548 | TFLOPs: 28.65 | +7: iteration 30920/ 37905 | consumed samples: 7915520 | consumed tokens: 16210984960 | elapsed time per iteration (s): 0.23 | learning rate: 3.495E-05 | global batch size: 256 | lm loss: 3.362681E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.236 | TFLOPs: 28.72 | +7: iteration 30930/ 37905 | consumed samples: 7918080 | consumed tokens: 16216227840 | elapsed time per iteration (s): 0.23 | learning rate: 3.491E-05 | global batch size: 256 | lm loss: 3.359678E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.335 | TFLOPs: 28.80 | +7: iteration 30940/ 37905 | consumed samples: 7920640 | consumed tokens: 16221470720 | elapsed time per iteration (s): 0.23 | learning rate: 3.487E-05 | global batch size: 256 | lm loss: 3.315410E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.435 | TFLOPs: 28.75 | +7: iteration 30950/ 37905 | consumed samples: 7923200 | consumed tokens: 16226713600 | elapsed time per iteration (s): 0.23 | learning rate: 3.483E-05 | global batch size: 256 | lm loss: 3.314635E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.451 | TFLOPs: 28.65 | +7: iteration 30960/ 37905 | consumed samples: 7925760 | consumed tokens: 16231956480 | elapsed time per iteration (s): 0.23 | learning rate: 3.479E-05 | global batch size: 256 | lm loss: 3.328635E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.298 | TFLOPs: 28.67 | +7: iteration 30970/ 37905 | consumed samples: 7928320 | consumed tokens: 16237199360 | elapsed time per iteration (s): 0.23 | learning rate: 3.475E-05 | global batch size: 256 | lm loss: 3.310030E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.988 | TFLOPs: 28.63 | +7: iteration 30980/ 37905 | consumed samples: 7930880 | consumed tokens: 16242442240 | elapsed time per iteration (s): 0.23 | learning rate: 3.471E-05 | global batch size: 256 | lm loss: 3.336177E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.223 | TFLOPs: 28.61 | +7: iteration 30990/ 37905 | consumed samples: 7933440 | consumed tokens: 16247685120 | elapsed time per iteration (s): 0.23 | learning rate: 3.466E-05 | global batch size: 256 | lm loss: 3.323512E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.162 | TFLOPs: 28.10 | +7: iteration 31000/ 37905 | consumed samples: 7936000 | consumed tokens: 16252928000 | elapsed time per iteration (s): 0.23 | learning rate: 3.462E-05 | global batch size: 256 | lm loss: 3.310997E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.040 | TFLOPs: 28.61 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 31000 | lm loss value: 3.206865E+00 | lm loss PPL: 2.470153E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 31000 to checkpoints_83moscar +0: [2022-11-29 18:58:17,800] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step31000 is begin to save! +0: [2022-11-29 18:58:17,803] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/layer_01-model_00-model_states.pt... +0: [2022-11-29 18:58:17,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/layer_01-model_00-model_states.pt. +0: [2022-11-29 18:58:17,874] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/layer_03-model_00-model_states.pt... +0: [2022-11-29 18:58:17,886] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/layer_03-model_00-model_states.pt. +0: [2022-11-29 18:58:17,886] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/layer_04-model_00-model_states.pt... +0: [2022-11-29 18:58:17,898] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/layer_04-model_00-model_states.pt. +0: [2022-11-29 18:58:17,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/layer_05-model_00-model_states.pt... +0: [2022-11-29 18:58:17,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/layer_05-model_00-model_states.pt. +0: [2022-11-29 18:58:17,909] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/layer_06-model_00-model_states.pt... +0: [2022-11-29 18:58:17,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/layer_06-model_00-model_states.pt. +0: [2022-11-29 18:58:17,920] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/layer_07-model_00-model_states.pt... +0: [2022-11-29 18:58:17,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/layer_07-model_00-model_states.pt. +0: [2022-11-29 18:58:17,931] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/layer_08-model_00-model_states.pt... +0: [2022-11-29 18:58:17,942] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/layer_08-model_00-model_states.pt. +0: [2022-11-29 18:58:17,942] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/layer_09-model_00-model_states.pt... +0: [2022-11-29 18:58:17,953] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/layer_09-model_00-model_states.pt. +0: [2022-11-29 18:58:17,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/layer_10-model_00-model_states.pt... +0: [2022-11-29 18:58:17,964] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/layer_10-model_00-model_states.pt. +0: [2022-11-29 18:58:17,965] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/layer_11-model_00-model_states.pt... +0: [2022-11-29 18:58:17,976] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/layer_11-model_00-model_states.pt. +0: [2022-11-29 18:58:17,976] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/layer_12-model_00-model_states.pt... +0: [2022-11-29 18:58:17,987] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/layer_12-model_00-model_states.pt. +0: [2022-11-29 18:58:17,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/layer_14-model_00-model_states.pt... +0: [2022-11-29 18:58:17,988] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/layer_14-model_00-model_states.pt. +0: [2022-11-29 18:58:17,988] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step31000/mp_rank_00_model_states.pt +0: [2022-11-29 18:58:17,988] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/mp_rank_00_model_states.pt... +0: [2022-11-29 18:58:17,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/mp_rank_00_model_states.pt. +0: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +0: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 18:58:18,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +3: [2022-11-29 18:58:18,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:58:18,026] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 18:58:18,026] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +2: [2022-11-29 18:58:18,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:58:18,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:58:18,026] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 18:58:18,026] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +1: [2022-11-29 18:58:18,027] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:58:18,027] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 18:58:18,027] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +1: [2022-11-29 18:58:18,027] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:58:18,027] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 18:58:18,027] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +5: [2022-11-29 18:58:18,027] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:58:18,027] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 18:58:18,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +7: [2022-11-29 18:58:18,027] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:58:18,028] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 18:58:18,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +4: [2022-11-29 18:58:18,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:58:18,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:58:18,028] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 18:58:18,028] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 18:58:18,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +4: [2022-11-29 18:58:18,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +2: [2022-11-29 18:58:18,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:58:18,028] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 18:58:18,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +0: [2022-11-29 18:58:18,028] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +7: [2022-11-29 18:58:18,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:58:18,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +7: [2022-11-29 18:58:18,028] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +3: [2022-11-29 18:58:18,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:58:18,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +3: [2022-11-29 18:58:18,028] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 18:58:18,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +6: [2022-11-29 18:58:18,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:58:18,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 18:58:18,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:58:18,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +6: [2022-11-29 18:58:18,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 18:58:18,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +1: [2022-11-29 18:58:18,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:58:18,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:58:18,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +0: [2022-11-29 18:58:18,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +1: [2022-11-29 18:58:18,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +0: [2022-11-29 18:58:18,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +5: [2022-11-29 18:58:18,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:58:18,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +2: [2022-11-29 18:58:18,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:58:18,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +2: [2022-11-29 18:58:18,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 18:58:18,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +7: [2022-11-29 18:58:18,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:58:18,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 18:58:18,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +4: [2022-11-29 18:58:18,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:58:18,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 18:58:18,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +0: [2022-11-29 18:58:18,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:58:18,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:58:18,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +5: [2022-11-29 18:58:18,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +0: [2022-11-29 18:58:18,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +5: [2022-11-29 18:58:18,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +2: [2022-11-29 18:58:18,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:58:18,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:58:18,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 18:58:18,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +3: [2022-11-29 18:58:18,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 18:58:18,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +7: [2022-11-29 18:58:18,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:58:18,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 18:58:18,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +4: [2022-11-29 18:58:18,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:58:18,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 18:58:18,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +1: [2022-11-29 18:58:18,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:58:18,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 18:58:18,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +6: [2022-11-29 18:58:18,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:58:18,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 18:58:18,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +3: [2022-11-29 18:58:18,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:58:18,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 18:58:18,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +5: [2022-11-29 18:58:18,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:58:18,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 18:58:18,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +2: [2022-11-29 18:58:18,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:58:18,032] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +0: [2022-11-29 18:58:18,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:58:18,032] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +0: [2022-11-29 18:58:18,032] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 18:58:18,032] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +7: [2022-11-29 18:58:18,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:58:18,032] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 18:58:18,032] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +3: [2022-11-29 18:58:18,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:58:18,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +3: [2022-11-29 18:58:18,033] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +2: [2022-11-29 18:58:18,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:58:18,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:58:18,033] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3: [2022-11-29 18:58:18,033] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +5: [2022-11-29 18:58:18,033] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +0: [2022-11-29 18:58:18,033] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +2: [2022-11-29 18:58:18,033] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +1: [2022-11-29 18:58:18,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:58:18,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:58:18,033] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +1: [2022-11-29 18:58:18,033] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +4: [2022-11-29 18:58:18,033] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +2: [2022-11-29 18:58:18,033] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +1: [2022-11-29 18:58:18,033] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +4: [2022-11-29 18:58:18,033] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +7: [2022-11-29 18:58:18,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:58:18,033] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 18:58:18,033] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +6: [2022-11-29 18:58:18,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:58:18,033] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 18:58:18,033] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +6: [2022-11-29 18:58:18,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:58:18,034] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 18:58:18,034] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +4: [2022-11-29 18:58:18,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:58:18,034] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +3: [2022-11-29 18:58:18,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:58:18,034] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +3: [2022-11-29 18:58:18,034] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 18:58:18,034] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +4: [2022-11-29 18:58:18,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:58:18,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:58:18,034] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +1: [2022-11-29 18:58:18,034] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +4: [2022-11-29 18:58:18,034] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +1: [2022-11-29 18:58:18,034] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +5: [2022-11-29 18:58:18,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:58:18,034] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +3: [2022-11-29 18:58:18,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:58:18,034] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +3: [2022-11-29 18:58:18,034] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 18:58:18,034] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +0: [2022-11-29 18:58:18,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:58:18,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:58:18,034] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 18:58:18,034] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +0: [2022-11-29 18:58:18,035] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 18:58:18,035] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +2: [2022-11-29 18:58:18,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +7: [2022-11-29 18:58:18,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +2: [2022-11-29 18:58:18,035] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +7: [2022-11-29 18:58:18,035] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +2: [2022-11-29 18:58:18,035] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +7: [2022-11-29 18:58:18,035] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +6: [2022-11-29 18:58:18,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:58:18,035] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 18:58:18,035] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +1: [2022-11-29 18:58:18,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:58:18,035] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 18:58:18,035] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +5: [2022-11-29 18:58:18,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:58:18,035] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 18:58:18,036] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +5: [2022-11-29 18:58:18,036] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +1: [2022-11-29 18:58:18,036] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:58:18,036] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +1: [2022-11-29 18:58:18,036] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +3: [2022-11-29 18:58:18,036] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +5: [2022-11-29 18:58:18,036] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +1: [2022-11-29 18:58:18,036] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +3: [2022-11-29 18:58:18,036] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 18:58:18,036] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +4: [2022-11-29 18:58:18,036] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 18:58:18,036] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 18:58:18,036] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +6: [2022-11-29 18:58:18,036] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:58:18,036] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +0: [2022-11-29 18:58:18,036] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:58:18,036] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +7: [2022-11-29 18:58:18,036] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:58:18,036] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +7: [2022-11-29 18:58:18,036] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +0: [2022-11-29 18:58:18,036] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +7: [2022-11-29 18:58:18,036] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +6: [2022-11-29 18:58:18,036] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 18:58:18,036] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 18:58:18,036] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +0: [2022-11-29 18:58:18,037] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 18:58:18,037] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step31000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 18:58:18,037] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +0: successfully saved checkpoint at iteration 31000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 238.94 +7: iteration 31010/ 37905 | consumed samples: 7938560 | consumed tokens: 16258170880 | elapsed time per iteration (s): 0.26 | learning rate: 3.458E-05 | global batch size: 256 | lm loss: 3.302004E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 991.995 | TFLOPs: 25.27 | +7: iteration 31020/ 37905 | consumed samples: 7941120 | consumed tokens: 16263413760 | elapsed time per iteration (s): 0.23 | learning rate: 3.454E-05 | global batch size: 256 | lm loss: 3.325079E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.827 | TFLOPs: 28.66 | +7: iteration 31030/ 37905 | consumed samples: 7943680 | consumed tokens: 16268656640 | elapsed time per iteration (s): 0.23 | learning rate: 3.450E-05 | global batch size: 256 | lm loss: 3.330055E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.608 | TFLOPs: 28.65 | +7: iteration 31040/ 37905 | consumed samples: 7946240 | consumed tokens: 16273899520 | elapsed time per iteration (s): 0.23 | learning rate: 3.446E-05 | global batch size: 256 | lm loss: 3.304229E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.793 | TFLOPs: 28.63 | +7: iteration 31050/ 37905 | consumed samples: 7948800 | consumed tokens: 16279142400 | elapsed time per iteration (s): 0.23 | learning rate: 3.442E-05 | global batch size: 256 | lm loss: 3.311497E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.651 | TFLOPs: 28.68 | +7: iteration 31060/ 37905 | consumed samples: 7951360 | consumed tokens: 16284385280 | elapsed time per iteration (s): 0.23 | learning rate: 3.438E-05 | global batch size: 256 | lm loss: 3.326862E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.266 | TFLOPs: 28.69 | +7: iteration 31070/ 37905 | consumed samples: 7953920 | consumed tokens: 16289628160 | elapsed time per iteration (s): 0.23 | learning rate: 3.434E-05 | global batch size: 256 | lm loss: 3.324636E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.221 | TFLOPs: 28.77 | +7: iteration 31080/ 37905 | consumed samples: 7956480 | consumed tokens: 16294871040 | elapsed time per iteration (s): 0.23 | learning rate: 3.430E-05 | global batch size: 256 | lm loss: 3.315944E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.465 | TFLOPs: 28.59 | +7: iteration 31090/ 37905 | consumed samples: 7959040 | consumed tokens: 16300113920 | elapsed time per iteration (s): 0.23 | learning rate: 3.426E-05 | global batch size: 256 | lm loss: 3.312505E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.014 | TFLOPs: 28.74 | +7: iteration 31100/ 37905 | consumed samples: 7961600 | consumed tokens: 16305356800 | elapsed time per iteration (s): 0.24 | learning rate: 3.421E-05 | global batch size: 256 | lm loss: 3.315036E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1045.221 | TFLOPs: 26.63 | +7: iteration 31110/ 37905 | consumed samples: 7964160 | consumed tokens: 16310599680 | elapsed time per iteration (s): 0.23 | learning rate: 3.417E-05 | global batch size: 256 | lm loss: 3.332518E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.567 | TFLOPs: 28.67 | +7: iteration 31120/ 37905 | consumed samples: 7966720 | consumed tokens: 16315842560 | elapsed time per iteration (s): 0.23 | learning rate: 3.413E-05 | global batch size: 256 | lm loss: 3.299777E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.073 | TFLOPs: 28.69 | +7: iteration 31130/ 37905 | consumed samples: 7969280 | consumed tokens: 16321085440 | elapsed time per iteration (s): 0.23 | learning rate: 3.409E-05 | global batch size: 256 | lm loss: 3.340968E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.158 | TFLOPs: 28.69 | +7: iteration 31140/ 37905 | consumed samples: 7971840 | consumed tokens: 16326328320 | elapsed time per iteration (s): 0.23 | learning rate: 3.405E-05 | global batch size: 256 | lm loss: 3.310889E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.676 | TFLOPs: 28.70 | +7: iteration 31150/ 37905 | consumed samples: 7974400 | consumed tokens: 16331571200 | elapsed time per iteration (s): 0.23 | learning rate: 3.401E-05 | global batch size: 256 | lm loss: 3.327105E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.400 | TFLOPs: 28.64 | +7: iteration 31160/ 37905 | consumed samples: 7976960 | consumed tokens: 16336814080 | elapsed time per iteration (s): 0.23 | learning rate: 3.397E-05 | global batch size: 256 | lm loss: 3.286742E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.549 | TFLOPs: 28.70 | +7: iteration 31170/ 37905 | consumed samples: 7979520 | consumed tokens: 16342056960 | elapsed time per iteration (s): 0.23 | learning rate: 3.393E-05 | global batch size: 256 | lm loss: 3.350854E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.252 | TFLOPs: 28.74 | +7: iteration 31180/ 37905 | consumed samples: 7982080 | consumed tokens: 16347299840 | elapsed time per iteration (s): 0.23 | learning rate: 3.389E-05 | global batch size: 256 | lm loss: 3.320863E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.072 | TFLOPs: 28.18 | +7: iteration 31190/ 37905 | consumed samples: 7984640 | consumed tokens: 16352542720 | elapsed time per iteration (s): 0.23 | learning rate: 3.385E-05 | global batch size: 256 | lm loss: 3.324968E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.946 | TFLOPs: 28.33 | +7: iteration 31200/ 37905 | consumed samples: 7987200 | consumed tokens: 16357785600 | elapsed time per iteration (s): 0.23 | learning rate: 3.381E-05 | global batch size: 256 | lm loss: 3.334008E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.977 | TFLOPs: 28.66 | +7: iteration 31210/ 37905 | consumed samples: 7989760 | consumed tokens: 16363028480 | elapsed time per iteration (s): 0.23 | learning rate: 3.377E-05 | global batch size: 256 | lm loss: 3.337093E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.777 | TFLOPs: 28.73 | +7: iteration 31220/ 37905 | consumed samples: 7992320 | consumed tokens: 16368271360 | elapsed time per iteration (s): 0.23 | learning rate: 3.373E-05 | global batch size: 256 | lm loss: 3.322789E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.838 | TFLOPs: 28.68 | +7: iteration 31230/ 37905 | consumed samples: 7994880 | consumed tokens: 16373514240 | elapsed time per iteration (s): 0.23 | learning rate: 3.369E-05 | global batch size: 256 | lm loss: 3.319491E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.933 | TFLOPs: 28.76 | +7: iteration 31240/ 37905 | consumed samples: 7997440 | consumed tokens: 16378757120 | elapsed time per iteration (s): 0.23 | learning rate: 3.365E-05 | global batch size: 256 | lm loss: 3.331189E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.969 | TFLOPs: 28.74 | +7: iteration 31250/ 37905 | consumed samples: 8000000 | consumed tokens: 16384000000 | elapsed time per iteration (s): 0.23 | learning rate: 3.361E-05 | global batch size: 256 | lm loss: 3.313166E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.533 | TFLOPs: 28.72 | +7: iteration 31260/ 37905 | consumed samples: 8002560 | consumed tokens: 16389242880 | elapsed time per iteration (s): 0.23 | learning rate: 3.357E-05 | global batch size: 256 | lm loss: 3.340868E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.482 | TFLOPs: 28.72 | +7: iteration 31270/ 37905 | consumed samples: 8005120 | consumed tokens: 16394485760 | elapsed time per iteration (s): 0.23 | learning rate: 3.353E-05 | global batch size: 256 | lm loss: 3.334902E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.885 | TFLOPs: 28.76 | +7: iteration 31280/ 37905 | consumed samples: 8007680 | consumed tokens: 16399728640 | elapsed time per iteration (s): 0.23 | learning rate: 3.349E-05 | global batch size: 256 | lm loss: 3.328910E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.879 | TFLOPs: 28.76 | +7: iteration 31290/ 37905 | consumed samples: 8010240 | consumed tokens: 16404971520 | elapsed time per iteration (s): 0.23 | learning rate: 3.345E-05 | global batch size: 256 | lm loss: 3.333797E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.396 | TFLOPs: 28.67 | +7: iteration 31300/ 37905 | consumed samples: 8012800 | consumed tokens: 16410214400 | elapsed time per iteration (s): 0.23 | learning rate: 3.341E-05 | global batch size: 256 | lm loss: 3.315129E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.619 | TFLOPs: 28.68 | +7: iteration 31310/ 37905 | consumed samples: 8015360 | consumed tokens: 16415457280 | elapsed time per iteration (s): 0.25 | learning rate: 3.337E-05 | global batch size: 256 | lm loss: 3.362833E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1043.174 | TFLOPs: 26.58 | +7: iteration 31320/ 37905 | consumed samples: 8017920 | consumed tokens: 16420700160 | elapsed time per iteration (s): 0.23 | learning rate: 3.333E-05 | global batch size: 256 | lm loss: 3.318806E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.978 | TFLOPs: 28.58 | +7: iteration 31330/ 37905 | consumed samples: 8020480 | consumed tokens: 16425943040 | elapsed time per iteration (s): 0.23 | learning rate: 3.329E-05 | global batch size: 256 | lm loss: 3.335138E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.342 | TFLOPs: 28.62 | +7: iteration 31340/ 37905 | consumed samples: 8023040 | consumed tokens: 16431185920 | elapsed time per iteration (s): 0.23 | learning rate: 3.325E-05 | global batch size: 256 | lm loss: 3.309388E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.204 | TFLOPs: 28.59 | +7: iteration 31350/ 37905 | consumed samples: 8025600 | consumed tokens: 16436428800 | elapsed time per iteration (s): 0.23 | learning rate: 3.322E-05 | global batch size: 256 | lm loss: 3.312477E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.813 | TFLOPs: 28.60 | +7: iteration 31360/ 37905 | consumed samples: 8028160 | consumed tokens: 16441671680 | elapsed time per iteration (s): 0.23 | learning rate: 3.318E-05 | global batch size: 256 | lm loss: 3.336930E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.245 | TFLOPs: 28.72 | +7: iteration 31370/ 37905 | consumed samples: 8030720 | consumed tokens: 16446914560 | elapsed time per iteration (s): 0.23 | learning rate: 3.314E-05 | global batch size: 256 | lm loss: 3.315113E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.231 | TFLOPs: 28.56 | +7: iteration 31380/ 37905 | consumed samples: 8033280 | consumed tokens: 16452157440 | elapsed time per iteration (s): 0.23 | learning rate: 3.310E-05 | global batch size: 256 | lm loss: 3.347396E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.766 | TFLOPs: 28.55 | +7: iteration 31390/ 37905 | consumed samples: 8035840 | consumed tokens: 16457400320 | elapsed time per iteration (s): 0.25 | learning rate: 3.306E-05 | global batch size: 256 | lm loss: 3.298336E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1035.254 | TFLOPs: 26.37 | +7: iteration 31400/ 37905 | consumed samples: 8038400 | consumed tokens: 16462643200 | elapsed time per iteration (s): 0.24 | learning rate: 3.302E-05 | global batch size: 256 | lm loss: 3.331708E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1062.058 | TFLOPs: 27.06 | +7: iteration 31410/ 37905 | consumed samples: 8040960 | consumed tokens: 16467886080 | elapsed time per iteration (s): 0.23 | learning rate: 3.298E-05 | global batch size: 256 | lm loss: 3.318478E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.866 | TFLOPs: 28.58 | +7: iteration 31420/ 37905 | consumed samples: 8043520 | consumed tokens: 16473128960 | elapsed time per iteration (s): 0.23 | learning rate: 3.294E-05 | global batch size: 256 | lm loss: 3.287707E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.572 | TFLOPs: 28.50 | +7: iteration 31430/ 37905 | consumed samples: 8046080 | consumed tokens: 16478371840 | elapsed time per iteration (s): 0.23 | learning rate: 3.290E-05 | global batch size: 256 | lm loss: 3.319260E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.177 | TFLOPs: 28.56 | +7: iteration 31440/ 37905 | consumed samples: 8048640 | consumed tokens: 16483614720 | elapsed time per iteration (s): 0.23 | learning rate: 3.286E-05 | global batch size: 256 | lm loss: 3.322900E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.226 | TFLOPs: 28.54 | +7: iteration 31450/ 37905 | consumed samples: 8051200 | consumed tokens: 16488857600 | elapsed time per iteration (s): 0.23 | learning rate: 3.282E-05 | global batch size: 256 | lm loss: 3.337090E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.984 | TFLOPs: 28.56 | +7: iteration 31460/ 37905 | consumed samples: 8053760 | consumed tokens: 16494100480 | elapsed time per iteration (s): 0.23 | learning rate: 3.279E-05 | global batch size: 256 | lm loss: 3.318441E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.175 | TFLOPs: 28.61 | +7: iteration 31470/ 37905 | consumed samples: 8056320 | consumed tokens: 16499343360 | elapsed time per iteration (s): 0.23 | learning rate: 3.275E-05 | global batch size: 256 | lm loss: 3.324588E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.806 | TFLOPs: 28.65 | +7: iteration 31480/ 37905 | consumed samples: 8058880 | consumed tokens: 16504586240 | elapsed time per iteration (s): 0.23 | learning rate: 3.271E-05 | global batch size: 256 | lm loss: 3.335597E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.191 | TFLOPs: 28.61 | +7: iteration 31490/ 37905 | consumed samples: 8061440 | consumed tokens: 16509829120 | elapsed time per iteration (s): 0.23 | learning rate: 3.267E-05 | global batch size: 256 | lm loss: 3.313470E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.292 | TFLOPs: 28.59 | +7: iteration 31500/ 37905 | consumed samples: 8064000 | consumed tokens: 16515072000 | elapsed time per iteration (s): 0.23 | learning rate: 3.263E-05 | global batch size: 256 | lm loss: 3.345725E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.013 | TFLOPs: 28.58 | +7: iteration 31510/ 37905 | consumed samples: 8066560 | consumed tokens: 16520314880 | elapsed time per iteration (s): 0.23 | learning rate: 3.259E-05 | global batch size: 256 | lm loss: 3.340763E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.725 | TFLOPs: 28.60 | +7: iteration 31520/ 37905 | consumed samples: 8069120 | consumed tokens: 16525557760 | elapsed time per iteration (s): 0.23 | learning rate: 3.255E-05 | global batch size: 256 | lm loss: 3.315766E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.454 | TFLOPs: 28.57 | +7: iteration 31530/ 37905 | consumed samples: 8071680 | consumed tokens: 16530800640 | elapsed time per iteration (s): 0.23 | learning rate: 3.252E-05 | global batch size: 256 | lm loss: 3.319745E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.652 | TFLOPs: 28.60 | +7: iteration 31540/ 37905 | consumed samples: 8074240 | consumed tokens: 16536043520 | elapsed time per iteration (s): 0.23 | learning rate: 3.248E-05 | global batch size: 256 | lm loss: 3.302713E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.286 | TFLOPs: 28.62 | +7: iteration 31550/ 37905 | consumed samples: 8076800 | consumed tokens: 16541286400 | elapsed time per iteration (s): 0.23 | learning rate: 3.244E-05 | global batch size: 256 | lm loss: 3.337062E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.543 | TFLOPs: 28.60 | +7: iteration 31560/ 37905 | consumed samples: 8079360 | consumed tokens: 16546529280 | elapsed time per iteration (s): 0.24 | learning rate: 3.240E-05 | global batch size: 256 | lm loss: 3.331866E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1059.105 | TFLOPs: 26.98 | +7: iteration 31570/ 37905 | consumed samples: 8081920 | consumed tokens: 16551772160 | elapsed time per iteration (s): 0.23 | learning rate: 3.236E-05 | global batch size: 256 | lm loss: 3.351909E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.412 | TFLOPs: 28.64 | +7: iteration 31580/ 37905 | consumed samples: 8084480 | consumed tokens: 16557015040 | elapsed time per iteration (s): 0.23 | learning rate: 3.233E-05 | global batch size: 256 | lm loss: 3.323579E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.724 | TFLOPs: 28.42 | +7: iteration 31590/ 37905 | consumed samples: 8087040 | consumed tokens: 16562257920 | elapsed time per iteration (s): 0.23 | learning rate: 3.229E-05 | global batch size: 256 | lm loss: 3.341166E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.963 | TFLOPs: 28.68 | +7: iteration 31600/ 37905 | consumed samples: 8089600 | consumed tokens: 16567500800 | elapsed time per iteration (s): 0.23 | learning rate: 3.225E-05 | global batch size: 256 | lm loss: 3.352282E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.042 | TFLOPs: 28.66 | +7: iteration 31610/ 37905 | consumed samples: 8092160 | consumed tokens: 16572743680 | elapsed time per iteration (s): 0.23 | learning rate: 3.221E-05 | global batch size: 256 | lm loss: 3.326496E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.677 | TFLOPs: 28.68 | +7: iteration 31620/ 37905 | consumed samples: 8094720 | consumed tokens: 16577986560 | elapsed time per iteration (s): 0.23 | learning rate: 3.217E-05 | global batch size: 256 | lm loss: 3.348410E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.259 | TFLOPs: 28.62 | +7: iteration 31630/ 37905 | consumed samples: 8097280 | consumed tokens: 16583229440 | elapsed time per iteration (s): 0.23 | learning rate: 3.214E-05 | global batch size: 256 | lm loss: 3.319955E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.313 | TFLOPs: 28.54 | +7: iteration 31640/ 37905 | consumed samples: 8099840 | consumed tokens: 16588472320 | elapsed time per iteration (s): 0.23 | learning rate: 3.210E-05 | global batch size: 256 | lm loss: 3.322917E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.912 | TFLOPs: 28.66 | +7: iteration 31650/ 37905 | consumed samples: 8102400 | consumed tokens: 16593715200 | elapsed time per iteration (s): 0.25 | learning rate: 3.206E-05 | global batch size: 256 | lm loss: 3.349317E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1039.032 | TFLOPs: 26.47 | +7: iteration 31660/ 37905 | consumed samples: 8104960 | consumed tokens: 16598958080 | elapsed time per iteration (s): 0.23 | learning rate: 3.202E-05 | global batch size: 256 | lm loss: 3.309266E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.962 | TFLOPs: 28.76 | +7: iteration 31670/ 37905 | consumed samples: 8107520 | consumed tokens: 16604200960 | elapsed time per iteration (s): 0.23 | learning rate: 3.199E-05 | global batch size: 256 | lm loss: 3.333229E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.689 | TFLOPs: 28.68 | +7: iteration 31680/ 37905 | consumed samples: 8110080 | consumed tokens: 16609443840 | elapsed time per iteration (s): 0.23 | learning rate: 3.195E-05 | global batch size: 256 | lm loss: 3.324292E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1131.298 | TFLOPs: 28.82 | +7: iteration 31690/ 37905 | consumed samples: 8112640 | consumed tokens: 16614686720 | elapsed time per iteration (s): 0.23 | learning rate: 3.191E-05 | global batch size: 256 | lm loss: 3.300370E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.967 | TFLOPs: 28.66 | +7: iteration 31700/ 37905 | consumed samples: 8115200 | consumed tokens: 16619929600 | elapsed time per iteration (s): 0.23 | learning rate: 3.187E-05 | global batch size: 256 | lm loss: 3.321677E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.535 | TFLOPs: 28.75 | +7: iteration 31710/ 37905 | consumed samples: 8117760 | consumed tokens: 16625172480 | elapsed time per iteration (s): 0.23 | learning rate: 3.184E-05 | global batch size: 256 | lm loss: 3.300956E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.001 | TFLOPs: 28.71 | +7: iteration 31720/ 37905 | consumed samples: 8120320 | consumed tokens: 16630415360 | elapsed time per iteration (s): 0.23 | learning rate: 3.180E-05 | global batch size: 256 | lm loss: 3.340780E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.411 | TFLOPs: 28.72 | +7: iteration 31730/ 37905 | consumed samples: 8122880 | consumed tokens: 16635658240 | elapsed time per iteration (s): 0.23 | learning rate: 3.176E-05 | global batch size: 256 | lm loss: 3.315582E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.142 | TFLOPs: 28.69 | +7: iteration 31740/ 37905 | consumed samples: 8125440 | consumed tokens: 16640901120 | elapsed time per iteration (s): 0.23 | learning rate: 3.172E-05 | global batch size: 256 | lm loss: 3.336513E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.131 | TFLOPs: 28.66 | +7: iteration 31750/ 37905 | consumed samples: 8128000 | consumed tokens: 16646144000 | elapsed time per iteration (s): 0.24 | learning rate: 3.169E-05 | global batch size: 256 | lm loss: 3.313539E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1075.230 | TFLOPs: 27.39 | +7: iteration 31760/ 37905 | consumed samples: 8130560 | consumed tokens: 16651386880 | elapsed time per iteration (s): 0.23 | learning rate: 3.165E-05 | global batch size: 256 | lm loss: 3.319805E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.654 | TFLOPs: 28.65 | +7: iteration 31770/ 37905 | consumed samples: 8133120 | consumed tokens: 16656629760 | elapsed time per iteration (s): 0.23 | learning rate: 3.161E-05 | global batch size: 256 | lm loss: 3.323501E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.109 | TFLOPs: 28.69 | +7: iteration 31780/ 37905 | consumed samples: 8135680 | consumed tokens: 16661872640 | elapsed time per iteration (s): 0.23 | learning rate: 3.158E-05 | global batch size: 256 | lm loss: 3.335450E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.725 | TFLOPs: 28.68 | +7: iteration 31790/ 37905 | consumed samples: 8138240 | consumed tokens: 16667115520 | elapsed time per iteration (s): 0.23 | learning rate: 3.154E-05 | global batch size: 256 | lm loss: 3.328989E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.534 | TFLOPs: 28.70 | +7: iteration 31800/ 37905 | consumed samples: 8140800 | consumed tokens: 16672358400 | elapsed time per iteration (s): 0.23 | learning rate: 3.150E-05 | global batch size: 256 | lm loss: 3.328315E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.435 | TFLOPs: 28.70 | +7: iteration 31810/ 37905 | consumed samples: 8143360 | consumed tokens: 16677601280 | elapsed time per iteration (s): 0.23 | learning rate: 3.146E-05 | global batch size: 256 | lm loss: 3.320674E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.701 | TFLOPs: 28.68 | +7: iteration 31820/ 37905 | consumed samples: 8145920 | consumed tokens: 16682844160 | elapsed time per iteration (s): 0.23 | learning rate: 3.143E-05 | global batch size: 256 | lm loss: 3.335153E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.483 | TFLOPs: 28.54 | +7: iteration 31830/ 37905 | consumed samples: 8148480 | consumed tokens: 16688087040 | elapsed time per iteration (s): 0.23 | learning rate: 3.139E-05 | global batch size: 256 | lm loss: 3.306882E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.664 | TFLOPs: 27.99 | +7: iteration 31840/ 37905 | consumed samples: 8151040 | consumed tokens: 16693329920 | elapsed time per iteration (s): 0.23 | learning rate: 3.135E-05 | global batch size: 256 | lm loss: 3.353105E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.960 | TFLOPs: 28.66 | +7: iteration 31850/ 37905 | consumed samples: 8153600 | consumed tokens: 16698572800 | elapsed time per iteration (s): 0.23 | learning rate: 3.132E-05 | global batch size: 256 | lm loss: 3.309242E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.395 | TFLOPs: 28.57 | +7: iteration 31860/ 37905 | consumed samples: 8156160 | consumed tokens: 16703815680 | elapsed time per iteration (s): 0.23 | learning rate: 3.128E-05 | global batch size: 256 | lm loss: 3.286503E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.438 | TFLOPs: 28.54 | +7: iteration 31870/ 37905 | consumed samples: 8158720 | consumed tokens: 16709058560 | elapsed time per iteration (s): 0.23 | learning rate: 3.124E-05 | global batch size: 256 | lm loss: 3.329776E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.185 | TFLOPs: 28.61 | +7: iteration 31880/ 37905 | consumed samples: 8161280 | consumed tokens: 16714301440 | elapsed time per iteration (s): 0.23 | learning rate: 3.121E-05 | global batch size: 256 | lm loss: 3.307122E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.157 | TFLOPs: 28.64 | +7: iteration 31890/ 37905 | consumed samples: 8163840 | consumed tokens: 16719544320 | elapsed time per iteration (s): 0.23 | learning rate: 3.117E-05 | global batch size: 256 | lm loss: 3.323096E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.264 | TFLOPs: 28.59 | +7: iteration 31900/ 37905 | consumed samples: 8166400 | consumed tokens: 16724787200 | elapsed time per iteration (s): 0.23 | learning rate: 3.114E-05 | global batch size: 256 | lm loss: 3.290736E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.710 | TFLOPs: 28.30 | +7: iteration 31910/ 37905 | consumed samples: 8168960 | consumed tokens: 16730030080 | elapsed time per iteration (s): 0.23 | learning rate: 3.110E-05 | global batch size: 256 | lm loss: 3.290997E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.166 | TFLOPs: 28.31 | +7: iteration 31920/ 37905 | consumed samples: 8171520 | consumed tokens: 16735272960 | elapsed time per iteration (s): 0.23 | learning rate: 3.106E-05 | global batch size: 256 | lm loss: 3.316004E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.943 | TFLOPs: 28.51 | +7: iteration 31930/ 37905 | consumed samples: 8174080 | consumed tokens: 16740515840 | elapsed time per iteration (s): 0.23 | learning rate: 3.103E-05 | global batch size: 256 | lm loss: 3.335667E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.137 | TFLOPs: 28.46 | +7: iteration 31940/ 37905 | consumed samples: 8176640 | consumed tokens: 16745758720 | elapsed time per iteration (s): 0.23 | learning rate: 3.099E-05 | global batch size: 256 | lm loss: 3.327090E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.031 | TFLOPs: 27.95 | +7: iteration 31950/ 37905 | consumed samples: 8179200 | consumed tokens: 16751001600 | elapsed time per iteration (s): 0.23 | learning rate: 3.095E-05 | global batch size: 256 | lm loss: 3.344955E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.771 | TFLOPs: 28.04 | +7: iteration 31960/ 37905 | consumed samples: 8181760 | consumed tokens: 16756244480 | elapsed time per iteration (s): 0.24 | learning rate: 3.092E-05 | global batch size: 256 | lm loss: 3.344204E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1068.712 | TFLOPs: 27.23 | +7: iteration 31970/ 37905 | consumed samples: 8184320 | consumed tokens: 16761487360 | elapsed time per iteration (s): 0.23 | learning rate: 3.088E-05 | global batch size: 256 | lm loss: 3.323751E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.099 | TFLOPs: 28.56 | +7: iteration 31980/ 37905 | consumed samples: 8186880 | consumed tokens: 16766730240 | elapsed time per iteration (s): 0.23 | learning rate: 3.085E-05 | global batch size: 256 | lm loss: 3.326311E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.987 | TFLOPs: 28.56 | +7: iteration 31990/ 37905 | consumed samples: 8189440 | consumed tokens: 16771973120 | elapsed time per iteration (s): 0.23 | learning rate: 3.081E-05 | global batch size: 256 | lm loss: 3.312033E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.475 | TFLOPs: 28.32 | +0: [2022-11-29 19:02:07,244] [INFO] [logging.py:68:log_dist] [Rank 0] step=32000, skipped=0, lr=[3.077546313866371e-05, 3.077546313866371e-05, 3.077546313866371e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 32000/ 37905 | consumed samples: 8192000 | consumed tokens: 16777216000 | elapsed time per iteration (s): 0.23 | learning rate: 3.078E-05 | global batch size: 256 | lm loss: 3.324529E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.539 | TFLOPs: 28.52 | +0: steps: 32000 loss: 3.3634 iter time (s): 0.228 samples/sec: 1123.349 +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 32000 | lm loss value: 3.194855E+00 | lm loss PPL: 2.440664E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 32000 to checkpoints_83moscar +0: [2022-11-29 19:02:07,333] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step32000 is begin to save! +0: [2022-11-29 19:02:07,337] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/layer_01-model_00-model_states.pt... +0: [2022-11-29 19:02:07,408] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/layer_01-model_00-model_states.pt. +0: [2022-11-29 19:02:07,408] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/layer_03-model_00-model_states.pt... +0: [2022-11-29 19:02:07,420] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/layer_03-model_00-model_states.pt. +0: [2022-11-29 19:02:07,420] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/layer_04-model_00-model_states.pt... +0: [2022-11-29 19:02:07,431] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/layer_04-model_00-model_states.pt. +0: [2022-11-29 19:02:07,431] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/layer_05-model_00-model_states.pt... +0: [2022-11-29 19:02:07,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/layer_05-model_00-model_states.pt. +0: [2022-11-29 19:02:07,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/layer_06-model_00-model_states.pt... +0: [2022-11-29 19:02:07,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/layer_06-model_00-model_states.pt. +0: [2022-11-29 19:02:07,453] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/layer_07-model_00-model_states.pt... +0: [2022-11-29 19:02:07,464] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/layer_07-model_00-model_states.pt. +0: [2022-11-29 19:02:07,464] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/layer_08-model_00-model_states.pt... +0: [2022-11-29 19:02:07,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/layer_08-model_00-model_states.pt. +0: [2022-11-29 19:02:07,476] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/layer_09-model_00-model_states.pt... +0: [2022-11-29 19:02:07,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/layer_09-model_00-model_states.pt. +0: [2022-11-29 19:02:07,487] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/layer_10-model_00-model_states.pt... +0: [2022-11-29 19:02:07,500] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/layer_10-model_00-model_states.pt. +0: [2022-11-29 19:02:07,500] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/layer_11-model_00-model_states.pt... +0: [2022-11-29 19:02:07,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/layer_11-model_00-model_states.pt. +0: [2022-11-29 19:02:07,512] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/layer_12-model_00-model_states.pt... +0: [2022-11-29 19:02:07,523] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/layer_12-model_00-model_states.pt. +0: [2022-11-29 19:02:07,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/layer_14-model_00-model_states.pt... +0: [2022-11-29 19:02:07,524] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/layer_14-model_00-model_states.pt. +0: [2022-11-29 19:02:07,524] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step32000/mp_rank_00_model_states.pt +0: [2022-11-29 19:02:07,524] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/mp_rank_00_model_states.pt... +0: [2022-11-29 19:02:07,526] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/mp_rank_00_model_states.pt. +0: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:02:07,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:02:07,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:02:07,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:02:07,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 19:02:07,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +4: [2022-11-29 19:02:07,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:02:07,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 19:02:07,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +7: [2022-11-29 19:02:07,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:02:07,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 19:02:07,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +0: [2022-11-29 19:02:07,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 19:02:07,571] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +1: [2022-11-29 19:02:07,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:02:07,571] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 19:02:07,571] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +5: [2022-11-29 19:02:07,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:02:07,571] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 19:02:07,571] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +2: [2022-11-29 19:02:07,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:02:07,571] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 19:02:07,571] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +7: [2022-11-29 19:02:07,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:02:07,571] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +6: [2022-11-29 19:02:07,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:02:07,571] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +6: [2022-11-29 19:02:07,571] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 19:02:07,571] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +4: [2022-11-29 19:02:07,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:02:07,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 19:02:07,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +0: [2022-11-29 19:02:07,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:02:07,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 19:02:07,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +1: [2022-11-29 19:02:07,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:02:07,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 19:02:07,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +0: [2022-11-29 19:02:07,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:02:07,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 19:02:07,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +5: [2022-11-29 19:02:07,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:02:07,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +4: [2022-11-29 19:02:07,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:02:07,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +4: [2022-11-29 19:02:07,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +2: [2022-11-29 19:02:07,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:02:07,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +2: [2022-11-29 19:02:07,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 19:02:07,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +1: [2022-11-29 19:02:07,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:02:07,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 19:02:07,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +7: [2022-11-29 19:02:07,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:02:07,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 19:02:07,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +2: [2022-11-29 19:02:07,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:02:07,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:02:07,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +2: [2022-11-29 19:02:07,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +4: [2022-11-29 19:02:07,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +2: [2022-11-29 19:02:07,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +0: [2022-11-29 19:02:07,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:02:07,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 19:02:07,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +1: [2022-11-29 19:02:07,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:02:07,575] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 19:02:07,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +5: [2022-11-29 19:02:07,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:02:07,575] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 19:02:07,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +4: [2022-11-29 19:02:07,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:02:07,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:02:07,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:02:07,575] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +6: [2022-11-29 19:02:07,576] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 19:02:07,576] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +4: [2022-11-29 19:02:07,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +6: [2022-11-29 19:02:07,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +6: [2022-11-29 19:02:07,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +2: [2022-11-29 19:02:07,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:02:07,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:02:07,576] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +7: [2022-11-29 19:02:07,576] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +2: [2022-11-29 19:02:07,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +7: [2022-11-29 19:02:07,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +0: [2022-11-29 19:02:07,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:02:07,576] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +5: [2022-11-29 19:02:07,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:02:07,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +5: [2022-11-29 19:02:07,576] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 19:02:07,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +7: [2022-11-29 19:02:07,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:02:07,576] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 19:02:07,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +1: [2022-11-29 19:02:07,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:02:07,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:02:07,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +6: [2022-11-29 19:02:07,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 19:02:07,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +2: [2022-11-29 19:02:07,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:02:07,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +2: [2022-11-29 19:02:07,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 19:02:07,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +4: [2022-11-29 19:02:07,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:02:07,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 19:02:07,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +0: [2022-11-29 19:02:07,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:02:07,578] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 19:02:07,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +5: [2022-11-29 19:02:07,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:02:07,578] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 19:02:07,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +6: [2022-11-29 19:02:07,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:02:07,578] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 19:02:07,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +3: [2022-11-29 19:02:07,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:02:07,578] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 19:02:07,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +7: [2022-11-29 19:02:07,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:02:07,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 19:02:07,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +4: [2022-11-29 19:02:07,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:02:07,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 19:02:07,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +1: [2022-11-29 19:02:07,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:02:07,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 19:02:07,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +0: [2022-11-29 19:02:07,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:02:07,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 19:02:07,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +5: [2022-11-29 19:02:07,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:02:07,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 19:02:07,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +6: [2022-11-29 19:02:07,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:02:07,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:02:07,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 19:02:07,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +2: [2022-11-29 19:02:07,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 19:02:07,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +7: [2022-11-29 19:02:07,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:02:07,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:02:07,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +3: [2022-11-29 19:02:07,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +7: [2022-11-29 19:02:07,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +3: [2022-11-29 19:02:07,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +2: [2022-11-29 19:02:07,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:02:07,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:02:07,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +4: [2022-11-29 19:02:07,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +5: [2022-11-29 19:02:07,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:02:07,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:02:07,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +4: [2022-11-29 19:02:07,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +5: [2022-11-29 19:02:07,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 19:02:07,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 19:02:07,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +5: [2022-11-29 19:02:07,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +0: [2022-11-29 19:02:07,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:02:07,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 19:02:07,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +1: [2022-11-29 19:02:07,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:02:07,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 19:02:07,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +7: [2022-11-29 19:02:07,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:02:07,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 19:02:07,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +3: [2022-11-29 19:02:07,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:02:07,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +1: [2022-11-29 19:02:07,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:02:07,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +1: [2022-11-29 19:02:07,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 19:02:07,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +3: [2022-11-29 19:02:07,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:02:07,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 19:02:07,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +3: [2022-11-29 19:02:07,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:02:07,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 19:02:07,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +3: [2022-11-29 19:02:07,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:02:07,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 19:02:07,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +3: [2022-11-29 19:02:07,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:02:07,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 19:02:07,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +3: [2022-11-29 19:02:07,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:02:07,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 19:02:07,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +6: [2022-11-29 19:02:07,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:02:07,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 19:02:07,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +6: [2022-11-29 19:02:07,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:02:07,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step32000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 19:02:07,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +0: successfully saved checkpoint at iteration 32000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 252.85 +7: iteration 32010/ 37905 | consumed samples: 8194560 | consumed tokens: 16782458880 | elapsed time per iteration (s): 0.26 | learning rate: 3.074E-05 | global batch size: 256 | lm loss: 3.296568E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 982.247 | TFLOPs: 25.02 | +7: iteration 32020/ 37905 | consumed samples: 8197120 | consumed tokens: 16787701760 | elapsed time per iteration (s): 0.23 | learning rate: 3.070E-05 | global batch size: 256 | lm loss: 3.315085E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.358 | TFLOPs: 27.78 | +7: iteration 32030/ 37905 | consumed samples: 8199680 | consumed tokens: 16792944640 | elapsed time per iteration (s): 0.23 | learning rate: 3.067E-05 | global batch size: 256 | lm loss: 3.328528E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.481 | TFLOPs: 28.57 | +7: iteration 32040/ 37905 | consumed samples: 8202240 | consumed tokens: 16798187520 | elapsed time per iteration (s): 0.23 | learning rate: 3.063E-05 | global batch size: 256 | lm loss: 3.334590E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.250 | TFLOPs: 28.54 | +7: iteration 32050/ 37905 | consumed samples: 8204800 | consumed tokens: 16803430400 | elapsed time per iteration (s): 0.24 | learning rate: 3.060E-05 | global batch size: 256 | lm loss: 3.333619E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1067.599 | TFLOPs: 27.20 | +7: iteration 32060/ 37905 | consumed samples: 8207360 | consumed tokens: 16808673280 | elapsed time per iteration (s): 0.23 | learning rate: 3.056E-05 | global batch size: 256 | lm loss: 3.326989E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.401 | TFLOPs: 28.59 | +7: iteration 32070/ 37905 | consumed samples: 8209920 | consumed tokens: 16813916160 | elapsed time per iteration (s): 0.23 | learning rate: 3.053E-05 | global batch size: 256 | lm loss: 3.299732E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.317 | TFLOPs: 28.54 | +7: iteration 32080/ 37905 | consumed samples: 8212480 | consumed tokens: 16819159040 | elapsed time per iteration (s): 0.23 | learning rate: 3.049E-05 | global batch size: 256 | lm loss: 3.360106E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.347 | TFLOPs: 28.41 | +7: iteration 32090/ 37905 | consumed samples: 8215040 | consumed tokens: 16824401920 | elapsed time per iteration (s): 0.23 | learning rate: 3.046E-05 | global batch size: 256 | lm loss: 3.325705E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.343 | TFLOPs: 28.49 | +7: iteration 32100/ 37905 | consumed samples: 8217600 | consumed tokens: 16829644800 | elapsed time per iteration (s): 0.23 | learning rate: 3.042E-05 | global batch size: 256 | lm loss: 3.290166E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.222 | TFLOPs: 28.56 | +7: iteration 32110/ 37905 | consumed samples: 8220160 | consumed tokens: 16834887680 | elapsed time per iteration (s): 0.23 | learning rate: 3.039E-05 | global batch size: 256 | lm loss: 3.321348E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.467 | TFLOPs: 28.54 | +7: iteration 32120/ 37905 | consumed samples: 8222720 | consumed tokens: 16840130560 | elapsed time per iteration (s): 0.23 | learning rate: 3.035E-05 | global batch size: 256 | lm loss: 3.300390E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.103 | TFLOPs: 28.61 | +7: iteration 32130/ 37905 | consumed samples: 8225280 | consumed tokens: 16845373440 | elapsed time per iteration (s): 0.23 | learning rate: 3.032E-05 | global batch size: 256 | lm loss: 3.307974E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.751 | TFLOPs: 28.60 | +7: iteration 32140/ 37905 | consumed samples: 8227840 | consumed tokens: 16850616320 | elapsed time per iteration (s): 0.23 | learning rate: 3.028E-05 | global batch size: 256 | lm loss: 3.344806E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.274 | TFLOPs: 28.11 | +7: iteration 32150/ 37905 | consumed samples: 8230400 | consumed tokens: 16855859200 | elapsed time per iteration (s): 0.23 | learning rate: 3.025E-05 | global batch size: 256 | lm loss: 3.317278E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.746 | TFLOPs: 28.60 | +7: iteration 32160/ 37905 | consumed samples: 8232960 | consumed tokens: 16861102080 | elapsed time per iteration (s): 0.23 | learning rate: 3.021E-05 | global batch size: 256 | lm loss: 3.320602E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.801 | TFLOPs: 28.35 | +7: iteration 32170/ 37905 | consumed samples: 8235520 | consumed tokens: 16866344960 | elapsed time per iteration (s): 0.23 | learning rate: 3.018E-05 | global batch size: 256 | lm loss: 3.327481E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.197 | TFLOPs: 28.61 | +7: iteration 32180/ 37905 | consumed samples: 8238080 | consumed tokens: 16871587840 | elapsed time per iteration (s): 0.23 | learning rate: 3.014E-05 | global batch size: 256 | lm loss: 3.318353E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.165 | TFLOPs: 28.56 | +7: iteration 32190/ 37905 | consumed samples: 8240640 | consumed tokens: 16876830720 | elapsed time per iteration (s): 0.23 | learning rate: 3.011E-05 | global batch size: 256 | lm loss: 3.294826E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.400 | TFLOPs: 28.70 | +7: iteration 32200/ 37905 | consumed samples: 8243200 | consumed tokens: 16882073600 | elapsed time per iteration (s): 0.23 | learning rate: 3.007E-05 | global batch size: 256 | lm loss: 3.322767E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.279 | TFLOPs: 28.59 | +7: iteration 32210/ 37905 | consumed samples: 8245760 | consumed tokens: 16887316480 | elapsed time per iteration (s): 0.23 | learning rate: 3.004E-05 | global batch size: 256 | lm loss: 3.323791E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.998 | TFLOPs: 28.63 | +7: iteration 32220/ 37905 | consumed samples: 8248320 | consumed tokens: 16892559360 | elapsed time per iteration (s): 0.24 | learning rate: 3.000E-05 | global batch size: 256 | lm loss: 3.330284E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1084.986 | TFLOPs: 27.64 | +7: iteration 32230/ 37905 | consumed samples: 8250880 | consumed tokens: 16897802240 | elapsed time per iteration (s): 0.23 | learning rate: 2.997E-05 | global batch size: 256 | lm loss: 3.304933E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.503 | TFLOPs: 28.65 | +7: iteration 32240/ 37905 | consumed samples: 8253440 | consumed tokens: 16903045120 | elapsed time per iteration (s): 0.23 | learning rate: 2.993E-05 | global batch size: 256 | lm loss: 3.331956E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.068 | TFLOPs: 28.58 | +7: iteration 32250/ 37905 | consumed samples: 8256000 | consumed tokens: 16908288000 | elapsed time per iteration (s): 0.23 | learning rate: 2.990E-05 | global batch size: 256 | lm loss: 3.336930E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.371 | TFLOPs: 28.69 | +7: iteration 32260/ 37905 | consumed samples: 8258560 | consumed tokens: 16913530880 | elapsed time per iteration (s): 0.23 | learning rate: 2.986E-05 | global batch size: 256 | lm loss: 3.337652E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.288 | TFLOPs: 28.59 | +7: iteration 32270/ 37905 | consumed samples: 8261120 | consumed tokens: 16918773760 | elapsed time per iteration (s): 0.23 | learning rate: 2.983E-05 | global batch size: 256 | lm loss: 3.288917E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.533 | TFLOPs: 28.62 | +7: iteration 32280/ 37905 | consumed samples: 8263680 | consumed tokens: 16924016640 | elapsed time per iteration (s): 0.23 | learning rate: 2.980E-05 | global batch size: 256 | lm loss: 3.311411E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.006 | TFLOPs: 28.63 | +7: iteration 32290/ 37905 | consumed samples: 8266240 | consumed tokens: 16929259520 | elapsed time per iteration (s): 0.23 | learning rate: 2.976E-05 | global batch size: 256 | lm loss: 3.307082E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.296 | TFLOPs: 28.62 | +7: iteration 32300/ 37905 | consumed samples: 8268800 | consumed tokens: 16934502400 | elapsed time per iteration (s): 0.25 | learning rate: 2.973E-05 | global batch size: 256 | lm loss: 3.328905E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1032.824 | TFLOPs: 26.31 | +7: iteration 32310/ 37905 | consumed samples: 8271360 | consumed tokens: 16939745280 | elapsed time per iteration (s): 0.23 | learning rate: 2.969E-05 | global batch size: 256 | lm loss: 3.343733E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.586 | TFLOPs: 28.60 | +7: iteration 32320/ 37905 | consumed samples: 8273920 | consumed tokens: 16944988160 | elapsed time per iteration (s): 0.23 | learning rate: 2.966E-05 | global batch size: 256 | lm loss: 3.343897E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.894 | TFLOPs: 28.68 | +7: iteration 32330/ 37905 | consumed samples: 8276480 | consumed tokens: 16950231040 | elapsed time per iteration (s): 0.23 | learning rate: 2.963E-05 | global batch size: 256 | lm loss: 3.311807E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.634 | TFLOPs: 28.62 | +7: iteration 32340/ 37905 | consumed samples: 8279040 | consumed tokens: 16955473920 | elapsed time per iteration (s): 0.23 | learning rate: 2.959E-05 | global batch size: 256 | lm loss: 3.318333E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.368 | TFLOPs: 28.72 | +7: iteration 32350/ 37905 | consumed samples: 8281600 | consumed tokens: 16960716800 | elapsed time per iteration (s): 0.23 | learning rate: 2.956E-05 | global batch size: 256 | lm loss: 3.314950E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.803 | TFLOPs: 28.50 | +7: iteration 32360/ 37905 | consumed samples: 8284160 | consumed tokens: 16965959680 | elapsed time per iteration (s): 0.23 | learning rate: 2.952E-05 | global batch size: 256 | lm loss: 3.325834E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.971 | TFLOPs: 28.68 | +7: iteration 32370/ 37905 | consumed samples: 8286720 | consumed tokens: 16971202560 | elapsed time per iteration (s): 0.23 | learning rate: 2.949E-05 | global batch size: 256 | lm loss: 3.312531E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.636 | TFLOPs: 28.62 | +7: iteration 32380/ 37905 | consumed samples: 8289280 | consumed tokens: 16976445440 | elapsed time per iteration (s): 0.23 | learning rate: 2.946E-05 | global batch size: 256 | lm loss: 3.306647E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.666 | TFLOPs: 28.68 | +7: iteration 32390/ 37905 | consumed samples: 8291840 | consumed tokens: 16981688320 | elapsed time per iteration (s): 0.23 | learning rate: 2.942E-05 | global batch size: 256 | lm loss: 3.318781E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.288 | TFLOPs: 28.62 | +7: iteration 32400/ 37905 | consumed samples: 8294400 | consumed tokens: 16986931200 | elapsed time per iteration (s): 0.23 | learning rate: 2.939E-05 | global batch size: 256 | lm loss: 3.329719E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.104 | TFLOPs: 28.71 | +7: iteration 32410/ 37905 | consumed samples: 8296960 | consumed tokens: 16992174080 | elapsed time per iteration (s): 0.25 | learning rate: 2.936E-05 | global batch size: 256 | lm loss: 3.335840E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1012.156 | TFLOPs: 25.78 | +7: iteration 32420/ 37905 | consumed samples: 8299520 | consumed tokens: 16997416960 | elapsed time per iteration (s): 0.23 | learning rate: 2.932E-05 | global batch size: 256 | lm loss: 3.306998E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.178 | TFLOPs: 28.66 | +7: iteration 32430/ 37905 | consumed samples: 8302080 | consumed tokens: 17002659840 | elapsed time per iteration (s): 0.23 | learning rate: 2.929E-05 | global batch size: 256 | lm loss: 3.316282E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.172 | TFLOPs: 28.66 | +7: iteration 32440/ 37905 | consumed samples: 8304640 | consumed tokens: 17007902720 | elapsed time per iteration (s): 0.23 | learning rate: 2.926E-05 | global batch size: 256 | lm loss: 3.325620E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.477 | TFLOPs: 28.44 | +7: iteration 32450/ 37905 | consumed samples: 8307200 | consumed tokens: 17013145600 | elapsed time per iteration (s): 0.23 | learning rate: 2.922E-05 | global batch size: 256 | lm loss: 3.336981E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.167 | TFLOPs: 28.74 | +7: iteration 32460/ 37905 | consumed samples: 8309760 | consumed tokens: 17018388480 | elapsed time per iteration (s): 0.23 | learning rate: 2.919E-05 | global batch size: 256 | lm loss: 3.328106E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.163 | TFLOPs: 27.95 | +7: iteration 32470/ 37905 | consumed samples: 8312320 | consumed tokens: 17023631360 | elapsed time per iteration (s): 0.23 | learning rate: 2.916E-05 | global batch size: 256 | lm loss: 3.300235E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.655 | TFLOPs: 28.45 | +7: iteration 32480/ 37905 | consumed samples: 8314880 | consumed tokens: 17028874240 | elapsed time per iteration (s): 0.25 | learning rate: 2.912E-05 | global batch size: 256 | lm loss: 3.341842E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1035.252 | TFLOPs: 26.37 | +7: iteration 32490/ 37905 | consumed samples: 8317440 | consumed tokens: 17034117120 | elapsed time per iteration (s): 0.24 | learning rate: 2.909E-05 | global batch size: 256 | lm loss: 3.330929E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1077.243 | TFLOPs: 27.44 | +7: iteration 32500/ 37905 | consumed samples: 8320000 | consumed tokens: 17039360000 | elapsed time per iteration (s): 0.25 | learning rate: 2.906E-05 | global batch size: 256 | lm loss: 3.330384E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1037.891 | TFLOPs: 26.44 | +7: iteration 32510/ 37905 | consumed samples: 8322560 | consumed tokens: 17044602880 | elapsed time per iteration (s): 0.25 | learning rate: 2.903E-05 | global batch size: 256 | lm loss: 3.331744E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1017.053 | TFLOPs: 25.91 | +7: iteration 32520/ 37905 | consumed samples: 8325120 | consumed tokens: 17049845760 | elapsed time per iteration (s): 0.23 | learning rate: 2.899E-05 | global batch size: 256 | lm loss: 3.319609E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.613 | TFLOPs: 28.11 | +7: iteration 32530/ 37905 | consumed samples: 8327680 | consumed tokens: 17055088640 | elapsed time per iteration (s): 0.24 | learning rate: 2.896E-05 | global batch size: 256 | lm loss: 3.298660E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.542 | TFLOPs: 27.68 | +7: iteration 32540/ 37905 | consumed samples: 8330240 | consumed tokens: 17060331520 | elapsed time per iteration (s): 0.23 | learning rate: 2.893E-05 | global batch size: 256 | lm loss: 3.289445E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.890 | TFLOPs: 28.33 | +7: iteration 32550/ 37905 | consumed samples: 8332800 | consumed tokens: 17065574400 | elapsed time per iteration (s): 0.23 | learning rate: 2.889E-05 | global batch size: 256 | lm loss: 3.328064E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.613 | TFLOPs: 28.73 | +7: iteration 32560/ 37905 | consumed samples: 8335360 | consumed tokens: 17070817280 | elapsed time per iteration (s): 0.23 | learning rate: 2.886E-05 | global batch size: 256 | lm loss: 3.360089E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.220 | TFLOPs: 27.88 | +7: iteration 32570/ 37905 | consumed samples: 8337920 | consumed tokens: 17076060160 | elapsed time per iteration (s): 0.25 | learning rate: 2.883E-05 | global batch size: 256 | lm loss: 3.310329E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1035.250 | TFLOPs: 26.37 | +7: iteration 32580/ 37905 | consumed samples: 8340480 | consumed tokens: 17081303040 | elapsed time per iteration (s): 0.23 | learning rate: 2.880E-05 | global batch size: 256 | lm loss: 3.304427E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.274 | TFLOPs: 28.23 | +7: iteration 32590/ 37905 | consumed samples: 8343040 | consumed tokens: 17086545920 | elapsed time per iteration (s): 0.23 | learning rate: 2.876E-05 | global batch size: 256 | lm loss: 3.295405E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.692 | TFLOPs: 28.17 | +7: iteration 32600/ 37905 | consumed samples: 8345600 | consumed tokens: 17091788800 | elapsed time per iteration (s): 0.23 | learning rate: 2.873E-05 | global batch size: 256 | lm loss: 3.333033E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.909 | TFLOPs: 28.12 | +7: iteration 32610/ 37905 | consumed samples: 8348160 | consumed tokens: 17097031680 | elapsed time per iteration (s): 0.26 | learning rate: 2.870E-05 | global batch size: 256 | lm loss: 3.337560E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1001.073 | TFLOPs: 25.50 | +7: iteration 32620/ 37905 | consumed samples: 8350720 | consumed tokens: 17102274560 | elapsed time per iteration (s): 0.24 | learning rate: 2.867E-05 | global batch size: 256 | lm loss: 3.308082E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1062.842 | TFLOPs: 27.08 | +7: iteration 32630/ 37905 | consumed samples: 8353280 | consumed tokens: 17107517440 | elapsed time per iteration (s): 0.25 | learning rate: 2.863E-05 | global batch size: 256 | lm loss: 3.321181E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1004.201 | TFLOPs: 25.58 | +7: iteration 32640/ 37905 | consumed samples: 8355840 | consumed tokens: 17112760320 | elapsed time per iteration (s): 0.23 | learning rate: 2.860E-05 | global batch size: 256 | lm loss: 3.341967E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.732 | TFLOPs: 28.14 | +7: iteration 32650/ 37905 | consumed samples: 8358400 | consumed tokens: 17118003200 | elapsed time per iteration (s): 0.25 | learning rate: 2.857E-05 | global batch size: 256 | lm loss: 3.338474E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1004.990 | TFLOPs: 25.60 | +7: iteration 32660/ 37905 | consumed samples: 8360960 | consumed tokens: 17123246080 | elapsed time per iteration (s): 0.23 | learning rate: 2.854E-05 | global batch size: 256 | lm loss: 3.319625E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.857 | TFLOPs: 28.02 | +7: iteration 32670/ 37905 | consumed samples: 8363520 | consumed tokens: 17128488960 | elapsed time per iteration (s): 0.24 | learning rate: 2.851E-05 | global batch size: 256 | lm loss: 3.309604E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.516 | TFLOPs: 27.73 | +7: iteration 32680/ 37905 | consumed samples: 8366080 | consumed tokens: 17133731840 | elapsed time per iteration (s): 0.23 | learning rate: 2.847E-05 | global batch size: 256 | lm loss: 3.260865E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.584 | TFLOPs: 28.22 | +7: iteration 32690/ 37905 | consumed samples: 8368640 | consumed tokens: 17138974720 | elapsed time per iteration (s): 0.25 | learning rate: 2.844E-05 | global batch size: 256 | lm loss: 3.318823E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1034.914 | TFLOPs: 26.36 | +7: iteration 32700/ 37905 | consumed samples: 8371200 | consumed tokens: 17144217600 | elapsed time per iteration (s): 0.24 | learning rate: 2.841E-05 | global batch size: 256 | lm loss: 3.301876E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.144 | TFLOPs: 27.72 | +7: iteration 32710/ 37905 | consumed samples: 8373760 | consumed tokens: 17149460480 | elapsed time per iteration (s): 0.23 | learning rate: 2.838E-05 | global batch size: 256 | lm loss: 3.346306E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.619 | TFLOPs: 28.17 | +7: iteration 32720/ 37905 | consumed samples: 8376320 | consumed tokens: 17154703360 | elapsed time per iteration (s): 0.23 | learning rate: 2.835E-05 | global batch size: 256 | lm loss: 3.325705E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.388 | TFLOPs: 28.11 | +7: iteration 32730/ 37905 | consumed samples: 8378880 | consumed tokens: 17159946240 | elapsed time per iteration (s): 0.23 | learning rate: 2.832E-05 | global batch size: 256 | lm loss: 3.314985E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.698 | TFLOPs: 28.24 | +7: iteration 32740/ 37905 | consumed samples: 8381440 | consumed tokens: 17165189120 | elapsed time per iteration (s): 0.23 | learning rate: 2.828E-05 | global batch size: 256 | lm loss: 3.336352E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.152 | TFLOPs: 28.43 | +7: iteration 32750/ 37905 | consumed samples: 8384000 | consumed tokens: 17170432000 | elapsed time per iteration (s): 0.23 | learning rate: 2.825E-05 | global batch size: 256 | lm loss: 3.302527E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.712 | TFLOPs: 28.37 | +7: iteration 32760/ 37905 | consumed samples: 8386560 | consumed tokens: 17175674880 | elapsed time per iteration (s): 0.23 | learning rate: 2.822E-05 | global batch size: 256 | lm loss: 3.320271E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.539 | TFLOPs: 28.65 | +7: iteration 32770/ 37905 | consumed samples: 8389120 | consumed tokens: 17180917760 | elapsed time per iteration (s): 0.23 | learning rate: 2.819E-05 | global batch size: 256 | lm loss: 3.314268E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.497 | TFLOPs: 28.37 | +7: iteration 32780/ 37905 | consumed samples: 8391680 | consumed tokens: 17186160640 | elapsed time per iteration (s): 0.23 | learning rate: 2.816E-05 | global batch size: 256 | lm loss: 3.319333E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.710 | TFLOPs: 28.14 | +7: iteration 32790/ 37905 | consumed samples: 8394240 | consumed tokens: 17191403520 | elapsed time per iteration (s): 0.23 | learning rate: 2.813E-05 | global batch size: 256 | lm loss: 3.347538E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.332 | TFLOPs: 28.01 | +7: iteration 32800/ 37905 | consumed samples: 8396800 | consumed tokens: 17196646400 | elapsed time per iteration (s): 0.23 | learning rate: 2.810E-05 | global batch size: 256 | lm loss: 3.309429E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.654 | TFLOPs: 28.29 | +7: iteration 32810/ 37905 | consumed samples: 8399360 | consumed tokens: 17201889280 | elapsed time per iteration (s): 0.23 | learning rate: 2.806E-05 | global batch size: 256 | lm loss: 3.338169E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.508 | TFLOPs: 28.44 | +7: iteration 32820/ 37905 | consumed samples: 8401920 | consumed tokens: 17207132160 | elapsed time per iteration (s): 0.23 | learning rate: 2.803E-05 | global batch size: 256 | lm loss: 3.336329E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.084 | TFLOPs: 28.23 | +7: iteration 32830/ 37905 | consumed samples: 8404480 | consumed tokens: 17212375040 | elapsed time per iteration (s): 0.24 | learning rate: 2.800E-05 | global batch size: 256 | lm loss: 3.329197E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.990 | TFLOPs: 27.67 | +7: iteration 32840/ 37905 | consumed samples: 8407040 | consumed tokens: 17217617920 | elapsed time per iteration (s): 0.23 | learning rate: 2.797E-05 | global batch size: 256 | lm loss: 3.313465E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.129 | TFLOPs: 28.56 | +7: iteration 32850/ 37905 | consumed samples: 8409600 | consumed tokens: 17222860800 | elapsed time per iteration (s): 0.23 | learning rate: 2.794E-05 | global batch size: 256 | lm loss: 3.317384E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.285 | TFLOPs: 28.08 | +7: iteration 32860/ 37905 | consumed samples: 8412160 | consumed tokens: 17228103680 | elapsed time per iteration (s): 0.23 | learning rate: 2.791E-05 | global batch size: 256 | lm loss: 3.323357E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.807 | TFLOPs: 28.17 | +7: iteration 32870/ 37905 | consumed samples: 8414720 | consumed tokens: 17233346560 | elapsed time per iteration (s): 0.23 | learning rate: 2.788E-05 | global batch size: 256 | lm loss: 3.312577E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.471 | TFLOPs: 28.37 | +7: iteration 32880/ 37905 | consumed samples: 8417280 | consumed tokens: 17238589440 | elapsed time per iteration (s): 0.24 | learning rate: 2.785E-05 | global batch size: 256 | lm loss: 3.336351E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.258 | TFLOPs: 27.67 | +7: iteration 32890/ 37905 | consumed samples: 8419840 | consumed tokens: 17243832320 | elapsed time per iteration (s): 0.23 | learning rate: 2.782E-05 | global batch size: 256 | lm loss: 3.329049E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.296 | TFLOPs: 27.85 | +7: iteration 32900/ 37905 | consumed samples: 8422400 | consumed tokens: 17249075200 | elapsed time per iteration (s): 0.23 | learning rate: 2.779E-05 | global batch size: 256 | lm loss: 3.335814E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.783 | TFLOPs: 28.32 | +7: iteration 32910/ 37905 | consumed samples: 8424960 | consumed tokens: 17254318080 | elapsed time per iteration (s): 0.23 | learning rate: 2.776E-05 | global batch size: 256 | lm loss: 3.306137E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.453 | TFLOPs: 28.37 | +7: iteration 32920/ 37905 | consumed samples: 8427520 | consumed tokens: 17259560960 | elapsed time per iteration (s): 0.23 | learning rate: 2.772E-05 | global batch size: 256 | lm loss: 3.318449E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.229 | TFLOPs: 27.80 | +7: iteration 32930/ 37905 | consumed samples: 8430080 | consumed tokens: 17264803840 | elapsed time per iteration (s): 0.23 | learning rate: 2.769E-05 | global batch size: 256 | lm loss: 3.328247E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.669 | TFLOPs: 28.12 | +7: iteration 32940/ 37905 | consumed samples: 8432640 | consumed tokens: 17270046720 | elapsed time per iteration (s): 0.24 | learning rate: 2.766E-05 | global batch size: 256 | lm loss: 3.324450E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1072.622 | TFLOPs: 27.33 | +7: iteration 32950/ 37905 | consumed samples: 8435200 | consumed tokens: 17275289600 | elapsed time per iteration (s): 0.26 | learning rate: 2.763E-05 | global batch size: 256 | lm loss: 3.307534E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 976.495 | TFLOPs: 24.88 | +7: iteration 32960/ 37905 | consumed samples: 8437760 | consumed tokens: 17280532480 | elapsed time per iteration (s): 0.23 | learning rate: 2.760E-05 | global batch size: 256 | lm loss: 3.320149E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.907 | TFLOPs: 28.02 | +7: iteration 32970/ 37905 | consumed samples: 8440320 | consumed tokens: 17285775360 | elapsed time per iteration (s): 0.23 | learning rate: 2.757E-05 | global batch size: 256 | lm loss: 3.331588E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.733 | TFLOPs: 28.58 | +7: iteration 32980/ 37905 | consumed samples: 8442880 | consumed tokens: 17291018240 | elapsed time per iteration (s): 0.25 | learning rate: 2.754E-05 | global batch size: 256 | lm loss: 3.317242E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1040.997 | TFLOPs: 26.52 | +7: iteration 32990/ 37905 | consumed samples: 8445440 | consumed tokens: 17296261120 | elapsed time per iteration (s): 0.23 | learning rate: 2.751E-05 | global batch size: 256 | lm loss: 3.322775E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.283 | TFLOPs: 27.90 | +7: iteration 33000/ 37905 | consumed samples: 8448000 | consumed tokens: 17301504000 | elapsed time per iteration (s): 0.24 | learning rate: 2.748E-05 | global batch size: 256 | lm loss: 3.316541E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1064.505 | TFLOPs: 27.12 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 33000 | lm loss value: 3.120558E+00 | lm loss PPL: 2.265902E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 33000 to checkpoints_83moscar +0: [2022-11-29 19:06:00,742] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step33000 is begin to save! +0: [2022-11-29 19:06:00,747] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/layer_01-model_00-model_states.pt... +0: [2022-11-29 19:06:00,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/layer_01-model_00-model_states.pt. +0: [2022-11-29 19:06:00,857] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/layer_03-model_00-model_states.pt... +0: [2022-11-29 19:06:00,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/layer_03-model_00-model_states.pt. +0: [2022-11-29 19:06:00,870] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/layer_04-model_00-model_states.pt... +0: [2022-11-29 19:06:00,882] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/layer_04-model_00-model_states.pt. +0: [2022-11-29 19:06:00,883] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/layer_05-model_00-model_states.pt... +0: [2022-11-29 19:06:00,895] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/layer_05-model_00-model_states.pt. +0: [2022-11-29 19:06:00,895] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/layer_06-model_00-model_states.pt... +0: [2022-11-29 19:06:00,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/layer_06-model_00-model_states.pt. +0: [2022-11-29 19:06:00,907] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/layer_07-model_00-model_states.pt... +0: [2022-11-29 19:06:00,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/layer_07-model_00-model_states.pt. +0: [2022-11-29 19:06:00,919] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/layer_08-model_00-model_states.pt... +0: [2022-11-29 19:06:00,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/layer_08-model_00-model_states.pt. +0: [2022-11-29 19:06:00,931] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/layer_09-model_00-model_states.pt... +0: [2022-11-29 19:06:00,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/layer_09-model_00-model_states.pt. +0: [2022-11-29 19:06:00,943] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/layer_10-model_00-model_states.pt... +0: [2022-11-29 19:06:00,955] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/layer_10-model_00-model_states.pt. +0: [2022-11-29 19:06:00,955] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/layer_11-model_00-model_states.pt... +0: [2022-11-29 19:06:00,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/layer_11-model_00-model_states.pt. +0: [2022-11-29 19:06:00,967] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/layer_12-model_00-model_states.pt... +0: [2022-11-29 19:06:00,979] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/layer_12-model_00-model_states.pt. +0: [2022-11-29 19:06:00,979] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/layer_14-model_00-model_states.pt... +0: [2022-11-29 19:06:00,980] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/layer_14-model_00-model_states.pt. +0: [2022-11-29 19:06:00,980] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step33000/mp_rank_00_model_states.pt +0: [2022-11-29 19:06:00,980] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/mp_rank_00_model_states.pt... +0: [2022-11-29 19:06:00,984] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/mp_rank_00_model_states.pt. +0: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:06:01,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:06:01,023] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:06:01,023] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:06:01,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 19:06:01,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +2: [2022-11-29 19:06:01,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:06:01,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 19:06:01,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +6: [2022-11-29 19:06:01,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:06:01,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 19:06:01,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:06:01,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +6: [2022-11-29 19:06:01,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 19:06:01,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +0: [2022-11-29 19:06:01,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:06:01,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +2: [2022-11-29 19:06:01,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:06:01,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +0: [2022-11-29 19:06:01,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +2: [2022-11-29 19:06:01,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +0: [2022-11-29 19:06:01,025] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 19:06:01,025] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +1: [2022-11-29 19:06:01,025] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:06:01,025] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:06:01,025] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 19:06:01,025] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +3: [2022-11-29 19:06:01,025] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 19:06:01,025] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +2: [2022-11-29 19:06:01,025] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:06:01,025] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 19:06:01,025] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +5: [2022-11-29 19:06:01,025] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:06:01,025] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 19:06:01,025] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +0: [2022-11-29 19:06:01,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:06:01,025] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:06:01,026] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +1: [2022-11-29 19:06:01,026] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 19:06:01,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:06:01,026] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +1: [2022-11-29 19:06:01,026] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +1: [2022-11-29 19:06:01,026] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 19:06:01,026] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +6: [2022-11-29 19:06:01,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:06:01,026] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 19:06:01,026] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +3: [2022-11-29 19:06:01,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:06:01,027] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 19:06:01,027] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +2: [2022-11-29 19:06:01,027] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:06:01,027] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:06:01,027] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 19:06:01,027] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +6: [2022-11-29 19:06:01,027] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 19:06:01,027] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +5: [2022-11-29 19:06:01,027] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:06:01,027] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 19:06:01,027] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +3: [2022-11-29 19:06:01,027] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:06:01,027] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +5: [2022-11-29 19:06:01,027] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:06:01,027] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +3: [2022-11-29 19:06:01,027] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +5: [2022-11-29 19:06:01,027] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +1: [2022-11-29 19:06:01,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:06:01,028] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 19:06:01,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +2: [2022-11-29 19:06:01,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:06:01,028] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 19:06:01,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +6: [2022-11-29 19:06:01,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:06:01,028] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 19:06:01,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +1: [2022-11-29 19:06:01,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:06:01,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 19:06:01,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +0: [2022-11-29 19:06:01,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:06:01,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 19:06:01,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +3: [2022-11-29 19:06:01,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:06:01,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:06:01,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 19:06:01,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +5: [2022-11-29 19:06:01,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:06:01,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 19:06:01,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +5: [2022-11-29 19:06:01,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 19:06:01,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +6: [2022-11-29 19:06:01,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:06:01,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 19:06:01,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +3: [2022-11-29 19:06:01,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:06:01,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 19:06:01,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +5: [2022-11-29 19:06:01,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:06:01,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:06:01,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:06:01,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +5: [2022-11-29 19:06:01,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +1: [2022-11-29 19:06:01,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +5: [2022-11-29 19:06:01,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +2: [2022-11-29 19:06:01,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +1: [2022-11-29 19:06:01,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +6: [2022-11-29 19:06:01,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:06:01,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 19:06:01,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +0: [2022-11-29 19:06:01,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:06:01,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 19:06:01,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +3: [2022-11-29 19:06:01,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:06:01,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:06:01,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +2: [2022-11-29 19:06:01,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +3: [2022-11-29 19:06:01,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +2: [2022-11-29 19:06:01,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +5: [2022-11-29 19:06:01,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:06:01,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:06:01,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 19:06:01,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +1: [2022-11-29 19:06:01,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 19:06:01,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +5: [2022-11-29 19:06:01,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:06:01,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 19:06:01,032] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +1: [2022-11-29 19:06:01,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:06:01,032] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 19:06:01,032] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +2: [2022-11-29 19:06:01,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:06:01,032] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 19:06:01,032] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +3: [2022-11-29 19:06:01,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:06:01,032] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 19:06:01,032] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +0: [2022-11-29 19:06:01,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:06:01,032] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 19:06:01,032] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +6: [2022-11-29 19:06:01,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:06:01,033] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 19:06:01,033] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +3: [2022-11-29 19:06:01,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:06:01,033] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 19:06:01,033] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +0: [2022-11-29 19:06:01,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:06:01,034] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 19:06:01,034] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +7: [2022-11-29 19:06:01,083] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:06:01,083] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:06:01,083] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:06:01,083] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:06:01,083] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:06:01,083] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:06:01,083] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:06:01,083] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:06:01,083] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 19:06:01,083] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 19:06:01,083] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 19:06:01,083] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 19:06:01,083] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 19:06:01,083] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 19:06:01,083] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 19:06:01,083] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 19:06:01,083] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +7: [2022-11-29 19:06:01,083] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +7: [2022-11-29 19:06:01,083] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +7: [2022-11-29 19:06:01,083] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +7: [2022-11-29 19:06:01,083] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +7: [2022-11-29 19:06:01,083] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +7: [2022-11-29 19:06:01,083] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +7: [2022-11-29 19:06:01,083] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +4: [2022-11-29 19:06:01,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:06:01,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:06:01,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:06:01,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:06:01,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:06:01,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:06:01,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:06:01,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:06:01,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 19:06:01,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 19:06:01,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 19:06:01,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 19:06:01,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 19:06:01,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 19:06:01,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 19:06:01,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step33000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 19:06:01,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +4: [2022-11-29 19:06:01,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +4: [2022-11-29 19:06:01,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +4: [2022-11-29 19:06:01,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +4: [2022-11-29 19:06:01,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +4: [2022-11-29 19:06:01,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +4: [2022-11-29 19:06:01,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +4: [2022-11-29 19:06:01,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +0: successfully saved checkpoint at iteration 33000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 416.37 +7: iteration 33010/ 37905 | consumed samples: 8450560 | consumed tokens: 17306746880 | elapsed time per iteration (s): 0.28 | learning rate: 2.745E-05 | global batch size: 256 | lm loss: 3.311082E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 923.148 | TFLOPs: 23.52 | +7: iteration 33020/ 37905 | consumed samples: 8453120 | consumed tokens: 17311989760 | elapsed time per iteration (s): 0.23 | learning rate: 2.742E-05 | global batch size: 256 | lm loss: 3.308976E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.658 | TFLOPs: 27.94 | +7: iteration 33030/ 37905 | consumed samples: 8455680 | consumed tokens: 17317232640 | elapsed time per iteration (s): 0.23 | learning rate: 2.739E-05 | global batch size: 256 | lm loss: 3.331823E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.511 | TFLOPs: 28.04 | +7: iteration 33040/ 37905 | consumed samples: 8458240 | consumed tokens: 17322475520 | elapsed time per iteration (s): 0.23 | learning rate: 2.736E-05 | global batch size: 256 | lm loss: 3.326148E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.248 | TFLOPs: 28.26 | +7: iteration 33050/ 37905 | consumed samples: 8460800 | consumed tokens: 17327718400 | elapsed time per iteration (s): 0.23 | learning rate: 2.733E-05 | global batch size: 256 | lm loss: 3.304396E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.085 | TFLOPs: 28.13 | +7: iteration 33060/ 37905 | consumed samples: 8463360 | consumed tokens: 17332961280 | elapsed time per iteration (s): 0.23 | learning rate: 2.730E-05 | global batch size: 256 | lm loss: 3.322057E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.198 | TFLOPs: 28.10 | +7: iteration 33070/ 37905 | consumed samples: 8465920 | consumed tokens: 17338204160 | elapsed time per iteration (s): 0.23 | learning rate: 2.727E-05 | global batch size: 256 | lm loss: 3.334492E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.939 | TFLOPs: 27.97 | +7: iteration 33080/ 37905 | consumed samples: 8468480 | consumed tokens: 17343447040 | elapsed time per iteration (s): 0.23 | learning rate: 2.724E-05 | global batch size: 256 | lm loss: 3.315129E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.363 | TFLOPs: 28.34 | +7: iteration 33090/ 37905 | consumed samples: 8471040 | consumed tokens: 17348689920 | elapsed time per iteration (s): 0.23 | learning rate: 2.721E-05 | global batch size: 256 | lm loss: 3.331187E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.827 | TFLOPs: 28.17 | +7: iteration 33100/ 37905 | consumed samples: 8473600 | consumed tokens: 17353932800 | elapsed time per iteration (s): 0.23 | learning rate: 2.718E-05 | global batch size: 256 | lm loss: 3.303219E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.281 | TFLOPs: 28.64 | +7: iteration 33110/ 37905 | consumed samples: 8476160 | consumed tokens: 17359175680 | elapsed time per iteration (s): 0.25 | learning rate: 2.715E-05 | global batch size: 256 | lm loss: 3.297696E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1031.655 | TFLOPs: 26.28 | +7: iteration 33120/ 37905 | consumed samples: 8478720 | consumed tokens: 17364418560 | elapsed time per iteration (s): 0.23 | learning rate: 2.713E-05 | global batch size: 256 | lm loss: 3.304417E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.771 | TFLOPs: 27.89 | +7: iteration 33130/ 37905 | consumed samples: 8481280 | consumed tokens: 17369661440 | elapsed time per iteration (s): 0.23 | learning rate: 2.710E-05 | global batch size: 256 | lm loss: 3.311294E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.358 | TFLOPs: 27.96 | +7: iteration 33140/ 37905 | consumed samples: 8483840 | consumed tokens: 17374904320 | elapsed time per iteration (s): 0.23 | learning rate: 2.707E-05 | global batch size: 256 | lm loss: 3.318642E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.033 | TFLOPs: 28.23 | +7: iteration 33150/ 37905 | consumed samples: 8486400 | consumed tokens: 17380147200 | elapsed time per iteration (s): 0.24 | learning rate: 2.704E-05 | global batch size: 256 | lm loss: 3.336371E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.789 | TFLOPs: 27.48 | +7: iteration 33160/ 37905 | consumed samples: 8488960 | consumed tokens: 17385390080 | elapsed time per iteration (s): 0.24 | learning rate: 2.701E-05 | global batch size: 256 | lm loss: 3.290523E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1068.570 | TFLOPs: 27.22 | +7: iteration 33170/ 37905 | consumed samples: 8491520 | consumed tokens: 17390632960 | elapsed time per iteration (s): 0.23 | learning rate: 2.698E-05 | global batch size: 256 | lm loss: 3.308162E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.021 | TFLOPs: 28.00 | +7: iteration 33180/ 37905 | consumed samples: 8494080 | consumed tokens: 17395875840 | elapsed time per iteration (s): 0.23 | learning rate: 2.695E-05 | global batch size: 256 | lm loss: 3.300585E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.015 | TFLOPs: 28.48 | +7: iteration 33190/ 37905 | consumed samples: 8496640 | consumed tokens: 17401118720 | elapsed time per iteration (s): 0.23 | learning rate: 2.692E-05 | global batch size: 256 | lm loss: 3.298924E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.660 | TFLOPs: 28.37 | +7: iteration 33200/ 37905 | consumed samples: 8499200 | consumed tokens: 17406361600 | elapsed time per iteration (s): 0.23 | learning rate: 2.689E-05 | global batch size: 256 | lm loss: 3.305859E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.486 | TFLOPs: 28.26 | +7: iteration 33210/ 37905 | consumed samples: 8501760 | consumed tokens: 17411604480 | elapsed time per iteration (s): 0.23 | learning rate: 2.686E-05 | global batch size: 256 | lm loss: 3.316656E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.830 | TFLOPs: 28.12 | +7: iteration 33220/ 37905 | consumed samples: 8504320 | consumed tokens: 17416847360 | elapsed time per iteration (s): 0.23 | learning rate: 2.683E-05 | global batch size: 256 | lm loss: 3.316607E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.923 | TFLOPs: 28.33 | +7: iteration 33230/ 37905 | consumed samples: 8506880 | consumed tokens: 17422090240 | elapsed time per iteration (s): 0.23 | learning rate: 2.681E-05 | global batch size: 256 | lm loss: 3.324586E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.281 | TFLOPs: 28.21 | +7: iteration 33240/ 37905 | consumed samples: 8509440 | consumed tokens: 17427333120 | elapsed time per iteration (s): 0.23 | learning rate: 2.678E-05 | global batch size: 256 | lm loss: 3.311736E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.392 | TFLOPs: 28.19 | +7: iteration 33250/ 37905 | consumed samples: 8512000 | consumed tokens: 17432576000 | elapsed time per iteration (s): 0.23 | learning rate: 2.675E-05 | global batch size: 256 | lm loss: 3.311051E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.723 | TFLOPs: 28.14 | +7: iteration 33260/ 37905 | consumed samples: 8514560 | consumed tokens: 17437818880 | elapsed time per iteration (s): 0.24 | learning rate: 2.672E-05 | global batch size: 256 | lm loss: 3.303263E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1068.834 | TFLOPs: 27.23 | +7: iteration 33270/ 37905 | consumed samples: 8517120 | consumed tokens: 17443061760 | elapsed time per iteration (s): 0.23 | learning rate: 2.669E-05 | global batch size: 256 | lm loss: 3.339651E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.889 | TFLOPs: 28.33 | +7: iteration 33280/ 37905 | consumed samples: 8519680 | consumed tokens: 17448304640 | elapsed time per iteration (s): 0.23 | learning rate: 2.666E-05 | global batch size: 256 | lm loss: 3.325168E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.213 | TFLOPs: 28.51 | +7: iteration 33290/ 37905 | consumed samples: 8522240 | consumed tokens: 17453547520 | elapsed time per iteration (s): 0.23 | learning rate: 2.663E-05 | global batch size: 256 | lm loss: 3.328601E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.531 | TFLOPs: 28.55 | +7: iteration 33300/ 37905 | consumed samples: 8524800 | consumed tokens: 17458790400 | elapsed time per iteration (s): 0.23 | learning rate: 2.661E-05 | global batch size: 256 | lm loss: 3.312145E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.686 | TFLOPs: 27.96 | +7: iteration 33310/ 37905 | consumed samples: 8527360 | consumed tokens: 17464033280 | elapsed time per iteration (s): 0.23 | learning rate: 2.658E-05 | global batch size: 256 | lm loss: 3.307642E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.967 | TFLOPs: 28.53 | +7: iteration 33320/ 37905 | consumed samples: 8529920 | consumed tokens: 17469276160 | elapsed time per iteration (s): 0.23 | learning rate: 2.655E-05 | global batch size: 256 | lm loss: 3.320621E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.345 | TFLOPs: 28.31 | +7: iteration 33330/ 37905 | consumed samples: 8532480 | consumed tokens: 17474519040 | elapsed time per iteration (s): 0.24 | learning rate: 2.652E-05 | global batch size: 256 | lm loss: 3.312555E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.808 | TFLOPs: 26.95 | +7: iteration 33340/ 37905 | consumed samples: 8535040 | consumed tokens: 17479761920 | elapsed time per iteration (s): 0.24 | learning rate: 2.649E-05 | global batch size: 256 | lm loss: 3.324508E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.566 | TFLOPs: 27.27 | +7: iteration 33350/ 37905 | consumed samples: 8537600 | consumed tokens: 17485004800 | elapsed time per iteration (s): 0.23 | learning rate: 2.647E-05 | global batch size: 256 | lm loss: 3.355490E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.378 | TFLOPs: 28.54 | +7: iteration 33360/ 37905 | consumed samples: 8540160 | consumed tokens: 17490247680 | elapsed time per iteration (s): 0.23 | learning rate: 2.644E-05 | global batch size: 256 | lm loss: 3.313221E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.503 | TFLOPs: 28.16 | +7: iteration 33370/ 37905 | consumed samples: 8542720 | consumed tokens: 17495490560 | elapsed time per iteration (s): 0.23 | learning rate: 2.641E-05 | global batch size: 256 | lm loss: 3.328320E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.955 | TFLOPs: 28.45 | +7: iteration 33380/ 37905 | consumed samples: 8545280 | consumed tokens: 17500733440 | elapsed time per iteration (s): 0.23 | learning rate: 2.638E-05 | global batch size: 256 | lm loss: 3.336722E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.037 | TFLOPs: 28.20 | +7: iteration 33390/ 37905 | consumed samples: 8547840 | consumed tokens: 17505976320 | elapsed time per iteration (s): 0.23 | learning rate: 2.635E-05 | global batch size: 256 | lm loss: 3.308049E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.039 | TFLOPs: 28.23 | +7: iteration 33400/ 37905 | consumed samples: 8550400 | consumed tokens: 17511219200 | elapsed time per iteration (s): 0.23 | learning rate: 2.633E-05 | global batch size: 256 | lm loss: 3.299544E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.497 | TFLOPs: 28.29 | +7: iteration 33410/ 37905 | consumed samples: 8552960 | consumed tokens: 17516462080 | elapsed time per iteration (s): 0.23 | learning rate: 2.630E-05 | global batch size: 256 | lm loss: 3.344507E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.754 | TFLOPs: 27.79 | +7: iteration 33420/ 37905 | consumed samples: 8555520 | consumed tokens: 17521704960 | elapsed time per iteration (s): 0.23 | learning rate: 2.627E-05 | global batch size: 256 | lm loss: 3.323983E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.844 | TFLOPs: 28.53 | +7: iteration 33430/ 37905 | consumed samples: 8558080 | consumed tokens: 17526947840 | elapsed time per iteration (s): 0.23 | learning rate: 2.624E-05 | global batch size: 256 | lm loss: 3.324134E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.929 | TFLOPs: 28.56 | +7: iteration 33440/ 37905 | consumed samples: 8560640 | consumed tokens: 17532190720 | elapsed time per iteration (s): 0.23 | learning rate: 2.622E-05 | global batch size: 256 | lm loss: 3.344926E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.311 | TFLOPs: 28.62 | +7: iteration 33450/ 37905 | consumed samples: 8563200 | consumed tokens: 17537433600 | elapsed time per iteration (s): 0.23 | learning rate: 2.619E-05 | global batch size: 256 | lm loss: 3.311760E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.669 | TFLOPs: 28.57 | +7: iteration 33460/ 37905 | consumed samples: 8565760 | consumed tokens: 17542676480 | elapsed time per iteration (s): 0.24 | learning rate: 2.616E-05 | global batch size: 256 | lm loss: 3.329024E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.947 | TFLOPs: 27.69 | +7: iteration 33470/ 37905 | consumed samples: 8568320 | consumed tokens: 17547919360 | elapsed time per iteration (s): 0.23 | learning rate: 2.613E-05 | global batch size: 256 | lm loss: 3.332326E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.351 | TFLOPs: 28.08 | +7: iteration 33480/ 37905 | consumed samples: 8570880 | consumed tokens: 17553162240 | elapsed time per iteration (s): 0.23 | learning rate: 2.611E-05 | global batch size: 256 | lm loss: 3.325063E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.834 | TFLOPs: 28.02 | +7: iteration 33490/ 37905 | consumed samples: 8573440 | consumed tokens: 17558405120 | elapsed time per iteration (s): 0.23 | learning rate: 2.608E-05 | global batch size: 256 | lm loss: 3.311943E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.128 | TFLOPs: 28.00 | +7: iteration 33500/ 37905 | consumed samples: 8576000 | consumed tokens: 17563648000 | elapsed time per iteration (s): 0.25 | learning rate: 2.605E-05 | global batch size: 256 | lm loss: 3.318550E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1020.261 | TFLOPs: 25.99 | +7: iteration 33510/ 37905 | consumed samples: 8578560 | consumed tokens: 17568890880 | elapsed time per iteration (s): 0.23 | learning rate: 2.602E-05 | global batch size: 256 | lm loss: 3.297909E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.796 | TFLOPs: 28.09 | +7: iteration 33520/ 37905 | consumed samples: 8581120 | consumed tokens: 17574133760 | elapsed time per iteration (s): 0.23 | learning rate: 2.600E-05 | global batch size: 256 | lm loss: 3.332654E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.048 | TFLOPs: 28.51 | +7: iteration 33530/ 37905 | consumed samples: 8583680 | consumed tokens: 17579376640 | elapsed time per iteration (s): 0.23 | learning rate: 2.597E-05 | global batch size: 256 | lm loss: 3.369482E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.121 | TFLOPs: 28.31 | +7: iteration 33540/ 37905 | consumed samples: 8586240 | consumed tokens: 17584619520 | elapsed time per iteration (s): 0.24 | learning rate: 2.594E-05 | global batch size: 256 | lm loss: 3.314483E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.674 | TFLOPs: 27.73 | +7: iteration 33550/ 37905 | consumed samples: 8588800 | consumed tokens: 17589862400 | elapsed time per iteration (s): 0.23 | learning rate: 2.592E-05 | global batch size: 256 | lm loss: 3.318391E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.853 | TFLOPs: 28.45 | +7: iteration 33560/ 37905 | consumed samples: 8591360 | consumed tokens: 17595105280 | elapsed time per iteration (s): 0.23 | learning rate: 2.589E-05 | global batch size: 256 | lm loss: 3.340439E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.905 | TFLOPs: 28.28 | +7: iteration 33570/ 37905 | consumed samples: 8593920 | consumed tokens: 17600348160 | elapsed time per iteration (s): 0.23 | learning rate: 2.586E-05 | global batch size: 256 | lm loss: 3.330313E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.372 | TFLOPs: 28.26 | +7: iteration 33580/ 37905 | consumed samples: 8596480 | consumed tokens: 17605591040 | elapsed time per iteration (s): 0.23 | learning rate: 2.584E-05 | global batch size: 256 | lm loss: 3.294002E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.077 | TFLOPs: 28.18 | +7: iteration 33590/ 37905 | consumed samples: 8599040 | consumed tokens: 17610833920 | elapsed time per iteration (s): 0.25 | learning rate: 2.581E-05 | global batch size: 256 | lm loss: 3.322152E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1039.465 | TFLOPs: 26.48 | +7: iteration 33600/ 37905 | consumed samples: 8601600 | consumed tokens: 17616076800 | elapsed time per iteration (s): 0.24 | learning rate: 2.578E-05 | global batch size: 256 | lm loss: 3.301921E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1069.952 | TFLOPs: 27.26 | +7: iteration 33610/ 37905 | consumed samples: 8604160 | consumed tokens: 17621319680 | elapsed time per iteration (s): 0.23 | learning rate: 2.576E-05 | global batch size: 256 | lm loss: 3.321700E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.740 | TFLOPs: 27.97 | +7: iteration 33620/ 37905 | consumed samples: 8606720 | consumed tokens: 17626562560 | elapsed time per iteration (s): 0.23 | learning rate: 2.573E-05 | global batch size: 256 | lm loss: 3.329289E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.585 | TFLOPs: 28.42 | +7: iteration 33630/ 37905 | consumed samples: 8609280 | consumed tokens: 17631805440 | elapsed time per iteration (s): 0.23 | learning rate: 2.570E-05 | global batch size: 256 | lm loss: 3.304009E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.452 | TFLOPs: 28.44 | +7: iteration 33640/ 37905 | consumed samples: 8611840 | consumed tokens: 17637048320 | elapsed time per iteration (s): 0.23 | learning rate: 2.568E-05 | global batch size: 256 | lm loss: 3.359724E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.013 | TFLOPs: 28.15 | +7: iteration 33650/ 37905 | consumed samples: 8614400 | consumed tokens: 17642291200 | elapsed time per iteration (s): 0.23 | learning rate: 2.565E-05 | global batch size: 256 | lm loss: 3.303714E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.944 | TFLOPs: 28.15 | +7: iteration 33660/ 37905 | consumed samples: 8616960 | consumed tokens: 17647534080 | elapsed time per iteration (s): 0.23 | learning rate: 2.562E-05 | global batch size: 256 | lm loss: 3.304192E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.245 | TFLOPs: 27.88 | +7: iteration 33670/ 37905 | consumed samples: 8619520 | consumed tokens: 17652776960 | elapsed time per iteration (s): 0.23 | learning rate: 2.560E-05 | global batch size: 256 | lm loss: 3.306022E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.997 | TFLOPs: 27.82 | +7: iteration 33680/ 37905 | consumed samples: 8622080 | consumed tokens: 17658019840 | elapsed time per iteration (s): 0.23 | learning rate: 2.557E-05 | global batch size: 256 | lm loss: 3.327963E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.116 | TFLOPs: 27.85 | +7: iteration 33690/ 37905 | consumed samples: 8624640 | consumed tokens: 17663262720 | elapsed time per iteration (s): 0.23 | learning rate: 2.555E-05 | global batch size: 256 | lm loss: 3.313134E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.769 | TFLOPs: 28.45 | +7: iteration 33700/ 37905 | consumed samples: 8627200 | consumed tokens: 17668505600 | elapsed time per iteration (s): 0.23 | learning rate: 2.552E-05 | global batch size: 256 | lm loss: 3.352610E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.053 | TFLOPs: 28.41 | +7: iteration 33710/ 37905 | consumed samples: 8629760 | consumed tokens: 17673748480 | elapsed time per iteration (s): 0.23 | learning rate: 2.549E-05 | global batch size: 256 | lm loss: 3.320847E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.229 | TFLOPs: 27.98 | +7: iteration 33720/ 37905 | consumed samples: 8632320 | consumed tokens: 17678991360 | elapsed time per iteration (s): 0.23 | learning rate: 2.547E-05 | global batch size: 256 | lm loss: 3.335234E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.580 | TFLOPs: 28.24 | +7: iteration 33730/ 37905 | consumed samples: 8634880 | consumed tokens: 17684234240 | elapsed time per iteration (s): 0.23 | learning rate: 2.544E-05 | global batch size: 256 | lm loss: 3.321343E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.629 | TFLOPs: 28.37 | +7: iteration 33740/ 37905 | consumed samples: 8637440 | consumed tokens: 17689477120 | elapsed time per iteration (s): 0.36 | learning rate: 2.542E-05 | global batch size: 256 | lm loss: 3.307088E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 719.753 | TFLOPs: 18.34 | +7: iteration 33750/ 37905 | consumed samples: 8640000 | consumed tokens: 17694720000 | elapsed time per iteration (s): 0.23 | learning rate: 2.539E-05 | global batch size: 256 | lm loss: 3.314781E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.181 | TFLOPs: 28.28 | +7: iteration 33760/ 37905 | consumed samples: 8642560 | consumed tokens: 17699962880 | elapsed time per iteration (s): 0.24 | learning rate: 2.536E-05 | global batch size: 256 | lm loss: 3.326329E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1084.925 | TFLOPs: 27.64 | +7: iteration 33770/ 37905 | consumed samples: 8645120 | consumed tokens: 17705205760 | elapsed time per iteration (s): 0.23 | learning rate: 2.534E-05 | global batch size: 256 | lm loss: 3.322322E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.429 | TFLOPs: 28.21 | +7: iteration 33780/ 37905 | consumed samples: 8647680 | consumed tokens: 17710448640 | elapsed time per iteration (s): 0.23 | learning rate: 2.531E-05 | global batch size: 256 | lm loss: 3.312600E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.419 | TFLOPs: 28.34 | +7: iteration 33790/ 37905 | consumed samples: 8650240 | consumed tokens: 17715691520 | elapsed time per iteration (s): 0.23 | learning rate: 2.529E-05 | global batch size: 256 | lm loss: 3.315945E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.917 | TFLOPs: 28.30 | +7: iteration 33800/ 37905 | consumed samples: 8652800 | consumed tokens: 17720934400 | elapsed time per iteration (s): 0.23 | learning rate: 2.526E-05 | global batch size: 256 | lm loss: 3.307295E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.802 | TFLOPs: 28.25 | +7: iteration 33810/ 37905 | consumed samples: 8655360 | consumed tokens: 17726177280 | elapsed time per iteration (s): 0.23 | learning rate: 2.524E-05 | global batch size: 256 | lm loss: 3.323159E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.594 | TFLOPs: 28.39 | +7: iteration 33820/ 37905 | consumed samples: 8657920 | consumed tokens: 17731420160 | elapsed time per iteration (s): 0.23 | learning rate: 2.521E-05 | global batch size: 256 | lm loss: 3.308002E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.379 | TFLOPs: 28.52 | +7: iteration 33830/ 37905 | consumed samples: 8660480 | consumed tokens: 17736663040 | elapsed time per iteration (s): 0.23 | learning rate: 2.519E-05 | global batch size: 256 | lm loss: 3.313223E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.676 | TFLOPs: 28.07 | +7: iteration 33840/ 37905 | consumed samples: 8663040 | consumed tokens: 17741905920 | elapsed time per iteration (s): 0.23 | learning rate: 2.516E-05 | global batch size: 256 | lm loss: 3.314602E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.545 | TFLOPs: 28.24 | +7: iteration 33850/ 37905 | consumed samples: 8665600 | consumed tokens: 17747148800 | elapsed time per iteration (s): 0.23 | learning rate: 2.514E-05 | global batch size: 256 | lm loss: 3.338459E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.238 | TFLOPs: 28.33 | +7: iteration 33860/ 37905 | consumed samples: 8668160 | consumed tokens: 17752391680 | elapsed time per iteration (s): 0.23 | learning rate: 2.511E-05 | global batch size: 256 | lm loss: 3.329881E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.438 | TFLOPs: 28.29 | +7: iteration 33870/ 37905 | consumed samples: 8670720 | consumed tokens: 17757634560 | elapsed time per iteration (s): 0.24 | learning rate: 2.509E-05 | global batch size: 256 | lm loss: 3.330582E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1082.952 | TFLOPs: 27.59 | +7: iteration 33880/ 37905 | consumed samples: 8673280 | consumed tokens: 17762877440 | elapsed time per iteration (s): 0.23 | learning rate: 2.506E-05 | global batch size: 256 | lm loss: 3.309301E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.278 | TFLOPs: 28.31 | +7: iteration 33890/ 37905 | consumed samples: 8675840 | consumed tokens: 17768120320 | elapsed time per iteration (s): 0.23 | learning rate: 2.504E-05 | global batch size: 256 | lm loss: 3.322940E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.500 | TFLOPs: 28.60 | +7: iteration 33900/ 37905 | consumed samples: 8678400 | consumed tokens: 17773363200 | elapsed time per iteration (s): 0.25 | learning rate: 2.501E-05 | global batch size: 256 | lm loss: 3.307302E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1035.602 | TFLOPs: 26.38 | +7: iteration 33910/ 37905 | consumed samples: 8680960 | consumed tokens: 17778606080 | elapsed time per iteration (s): 0.23 | learning rate: 2.499E-05 | global batch size: 256 | lm loss: 3.293053E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.402 | TFLOPs: 28.39 | +7: iteration 33920/ 37905 | consumed samples: 8683520 | consumed tokens: 17783848960 | elapsed time per iteration (s): 0.23 | learning rate: 2.496E-05 | global batch size: 256 | lm loss: 3.291716E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.812 | TFLOPs: 28.40 | +7: iteration 33930/ 37905 | consumed samples: 8686080 | consumed tokens: 17789091840 | elapsed time per iteration (s): 0.23 | learning rate: 2.494E-05 | global batch size: 256 | lm loss: 3.309597E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.855 | TFLOPs: 28.60 | +7: iteration 33940/ 37905 | consumed samples: 8688640 | consumed tokens: 17794334720 | elapsed time per iteration (s): 0.23 | learning rate: 2.491E-05 | global batch size: 256 | lm loss: 3.327707E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.891 | TFLOPs: 28.63 | +7: iteration 33950/ 37905 | consumed samples: 8691200 | consumed tokens: 17799577600 | elapsed time per iteration (s): 0.23 | learning rate: 2.489E-05 | global batch size: 256 | lm loss: 3.313089E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.386 | TFLOPs: 27.91 | +7: iteration 33960/ 37905 | consumed samples: 8693760 | consumed tokens: 17804820480 | elapsed time per iteration (s): 0.23 | learning rate: 2.486E-05 | global batch size: 256 | lm loss: 3.300062E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.267 | TFLOPs: 28.23 | +7: iteration 33970/ 37905 | consumed samples: 8696320 | consumed tokens: 17810063360 | elapsed time per iteration (s): 0.24 | learning rate: 2.484E-05 | global batch size: 256 | lm loss: 3.291638E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1063.782 | TFLOPs: 27.10 | +7: iteration 33980/ 37905 | consumed samples: 8698880 | consumed tokens: 17815306240 | elapsed time per iteration (s): 0.23 | learning rate: 2.482E-05 | global batch size: 256 | lm loss: 3.343315E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.341 | TFLOPs: 28.49 | +7: iteration 33990/ 37905 | consumed samples: 8701440 | consumed tokens: 17820549120 | elapsed time per iteration (s): 0.24 | learning rate: 2.479E-05 | global batch size: 256 | lm loss: 3.318455E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1046.960 | TFLOPs: 26.67 | +0: [2022-11-29 19:09:54,754] [INFO] [logging.py:68:log_dist] [Rank 0] step=34000, skipped=0, lr=[2.4766896881602934e-05, 2.4766896881602934e-05, 2.4766896881602934e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 34000/ 37905 | consumed samples: 8704000 | consumed tokens: 17825792000 | elapsed time per iteration (s): 0.23 | learning rate: 2.477E-05 | global batch size: 256 | lm loss: 3.352442E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.710 | TFLOPs: 28.63 | +0: steps: 34000 loss: 3.2674 iter time (s): 0.232 samples/sec: 1102.079 +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 34000 | lm loss value: 3.208467E+00 | lm loss PPL: 2.474114E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 34000 to checkpoints_83moscar +0: [2022-11-29 19:09:54,861] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step34000 is begin to save! +0: [2022-11-29 19:09:54,866] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/layer_01-model_00-model_states.pt... +0: [2022-11-29 19:09:54,947] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/layer_01-model_00-model_states.pt. +0: [2022-11-29 19:09:54,948] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/layer_03-model_00-model_states.pt... +0: [2022-11-29 19:09:54,960] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/layer_03-model_00-model_states.pt. +0: [2022-11-29 19:09:54,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/layer_04-model_00-model_states.pt... +0: [2022-11-29 19:09:54,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/layer_04-model_00-model_states.pt. +0: [2022-11-29 19:09:54,973] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/layer_05-model_00-model_states.pt... +0: [2022-11-29 19:09:54,985] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/layer_05-model_00-model_states.pt. +0: [2022-11-29 19:09:54,985] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/layer_06-model_00-model_states.pt... +0: [2022-11-29 19:09:54,997] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/layer_06-model_00-model_states.pt. +0: [2022-11-29 19:09:54,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/layer_07-model_00-model_states.pt... +0: [2022-11-29 19:09:55,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/layer_07-model_00-model_states.pt. +0: [2022-11-29 19:09:55,009] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/layer_08-model_00-model_states.pt... +0: [2022-11-29 19:09:55,021] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/layer_08-model_00-model_states.pt. +0: [2022-11-29 19:09:55,021] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/layer_09-model_00-model_states.pt... +0: [2022-11-29 19:09:55,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/layer_09-model_00-model_states.pt. +0: [2022-11-29 19:09:55,033] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/layer_10-model_00-model_states.pt... +0: [2022-11-29 19:09:55,045] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/layer_10-model_00-model_states.pt. +0: [2022-11-29 19:09:55,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/layer_11-model_00-model_states.pt... +0: [2022-11-29 19:09:55,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/layer_11-model_00-model_states.pt. +0: [2022-11-29 19:09:55,057] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/layer_12-model_00-model_states.pt... +0: [2022-11-29 19:09:55,069] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/layer_12-model_00-model_states.pt. +0: [2022-11-29 19:09:55,069] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/layer_14-model_00-model_states.pt... +0: [2022-11-29 19:09:55,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/layer_14-model_00-model_states.pt. +0: [2022-11-29 19:09:55,070] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step34000/mp_rank_00_model_states.pt +0: [2022-11-29 19:09:55,070] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/mp_rank_00_model_states.pt... +0: [2022-11-29 19:09:55,072] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/mp_rank_00_model_states.pt. +0: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:09:55,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:09:55,109] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:09:55,109] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 19:09:55,109] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +3: [2022-11-29 19:09:55,109] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:09:55,109] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 19:09:55,109] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +0: [2022-11-29 19:09:55,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:09:55,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:09:55,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:09:55,110] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +1: [2022-11-29 19:09:55,110] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +2: [2022-11-29 19:09:55,110] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +1: [2022-11-29 19:09:55,110] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +1: [2022-11-29 19:09:55,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:09:55,110] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 19:09:55,110] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +6: [2022-11-29 19:09:55,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:09:55,111] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 19:09:55,111] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +6: [2022-11-29 19:09:55,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:09:55,111] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 19:09:55,111] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +0: [2022-11-29 19:09:55,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:09:55,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:09:55,111] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +2: [2022-11-29 19:09:55,111] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +0: [2022-11-29 19:09:55,111] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +2: [2022-11-29 19:09:55,111] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +5: [2022-11-29 19:09:55,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:09:55,111] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 19:09:55,111] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +6: [2022-11-29 19:09:55,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:09:55,112] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 19:09:55,112] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +3: [2022-11-29 19:09:55,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:09:55,112] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 19:09:55,112] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +0: [2022-11-29 19:09:55,112] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 19:09:55,112] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +3: [2022-11-29 19:09:55,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:09:55,112] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 19:09:55,112] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +1: [2022-11-29 19:09:55,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:09:55,112] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 19:09:55,112] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +5: [2022-11-29 19:09:55,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:09:55,113] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 19:09:55,113] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +1: [2022-11-29 19:09:55,113] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:09:55,113] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:09:55,113] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +2: [2022-11-29 19:09:55,113] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +1: [2022-11-29 19:09:55,113] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +2: [2022-11-29 19:09:55,113] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +0: [2022-11-29 19:09:55,113] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:09:55,113] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 19:09:55,113] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +5: [2022-11-29 19:09:55,113] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:09:55,113] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:09:55,113] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +5: [2022-11-29 19:09:55,113] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 19:09:55,114] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +6: [2022-11-29 19:09:55,114] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +2: [2022-11-29 19:09:55,113] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:09:55,114] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 19:09:55,114] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +3: [2022-11-29 19:09:55,114] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:09:55,114] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 19:09:55,114] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +0: [2022-11-29 19:09:55,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:09:55,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:09:55,115] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +0: [2022-11-29 19:09:55,115] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +1: [2022-11-29 19:09:55,115] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +5: [2022-11-29 19:09:55,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:09:55,115] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +5: [2022-11-29 19:09:55,115] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 19:09:55,115] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +2: [2022-11-29 19:09:55,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:09:55,115] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +1: [2022-11-29 19:09:55,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:09:55,115] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +1: [2022-11-29 19:09:55,115] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +3: [2022-11-29 19:09:55,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:09:55,115] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +3: [2022-11-29 19:09:55,115] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 19:09:55,115] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +0: [2022-11-29 19:09:55,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:09:55,115] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 19:09:55,115] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +6: [2022-11-29 19:09:55,116] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:09:55,116] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 19:09:55,116] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +5: [2022-11-29 19:09:55,116] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:09:55,116] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 19:09:55,116] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +6: [2022-11-29 19:09:55,116] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:09:55,116] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 19:09:55,116] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +0: [2022-11-29 19:09:55,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:09:55,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:09:55,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +0: [2022-11-29 19:09:55,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +2: [2022-11-29 19:09:55,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:09:55,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +0: [2022-11-29 19:09:55,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +2: [2022-11-29 19:09:55,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 19:09:55,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +6: [2022-11-29 19:09:55,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:09:55,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 19:09:55,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +7: [2022-11-29 19:09:55,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:09:55,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:09:55,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 19:09:55,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +3: [2022-11-29 19:09:55,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 19:09:55,118] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +5: [2022-11-29 19:09:55,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:09:55,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:09:55,118] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 19:09:55,118] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +7: [2022-11-29 19:09:55,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:09:55,118] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +7: [2022-11-29 19:09:55,118] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +1: [2022-11-29 19:09:55,118] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +7: [2022-11-29 19:09:55,118] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +7: [2022-11-29 19:09:55,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:09:55,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:09:55,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:09:55,118] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +5: [2022-11-29 19:09:55,118] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 19:09:55,118] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +6: [2022-11-29 19:09:55,118] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +7: [2022-11-29 19:09:55,118] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +6: [2022-11-29 19:09:55,118] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +7: [2022-11-29 19:09:55,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:09:55,118] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +3: [2022-11-29 19:09:55,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:09:55,118] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +3: [2022-11-29 19:09:55,118] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +7: [2022-11-29 19:09:55,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:09:55,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +7: [2022-11-29 19:09:55,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 19:09:55,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +0: [2022-11-29 19:09:55,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:09:55,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 19:09:55,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +2: [2022-11-29 19:09:55,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:09:55,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:09:55,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:09:55,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +2: [2022-11-29 19:09:55,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 19:09:55,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +3: [2022-11-29 19:09:55,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +2: [2022-11-29 19:09:55,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +2: [2022-11-29 19:09:55,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +7: [2022-11-29 19:09:55,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:09:55,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 19:09:55,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +0: [2022-11-29 19:09:55,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:09:55,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 19:09:55,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +7: [2022-11-29 19:09:55,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:09:55,120] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 19:09:55,120] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +7: [2022-11-29 19:09:55,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:09:55,121] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 19:09:55,121] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +4: [2022-11-29 19:09:55,137] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:09:55,137] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 19:09:55,137] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +4: [2022-11-29 19:09:55,137] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:09:55,137] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 19:09:55,137] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +4: [2022-11-29 19:09:55,137] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:09:55,137] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 19:09:55,138] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +4: [2022-11-29 19:09:55,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:09:55,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:09:55,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:09:55,138] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 19:09:55,138] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 19:09:55,138] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 19:09:55,138] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +4: [2022-11-29 19:09:55,138] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +4: [2022-11-29 19:09:55,138] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +4: [2022-11-29 19:09:55,139] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:09:55,139] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 19:09:55,139] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +4: [2022-11-29 19:09:55,139] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:09:55,139] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step34000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 19:09:55,139] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +0: successfully saved checkpoint at iteration 34000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 299.35 +7: iteration 34010/ 37905 | consumed samples: 8706560 | consumed tokens: 17831034880 | elapsed time per iteration (s): 0.27 | learning rate: 2.474E-05 | global batch size: 256 | lm loss: 3.299909E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 959.138 | TFLOPs: 24.43 | +7: iteration 34020/ 37905 | consumed samples: 8709120 | consumed tokens: 17836277760 | elapsed time per iteration (s): 0.23 | learning rate: 2.472E-05 | global batch size: 256 | lm loss: 3.327533E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.189 | TFLOPs: 28.49 | +7: iteration 34030/ 37905 | consumed samples: 8711680 | consumed tokens: 17841520640 | elapsed time per iteration (s): 0.23 | learning rate: 2.469E-05 | global batch size: 256 | lm loss: 3.320727E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.606 | TFLOPs: 28.50 | +7: iteration 34040/ 37905 | consumed samples: 8714240 | consumed tokens: 17846763520 | elapsed time per iteration (s): 0.23 | learning rate: 2.467E-05 | global batch size: 256 | lm loss: 3.316864E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.455 | TFLOPs: 28.42 | +7: iteration 34050/ 37905 | consumed samples: 8716800 | consumed tokens: 17852006400 | elapsed time per iteration (s): 0.23 | learning rate: 2.465E-05 | global batch size: 256 | lm loss: 3.295593E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.011 | TFLOPs: 28.07 | +7: iteration 34060/ 37905 | consumed samples: 8719360 | consumed tokens: 17857249280 | elapsed time per iteration (s): 0.23 | learning rate: 2.462E-05 | global batch size: 256 | lm loss: 3.328473E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.890 | TFLOPs: 28.38 | +7: iteration 34070/ 37905 | consumed samples: 8721920 | consumed tokens: 17862492160 | elapsed time per iteration (s): 0.23 | learning rate: 2.460E-05 | global batch size: 256 | lm loss: 3.315711E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.665 | TFLOPs: 28.40 | +7: iteration 34080/ 37905 | consumed samples: 8724480 | consumed tokens: 17867735040 | elapsed time per iteration (s): 0.23 | learning rate: 2.458E-05 | global batch size: 256 | lm loss: 3.319535E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.203 | TFLOPs: 27.87 | +7: iteration 34090/ 37905 | consumed samples: 8727040 | consumed tokens: 17872977920 | elapsed time per iteration (s): 0.23 | learning rate: 2.455E-05 | global batch size: 256 | lm loss: 3.331499E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.501 | TFLOPs: 28.34 | +7: iteration 34100/ 37905 | consumed samples: 8729600 | consumed tokens: 17878220800 | elapsed time per iteration (s): 0.23 | learning rate: 2.453E-05 | global batch size: 256 | lm loss: 3.309347E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.083 | TFLOPs: 28.08 | +7: iteration 34110/ 37905 | consumed samples: 8732160 | consumed tokens: 17883463680 | elapsed time per iteration (s): 0.23 | learning rate: 2.450E-05 | global batch size: 256 | lm loss: 3.330491E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.166 | TFLOPs: 28.36 | +7: iteration 34120/ 37905 | consumed samples: 8734720 | consumed tokens: 17888706560 | elapsed time per iteration (s): 0.25 | learning rate: 2.448E-05 | global batch size: 256 | lm loss: 3.322343E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1031.874 | TFLOPs: 26.29 | +7: iteration 34130/ 37905 | consumed samples: 8737280 | consumed tokens: 17893949440 | elapsed time per iteration (s): 0.33 | learning rate: 2.446E-05 | global batch size: 256 | lm loss: 3.332109E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 775.534 | TFLOPs: 19.76 | +7: iteration 34140/ 37905 | consumed samples: 8739840 | consumed tokens: 17899192320 | elapsed time per iteration (s): 0.24 | learning rate: 2.443E-05 | global batch size: 256 | lm loss: 3.312294E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1072.491 | TFLOPs: 27.32 | +7: iteration 34150/ 37905 | consumed samples: 8742400 | consumed tokens: 17904435200 | elapsed time per iteration (s): 0.24 | learning rate: 2.441E-05 | global batch size: 256 | lm loss: 3.306622E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.454 | TFLOPs: 27.27 | +7: iteration 34160/ 37905 | consumed samples: 8744960 | consumed tokens: 17909678080 | elapsed time per iteration (s): 0.23 | learning rate: 2.439E-05 | global batch size: 256 | lm loss: 3.300999E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.031 | TFLOPs: 28.28 | +7: iteration 34170/ 37905 | consumed samples: 8747520 | consumed tokens: 17914920960 | elapsed time per iteration (s): 0.23 | learning rate: 2.436E-05 | global batch size: 256 | lm loss: 3.291340E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.634 | TFLOPs: 28.34 | +7: iteration 34180/ 37905 | consumed samples: 8750080 | consumed tokens: 17920163840 | elapsed time per iteration (s): 0.23 | learning rate: 2.434E-05 | global batch size: 256 | lm loss: 3.317682E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.467 | TFLOPs: 27.91 | +7: iteration 34190/ 37905 | consumed samples: 8752640 | consumed tokens: 17925406720 | elapsed time per iteration (s): 0.23 | learning rate: 2.432E-05 | global batch size: 256 | lm loss: 3.322421E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.041 | TFLOPs: 28.20 | +7: iteration 34200/ 37905 | consumed samples: 8755200 | consumed tokens: 17930649600 | elapsed time per iteration (s): 0.23 | learning rate: 2.429E-05 | global batch size: 256 | lm loss: 3.314248E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.894 | TFLOPs: 28.17 | +7: iteration 34210/ 37905 | consumed samples: 8757760 | consumed tokens: 17935892480 | elapsed time per iteration (s): 0.23 | learning rate: 2.427E-05 | global batch size: 256 | lm loss: 3.346612E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.521 | TFLOPs: 28.14 | +7: iteration 34220/ 37905 | consumed samples: 8760320 | consumed tokens: 17941135360 | elapsed time per iteration (s): 0.23 | learning rate: 2.425E-05 | global batch size: 256 | lm loss: 3.328949E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.567 | TFLOPs: 27.76 | +7: iteration 34230/ 37905 | consumed samples: 8762880 | consumed tokens: 17946378240 | elapsed time per iteration (s): 0.23 | learning rate: 2.423E-05 | global batch size: 256 | lm loss: 3.324920E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.660 | TFLOPs: 28.06 | +7: iteration 34240/ 37905 | consumed samples: 8765440 | consumed tokens: 17951621120 | elapsed time per iteration (s): 0.23 | learning rate: 2.420E-05 | global batch size: 256 | lm loss: 3.288745E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.087 | TFLOPs: 28.48 | +7: iteration 34250/ 37905 | consumed samples: 8768000 | consumed tokens: 17956864000 | elapsed time per iteration (s): 0.23 | learning rate: 2.418E-05 | global batch size: 256 | lm loss: 3.270954E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.139 | TFLOPs: 28.33 | +7: iteration 34260/ 37905 | consumed samples: 8770560 | consumed tokens: 17962106880 | elapsed time per iteration (s): 0.23 | learning rate: 2.416E-05 | global batch size: 256 | lm loss: 3.297705E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.428 | TFLOPs: 28.31 | +7: iteration 34270/ 37905 | consumed samples: 8773120 | consumed tokens: 17967349760 | elapsed time per iteration (s): 0.23 | learning rate: 2.414E-05 | global batch size: 256 | lm loss: 3.337617E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.465 | TFLOPs: 27.98 | +7: iteration 34280/ 37905 | consumed samples: 8775680 | consumed tokens: 17972592640 | elapsed time per iteration (s): 0.23 | learning rate: 2.411E-05 | global batch size: 256 | lm loss: 3.312381E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.789 | TFLOPs: 28.40 | +7: iteration 34290/ 37905 | consumed samples: 8778240 | consumed tokens: 17977835520 | elapsed time per iteration (s): 0.23 | learning rate: 2.409E-05 | global batch size: 256 | lm loss: 3.293545E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.500 | TFLOPs: 28.24 | +7: iteration 34300/ 37905 | consumed samples: 8780800 | consumed tokens: 17983078400 | elapsed time per iteration (s): 0.23 | learning rate: 2.407E-05 | global batch size: 256 | lm loss: 3.345123E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.492 | TFLOPs: 28.52 | +7: iteration 34310/ 37905 | consumed samples: 8783360 | consumed tokens: 17988321280 | elapsed time per iteration (s): 0.23 | learning rate: 2.405E-05 | global batch size: 256 | lm loss: 3.299072E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.390 | TFLOPs: 28.41 | +7: iteration 34320/ 37905 | consumed samples: 8785920 | consumed tokens: 17993564160 | elapsed time per iteration (s): 0.23 | learning rate: 2.402E-05 | global batch size: 256 | lm loss: 3.310138E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.115 | TFLOPs: 28.15 | +7: iteration 34330/ 37905 | consumed samples: 8788480 | consumed tokens: 17998807040 | elapsed time per iteration (s): 0.25 | learning rate: 2.400E-05 | global batch size: 256 | lm loss: 3.305988E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1016.005 | TFLOPs: 25.88 | +7: iteration 34340/ 37905 | consumed samples: 8791040 | consumed tokens: 18004049920 | elapsed time per iteration (s): 0.23 | learning rate: 2.398E-05 | global batch size: 256 | lm loss: 3.329652E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.755 | TFLOPs: 28.12 | +7: iteration 34350/ 37905 | consumed samples: 8793600 | consumed tokens: 18009292800 | elapsed time per iteration (s): 0.23 | learning rate: 2.396E-05 | global batch size: 256 | lm loss: 3.305299E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.068 | TFLOPs: 28.38 | +7: iteration 34360/ 37905 | consumed samples: 8796160 | consumed tokens: 18014535680 | elapsed time per iteration (s): 0.23 | learning rate: 2.393E-05 | global batch size: 256 | lm loss: 3.331075E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.177 | TFLOPs: 27.90 | +7: iteration 34370/ 37905 | consumed samples: 8798720 | consumed tokens: 18019778560 | elapsed time per iteration (s): 0.23 | learning rate: 2.391E-05 | global batch size: 256 | lm loss: 3.312388E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.010 | TFLOPs: 28.71 | +7: iteration 34380/ 37905 | consumed samples: 8801280 | consumed tokens: 18025021440 | elapsed time per iteration (s): 0.23 | learning rate: 2.389E-05 | global batch size: 256 | lm loss: 3.336680E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.839 | TFLOPs: 28.25 | +7: iteration 34390/ 37905 | consumed samples: 8803840 | consumed tokens: 18030264320 | elapsed time per iteration (s): 0.23 | learning rate: 2.387E-05 | global batch size: 256 | lm loss: 3.302517E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.791 | TFLOPs: 28.27 | +7: iteration 34400/ 37905 | consumed samples: 8806400 | consumed tokens: 18035507200 | elapsed time per iteration (s): 0.23 | learning rate: 2.385E-05 | global batch size: 256 | lm loss: 3.293869E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.847 | TFLOPs: 28.63 | +7: iteration 34410/ 37905 | consumed samples: 8808960 | consumed tokens: 18040750080 | elapsed time per iteration (s): 0.23 | learning rate: 2.383E-05 | global batch size: 256 | lm loss: 3.305869E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.423 | TFLOPs: 28.01 | +7: iteration 34420/ 37905 | consumed samples: 8811520 | consumed tokens: 18045992960 | elapsed time per iteration (s): 0.23 | learning rate: 2.380E-05 | global batch size: 256 | lm loss: 3.322921E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.400 | TFLOPs: 28.59 | +7: iteration 34430/ 37905 | consumed samples: 8814080 | consumed tokens: 18051235840 | elapsed time per iteration (s): 0.23 | learning rate: 2.378E-05 | global batch size: 256 | lm loss: 3.301653E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.901 | TFLOPs: 28.22 | +7: iteration 34440/ 37905 | consumed samples: 8816640 | consumed tokens: 18056478720 | elapsed time per iteration (s): 0.23 | learning rate: 2.376E-05 | global batch size: 256 | lm loss: 3.306673E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.919 | TFLOPs: 28.20 | +7: iteration 34450/ 37905 | consumed samples: 8819200 | consumed tokens: 18061721600 | elapsed time per iteration (s): 0.23 | learning rate: 2.374E-05 | global batch size: 256 | lm loss: 3.320583E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.630 | TFLOPs: 28.29 | +7: iteration 34460/ 37905 | consumed samples: 8821760 | consumed tokens: 18066964480 | elapsed time per iteration (s): 0.23 | learning rate: 2.372E-05 | global batch size: 256 | lm loss: 3.328994E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.852 | TFLOPs: 28.35 | +7: iteration 34470/ 37905 | consumed samples: 8824320 | consumed tokens: 18072207360 | elapsed time per iteration (s): 0.23 | learning rate: 2.370E-05 | global batch size: 256 | lm loss: 3.327921E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.133 | TFLOPs: 27.92 | +7: iteration 34480/ 37905 | consumed samples: 8826880 | consumed tokens: 18077450240 | elapsed time per iteration (s): 0.23 | learning rate: 2.367E-05 | global batch size: 256 | lm loss: 3.304723E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.035 | TFLOPs: 28.41 | +7: iteration 34490/ 37905 | consumed samples: 8829440 | consumed tokens: 18082693120 | elapsed time per iteration (s): 0.23 | learning rate: 2.365E-05 | global batch size: 256 | lm loss: 3.312400E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.185 | TFLOPs: 28.18 | +7: iteration 34500/ 37905 | consumed samples: 8832000 | consumed tokens: 18087936000 | elapsed time per iteration (s): 0.23 | learning rate: 2.363E-05 | global batch size: 256 | lm loss: 3.331688E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.262 | TFLOPs: 28.00 | +7: iteration 34510/ 37905 | consumed samples: 8834560 | consumed tokens: 18093178880 | elapsed time per iteration (s): 0.23 | learning rate: 2.361E-05 | global batch size: 256 | lm loss: 3.325074E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.278 | TFLOPs: 27.93 | +7: iteration 34520/ 37905 | consumed samples: 8837120 | consumed tokens: 18098421760 | elapsed time per iteration (s): 0.23 | learning rate: 2.359E-05 | global batch size: 256 | lm loss: 3.292387E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.062 | TFLOPs: 28.33 | +7: iteration 34530/ 37905 | consumed samples: 8839680 | consumed tokens: 18103664640 | elapsed time per iteration (s): 0.23 | learning rate: 2.357E-05 | global batch size: 256 | lm loss: 3.322094E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.886 | TFLOPs: 28.22 | +7: iteration 34540/ 37905 | consumed samples: 8842240 | consumed tokens: 18108907520 | elapsed time per iteration (s): 0.24 | learning rate: 2.355E-05 | global batch size: 256 | lm loss: 3.317301E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1079.437 | TFLOPs: 27.50 | +7: iteration 34550/ 37905 | consumed samples: 8844800 | consumed tokens: 18114150400 | elapsed time per iteration (s): 0.23 | learning rate: 2.353E-05 | global batch size: 256 | lm loss: 3.337679E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.565 | TFLOPs: 28.44 | +7: iteration 34560/ 37905 | consumed samples: 8847360 | consumed tokens: 18119393280 | elapsed time per iteration (s): 0.23 | learning rate: 2.351E-05 | global batch size: 256 | lm loss: 3.334283E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.942 | TFLOPs: 28.07 | +7: iteration 34570/ 37905 | consumed samples: 8849920 | consumed tokens: 18124636160 | elapsed time per iteration (s): 0.23 | learning rate: 2.349E-05 | global batch size: 256 | lm loss: 3.317641E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.340 | TFLOPs: 28.52 | +7: iteration 34580/ 37905 | consumed samples: 8852480 | consumed tokens: 18129879040 | elapsed time per iteration (s): 0.23 | learning rate: 2.346E-05 | global batch size: 256 | lm loss: 3.298739E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.832 | TFLOPs: 27.79 | +7: iteration 34590/ 37905 | consumed samples: 8855040 | consumed tokens: 18135121920 | elapsed time per iteration (s): 0.23 | learning rate: 2.344E-05 | global batch size: 256 | lm loss: 3.314742E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.276 | TFLOPs: 28.11 | +7: iteration 34600/ 37905 | consumed samples: 8857600 | consumed tokens: 18140364800 | elapsed time per iteration (s): 0.23 | learning rate: 2.342E-05 | global batch size: 256 | lm loss: 3.326299E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.935 | TFLOPs: 27.94 | +7: iteration 34610/ 37905 | consumed samples: 8860160 | consumed tokens: 18145607680 | elapsed time per iteration (s): 0.23 | learning rate: 2.340E-05 | global batch size: 256 | lm loss: 3.296301E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.186 | TFLOPs: 28.05 | +7: iteration 34620/ 37905 | consumed samples: 8862720 | consumed tokens: 18150850560 | elapsed time per iteration (s): 0.25 | learning rate: 2.338E-05 | global batch size: 256 | lm loss: 3.342636E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1023.983 | TFLOPs: 26.09 | +7: iteration 34630/ 37905 | consumed samples: 8865280 | consumed tokens: 18156093440 | elapsed time per iteration (s): 0.24 | learning rate: 2.336E-05 | global batch size: 256 | lm loss: 3.317578E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1053.553 | TFLOPs: 26.84 | +7: iteration 34640/ 37905 | consumed samples: 8867840 | consumed tokens: 18161336320 | elapsed time per iteration (s): 0.23 | learning rate: 2.334E-05 | global batch size: 256 | lm loss: 3.304780E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.020 | TFLOPs: 28.51 | +7: iteration 34650/ 37905 | consumed samples: 8870400 | consumed tokens: 18166579200 | elapsed time per iteration (s): 0.23 | learning rate: 2.332E-05 | global batch size: 256 | lm loss: 3.331859E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.661 | TFLOPs: 28.17 | +7: iteration 34660/ 37905 | consumed samples: 8872960 | consumed tokens: 18171822080 | elapsed time per iteration (s): 0.23 | learning rate: 2.330E-05 | global batch size: 256 | lm loss: 3.330795E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.659 | TFLOPs: 28.68 | +7: iteration 34670/ 37905 | consumed samples: 8875520 | consumed tokens: 18177064960 | elapsed time per iteration (s): 0.23 | learning rate: 2.328E-05 | global batch size: 256 | lm loss: 3.302299E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.650 | TFLOPs: 28.70 | +7: iteration 34680/ 37905 | consumed samples: 8878080 | consumed tokens: 18182307840 | elapsed time per iteration (s): 0.23 | learning rate: 2.326E-05 | global batch size: 256 | lm loss: 3.345821E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.904 | TFLOPs: 28.71 | +7: iteration 34690/ 37905 | consumed samples: 8880640 | consumed tokens: 18187550720 | elapsed time per iteration (s): 0.23 | learning rate: 2.324E-05 | global batch size: 256 | lm loss: 3.337036E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.117 | TFLOPs: 28.66 | +7: iteration 34700/ 37905 | consumed samples: 8883200 | consumed tokens: 18192793600 | elapsed time per iteration (s): 0.23 | learning rate: 2.322E-05 | global batch size: 256 | lm loss: 3.298678E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.857 | TFLOPs: 28.60 | +7: iteration 34710/ 37905 | consumed samples: 8885760 | consumed tokens: 18198036480 | elapsed time per iteration (s): 0.23 | learning rate: 2.320E-05 | global batch size: 256 | lm loss: 3.321925E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.582 | TFLOPs: 28.57 | +7: iteration 34720/ 37905 | consumed samples: 8888320 | consumed tokens: 18203279360 | elapsed time per iteration (s): 0.23 | learning rate: 2.318E-05 | global batch size: 256 | lm loss: 3.329222E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.700 | TFLOPs: 28.35 | +7: iteration 34730/ 37905 | consumed samples: 8890880 | consumed tokens: 18208522240 | elapsed time per iteration (s): 0.23 | learning rate: 2.316E-05 | global batch size: 256 | lm loss: 3.318689E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.011 | TFLOPs: 28.46 | +7: iteration 34740/ 37905 | consumed samples: 8893440 | consumed tokens: 18213765120 | elapsed time per iteration (s): 0.23 | learning rate: 2.314E-05 | global batch size: 256 | lm loss: 3.282349E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.322 | TFLOPs: 28.16 | +7: iteration 34750/ 37905 | consumed samples: 8896000 | consumed tokens: 18219008000 | elapsed time per iteration (s): 0.23 | learning rate: 2.312E-05 | global batch size: 256 | lm loss: 3.324129E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.015 | TFLOPs: 28.20 | +7: iteration 34760/ 37905 | consumed samples: 8898560 | consumed tokens: 18224250880 | elapsed time per iteration (s): 0.23 | learning rate: 2.310E-05 | global batch size: 256 | lm loss: 3.316588E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.852 | TFLOPs: 28.60 | +7: iteration 34770/ 37905 | consumed samples: 8901120 | consumed tokens: 18229493760 | elapsed time per iteration (s): 0.23 | learning rate: 2.308E-05 | global batch size: 256 | lm loss: 3.288440E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.145 | TFLOPs: 28.23 | +7: iteration 34780/ 37905 | consumed samples: 8903680 | consumed tokens: 18234736640 | elapsed time per iteration (s): 0.23 | learning rate: 2.306E-05 | global batch size: 256 | lm loss: 3.295071E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.418 | TFLOPs: 28.59 | +7: iteration 34790/ 37905 | consumed samples: 8906240 | consumed tokens: 18239979520 | elapsed time per iteration (s): 0.23 | learning rate: 2.304E-05 | global batch size: 256 | lm loss: 3.317479E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.503 | TFLOPs: 28.19 | +7: iteration 34800/ 37905 | consumed samples: 8908800 | consumed tokens: 18245222400 | elapsed time per iteration (s): 0.23 | learning rate: 2.302E-05 | global batch size: 256 | lm loss: 3.313239E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.543 | TFLOPs: 28.39 | +7: iteration 34810/ 37905 | consumed samples: 8911360 | consumed tokens: 18250465280 | elapsed time per iteration (s): 0.23 | learning rate: 2.300E-05 | global batch size: 256 | lm loss: 3.327244E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.497 | TFLOPs: 28.57 | +7: iteration 34820/ 37905 | consumed samples: 8913920 | consumed tokens: 18255708160 | elapsed time per iteration (s): 0.25 | learning rate: 2.299E-05 | global batch size: 256 | lm loss: 3.302140E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1009.074 | TFLOPs: 25.71 | +7: iteration 34830/ 37905 | consumed samples: 8916480 | consumed tokens: 18260951040 | elapsed time per iteration (s): 0.27 | learning rate: 2.297E-05 | global batch size: 256 | lm loss: 3.317984E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 962.358 | TFLOPs: 24.52 | +7: iteration 34840/ 37905 | consumed samples: 8919040 | consumed tokens: 18266193920 | elapsed time per iteration (s): 0.27 | learning rate: 2.295E-05 | global batch size: 256 | lm loss: 3.347329E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 964.007 | TFLOPs: 24.56 | +7: iteration 34850/ 37905 | consumed samples: 8921600 | consumed tokens: 18271436800 | elapsed time per iteration (s): 0.26 | learning rate: 2.293E-05 | global batch size: 256 | lm loss: 3.320834E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 968.940 | TFLOPs: 24.68 | +7: iteration 34860/ 37905 | consumed samples: 8924160 | consumed tokens: 18276679680 | elapsed time per iteration (s): 0.23 | learning rate: 2.291E-05 | global batch size: 256 | lm loss: 3.324150E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.613 | TFLOPs: 28.34 | +7: iteration 34870/ 37905 | consumed samples: 8926720 | consumed tokens: 18281922560 | elapsed time per iteration (s): 0.24 | learning rate: 2.289E-05 | global batch size: 256 | lm loss: 3.324700E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1066.453 | TFLOPs: 27.17 | +7: iteration 34880/ 37905 | consumed samples: 8929280 | consumed tokens: 18287165440 | elapsed time per iteration (s): 0.23 | learning rate: 2.287E-05 | global batch size: 256 | lm loss: 3.333183E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.757 | TFLOPs: 27.89 | +7: iteration 34890/ 37905 | consumed samples: 8931840 | consumed tokens: 18292408320 | elapsed time per iteration (s): 0.23 | learning rate: 2.285E-05 | global batch size: 256 | lm loss: 3.331599E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.720 | TFLOPs: 28.55 | +7: iteration 34900/ 37905 | consumed samples: 8934400 | consumed tokens: 18297651200 | elapsed time per iteration (s): 0.23 | learning rate: 2.283E-05 | global batch size: 256 | lm loss: 3.320269E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.435 | TFLOPs: 28.65 | +7: iteration 34910/ 37905 | consumed samples: 8936960 | consumed tokens: 18302894080 | elapsed time per iteration (s): 0.23 | learning rate: 2.281E-05 | global batch size: 256 | lm loss: 3.330699E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.596 | TFLOPs: 28.34 | +7: iteration 34920/ 37905 | consumed samples: 8939520 | consumed tokens: 18308136960 | elapsed time per iteration (s): 0.23 | learning rate: 2.280E-05 | global batch size: 256 | lm loss: 3.290813E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.375 | TFLOPs: 28.36 | +7: iteration 34930/ 37905 | consumed samples: 8942080 | consumed tokens: 18313379840 | elapsed time per iteration (s): 0.23 | learning rate: 2.278E-05 | global batch size: 256 | lm loss: 3.319281E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.702 | TFLOPs: 28.35 | +7: iteration 34940/ 37905 | consumed samples: 8944640 | consumed tokens: 18318622720 | elapsed time per iteration (s): 0.23 | learning rate: 2.276E-05 | global batch size: 256 | lm loss: 3.286132E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.999 | TFLOPs: 28.58 | +7: iteration 34950/ 37905 | consumed samples: 8947200 | consumed tokens: 18323865600 | elapsed time per iteration (s): 0.23 | learning rate: 2.274E-05 | global batch size: 256 | lm loss: 3.320591E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.287 | TFLOPs: 28.54 | +7: iteration 34960/ 37905 | consumed samples: 8949760 | consumed tokens: 18329108480 | elapsed time per iteration (s): 0.23 | learning rate: 2.272E-05 | global batch size: 256 | lm loss: 3.285385E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.862 | TFLOPs: 28.25 | +7: iteration 34970/ 37905 | consumed samples: 8952320 | consumed tokens: 18334351360 | elapsed time per iteration (s): 0.23 | learning rate: 2.270E-05 | global batch size: 256 | lm loss: 3.319587E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.708 | TFLOPs: 28.45 | +7: iteration 34980/ 37905 | consumed samples: 8954880 | consumed tokens: 18339594240 | elapsed time per iteration (s): 0.24 | learning rate: 2.269E-05 | global batch size: 256 | lm loss: 3.330046E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1083.292 | TFLOPs: 27.60 | +7: iteration 34990/ 37905 | consumed samples: 8957440 | consumed tokens: 18344837120 | elapsed time per iteration (s): 0.23 | learning rate: 2.267E-05 | global batch size: 256 | lm loss: 3.311018E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.215 | TFLOPs: 28.46 | +7: iteration 35000/ 37905 | consumed samples: 8960000 | consumed tokens: 18350080000 | elapsed time per iteration (s): 0.23 | learning rate: 2.265E-05 | global batch size: 256 | lm loss: 3.314605E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.823 | TFLOPs: 28.12 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 35000 | lm loss value: 3.134352E+00 | lm loss PPL: 2.297375E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 35000 to checkpoints_83moscar +0: [2022-11-29 19:13:49,030] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step35000 is begin to save! +0: [2022-11-29 19:13:49,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/layer_01-model_00-model_states.pt... +0: [2022-11-29 19:13:49,122] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/layer_01-model_00-model_states.pt. +0: [2022-11-29 19:13:49,123] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/layer_03-model_00-model_states.pt... +0: [2022-11-29 19:13:49,136] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/layer_03-model_00-model_states.pt. +0: [2022-11-29 19:13:49,136] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/layer_04-model_00-model_states.pt... +0: [2022-11-29 19:13:49,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/layer_04-model_00-model_states.pt. +0: [2022-11-29 19:13:49,148] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/layer_05-model_00-model_states.pt... +0: [2022-11-29 19:13:49,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/layer_05-model_00-model_states.pt. +0: [2022-11-29 19:13:49,160] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/layer_06-model_00-model_states.pt... +0: [2022-11-29 19:13:49,171] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/layer_06-model_00-model_states.pt. +0: [2022-11-29 19:13:49,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/layer_07-model_00-model_states.pt... +0: [2022-11-29 19:13:49,183] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/layer_07-model_00-model_states.pt. +0: [2022-11-29 19:13:49,183] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/layer_08-model_00-model_states.pt... +0: [2022-11-29 19:13:49,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/layer_08-model_00-model_states.pt. +0: [2022-11-29 19:13:49,195] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/layer_09-model_00-model_states.pt... +0: [2022-11-29 19:13:49,206] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/layer_09-model_00-model_states.pt. +0: [2022-11-29 19:13:49,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/layer_10-model_00-model_states.pt... +0: [2022-11-29 19:13:49,218] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/layer_10-model_00-model_states.pt. +0: [2022-11-29 19:13:49,218] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/layer_11-model_00-model_states.pt... +0: [2022-11-29 19:13:49,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/layer_11-model_00-model_states.pt. +0: [2022-11-29 19:13:49,230] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/layer_12-model_00-model_states.pt... +0: [2022-11-29 19:13:49,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/layer_12-model_00-model_states.pt. +0: [2022-11-29 19:13:49,241] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/layer_14-model_00-model_states.pt... +0: [2022-11-29 19:13:49,242] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/layer_14-model_00-model_states.pt. +0: [2022-11-29 19:13:49,243] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step35000/mp_rank_00_model_states.pt +0: [2022-11-29 19:13:49,243] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/mp_rank_00_model_states.pt... +0: [2022-11-29 19:13:49,245] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/mp_rank_00_model_states.pt. +0: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:13:49,261] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:13:49,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:13:49,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:13:49,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 19:13:49,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +5: [2022-11-29 19:13:49,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:13:49,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 19:13:49,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +0: [2022-11-29 19:13:49,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:13:49,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:13:49,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:13:49,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +4: [2022-11-29 19:13:49,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +3: [2022-11-29 19:13:49,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +4: [2022-11-29 19:13:49,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +3: [2022-11-29 19:13:49,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:13:49,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 19:13:49,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +7: [2022-11-29 19:13:49,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:13:49,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 19:13:49,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +5: [2022-11-29 19:13:49,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:13:49,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 19:13:49,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +5: [2022-11-29 19:13:49,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:13:49,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 19:13:49,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +0: [2022-11-29 19:13:49,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 19:13:49,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +4: [2022-11-29 19:13:49,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:13:49,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 19:13:49,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +0: [2022-11-29 19:13:49,284] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:13:49,284] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +7: [2022-11-29 19:13:49,284] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:13:49,284] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +0: [2022-11-29 19:13:49,284] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +7: [2022-11-29 19:13:49,284] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +4: [2022-11-29 19:13:49,284] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:13:49,284] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 19:13:49,284] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +3: [2022-11-29 19:13:49,284] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:13:49,284] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +0: [2022-11-29 19:13:49,284] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:13:49,285] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +0: [2022-11-29 19:13:49,285] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 19:13:49,285] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +5: [2022-11-29 19:13:49,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:13:49,285] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 19:13:49,285] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +2: [2022-11-29 19:13:49,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:13:49,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:13:49,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:13:49,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:13:49,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:13:49,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +2: [2022-11-29 19:13:49,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 19:13:49,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 19:13:49,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 19:13:49,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +7: [2022-11-29 19:13:49,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +2: [2022-11-29 19:13:49,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +2: [2022-11-29 19:13:49,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +2: [2022-11-29 19:13:49,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +2: [2022-11-29 19:13:49,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +3: [2022-11-29 19:13:49,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:13:49,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 19:13:49,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +7: [2022-11-29 19:13:49,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:13:49,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:13:49,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 19:13:49,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +5: [2022-11-29 19:13:49,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 19:13:49,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +4: [2022-11-29 19:13:49,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:13:49,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:13:49,287] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +3: [2022-11-29 19:13:49,287] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +4: [2022-11-29 19:13:49,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +3: [2022-11-29 19:13:49,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +3: [2022-11-29 19:13:49,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:13:49,287] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 19:13:49,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +4: [2022-11-29 19:13:49,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:13:49,287] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +2: [2022-11-29 19:13:49,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:13:49,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +2: [2022-11-29 19:13:49,287] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 19:13:49,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +0: [2022-11-29 19:13:49,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:13:49,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 19:13:49,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +0: [2022-11-29 19:13:49,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:13:49,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 19:13:49,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +7: [2022-11-29 19:13:49,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:13:49,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 19:13:49,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +2: [2022-11-29 19:13:49,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:13:49,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +4: [2022-11-29 19:13:49,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:13:49,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +4: [2022-11-29 19:13:49,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +3: [2022-11-29 19:13:49,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:13:49,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +3: [2022-11-29 19:13:49,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 19:13:49,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +5: [2022-11-29 19:13:49,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:13:49,289] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 19:13:49,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:13:49,289] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +5: [2022-11-29 19:13:49,289] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 19:13:49,289] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +0: [2022-11-29 19:13:49,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:13:49,289] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 19:13:49,289] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +5: [2022-11-29 19:13:49,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:13:49,289] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 19:13:49,289] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +4: [2022-11-29 19:13:49,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:13:49,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 19:13:49,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +3: [2022-11-29 19:13:49,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:13:49,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 19:13:49,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +2: [2022-11-29 19:13:49,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:13:49,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +0: [2022-11-29 19:13:49,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:13:49,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:13:49,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +0: [2022-11-29 19:13:49,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +2: [2022-11-29 19:13:49,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +0: [2022-11-29 19:13:49,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +2: [2022-11-29 19:13:49,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +7: [2022-11-29 19:13:49,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:13:49,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 19:13:49,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +7: [2022-11-29 19:13:49,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:13:49,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 19:13:49,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +7: [2022-11-29 19:13:49,292] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:13:49,292] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 19:13:49,292] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +0: [2022-11-29 19:13:49,292] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:13:49,292] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 19:13:49,292] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +6: [2022-11-29 19:13:49,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:13:49,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:13:49,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:13:49,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 19:13:49,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 19:13:49,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 19:13:49,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:13:49,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +6: [2022-11-29 19:13:49,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +6: [2022-11-29 19:13:49,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +6: [2022-11-29 19:13:49,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:13:49,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 19:13:49,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +6: [2022-11-29 19:13:49,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 19:13:49,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +6: [2022-11-29 19:13:49,294] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:13:49,294] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 19:13:49,294] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +6: [2022-11-29 19:13:49,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:13:49,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 19:13:49,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +6: [2022-11-29 19:13:49,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:13:49,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 19:13:49,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +1: [2022-11-29 19:13:49,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:13:49,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:13:49,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:13:49,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:13:49,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:13:49,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:13:49,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:13:49,299] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 19:13:49,299] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 19:13:49,299] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 19:13:49,299] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 19:13:49,299] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 19:13:49,299] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 19:13:49,299] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 19:13:49,299] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +1: [2022-11-29 19:13:49,299] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +1: [2022-11-29 19:13:49,299] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +1: [2022-11-29 19:13:49,299] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +1: [2022-11-29 19:13:49,299] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +1: [2022-11-29 19:13:49,299] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +1: [2022-11-29 19:13:49,299] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +1: [2022-11-29 19:13:49,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:13:49,299] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step35000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 19:13:49,299] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +0: successfully saved checkpoint at iteration 35000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 275.12 +7: iteration 35010/ 37905 | consumed samples: 8962560 | consumed tokens: 18355322880 | elapsed time per iteration (s): 0.26 | learning rate: 2.263E-05 | global batch size: 256 | lm loss: 3.310370E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 971.706 | TFLOPs: 24.75 | +7: iteration 35020/ 37905 | consumed samples: 8965120 | consumed tokens: 18360565760 | elapsed time per iteration (s): 0.23 | learning rate: 2.261E-05 | global batch size: 256 | lm loss: 3.311533E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.700 | TFLOPs: 28.65 | +7: iteration 35030/ 37905 | consumed samples: 8967680 | consumed tokens: 18365808640 | elapsed time per iteration (s): 0.23 | learning rate: 2.259E-05 | global batch size: 256 | lm loss: 3.284215E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.851 | TFLOPs: 28.68 | +7: iteration 35040/ 37905 | consumed samples: 8970240 | consumed tokens: 18371051520 | elapsed time per iteration (s): 0.23 | learning rate: 2.258E-05 | global batch size: 256 | lm loss: 3.292463E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.420 | TFLOPs: 28.59 | +7: iteration 35050/ 37905 | consumed samples: 8972800 | consumed tokens: 18376294400 | elapsed time per iteration (s): 0.23 | learning rate: 2.256E-05 | global batch size: 256 | lm loss: 3.332081E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.175 | TFLOPs: 28.51 | +7: iteration 35060/ 37905 | consumed samples: 8975360 | consumed tokens: 18381537280 | elapsed time per iteration (s): 0.23 | learning rate: 2.254E-05 | global batch size: 256 | lm loss: 3.323066E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.499 | TFLOPs: 28.06 | +7: iteration 35070/ 37905 | consumed samples: 8977920 | consumed tokens: 18386780160 | elapsed time per iteration (s): 0.23 | learning rate: 2.252E-05 | global batch size: 256 | lm loss: 3.318110E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.453 | TFLOPs: 28.59 | +7: iteration 35080/ 37905 | consumed samples: 8980480 | consumed tokens: 18392023040 | elapsed time per iteration (s): 0.23 | learning rate: 2.251E-05 | global batch size: 256 | lm loss: 3.330336E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.143 | TFLOPs: 28.33 | +7: iteration 35090/ 37905 | consumed samples: 8983040 | consumed tokens: 18397265920 | elapsed time per iteration (s): 0.23 | learning rate: 2.249E-05 | global batch size: 256 | lm loss: 3.294437E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.002 | TFLOPs: 28.38 | +7: iteration 35100/ 37905 | consumed samples: 8985600 | consumed tokens: 18402508800 | elapsed time per iteration (s): 0.23 | learning rate: 2.247E-05 | global batch size: 256 | lm loss: 3.315468E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.551 | TFLOPs: 28.42 | +7: iteration 35110/ 37905 | consumed samples: 8988160 | consumed tokens: 18407751680 | elapsed time per iteration (s): 0.23 | learning rate: 2.245E-05 | global batch size: 256 | lm loss: 3.311299E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.048 | TFLOPs: 28.41 | +7: iteration 35120/ 37905 | consumed samples: 8990720 | consumed tokens: 18412994560 | elapsed time per iteration (s): 0.23 | learning rate: 2.244E-05 | global batch size: 256 | lm loss: 3.267738E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.002 | TFLOPs: 28.02 | +7: iteration 35130/ 37905 | consumed samples: 8993280 | consumed tokens: 18418237440 | elapsed time per iteration (s): 0.23 | learning rate: 2.242E-05 | global batch size: 256 | lm loss: 3.322466E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.019 | TFLOPs: 28.28 | +7: iteration 35140/ 37905 | consumed samples: 8995840 | consumed tokens: 18423480320 | elapsed time per iteration (s): 0.23 | learning rate: 2.240E-05 | global batch size: 256 | lm loss: 3.315680E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.704 | TFLOPs: 28.37 | +7: iteration 35150/ 37905 | consumed samples: 8998400 | consumed tokens: 18428723200 | elapsed time per iteration (s): 0.23 | learning rate: 2.238E-05 | global batch size: 256 | lm loss: 3.326498E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.533 | TFLOPs: 28.09 | +7: iteration 35160/ 37905 | consumed samples: 9000960 | consumed tokens: 18433966080 | elapsed time per iteration (s): 0.23 | learning rate: 2.237E-05 | global batch size: 256 | lm loss: 3.316989E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.861 | TFLOPs: 28.38 | +7: iteration 35170/ 37905 | consumed samples: 9003520 | consumed tokens: 18439208960 | elapsed time per iteration (s): 0.23 | learning rate: 2.235E-05 | global batch size: 256 | lm loss: 3.322285E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.944 | TFLOPs: 28.63 | +7: iteration 35180/ 37905 | consumed samples: 9006080 | consumed tokens: 18444451840 | elapsed time per iteration (s): 0.23 | learning rate: 2.233E-05 | global batch size: 256 | lm loss: 3.299078E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.988 | TFLOPs: 28.28 | +7: iteration 35190/ 37905 | consumed samples: 9008640 | consumed tokens: 18449694720 | elapsed time per iteration (s): 0.25 | learning rate: 2.231E-05 | global batch size: 256 | lm loss: 3.324535E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1036.363 | TFLOPs: 26.40 | +7: iteration 35200/ 37905 | consumed samples: 9011200 | consumed tokens: 18454937600 | elapsed time per iteration (s): 0.23 | learning rate: 2.230E-05 | global batch size: 256 | lm loss: 3.315020E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.548 | TFLOPs: 28.47 | +7: iteration 35210/ 37905 | consumed samples: 9013760 | consumed tokens: 18460180480 | elapsed time per iteration (s): 0.23 | learning rate: 2.228E-05 | global batch size: 256 | lm loss: 3.320012E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.571 | TFLOPs: 28.37 | +7: iteration 35220/ 37905 | consumed samples: 9016320 | consumed tokens: 18465423360 | elapsed time per iteration (s): 0.23 | learning rate: 2.226E-05 | global batch size: 256 | lm loss: 3.331388E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.739 | TFLOPs: 27.94 | +7: iteration 35230/ 37905 | consumed samples: 9018880 | consumed tokens: 18470666240 | elapsed time per iteration (s): 0.23 | learning rate: 2.225E-05 | global batch size: 256 | lm loss: 3.315260E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.854 | TFLOPs: 28.32 | +7: iteration 35240/ 37905 | consumed samples: 9021440 | consumed tokens: 18475909120 | elapsed time per iteration (s): 0.23 | learning rate: 2.223E-05 | global batch size: 256 | lm loss: 3.335535E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.400 | TFLOPs: 28.47 | +7: iteration 35250/ 37905 | consumed samples: 9024000 | consumed tokens: 18481152000 | elapsed time per iteration (s): 0.23 | learning rate: 2.221E-05 | global batch size: 256 | lm loss: 3.297528E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.825 | TFLOPs: 27.81 | +7: iteration 35260/ 37905 | consumed samples: 9026560 | consumed tokens: 18486394880 | elapsed time per iteration (s): 0.24 | learning rate: 2.220E-05 | global batch size: 256 | lm loss: 3.310081E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1052.083 | TFLOPs: 26.80 | +7: iteration 35270/ 37905 | consumed samples: 9029120 | consumed tokens: 18491637760 | elapsed time per iteration (s): 0.23 | learning rate: 2.218E-05 | global batch size: 256 | lm loss: 3.316091E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.746 | TFLOPs: 28.02 | +7: iteration 35280/ 37905 | consumed samples: 9031680 | consumed tokens: 18496880640 | elapsed time per iteration (s): 0.23 | learning rate: 2.216E-05 | global batch size: 256 | lm loss: 3.333471E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.893 | TFLOPs: 27.84 | +7: iteration 35290/ 37905 | consumed samples: 9034240 | consumed tokens: 18502123520 | elapsed time per iteration (s): 0.23 | learning rate: 2.215E-05 | global batch size: 256 | lm loss: 3.333294E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.257 | TFLOPs: 28.72 | +7: iteration 35300/ 37905 | consumed samples: 9036800 | consumed tokens: 18507366400 | elapsed time per iteration (s): 0.23 | learning rate: 2.213E-05 | global batch size: 256 | lm loss: 3.326507E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.782 | TFLOPs: 28.70 | +7: iteration 35310/ 37905 | consumed samples: 9039360 | consumed tokens: 18512609280 | elapsed time per iteration (s): 0.23 | learning rate: 2.212E-05 | global batch size: 256 | lm loss: 3.316959E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.577 | TFLOPs: 28.67 | +7: iteration 35320/ 37905 | consumed samples: 9041920 | consumed tokens: 18517852160 | elapsed time per iteration (s): 0.23 | learning rate: 2.210E-05 | global batch size: 256 | lm loss: 3.326911E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.700 | TFLOPs: 28.55 | +7: iteration 35330/ 37905 | consumed samples: 9044480 | consumed tokens: 18523095040 | elapsed time per iteration (s): 0.23 | learning rate: 2.208E-05 | global batch size: 256 | lm loss: 3.305356E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.121 | TFLOPs: 28.38 | +7: iteration 35340/ 37905 | consumed samples: 9047040 | consumed tokens: 18528337920 | elapsed time per iteration (s): 0.23 | learning rate: 2.207E-05 | global batch size: 256 | lm loss: 3.311502E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.269 | TFLOPs: 28.11 | +7: iteration 35350/ 37905 | consumed samples: 9049600 | consumed tokens: 18533580800 | elapsed time per iteration (s): 0.23 | learning rate: 2.205E-05 | global batch size: 256 | lm loss: 3.334799E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.001 | TFLOPs: 28.74 | +7: iteration 35360/ 37905 | consumed samples: 9052160 | consumed tokens: 18538823680 | elapsed time per iteration (s): 0.23 | learning rate: 2.204E-05 | global batch size: 256 | lm loss: 3.325035E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.503 | TFLOPs: 28.52 | +7: iteration 35370/ 37905 | consumed samples: 9054720 | consumed tokens: 18544066560 | elapsed time per iteration (s): 0.23 | learning rate: 2.202E-05 | global batch size: 256 | lm loss: 3.333948E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.170 | TFLOPs: 28.43 | +7: iteration 35380/ 37905 | consumed samples: 9057280 | consumed tokens: 18549309440 | elapsed time per iteration (s): 0.23 | learning rate: 2.200E-05 | global batch size: 256 | lm loss: 3.323848E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.899 | TFLOPs: 28.66 | +7: iteration 35390/ 37905 | consumed samples: 9059840 | consumed tokens: 18554552320 | elapsed time per iteration (s): 0.24 | learning rate: 2.199E-05 | global batch size: 256 | lm loss: 3.316403E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.288 | TFLOPs: 27.27 | +7: iteration 35400/ 37905 | consumed samples: 9062400 | consumed tokens: 18559795200 | elapsed time per iteration (s): 0.23 | learning rate: 2.197E-05 | global batch size: 256 | lm loss: 3.322425E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.302 | TFLOPs: 28.64 | +7: iteration 35410/ 37905 | consumed samples: 9064960 | consumed tokens: 18565038080 | elapsed time per iteration (s): 0.23 | learning rate: 2.196E-05 | global batch size: 256 | lm loss: 3.307056E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.667 | TFLOPs: 28.45 | +7: iteration 35420/ 37905 | consumed samples: 9067520 | consumed tokens: 18570280960 | elapsed time per iteration (s): 0.23 | learning rate: 2.194E-05 | global batch size: 256 | lm loss: 3.311152E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.539 | TFLOPs: 28.21 | +7: iteration 35430/ 37905 | consumed samples: 9070080 | consumed tokens: 18575523840 | elapsed time per iteration (s): 0.23 | learning rate: 2.193E-05 | global batch size: 256 | lm loss: 3.295422E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.183 | TFLOPs: 28.61 | +7: iteration 35440/ 37905 | consumed samples: 9072640 | consumed tokens: 18580766720 | elapsed time per iteration (s): 0.24 | learning rate: 2.191E-05 | global batch size: 256 | lm loss: 3.316499E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1046.018 | TFLOPs: 26.65 | +7: iteration 35450/ 37905 | consumed samples: 9075200 | consumed tokens: 18586009600 | elapsed time per iteration (s): 0.23 | learning rate: 2.189E-05 | global batch size: 256 | lm loss: 3.331310E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.678 | TFLOPs: 28.70 | +7: iteration 35460/ 37905 | consumed samples: 9077760 | consumed tokens: 18591252480 | elapsed time per iteration (s): 0.23 | learning rate: 2.188E-05 | global batch size: 256 | lm loss: 3.301360E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.629 | TFLOPs: 27.76 | +7: iteration 35470/ 37905 | consumed samples: 9080320 | consumed tokens: 18596495360 | elapsed time per iteration (s): 0.23 | learning rate: 2.186E-05 | global batch size: 256 | lm loss: 3.346357E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.684 | TFLOPs: 28.47 | +7: iteration 35480/ 37905 | consumed samples: 9082880 | consumed tokens: 18601738240 | elapsed time per iteration (s): 0.23 | learning rate: 2.185E-05 | global batch size: 256 | lm loss: 3.309830E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.075 | TFLOPs: 28.51 | +7: iteration 35490/ 37905 | consumed samples: 9085440 | consumed tokens: 18606981120 | elapsed time per iteration (s): 0.23 | learning rate: 2.183E-05 | global batch size: 256 | lm loss: 3.319663E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.903 | TFLOPs: 28.17 | +7: iteration 35500/ 37905 | consumed samples: 9088000 | consumed tokens: 18612224000 | elapsed time per iteration (s): 0.23 | learning rate: 2.182E-05 | global batch size: 256 | lm loss: 3.328983E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.398 | TFLOPs: 28.41 | +7: iteration 35510/ 37905 | consumed samples: 9090560 | consumed tokens: 18617466880 | elapsed time per iteration (s): 0.23 | learning rate: 2.180E-05 | global batch size: 256 | lm loss: 3.323039E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.515 | TFLOPs: 28.34 | +7: iteration 35520/ 37905 | consumed samples: 9093120 | consumed tokens: 18622709760 | elapsed time per iteration (s): 0.25 | learning rate: 2.179E-05 | global batch size: 256 | lm loss: 3.308315E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1039.202 | TFLOPs: 26.47 | +7: iteration 35530/ 37905 | consumed samples: 9095680 | consumed tokens: 18627952640 | elapsed time per iteration (s): 0.23 | learning rate: 2.177E-05 | global batch size: 256 | lm loss: 3.325485E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.134 | TFLOPs: 28.64 | +7: iteration 35540/ 37905 | consumed samples: 9098240 | consumed tokens: 18633195520 | elapsed time per iteration (s): 0.23 | learning rate: 2.176E-05 | global batch size: 256 | lm loss: 3.331108E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.655 | TFLOPs: 28.27 | +7: iteration 35550/ 37905 | consumed samples: 9100800 | consumed tokens: 18638438400 | elapsed time per iteration (s): 0.23 | learning rate: 2.174E-05 | global batch size: 256 | lm loss: 3.320255E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.333 | TFLOPs: 28.13 | +7: iteration 35560/ 37905 | consumed samples: 9103360 | consumed tokens: 18643681280 | elapsed time per iteration (s): 0.23 | learning rate: 2.173E-05 | global batch size: 256 | lm loss: 3.299638E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.307 | TFLOPs: 28.31 | +7: iteration 35570/ 37905 | consumed samples: 9105920 | consumed tokens: 18648924160 | elapsed time per iteration (s): 0.23 | learning rate: 2.171E-05 | global batch size: 256 | lm loss: 3.314583E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.357 | TFLOPs: 28.75 | +7: iteration 35580/ 37905 | consumed samples: 9108480 | consumed tokens: 18654167040 | elapsed time per iteration (s): 0.23 | learning rate: 2.170E-05 | global batch size: 256 | lm loss: 3.288707E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.999 | TFLOPs: 28.51 | +7: iteration 35590/ 37905 | consumed samples: 9111040 | consumed tokens: 18659409920 | elapsed time per iteration (s): 0.23 | learning rate: 2.169E-05 | global batch size: 256 | lm loss: 3.335413E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.037 | TFLOPs: 28.43 | +7: iteration 35600/ 37905 | consumed samples: 9113600 | consumed tokens: 18664652800 | elapsed time per iteration (s): 0.23 | learning rate: 2.167E-05 | global batch size: 256 | lm loss: 3.327851E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.874 | TFLOPs: 28.22 | +7: iteration 35610/ 37905 | consumed samples: 9116160 | consumed tokens: 18669895680 | elapsed time per iteration (s): 0.23 | learning rate: 2.166E-05 | global batch size: 256 | lm loss: 3.290717E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.712 | TFLOPs: 28.70 | +7: iteration 35620/ 37905 | consumed samples: 9118720 | consumed tokens: 18675138560 | elapsed time per iteration (s): 0.23 | learning rate: 2.164E-05 | global batch size: 256 | lm loss: 3.302391E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.113 | TFLOPs: 27.82 | +7: iteration 35630/ 37905 | consumed samples: 9121280 | consumed tokens: 18680381440 | elapsed time per iteration (s): 0.24 | learning rate: 2.163E-05 | global batch size: 256 | lm loss: 3.356294E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.274 | TFLOPs: 26.93 | +7: iteration 35640/ 37905 | consumed samples: 9123840 | consumed tokens: 18685624320 | elapsed time per iteration (s): 0.23 | learning rate: 2.161E-05 | global batch size: 256 | lm loss: 3.325885E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.748 | TFLOPs: 28.40 | +7: iteration 35650/ 37905 | consumed samples: 9126400 | consumed tokens: 18690867200 | elapsed time per iteration (s): 0.23 | learning rate: 2.160E-05 | global batch size: 256 | lm loss: 3.323703E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.004 | TFLOPs: 28.12 | +7: iteration 35660/ 37905 | consumed samples: 9128960 | consumed tokens: 18696110080 | elapsed time per iteration (s): 0.23 | learning rate: 2.159E-05 | global batch size: 256 | lm loss: 3.317179E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.592 | TFLOPs: 28.37 | +7: iteration 35670/ 37905 | consumed samples: 9131520 | consumed tokens: 18701352960 | elapsed time per iteration (s): 0.23 | learning rate: 2.157E-05 | global batch size: 256 | lm loss: 3.304771E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.009 | TFLOPs: 28.53 | +7: iteration 35680/ 37905 | consumed samples: 9134080 | consumed tokens: 18706595840 | elapsed time per iteration (s): 0.23 | learning rate: 2.156E-05 | global batch size: 256 | lm loss: 3.325121E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.800 | TFLOPs: 27.86 | +7: iteration 35690/ 37905 | consumed samples: 9136640 | consumed tokens: 18711838720 | elapsed time per iteration (s): 0.23 | learning rate: 2.154E-05 | global batch size: 256 | lm loss: 3.324052E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.967 | TFLOPs: 28.05 | +7: iteration 35700/ 37905 | consumed samples: 9139200 | consumed tokens: 18717081600 | elapsed time per iteration (s): 0.23 | learning rate: 2.153E-05 | global batch size: 256 | lm loss: 3.316124E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.361 | TFLOPs: 28.46 | +7: iteration 35710/ 37905 | consumed samples: 9141760 | consumed tokens: 18722324480 | elapsed time per iteration (s): 0.23 | learning rate: 2.152E-05 | global batch size: 256 | lm loss: 3.317187E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.521 | TFLOPs: 27.93 | +7: iteration 35720/ 37905 | consumed samples: 9144320 | consumed tokens: 18727567360 | elapsed time per iteration (s): 0.23 | learning rate: 2.150E-05 | global batch size: 256 | lm loss: 3.310659E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.690 | TFLOPs: 28.60 | +7: iteration 35730/ 37905 | consumed samples: 9146880 | consumed tokens: 18732810240 | elapsed time per iteration (s): 0.23 | learning rate: 2.149E-05 | global batch size: 256 | lm loss: 3.327496E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.888 | TFLOPs: 28.61 | +7: iteration 35740/ 37905 | consumed samples: 9149440 | consumed tokens: 18738053120 | elapsed time per iteration (s): 0.23 | learning rate: 2.147E-05 | global batch size: 256 | lm loss: 3.315150E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.345 | TFLOPs: 28.08 | +7: iteration 35750/ 37905 | consumed samples: 9152000 | consumed tokens: 18743296000 | elapsed time per iteration (s): 0.23 | learning rate: 2.146E-05 | global batch size: 256 | lm loss: 3.297579E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.711 | TFLOPs: 28.45 | +7: iteration 35760/ 37905 | consumed samples: 9154560 | consumed tokens: 18748538880 | elapsed time per iteration (s): 0.23 | learning rate: 2.145E-05 | global batch size: 256 | lm loss: 3.297591E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.304 | TFLOPs: 28.31 | +7: iteration 35770/ 37905 | consumed samples: 9157120 | consumed tokens: 18753781760 | elapsed time per iteration (s): 0.23 | learning rate: 2.143E-05 | global batch size: 256 | lm loss: 3.292750E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.033 | TFLOPs: 28.61 | +7: iteration 35780/ 37905 | consumed samples: 9159680 | consumed tokens: 18759024640 | elapsed time per iteration (s): 0.23 | learning rate: 2.142E-05 | global batch size: 256 | lm loss: 3.300593E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.795 | TFLOPs: 28.25 | +7: iteration 35790/ 37905 | consumed samples: 9162240 | consumed tokens: 18764267520 | elapsed time per iteration (s): 0.23 | learning rate: 2.141E-05 | global batch size: 256 | lm loss: 3.313671E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.021 | TFLOPs: 28.53 | +7: iteration 35800/ 37905 | consumed samples: 9164800 | consumed tokens: 18769510400 | elapsed time per iteration (s): 0.23 | learning rate: 2.139E-05 | global batch size: 256 | lm loss: 3.331118E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.568 | TFLOPs: 28.29 | +7: iteration 35810/ 37905 | consumed samples: 9167360 | consumed tokens: 18774753280 | elapsed time per iteration (s): 0.23 | learning rate: 2.138E-05 | global batch size: 256 | lm loss: 3.319120E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.139 | TFLOPs: 28.23 | +7: iteration 35820/ 37905 | consumed samples: 9169920 | consumed tokens: 18779996160 | elapsed time per iteration (s): 0.23 | learning rate: 2.137E-05 | global batch size: 256 | lm loss: 3.305867E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.690 | TFLOPs: 28.60 | +7: iteration 35830/ 37905 | consumed samples: 9172480 | consumed tokens: 18785239040 | elapsed time per iteration (s): 0.23 | learning rate: 2.135E-05 | global batch size: 256 | lm loss: 3.309765E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.895 | TFLOPs: 28.63 | +7: iteration 35840/ 37905 | consumed samples: 9175040 | consumed tokens: 18790481920 | elapsed time per iteration (s): 0.23 | learning rate: 2.134E-05 | global batch size: 256 | lm loss: 3.324199E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.165 | TFLOPs: 28.41 | +7: iteration 35850/ 37905 | consumed samples: 9177600 | consumed tokens: 18795724800 | elapsed time per iteration (s): 0.23 | learning rate: 2.133E-05 | global batch size: 256 | lm loss: 3.317061E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.581 | TFLOPs: 28.60 | +7: iteration 35860/ 37905 | consumed samples: 9180160 | consumed tokens: 18800967680 | elapsed time per iteration (s): 0.23 | learning rate: 2.132E-05 | global batch size: 256 | lm loss: 3.309732E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.752 | TFLOPs: 28.30 | +7: iteration 35870/ 37905 | consumed samples: 9182720 | consumed tokens: 18806210560 | elapsed time per iteration (s): 0.32 | learning rate: 2.130E-05 | global batch size: 256 | lm loss: 3.312114E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 805.896 | TFLOPs: 20.53 | +7: iteration 35880/ 37905 | consumed samples: 9185280 | consumed tokens: 18811453440 | elapsed time per iteration (s): 0.26 | learning rate: 2.129E-05 | global batch size: 256 | lm loss: 3.339887E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1000.363 | TFLOPs: 25.48 | +7: iteration 35890/ 37905 | consumed samples: 9187840 | consumed tokens: 18816696320 | elapsed time per iteration (s): 0.23 | learning rate: 2.128E-05 | global batch size: 256 | lm loss: 3.316207E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.160 | TFLOPs: 28.59 | +7: iteration 35900/ 37905 | consumed samples: 9190400 | consumed tokens: 18821939200 | elapsed time per iteration (s): 0.23 | learning rate: 2.127E-05 | global batch size: 256 | lm loss: 3.328667E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.597 | TFLOPs: 28.27 | +7: iteration 35910/ 37905 | consumed samples: 9192960 | consumed tokens: 18827182080 | elapsed time per iteration (s): 0.24 | learning rate: 2.125E-05 | global batch size: 256 | lm loss: 3.307491E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1048.336 | TFLOPs: 26.71 | +7: iteration 35920/ 37905 | consumed samples: 9195520 | consumed tokens: 18832424960 | elapsed time per iteration (s): 0.25 | learning rate: 2.124E-05 | global batch size: 256 | lm loss: 3.329293E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1044.107 | TFLOPs: 26.60 | +7: iteration 35930/ 37905 | consumed samples: 9198080 | consumed tokens: 18837667840 | elapsed time per iteration (s): 0.23 | learning rate: 2.123E-05 | global batch size: 256 | lm loss: 3.286069E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.484 | TFLOPs: 28.65 | +7: iteration 35940/ 37905 | consumed samples: 9200640 | consumed tokens: 18842910720 | elapsed time per iteration (s): 0.23 | learning rate: 2.122E-05 | global batch size: 256 | lm loss: 3.321194E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.319 | TFLOPs: 28.13 | +7: iteration 35950/ 37905 | consumed samples: 9203200 | consumed tokens: 18848153600 | elapsed time per iteration (s): 0.23 | learning rate: 2.120E-05 | global batch size: 256 | lm loss: 3.315609E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.590 | TFLOPs: 28.52 | +7: iteration 35960/ 37905 | consumed samples: 9205760 | consumed tokens: 18853396480 | elapsed time per iteration (s): 0.23 | learning rate: 2.119E-05 | global batch size: 256 | lm loss: 3.301259E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.131 | TFLOPs: 28.59 | +7: iteration 35970/ 37905 | consumed samples: 9208320 | consumed tokens: 18858639360 | elapsed time per iteration (s): 0.23 | learning rate: 2.118E-05 | global batch size: 256 | lm loss: 3.293208E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.297 | TFLOPs: 28.36 | +7: iteration 35980/ 37905 | consumed samples: 9210880 | consumed tokens: 18863882240 | elapsed time per iteration (s): 0.23 | learning rate: 2.117E-05 | global batch size: 256 | lm loss: 3.287010E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.646 | TFLOPs: 28.47 | +7: iteration 35990/ 37905 | consumed samples: 9213440 | consumed tokens: 18869125120 | elapsed time per iteration (s): 0.23 | learning rate: 2.115E-05 | global batch size: 256 | lm loss: 3.336882E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.651 | TFLOPs: 28.32 | +0: [2022-11-29 19:17:41,370] [INFO] [logging.py:68:log_dist] [Rank 0] step=36000, skipped=0, lr=[2.1142230010800715e-05, 2.1142230010800715e-05, 2.1142230010800715e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 36000/ 37905 | consumed samples: 9216000 | consumed tokens: 18874368000 | elapsed time per iteration (s): 0.23 | learning rate: 2.114E-05 | global batch size: 256 | lm loss: 3.317688E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.734 | TFLOPs: 28.25 | +0: steps: 36000 loss: 3.2504 iter time (s): 0.232 samples/sec: 1104.079 +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 36000 | lm loss value: 3.161755E+00 | lm loss PPL: 2.361199E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 36000 to checkpoints_83moscar +0: [2022-11-29 19:17:41,463] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step36000 is begin to save! +0: [2022-11-29 19:17:41,467] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/layer_01-model_00-model_states.pt... +0: [2022-11-29 19:17:41,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/layer_01-model_00-model_states.pt. +0: [2022-11-29 19:17:41,549] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/layer_03-model_00-model_states.pt... +0: [2022-11-29 19:17:41,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/layer_03-model_00-model_states.pt. +0: [2022-11-29 19:17:41,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/layer_04-model_00-model_states.pt... +0: [2022-11-29 19:17:41,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/layer_04-model_00-model_states.pt. +0: [2022-11-29 19:17:41,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/layer_05-model_00-model_states.pt... +0: [2022-11-29 19:17:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/layer_05-model_00-model_states.pt. +0: [2022-11-29 19:17:41,585] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/layer_06-model_00-model_states.pt... +0: [2022-11-29 19:17:41,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/layer_06-model_00-model_states.pt. +0: [2022-11-29 19:17:41,597] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/layer_07-model_00-model_states.pt... +0: [2022-11-29 19:17:41,608] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/layer_07-model_00-model_states.pt. +0: [2022-11-29 19:17:41,609] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/layer_08-model_00-model_states.pt... +0: [2022-11-29 19:17:41,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/layer_08-model_00-model_states.pt. +0: [2022-11-29 19:17:41,620] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/layer_09-model_00-model_states.pt... +0: [2022-11-29 19:17:41,632] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/layer_09-model_00-model_states.pt. +0: [2022-11-29 19:17:41,632] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/layer_10-model_00-model_states.pt... +0: [2022-11-29 19:17:41,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/layer_10-model_00-model_states.pt. +0: [2022-11-29 19:17:41,644] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/layer_11-model_00-model_states.pt... +0: [2022-11-29 19:17:41,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/layer_11-model_00-model_states.pt. +0: [2022-11-29 19:17:41,656] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/layer_12-model_00-model_states.pt... +0: [2022-11-29 19:17:41,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/layer_12-model_00-model_states.pt. +0: [2022-11-29 19:17:41,667] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/layer_14-model_00-model_states.pt... +0: [2022-11-29 19:17:41,668] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/layer_14-model_00-model_states.pt. +0: [2022-11-29 19:17:41,669] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step36000/mp_rank_00_model_states.pt +0: [2022-11-29 19:17:41,669] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/mp_rank_00_model_states.pt... +0: [2022-11-29 19:17:41,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/mp_rank_00_model_states.pt. +0: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:17:41,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:17:41,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:17:41,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 19:17:41,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +3: [2022-11-29 19:17:41,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:17:41,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 19:17:41,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +7: [2022-11-29 19:17:41,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:17:41,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 19:17:41,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +2: [2022-11-29 19:17:41,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:17:41,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 19:17:41,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +0: [2022-11-29 19:17:41,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:17:41,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:17:41,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-29 19:17:41,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +3: [2022-11-29 19:17:41,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:17:41,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 19:17:41,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +2: [2022-11-29 19:17:41,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:17:41,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:17:41,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +1: [2022-11-29 19:17:41,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 19:17:41,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +2: [2022-11-29 19:17:41,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +6: [2022-11-29 19:17:41,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:17:41,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 19:17:41,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +0: [2022-11-29 19:17:41,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 19:17:41,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +0: [2022-11-29 19:17:41,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:17:41,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 19:17:41,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +4: [2022-11-29 19:17:41,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:17:41,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +0: [2022-11-29 19:17:41,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:17:41,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:17:41,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +2: [2022-11-29 19:17:41,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +0: [2022-11-29 19:17:41,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 19:17:41,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +2: [2022-11-29 19:17:41,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +1: [2022-11-29 19:17:41,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:17:41,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +6: [2022-11-29 19:17:41,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:17:41,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +6: [2022-11-29 19:17:41,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 19:17:41,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +7: [2022-11-29 19:17:41,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:17:41,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 19:17:41,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +7: [2022-11-29 19:17:41,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:17:41,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:17:41,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +1: [2022-11-29 19:17:41,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +7: [2022-11-29 19:17:41,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +1: [2022-11-29 19:17:41,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +0: [2022-11-29 19:17:41,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:17:41,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 19:17:41,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +4: [2022-11-29 19:17:41,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:17:41,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 19:17:41,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +1: [2022-11-29 19:17:41,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:17:41,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +3: [2022-11-29 19:17:41,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:17:41,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +3: [2022-11-29 19:17:41,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 19:17:41,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +1: [2022-11-29 19:17:41,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:17:41,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 19:17:41,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +2: [2022-11-29 19:17:41,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:17:41,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 19:17:41,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +4: [2022-11-29 19:17:41,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:17:41,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 19:17:41,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +7: [2022-11-29 19:17:41,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:17:41,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-29 19:17:41,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +0: [2022-11-29 19:17:41,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:17:41,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-29 19:17:41,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +6: [2022-11-29 19:17:41,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:17:41,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-29 19:17:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +2: [2022-11-29 19:17:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:17:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 19:17:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +1: [2022-11-29 19:17:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:17:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:17:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +6: [2022-11-29 19:17:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:17:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +1: [2022-11-29 19:17:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +6: [2022-11-29 19:17:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +3: [2022-11-29 19:17:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +6: [2022-11-29 19:17:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +7: [2022-11-29 19:17:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:17:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 19:17:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +4: [2022-11-29 19:17:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:17:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 19:17:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +6: [2022-11-29 19:17:41,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:17:41,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 19:17:41,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +4: [2022-11-29 19:17:41,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:17:41,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 19:17:41,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +3: [2022-11-29 19:17:41,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:17:41,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +2: [2022-11-29 19:17:41,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:17:41,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +2: [2022-11-29 19:17:41,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +1: [2022-11-29 19:17:41,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:17:41,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:17:41,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +1: [2022-11-29 19:17:41,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +0: [2022-11-29 19:17:41,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +1: [2022-11-29 19:17:41,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +0: [2022-11-29 19:17:41,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +4: [2022-11-29 19:17:41,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:17:41,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:17:41,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +7: [2022-11-29 19:17:41,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +4: [2022-11-29 19:17:41,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +7: [2022-11-29 19:17:41,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +0: [2022-11-29 19:17:41,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:17:41,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-29 19:17:41,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +3: [2022-11-29 19:17:41,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:17:41,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 19:17:41,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +1: [2022-11-29 19:17:41,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:17:41,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 19:17:41,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +3: [2022-11-29 19:17:41,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:17:41,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +7: [2022-11-29 19:17:41,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:17:41,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:17:41,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +7: [2022-11-29 19:17:41,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +6: [2022-11-29 19:17:41,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 19:17:41,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +7: [2022-11-29 19:17:41,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +3: [2022-11-29 19:17:41,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:17:41,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +6: [2022-11-29 19:17:41,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:17:41,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:17:41,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +6: [2022-11-29 19:17:41,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 19:17:41,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +0: [2022-11-29 19:17:41,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:17:41,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +6: [2022-11-29 19:17:41,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +0: [2022-11-29 19:17:41,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 19:17:41,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +4: [2022-11-29 19:17:41,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:17:41,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 19:17:41,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +2: [2022-11-29 19:17:41,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:17:41,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 19:17:41,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +7: [2022-11-29 19:17:41,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:17:41,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 19:17:41,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +5: [2022-11-29 19:17:41,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:17:41,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:17:41,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:17:41,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:17:41,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:17:41,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 19:17:41,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:17:41,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:17:41,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +5: [2022-11-29 19:17:41,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 19:17:41,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 19:17:41,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 19:17:41,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 19:17:41,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 19:17:41,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 19:17:41,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +5: [2022-11-29 19:17:41,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:17:41,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +5: [2022-11-29 19:17:41,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +5: [2022-11-29 19:17:41,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +5: [2022-11-29 19:17:41,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +5: [2022-11-29 19:17:41,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +5: [2022-11-29 19:17:41,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step36000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 19:17:41,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +0: successfully saved checkpoint at iteration 36000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 313.69 +7: iteration 36010/ 37905 | consumed samples: 9218560 | consumed tokens: 18879610880 | elapsed time per iteration (s): 0.27 | learning rate: 2.113E-05 | global batch size: 256 | lm loss: 3.297874E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 943.644 | TFLOPs: 24.04 | +7: iteration 36020/ 37905 | consumed samples: 9221120 | consumed tokens: 18884853760 | elapsed time per iteration (s): 0.23 | learning rate: 2.112E-05 | global batch size: 256 | lm loss: 3.318555E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.374 | TFLOPs: 28.41 | +7: iteration 36030/ 37905 | consumed samples: 9223680 | consumed tokens: 18890096640 | elapsed time per iteration (s): 0.23 | learning rate: 2.111E-05 | global batch size: 256 | lm loss: 3.289389E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.174 | TFLOPs: 28.08 | +7: iteration 36040/ 37905 | consumed samples: 9226240 | consumed tokens: 18895339520 | elapsed time per iteration (s): 0.23 | learning rate: 2.109E-05 | global batch size: 256 | lm loss: 3.319517E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.803 | TFLOPs: 28.37 | +7: iteration 36050/ 37905 | consumed samples: 9228800 | consumed tokens: 18900582400 | elapsed time per iteration (s): 0.23 | learning rate: 2.108E-05 | global batch size: 256 | lm loss: 3.334912E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.098 | TFLOPs: 27.92 | +7: iteration 36060/ 37905 | consumed samples: 9231360 | consumed tokens: 18905825280 | elapsed time per iteration (s): 0.23 | learning rate: 2.107E-05 | global batch size: 256 | lm loss: 3.287463E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.438 | TFLOPs: 28.16 | +7: iteration 36070/ 37905 | consumed samples: 9233920 | consumed tokens: 18911068160 | elapsed time per iteration (s): 0.23 | learning rate: 2.106E-05 | global batch size: 256 | lm loss: 3.307791E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.756 | TFLOPs: 28.40 | +7: iteration 36080/ 37905 | consumed samples: 9236480 | consumed tokens: 18916311040 | elapsed time per iteration (s): 0.24 | learning rate: 2.105E-05 | global batch size: 256 | lm loss: 3.307570E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.794 | TFLOPs: 27.28 | +7: iteration 36090/ 37905 | consumed samples: 9239040 | consumed tokens: 18921553920 | elapsed time per iteration (s): 0.23 | learning rate: 2.104E-05 | global batch size: 256 | lm loss: 3.323193E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.648 | TFLOPs: 28.29 | +7: iteration 36100/ 37905 | consumed samples: 9241600 | consumed tokens: 18926796800 | elapsed time per iteration (s): 0.23 | learning rate: 2.103E-05 | global batch size: 256 | lm loss: 3.325474E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.363 | TFLOPs: 28.57 | +7: iteration 36110/ 37905 | consumed samples: 9244160 | consumed tokens: 18932039680 | elapsed time per iteration (s): 0.23 | learning rate: 2.101E-05 | global batch size: 256 | lm loss: 3.298891E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.501 | TFLOPs: 28.34 | +7: iteration 36120/ 37905 | consumed samples: 9246720 | consumed tokens: 18937282560 | elapsed time per iteration (s): 0.23 | learning rate: 2.100E-05 | global batch size: 256 | lm loss: 3.315210E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.721 | TFLOPs: 28.53 | +7: iteration 36130/ 37905 | consumed samples: 9249280 | consumed tokens: 18942525440 | elapsed time per iteration (s): 0.23 | learning rate: 2.099E-05 | global batch size: 256 | lm loss: 3.329932E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.402 | TFLOPs: 28.47 | +7: iteration 36140/ 37905 | consumed samples: 9251840 | consumed tokens: 18947768320 | elapsed time per iteration (s): 0.23 | learning rate: 2.098E-05 | global batch size: 256 | lm loss: 3.281578E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.629 | TFLOPs: 27.96 | +7: iteration 36150/ 37905 | consumed samples: 9254400 | consumed tokens: 18953011200 | elapsed time per iteration (s): 0.23 | learning rate: 2.097E-05 | global batch size: 256 | lm loss: 3.309478E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.619 | TFLOPs: 28.24 | +7: iteration 36160/ 37905 | consumed samples: 9256960 | consumed tokens: 18958254080 | elapsed time per iteration (s): 0.23 | learning rate: 2.096E-05 | global batch size: 256 | lm loss: 3.326109E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.198 | TFLOPs: 28.38 | +7: iteration 36170/ 37905 | consumed samples: 9259520 | consumed tokens: 18963496960 | elapsed time per iteration (s): 0.25 | learning rate: 2.095E-05 | global batch size: 256 | lm loss: 3.280141E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1008.070 | TFLOPs: 25.68 | +7: iteration 36180/ 37905 | consumed samples: 9262080 | consumed tokens: 18968739840 | elapsed time per iteration (s): 0.23 | learning rate: 2.094E-05 | global batch size: 256 | lm loss: 3.331843E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.305 | TFLOPs: 28.44 | +7: iteration 36190/ 37905 | consumed samples: 9264640 | consumed tokens: 18973982720 | elapsed time per iteration (s): 0.23 | learning rate: 2.093E-05 | global batch size: 256 | lm loss: 3.318722E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.948 | TFLOPs: 27.82 | +7: iteration 36200/ 37905 | consumed samples: 9267200 | consumed tokens: 18979225600 | elapsed time per iteration (s): 0.23 | learning rate: 2.092E-05 | global batch size: 256 | lm loss: 3.308154E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.120 | TFLOPs: 28.10 | +7: iteration 36210/ 37905 | consumed samples: 9269760 | consumed tokens: 18984468480 | elapsed time per iteration (s): 0.23 | learning rate: 2.090E-05 | global batch size: 256 | lm loss: 3.318377E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.497 | TFLOPs: 28.14 | +7: iteration 36220/ 37905 | consumed samples: 9272320 | consumed tokens: 18989711360 | elapsed time per iteration (s): 0.23 | learning rate: 2.089E-05 | global batch size: 256 | lm loss: 3.321247E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.074 | TFLOPs: 28.48 | +7: iteration 36230/ 37905 | consumed samples: 9274880 | consumed tokens: 18994954240 | elapsed time per iteration (s): 0.23 | learning rate: 2.088E-05 | global batch size: 256 | lm loss: 3.337465E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.518 | TFLOPs: 28.11 | +7: iteration 36240/ 37905 | consumed samples: 9277440 | consumed tokens: 19000197120 | elapsed time per iteration (s): 0.23 | learning rate: 2.087E-05 | global batch size: 256 | lm loss: 3.296343E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.838 | TFLOPs: 28.60 | +7: iteration 36250/ 37905 | consumed samples: 9280000 | consumed tokens: 19005440000 | elapsed time per iteration (s): 0.24 | learning rate: 2.086E-05 | global batch size: 256 | lm loss: 3.308824E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1081.702 | TFLOPs: 27.56 | +7: iteration 36260/ 37905 | consumed samples: 9282560 | consumed tokens: 19010682880 | elapsed time per iteration (s): 0.23 | learning rate: 2.085E-05 | global batch size: 256 | lm loss: 3.315599E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.958 | TFLOPs: 28.35 | +7: iteration 36270/ 37905 | consumed samples: 9285120 | consumed tokens: 19015925760 | elapsed time per iteration (s): 0.24 | learning rate: 2.084E-05 | global batch size: 256 | lm loss: 3.304130E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1062.640 | TFLOPs: 27.07 | +7: iteration 36280/ 37905 | consumed samples: 9287680 | consumed tokens: 19021168640 | elapsed time per iteration (s): 0.23 | learning rate: 2.083E-05 | global batch size: 256 | lm loss: 3.301715E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.203 | TFLOPs: 28.00 | +7: iteration 36290/ 37905 | consumed samples: 9290240 | consumed tokens: 19026411520 | elapsed time per iteration (s): 0.23 | learning rate: 2.082E-05 | global batch size: 256 | lm loss: 3.305635E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.092 | TFLOPs: 28.66 | +7: iteration 36300/ 37905 | consumed samples: 9292800 | consumed tokens: 19031654400 | elapsed time per iteration (s): 0.23 | learning rate: 2.081E-05 | global batch size: 256 | lm loss: 3.328886E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.509 | TFLOPs: 28.60 | +7: iteration 36310/ 37905 | consumed samples: 9295360 | consumed tokens: 19036897280 | elapsed time per iteration (s): 0.23 | learning rate: 2.080E-05 | global batch size: 256 | lm loss: 3.303269E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.743 | TFLOPs: 27.94 | +7: iteration 36320/ 37905 | consumed samples: 9297920 | consumed tokens: 19042140160 | elapsed time per iteration (s): 0.23 | learning rate: 2.079E-05 | global batch size: 256 | lm loss: 3.304217E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.133 | TFLOPs: 28.36 | +7: iteration 36330/ 37905 | consumed samples: 9300480 | consumed tokens: 19047383040 | elapsed time per iteration (s): 0.23 | learning rate: 2.078E-05 | global batch size: 256 | lm loss: 3.297360E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.373 | TFLOPs: 28.36 | +7: iteration 36340/ 37905 | consumed samples: 9303040 | consumed tokens: 19052625920 | elapsed time per iteration (s): 0.23 | learning rate: 2.077E-05 | global batch size: 256 | lm loss: 3.328969E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.908 | TFLOPs: 28.17 | +7: iteration 36350/ 37905 | consumed samples: 9305600 | consumed tokens: 19057868800 | elapsed time per iteration (s): 0.23 | learning rate: 2.076E-05 | global batch size: 256 | lm loss: 3.351957E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.540 | TFLOPs: 27.91 | +7: iteration 36360/ 37905 | consumed samples: 9308160 | consumed tokens: 19063111680 | elapsed time per iteration (s): 0.23 | learning rate: 2.075E-05 | global batch size: 256 | lm loss: 3.323115E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.170 | TFLOPs: 28.41 | +7: iteration 36370/ 37905 | consumed samples: 9310720 | consumed tokens: 19068354560 | elapsed time per iteration (s): 0.23 | learning rate: 2.074E-05 | global batch size: 256 | lm loss: 3.338639E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.190 | TFLOPs: 28.28 | +7: iteration 36380/ 37905 | consumed samples: 9313280 | consumed tokens: 19073597440 | elapsed time per iteration (s): 0.23 | learning rate: 2.073E-05 | global batch size: 256 | lm loss: 3.303743E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.552 | TFLOPs: 28.39 | +7: iteration 36390/ 37905 | consumed samples: 9315840 | consumed tokens: 19078840320 | elapsed time per iteration (s): 0.23 | learning rate: 2.072E-05 | global batch size: 256 | lm loss: 3.317706E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.573 | TFLOPs: 28.19 | +7: iteration 36400/ 37905 | consumed samples: 9318400 | consumed tokens: 19084083200 | elapsed time per iteration (s): 0.23 | learning rate: 2.071E-05 | global batch size: 256 | lm loss: 3.302231E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.259 | TFLOPs: 28.44 | +7: iteration 36410/ 37905 | consumed samples: 9320960 | consumed tokens: 19089326080 | elapsed time per iteration (s): 0.23 | learning rate: 2.070E-05 | global batch size: 256 | lm loss: 3.312317E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.525 | TFLOPs: 28.32 | +7: iteration 36420/ 37905 | consumed samples: 9323520 | consumed tokens: 19094568960 | elapsed time per iteration (s): 0.23 | learning rate: 2.069E-05 | global batch size: 256 | lm loss: 3.317515E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.629 | TFLOPs: 28.37 | +7: iteration 36430/ 37905 | consumed samples: 9326080 | consumed tokens: 19099811840 | elapsed time per iteration (s): 0.23 | learning rate: 2.069E-05 | global batch size: 256 | lm loss: 3.306027E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.794 | TFLOPs: 28.65 | +7: iteration 36440/ 37905 | consumed samples: 9328640 | consumed tokens: 19105054720 | elapsed time per iteration (s): 0.23 | learning rate: 2.068E-05 | global batch size: 256 | lm loss: 3.281790E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.861 | TFLOPs: 27.92 | +7: iteration 36450/ 37905 | consumed samples: 9331200 | consumed tokens: 19110297600 | elapsed time per iteration (s): 0.23 | learning rate: 2.067E-05 | global batch size: 256 | lm loss: 3.320919E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.563 | TFLOPs: 28.44 | +7: iteration 36460/ 37905 | consumed samples: 9333760 | consumed tokens: 19115540480 | elapsed time per iteration (s): 0.23 | learning rate: 2.066E-05 | global batch size: 256 | lm loss: 3.319063E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.345 | TFLOPs: 28.36 | +7: iteration 36470/ 37905 | consumed samples: 9336320 | consumed tokens: 19120783360 | elapsed time per iteration (s): 0.23 | learning rate: 2.065E-05 | global batch size: 256 | lm loss: 3.312621E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.461 | TFLOPs: 28.21 | +7: iteration 36480/ 37905 | consumed samples: 9338880 | consumed tokens: 19126026240 | elapsed time per iteration (s): 0.25 | learning rate: 2.064E-05 | global batch size: 256 | lm loss: 3.325031E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1041.815 | TFLOPs: 26.54 | +7: iteration 36490/ 37905 | consumed samples: 9341440 | consumed tokens: 19131269120 | elapsed time per iteration (s): 0.23 | learning rate: 2.063E-05 | global batch size: 256 | lm loss: 3.306907E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.013 | TFLOPs: 28.48 | +7: iteration 36500/ 37905 | consumed samples: 9344000 | consumed tokens: 19136512000 | elapsed time per iteration (s): 0.23 | learning rate: 2.062E-05 | global batch size: 256 | lm loss: 3.331927E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.241 | TFLOPs: 28.05 | +7: iteration 36510/ 37905 | consumed samples: 9346560 | consumed tokens: 19141754880 | elapsed time per iteration (s): 0.23 | learning rate: 2.061E-05 | global batch size: 256 | lm loss: 3.328446E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.541 | TFLOPs: 28.42 | +7: iteration 36520/ 37905 | consumed samples: 9349120 | consumed tokens: 19146997760 | elapsed time per iteration (s): 0.23 | learning rate: 2.060E-05 | global batch size: 256 | lm loss: 3.324671E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.342 | TFLOPs: 27.88 | +7: iteration 36530/ 37905 | consumed samples: 9351680 | consumed tokens: 19152240640 | elapsed time per iteration (s): 0.23 | learning rate: 2.060E-05 | global batch size: 256 | lm loss: 3.280048E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.325 | TFLOPs: 28.11 | +7: iteration 36540/ 37905 | consumed samples: 9354240 | consumed tokens: 19157483520 | elapsed time per iteration (s): 0.23 | learning rate: 2.059E-05 | global batch size: 256 | lm loss: 3.326691E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.667 | TFLOPs: 28.37 | +7: iteration 36550/ 37905 | consumed samples: 9356800 | consumed tokens: 19162726400 | elapsed time per iteration (s): 0.23 | learning rate: 2.058E-05 | global batch size: 256 | lm loss: 3.304274E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.746 | TFLOPs: 28.19 | +7: iteration 36560/ 37905 | consumed samples: 9359360 | consumed tokens: 19167969280 | elapsed time per iteration (s): 0.23 | learning rate: 2.057E-05 | global batch size: 256 | lm loss: 3.299831E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.392 | TFLOPs: 28.34 | +7: iteration 36570/ 37905 | consumed samples: 9361920 | consumed tokens: 19173212160 | elapsed time per iteration (s): 0.23 | learning rate: 2.056E-05 | global batch size: 256 | lm loss: 3.325287E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.965 | TFLOPs: 28.12 | +7: iteration 36580/ 37905 | consumed samples: 9364480 | consumed tokens: 19178455040 | elapsed time per iteration (s): 0.23 | learning rate: 2.055E-05 | global batch size: 256 | lm loss: 3.321408E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.510 | TFLOPs: 27.83 | +7: iteration 36590/ 37905 | consumed samples: 9367040 | consumed tokens: 19183697920 | elapsed time per iteration (s): 0.23 | learning rate: 2.054E-05 | global batch size: 256 | lm loss: 3.299766E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.986 | TFLOPs: 27.92 | +7: iteration 36600/ 37905 | consumed samples: 9369600 | consumed tokens: 19188940800 | elapsed time per iteration (s): 0.23 | learning rate: 2.054E-05 | global batch size: 256 | lm loss: 3.334048E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.866 | TFLOPs: 28.38 | +7: iteration 36610/ 37905 | consumed samples: 9372160 | consumed tokens: 19194183680 | elapsed time per iteration (s): 0.23 | learning rate: 2.053E-05 | global batch size: 256 | lm loss: 3.330436E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.774 | TFLOPs: 28.48 | +7: iteration 36620/ 37905 | consumed samples: 9374720 | consumed tokens: 19199426560 | elapsed time per iteration (s): 0.23 | learning rate: 2.052E-05 | global batch size: 256 | lm loss: 3.304765E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.952 | TFLOPs: 28.56 | +7: iteration 36630/ 37905 | consumed samples: 9377280 | consumed tokens: 19204669440 | elapsed time per iteration (s): 0.23 | learning rate: 2.051E-05 | global batch size: 256 | lm loss: 3.274976E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.451 | TFLOPs: 28.19 | +7: iteration 36640/ 37905 | consumed samples: 9379840 | consumed tokens: 19209912320 | elapsed time per iteration (s): 0.23 | learning rate: 2.050E-05 | global batch size: 256 | lm loss: 3.320012E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.883 | TFLOPs: 28.12 | +7: iteration 36650/ 37905 | consumed samples: 9382400 | consumed tokens: 19215155200 | elapsed time per iteration (s): 0.23 | learning rate: 2.050E-05 | global batch size: 256 | lm loss: 3.310846E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.010 | TFLOPs: 28.23 | +7: iteration 36660/ 37905 | consumed samples: 9384960 | consumed tokens: 19220398080 | elapsed time per iteration (s): 0.23 | learning rate: 2.049E-05 | global batch size: 256 | lm loss: 3.339046E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.296 | TFLOPs: 28.23 | +7: iteration 36670/ 37905 | consumed samples: 9387520 | consumed tokens: 19225640960 | elapsed time per iteration (s): 0.23 | learning rate: 2.048E-05 | global batch size: 256 | lm loss: 3.298900E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.330 | TFLOPs: 28.21 | +7: iteration 36680/ 37905 | consumed samples: 9390080 | consumed tokens: 19230883840 | elapsed time per iteration (s): 0.23 | learning rate: 2.047E-05 | global batch size: 256 | lm loss: 3.332735E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.494 | TFLOPs: 28.44 | +7: iteration 36690/ 37905 | consumed samples: 9392640 | consumed tokens: 19236126720 | elapsed time per iteration (s): 0.23 | learning rate: 2.047E-05 | global batch size: 256 | lm loss: 3.336740E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.418 | TFLOPs: 28.36 | +7: iteration 36700/ 37905 | consumed samples: 9395200 | consumed tokens: 19241369600 | elapsed time per iteration (s): 0.23 | learning rate: 2.046E-05 | global batch size: 256 | lm loss: 3.338086E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.067 | TFLOPs: 28.58 | +7: iteration 36710/ 37905 | consumed samples: 9397760 | consumed tokens: 19246612480 | elapsed time per iteration (s): 0.23 | learning rate: 2.045E-05 | global batch size: 256 | lm loss: 3.328042E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.557 | TFLOPs: 28.52 | +7: iteration 36720/ 37905 | consumed samples: 9400320 | consumed tokens: 19251855360 | elapsed time per iteration (s): 0.23 | learning rate: 2.044E-05 | global batch size: 256 | lm loss: 3.323492E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.528 | TFLOPs: 28.19 | +7: iteration 36730/ 37905 | consumed samples: 9402880 | consumed tokens: 19257098240 | elapsed time per iteration (s): 0.24 | learning rate: 2.044E-05 | global batch size: 256 | lm loss: 3.331179E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1044.979 | TFLOPs: 26.62 | +7: iteration 36740/ 37905 | consumed samples: 9405440 | consumed tokens: 19262341120 | elapsed time per iteration (s): 0.23 | learning rate: 2.043E-05 | global batch size: 256 | lm loss: 3.315633E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.417 | TFLOPs: 28.62 | +7: iteration 36750/ 37905 | consumed samples: 9408000 | consumed tokens: 19267584000 | elapsed time per iteration (s): 0.23 | learning rate: 2.042E-05 | global batch size: 256 | lm loss: 3.289218E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.030 | TFLOPs: 28.41 | +7: iteration 36760/ 37905 | consumed samples: 9410560 | consumed tokens: 19272826880 | elapsed time per iteration (s): 0.23 | learning rate: 2.041E-05 | global batch size: 256 | lm loss: 3.298719E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.329 | TFLOPs: 28.08 | +7: iteration 36770/ 37905 | consumed samples: 9413120 | consumed tokens: 19278069760 | elapsed time per iteration (s): 0.23 | learning rate: 2.041E-05 | global batch size: 256 | lm loss: 3.300754E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.054 | TFLOPs: 28.36 | +7: iteration 36780/ 37905 | consumed samples: 9415680 | consumed tokens: 19283312640 | elapsed time per iteration (s): 0.23 | learning rate: 2.040E-05 | global batch size: 256 | lm loss: 3.288911E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.549 | TFLOPs: 28.60 | +7: iteration 36790/ 37905 | consumed samples: 9418240 | consumed tokens: 19288555520 | elapsed time per iteration (s): 0.23 | learning rate: 2.039E-05 | global batch size: 256 | lm loss: 3.306507E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.634 | TFLOPs: 28.34 | +7: iteration 36800/ 37905 | consumed samples: 9420800 | consumed tokens: 19293798400 | elapsed time per iteration (s): 0.23 | learning rate: 2.038E-05 | global batch size: 256 | lm loss: 3.317306E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.886 | TFLOPs: 28.55 | +7: iteration 36810/ 37905 | consumed samples: 9423360 | consumed tokens: 19299041280 | elapsed time per iteration (s): 0.23 | learning rate: 2.038E-05 | global batch size: 256 | lm loss: 3.295669E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.739 | TFLOPs: 28.22 | +7: iteration 36820/ 37905 | consumed samples: 9425920 | consumed tokens: 19304284160 | elapsed time per iteration (s): 0.25 | learning rate: 2.037E-05 | global batch size: 256 | lm loss: 3.311652E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1029.223 | TFLOPs: 26.22 | +7: iteration 36830/ 37905 | consumed samples: 9428480 | consumed tokens: 19309527040 | elapsed time per iteration (s): 0.23 | learning rate: 2.036E-05 | global batch size: 256 | lm loss: 3.352389E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.744 | TFLOPs: 28.22 | +7: iteration 36840/ 37905 | consumed samples: 9431040 | consumed tokens: 19314769920 | elapsed time per iteration (s): 0.23 | learning rate: 2.036E-05 | global batch size: 256 | lm loss: 3.342757E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.679 | TFLOPs: 28.04 | +7: iteration 36850/ 37905 | consumed samples: 9433600 | consumed tokens: 19320012800 | elapsed time per iteration (s): 0.23 | learning rate: 2.035E-05 | global batch size: 256 | lm loss: 3.315120E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.994 | TFLOPs: 28.25 | +7: iteration 36860/ 37905 | consumed samples: 9436160 | consumed tokens: 19325255680 | elapsed time per iteration (s): 0.23 | learning rate: 2.034E-05 | global batch size: 256 | lm loss: 3.311015E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.214 | TFLOPs: 28.56 | +7: iteration 36870/ 37905 | consumed samples: 9438720 | consumed tokens: 19330498560 | elapsed time per iteration (s): 0.41 | learning rate: 2.034E-05 | global batch size: 256 | lm loss: 3.317506E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 622.420 | TFLOPs: 15.86 | +7: iteration 36880/ 37905 | consumed samples: 9441280 | consumed tokens: 19335741440 | elapsed time per iteration (s): 0.23 | learning rate: 2.033E-05 | global batch size: 256 | lm loss: 3.280497E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.263 | TFLOPs: 28.23 | +7: iteration 36890/ 37905 | consumed samples: 9443840 | consumed tokens: 19340984320 | elapsed time per iteration (s): 0.23 | learning rate: 2.032E-05 | global batch size: 256 | lm loss: 3.309631E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.995 | TFLOPs: 27.84 | +7: iteration 36900/ 37905 | consumed samples: 9446400 | consumed tokens: 19346227200 | elapsed time per iteration (s): 0.23 | learning rate: 2.032E-05 | global batch size: 256 | lm loss: 3.352002E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.525 | TFLOPs: 28.57 | +7: iteration 36910/ 37905 | consumed samples: 9448960 | consumed tokens: 19351470080 | elapsed time per iteration (s): 0.24 | learning rate: 2.031E-05 | global batch size: 256 | lm loss: 3.288203E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.111 | TFLOPs: 27.64 | +7: iteration 36920/ 37905 | consumed samples: 9451520 | consumed tokens: 19356712960 | elapsed time per iteration (s): 0.23 | learning rate: 2.031E-05 | global batch size: 256 | lm loss: 3.360953E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.994 | TFLOPs: 28.43 | +7: iteration 36930/ 37905 | consumed samples: 9454080 | consumed tokens: 19361955840 | elapsed time per iteration (s): 0.23 | learning rate: 2.030E-05 | global batch size: 256 | lm loss: 3.339983E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.466 | TFLOPs: 28.11 | +7: iteration 36940/ 37905 | consumed samples: 9456640 | consumed tokens: 19367198720 | elapsed time per iteration (s): 0.23 | learning rate: 2.029E-05 | global batch size: 256 | lm loss: 3.315016E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.644 | TFLOPs: 28.68 | +7: iteration 36950/ 37905 | consumed samples: 9459200 | consumed tokens: 19372441600 | elapsed time per iteration (s): 0.23 | learning rate: 2.029E-05 | global batch size: 256 | lm loss: 3.305885E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.301 | TFLOPs: 28.29 | +7: iteration 36960/ 37905 | consumed samples: 9461760 | consumed tokens: 19377684480 | elapsed time per iteration (s): 0.23 | learning rate: 2.028E-05 | global batch size: 256 | lm loss: 3.309131E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.358 | TFLOPs: 27.93 | +7: iteration 36970/ 37905 | consumed samples: 9464320 | consumed tokens: 19382927360 | elapsed time per iteration (s): 0.23 | learning rate: 2.028E-05 | global batch size: 256 | lm loss: 3.320794E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.684 | TFLOPs: 28.32 | +7: iteration 36980/ 37905 | consumed samples: 9466880 | consumed tokens: 19388170240 | elapsed time per iteration (s): 0.23 | learning rate: 2.027E-05 | global batch size: 256 | lm loss: 3.304106E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.946 | TFLOPs: 28.25 | +7: iteration 36990/ 37905 | consumed samples: 9469440 | consumed tokens: 19393413120 | elapsed time per iteration (s): 0.23 | learning rate: 2.026E-05 | global batch size: 256 | lm loss: 3.319167E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.253 | TFLOPs: 28.33 | +7: iteration 37000/ 37905 | consumed samples: 9472000 | consumed tokens: 19398656000 | elapsed time per iteration (s): 0.23 | learning rate: 2.026E-05 | global batch size: 256 | lm loss: 3.327927E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.831 | TFLOPs: 28.09 | +7: ------------------------------------------------------------------------------------------- +7: valid loss at iteration 37000 | lm loss value: 3.191825E+00 | lm loss PPL: 2.433279E+01 | +7: ------------------------------------------------------------------------------------------- +0: saving checkpoint at iteration 37000 to checkpoints_83moscar +0: [2022-11-29 19:21:35,262] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step37000 is begin to save! +0: [2022-11-29 19:21:35,266] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/layer_01-model_00-model_states.pt... +0: [2022-11-29 19:21:35,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/layer_01-model_00-model_states.pt. +0: [2022-11-29 19:21:35,349] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/layer_03-model_00-model_states.pt... +0: [2022-11-29 19:21:35,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/layer_03-model_00-model_states.pt. +0: [2022-11-29 19:21:35,361] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/layer_04-model_00-model_states.pt... +0: [2022-11-29 19:21:35,372] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/layer_04-model_00-model_states.pt. +0: [2022-11-29 19:21:35,372] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/layer_05-model_00-model_states.pt... +0: [2022-11-29 19:21:35,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/layer_05-model_00-model_states.pt. +0: [2022-11-29 19:21:35,384] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/layer_06-model_00-model_states.pt... +0: [2022-11-29 19:21:35,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/layer_06-model_00-model_states.pt. +0: [2022-11-29 19:21:35,395] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/layer_07-model_00-model_states.pt... +0: [2022-11-29 19:21:35,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/layer_07-model_00-model_states.pt. +0: [2022-11-29 19:21:35,406] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/layer_08-model_00-model_states.pt... +0: [2022-11-29 19:21:35,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/layer_08-model_00-model_states.pt. +0: [2022-11-29 19:21:35,417] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/layer_09-model_00-model_states.pt... +0: [2022-11-29 19:21:35,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/layer_09-model_00-model_states.pt. +0: [2022-11-29 19:21:35,429] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/layer_10-model_00-model_states.pt... +0: [2022-11-29 19:21:35,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/layer_10-model_00-model_states.pt. +0: [2022-11-29 19:21:35,440] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/layer_11-model_00-model_states.pt... +0: [2022-11-29 19:21:35,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/layer_11-model_00-model_states.pt. +0: [2022-11-29 19:21:35,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/layer_12-model_00-model_states.pt... +0: [2022-11-29 19:21:35,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/layer_12-model_00-model_states.pt. +0: [2022-11-29 19:21:35,462] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/layer_14-model_00-model_states.pt... +0: [2022-11-29 19:21:35,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/layer_14-model_00-model_states.pt. +0: [2022-11-29 19:21:35,464] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step37000/mp_rank_00_model_states.pt +0: [2022-11-29 19:21:35,464] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/mp_rank_00_model_states.pt... +0: [2022-11-29 19:21:35,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/mp_rank_00_model_states.pt. +0: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:21:35,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:21:35,502] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:21:35,502] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:21:35,503] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-29 19:21:35,503] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +2: [2022-11-29 19:21:35,504] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:21:35,504] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 19:21:35,504] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +1: [2022-11-29 19:21:35,504] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:21:35,504] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +1: [2022-11-29 19:21:35,504] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 19:21:35,504] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +0: [2022-11-29 19:21:35,504] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +6: [2022-11-29 19:21:35,504] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:21:35,504] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +1: [2022-11-29 19:21:35,504] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:21:35,504] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +1: [2022-11-29 19:21:35,504] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 19:21:35,504] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +1: [2022-11-29 19:21:35,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:21:35,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 19:21:35,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +2: [2022-11-29 19:21:35,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:21:35,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 19:21:35,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +7: [2022-11-29 19:21:35,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:21:35,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 19:21:35,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +7: [2022-11-29 19:21:35,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:21:35,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 19:21:35,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +0: [2022-11-29 19:21:35,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:21:35,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 19:21:35,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +6: [2022-11-29 19:21:35,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:21:35,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:21:35,506] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 19:21:35,506] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +0: [2022-11-29 19:21:35,506] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +1: [2022-11-29 19:21:35,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:21:35,506] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +1: [2022-11-29 19:21:35,506] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 19:21:35,506] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +4: [2022-11-29 19:21:35,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:21:35,506] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 19:21:35,506] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +7: [2022-11-29 19:21:35,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:21:35,506] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +6: [2022-11-29 19:21:35,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:21:35,506] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +0: [2022-11-29 19:21:35,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:21:35,506] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 19:21:35,506] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +0: [2022-11-29 19:21:35,506] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 19:21:35,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +4: [2022-11-29 19:21:35,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:21:35,507] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-29 19:21:35,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +2: [2022-11-29 19:21:35,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:21:35,507] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 19:21:35,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +1: [2022-11-29 19:21:35,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:21:35,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:21:35,507] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +4: [2022-11-29 19:21:35,507] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +1: [2022-11-29 19:21:35,508] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +4: [2022-11-29 19:21:35,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +0: [2022-11-29 19:21:35,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:21:35,508] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-29 19:21:35,508] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +2: [2022-11-29 19:21:35,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:21:35,508] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-29 19:21:35,508] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +5: [2022-11-29 19:21:35,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:21:35,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:21:35,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:21:35,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:21:35,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:21:35,508] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 19:21:35,508] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 19:21:35,508] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +4: [2022-11-29 19:21:35,508] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +5: [2022-11-29 19:21:35,508] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 19:21:35,508] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +4: [2022-11-29 19:21:35,508] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +5: [2022-11-29 19:21:35,508] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +5: [2022-11-29 19:21:35,508] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +5: [2022-11-29 19:21:35,508] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +7: [2022-11-29 19:21:35,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:21:35,508] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 19:21:35,508] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +6: [2022-11-29 19:21:35,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:21:35,508] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-29 19:21:35,508] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +1: [2022-11-29 19:21:35,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:21:35,509] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-29 19:21:35,509] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +2: [2022-11-29 19:21:35,509] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:21:35,509] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:21:35,509] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +7: [2022-11-29 19:21:35,509] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +6: [2022-11-29 19:21:35,509] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:21:35,509] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +7: [2022-11-29 19:21:35,509] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +6: [2022-11-29 19:21:35,509] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 19:21:35,509] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +1: [2022-11-29 19:21:35,509] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:21:35,509] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 19:21:35,509] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +4: [2022-11-29 19:21:35,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:21:35,510] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 19:21:35,510] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +2: [2022-11-29 19:21:35,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:21:35,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:21:35,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:21:35,510] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +7: [2022-11-29 19:21:35,510] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +2: [2022-11-29 19:21:35,510] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +5: [2022-11-29 19:21:35,510] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +6: [2022-11-29 19:21:35,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:21:35,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:21:35,511] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +2: [2022-11-29 19:21:35,510] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +0: [2022-11-29 19:21:35,511] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +6: [2022-11-29 19:21:35,510] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +0: [2022-11-29 19:21:35,511] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +6: [2022-11-29 19:21:35,511] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +0: [2022-11-29 19:21:35,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:21:35,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:21:35,511] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +2: [2022-11-29 19:21:35,511] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +0: [2022-11-29 19:21:35,511] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +0: [2022-11-29 19:21:35,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:21:35,511] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +0: [2022-11-29 19:21:35,511] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +5: [2022-11-29 19:21:35,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:21:35,511] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +5: [2022-11-29 19:21:35,511] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 19:21:35,511] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +6: [2022-11-29 19:21:35,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:21:35,511] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 19:21:35,511] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +6: [2022-11-29 19:21:35,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:21:35,511] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-29 19:21:35,511] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +1: [2022-11-29 19:21:35,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:21:35,511] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 19:21:35,511] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +5: [2022-11-29 19:21:35,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:21:35,512] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 19:21:35,512] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +4: [2022-11-29 19:21:35,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:21:35,512] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 19:21:35,512] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +4: [2022-11-29 19:21:35,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:21:35,512] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-29 19:21:35,512] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +5: [2022-11-29 19:21:35,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:21:35,512] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 19:21:35,512] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +2: [2022-11-29 19:21:35,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:21:35,512] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 19:21:35,513] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +7: [2022-11-29 19:21:35,513] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:21:35,513] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 19:21:35,513] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +7: [2022-11-29 19:21:35,513] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:21:35,513] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 19:21:35,513] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +3: [2022-11-29 19:21:35,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:21:35,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:21:35,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:21:35,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:21:35,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:21:35,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:21:35,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 19:21:35,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:21:35,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-29 19:21:35,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 19:21:35,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-29 19:21:35,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:21:35,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 19:21:35,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 19:21:35,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +3: [2022-11-29 19:21:35,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +3: [2022-11-29 19:21:35,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 19:21:35,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +3: [2022-11-29 19:21:35,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +3: [2022-11-29 19:21:35,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +3: [2022-11-29 19:21:35,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +3: [2022-11-29 19:21:35,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 19:21:35,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +3: [2022-11-29 19:21:35,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +0: successfully saved checkpoint at iteration 37000 to checkpoints_83moscar +7: time (ms) | save-checkpoint: 375.22 +7: iteration 37010/ 37905 | consumed samples: 9474560 | consumed tokens: 19403898880 | elapsed time per iteration (s): 0.27 | learning rate: 2.025E-05 | global batch size: 256 | lm loss: 3.317694E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 933.802 | TFLOPs: 23.79 | +7: iteration 37020/ 37905 | consumed samples: 9477120 | consumed tokens: 19409141760 | elapsed time per iteration (s): 0.23 | learning rate: 2.025E-05 | global batch size: 256 | lm loss: 3.306322E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.410 | TFLOPs: 28.06 | +7: iteration 37030/ 37905 | consumed samples: 9479680 | consumed tokens: 19414384640 | elapsed time per iteration (s): 0.23 | learning rate: 2.024E-05 | global batch size: 256 | lm loss: 3.297681E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.573 | TFLOPs: 28.39 | +7: iteration 37040/ 37905 | consumed samples: 9482240 | consumed tokens: 19419627520 | elapsed time per iteration (s): 0.23 | learning rate: 2.024E-05 | global batch size: 256 | lm loss: 3.301276E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.188 | TFLOPs: 28.66 | +7: iteration 37050/ 37905 | consumed samples: 9484800 | consumed tokens: 19424870400 | elapsed time per iteration (s): 0.23 | learning rate: 2.023E-05 | global batch size: 256 | lm loss: 3.284751E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.757 | TFLOPs: 28.50 | +7: iteration 37060/ 37905 | consumed samples: 9487360 | consumed tokens: 19430113280 | elapsed time per iteration (s): 0.23 | learning rate: 2.023E-05 | global batch size: 256 | lm loss: 3.353075E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.297 | TFLOPs: 28.67 | +7: iteration 37070/ 37905 | consumed samples: 9489920 | consumed tokens: 19435356160 | elapsed time per iteration (s): 0.23 | learning rate: 2.022E-05 | global batch size: 256 | lm loss: 3.323590E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.278 | TFLOPs: 28.69 | +7: iteration 37080/ 37905 | consumed samples: 9492480 | consumed tokens: 19440599040 | elapsed time per iteration (s): 0.23 | learning rate: 2.021E-05 | global batch size: 256 | lm loss: 3.333987E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.982 | TFLOPs: 28.61 | +7: iteration 37090/ 37905 | consumed samples: 9495040 | consumed tokens: 19445841920 | elapsed time per iteration (s): 0.23 | learning rate: 2.021E-05 | global batch size: 256 | lm loss: 3.309906E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.815 | TFLOPs: 28.65 | +7: iteration 37100/ 37905 | consumed samples: 9497600 | consumed tokens: 19451084800 | elapsed time per iteration (s): 0.23 | learning rate: 2.020E-05 | global batch size: 256 | lm loss: 3.312595E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.513 | TFLOPs: 28.52 | +7: iteration 37110/ 37905 | consumed samples: 9500160 | consumed tokens: 19456327680 | elapsed time per iteration (s): 0.23 | learning rate: 2.020E-05 | global batch size: 256 | lm loss: 3.321875E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.276 | TFLOPs: 28.56 | +7: iteration 37120/ 37905 | consumed samples: 9502720 | consumed tokens: 19461570560 | elapsed time per iteration (s): 0.24 | learning rate: 2.019E-05 | global batch size: 256 | lm loss: 3.313351E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1066.895 | TFLOPs: 27.18 | +7: iteration 37130/ 37905 | consumed samples: 9505280 | consumed tokens: 19466813440 | elapsed time per iteration (s): 0.23 | learning rate: 2.019E-05 | global batch size: 256 | lm loss: 3.316013E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.302 | TFLOPs: 28.41 | +7: iteration 37140/ 37905 | consumed samples: 9507840 | consumed tokens: 19472056320 | elapsed time per iteration (s): 0.23 | learning rate: 2.018E-05 | global batch size: 256 | lm loss: 3.301710E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.362 | TFLOPs: 28.64 | +7: iteration 37150/ 37905 | consumed samples: 9510400 | consumed tokens: 19477299200 | elapsed time per iteration (s): 0.23 | learning rate: 2.018E-05 | global batch size: 256 | lm loss: 3.289926E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.733 | TFLOPs: 27.91 | +7: iteration 37160/ 37905 | consumed samples: 9512960 | consumed tokens: 19482542080 | elapsed time per iteration (s): 0.23 | learning rate: 2.018E-05 | global batch size: 256 | lm loss: 3.296976E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.459 | TFLOPs: 28.70 | +7: iteration 37170/ 37905 | consumed samples: 9515520 | consumed tokens: 19487784960 | elapsed time per iteration (s): 0.23 | learning rate: 2.017E-05 | global batch size: 256 | lm loss: 3.295255E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.750 | TFLOPs: 28.45 | +7: iteration 37180/ 37905 | consumed samples: 9518080 | consumed tokens: 19493027840 | elapsed time per iteration (s): 0.23 | learning rate: 2.017E-05 | global batch size: 256 | lm loss: 3.279175E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.546 | TFLOPs: 28.52 | +7: iteration 37190/ 37905 | consumed samples: 9520640 | consumed tokens: 19498270720 | elapsed time per iteration (s): 0.23 | learning rate: 2.016E-05 | global batch size: 256 | lm loss: 3.343323E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.910 | TFLOPs: 28.43 | +7: iteration 37200/ 37905 | consumed samples: 9523200 | consumed tokens: 19503513600 | elapsed time per iteration (s): 0.24 | learning rate: 2.016E-05 | global batch size: 256 | lm loss: 3.303493E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1051.513 | TFLOPs: 26.79 | +7: iteration 37210/ 37905 | consumed samples: 9525760 | consumed tokens: 19508756480 | elapsed time per iteration (s): 0.24 | learning rate: 2.015E-05 | global batch size: 256 | lm loss: 3.310480E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1045.680 | TFLOPs: 26.64 | +7: iteration 37220/ 37905 | consumed samples: 9528320 | consumed tokens: 19513999360 | elapsed time per iteration (s): 0.24 | learning rate: 2.015E-05 | global batch size: 256 | lm loss: 3.320643E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1080.426 | TFLOPs: 27.52 | +7: iteration 37230/ 37905 | consumed samples: 9530880 | consumed tokens: 19519242240 | elapsed time per iteration (s): 0.23 | learning rate: 2.014E-05 | global batch size: 256 | lm loss: 3.293681E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.455 | TFLOPs: 28.01 | +7: iteration 37240/ 37905 | consumed samples: 9533440 | consumed tokens: 19524485120 | elapsed time per iteration (s): 0.23 | learning rate: 2.014E-05 | global batch size: 256 | lm loss: 3.315989E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.260 | TFLOPs: 28.13 | +7: iteration 37250/ 37905 | consumed samples: 9536000 | consumed tokens: 19529728000 | elapsed time per iteration (s): 0.23 | learning rate: 2.014E-05 | global batch size: 256 | lm loss: 3.307364E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.544 | TFLOPs: 28.67 | +7: iteration 37260/ 37905 | consumed samples: 9538560 | consumed tokens: 19534970880 | elapsed time per iteration (s): 0.23 | learning rate: 2.013E-05 | global batch size: 256 | lm loss: 3.325042E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.109 | TFLOPs: 28.31 | +7: iteration 37270/ 37905 | consumed samples: 9541120 | consumed tokens: 19540213760 | elapsed time per iteration (s): 0.23 | learning rate: 2.013E-05 | global batch size: 256 | lm loss: 3.291169E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.385 | TFLOPs: 28.26 | +7: iteration 37280/ 37905 | consumed samples: 9543680 | consumed tokens: 19545456640 | elapsed time per iteration (s): 0.23 | learning rate: 2.012E-05 | global batch size: 256 | lm loss: 3.313018E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.356 | TFLOPs: 28.26 | +7: iteration 37290/ 37905 | consumed samples: 9546240 | consumed tokens: 19550699520 | elapsed time per iteration (s): 0.23 | learning rate: 2.012E-05 | global batch size: 256 | lm loss: 3.311690E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.913 | TFLOPs: 28.45 | +7: iteration 37300/ 37905 | consumed samples: 9548800 | consumed tokens: 19555942400 | elapsed time per iteration (s): 0.23 | learning rate: 2.012E-05 | global batch size: 256 | lm loss: 3.313812E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.712 | TFLOPs: 28.58 | +7: iteration 37310/ 37905 | consumed samples: 9551360 | consumed tokens: 19561185280 | elapsed time per iteration (s): 0.23 | learning rate: 2.011E-05 | global batch size: 256 | lm loss: 3.309199E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.366 | TFLOPs: 28.29 | +7: iteration 37320/ 37905 | consumed samples: 9553920 | consumed tokens: 19566428160 | elapsed time per iteration (s): 0.23 | learning rate: 2.011E-05 | global batch size: 256 | lm loss: 3.341665E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.603 | TFLOPs: 28.57 | +7: iteration 37330/ 37905 | consumed samples: 9556480 | consumed tokens: 19571671040 | elapsed time per iteration (s): 0.23 | learning rate: 2.010E-05 | global batch size: 256 | lm loss: 3.319225E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.527 | TFLOPs: 27.93 | +7: iteration 37340/ 37905 | consumed samples: 9559040 | consumed tokens: 19576913920 | elapsed time per iteration (s): 0.23 | learning rate: 2.010E-05 | global batch size: 256 | lm loss: 3.322459E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.786 | TFLOPs: 28.60 | +7: iteration 37350/ 37905 | consumed samples: 9561600 | consumed tokens: 19582156800 | elapsed time per iteration (s): 0.23 | learning rate: 2.010E-05 | global batch size: 256 | lm loss: 3.309017E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.951 | TFLOPs: 28.38 | +7: iteration 37360/ 37905 | consumed samples: 9564160 | consumed tokens: 19587399680 | elapsed time per iteration (s): 0.23 | learning rate: 2.009E-05 | global batch size: 256 | lm loss: 3.319814E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.656 | TFLOPs: 28.09 | +7: iteration 37370/ 37905 | consumed samples: 9566720 | consumed tokens: 19592642560 | elapsed time per iteration (s): 0.23 | learning rate: 2.009E-05 | global batch size: 256 | lm loss: 3.298977E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.923 | TFLOPs: 28.30 | +7: iteration 37380/ 37905 | consumed samples: 9569280 | consumed tokens: 19597885440 | elapsed time per iteration (s): 0.23 | learning rate: 2.009E-05 | global batch size: 256 | lm loss: 3.317372E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.865 | TFLOPs: 28.48 | +7: iteration 37390/ 37905 | consumed samples: 9571840 | consumed tokens: 19603128320 | elapsed time per iteration (s): 0.23 | learning rate: 2.008E-05 | global batch size: 256 | lm loss: 3.319060E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.602 | TFLOPs: 28.27 | +7: iteration 37400/ 37905 | consumed samples: 9574400 | consumed tokens: 19608371200 | elapsed time per iteration (s): 0.23 | learning rate: 2.008E-05 | global batch size: 256 | lm loss: 3.293789E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.950 | TFLOPs: 28.17 | +7: iteration 37410/ 37905 | consumed samples: 9576960 | consumed tokens: 19613614080 | elapsed time per iteration (s): 0.23 | learning rate: 2.008E-05 | global batch size: 256 | lm loss: 3.318817E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.379 | TFLOPs: 28.75 | +7: iteration 37420/ 37905 | consumed samples: 9579520 | consumed tokens: 19618856960 | elapsed time per iteration (s): 0.23 | learning rate: 2.007E-05 | global batch size: 256 | lm loss: 3.304767E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.729 | TFLOPs: 28.45 | +7: iteration 37430/ 37905 | consumed samples: 9582080 | consumed tokens: 19624099840 | elapsed time per iteration (s): 0.23 | learning rate: 2.007E-05 | global batch size: 256 | lm loss: 3.323571E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.131 | TFLOPs: 28.59 | +7: iteration 37440/ 37905 | consumed samples: 9584640 | consumed tokens: 19629342720 | elapsed time per iteration (s): 0.23 | learning rate: 2.007E-05 | global batch size: 256 | lm loss: 3.337039E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.401 | TFLOPs: 28.64 | +7: iteration 37450/ 37905 | consumed samples: 9587200 | consumed tokens: 19634585600 | elapsed time per iteration (s): 0.23 | learning rate: 2.007E-05 | global batch size: 256 | lm loss: 3.292064E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.197 | TFLOPs: 28.28 | +7: iteration 37460/ 37905 | consumed samples: 9589760 | consumed tokens: 19639828480 | elapsed time per iteration (s): 0.24 | learning rate: 2.006E-05 | global batch size: 256 | lm loss: 3.307025E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.310 | TFLOPs: 27.67 | +7: iteration 37470/ 37905 | consumed samples: 9592320 | consumed tokens: 19645071360 | elapsed time per iteration (s): 0.23 | learning rate: 2.006E-05 | global batch size: 256 | lm loss: 3.315988E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.603 | TFLOPs: 28.52 | +7: iteration 37480/ 37905 | consumed samples: 9594880 | consumed tokens: 19650314240 | elapsed time per iteration (s): 0.23 | learning rate: 2.006E-05 | global batch size: 256 | lm loss: 3.322175E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.111 | TFLOPs: 28.64 | +7: iteration 37490/ 37905 | consumed samples: 9597440 | consumed tokens: 19655557120 | elapsed time per iteration (s): 0.23 | learning rate: 2.005E-05 | global batch size: 256 | lm loss: 3.317957E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.295 | TFLOPs: 28.51 | +7: iteration 37500/ 37905 | consumed samples: 9600000 | consumed tokens: 19660800000 | elapsed time per iteration (s): 0.23 | learning rate: 2.005E-05 | global batch size: 256 | lm loss: 3.317284E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.160 | TFLOPs: 28.31 | +7: iteration 37510/ 37905 | consumed samples: 9602560 | consumed tokens: 19666042880 | elapsed time per iteration (s): 0.23 | learning rate: 2.005E-05 | global batch size: 256 | lm loss: 3.339214E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.170 | TFLOPs: 28.31 | +7: iteration 37520/ 37905 | consumed samples: 9605120 | consumed tokens: 19671285760 | elapsed time per iteration (s): 0.23 | learning rate: 2.005E-05 | global batch size: 256 | lm loss: 3.307112E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.112 | TFLOPs: 28.28 | +7: iteration 37530/ 37905 | consumed samples: 9607680 | consumed tokens: 19676528640 | elapsed time per iteration (s): 0.23 | learning rate: 2.004E-05 | global batch size: 256 | lm loss: 3.327686E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.789 | TFLOPs: 28.04 | +7: iteration 37540/ 37905 | consumed samples: 9610240 | consumed tokens: 19681771520 | elapsed time per iteration (s): 0.23 | learning rate: 2.004E-05 | global batch size: 256 | lm loss: 3.298999E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.105 | TFLOPs: 28.64 | +7: iteration 37550/ 37905 | consumed samples: 9612800 | consumed tokens: 19687014400 | elapsed time per iteration (s): 0.23 | learning rate: 2.004E-05 | global batch size: 256 | lm loss: 3.323520E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.326 | TFLOPs: 28.52 | +7: iteration 37560/ 37905 | consumed samples: 9615360 | consumed tokens: 19692257280 | elapsed time per iteration (s): 0.24 | learning rate: 2.004E-05 | global batch size: 256 | lm loss: 3.353551E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1079.792 | TFLOPs: 27.51 | +7: iteration 37570/ 37905 | consumed samples: 9617920 | consumed tokens: 19697500160 | elapsed time per iteration (s): 0.23 | learning rate: 2.004E-05 | global batch size: 256 | lm loss: 3.329061E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.707 | TFLOPs: 28.40 | +7: iteration 37580/ 37905 | consumed samples: 9620480 | consumed tokens: 19702743040 | elapsed time per iteration (s): 0.23 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 3.302517E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.499 | TFLOPs: 28.52 | +7: iteration 37590/ 37905 | consumed samples: 9623040 | consumed tokens: 19707985920 | elapsed time per iteration (s): 0.23 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 3.308638E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.224 | TFLOPs: 28.36 | +7: iteration 37600/ 37905 | consumed samples: 9625600 | consumed tokens: 19713228800 | elapsed time per iteration (s): 0.23 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 3.310181E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.535 | TFLOPs: 28.60 | +7: iteration 37610/ 37905 | consumed samples: 9628160 | consumed tokens: 19718471680 | elapsed time per iteration (s): 0.23 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 3.323489E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.750 | TFLOPs: 28.50 | +7: iteration 37620/ 37905 | consumed samples: 9630720 | consumed tokens: 19723714560 | elapsed time per iteration (s): 0.23 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 3.305260E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.737 | TFLOPs: 28.40 | +7: iteration 37630/ 37905 | consumed samples: 9633280 | consumed tokens: 19728957440 | elapsed time per iteration (s): 0.23 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 3.293521E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.644 | TFLOPs: 28.52 | +7: iteration 37640/ 37905 | consumed samples: 9635840 | consumed tokens: 19734200320 | elapsed time per iteration (s): 0.23 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 3.315474E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.857 | TFLOPs: 28.58 | +7: iteration 37650/ 37905 | consumed samples: 9638400 | consumed tokens: 19739443200 | elapsed time per iteration (s): 0.23 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 3.304124E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.916 | TFLOPs: 28.38 | +7: iteration 37660/ 37905 | consumed samples: 9640960 | consumed tokens: 19744686080 | elapsed time per iteration (s): 0.23 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 3.300890E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1131.087 | TFLOPs: 28.81 | +7: iteration 37670/ 37905 | consumed samples: 9643520 | consumed tokens: 19749928960 | elapsed time per iteration (s): 0.23 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 3.313767E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.870 | TFLOPs: 28.38 | +7: iteration 37680/ 37905 | consumed samples: 9646080 | consumed tokens: 19755171840 | elapsed time per iteration (s): 0.23 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 3.340939E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.305 | TFLOPs: 28.54 | +7: iteration 37690/ 37905 | consumed samples: 9648640 | consumed tokens: 19760414720 | elapsed time per iteration (s): 0.23 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 3.320802E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.877 | TFLOPs: 28.73 | +7: iteration 37700/ 37905 | consumed samples: 9651200 | consumed tokens: 19765657600 | elapsed time per iteration (s): 0.23 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 3.329371E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.292 | TFLOPs: 28.64 | +7: iteration 37710/ 37905 | consumed samples: 9653760 | consumed tokens: 19770900480 | elapsed time per iteration (s): 0.23 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 3.305999E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.946 | TFLOPs: 28.71 | +7: iteration 37720/ 37905 | consumed samples: 9656320 | consumed tokens: 19776143360 | elapsed time per iteration (s): 0.23 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 3.323290E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.743 | TFLOPs: 28.68 | +7: iteration 37730/ 37905 | consumed samples: 9658880 | consumed tokens: 19781386240 | elapsed time per iteration (s): 0.23 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 3.328555E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.896 | TFLOPs: 27.77 | +7: iteration 37740/ 37905 | consumed samples: 9661440 | consumed tokens: 19786629120 | elapsed time per iteration (s): 0.23 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 3.305111E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.892 | TFLOPs: 27.99 | +7: iteration 37750/ 37905 | consumed samples: 9664000 | consumed tokens: 19791872000 | elapsed time per iteration (s): 0.23 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 3.310729E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.470 | TFLOPs: 28.62 | +7: iteration 37760/ 37905 | consumed samples: 9666560 | consumed tokens: 19797114880 | elapsed time per iteration (s): 0.23 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 3.316869E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.858 | TFLOPs: 28.35 | +7: iteration 37770/ 37905 | consumed samples: 9669120 | consumed tokens: 19802357760 | elapsed time per iteration (s): 0.23 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 3.315420E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.474 | TFLOPs: 28.34 | +7: iteration 37780/ 37905 | consumed samples: 9671680 | consumed tokens: 19807600640 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 3.310020E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1045.232 | TFLOPs: 26.63 | +7: iteration 37790/ 37905 | consumed samples: 9674240 | consumed tokens: 19812843520 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 3.306012E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.768 | TFLOPs: 28.42 | +7: iteration 37800/ 37905 | consumed samples: 9676800 | consumed tokens: 19818086400 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 3.311381E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.459 | TFLOPs: 28.34 | +7: iteration 37810/ 37905 | consumed samples: 9679360 | consumed tokens: 19823329280 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 3.320591E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.261 | TFLOPs: 28.34 | +7: iteration 37820/ 37905 | consumed samples: 9681920 | consumed tokens: 19828572160 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 3.329342E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.750 | TFLOPs: 27.79 | +7: iteration 37830/ 37905 | consumed samples: 9684480 | consumed tokens: 19833815040 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 3.317222E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.749 | TFLOPs: 28.30 | +7: iteration 37840/ 37905 | consumed samples: 9687040 | consumed tokens: 19839057920 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 3.291977E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.538 | TFLOPs: 27.73 | +7: iteration 37850/ 37905 | consumed samples: 9689600 | consumed tokens: 19844300800 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 3.297684E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.517 | TFLOPs: 27.70 | +7: iteration 37860/ 37905 | consumed samples: 9692160 | consumed tokens: 19849543680 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 3.299090E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.741 | TFLOPs: 28.55 | +7: iteration 37870/ 37905 | consumed samples: 9694720 | consumed tokens: 19854786560 | elapsed time per iteration (s): 0.25 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 3.313260E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1039.499 | TFLOPs: 26.48 | +7: iteration 37880/ 37905 | consumed samples: 9697280 | consumed tokens: 19860029440 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 3.314126E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.068 | TFLOPs: 28.20 | +7: iteration 37890/ 37905 | consumed samples: 9699840 | consumed tokens: 19865272320 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 3.310131E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.445 | TFLOPs: 28.11 | +7: iteration 37900/ 37905 | consumed samples: 9702400 | consumed tokens: 19870515200 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 3.294880E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.624 | TFLOPs: 28.45 | +0: [after training is done] datetime: 2022-11-29 19:25:04 +0: saving checkpoint at iteration 37905 to checkpoints_83moscar +7: ------------------------------------------------------------------------------------------------------------ +7: valid loss at the end of training for val data | lm loss value: 3.184332E+00 | lm loss PPL: 2.415114E+01 | +7: ------------------------------------------------------------------------------------------------------------ +0: [2022-11-29 19:25:04,480] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step37905 is begin to save! +0: [2022-11-29 19:25:04,483] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/layer_01-model_00-model_states.pt... +0: [2022-11-29 19:25:04,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/layer_01-model_00-model_states.pt. +0: [2022-11-29 19:25:04,559] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/layer_03-model_00-model_states.pt... +0: [2022-11-29 19:25:04,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/layer_03-model_00-model_states.pt. +0: [2022-11-29 19:25:04,571] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/layer_04-model_00-model_states.pt... +0: [2022-11-29 19:25:04,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/layer_04-model_00-model_states.pt. +0: [2022-11-29 19:25:04,582] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/layer_05-model_00-model_states.pt... +0: [2022-11-29 19:25:04,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/layer_05-model_00-model_states.pt. +0: [2022-11-29 19:25:04,593] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/layer_06-model_00-model_states.pt... +0: [2022-11-29 19:25:04,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/layer_06-model_00-model_states.pt. +0: [2022-11-29 19:25:04,605] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/layer_07-model_00-model_states.pt... +0: [2022-11-29 19:25:04,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/layer_07-model_00-model_states.pt. +0: [2022-11-29 19:25:04,616] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/layer_08-model_00-model_states.pt... +0: [2022-11-29 19:25:04,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/layer_08-model_00-model_states.pt. +0: [2022-11-29 19:25:04,627] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/layer_09-model_00-model_states.pt... +0: [2022-11-29 19:25:04,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/layer_09-model_00-model_states.pt. +0: [2022-11-29 19:25:04,638] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/layer_10-model_00-model_states.pt... +0: [2022-11-29 19:25:04,650] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/layer_10-model_00-model_states.pt. +0: [2022-11-29 19:25:04,650] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/layer_11-model_00-model_states.pt... +0: [2022-11-29 19:25:04,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/layer_11-model_00-model_states.pt. +0: [2022-11-29 19:25:04,661] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/layer_12-model_00-model_states.pt... +0: [2022-11-29 19:25:04,672] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/layer_12-model_00-model_states.pt. +0: [2022-11-29 19:25:04,672] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/layer_14-model_00-model_states.pt... +0: [2022-11-29 19:25:04,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/layer_14-model_00-model_states.pt. +0: [2022-11-29 19:25:04,674] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83moscar/global_step37905/mp_rank_00_model_states.pt +0: [2022-11-29 19:25:04,674] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/mp_rank_00_model_states.pt... +0: [2022-11-29 19:25:04,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/mp_rank_00_model_states.pt. +0: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +3: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +1: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +6: [2022-11-29 19:25:04,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +0: [2022-11-29 19:25:04,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:25:04,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:25:04,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +1: [2022-11-29 19:25:04,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:25:04,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +1: [2022-11-29 19:25:04,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-29 19:25:04,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +6: [2022-11-29 19:25:04,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:25:04,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-29 19:25:04,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +2: [2022-11-29 19:25:04,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:25:04,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-29 19:25:04,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +0: [2022-11-29 19:25:04,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-29 19:25:04,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +7: [2022-11-29 19:25:04,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:25:04,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-29 19:25:04,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +1: [2022-11-29 19:25:04,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:25:04,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-29 19:25:04,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +6: [2022-11-29 19:25:04,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:25:04,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +2: [2022-11-29 19:25:04,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:25:04,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +2: [2022-11-29 19:25:04,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-29 19:25:04,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +5: [2022-11-29 19:25:04,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:25:04,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-29 19:25:04,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +4: [2022-11-29 19:25:04,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:25:04,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-29 19:25:04,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +0: [2022-11-29 19:25:04,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:25:04,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-29 19:25:04,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +0: [2022-11-29 19:25:04,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:25:04,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-29 19:25:04,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +1: [2022-11-29 19:25:04,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:25:04,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-29 19:25:04,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +7: [2022-11-29 19:25:04,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:25:04,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:25:04,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-29 19:25:04,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-29 19:25:04,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +7: [2022-11-29 19:25:04,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +6: [2022-11-29 19:25:04,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:25:04,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-29 19:25:04,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +1: [2022-11-29 19:25:04,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:25:04,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-29 19:25:04,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +0: [2022-11-29 19:25:04,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:25:04,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:25:04,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +0: [2022-11-29 19:25:04,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +4: [2022-11-29 19:25:04,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +0: [2022-11-29 19:25:04,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +7: [2022-11-29 19:25:04,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:25:04,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-29 19:25:04,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +2: [2022-11-29 19:25:04,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:25:04,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-29 19:25:04,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +2: [2022-11-29 19:25:04,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:25:04,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:25:04,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:25:04,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +3: [2022-11-29 19:25:04,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-29 19:25:04,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:25:04,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +3: [2022-11-29 19:25:04,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-29 19:25:04,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +3: [2022-11-29 19:25:04,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-29 19:25:04,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +3: [2022-11-29 19:25:04,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +5: [2022-11-29 19:25:04,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:25:04,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:25:04,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-29 19:25:04,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-29 19:25:04,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +5: [2022-11-29 19:25:04,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +6: [2022-11-29 19:25:04,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:25:04,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-29 19:25:04,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +3: [2022-11-29 19:25:04,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:25:04,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-29 19:25:04,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +4: [2022-11-29 19:25:04,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:25:04,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-29 19:25:04,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +2: [2022-11-29 19:25:04,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:25:04,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-29 19:25:04,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +0: [2022-11-29 19:25:04,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:25:04,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:25:04,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +6: [2022-11-29 19:25:04,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +5: [2022-11-29 19:25:04,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:25:04,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +0: [2022-11-29 19:25:04,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +5: [2022-11-29 19:25:04,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-29 19:25:04,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +1: [2022-11-29 19:25:04,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:25:04,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-29 19:25:04,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +7: [2022-11-29 19:25:04,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:25:04,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-29 19:25:04,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +1: [2022-11-29 19:25:04,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:25:04,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-29 19:25:04,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +3: [2022-11-29 19:25:04,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:25:04,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-29 19:25:04,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +6: [2022-11-29 19:25:04,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:25:04,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-29 19:25:04,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +4: [2022-11-29 19:25:04,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:25:04,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-29 19:25:04,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +0: [2022-11-29 19:25:04,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:25:04,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-29 19:25:04,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +2: [2022-11-29 19:25:04,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:25:04,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-29 19:25:04,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +3: [2022-11-29 19:25:04,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:25:04,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +5: [2022-11-29 19:25:04,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:25:04,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +5: [2022-11-29 19:25:04,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-29 19:25:04,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +7: [2022-11-29 19:25:04,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:25:04,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-29 19:25:04,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +7: [2022-11-29 19:25:04,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:25:04,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +4: [2022-11-29 19:25:04,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:25:04,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +4: [2022-11-29 19:25:04,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-29 19:25:04,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +3: [2022-11-29 19:25:04,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:25:04,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-29 19:25:04,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +6: [2022-11-29 19:25:04,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:25:04,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:25:04,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +5: [2022-11-29 19:25:04,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-29 19:25:04,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +6: [2022-11-29 19:25:04,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +4: [2022-11-29 19:25:04,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:25:04,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +1: [2022-11-29 19:25:04,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:25:04,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +1: [2022-11-29 19:25:04,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +4: [2022-11-29 19:25:04,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:25:04,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +4: [2022-11-29 19:25:04,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +0: [2022-11-29 19:25:04,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +4: [2022-11-29 19:25:04,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +0: [2022-11-29 19:25:04,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-29 19:25:04,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +2: [2022-11-29 19:25:04,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:25:04,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-29 19:25:04,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +2: [2022-11-29 19:25:04,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-29 19:25:04,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-29 19:25:04,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +0: [2022-11-29 19:25:04,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +3: [2022-11-29 19:25:04,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +0: [2022-11-29 19:25:04,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3: [2022-11-29 19:25:04,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +0: [2022-11-29 19:25:04,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +3: [2022-11-29 19:25:04,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +5: [2022-11-29 19:25:04,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:25:04,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-29 19:25:04,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +1: [2022-11-29 19:25:04,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-29 19:25:04,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-29 19:25:04,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +5: [2022-11-29 19:25:04,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-29 19:25:04,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-29 19:25:04,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +7: [2022-11-29 19:25:04,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-29 19:25:04,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-29 19:25:04,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +6: [2022-11-29 19:25:04,725] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-29 19:25:04,725] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83moscar/global_step37905/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-29 19:25:04,725] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +0: successfully saved checkpoint at iteration 37905 to checkpoints_83moscar +7: ------------------------------------------------------------------------------------------------------------ +7: test loss at the end of training for test data | lm loss value: 3.189175E+00 | lm loss PPL: 2.426840E+01 | +7: ------------------------------------------------------------------------------------------------------------ +END 2085611: Tue Nov 29 19:25:17 EET 2022 diff --git a/83m20b20b/tensorboard_83moscar/events.out.tfevents.1669733029.nid005049.82864.0 b/83m20b20b/tensorboard_83moscar/events.out.tfevents.1669733029.nid005049.82864.0 new file mode 100644 index 0000000000000000000000000000000000000000..d2007ece2936f527584f5564b3ca842323890c66 --- /dev/null +++ b/83m20b20b/tensorboard_83moscar/events.out.tfevents.1669733029.nid005049.82864.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0dc5b04688ec604eabd7b66aab5778b78180489f61d4e4f3d3c80c672735f6c +size 40 diff --git a/83m20b20b/tensorboard_83moscar/events.out.tfevents.1669733535.nid006772.25768.0 b/83m20b20b/tensorboard_83moscar/events.out.tfevents.1669733535.nid006772.25768.0 new file mode 100644 index 0000000000000000000000000000000000000000..a9bd343c709e245d22b72e0c5e966baa34371304 --- /dev/null +++ b/83m20b20b/tensorboard_83moscar/events.out.tfevents.1669733535.nid006772.25768.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d65b0000cfc7de582b85a5a22df730b2b33a10eb8d49c94a372414305e77f0cf +size 40 diff --git a/83m20b20b/tensorboard_83moscar/events.out.tfevents.1669733643.nid006656.115246.0 b/83m20b20b/tensorboard_83moscar/events.out.tfevents.1669733643.nid006656.115246.0 new file mode 100644 index 0000000000000000000000000000000000000000..291ab9890e05733298f4e797771b190fc8170bee --- /dev/null +++ b/83m20b20b/tensorboard_83moscar/events.out.tfevents.1669733643.nid006656.115246.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b53e0344ded6a36d96b5256fbd4d31c9097f9675946837822e18f58738cf3a8f +size 67725395